Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
aaef169d | 2 | Copyright (C) 2001, 2002, 2003, 2004, 2005, |
114f9c96 | 3 | 2006, 2007, 2008, 2009, 2010 Free Software Foundation, Inc. |
7976eda0 | 4 | Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, |
114f9c96 | 5 | 2005, 2006, 2007, 2008, 2009, 2010 |
ce03bf76 KH |
6 | National Institute of Advanced Industrial Science and Technology (AIST) |
7 | Registration Number H14PRO021 | |
8f924df7 | 8 | Copyright (C) 2003 |
df7492f9 KH |
9 | National Institute of Advanced Industrial Science and Technology (AIST) |
10 | Registration Number H13PRO009 | |
4ed46869 | 11 | |
369314dc KH |
12 | This file is part of GNU Emacs. |
13 | ||
9ec0b715 | 14 | GNU Emacs is free software: you can redistribute it and/or modify |
369314dc | 15 | it under the terms of the GNU General Public License as published by |
9ec0b715 GM |
16 | the Free Software Foundation, either version 3 of the License, or |
17 | (at your option) any later version. | |
4ed46869 | 18 | |
369314dc KH |
19 | GNU Emacs is distributed in the hope that it will be useful, |
20 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
21 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
22 | GNU General Public License for more details. | |
4ed46869 | 23 | |
369314dc | 24 | You should have received a copy of the GNU General Public License |
9ec0b715 | 25 | along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */ |
4ed46869 KH |
26 | |
27 | /*** TABLE OF CONTENTS *** | |
28 | ||
b73bfc1c | 29 | 0. General comments |
4ed46869 | 30 | 1. Preamble |
df7492f9 KH |
31 | 2. Emacs' internal format (emacs-utf-8) handlers |
32 | 3. UTF-8 handlers | |
33 | 4. UTF-16 handlers | |
34 | 5. Charset-base coding systems handlers | |
35 | 6. emacs-mule (old Emacs' internal format) handlers | |
36 | 7. ISO2022 handlers | |
37 | 8. Shift-JIS and BIG5 handlers | |
38 | 9. CCL handlers | |
39 | 10. C library functions | |
40 | 11. Emacs Lisp library functions | |
41 | 12. Postamble | |
4ed46869 KH |
42 | |
43 | */ | |
44 | ||
df7492f9 | 45 | /*** 0. General comments *** |
b73bfc1c KH |
46 | |
47 | ||
df7492f9 | 48 | CODING SYSTEM |
4ed46869 | 49 | |
5bad0796 DL |
50 | A coding system is an object for an encoding mechanism that contains |
51 | information about how to convert byte sequences to character | |
e19c3639 KH |
52 | sequences and vice versa. When we say "decode", it means converting |
53 | a byte sequence of a specific coding system into a character | |
54 | sequence that is represented by Emacs' internal coding system | |
55 | `emacs-utf-8', and when we say "encode", it means converting a | |
56 | character sequence of emacs-utf-8 to a byte sequence of a specific | |
0ef69138 | 57 | coding system. |
4ed46869 | 58 | |
e19c3639 KH |
59 | In Emacs Lisp, a coding system is represented by a Lisp symbol. In |
60 | C level, a coding system is represented by a vector of attributes | |
5bad0796 | 61 | stored in the hash table Vcharset_hash_table. The conversion from |
e19c3639 KH |
62 | coding system symbol to attributes vector is done by looking up |
63 | Vcharset_hash_table by the symbol. | |
4ed46869 | 64 | |
e19c3639 | 65 | Coding systems are classified into the following types depending on |
5bad0796 | 66 | the encoding mechanism. Here's a brief description of the types. |
4ed46869 | 67 | |
df7492f9 KH |
68 | o UTF-8 |
69 | ||
70 | o UTF-16 | |
71 | ||
72 | o Charset-base coding system | |
73 | ||
74 | A coding system defined by one or more (coded) character sets. | |
5bad0796 | 75 | Decoding and encoding are done by a code converter defined for each |
df7492f9 KH |
76 | character set. |
77 | ||
5bad0796 | 78 | o Old Emacs internal format (emacs-mule) |
df7492f9 | 79 | |
5bad0796 | 80 | The coding system adopted by old versions of Emacs (20 and 21). |
4ed46869 | 81 | |
df7492f9 | 82 | o ISO2022-base coding system |
4ed46869 KH |
83 | |
84 | The most famous coding system for multiple character sets. X's | |
df7492f9 KH |
85 | Compound Text, various EUCs (Extended Unix Code), and coding systems |
86 | used in the Internet communication such as ISO-2022-JP are all | |
87 | variants of ISO2022. | |
4ed46869 | 88 | |
df7492f9 | 89 | o SJIS (or Shift-JIS or MS-Kanji-Code) |
93dec019 | 90 | |
4ed46869 KH |
91 | A coding system to encode character sets: ASCII, JISX0201, and |
92 | JISX0208. Widely used for PC's in Japan. Details are described in | |
df7492f9 | 93 | section 8. |
4ed46869 | 94 | |
df7492f9 | 95 | o BIG5 |
4ed46869 | 96 | |
df7492f9 | 97 | A coding system to encode character sets: ASCII and Big5. Widely |
cfb43547 | 98 | used for Chinese (mainly in Taiwan and Hong Kong). Details are |
df7492f9 KH |
99 | described in section 8. In this file, when we write "big5" (all |
100 | lowercase), we mean the coding system, and when we write "Big5" | |
101 | (capitalized), we mean the character set. | |
4ed46869 | 102 | |
df7492f9 | 103 | o CCL |
27901516 | 104 | |
5bad0796 | 105 | If a user wants to decode/encode text encoded in a coding system |
df7492f9 KH |
106 | not listed above, he can supply a decoder and an encoder for it in |
107 | CCL (Code Conversion Language) programs. Emacs executes the CCL | |
108 | program while decoding/encoding. | |
27901516 | 109 | |
df7492f9 | 110 | o Raw-text |
4ed46869 | 111 | |
5a936b46 | 112 | A coding system for text containing raw eight-bit data. Emacs |
5bad0796 | 113 | treats each byte of source text as a character (except for |
df7492f9 | 114 | end-of-line conversion). |
4ed46869 | 115 | |
df7492f9 KH |
116 | o No-conversion |
117 | ||
118 | Like raw text, but don't do end-of-line conversion. | |
4ed46869 | 119 | |
4ed46869 | 120 | |
df7492f9 | 121 | END-OF-LINE FORMAT |
4ed46869 | 122 | |
5bad0796 | 123 | How text end-of-line is encoded depends on operating system. For |
df7492f9 | 124 | instance, Unix's format is just one byte of LF (line-feed) code, |
f4dee582 | 125 | whereas DOS's format is two-byte sequence of `carriage-return' and |
d46c5b12 KH |
126 | `line-feed' codes. MacOS's format is usually one byte of |
127 | `carriage-return'. | |
4ed46869 | 128 | |
cfb43547 | 129 | Since text character encoding and end-of-line encoding are |
df7492f9 KH |
130 | independent, any coding system described above can take any format |
131 | of end-of-line (except for no-conversion). | |
4ed46869 | 132 | |
e19c3639 KH |
133 | STRUCT CODING_SYSTEM |
134 | ||
135 | Before using a coding system for code conversion (i.e. decoding and | |
136 | encoding), we setup a structure of type `struct coding_system'. | |
137 | This structure keeps various information about a specific code | |
5bad0796 | 138 | conversion (e.g. the location of source and destination data). |
4ed46869 KH |
139 | |
140 | */ | |
141 | ||
df7492f9 KH |
142 | /* COMMON MACROS */ |
143 | ||
144 | ||
4ed46869 KH |
145 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
146 | ||
df7492f9 | 147 | These functions check if a byte sequence specified as a source in |
ff0dacd7 KH |
148 | CODING conforms to the format of XXX, and update the members of |
149 | DETECT_INFO. | |
df7492f9 | 150 | |
ff0dacd7 | 151 | Return 1 if the byte sequence conforms to XXX, otherwise return 0. |
df7492f9 KH |
152 | |
153 | Below is the template of these functions. */ | |
154 | ||
4ed46869 | 155 | #if 0 |
df7492f9 | 156 | static int |
cf84bb53 JB |
157 | detect_coding_XXX (struct coding_system *coding, |
158 | struct coding_detection_info *detect_info) | |
4ed46869 | 159 | { |
f1d34bca MB |
160 | const unsigned char *src = coding->source; |
161 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 162 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 163 | int consumed_chars = 0; |
df7492f9 KH |
164 | int found = 0; |
165 | ...; | |
166 | ||
167 | while (1) | |
168 | { | |
169 | /* Get one byte from the source. If the souce is exausted, jump | |
170 | to no_more_source:. */ | |
171 | ONE_MORE_BYTE (c); | |
ff0dacd7 KH |
172 | |
173 | if (! __C_conforms_to_XXX___ (c)) | |
174 | break; | |
175 | if (! __C_strongly_suggests_XXX__ (c)) | |
176 | found = CATEGORY_MASK_XXX; | |
df7492f9 | 177 | } |
ff0dacd7 KH |
178 | /* The byte sequence is invalid for XXX. */ |
179 | detect_info->rejected |= CATEGORY_MASK_XXX; | |
df7492f9 | 180 | return 0; |
ff0dacd7 | 181 | |
df7492f9 | 182 | no_more_source: |
ff0dacd7 KH |
183 | /* The source exausted successfully. */ |
184 | detect_info->found |= found; | |
df7492f9 | 185 | return 1; |
4ed46869 KH |
186 | } |
187 | #endif | |
188 | ||
189 | /*** GENERAL NOTES on `decode_coding_XXX ()' functions *** | |
190 | ||
df7492f9 KH |
191 | These functions decode a byte sequence specified as a source by |
192 | CODING. The resulting multibyte text goes to a place pointed to by | |
193 | CODING->charbuf, the length of which should not exceed | |
194 | CODING->charbuf_size; | |
d46c5b12 | 195 | |
df7492f9 KH |
196 | These functions set the information of original and decoded texts in |
197 | CODING->consumed, CODING->consumed_char, and CODING->charbuf_used. | |
198 | They also set CODING->result to one of CODING_RESULT_XXX indicating | |
199 | how the decoding is finished. | |
d46c5b12 | 200 | |
df7492f9 | 201 | Below is the template of these functions. */ |
d46c5b12 | 202 | |
4ed46869 | 203 | #if 0 |
b73bfc1c | 204 | static void |
cf84bb53 | 205 | decode_coding_XXXX (struct coding_system *coding) |
4ed46869 | 206 | { |
f1d34bca MB |
207 | const unsigned char *src = coding->source + coding->consumed; |
208 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
209 | /* SRC_BASE remembers the start position in source in each loop. |
210 | The loop will be exited when there's not enough source code, or | |
211 | when there's no room in CHARBUF for a decoded character. */ | |
f1d34bca | 212 | const unsigned char *src_base; |
df7492f9 | 213 | /* A buffer to produce decoded characters. */ |
69a80ea3 KH |
214 | int *charbuf = coding->charbuf + coding->charbuf_used; |
215 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
216 | int multibytep = coding->src_multibyte; |
217 | ||
218 | while (1) | |
219 | { | |
220 | src_base = src; | |
221 | if (charbuf < charbuf_end) | |
222 | /* No more room to produce a decoded character. */ | |
223 | break; | |
224 | ONE_MORE_BYTE (c); | |
225 | /* Decode it. */ | |
226 | } | |
227 | ||
228 | no_more_source: | |
229 | if (src_base < src_end | |
230 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
231 | /* If the source ends by partial bytes to construct a character, | |
232 | treat them as eight-bit raw data. */ | |
233 | while (src_base < src_end && charbuf < charbuf_end) | |
234 | *charbuf++ = *src_base++; | |
235 | /* Remember how many bytes and characters we consumed. If the | |
236 | source is multibyte, the bytes and chars are not identical. */ | |
237 | coding->consumed = coding->consumed_char = src_base - coding->source; | |
238 | /* Remember how many characters we produced. */ | |
239 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
240 | } |
241 | #endif | |
242 | ||
243 | /*** GENERAL NOTES on `encode_coding_XXX ()' functions *** | |
244 | ||
df7492f9 KH |
245 | These functions encode SRC_BYTES length text at SOURCE of Emacs' |
246 | internal multibyte format by CODING. The resulting byte sequence | |
b73bfc1c KH |
247 | goes to a place pointed to by DESTINATION, the length of which |
248 | should not exceed DST_BYTES. | |
d46c5b12 | 249 | |
df7492f9 KH |
250 | These functions set the information of original and encoded texts in |
251 | the members produced, produced_char, consumed, and consumed_char of | |
252 | the structure *CODING. They also set the member result to one of | |
253 | CODING_RESULT_XXX indicating how the encoding finished. | |
d46c5b12 | 254 | |
df7492f9 KH |
255 | DST_BYTES zero means that source area and destination area are |
256 | overlapped, which means that we can produce a encoded text until it | |
257 | reaches at the head of not-yet-encoded source text. | |
d46c5b12 | 258 | |
df7492f9 | 259 | Below is a template of these functions. */ |
4ed46869 | 260 | #if 0 |
b73bfc1c | 261 | static void |
cf84bb53 | 262 | encode_coding_XXX (struct coding_system *coding) |
4ed46869 | 263 | { |
df7492f9 KH |
264 | int multibytep = coding->dst_multibyte; |
265 | int *charbuf = coding->charbuf; | |
266 | int *charbuf_end = charbuf->charbuf + coding->charbuf_used; | |
267 | unsigned char *dst = coding->destination + coding->produced; | |
268 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
269 | unsigned char *adjusted_dst_end = dst_end - _MAX_BYTES_PRODUCED_IN_LOOP_; | |
270 | int produced_chars = 0; | |
271 | ||
272 | for (; charbuf < charbuf_end && dst < adjusted_dst_end; charbuf++) | |
273 | { | |
274 | int c = *charbuf; | |
275 | /* Encode C into DST, and increment DST. */ | |
276 | } | |
277 | label_no_more_destination: | |
278 | /* How many chars and bytes we produced. */ | |
279 | coding->produced_char += produced_chars; | |
280 | coding->produced = dst - coding->destination; | |
4ed46869 KH |
281 | } |
282 | #endif | |
283 | ||
4ed46869 KH |
284 | \f |
285 | /*** 1. Preamble ***/ | |
286 | ||
68c45bf0 | 287 | #include <config.h> |
4ed46869 | 288 | #include <stdio.h> |
d7306fe6 | 289 | #include <setjmp.h> |
4ed46869 | 290 | |
4ed46869 KH |
291 | #include "lisp.h" |
292 | #include "buffer.h" | |
df7492f9 | 293 | #include "character.h" |
4ed46869 KH |
294 | #include "charset.h" |
295 | #include "ccl.h" | |
df7492f9 | 296 | #include "composite.h" |
4ed46869 KH |
297 | #include "coding.h" |
298 | #include "window.h" | |
b8299c66 KL |
299 | #include "frame.h" |
300 | #include "termhooks.h" | |
4ed46869 | 301 | |
df7492f9 | 302 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 303 | |
df7492f9 | 304 | Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type; |
1965cb73 | 305 | Lisp_Object Qunix, Qdos; |
4ed46869 KH |
306 | Lisp_Object Qbuffer_file_coding_system; |
307 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
df7492f9 | 308 | Lisp_Object Qdefault_char; |
27901516 | 309 | Lisp_Object Qno_conversion, Qundecided; |
df7492f9 | 310 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
b49a1807 | 311 | Lisp_Object Qbig, Qlittle; |
bb0115a2 | 312 | Lisp_Object Qcoding_system_history; |
1397dc18 | 313 | Lisp_Object Qvalid_codes; |
2133e2d1 | 314 | Lisp_Object QCcategory, QCmnemonic, QCdefault_char; |
a6f87d34 KH |
315 | Lisp_Object QCdecode_translation_table, QCencode_translation_table; |
316 | Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
35befdaa | 317 | Lisp_Object QCascii_compatible_p; |
4ed46869 | 318 | |
387f6ba5 | 319 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 KH |
320 | Lisp_Object Qstart_process, Qopen_network_stream; |
321 | Lisp_Object Qtarget_idx; | |
322 | ||
065e3595 KH |
323 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
324 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
325 | ||
44e8490d KH |
326 | /* If a symbol has this property, evaluate the value to define the |
327 | symbol as a coding system. */ | |
328 | static Lisp_Object Qcoding_system_define_form; | |
329 | ||
5d5bf4d8 KH |
330 | int coding_system_require_warning; |
331 | ||
d46c5b12 KH |
332 | Lisp_Object Vselect_safe_coding_system_function; |
333 | ||
7722baf9 EZ |
334 | /* Mnemonic string for each format of end-of-line. */ |
335 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
336 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 337 | decided. */ |
7722baf9 | 338 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 | 339 | |
fcbcfb64 KH |
340 | /* Format of end-of-line decided by system. This is Qunix on |
341 | Unix and Mac, Qdos on DOS/Windows. | |
342 | This has an effect only for external encoding (i.e. for output to | |
343 | file and process), not for in-buffer or Lisp string encoding. */ | |
344 | static Lisp_Object system_eol_type; | |
345 | ||
4ed46869 KH |
346 | #ifdef emacs |
347 | ||
4608c386 KH |
348 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
349 | ||
350 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 351 | |
d46c5b12 KH |
352 | /* Coding system emacs-mule and raw-text are for converting only |
353 | end-of-line format. */ | |
354 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 355 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 356 | |
4ed46869 KH |
357 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
358 | routines by the following three variables. */ | |
359 | /* Coding-system for reading files and receiving data from process. */ | |
360 | Lisp_Object Vcoding_system_for_read; | |
361 | /* Coding-system for writing files and sending data to process. */ | |
362 | Lisp_Object Vcoding_system_for_write; | |
363 | /* Coding-system actually used in the latest I/O. */ | |
364 | Lisp_Object Vlast_coding_system_used; | |
065e3595 KH |
365 | /* Set to non-nil when an error is detected while code conversion. */ |
366 | Lisp_Object Vlast_code_conversion_error; | |
c4825358 | 367 | /* A vector of length 256 which contains information about special |
94487c4e | 368 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 369 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 370 | |
9ce27fde KH |
371 | /* Flag to inhibit code conversion of end-of-line format. */ |
372 | int inhibit_eol_conversion; | |
373 | ||
74383408 KH |
374 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
375 | int inhibit_iso_escape_detection; | |
376 | ||
97b1b294 EZ |
377 | /* Flag to inhibit detection of binary files through null bytes. */ |
378 | int inhibit_null_byte_detection; | |
379 | ||
ed29121d EZ |
380 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
381 | int inherit_process_coding_system; | |
382 | ||
c4825358 KH |
383 | /* Coding system to be used to encode text for terminal display when |
384 | terminal coding system is nil. */ | |
385 | struct coding_system safe_terminal_coding; | |
386 | ||
02ba4723 KH |
387 | Lisp_Object Vfile_coding_system_alist; |
388 | Lisp_Object Vprocess_coding_system_alist; | |
389 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 390 | |
68c45bf0 PE |
391 | Lisp_Object Vlocale_coding_system; |
392 | ||
4ed46869 KH |
393 | #endif /* emacs */ |
394 | ||
f967223b KH |
395 | /* Flag to tell if we look up translation table on character code |
396 | conversion. */ | |
84fbb8a0 | 397 | Lisp_Object Venable_character_translation; |
f967223b KH |
398 | /* Standard translation table to look up on decoding (reading). */ |
399 | Lisp_Object Vstandard_translation_table_for_decode; | |
400 | /* Standard translation table to look up on encoding (writing). */ | |
401 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 402 | |
f967223b KH |
403 | Lisp_Object Qtranslation_table; |
404 | Lisp_Object Qtranslation_table_id; | |
405 | Lisp_Object Qtranslation_table_for_decode; | |
406 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
407 | |
408 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 409 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 410 | |
02ba4723 KH |
411 | /* Default coding systems used for process I/O. */ |
412 | Lisp_Object Vdefault_process_coding_system; | |
413 | ||
002fdb44 DL |
414 | /* Char table for translating Quail and self-inserting input. */ |
415 | Lisp_Object Vtranslation_table_for_input; | |
416 | ||
df7492f9 KH |
417 | /* Two special coding systems. */ |
418 | Lisp_Object Vsjis_coding_system; | |
419 | Lisp_Object Vbig5_coding_system; | |
420 | ||
df7492f9 KH |
421 | /* ISO2022 section */ |
422 | ||
423 | #define CODING_ISO_INITIAL(coding, reg) \ | |
424 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
425 | coding_attr_iso_initial), \ | |
426 | reg))) | |
427 | ||
428 | ||
1b3b981b AS |
429 | #define CODING_ISO_REQUEST(coding, charset_id) \ |
430 | (((charset_id) <= (coding)->max_charset_id \ | |
431 | ? ((coding)->safe_charsets[charset_id] != 255 \ | |
432 | ? (coding)->safe_charsets[charset_id] \ | |
433 | : -1) \ | |
df7492f9 KH |
434 | : -1)) |
435 | ||
436 | ||
437 | #define CODING_ISO_FLAGS(coding) \ | |
438 | ((coding)->spec.iso_2022.flags) | |
439 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
440 | ((coding)->spec.iso_2022.current_designation[reg]) | |
441 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
442 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
443 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
444 | ((coding)->spec.iso_2022.single_shifting) | |
445 | #define CODING_ISO_BOL(coding) \ | |
446 | ((coding)->spec.iso_2022.bol) | |
447 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
448 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
e951386e KH |
449 | #define CODING_ISO_CMP_STATUS(coding) \ |
450 | (&(coding)->spec.iso_2022.cmp_status) | |
451 | #define CODING_ISO_EXTSEGMENT_LEN(coding) \ | |
452 | ((coding)->spec.iso_2022.ctext_extended_segment_len) | |
453 | #define CODING_ISO_EMBEDDED_UTF_8(coding) \ | |
454 | ((coding)->spec.iso_2022.embedded_utf_8) | |
df7492f9 KH |
455 | |
456 | /* Control characters of ISO2022. */ | |
457 | /* code */ /* function */ | |
458 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
459 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
460 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
461 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
462 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
463 | #define ISO_CODE_ESC 0x1B /* escape */ | |
464 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
465 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
466 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
467 | ||
468 | /* All code (1-byte) of ISO2022 is classified into one of the | |
469 | followings. */ | |
470 | enum iso_code_class_type | |
471 | { | |
472 | ISO_control_0, /* Control codes in the range | |
473 | 0x00..0x1F and 0x7F, except for the | |
474 | following 5 codes. */ | |
df7492f9 KH |
475 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
476 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
477 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
478 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
479 | ISO_control_1, /* Control codes in the range | |
480 | 0x80..0x9F, except for the | |
481 | following 3 codes. */ | |
482 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
483 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
484 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
485 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
486 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
487 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
488 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
489 | }; | |
05e6f5dc | 490 | |
df7492f9 KH |
491 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
492 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 493 | |
df7492f9 KH |
494 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
495 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
496 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 497 | |
df7492f9 KH |
498 | /* If set, reset graphic planes and registers at end-of-line to the |
499 | initial state. */ | |
500 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 501 | |
df7492f9 KH |
502 | /* If set, reset graphic planes and registers before any control |
503 | characters to the initial state. */ | |
504 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 505 | |
df7492f9 KH |
506 | /* If set, encode by 7-bit environment. */ |
507 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 508 | |
df7492f9 KH |
509 | /* If set, use locking-shift function. */ |
510 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 511 | |
df7492f9 KH |
512 | /* If set, use single-shift function. Overwrite |
513 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
514 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 515 | |
df7492f9 KH |
516 | /* If set, use designation escape sequence. */ |
517 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 518 | |
df7492f9 KH |
519 | /* If set, produce revision number sequence. */ |
520 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 521 | |
df7492f9 KH |
522 | /* If set, produce ISO6429's direction specifying sequence. */ |
523 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 524 | |
df7492f9 KH |
525 | /* If set, assume designation states are reset at beginning of line on |
526 | output. */ | |
527 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 528 | |
df7492f9 KH |
529 | /* If set, designation sequence should be placed at beginning of line |
530 | on output. */ | |
531 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 532 | |
df7492f9 KH |
533 | /* If set, do not encode unsafe charactes on output. */ |
534 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 535 | |
df7492f9 KH |
536 | /* If set, extra latin codes (128..159) are accepted as a valid code |
537 | on input. */ | |
538 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 539 | |
df7492f9 | 540 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 541 | |
df7492f9 | 542 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 543 | |
bf16eb23 | 544 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 545 | |
bf16eb23 | 546 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 547 | |
bf16eb23 | 548 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 549 | |
df7492f9 KH |
550 | /* A character to be produced on output if encoding of the original |
551 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
552 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 553 | |
a470d443 KH |
554 | /* UTF-8 section */ |
555 | #define CODING_UTF_8_BOM(coding) \ | |
556 | ((coding)->spec.utf_8_bom) | |
4ed46869 | 557 | |
df7492f9 KH |
558 | /* UTF-16 section */ |
559 | #define CODING_UTF_16_BOM(coding) \ | |
560 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 561 | |
df7492f9 KH |
562 | #define CODING_UTF_16_ENDIAN(coding) \ |
563 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 564 | |
df7492f9 KH |
565 | #define CODING_UTF_16_SURROGATE(coding) \ |
566 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 567 | |
4ed46869 | 568 | |
df7492f9 KH |
569 | /* CCL section */ |
570 | #define CODING_CCL_DECODER(coding) \ | |
571 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
572 | #define CODING_CCL_ENCODER(coding) \ | |
573 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
574 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 575 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 576 | |
5a936b46 | 577 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 578 | |
df7492f9 KH |
579 | enum coding_category |
580 | { | |
581 | coding_category_iso_7, | |
582 | coding_category_iso_7_tight, | |
583 | coding_category_iso_8_1, | |
584 | coding_category_iso_8_2, | |
585 | coding_category_iso_7_else, | |
586 | coding_category_iso_8_else, | |
a470d443 KH |
587 | coding_category_utf_8_auto, |
588 | coding_category_utf_8_nosig, | |
589 | coding_category_utf_8_sig, | |
df7492f9 KH |
590 | coding_category_utf_16_auto, |
591 | coding_category_utf_16_be, | |
592 | coding_category_utf_16_le, | |
593 | coding_category_utf_16_be_nosig, | |
594 | coding_category_utf_16_le_nosig, | |
595 | coding_category_charset, | |
596 | coding_category_sjis, | |
597 | coding_category_big5, | |
598 | coding_category_ccl, | |
599 | coding_category_emacs_mule, | |
600 | /* All above are targets of code detection. */ | |
601 | coding_category_raw_text, | |
602 | coding_category_undecided, | |
603 | coding_category_max | |
604 | }; | |
605 | ||
606 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
607 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
608 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
609 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
610 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
611 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
612 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
a470d443 KH |
613 | #define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto) |
614 | #define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig) | |
615 | #define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig) | |
b49a1807 | 616 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
617 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
618 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
619 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
620 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
621 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
622 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
623 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
624 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
625 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 626 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
627 | |
628 | /* This value is returned if detect_coding_mask () find nothing other | |
629 | than ASCII characters. */ | |
630 | #define CATEGORY_MASK_ANY \ | |
631 | (CATEGORY_MASK_ISO_7 \ | |
632 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
633 | | CATEGORY_MASK_ISO_8_1 \ | |
634 | | CATEGORY_MASK_ISO_8_2 \ | |
635 | | CATEGORY_MASK_ISO_7_ELSE \ | |
636 | | CATEGORY_MASK_ISO_8_ELSE \ | |
a470d443 KH |
637 | | CATEGORY_MASK_UTF_8_AUTO \ |
638 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
639 | | CATEGORY_MASK_UTF_8_SIG \ | |
2f3cbb32 | 640 | | CATEGORY_MASK_UTF_16_AUTO \ |
df7492f9 KH |
641 | | CATEGORY_MASK_UTF_16_BE \ |
642 | | CATEGORY_MASK_UTF_16_LE \ | |
643 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
644 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
645 | | CATEGORY_MASK_CHARSET \ | |
646 | | CATEGORY_MASK_SJIS \ | |
647 | | CATEGORY_MASK_BIG5 \ | |
648 | | CATEGORY_MASK_CCL \ | |
649 | | CATEGORY_MASK_EMACS_MULE) | |
650 | ||
651 | ||
652 | #define CATEGORY_MASK_ISO_7BIT \ | |
653 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
654 | ||
655 | #define CATEGORY_MASK_ISO_8BIT \ | |
656 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
657 | ||
658 | #define CATEGORY_MASK_ISO_ELSE \ | |
659 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
660 | ||
661 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
662 | (CATEGORY_MASK_ISO_7 \ | |
663 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
664 | | CATEGORY_MASK_ISO_7_ELSE \ | |
665 | | CATEGORY_MASK_ISO_8_ELSE) | |
666 | ||
667 | #define CATEGORY_MASK_ISO \ | |
668 | ( CATEGORY_MASK_ISO_7BIT \ | |
669 | | CATEGORY_MASK_ISO_8BIT \ | |
670 | | CATEGORY_MASK_ISO_ELSE) | |
671 | ||
672 | #define CATEGORY_MASK_UTF_16 \ | |
2f3cbb32 KH |
673 | (CATEGORY_MASK_UTF_16_AUTO \ |
674 | | CATEGORY_MASK_UTF_16_BE \ | |
df7492f9 KH |
675 | | CATEGORY_MASK_UTF_16_LE \ |
676 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
677 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
678 | ||
a470d443 KH |
679 | #define CATEGORY_MASK_UTF_8 \ |
680 | (CATEGORY_MASK_UTF_8_AUTO \ | |
681 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
682 | | CATEGORY_MASK_UTF_8_SIG) | |
df7492f9 KH |
683 | |
684 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
685 | variable is exposed to Emacs Lisp. */ | |
686 | static Lisp_Object Vcoding_category_list; | |
687 | ||
688 | /* Table of coding categories (Lisp symbols). This variable is for | |
689 | internal use oly. */ | |
690 | static Lisp_Object Vcoding_category_table; | |
691 | ||
692 | /* Table of coding-categories ordered by priority. */ | |
693 | static enum coding_category coding_priorities[coding_category_max]; | |
694 | ||
695 | /* Nth element is a coding context for the coding system bound to the | |
696 | Nth coding category. */ | |
697 | static struct coding_system coding_categories[coding_category_max]; | |
698 | ||
df7492f9 KH |
699 | /*** Commonly used macros and functions ***/ |
700 | ||
701 | #ifndef min | |
702 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
703 | #endif | |
704 | #ifndef max | |
705 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
706 | #endif | |
4ed46869 | 707 | |
24a73b0a KH |
708 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
709 | do { \ | |
710 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
711 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 712 | } while (0) |
4ed46869 | 713 | |
4ed46869 | 714 | |
df7492f9 KH |
715 | /* Safely get one byte from the source text pointed by SRC which ends |
716 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
717 | in the source, it jumps to `no_more_source'. If multibytep is |
718 | nonzero, and a multibyte character is found at SRC, set C to the | |
719 | negative value of the character code. The caller should declare | |
720 | and set these variables appropriately in advance: | |
721 | src, src_end, multibytep */ | |
aa72b389 | 722 | |
065e3595 KH |
723 | #define ONE_MORE_BYTE(c) \ |
724 | do { \ | |
725 | if (src == src_end) \ | |
726 | { \ | |
727 | if (src_base < src) \ | |
728 | record_conversion_result \ | |
729 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
730 | goto no_more_source; \ | |
731 | } \ | |
732 | c = *src++; \ | |
733 | if (multibytep && (c & 0x80)) \ | |
734 | { \ | |
735 | if ((c & 0xFE) == 0xC0) \ | |
736 | c = ((c & 1) << 6) | *src++; \ | |
737 | else \ | |
738 | { \ | |
35befdaa KH |
739 | src--; \ |
740 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
741 | record_conversion_result \ |
742 | (coding, CODING_RESULT_INVALID_SRC); \ | |
743 | } \ | |
744 | } \ | |
745 | consumed_chars++; \ | |
aa72b389 KH |
746 | } while (0) |
747 | ||
f56a4450 | 748 | /* Safely get two bytes from the source text pointed by SRC which ends |
220eeac9 KH |
749 | at SRC_END, and set C1 and C2 to those bytes while skipping the |
750 | heading multibyte characters. If there are not enough bytes in the | |
751 | source, it jumps to `no_more_source'. If multibytep is nonzero and | |
752 | a multibyte character is found for C2, set C2 to the negative value | |
753 | of the character code. The caller should declare and set these | |
754 | variables appropriately in advance: | |
f56a4450 KH |
755 | src, src_end, multibytep |
756 | It is intended that this macro is used in detect_coding_utf_16. */ | |
757 | ||
220eeac9 KH |
758 | #define TWO_MORE_BYTES(c1, c2) \ |
759 | do { \ | |
760 | do { \ | |
761 | if (src == src_end) \ | |
762 | goto no_more_source; \ | |
763 | c1 = *src++; \ | |
764 | if (multibytep && (c1 & 0x80)) \ | |
765 | { \ | |
766 | if ((c1 & 0xFE) == 0xC0) \ | |
767 | c1 = ((c1 & 1) << 6) | *src++; \ | |
768 | else \ | |
769 | { \ | |
770 | src += BYTES_BY_CHAR_HEAD (c1) - 1; \ | |
771 | c1 = -1; \ | |
772 | } \ | |
773 | } \ | |
774 | } while (c1 < 0); \ | |
775 | if (src == src_end) \ | |
776 | goto no_more_source; \ | |
777 | c2 = *src++; \ | |
778 | if (multibytep && (c2 & 0x80)) \ | |
779 | { \ | |
780 | if ((c2 & 0xFE) == 0xC0) \ | |
781 | c2 = ((c2 & 1) << 6) | *src++; \ | |
782 | else \ | |
783 | c2 = -1; \ | |
784 | } \ | |
f56a4450 KH |
785 | } while (0) |
786 | ||
aa72b389 | 787 | |
065e3595 KH |
788 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
789 | do { \ | |
790 | c = *src++; \ | |
791 | if (multibytep && (c & 0x80)) \ | |
792 | { \ | |
793 | if ((c & 0xFE) == 0xC0) \ | |
794 | c = ((c & 1) << 6) | *src++; \ | |
795 | else \ | |
796 | { \ | |
35befdaa KH |
797 | src--; \ |
798 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
799 | record_conversion_result \ |
800 | (coding, CODING_RESULT_INVALID_SRC); \ | |
801 | } \ | |
802 | } \ | |
803 | consumed_chars++; \ | |
aa72b389 KH |
804 | } while (0) |
805 | ||
aa72b389 | 806 | |
df7492f9 KH |
807 | /* Store a byte C in the place pointed by DST and increment DST to the |
808 | next free point, and increment PRODUCED_CHARS. The caller should | |
809 | assure that C is 0..127, and declare and set the variable `dst' | |
810 | appropriately in advance. | |
811 | */ | |
aa72b389 KH |
812 | |
813 | ||
df7492f9 KH |
814 | #define EMIT_ONE_ASCII_BYTE(c) \ |
815 | do { \ | |
816 | produced_chars++; \ | |
817 | *dst++ = (c); \ | |
b6871cc7 | 818 | } while (0) |
aa72b389 KH |
819 | |
820 | ||
df7492f9 | 821 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 822 | |
df7492f9 KH |
823 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
824 | do { \ | |
825 | produced_chars += 2; \ | |
826 | *dst++ = (c1), *dst++ = (c2); \ | |
827 | } while (0) | |
aa72b389 KH |
828 | |
829 | ||
df7492f9 KH |
830 | /* Store a byte C in the place pointed by DST and increment DST to the |
831 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
832 | nonzero, store in an appropriate multibyte from. The caller should | |
833 | declare and set the variables `dst' and `multibytep' appropriately | |
834 | in advance. */ | |
835 | ||
836 | #define EMIT_ONE_BYTE(c) \ | |
837 | do { \ | |
838 | produced_chars++; \ | |
839 | if (multibytep) \ | |
840 | { \ | |
841 | int ch = (c); \ | |
842 | if (ch >= 0x80) \ | |
843 | ch = BYTE8_TO_CHAR (ch); \ | |
844 | CHAR_STRING_ADVANCE (ch, dst); \ | |
845 | } \ | |
846 | else \ | |
847 | *dst++ = (c); \ | |
aa72b389 | 848 | } while (0) |
aa72b389 | 849 | |
aa72b389 | 850 | |
df7492f9 | 851 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 852 | |
e19c3639 KH |
853 | #define EMIT_TWO_BYTES(c1, c2) \ |
854 | do { \ | |
855 | produced_chars += 2; \ | |
856 | if (multibytep) \ | |
857 | { \ | |
858 | int ch; \ | |
859 | \ | |
860 | ch = (c1); \ | |
861 | if (ch >= 0x80) \ | |
862 | ch = BYTE8_TO_CHAR (ch); \ | |
863 | CHAR_STRING_ADVANCE (ch, dst); \ | |
864 | ch = (c2); \ | |
865 | if (ch >= 0x80) \ | |
866 | ch = BYTE8_TO_CHAR (ch); \ | |
867 | CHAR_STRING_ADVANCE (ch, dst); \ | |
868 | } \ | |
869 | else \ | |
870 | { \ | |
871 | *dst++ = (c1); \ | |
872 | *dst++ = (c2); \ | |
873 | } \ | |
aa72b389 KH |
874 | } while (0) |
875 | ||
876 | ||
df7492f9 KH |
877 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
878 | do { \ | |
879 | EMIT_ONE_BYTE (c1); \ | |
880 | EMIT_TWO_BYTES (c2, c3); \ | |
881 | } while (0) | |
aa72b389 | 882 | |
aa72b389 | 883 | |
df7492f9 KH |
884 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
885 | do { \ | |
886 | EMIT_TWO_BYTES (c1, c2); \ | |
887 | EMIT_TWO_BYTES (c3, c4); \ | |
888 | } while (0) | |
aa72b389 | 889 | |
aa72b389 | 890 | |
f6cbaf43 | 891 | /* Prototypes for static functions. */ |
f57e2426 J |
892 | static void record_conversion_result (struct coding_system *coding, |
893 | enum coding_result_code result); | |
894 | static int detect_coding_utf_8 (struct coding_system *, | |
895 | struct coding_detection_info *info); | |
896 | static void decode_coding_utf_8 (struct coding_system *); | |
897 | static int encode_coding_utf_8 (struct coding_system *); | |
898 | ||
899 | static int detect_coding_utf_16 (struct coding_system *, | |
900 | struct coding_detection_info *info); | |
901 | static void decode_coding_utf_16 (struct coding_system *); | |
902 | static int encode_coding_utf_16 (struct coding_system *); | |
903 | ||
904 | static int detect_coding_iso_2022 (struct coding_system *, | |
905 | struct coding_detection_info *info); | |
906 | static void decode_coding_iso_2022 (struct coding_system *); | |
907 | static int encode_coding_iso_2022 (struct coding_system *); | |
908 | ||
909 | static int detect_coding_emacs_mule (struct coding_system *, | |
910 | struct coding_detection_info *info); | |
911 | static void decode_coding_emacs_mule (struct coding_system *); | |
912 | static int encode_coding_emacs_mule (struct coding_system *); | |
913 | ||
914 | static int detect_coding_sjis (struct coding_system *, | |
915 | struct coding_detection_info *info); | |
916 | static void decode_coding_sjis (struct coding_system *); | |
917 | static int encode_coding_sjis (struct coding_system *); | |
918 | ||
919 | static int detect_coding_big5 (struct coding_system *, | |
920 | struct coding_detection_info *info); | |
921 | static void decode_coding_big5 (struct coding_system *); | |
922 | static int encode_coding_big5 (struct coding_system *); | |
923 | ||
924 | static int detect_coding_ccl (struct coding_system *, | |
925 | struct coding_detection_info *info); | |
926 | static void decode_coding_ccl (struct coding_system *); | |
927 | static int encode_coding_ccl (struct coding_system *); | |
928 | ||
929 | static void decode_coding_raw_text (struct coding_system *); | |
930 | static int encode_coding_raw_text (struct coding_system *); | |
931 | ||
932 | static void coding_set_source (struct coding_system *); | |
933 | static void coding_set_destination (struct coding_system *); | |
934 | static void coding_alloc_by_realloc (struct coding_system *, EMACS_INT); | |
935 | static void coding_alloc_by_making_gap (struct coding_system *, | |
936 | EMACS_INT, EMACS_INT); | |
937 | static unsigned char *alloc_destination (struct coding_system *, | |
938 | EMACS_INT, unsigned char *); | |
939 | static void setup_iso_safe_charsets (Lisp_Object); | |
940 | static unsigned char *encode_designation_at_bol (struct coding_system *, | |
941 | int *, int *, | |
942 | unsigned char *); | |
943 | static int detect_eol (const unsigned char *, | |
944 | EMACS_INT, enum coding_category); | |
945 | static Lisp_Object adjust_coding_eol_type (struct coding_system *, int); | |
946 | static void decode_eol (struct coding_system *); | |
947 | static Lisp_Object get_translation_table (Lisp_Object, int, int *); | |
948 | static Lisp_Object get_translation (Lisp_Object, int *, int *); | |
949 | static int produce_chars (struct coding_system *, Lisp_Object, int); | |
950 | static INLINE void produce_charset (struct coding_system *, int *, | |
951 | EMACS_INT); | |
952 | static void produce_annotation (struct coding_system *, EMACS_INT); | |
953 | static int decode_coding (struct coding_system *); | |
954 | static INLINE int *handle_composition_annotation (EMACS_INT, EMACS_INT, | |
955 | struct coding_system *, | |
956 | int *, EMACS_INT *); | |
957 | static INLINE int *handle_charset_annotation (EMACS_INT, EMACS_INT, | |
958 | struct coding_system *, | |
959 | int *, EMACS_INT *); | |
960 | static void consume_chars (struct coding_system *, Lisp_Object, int); | |
961 | static int encode_coding (struct coding_system *); | |
962 | static Lisp_Object make_conversion_work_buffer (int); | |
963 | static Lisp_Object code_conversion_restore (Lisp_Object); | |
964 | static INLINE int char_encodable_p (int, Lisp_Object); | |
965 | static Lisp_Object make_subsidiaries (Lisp_Object); | |
f6cbaf43 | 966 | |
065e3595 KH |
967 | static void |
968 | record_conversion_result (struct coding_system *coding, | |
969 | enum coding_result_code result) | |
970 | { | |
971 | coding->result = result; | |
972 | switch (result) | |
973 | { | |
974 | case CODING_RESULT_INSUFFICIENT_SRC: | |
975 | Vlast_code_conversion_error = Qinsufficient_source; | |
976 | break; | |
977 | case CODING_RESULT_INCONSISTENT_EOL: | |
978 | Vlast_code_conversion_error = Qinconsistent_eol; | |
979 | break; | |
980 | case CODING_RESULT_INVALID_SRC: | |
981 | Vlast_code_conversion_error = Qinvalid_source; | |
982 | break; | |
983 | case CODING_RESULT_INTERRUPT: | |
984 | Vlast_code_conversion_error = Qinterrupted; | |
985 | break; | |
986 | case CODING_RESULT_INSUFFICIENT_MEM: | |
987 | Vlast_code_conversion_error = Qinsufficient_memory; | |
988 | break; | |
ebaf11b6 KH |
989 | case CODING_RESULT_INSUFFICIENT_DST: |
990 | /* Don't record this error in Vlast_code_conversion_error | |
991 | because it happens just temporarily and is resolved when the | |
992 | whole conversion is finished. */ | |
993 | break; | |
409ea3a1 AS |
994 | case CODING_RESULT_SUCCESS: |
995 | break; | |
35befdaa KH |
996 | default: |
997 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
998 | } |
999 | } | |
1000 | ||
75f80e63 EZ |
1001 | /* This wrapper macro is used to preserve validity of pointers into |
1002 | buffer text across calls to decode_char, which could cause | |
1003 | relocation of buffers if it loads a charset map, because loading a | |
1004 | charset map allocates large structures. */ | |
df7492f9 KH |
1005 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
1006 | do { \ | |
1007 | charset_map_loaded = 0; \ | |
1008 | c = DECODE_CHAR (charset, code); \ | |
1009 | if (charset_map_loaded) \ | |
1010 | { \ | |
8f924df7 | 1011 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
1012 | EMACS_INT offset; \ |
1013 | \ | |
1014 | coding_set_source (coding); \ | |
1015 | offset = coding->source - orig; \ | |
1016 | src += offset; \ | |
1017 | src_base += offset; \ | |
1018 | src_end += offset; \ | |
1019 | } \ | |
aa72b389 KH |
1020 | } while (0) |
1021 | ||
1022 | ||
119852e7 KH |
1023 | /* If there are at least BYTES length of room at dst, allocate memory |
1024 | for coding->destination and update dst and dst_end. We don't have | |
1025 | to take care of coding->source which will be relocated. It is | |
1026 | handled by calling coding_set_source in encode_coding. */ | |
1027 | ||
df7492f9 KH |
1028 | #define ASSURE_DESTINATION(bytes) \ |
1029 | do { \ | |
1030 | if (dst + (bytes) >= dst_end) \ | |
1031 | { \ | |
1032 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
1033 | \ | |
1034 | dst = alloc_destination (coding, more_bytes, dst); \ | |
1035 | dst_end = coding->destination + coding->dst_bytes; \ | |
1036 | } \ | |
1037 | } while (0) | |
aa72b389 | 1038 | |
aa72b389 | 1039 | |
db274c7a KH |
1040 | /* Store multibyte form of the character C in P, and advance P to the |
1041 | end of the multibyte form. This is like CHAR_STRING_ADVANCE but it | |
1042 | never calls MAYBE_UNIFY_CHAR. */ | |
1043 | ||
1044 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) \ | |
1045 | do { \ | |
1046 | if ((c) <= MAX_1_BYTE_CHAR) \ | |
1047 | *(p)++ = (c); \ | |
1048 | else if ((c) <= MAX_2_BYTE_CHAR) \ | |
1049 | *(p)++ = (0xC0 | ((c) >> 6)), \ | |
1050 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
1051 | else if ((c) <= MAX_3_BYTE_CHAR) \ | |
1052 | *(p)++ = (0xE0 | ((c) >> 12)), \ | |
1053 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ | |
1054 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
1055 | else if ((c) <= MAX_4_BYTE_CHAR) \ | |
1056 | *(p)++ = (0xF0 | (c >> 18)), \ | |
1057 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
1058 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
1059 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
1060 | else if ((c) <= MAX_5_BYTE_CHAR) \ | |
1061 | *(p)++ = 0xF8, \ | |
1062 | *(p)++ = (0x80 | ((c >> 18) & 0x0F)), \ | |
1063 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
1064 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
1065 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
1066 | else \ | |
1067 | (p) += BYTE8_STRING ((c) - 0x3FFF80, p); \ | |
1068 | } while (0) | |
1069 | ||
1070 | ||
1071 | /* Return the character code of character whose multibyte form is at | |
1072 | P, and advance P to the end of the multibyte form. This is like | |
1073 | STRING_CHAR_ADVANCE, but it never calls MAYBE_UNIFY_CHAR. */ | |
1074 | ||
1075 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) \ | |
1076 | (!((p)[0] & 0x80) \ | |
1077 | ? *(p)++ \ | |
1078 | : ! ((p)[0] & 0x20) \ | |
1079 | ? ((p) += 2, \ | |
1080 | ((((p)[-2] & 0x1F) << 6) \ | |
1081 | | ((p)[-1] & 0x3F) \ | |
1082 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
1083 | : ! ((p)[0] & 0x10) \ | |
1084 | ? ((p) += 3, \ | |
1085 | ((((p)[-3] & 0x0F) << 12) \ | |
1086 | | (((p)[-2] & 0x3F) << 6) \ | |
1087 | | ((p)[-1] & 0x3F))) \ | |
1088 | : ! ((p)[0] & 0x08) \ | |
1089 | ? ((p) += 4, \ | |
1090 | ((((p)[-4] & 0xF) << 18) \ | |
1091 | | (((p)[-3] & 0x3F) << 12) \ | |
1092 | | (((p)[-2] & 0x3F) << 6) \ | |
1093 | | ((p)[-1] & 0x3F))) \ | |
1094 | : ((p) += 5, \ | |
1095 | ((((p)[-4] & 0x3F) << 18) \ | |
1096 | | (((p)[-3] & 0x3F) << 12) \ | |
1097 | | (((p)[-2] & 0x3F) << 6) \ | |
1098 | | ((p)[-1] & 0x3F)))) | |
1099 | ||
aa72b389 | 1100 | |
df7492f9 | 1101 | static void |
971de7fb | 1102 | coding_set_source (struct coding_system *coding) |
aa72b389 | 1103 | { |
df7492f9 KH |
1104 | if (BUFFERP (coding->src_object)) |
1105 | { | |
2cb26057 | 1106 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 1107 | |
df7492f9 | 1108 | if (coding->src_pos < 0) |
2cb26057 | 1109 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 1110 | else |
2cb26057 | 1111 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 1112 | } |
df7492f9 | 1113 | else if (STRINGP (coding->src_object)) |
aa72b389 | 1114 | { |
8f924df7 | 1115 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 1116 | } |
df7492f9 KH |
1117 | else |
1118 | /* Otherwise, the source is C string and is never relocated | |
1119 | automatically. Thus we don't have to update anything. */ | |
1120 | ; | |
1121 | } | |
aa72b389 | 1122 | |
df7492f9 | 1123 | static void |
971de7fb | 1124 | coding_set_destination (struct coding_system *coding) |
df7492f9 KH |
1125 | { |
1126 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 1127 | { |
df7492f9 | 1128 | if (coding->src_pos < 0) |
aa72b389 | 1129 | { |
13818c30 | 1130 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
1131 | coding->dst_bytes = (GAP_END_ADDR |
1132 | - (coding->src_bytes - coding->consumed) | |
1133 | - coding->destination); | |
aa72b389 | 1134 | } |
df7492f9 | 1135 | else |
28f67a95 KH |
1136 | { |
1137 | /* We are sure that coding->dst_pos_byte is before the gap | |
1138 | of the buffer. */ | |
1139 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 1140 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
1141 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
1142 | - coding->destination); | |
1143 | } | |
df7492f9 KH |
1144 | } |
1145 | else | |
1146 | /* Otherwise, the destination is C string and is never relocated | |
1147 | automatically. Thus we don't have to update anything. */ | |
1148 | ; | |
1149 | } | |
1150 | ||
1151 | ||
1152 | static void | |
971de7fb | 1153 | coding_alloc_by_realloc (struct coding_system *coding, EMACS_INT bytes) |
df7492f9 KH |
1154 | { |
1155 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
1156 | coding->dst_bytes + bytes); | |
1157 | coding->dst_bytes += bytes; | |
1158 | } | |
1159 | ||
1160 | static void | |
cf84bb53 JB |
1161 | coding_alloc_by_making_gap (struct coding_system *coding, |
1162 | EMACS_INT gap_head_used, EMACS_INT bytes) | |
df7492f9 | 1163 | { |
db274c7a | 1164 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1165 | { |
db274c7a KH |
1166 | /* The gap may contain the produced data at the head and not-yet |
1167 | consumed data at the tail. To preserve those data, we at | |
1168 | first make the gap size to zero, then increase the gap | |
1169 | size. */ | |
1170 | EMACS_INT add = GAP_SIZE; | |
1171 | ||
1172 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1173 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1174 | make_gap (bytes); |
1175 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1176 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1177 | } |
730fff51 | 1178 | else |
df7492f9 | 1179 | { |
2c78b7e1 KH |
1180 | Lisp_Object this_buffer; |
1181 | ||
1182 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1183 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1184 | make_gap (bytes); | |
1185 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1186 | } |
df7492f9 | 1187 | } |
8f924df7 | 1188 | |
df7492f9 KH |
1189 | |
1190 | static unsigned char * | |
cf84bb53 JB |
1191 | alloc_destination (struct coding_system *coding, EMACS_INT nbytes, |
1192 | unsigned char *dst) | |
df7492f9 KH |
1193 | { |
1194 | EMACS_INT offset = dst - coding->destination; | |
1195 | ||
1196 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1197 | { |
1198 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1199 | ||
1200 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1201 | } | |
aa72b389 | 1202 | else |
df7492f9 | 1203 | coding_alloc_by_realloc (coding, nbytes); |
df7492f9 KH |
1204 | coding_set_destination (coding); |
1205 | dst = coding->destination + offset; | |
1206 | return dst; | |
1207 | } | |
aa72b389 | 1208 | |
ff0dacd7 KH |
1209 | /** Macros for annotations. */ |
1210 | ||
ff0dacd7 KH |
1211 | /* An annotation data is stored in the array coding->charbuf in this |
1212 | format: | |
69a80ea3 | 1213 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1214 | LENGTH is the number of elements in the annotation. |
1215 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1216 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1217 | |
1218 | The format of the following elements depend on ANNOTATION_MASK. | |
1219 | ||
1220 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1221 | follows: | |
e951386e KH |
1222 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
1223 | ||
1224 | NBYTES is the number of bytes specified in the header part of | |
1225 | old-style emacs-mule encoding, or 0 for the other kind of | |
1226 | composition. | |
1227 | ||
ff0dacd7 | 1228 | METHOD is one of enum composition_method. |
e951386e | 1229 | |
ff0dacd7 KH |
1230 | Optionnal COMPOSITION-COMPONENTS are characters and composition |
1231 | rules. | |
1232 | ||
1233 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
e951386e KH |
1234 | follows. |
1235 | ||
1236 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | |
1237 | recover from an invalid annotation, and should be skipped by | |
1238 | produce_annotation. */ | |
1239 | ||
1240 | /* Maximum length of the header of annotation data. */ | |
1241 | #define MAX_ANNOTATION_LENGTH 5 | |
ff0dacd7 | 1242 | |
69a80ea3 | 1243 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1244 | do { \ |
1245 | *(buf)++ = -(len); \ | |
1246 | *(buf)++ = (mask); \ | |
69a80ea3 | 1247 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1248 | coding->annotated = 1; \ |
1249 | } while (0); | |
1250 | ||
e951386e | 1251 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
69a80ea3 | 1252 | do { \ |
e951386e KH |
1253 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
1254 | *buf++ = nbytes; \ | |
69a80ea3 | 1255 | *buf++ = method; \ |
ff0dacd7 KH |
1256 | } while (0) |
1257 | ||
1258 | ||
69a80ea3 KH |
1259 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1260 | do { \ | |
1261 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1262 | *buf++ = id; \ | |
ff0dacd7 KH |
1263 | } while (0) |
1264 | ||
df7492f9 KH |
1265 | \f |
1266 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1267 | ||
1268 | ||
1269 | ||
1270 | \f | |
1271 | /*** 3. UTF-8 ***/ | |
1272 | ||
1273 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1274 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1275 | return 0. */ | |
df7492f9 KH |
1276 | |
1277 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1278 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1279 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1280 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1281 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1282 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1283 | ||
a470d443 KH |
1284 | #define UTF_BOM 0xFEFF |
1285 | #define UTF_8_BOM_1 0xEF | |
1286 | #define UTF_8_BOM_2 0xBB | |
1287 | #define UTF_8_BOM_3 0xBF | |
1288 | ||
df7492f9 | 1289 | static int |
cf84bb53 JB |
1290 | detect_coding_utf_8 (struct coding_system *coding, |
1291 | struct coding_detection_info *detect_info) | |
df7492f9 | 1292 | { |
065e3595 | 1293 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1294 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1295 | int multibytep = coding->src_multibyte; |
1296 | int consumed_chars = 0; | |
a470d443 | 1297 | int bom_found = 0; |
df7492f9 KH |
1298 | int found = 0; |
1299 | ||
ff0dacd7 | 1300 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1301 | /* A coding system of this category is always ASCII compatible. */ |
1302 | src += coding->head_ascii; | |
1303 | ||
1304 | while (1) | |
aa72b389 | 1305 | { |
df7492f9 | 1306 | int c, c1, c2, c3, c4; |
aa72b389 | 1307 | |
065e3595 | 1308 | src_base = src; |
df7492f9 | 1309 | ONE_MORE_BYTE (c); |
065e3595 | 1310 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1311 | continue; |
1312 | ONE_MORE_BYTE (c1); | |
065e3595 | 1313 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1314 | break; |
1315 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1316 | { |
a470d443 | 1317 | found = 1; |
df7492f9 | 1318 | continue; |
aa72b389 | 1319 | } |
df7492f9 | 1320 | ONE_MORE_BYTE (c2); |
065e3595 | 1321 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1322 | break; |
1323 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1324 | { |
a470d443 KH |
1325 | found = 1; |
1326 | if (src_base == coding->source | |
1327 | && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3) | |
1328 | bom_found = 1; | |
df7492f9 | 1329 | continue; |
aa72b389 | 1330 | } |
df7492f9 | 1331 | ONE_MORE_BYTE (c3); |
065e3595 | 1332 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1333 | break; |
1334 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1335 | { |
a470d443 | 1336 | found = 1; |
df7492f9 KH |
1337 | continue; |
1338 | } | |
1339 | ONE_MORE_BYTE (c4); | |
065e3595 | 1340 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1341 | break; |
1342 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1343 | { | |
a470d443 | 1344 | found = 1; |
df7492f9 KH |
1345 | continue; |
1346 | } | |
1347 | break; | |
aa72b389 | 1348 | } |
ff0dacd7 | 1349 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1350 | return 0; |
aa72b389 | 1351 | |
df7492f9 | 1352 | no_more_source: |
065e3595 | 1353 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1354 | { |
ff0dacd7 | 1355 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1356 | return 0; |
aa72b389 | 1357 | } |
a470d443 KH |
1358 | if (bom_found) |
1359 | { | |
1360 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
1361 | detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; | |
1362 | } | |
1363 | else | |
1364 | { | |
1365 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
0e17387a KH |
1366 | if (found) |
1367 | detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1368 | } |
ff0dacd7 | 1369 | return 1; |
aa72b389 KH |
1370 | } |
1371 | ||
4ed46869 | 1372 | |
b73bfc1c | 1373 | static void |
971de7fb | 1374 | decode_coding_utf_8 (struct coding_system *coding) |
b73bfc1c | 1375 | { |
8f924df7 KH |
1376 | const unsigned char *src = coding->source + coding->consumed; |
1377 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1378 | const unsigned char *src_base; | |
69a80ea3 KH |
1379 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1380 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
453b38f0 | 1381 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1382 | int multibytep = coding->src_multibyte; |
a470d443 | 1383 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
24a73b0a | 1384 | Lisp_Object attr, charset_list; |
0a9564cb EZ |
1385 | int eol_crlf = |
1386 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1387 | int byte_after_cr = -1; |
4ed46869 | 1388 | |
24a73b0a | 1389 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1390 | |
a470d443 KH |
1391 | if (bom != utf_without_bom) |
1392 | { | |
1393 | int c1, c2, c3; | |
1394 | ||
1395 | src_base = src; | |
1396 | ONE_MORE_BYTE (c1); | |
1397 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1398 | src = src_base; | |
1399 | else | |
1400 | { | |
159bd5a2 | 1401 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1402 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1403 | src = src_base; | |
1404 | else | |
1405 | { | |
159bd5a2 | 1406 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1407 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1408 | src = src_base; | |
1409 | else | |
1410 | { | |
1411 | if ((c1 != UTF_8_BOM_1) | |
1412 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1413 | src = src_base; | |
1414 | else | |
1415 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1416 | } | |
1417 | } | |
1418 | } | |
1419 | } | |
1420 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1421 | ||
df7492f9 | 1422 | while (1) |
b73bfc1c | 1423 | { |
df7492f9 | 1424 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1425 | |
df7492f9 KH |
1426 | src_base = src; |
1427 | consumed_chars_base = consumed_chars; | |
4af310db | 1428 | |
df7492f9 | 1429 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1430 | { |
1431 | if (byte_after_cr >= 0) | |
1432 | src_base--; | |
1433 | break; | |
1434 | } | |
df7492f9 | 1435 | |
119852e7 KH |
1436 | if (byte_after_cr >= 0) |
1437 | c1 = byte_after_cr, byte_after_cr = -1; | |
1438 | else | |
1439 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1440 | if (c1 < 0) |
1441 | { | |
1442 | c = - c1; | |
1443 | } | |
1a4990fb | 1444 | else if (UTF_8_1_OCTET_P (c1)) |
df7492f9 | 1445 | { |
119852e7 KH |
1446 | if (eol_crlf && c1 == '\r') |
1447 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 | 1448 | c = c1; |
4af310db | 1449 | } |
df7492f9 | 1450 | else |
4af310db | 1451 | { |
df7492f9 | 1452 | ONE_MORE_BYTE (c2); |
065e3595 | 1453 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1454 | goto invalid_code; |
1455 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1456 | { |
b0edb2c5 DL |
1457 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1458 | /* Reject overlong sequences here and below. Encoders | |
1459 | producing them are incorrect, they can be misleading, | |
1460 | and they mess up read/write invariance. */ | |
1461 | if (c < 128) | |
1462 | goto invalid_code; | |
4af310db | 1463 | } |
df7492f9 | 1464 | else |
aa72b389 | 1465 | { |
df7492f9 | 1466 | ONE_MORE_BYTE (c3); |
065e3595 | 1467 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1468 | goto invalid_code; |
1469 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1470 | { |
1471 | c = (((c1 & 0xF) << 12) | |
1472 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1473 | if (c < 0x800 |
1474 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1475 | goto invalid_code; |
1476 | } | |
df7492f9 KH |
1477 | else |
1478 | { | |
1479 | ONE_MORE_BYTE (c4); | |
065e3595 | 1480 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1481 | goto invalid_code; |
1482 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1483 | { |
df7492f9 KH |
1484 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1485 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1486 | if (c < 0x10000) |
1487 | goto invalid_code; | |
1488 | } | |
df7492f9 KH |
1489 | else |
1490 | { | |
1491 | ONE_MORE_BYTE (c5); | |
065e3595 | 1492 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1493 | goto invalid_code; |
1494 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1495 | { | |
1496 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1497 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1498 | | (c5 & 0x3F)); | |
b0edb2c5 | 1499 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1500 | goto invalid_code; |
1501 | } | |
1502 | else | |
1503 | goto invalid_code; | |
1504 | } | |
1505 | } | |
aa72b389 | 1506 | } |
b73bfc1c | 1507 | } |
df7492f9 KH |
1508 | |
1509 | *charbuf++ = c; | |
1510 | continue; | |
1511 | ||
1512 | invalid_code: | |
1513 | src = src_base; | |
1514 | consumed_chars = consumed_chars_base; | |
1515 | ONE_MORE_BYTE (c); | |
1516 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1517 | coding->errors++; | |
aa72b389 KH |
1518 | } |
1519 | ||
df7492f9 KH |
1520 | no_more_source: |
1521 | coding->consumed_char += consumed_chars_base; | |
1522 | coding->consumed = src_base - coding->source; | |
1523 | coding->charbuf_used = charbuf - coding->charbuf; | |
1524 | } | |
1525 | ||
1526 | ||
1527 | static int | |
971de7fb | 1528 | encode_coding_utf_8 (struct coding_system *coding) |
df7492f9 KH |
1529 | { |
1530 | int multibytep = coding->dst_multibyte; | |
1531 | int *charbuf = coding->charbuf; | |
1532 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1533 | unsigned char *dst = coding->destination + coding->produced; | |
1534 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1535 | int produced_chars = 0; |
df7492f9 KH |
1536 | int c; |
1537 | ||
a470d443 KH |
1538 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1539 | { | |
1540 | ASSURE_DESTINATION (3); | |
1541 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1542 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1543 | } | |
1544 | ||
df7492f9 | 1545 | if (multibytep) |
aa72b389 | 1546 | { |
df7492f9 KH |
1547 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1548 | ||
1549 | while (charbuf < charbuf_end) | |
b73bfc1c | 1550 | { |
df7492f9 | 1551 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1552 | |
df7492f9 KH |
1553 | ASSURE_DESTINATION (safe_room); |
1554 | c = *charbuf++; | |
28f67a95 KH |
1555 | if (CHAR_BYTE8_P (c)) |
1556 | { | |
1557 | c = CHAR_TO_BYTE8 (c); | |
1558 | EMIT_ONE_BYTE (c); | |
1559 | } | |
1560 | else | |
1561 | { | |
db274c7a | 1562 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1563 | for (p = str; p < pend; p++) |
1564 | EMIT_ONE_BYTE (*p); | |
1565 | } | |
b73bfc1c | 1566 | } |
aa72b389 | 1567 | } |
df7492f9 KH |
1568 | else |
1569 | { | |
1570 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1571 | ||
1572 | while (charbuf < charbuf_end) | |
b73bfc1c | 1573 | { |
df7492f9 KH |
1574 | ASSURE_DESTINATION (safe_room); |
1575 | c = *charbuf++; | |
f03caae0 KH |
1576 | if (CHAR_BYTE8_P (c)) |
1577 | *dst++ = CHAR_TO_BYTE8 (c); | |
1578 | else | |
db274c7a | 1579 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1580 | produced_chars++; |
4ed46869 KH |
1581 | } |
1582 | } | |
065e3595 | 1583 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1584 | coding->produced_char += produced_chars; |
1585 | coding->produced = dst - coding->destination; | |
1586 | return 0; | |
4ed46869 KH |
1587 | } |
1588 | ||
b73bfc1c | 1589 | |
df7492f9 | 1590 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1591 | Check if a text is encoded in one of UTF-16 based coding systems. |
1592 | If it is, return 1, else return 0. */ | |
aa72b389 | 1593 | |
df7492f9 KH |
1594 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1595 | (((val) & 0xFC00) == 0xD800) | |
1596 | ||
1597 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1598 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1599 | |
df7492f9 KH |
1600 | #define UTF_16_INVALID_P(val) \ |
1601 | (((val) == 0xFFFE) \ | |
1602 | || ((val) == 0xFFFF) \ | |
1603 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1604 | |
aa72b389 | 1605 | |
df7492f9 | 1606 | static int |
cf84bb53 JB |
1607 | detect_coding_utf_16 (struct coding_system *coding, |
1608 | struct coding_detection_info *detect_info) | |
aa72b389 | 1609 | { |
8f924df7 KH |
1610 | const unsigned char *src = coding->source, *src_base = src; |
1611 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1612 | int multibytep = coding->src_multibyte; |
1613 | int consumed_chars = 0; | |
1614 | int c1, c2; | |
aa72b389 | 1615 | |
ff0dacd7 | 1616 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1617 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1618 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1619 | { |
1620 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1621 | return 0; | |
1622 | } | |
24a73b0a | 1623 | |
f56a4450 | 1624 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1625 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1626 | { |
b49a1807 KH |
1627 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1628 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1629 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1630 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1631 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1632 | } |
df7492f9 | 1633 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1634 | { |
b49a1807 KH |
1635 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1636 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1637 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1638 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1639 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1640 | } | |
220eeac9 | 1641 | else if (c2 < 0) |
f56a4450 KH |
1642 | { |
1643 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1644 | return 0; | |
1645 | } | |
2f3cbb32 | 1646 | else |
24a73b0a | 1647 | { |
2f3cbb32 KH |
1648 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1649 | O is odd. If both are high, we assume binary data.*/ | |
1650 | unsigned char e[256], o[256]; | |
1651 | unsigned e_num = 1, o_num = 1; | |
1652 | ||
1653 | memset (e, 0, 256); | |
1654 | memset (o, 0, 256); | |
1655 | e[c1] = 1; | |
1656 | o[c2] = 1; | |
1657 | ||
cc13543e KH |
1658 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO |
1659 | |CATEGORY_MASK_UTF_16_BE | |
1660 | | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 | 1661 | |
7f1faf1c KH |
1662 | while ((detect_info->rejected & CATEGORY_MASK_UTF_16) |
1663 | != CATEGORY_MASK_UTF_16) | |
2f3cbb32 | 1664 | { |
f56a4450 | 1665 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1666 | if (c2 < 0) |
f56a4450 | 1667 | break; |
2f3cbb32 KH |
1668 | if (! e[c1]) |
1669 | { | |
1670 | e[c1] = 1; | |
1671 | e_num++; | |
cc13543e KH |
1672 | if (e_num >= 128) |
1673 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
2f3cbb32 KH |
1674 | } |
1675 | if (! o[c2]) | |
1676 | { | |
977b85f4 | 1677 | o[c2] = 1; |
2f3cbb32 | 1678 | o_num++; |
cc13543e KH |
1679 | if (o_num >= 128) |
1680 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
2f3cbb32 KH |
1681 | } |
1682 | } | |
2f3cbb32 | 1683 | return 0; |
ff0dacd7 | 1684 | } |
2f3cbb32 | 1685 | |
df7492f9 | 1686 | no_more_source: |
ff0dacd7 | 1687 | return 1; |
df7492f9 | 1688 | } |
aa72b389 | 1689 | |
df7492f9 | 1690 | static void |
971de7fb | 1691 | decode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1692 | { |
8f924df7 KH |
1693 | const unsigned char *src = coding->source + coding->consumed; |
1694 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1695 | const unsigned char *src_base; | |
69a80ea3 | 1696 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
1697 | /* We may produces at most 3 chars in one loop. */ |
1698 | int *charbuf_end = coding->charbuf + coding->charbuf_size - 2; | |
3a8406e1 | 1699 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1700 | int multibytep = coding->src_multibyte; |
a470d443 | 1701 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1702 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1703 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1704 | Lisp_Object attr, charset_list; |
0a9564cb EZ |
1705 | int eol_crlf = |
1706 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1707 | int byte_after_cr1 = -1, byte_after_cr2 = -1; |
df7492f9 | 1708 | |
24a73b0a | 1709 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1710 | |
a470d443 | 1711 | if (bom == utf_with_bom) |
aa72b389 | 1712 | { |
df7492f9 | 1713 | int c, c1, c2; |
4af310db | 1714 | |
aa72b389 | 1715 | src_base = src; |
df7492f9 KH |
1716 | ONE_MORE_BYTE (c1); |
1717 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1718 | c = (c1 << 8) | c2; |
aa72b389 | 1719 | |
b49a1807 KH |
1720 | if (endian == utf_16_big_endian |
1721 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1722 | { |
b49a1807 KH |
1723 | /* The first two bytes are not BOM. Treat them as bytes |
1724 | for a normal character. */ | |
1725 | src = src_base; | |
1726 | coding->errors++; | |
aa72b389 | 1727 | } |
a470d443 | 1728 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1729 | } |
a470d443 | 1730 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1731 | { |
1732 | /* We have already tried to detect BOM and failed in | |
1733 | detect_coding. */ | |
a470d443 | 1734 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1735 | } |
aa72b389 | 1736 | |
df7492f9 KH |
1737 | while (1) |
1738 | { | |
1739 | int c, c1, c2; | |
1740 | ||
1741 | src_base = src; | |
1742 | consumed_chars_base = consumed_chars; | |
1743 | ||
df80c7f0 | 1744 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1745 | { |
1746 | if (byte_after_cr1 >= 0) | |
1747 | src_base -= 2; | |
1748 | break; | |
1749 | } | |
df7492f9 | 1750 | |
119852e7 KH |
1751 | if (byte_after_cr1 >= 0) |
1752 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1753 | else | |
1754 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1755 | if (c1 < 0) |
1756 | { | |
1757 | *charbuf++ = -c1; | |
1758 | continue; | |
1759 | } | |
119852e7 KH |
1760 | if (byte_after_cr2 >= 0) |
1761 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1762 | else | |
1763 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1764 | if (c2 < 0) |
1765 | { | |
1766 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1767 | *charbuf++ = -c2; | |
1768 | continue; | |
1769 | } | |
df7492f9 | 1770 | c = (endian == utf_16_big_endian |
e19c3639 | 1771 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1772 | |
df7492f9 | 1773 | if (surrogate) |
fd3ae0b9 | 1774 | { |
df7492f9 | 1775 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1776 | { |
df7492f9 KH |
1777 | if (endian == utf_16_big_endian) |
1778 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1779 | else | |
1780 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1781 | *charbuf++ = c1; | |
1782 | *charbuf++ = c2; | |
1783 | coding->errors++; | |
1784 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1785 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1786 | else |
df7492f9 | 1787 | *charbuf++ = c; |
fd3ae0b9 KH |
1788 | } |
1789 | else | |
df7492f9 KH |
1790 | { |
1791 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1792 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1793 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1794 | } |
fd3ae0b9 | 1795 | } |
aa72b389 | 1796 | else |
df7492f9 KH |
1797 | { |
1798 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1799 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1800 | else | |
119852e7 KH |
1801 | { |
1802 | if (eol_crlf && c == '\r') | |
1803 | { | |
1804 | ONE_MORE_BYTE (byte_after_cr1); | |
1805 | ONE_MORE_BYTE (byte_after_cr2); | |
1806 | } | |
1807 | *charbuf++ = c; | |
1808 | } | |
8f924df7 | 1809 | } |
aa72b389 | 1810 | } |
df7492f9 KH |
1811 | |
1812 | no_more_source: | |
1813 | coding->consumed_char += consumed_chars_base; | |
1814 | coding->consumed = src_base - coding->source; | |
1815 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1816 | } |
b73bfc1c | 1817 | |
df7492f9 | 1818 | static int |
971de7fb | 1819 | encode_coding_utf_16 (struct coding_system *coding) |
df7492f9 KH |
1820 | { |
1821 | int multibytep = coding->dst_multibyte; | |
1822 | int *charbuf = coding->charbuf; | |
1823 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1824 | unsigned char *dst = coding->destination + coding->produced; | |
1825 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1826 | int safe_room = 8; | |
a470d443 | 1827 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1828 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
1829 | int produced_chars = 0; | |
24a73b0a | 1830 | Lisp_Object attrs, charset_list; |
df7492f9 | 1831 | int c; |
4ed46869 | 1832 | |
24a73b0a | 1833 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1834 | |
a470d443 | 1835 | if (bom != utf_without_bom) |
df7492f9 KH |
1836 | { |
1837 | ASSURE_DESTINATION (safe_room); | |
1838 | if (big_endian) | |
df7492f9 | 1839 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1840 | else |
1841 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1842 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1843 | } |
1844 | ||
1845 | while (charbuf < charbuf_end) | |
1846 | { | |
1847 | ASSURE_DESTINATION (safe_room); | |
1848 | c = *charbuf++; | |
60afa08d | 1849 | if (c > MAX_UNICODE_CHAR) |
e19c3639 | 1850 | c = coding->default_char; |
df7492f9 KH |
1851 | |
1852 | if (c < 0x10000) | |
1853 | { | |
1854 | if (big_endian) | |
1855 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1856 | else | |
1857 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1858 | } | |
1859 | else | |
1860 | { | |
1861 | int c1, c2; | |
1862 | ||
1863 | c -= 0x10000; | |
1864 | c1 = (c >> 10) + 0xD800; | |
1865 | c2 = (c & 0x3FF) + 0xDC00; | |
1866 | if (big_endian) | |
1867 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1868 | else | |
1869 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1870 | } | |
1871 | } | |
065e3595 | 1872 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1873 | coding->produced = dst - coding->destination; |
1874 | coding->produced_char += produced_chars; | |
1875 | return 0; | |
1876 | } | |
1877 | ||
1878 | \f | |
1879 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1880 | ||
1881 | /* Emacs' internal format for representation of multiple character | |
1882 | sets is a kind of multi-byte encoding, i.e. characters are | |
1883 | represented by variable-length sequences of one-byte codes. | |
1884 | ||
1885 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1886 | represented by one-byte sequences which are their ASCII codes, in | |
1887 | the range 0x00 through 0x7F. | |
1888 | ||
1889 | 8-bit characters of the range 0x80..0x9F are represented by | |
1890 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1891 | code + 0x20). | |
1892 | ||
1893 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1894 | one-byte sequences which are their 8-bit code. | |
1895 | ||
1896 | The other characters are represented by a sequence of `base | |
1897 | leading-code', optional `extended leading-code', and one or two | |
1898 | `position-code's. The length of the sequence is determined by the | |
1899 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1900 | whereas extended leading-code and position-code take the range 0xA0 | |
1901 | through 0xFF. See `charset.h' for more details about leading-code | |
1902 | and position-code. | |
1903 | ||
1904 | --- CODE RANGE of Emacs' internal format --- | |
1905 | character set range | |
1906 | ------------- ----- | |
1907 | ascii 0x00..0x7F | |
1908 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1909 | eight-bit-graphic 0xA0..0xBF | |
1910 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1911 | --------------------------------------------- | |
1912 | ||
1913 | As this is the internal character representation, the format is | |
1914 | usually not used externally (i.e. in a file or in a data sent to a | |
1915 | process). But, it is possible to have a text externally in this | |
1916 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1917 | ||
1918 | In that case, a sequence of one-byte codes has a slightly different | |
1919 | form. | |
1920 | ||
1921 | At first, all characters in eight-bit-control are represented by | |
1922 | one-byte sequences which are their 8-bit code. | |
1923 | ||
1924 | Next, character composition data are represented by the byte | |
1925 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1926 | where, | |
e951386e | 1927 | METHOD is 0xF2 plus one of composition method (enum |
df7492f9 KH |
1928 | composition_method), |
1929 | ||
1930 | BYTES is 0xA0 plus a byte length of this composition data, | |
1931 | ||
e951386e | 1932 | CHARS is 0xA0 plus a number of characters composed by this |
df7492f9 KH |
1933 | data, |
1934 | ||
1935 | COMPONENTs are characters of multibye form or composition | |
1936 | rules encoded by two-byte of ASCII codes. | |
1937 | ||
1938 | In addition, for backward compatibility, the following formats are | |
1939 | also recognized as composition data on decoding. | |
1940 | ||
1941 | 0x80 MSEQ ... | |
1942 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1943 | ||
1944 | Here, | |
1945 | MSEQ is a multibyte form but in these special format: | |
1946 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1947 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1948 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1949 | represents a composition rule. | |
1950 | */ | |
1951 | ||
1952 | char emacs_mule_bytes[256]; | |
1953 | ||
e951386e KH |
1954 | |
1955 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
1956 | Check if a text is encoded in `emacs-mule'. If it is, return 1, | |
1957 | else return 0. */ | |
1958 | ||
1959 | static int | |
cf84bb53 JB |
1960 | detect_coding_emacs_mule (struct coding_system *coding, |
1961 | struct coding_detection_info *detect_info) | |
e951386e KH |
1962 | { |
1963 | const unsigned char *src = coding->source, *src_base; | |
1964 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1965 | int multibytep = coding->src_multibyte; | |
1966 | int consumed_chars = 0; | |
1967 | int c; | |
1968 | int found = 0; | |
1969 | ||
1970 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | |
1971 | /* A coding system of this category is always ASCII compatible. */ | |
1972 | src += coding->head_ascii; | |
1973 | ||
1974 | while (1) | |
1975 | { | |
1976 | src_base = src; | |
1977 | ONE_MORE_BYTE (c); | |
1978 | if (c < 0) | |
1979 | continue; | |
1980 | if (c == 0x80) | |
1981 | { | |
1982 | /* Perhaps the start of composite character. We simply skip | |
1983 | it because analyzing it is too heavy for detecting. But, | |
1984 | at least, we check that the composite character | |
1985 | constitutes of more than 4 bytes. */ | |
1986 | const unsigned char *src_base; | |
1987 | ||
1988 | repeat: | |
1989 | src_base = src; | |
1990 | do | |
1991 | { | |
1992 | ONE_MORE_BYTE (c); | |
1993 | } | |
1994 | while (c >= 0xA0); | |
1995 | ||
1996 | if (src - src_base <= 4) | |
1997 | break; | |
1998 | found = CATEGORY_MASK_EMACS_MULE; | |
1999 | if (c == 0x80) | |
2000 | goto repeat; | |
2001 | } | |
2002 | ||
2003 | if (c < 0x80) | |
2004 | { | |
2005 | if (c < 0x20 | |
2006 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
2007 | break; | |
2008 | } | |
2009 | else | |
2010 | { | |
2011 | int more_bytes = emacs_mule_bytes[*src_base] - 1; | |
2012 | ||
2013 | while (more_bytes > 0) | |
2014 | { | |
2015 | ONE_MORE_BYTE (c); | |
2016 | if (c < 0xA0) | |
2017 | { | |
2018 | src--; /* Unread the last byte. */ | |
2019 | break; | |
2020 | } | |
2021 | more_bytes--; | |
2022 | } | |
2023 | if (more_bytes != 0) | |
2024 | break; | |
2025 | found = CATEGORY_MASK_EMACS_MULE; | |
2026 | } | |
2027 | } | |
2028 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
2029 | return 0; | |
2030 | ||
2031 | no_more_source: | |
2032 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | |
2033 | { | |
2034 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
2035 | return 0; | |
2036 | } | |
2037 | detect_info->found |= found; | |
2038 | return 1; | |
2039 | } | |
2040 | ||
2041 | ||
2042 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | |
2043 | character. If CMP_STATUS indicates that we must expect MSEQ or | |
2044 | RULE described above, decode it and return the negative value of | |
685ebdc8 | 2045 | the decoded character or rule. If an invalid byte is found, return |
e951386e KH |
2046 | -1. If SRC is too short, return -2. */ |
2047 | ||
df7492f9 | 2048 | int |
cf84bb53 JB |
2049 | emacs_mule_char (struct coding_system *coding, const unsigned char *src, |
2050 | int *nbytes, int *nchars, int *id, | |
2051 | struct composition_status *cmp_status) | |
df7492f9 | 2052 | { |
8f924df7 KH |
2053 | const unsigned char *src_end = coding->source + coding->src_bytes; |
2054 | const unsigned char *src_base = src; | |
df7492f9 | 2055 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
2056 | struct charset *charset; |
2057 | unsigned code; | |
2058 | int c; | |
2059 | int consumed_chars = 0; | |
e951386e | 2060 | int mseq_found = 0; |
df7492f9 KH |
2061 | |
2062 | ONE_MORE_BYTE (c); | |
065e3595 | 2063 | if (c < 0) |
df7492f9 | 2064 | { |
065e3595 KH |
2065 | c = -c; |
2066 | charset = emacs_mule_charset[0]; | |
2067 | } | |
2068 | else | |
2069 | { | |
4d41e8b7 KH |
2070 | if (c >= 0xA0) |
2071 | { | |
e951386e KH |
2072 | if (cmp_status->state != COMPOSING_NO |
2073 | && cmp_status->old_form) | |
4d41e8b7 | 2074 | { |
e951386e KH |
2075 | if (cmp_status->state == COMPOSING_CHAR) |
2076 | { | |
2077 | if (c == 0xA0) | |
2078 | { | |
2079 | ONE_MORE_BYTE (c); | |
2080 | c -= 0x80; | |
2081 | if (c < 0) | |
2082 | goto invalid_code; | |
2083 | } | |
2084 | else | |
2085 | c -= 0x20; | |
2086 | mseq_found = 1; | |
2087 | } | |
2088 | else | |
2089 | { | |
2090 | *nbytes = src - src_base; | |
2091 | *nchars = consumed_chars; | |
2092 | return -c; | |
2093 | } | |
4d41e8b7 KH |
2094 | } |
2095 | else | |
e951386e | 2096 | goto invalid_code; |
4d41e8b7 KH |
2097 | } |
2098 | ||
065e3595 | 2099 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 2100 | { |
065e3595 | 2101 | case 2: |
df7492f9 KH |
2102 | if (! (charset = emacs_mule_charset[c])) |
2103 | goto invalid_code; | |
2104 | ONE_MORE_BYTE (c); | |
9ffd559c | 2105 | if (c < 0xA0) |
065e3595 | 2106 | goto invalid_code; |
df7492f9 | 2107 | code = c & 0x7F; |
065e3595 KH |
2108 | break; |
2109 | ||
2110 | case 3: | |
2111 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
2112 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
2113 | { | |
2114 | ONE_MORE_BYTE (c); | |
9ffd559c | 2115 | if (c < 0xA0 || ! (charset = emacs_mule_charset[c])) |
065e3595 KH |
2116 | goto invalid_code; |
2117 | ONE_MORE_BYTE (c); | |
9ffd559c | 2118 | if (c < 0xA0) |
065e3595 KH |
2119 | goto invalid_code; |
2120 | code = c & 0x7F; | |
2121 | } | |
2122 | else | |
2123 | { | |
2124 | if (! (charset = emacs_mule_charset[c])) | |
2125 | goto invalid_code; | |
2126 | ONE_MORE_BYTE (c); | |
9ffd559c | 2127 | if (c < 0xA0) |
065e3595 KH |
2128 | goto invalid_code; |
2129 | code = (c & 0x7F) << 8; | |
2130 | ONE_MORE_BYTE (c); | |
9ffd559c | 2131 | if (c < 0xA0) |
065e3595 KH |
2132 | goto invalid_code; |
2133 | code |= c & 0x7F; | |
2134 | } | |
2135 | break; | |
2136 | ||
2137 | case 4: | |
2138 | ONE_MORE_BYTE (c); | |
2139 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
df7492f9 KH |
2140 | goto invalid_code; |
2141 | ONE_MORE_BYTE (c); | |
9ffd559c | 2142 | if (c < 0xA0) |
065e3595 | 2143 | goto invalid_code; |
781d7a48 | 2144 | code = (c & 0x7F) << 8; |
df7492f9 | 2145 | ONE_MORE_BYTE (c); |
9ffd559c | 2146 | if (c < 0xA0) |
065e3595 | 2147 | goto invalid_code; |
df7492f9 | 2148 | code |= c & 0x7F; |
065e3595 | 2149 | break; |
df7492f9 | 2150 | |
065e3595 KH |
2151 | case 1: |
2152 | code = c; | |
2153 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) | |
2154 | ? charset_ascii : charset_eight_bit); | |
2155 | break; | |
df7492f9 | 2156 | |
065e3595 KH |
2157 | default: |
2158 | abort (); | |
2159 | } | |
75f80e63 | 2160 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, code, c); |
065e3595 KH |
2161 | if (c < 0) |
2162 | goto invalid_code; | |
df7492f9 | 2163 | } |
df7492f9 KH |
2164 | *nbytes = src - src_base; |
2165 | *nchars = consumed_chars; | |
ff0dacd7 KH |
2166 | if (id) |
2167 | *id = charset->id; | |
e951386e | 2168 | return (mseq_found ? -c : c); |
df7492f9 KH |
2169 | |
2170 | no_more_source: | |
2171 | return -2; | |
2172 | ||
2173 | invalid_code: | |
2174 | return -1; | |
2175 | } | |
2176 | ||
2177 | ||
e951386e | 2178 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
df7492f9 | 2179 | |
e951386e KH |
2180 | /* Handle these composition sequence ('|': the end of header elements, |
2181 | BYTES and CHARS >= 0xA0): | |
df7492f9 | 2182 | |
e951386e KH |
2183 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
2184 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... | |
2185 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... | |
df7492f9 | 2186 | |
e951386e | 2187 | and these old form: |
1a4990fb | 2188 | |
e951386e KH |
2189 | (4) relative composition: 0x80 | MSEQ ... MSEQ |
2190 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ | |
df7492f9 | 2191 | |
e951386e KH |
2192 | When the starter 0x80 and the following header elements are found, |
2193 | this annotation header is produced. | |
df7492f9 | 2194 | |
e951386e | 2195 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
df7492f9 | 2196 | |
e951386e KH |
2197 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
2198 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). | |
df7492f9 | 2199 | |
e951386e KH |
2200 | Then, upon reading the following elements, these codes are produced |
2201 | until the composition end is found: | |
df7492f9 | 2202 | |
e951386e KH |
2203 | (1) CHAR ... CHAR |
2204 | (2) ALT ... ALT CHAR ... CHAR | |
2205 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR | |
2206 | (4) CHAR ... CHAR | |
2207 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
4ed46869 | 2208 | |
e951386e KH |
2209 | When the composition end is found, LENGTH and NCHARS in the |
2210 | annotation header is updated as below: | |
b73bfc1c | 2211 | |
e951386e KH |
2212 | (1) LENGTH: unchanged, NCHARS: unchanged |
2213 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2214 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2215 | (4) LENGTH: unchanged, NCHARS: number of CHARs | |
2216 | (5) LENGTH: unchanged, NCHARS: number of CHARs | |
df7492f9 | 2217 | |
e951386e KH |
2218 | If an error is found while composing, the annotation header is |
2219 | changed to the original composition header (plus filler -1s) as | |
2220 | below: | |
2221 | ||
2222 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] | |
2223 | (5) [ 0x80 0xFF -1 -1- -1 ] | |
2224 | ||
2225 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
2226 | byte sequence as below: | |
2227 | o the original byte sequence is B: [ B -1 ] | |
2228 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
2229 | ||
2230 | Most of the routines are implemented by macros because many | |
2231 | variables and labels in the caller decode_coding_emacs_mule must be | |
2232 | accessible, and they are usually called just once (thus doesn't | |
2233 | increase the size of compiled object). */ | |
2234 | ||
2235 | /* Decode a composition rule represented by C as a component of | |
2236 | composition sequence of Emacs 20 style. Set RULE to the decoded | |
2237 | rule. */ | |
2238 | ||
2239 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ | |
df7492f9 | 2240 | do { \ |
e951386e KH |
2241 | int gref, nref; \ |
2242 | \ | |
4d41e8b7 | 2243 | c -= 0xA0; \ |
df7492f9 KH |
2244 | if (c < 0 || c >= 81) \ |
2245 | goto invalid_code; \ | |
df7492f9 | 2246 | gref = c / 9, nref = c % 9; \ |
e951386e KH |
2247 | if (gref == 4) gref = 10; \ |
2248 | if (nref == 4) nref = 10; \ | |
2249 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
df7492f9 KH |
2250 | } while (0) |
2251 | ||
2252 | ||
e951386e KH |
2253 | /* Decode a composition rule represented by C and the following byte |
2254 | at SRC as a component of composition sequence of Emacs 21 style. | |
2255 | Set RULE to the decoded rule. */ | |
781d7a48 | 2256 | |
e951386e | 2257 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
781d7a48 KH |
2258 | do { \ |
2259 | int gref, nref; \ | |
e951386e KH |
2260 | \ |
2261 | gref = c - 0x20; \ | |
2262 | if (gref < 0 || gref >= 81) \ | |
781d7a48 | 2263 | goto invalid_code; \ |
e951386e KH |
2264 | ONE_MORE_BYTE (c); \ |
2265 | nref = c - 0x20; \ | |
2266 | if (nref < 0 || nref >= 81) \ | |
781d7a48 | 2267 | goto invalid_code; \ |
e951386e | 2268 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
781d7a48 KH |
2269 | } while (0) |
2270 | ||
2271 | ||
e951386e KH |
2272 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
2273 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | |
2274 | byte length of this composition information, CHARS is the number of | |
2275 | characters composed by this composition. */ | |
2276 | ||
2277 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | |
aa72b389 | 2278 | do { \ |
781d7a48 KH |
2279 | enum composition_method method = c - 0xF2; \ |
2280 | int *charbuf_base = charbuf; \ | |
df7492f9 | 2281 | int nbytes, nchars; \ |
e951386e | 2282 | \ |
df7492f9 | 2283 | ONE_MORE_BYTE (c); \ |
065e3595 KH |
2284 | if (c < 0) \ |
2285 | goto invalid_code; \ | |
df7492f9 | 2286 | nbytes = c - 0xA0; \ |
e951386e | 2287 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
df7492f9 KH |
2288 | goto invalid_code; \ |
2289 | ONE_MORE_BYTE (c); \ | |
2290 | nchars = c - 0xA0; \ | |
e951386e KH |
2291 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
2292 | goto invalid_code; \ | |
2293 | cmp_status->old_form = 0; \ | |
2294 | cmp_status->method = method; \ | |
2295 | if (method == COMPOSITION_RELATIVE) \ | |
2296 | cmp_status->state = COMPOSING_CHAR; \ | |
2297 | else \ | |
2298 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ | |
2299 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2300 | cmp_status->nchars = nchars; \ | |
2301 | cmp_status->ncomps = nbytes - 4; \ | |
2302 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ | |
aa72b389 | 2303 | } while (0) |
93dec019 | 2304 | |
aa72b389 | 2305 | |
e951386e KH |
2306 | /* Start of Emacs 20 style format for relative composition. */ |
2307 | ||
2308 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ | |
2309 | do { \ | |
2310 | cmp_status->old_form = 1; \ | |
2311 | cmp_status->method = COMPOSITION_RELATIVE; \ | |
2312 | cmp_status->state = COMPOSING_CHAR; \ | |
2313 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2314 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2315 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
2316 | } while (0) | |
2317 | ||
2318 | ||
2319 | /* Start of Emacs 20 style format for rule-base composition. */ | |
2320 | ||
2321 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | |
2322 | do { \ | |
2323 | cmp_status->old_form = 1; \ | |
2324 | cmp_status->method = COMPOSITION_WITH_RULE; \ | |
2325 | cmp_status->state = COMPOSING_CHAR; \ | |
2326 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2327 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2328 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
df7492f9 KH |
2329 | } while (0) |
2330 | ||
2331 | ||
e951386e KH |
2332 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ |
2333 | do { \ | |
2334 | const unsigned char *current_src = src; \ | |
2335 | \ | |
2336 | ONE_MORE_BYTE (c); \ | |
2337 | if (c < 0) \ | |
2338 | goto invalid_code; \ | |
2339 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | |
2340 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | |
2341 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | |
2342 | else if (c < 0xA0) \ | |
2343 | goto invalid_code; \ | |
2344 | else if (c < 0xC0) \ | |
2345 | { \ | |
2346 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | |
2347 | /* Re-read C as a composition component. */ \ | |
2348 | src = current_src; \ | |
2349 | } \ | |
2350 | else if (c == 0xFF) \ | |
2351 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | |
2352 | else \ | |
2353 | goto invalid_code; \ | |
2354 | } while (0) | |
2355 | ||
2356 | #define EMACS_MULE_COMPOSITION_END() \ | |
df7492f9 | 2357 | do { \ |
e951386e | 2358 | int idx = - cmp_status->length; \ |
4d41e8b7 | 2359 | \ |
e951386e KH |
2360 | if (cmp_status->old_form) \ |
2361 | charbuf[idx + 2] = cmp_status->nchars; \ | |
2362 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ | |
2363 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ | |
2364 | cmp_status->state = COMPOSING_NO; \ | |
2365 | } while (0) | |
2366 | ||
2367 | ||
2368 | static int | |
cf84bb53 JB |
2369 | emacs_mule_finish_composition (int *charbuf, |
2370 | struct composition_status *cmp_status) | |
e951386e KH |
2371 | { |
2372 | int idx = - cmp_status->length; | |
2373 | int new_chars; | |
2374 | ||
2375 | if (cmp_status->old_form && cmp_status->nchars > 0) | |
2376 | { | |
2377 | charbuf[idx + 2] = cmp_status->nchars; | |
2378 | new_chars = 0; | |
2379 | if (cmp_status->method == COMPOSITION_WITH_RULE | |
2380 | && cmp_status->state == COMPOSING_CHAR) | |
2381 | { | |
2382 | /* The last rule was invalid. */ | |
2383 | int rule = charbuf[-1] + 0xA0; | |
2384 | ||
2385 | charbuf[-2] = BYTE8_TO_CHAR (rule); | |
2386 | charbuf[-1] = -1; | |
2387 | new_chars = 1; | |
2388 | } | |
2389 | } | |
2390 | else | |
2391 | { | |
2392 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | |
2393 | ||
2394 | if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2395 | { | |
2396 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | |
2397 | charbuf[idx++] = -3; | |
2398 | charbuf[idx++] = 0; | |
2399 | new_chars = 1; | |
2400 | } | |
2401 | else | |
2402 | { | |
2403 | int nchars = charbuf[idx + 1] + 0xA0; | |
2404 | int nbytes = charbuf[idx + 2] + 0xA0; | |
2405 | ||
2406 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | |
2407 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | |
2408 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | |
2409 | charbuf[idx++] = -1; | |
2410 | new_chars = 4; | |
2411 | } | |
2412 | } | |
2413 | cmp_status->state = COMPOSING_NO; | |
2414 | return new_chars; | |
2415 | } | |
2416 | ||
2417 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | |
2418 | do { \ | |
2419 | if (cmp_status->state != COMPOSING_NO) \ | |
2420 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | |
df7492f9 KH |
2421 | } while (0) |
2422 | ||
aa72b389 KH |
2423 | |
2424 | static void | |
971de7fb | 2425 | decode_coding_emacs_mule (struct coding_system *coding) |
aa72b389 | 2426 | { |
8f924df7 KH |
2427 | const unsigned char *src = coding->source + coding->consumed; |
2428 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2429 | const unsigned char *src_base; | |
69a80ea3 | 2430 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
2431 | /* We may produce two annocations (charset and composition) in one |
2432 | loop and one more charset annocation at the end. */ | |
69a80ea3 | 2433 | int *charbuf_end |
df80c7f0 | 2434 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
df7492f9 | 2435 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2436 | int multibytep = coding->src_multibyte; |
24a73b0a | 2437 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2438 | int char_offset = coding->produced_char; |
2439 | int last_offset = char_offset; | |
2440 | int last_id = charset_ascii; | |
0a9564cb EZ |
2441 | int eol_crlf = |
2442 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 2443 | int byte_after_cr = -1; |
e951386e | 2444 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; |
aa72b389 | 2445 | |
24a73b0a | 2446 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2447 | |
e951386e KH |
2448 | if (cmp_status->state != COMPOSING_NO) |
2449 | { | |
2450 | int i; | |
2451 | ||
2452 | for (i = 0; i < cmp_status->length; i++) | |
2453 | *charbuf++ = cmp_status->carryover[i]; | |
2454 | coding->annotated = 1; | |
2455 | } | |
2456 | ||
aa72b389 KH |
2457 | while (1) |
2458 | { | |
e951386e | 2459 | int c, id; |
df7492f9 | 2460 | |
aa72b389 | 2461 | src_base = src; |
df7492f9 KH |
2462 | consumed_chars_base = consumed_chars; |
2463 | ||
2464 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2465 | { |
2466 | if (byte_after_cr >= 0) | |
2467 | src_base--; | |
2468 | break; | |
2469 | } | |
aa72b389 | 2470 | |
119852e7 KH |
2471 | if (byte_after_cr >= 0) |
2472 | c = byte_after_cr, byte_after_cr = -1; | |
2473 | else | |
2474 | ONE_MORE_BYTE (c); | |
e951386e KH |
2475 | |
2476 | if (c < 0 || c == 0x80) | |
065e3595 | 2477 | { |
e951386e KH |
2478 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
2479 | if (c < 0) | |
2480 | { | |
2481 | *charbuf++ = -c; | |
2482 | char_offset++; | |
2483 | } | |
2484 | else | |
2485 | DECODE_EMACS_MULE_COMPOSITION_START (); | |
2486 | continue; | |
065e3595 | 2487 | } |
e951386e KH |
2488 | |
2489 | if (c < 0x80) | |
aa72b389 | 2490 | { |
119852e7 KH |
2491 | if (eol_crlf && c == '\r') |
2492 | ONE_MORE_BYTE (byte_after_cr); | |
e951386e KH |
2493 | id = charset_ascii; |
2494 | if (cmp_status->state != COMPOSING_NO) | |
2495 | { | |
2496 | if (cmp_status->old_form) | |
2497 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2498 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2499 | cmp_status->ncomps--; | |
2500 | } | |
2501 | } | |
2502 | else | |
2503 | { | |
2504 | int nchars, nbytes; | |
75f80e63 EZ |
2505 | /* emacs_mule_char can load a charset map from a file, which |
2506 | allocates a large structure and might cause buffer text | |
2507 | to be relocated as result. Thus, we need to remember the | |
2508 | original pointer to buffer text, and fixup all related | |
2509 | pointers after the call. */ | |
2510 | const unsigned char *orig = coding->source; | |
2511 | EMACS_INT offset; | |
e951386e KH |
2512 | |
2513 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, | |
2514 | cmp_status); | |
75f80e63 EZ |
2515 | offset = coding->source - orig; |
2516 | if (offset) | |
2517 | { | |
2518 | src += offset; | |
2519 | src_base += offset; | |
2520 | src_end += offset; | |
2521 | } | |
e951386e KH |
2522 | if (c < 0) |
2523 | { | |
2524 | if (c == -1) | |
2525 | goto invalid_code; | |
2526 | if (c == -2) | |
2527 | break; | |
2528 | } | |
2529 | src = src_base + nbytes; | |
2530 | consumed_chars = consumed_chars_base + nchars; | |
2531 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2532 | cmp_status->ncomps -= nchars; | |
2533 | } | |
2534 | ||
2535 | /* Now if C >= 0, we found a normally encoded characer, if C < | |
2536 | 0, we found an old-style composition component character or | |
2537 | rule. */ | |
2538 | ||
2539 | if (cmp_status->state == COMPOSING_NO) | |
2540 | { | |
2541 | if (last_id != id) | |
2542 | { | |
2543 | if (last_id != charset_ascii) | |
2544 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, | |
2545 | last_id); | |
2546 | last_id = id; | |
2547 | last_offset = char_offset; | |
2548 | } | |
df7492f9 KH |
2549 | *charbuf++ = c; |
2550 | char_offset++; | |
aa72b389 | 2551 | } |
e951386e | 2552 | else if (cmp_status->state == COMPOSING_CHAR) |
df7492f9 | 2553 | { |
e951386e KH |
2554 | if (cmp_status->old_form) |
2555 | { | |
2556 | if (c >= 0) | |
2557 | { | |
2558 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2559 | *charbuf++ = c; | |
2560 | char_offset++; | |
2561 | } | |
2562 | else | |
2563 | { | |
2564 | *charbuf++ = -c; | |
2565 | cmp_status->nchars++; | |
2566 | cmp_status->length++; | |
2567 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | |
2568 | EMACS_MULE_COMPOSITION_END (); | |
2569 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2570 | cmp_status->state = COMPOSING_RULE; | |
2571 | } | |
2572 | } | |
df7492f9 | 2573 | else |
e951386e KH |
2574 | { |
2575 | *charbuf++ = c; | |
2576 | cmp_status->length++; | |
2577 | cmp_status->nchars--; | |
2578 | if (cmp_status->nchars == 0) | |
2579 | EMACS_MULE_COMPOSITION_END (); | |
2580 | } | |
df7492f9 | 2581 | } |
e951386e | 2582 | else if (cmp_status->state == COMPOSING_RULE) |
df7492f9 | 2583 | { |
e951386e | 2584 | int rule; |
ff0dacd7 | 2585 | |
e951386e | 2586 | if (c >= 0) |
df7492f9 | 2587 | { |
e951386e KH |
2588 | EMACS_MULE_COMPOSITION_END (); |
2589 | *charbuf++ = c; | |
2590 | char_offset++; | |
df7492f9 | 2591 | } |
e951386e | 2592 | else |
ff0dacd7 | 2593 | { |
e951386e KH |
2594 | c = -c; |
2595 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | |
2596 | if (rule < 0) | |
2597 | goto invalid_code; | |
2598 | *charbuf++ = -2; | |
2599 | *charbuf++ = rule; | |
2600 | cmp_status->length += 2; | |
2601 | cmp_status->state = COMPOSING_CHAR; | |
ff0dacd7 | 2602 | } |
e951386e KH |
2603 | } |
2604 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | |
2605 | { | |
df7492f9 | 2606 | *charbuf++ = c; |
e951386e KH |
2607 | cmp_status->length++; |
2608 | if (cmp_status->ncomps == 0) | |
2609 | cmp_status->state = COMPOSING_CHAR; | |
2610 | else if (cmp_status->ncomps > 0) | |
2611 | { | |
2612 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | |
2613 | cmp_status->state = COMPOSING_COMPONENT_RULE; | |
2614 | } | |
2615 | else | |
2616 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 2617 | } |
e951386e KH |
2618 | else /* COMPOSING_COMPONENT_RULE */ |
2619 | { | |
2620 | int rule; | |
2621 | ||
2622 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | |
2623 | if (rule < 0) | |
2624 | goto invalid_code; | |
2625 | *charbuf++ = -2; | |
2626 | *charbuf++ = rule; | |
2627 | cmp_status->length += 2; | |
2628 | cmp_status->ncomps--; | |
2629 | if (cmp_status->ncomps > 0) | |
2630 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | |
2631 | else | |
2632 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2633 | } | |
2634 | continue; | |
2635 | ||
2636 | retry: | |
2637 | src = src_base; | |
2638 | consumed_chars = consumed_chars_base; | |
df7492f9 KH |
2639 | continue; |
2640 | ||
2641 | invalid_code: | |
e951386e | 2642 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
df7492f9 KH |
2643 | src = src_base; |
2644 | consumed_chars = consumed_chars_base; | |
2645 | ONE_MORE_BYTE (c); | |
2646 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2647 | char_offset++; |
df7492f9 KH |
2648 | coding->errors++; |
2649 | } | |
2650 | ||
2651 | no_more_source: | |
e951386e KH |
2652 | if (cmp_status->state != COMPOSING_NO) |
2653 | { | |
2654 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
2655 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2656 | else | |
2657 | { | |
2658 | int i; | |
2659 | ||
2660 | charbuf -= cmp_status->length; | |
2661 | for (i = 0; i < cmp_status->length; i++) | |
2662 | cmp_status->carryover[i] = charbuf[i]; | |
2663 | } | |
2664 | } | |
ff0dacd7 | 2665 | if (last_id != charset_ascii) |
69a80ea3 | 2666 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2667 | coding->consumed_char += consumed_chars_base; |
2668 | coding->consumed = src_base - coding->source; | |
2669 | coding->charbuf_used = charbuf - coding->charbuf; | |
2670 | } | |
2671 | ||
2672 | ||
2673 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2674 | do { \ | |
2675 | if (id < 0xA0) \ | |
2676 | codes[0] = id, codes[1] = 0; \ | |
2677 | else if (id < 0xE0) \ | |
2678 | codes[0] = 0x9A, codes[1] = id; \ | |
2679 | else if (id < 0xF0) \ | |
2680 | codes[0] = 0x9B, codes[1] = id; \ | |
2681 | else if (id < 0xF5) \ | |
2682 | codes[0] = 0x9C, codes[1] = id; \ | |
2683 | else \ | |
2684 | codes[0] = 0x9D, codes[1] = id; \ | |
2685 | } while (0); | |
2686 | ||
aa72b389 | 2687 | |
df7492f9 | 2688 | static int |
971de7fb | 2689 | encode_coding_emacs_mule (struct coding_system *coding) |
df7492f9 KH |
2690 | { |
2691 | int multibytep = coding->dst_multibyte; | |
2692 | int *charbuf = coding->charbuf; | |
2693 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2694 | unsigned char *dst = coding->destination + coding->produced; | |
2695 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2696 | int safe_room = 8; | |
df7492f9 | 2697 | int produced_chars = 0; |
24a73b0a | 2698 | Lisp_Object attrs, charset_list; |
df7492f9 | 2699 | int c; |
ff0dacd7 | 2700 | int preferred_charset_id = -1; |
df7492f9 | 2701 | |
24a73b0a | 2702 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2703 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2704 | { | |
2705 | CODING_ATTR_CHARSET_LIST (attrs) | |
2706 | = charset_list = Vemacs_mule_charset_list; | |
2707 | } | |
df7492f9 KH |
2708 | |
2709 | while (charbuf < charbuf_end) | |
2710 | { | |
2711 | ASSURE_DESTINATION (safe_room); | |
2712 | c = *charbuf++; | |
ff0dacd7 KH |
2713 | |
2714 | if (c < 0) | |
2715 | { | |
2716 | /* Handle an annotation. */ | |
2717 | switch (*charbuf) | |
2718 | { | |
2719 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2720 | /* Not yet implemented. */ | |
2721 | break; | |
2722 | case CODING_ANNOTATE_CHARSET_MASK: | |
2723 | preferred_charset_id = charbuf[3]; | |
2724 | if (preferred_charset_id >= 0 | |
2725 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2726 | charset_list))) | |
2727 | preferred_charset_id = -1; | |
2728 | break; | |
2729 | default: | |
2730 | abort (); | |
2731 | } | |
2732 | charbuf += -c - 1; | |
2733 | continue; | |
2734 | } | |
2735 | ||
df7492f9 KH |
2736 | if (ASCII_CHAR_P (c)) |
2737 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2738 | else if (CHAR_BYTE8_P (c)) |
2739 | { | |
2740 | c = CHAR_TO_BYTE8 (c); | |
2741 | EMIT_ONE_BYTE (c); | |
2742 | } | |
df7492f9 | 2743 | else |
aa72b389 | 2744 | { |
df7492f9 KH |
2745 | struct charset *charset; |
2746 | unsigned code; | |
2747 | int dimension; | |
2748 | int emacs_mule_id; | |
2749 | unsigned char leading_codes[2]; | |
2750 | ||
ff0dacd7 KH |
2751 | if (preferred_charset_id >= 0) |
2752 | { | |
2753 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
905ca9d2 KH |
2754 | if (CHAR_CHARSET_P (c, charset)) |
2755 | code = ENCODE_CHAR (charset, c); | |
2756 | else | |
2757 | charset = char_charset (c, charset_list, &code); | |
ff0dacd7 KH |
2758 | } |
2759 | else | |
2760 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2761 | if (! charset) |
2762 | { | |
2763 | c = coding->default_char; | |
2764 | if (ASCII_CHAR_P (c)) | |
2765 | { | |
2766 | EMIT_ONE_ASCII_BYTE (c); | |
2767 | continue; | |
2768 | } | |
2769 | charset = char_charset (c, charset_list, &code); | |
2770 | } | |
2771 | dimension = CHARSET_DIMENSION (charset); | |
2772 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2773 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2774 | EMIT_ONE_BYTE (leading_codes[0]); | |
2775 | if (leading_codes[1]) | |
2776 | EMIT_ONE_BYTE (leading_codes[1]); | |
2777 | if (dimension == 1) | |
1fa663f9 | 2778 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2779 | else |
df7492f9 | 2780 | { |
1fa663f9 | 2781 | code |= 0x8080; |
df7492f9 KH |
2782 | EMIT_ONE_BYTE (code >> 8); |
2783 | EMIT_ONE_BYTE (code & 0xFF); | |
2784 | } | |
aa72b389 | 2785 | } |
aa72b389 | 2786 | } |
065e3595 | 2787 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2788 | coding->produced_char += produced_chars; |
2789 | coding->produced = dst - coding->destination; | |
2790 | return 0; | |
aa72b389 | 2791 | } |
b73bfc1c | 2792 | |
4ed46869 | 2793 | \f |
df7492f9 | 2794 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2795 | |
2796 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2797 | Since the intention of this note is to help understand the |
5a936b46 | 2798 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2799 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2800 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2801 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2802 | |
2803 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2804 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2805 | is encoded using bytes less than 128. This may make the encoded |
2806 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2807 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2808 | Significant Bit). |
b73bfc1c | 2809 | |
cfb43547 DL |
2810 | There are two kinds of character sets: control character sets and |
2811 | graphic character sets. The former contain control characters such | |
4ed46869 | 2812 | as `newline' and `escape' to provide control functions (control |
39787efd | 2813 | functions are also provided by escape sequences). The latter |
cfb43547 | 2814 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2815 | two control character sets and many graphic character sets. |
2816 | ||
2817 | Graphic character sets are classified into one of the following | |
39787efd KH |
2818 | four classes, according to the number of bytes (DIMENSION) and |
2819 | number of characters in one dimension (CHARS) of the set: | |
2820 | - DIMENSION1_CHARS94 | |
2821 | - DIMENSION1_CHARS96 | |
2822 | - DIMENSION2_CHARS94 | |
2823 | - DIMENSION2_CHARS96 | |
2824 | ||
2825 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2826 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2827 | hereafter). The <F> of each character set is decided by ECMA(*) |
2828 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2829 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2830 | |
2831 | Note (*): ECMA = European Computer Manufacturers Association | |
2832 | ||
cfb43547 | 2833 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2834 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2835 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2836 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2837 | o DIMENSION2_CHARS96 -- none for the moment | |
2838 | ||
39787efd | 2839 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2840 | C0 [0x00..0x1F] -- control character plane 0 |
2841 | GL [0x20..0x7F] -- graphic character plane 0 | |
2842 | C1 [0x80..0x9F] -- control character plane 1 | |
2843 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2844 | ||
2845 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2846 | C1 by an escape sequence. The most common case is that: |
2847 | - ISO646's control character set is designated/invoked to C0, and | |
2848 | - ISO6429's control character set is designated/invoked to C1, | |
2849 | and usually these designations/invocations are omitted in encoded | |
2850 | text. In a 7-bit environment, only C0 can be used, and a control | |
2851 | character for C1 is encoded by an appropriate escape sequence to | |
2852 | fit into the environment. All control characters for C1 are | |
2853 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2854 | |
2855 | A graphic character set is at first designated to one of four | |
2856 | graphic registers (G0 through G3), then these graphic registers are | |
2857 | invoked to GL or GR. These designations and invocations can be | |
2858 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2859 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2860 | these invocations and designations are omitted in encoded text. | |
2861 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2862 | |
39787efd KH |
2863 | When a graphic character set of CHARS94 is invoked to GL, codes |
2864 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2865 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2866 | be used. | |
4ed46869 KH |
2867 | |
2868 | There are two ways of invocation: locking-shift and single-shift. | |
2869 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2870 | invocation, whereas with single-shift, the invocation affects the |
2871 | following character only and doesn't affect the locking-shift | |
2872 | state. Invocations are done by the following control characters or | |
2873 | escape sequences: | |
4ed46869 KH |
2874 | |
2875 | ---------------------------------------------------------------------- | |
39787efd | 2876 | abbrev function cntrl escape seq description |
4ed46869 | 2877 | ---------------------------------------------------------------------- |
39787efd KH |
2878 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2879 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2880 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2881 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2882 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2883 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2884 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2885 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2886 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2887 | ---------------------------------------------------------------------- |
39787efd KH |
2888 | (*) These are not used by any known coding system. |
2889 | ||
2890 | Control characters for these functions are defined by macros | |
2891 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2892 | |
39787efd | 2893 | Designations are done by the following escape sequences: |
4ed46869 KH |
2894 | ---------------------------------------------------------------------- |
2895 | escape sequence description | |
2896 | ---------------------------------------------------------------------- | |
2897 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2898 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2899 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2900 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2901 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2902 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2903 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2904 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2905 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2906 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2907 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2908 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2909 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2910 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2911 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2912 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2913 | ---------------------------------------------------------------------- | |
2914 | ||
2915 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2916 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2917 | |
2918 | Note (*): Although these designations are not allowed in ISO2022, | |
2919 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2920 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2921 | 7-bit environment, non-locking-shift, and non-single-shift. |
2922 | ||
2923 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2924 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2925 | |
cfb43547 | 2926 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2927 | same multilingual text in ISO2022. Actually, there exist many |
2928 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2929 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2930 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2931 | localized platforms), and all of these are variants of ISO2022. |
2932 | ||
2933 | In addition to the above, Emacs handles two more kinds of escape | |
2934 | sequences: ISO6429's direction specification and Emacs' private | |
2935 | sequence for specifying character composition. | |
2936 | ||
39787efd | 2937 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2938 | o CSI ']' -- end of the current direction |
2939 | o CSI '0' ']' -- end of the current direction | |
2940 | o CSI '1' ']' -- start of left-to-right text | |
2941 | o CSI '2' ']' -- start of right-to-left text | |
2942 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2943 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2944 | ||
2945 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2946 | o ESC '0' -- start relative composition |
2947 | o ESC '1' -- end composition | |
2948 | o ESC '2' -- start rule-base composition (*) | |
2949 | o ESC '3' -- start relative composition with alternate chars (**) | |
2950 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2951 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2952 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2953 | |
5a936b46 DL |
2954 | (*) This form is used only in Emacs 20.7 and older versions, |
2955 | but newer versions can safely decode it. | |
cfb43547 | 2956 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2957 | and older versions can't decode it. |
ec6d2bb8 | 2958 | |
cfb43547 | 2959 | Here's a list of example usages of these composition escape |
b73bfc1c | 2960 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2961 | |
b73bfc1c | 2962 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2963 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2964 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2965 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2966 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2967 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2968 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2969 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2970 | |
2971 | enum iso_code_class_type iso_code_class[256]; | |
2972 | ||
df7492f9 KH |
2973 | #define SAFE_CHARSET_P(coding, id) \ |
2974 | ((id) <= (coding)->max_charset_id \ | |
1b3b981b | 2975 | && (coding)->safe_charsets[id] != 255) |
df7492f9 KH |
2976 | |
2977 | ||
2978 | #define SHIFT_OUT_OK(category) \ | |
2979 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2980 | ||
2981 | static void | |
971de7fb | 2982 | setup_iso_safe_charsets (Lisp_Object attrs) |
df7492f9 KH |
2983 | { |
2984 | Lisp_Object charset_list, safe_charsets; | |
2985 | Lisp_Object request; | |
2986 | Lisp_Object reg_usage; | |
2987 | Lisp_Object tail; | |
2988 | int reg94, reg96; | |
2989 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2990 | int max_charset_id; | |
2991 | ||
2992 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2993 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2994 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2995 | { | |
2996 | CODING_ATTR_CHARSET_LIST (attrs) | |
2997 | = charset_list = Viso_2022_charset_list; | |
2998 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2999 | } | |
3000 | ||
3001 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
3002 | return; | |
3003 | ||
3004 | max_charset_id = 0; | |
3005 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
3006 | { | |
3007 | int id = XINT (XCAR (tail)); | |
3008 | if (max_charset_id < id) | |
3009 | max_charset_id = id; | |
3010 | } | |
d46c5b12 | 3011 | |
1b3b981b AS |
3012 | safe_charsets = make_uninit_string (max_charset_id + 1); |
3013 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
3014 | request = AREF (attrs, coding_attr_iso_request); |
3015 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
3016 | reg94 = XINT (XCAR (reg_usage)); | |
3017 | reg96 = XINT (XCDR (reg_usage)); | |
3018 | ||
3019 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
3020 | { | |
3021 | Lisp_Object id; | |
3022 | Lisp_Object reg; | |
3023 | struct charset *charset; | |
3024 | ||
3025 | id = XCAR (tail); | |
3026 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 3027 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 3028 | if (! NILP (reg)) |
8f924df7 | 3029 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
3030 | else if (charset->iso_chars_96) |
3031 | { | |
3032 | if (reg96 < 4) | |
8f924df7 | 3033 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
3034 | } |
3035 | else | |
3036 | { | |
3037 | if (reg94 < 4) | |
8f924df7 | 3038 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
3039 | } |
3040 | } | |
3041 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
3042 | } | |
d46c5b12 | 3043 | |
b6871cc7 | 3044 | |
4ed46869 | 3045 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
3046 | Check if a text is encoded in one of ISO-2022 based codig systems. |
3047 | If it is, return 1, else return 0. */ | |
4ed46869 | 3048 | |
0a28aafb | 3049 | static int |
cf84bb53 JB |
3050 | detect_coding_iso_2022 (struct coding_system *coding, |
3051 | struct coding_detection_info *detect_info) | |
4ed46869 | 3052 | { |
8f924df7 KH |
3053 | const unsigned char *src = coding->source, *src_base = src; |
3054 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 3055 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 3056 | int single_shifting = 0; |
df7492f9 KH |
3057 | int id; |
3058 | int c, c1; | |
3059 | int consumed_chars = 0; | |
3060 | int i; | |
ff0dacd7 KH |
3061 | int rejected = 0; |
3062 | int found = 0; | |
cee53ed4 | 3063 | int composition_count = -1; |
ff0dacd7 KH |
3064 | |
3065 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
3066 | |
3067 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
3068 | { | |
3069 | struct coding_system *this = &(coding_categories[i]); | |
3070 | Lisp_Object attrs, val; | |
3071 | ||
c6b278e7 KH |
3072 | if (this->id < 0) |
3073 | continue; | |
df7492f9 KH |
3074 | attrs = CODING_ID_ATTRS (this->id); |
3075 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
1b3b981b | 3076 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list)) |
df7492f9 KH |
3077 | setup_iso_safe_charsets (attrs); |
3078 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 3079 | this->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 3080 | this->safe_charsets = SDATA (val); |
df7492f9 KH |
3081 | } |
3082 | ||
3083 | /* A coding system of this category is always ASCII compatible. */ | |
3084 | src += coding->head_ascii; | |
3f003981 | 3085 | |
ff0dacd7 | 3086 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 3087 | { |
065e3595 | 3088 | src_base = src; |
df7492f9 | 3089 | ONE_MORE_BYTE (c); |
4ed46869 KH |
3090 | switch (c) |
3091 | { | |
3092 | case ISO_CODE_ESC: | |
74383408 KH |
3093 | if (inhibit_iso_escape_detection) |
3094 | break; | |
f46869e4 | 3095 | single_shifting = 0; |
df7492f9 | 3096 | ONE_MORE_BYTE (c); |
d46c5b12 | 3097 | if (c >= '(' && c <= '/') |
4ed46869 | 3098 | { |
bf9cdd4e | 3099 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 3100 | ONE_MORE_BYTE (c1); |
d46c5b12 | 3101 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 3102 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
3103 | /* Invalid designation sequence. Just ignore. */ |
3104 | break; | |
bf9cdd4e KH |
3105 | } |
3106 | else if (c == '$') | |
3107 | { | |
3108 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 3109 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
3110 | if (c >= '@' && c <= 'B') |
3111 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 3112 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 3113 | else if (c >= '(' && c <= '/') |
bcf26d6a | 3114 | { |
df7492f9 | 3115 | ONE_MORE_BYTE (c1); |
d46c5b12 | 3116 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 3117 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
3118 | /* Invalid designation sequence. Just ignore. */ |
3119 | break; | |
bcf26d6a | 3120 | } |
bf9cdd4e | 3121 | else |
ff0dacd7 | 3122 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
3123 | break; |
3124 | } | |
ae9ff118 | 3125 | else if (c == 'N' || c == 'O') |
d46c5b12 | 3126 | { |
ae9ff118 | 3127 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
3128 | single_shifting = 1; |
3129 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 3130 | break; |
4ed46869 | 3131 | } |
cee53ed4 KH |
3132 | else if (c == '1') |
3133 | { | |
3134 | /* End of composition. */ | |
3135 | if (composition_count < 0 | |
3136 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
3137 | /* Invalid */ | |
3138 | break; | |
3139 | composition_count = -1; | |
3140 | found |= CATEGORY_MASK_ISO; | |
3141 | } | |
ec6d2bb8 KH |
3142 | else if (c >= '0' && c <= '4') |
3143 | { | |
3144 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 3145 | composition_count = 0; |
ec6d2bb8 KH |
3146 | break; |
3147 | } | |
bf9cdd4e | 3148 | else |
df7492f9 | 3149 | { |
ff0dacd7 | 3150 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
3151 | break; |
3152 | } | |
d46c5b12 KH |
3153 | |
3154 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 3155 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
3156 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
3157 | id)) | |
ff0dacd7 | 3158 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 3159 | else |
ff0dacd7 | 3160 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
3161 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
3162 | id)) | |
ff0dacd7 | 3163 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 3164 | else |
ff0dacd7 | 3165 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
3166 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
3167 | id)) | |
ff0dacd7 | 3168 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 3169 | else |
ff0dacd7 | 3170 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
3171 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
3172 | id)) | |
ff0dacd7 | 3173 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 3174 | else |
ff0dacd7 | 3175 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
3176 | break; |
3177 | ||
4ed46869 | 3178 | case ISO_CODE_SO: |
d46c5b12 | 3179 | case ISO_CODE_SI: |
ff0dacd7 | 3180 | /* Locking shift out/in. */ |
74383408 KH |
3181 | if (inhibit_iso_escape_detection) |
3182 | break; | |
f46869e4 | 3183 | single_shifting = 0; |
ff0dacd7 | 3184 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
3185 | break; |
3186 | ||
4ed46869 | 3187 | case ISO_CODE_CSI: |
ff0dacd7 | 3188 | /* Control sequence introducer. */ |
f46869e4 | 3189 | single_shifting = 0; |
ff0dacd7 KH |
3190 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3191 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3192 | goto check_extra_latin; | |
3193 | ||
4ed46869 KH |
3194 | case ISO_CODE_SS2: |
3195 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
3196 | /* Single shift. */ |
3197 | if (inhibit_iso_escape_detection) | |
3198 | break; | |
75e2a253 | 3199 | single_shifting = 0; |
ff0dacd7 KH |
3200 | rejected |= CATEGORY_MASK_ISO_7BIT; |
3201 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3202 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 3203 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
3204 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
3205 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
3206 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
3207 | if (single_shifting) | |
3208 | break; | |
ff0dacd7 | 3209 | goto check_extra_latin; |
4ed46869 KH |
3210 | |
3211 | default: | |
065e3595 KH |
3212 | if (c < 0) |
3213 | continue; | |
4ed46869 | 3214 | if (c < 0x80) |
f46869e4 | 3215 | { |
cee53ed4 KH |
3216 | if (composition_count >= 0) |
3217 | composition_count++; | |
f46869e4 KH |
3218 | single_shifting = 0; |
3219 | break; | |
3220 | } | |
ff0dacd7 | 3221 | if (c >= 0xA0) |
c4825358 | 3222 | { |
ff0dacd7 KH |
3223 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3224 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 3225 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
3226 | 0xA0..0FF. If the byte length is even, we include |
3227 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
3228 | only when we are not single shifting. */ | |
3229 | if (! single_shifting | |
3230 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 3231 | { |
e17de821 | 3232 | int i = 1; |
b73bfc1c KH |
3233 | while (src < src_end) |
3234 | { | |
d12bd917 | 3235 | src_base = src; |
df7492f9 | 3236 | ONE_MORE_BYTE (c); |
b73bfc1c | 3237 | if (c < 0xA0) |
d12bd917 KH |
3238 | { |
3239 | src = src_base; | |
3240 | break; | |
3241 | } | |
b73bfc1c KH |
3242 | i++; |
3243 | } | |
3244 | ||
3245 | if (i & 1 && src < src_end) | |
cee53ed4 KH |
3246 | { |
3247 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3248 | if (composition_count >= 0) | |
3249 | composition_count += i; | |
3250 | } | |
f46869e4 | 3251 | else |
cee53ed4 KH |
3252 | { |
3253 | found |= CATEGORY_MASK_ISO_8_2; | |
3254 | if (composition_count >= 0) | |
3255 | composition_count += i / 2; | |
3256 | } | |
f46869e4 | 3257 | } |
ff0dacd7 | 3258 | break; |
4ed46869 | 3259 | } |
ff0dacd7 KH |
3260 | check_extra_latin: |
3261 | single_shifting = 0; | |
3262 | if (! VECTORP (Vlatin_extra_code_table) | |
3263 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
3264 | { | |
3265 | rejected = CATEGORY_MASK_ISO; | |
3266 | break; | |
3267 | } | |
3268 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3269 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3270 | found |= CATEGORY_MASK_ISO_8_1; | |
3271 | else | |
3272 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 3273 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
3274 | } |
3275 | } | |
ff0dacd7 KH |
3276 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3277 | return 0; | |
4ed46869 | 3278 | |
df7492f9 | 3279 | no_more_source: |
ff0dacd7 KH |
3280 | detect_info->rejected |= rejected; |
3281 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3282 | return 1; |
4ed46869 | 3283 | } |
ec6d2bb8 | 3284 | |
4ed46869 | 3285 | |
134b9549 KH |
3286 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3287 | escape sequence should be kept. */ | |
df7492f9 KH |
3288 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3289 | do { \ | |
3290 | int id, prev; \ | |
3291 | \ | |
3292 | if (final < '0' || final >= 128 \ | |
3293 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3294 | || !SAFE_CHARSET_P (coding, id)) \ | |
3295 | { \ | |
3296 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3297 | chars_96 = -1; \ |
3298 | break; \ | |
df7492f9 KH |
3299 | } \ |
3300 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3301 | if (id == charset_jisx0201_roman) \ |
3302 | { \ | |
3303 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3304 | id = charset_ascii; \ | |
3305 | } \ | |
3306 | else if (id == charset_jisx0208_1978) \ | |
3307 | { \ | |
3308 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3309 | id = charset_jisx0208; \ | |
3310 | } \ | |
df7492f9 KH |
3311 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3312 | /* If there was an invalid designation to REG previously, and this \ | |
3313 | designation is ASCII to REG, we should keep this designation \ | |
3314 | sequence. */ \ | |
3315 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3316 | chars_96 = -1; \ |
4ed46869 KH |
3317 | } while (0) |
3318 | ||
d46c5b12 | 3319 | |
e951386e KH |
3320 | /* Handle these composition sequence (ALT: alternate char): |
3321 | ||
3322 | (1) relative composition: ESC 0 CHAR ... ESC 1 | |
3323 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
3324 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | |
3325 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | |
3326 | ||
3327 | When the start sequence (ESC 0/2/3/4) is found, this annotation | |
3328 | header is produced. | |
3329 | ||
3330 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | |
3331 | ||
3332 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | |
3333 | produced until the end sequence (ESC 1) is found: | |
3334 | ||
3335 | (1) CHAR ... CHAR | |
3336 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
3337 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | |
3338 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | |
3339 | ||
3340 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | |
3341 | annotation header is updated as below: | |
3342 | ||
3343 | (1) LENGTH: unchanged, NCHARS: number of CHARs | |
3344 | (2) LENGTH: unchanged, NCHARS: number of CHARs | |
3345 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | |
3346 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | |
3347 | ||
3348 | If an error is found while composing, the annotation header is | |
3349 | changed to: | |
3350 | ||
3351 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | |
3352 | ||
3353 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
3354 | byte sequence as below: | |
3355 | o the original byte sequence is B: [ B -1 ] | |
3356 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
3357 | and the sequence [ -1 -1 ] is changed to the original byte | |
3358 | sequence: | |
3359 | [ ESC '0' ] | |
3360 | */ | |
3361 | ||
3362 | /* Decode a composition rule C1 and maybe one more byte from the | |
3363 | source, and set RULE to the encoded composition rule, NBYTES to the | |
3364 | length of the composition rule. If the rule is invalid, set RULE | |
3365 | to some negative value. */ | |
3366 | ||
3367 | #define DECODE_COMPOSITION_RULE(rule, nbytes) \ | |
3368 | do { \ | |
3369 | rule = c1 - 32; \ | |
3370 | if (rule < 0) \ | |
3371 | break; \ | |
3372 | if (rule < 81) /* old format (before ver.21) */ \ | |
3373 | { \ | |
3374 | int gref = (rule) / 9; \ | |
3375 | int nref = (rule) % 9; \ | |
3376 | if (gref == 4) gref = 10; \ | |
3377 | if (nref == 4) nref = 10; \ | |
3378 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
3379 | nbytes = 1; \ | |
3380 | } \ | |
3381 | else /* new format (after ver.21) */ \ | |
3382 | { \ | |
3383 | int c; \ | |
3384 | \ | |
3385 | ONE_MORE_BYTE (c); \ | |
3386 | rule = COMPOSITION_ENCODE_RULE (rule - 81, c - 32); \ | |
3387 | if (rule >= 0) \ | |
3388 | rule += 0x100; /* to destinguish it from the old format */ \ | |
3389 | nbytes = 2; \ | |
3390 | } \ | |
3391 | } while (0) | |
3392 | ||
3393 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
df7492f9 | 3394 | do { \ |
e951386e KH |
3395 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
3396 | \ | |
3397 | if (rule < 0x100) /* old format */ \ | |
df7492f9 | 3398 | { \ |
e951386e KH |
3399 | if (gref == 10) gref = 4; \ |
3400 | if (nref == 10) nref = 4; \ | |
3401 | charbuf[idx] = 32 + gref * 9 + nref; \ | |
3402 | charbuf[idx + 1] = -1; \ | |
3403 | new_chars++; \ | |
df7492f9 | 3404 | } \ |
e951386e | 3405 | else /* new format */ \ |
df7492f9 | 3406 | { \ |
e951386e KH |
3407 | charbuf[idx] = 32 + 81 + gref; \ |
3408 | charbuf[idx + 1] = 32 + nref; \ | |
3409 | new_chars += 2; \ | |
df7492f9 KH |
3410 | } \ |
3411 | } while (0) | |
3412 | ||
e951386e KH |
3413 | /* Finish the current composition as invalid. */ |
3414 | ||
f57e2426 | 3415 | static int finish_composition (int *, struct composition_status *); |
e951386e KH |
3416 | |
3417 | static int | |
971de7fb | 3418 | finish_composition (int *charbuf, struct composition_status *cmp_status) |
e951386e KH |
3419 | { |
3420 | int idx = - cmp_status->length; | |
3421 | int new_chars; | |
3422 | ||
3423 | /* Recover the original ESC sequence */ | |
3424 | charbuf[idx++] = ISO_CODE_ESC; | |
3425 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | |
3426 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | |
3427 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | |
3428 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | |
3429 | : '4'); | |
3430 | charbuf[idx++] = -2; | |
3431 | charbuf[idx++] = 0; | |
3432 | charbuf[idx++] = -1; | |
3433 | new_chars = cmp_status->nchars; | |
3434 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | |
3435 | for (; idx < 0; idx++) | |
3436 | { | |
3437 | int elt = charbuf[idx]; | |
3438 | ||
3439 | if (elt == -2) | |
3440 | { | |
3441 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | |
3442 | idx++; | |
3443 | } | |
3444 | else if (elt == -1) | |
3445 | { | |
3446 | charbuf[idx++] = ISO_CODE_ESC; | |
3447 | charbuf[idx] = '0'; | |
3448 | new_chars += 2; | |
3449 | } | |
3450 | } | |
3451 | cmp_status->state = COMPOSING_NO; | |
3452 | return new_chars; | |
3453 | } | |
3454 | ||
3455 | /* If characers are under composition, finish the composition. */ | |
3456 | #define MAYBE_FINISH_COMPOSITION() \ | |
3457 | do { \ | |
3458 | if (cmp_status->state != COMPOSING_NO) \ | |
3459 | char_offset += finish_composition (charbuf, cmp_status); \ | |
3460 | } while (0) | |
d46c5b12 | 3461 | |
aa72b389 | 3462 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
e951386e | 3463 | |
aa72b389 KH |
3464 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
3465 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3466 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3467 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
ec6d2bb8 | 3468 | |
e951386e KH |
3469 | Produce this annotation sequence now: |
3470 | ||
3471 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] | |
3472 | */ | |
3473 | ||
3474 | #define DECODE_COMPOSITION_START(c1) \ | |
3475 | do { \ | |
3476 | if (c1 == '0' \ | |
3477 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ | |
3478 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ | |
3479 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ | |
3480 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ | |
3481 | { \ | |
3482 | *charbuf++ = -1; \ | |
3483 | *charbuf++= -1; \ | |
3484 | cmp_status->state = COMPOSING_CHAR; \ | |
3485 | cmp_status->length += 2; \ | |
3486 | } \ | |
3487 | else \ | |
3488 | { \ | |
3489 | MAYBE_FINISH_COMPOSITION (); \ | |
3490 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3491 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3492 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3493 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3494 | cmp_status->state \ | |
3495 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ | |
3496 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
3497 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
3498 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
3499 | coding->annotated = 1; \ | |
3500 | } \ | |
ec6d2bb8 KH |
3501 | } while (0) |
3502 | ||
ec6d2bb8 | 3503 | |
e951386e | 3504 | /* Handle composition end sequence ESC 1. */ |
df7492f9 KH |
3505 | |
3506 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3507 | do { \ |
e951386e KH |
3508 | if (cmp_status->nchars == 0 \ |
3509 | || ((cmp_status->state == COMPOSING_CHAR) \ | |
3510 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ | |
ec6d2bb8 | 3511 | { \ |
e951386e KH |
3512 | MAYBE_FINISH_COMPOSITION (); \ |
3513 | goto invalid_code; \ | |
ec6d2bb8 | 3514 | } \ |
e951386e KH |
3515 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
3516 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ | |
3517 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
3518 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ | |
3519 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ | |
3520 | char_offset += cmp_status->nchars; \ | |
3521 | cmp_status->state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3522 | } while (0) |
3523 | ||
e951386e | 3524 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ |
df7492f9 | 3525 | |
e951386e KH |
3526 | #define STORE_COMPOSITION_RULE(rule) \ |
3527 | do { \ | |
3528 | *charbuf++ = -2; \ | |
3529 | *charbuf++ = rule; \ | |
3530 | cmp_status->length += 2; \ | |
3531 | cmp_status->state--; \ | |
3532 | } while (0) | |
ec6d2bb8 | 3533 | |
e951386e KH |
3534 | /* Store a composed char or a component char C in charbuf, and update |
3535 | cmp_status. */ | |
3536 | ||
3537 | #define STORE_COMPOSITION_CHAR(c) \ | |
ec6d2bb8 | 3538 | do { \ |
e951386e KH |
3539 | *charbuf++ = (c); \ |
3540 | cmp_status->length++; \ | |
3541 | if (cmp_status->state == COMPOSING_CHAR) \ | |
3542 | cmp_status->nchars++; \ | |
df7492f9 | 3543 | else \ |
e951386e KH |
3544 | cmp_status->ncomps++; \ |
3545 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | |
3546 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | |
3547 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | |
3548 | cmp_status->state++; \ | |
ec6d2bb8 | 3549 | } while (0) |
88993dfd | 3550 | |
d46c5b12 | 3551 | |
4ed46869 KH |
3552 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3553 | ||
b73bfc1c | 3554 | static void |
971de7fb | 3555 | decode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 3556 | { |
8f924df7 KH |
3557 | const unsigned char *src = coding->source + coding->consumed; |
3558 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3559 | const unsigned char *src_base; | |
69a80ea3 | 3560 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
3561 | /* We may produce two annocations (charset and composition) in one |
3562 | loop and one more charset annocation at the end. */ | |
ff0dacd7 | 3563 | int *charbuf_end |
df80c7f0 | 3564 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
df7492f9 | 3565 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 3566 | int multibytep = coding->src_multibyte; |
4ed46869 | 3567 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3568 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3569 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3570 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3571 | struct charset *charset; |
3572 | int c; | |
e951386e | 3573 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
24a73b0a | 3574 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
3575 | int char_offset = coding->produced_char; |
3576 | int last_offset = char_offset; | |
3577 | int last_id = charset_ascii; | |
0a9564cb EZ |
3578 | int eol_crlf = |
3579 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 3580 | int byte_after_cr = -1; |
e951386e | 3581 | int i; |
df7492f9 | 3582 | |
24a73b0a | 3583 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 3584 | setup_iso_safe_charsets (attrs); |
287c57d7 KH |
3585 | /* Charset list may have been changed. */ |
3586 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
1b3b981b | 3587 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
b73bfc1c | 3588 | |
e951386e KH |
3589 | if (cmp_status->state != COMPOSING_NO) |
3590 | { | |
3591 | for (i = 0; i < cmp_status->length; i++) | |
3592 | *charbuf++ = cmp_status->carryover[i]; | |
3593 | coding->annotated = 1; | |
3594 | } | |
3595 | ||
b73bfc1c | 3596 | while (1) |
4ed46869 | 3597 | { |
cf299835 | 3598 | int c1, c2, c3; |
b73bfc1c KH |
3599 | |
3600 | src_base = src; | |
df7492f9 KH |
3601 | consumed_chars_base = consumed_chars; |
3602 | ||
3603 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3604 | { |
3605 | if (byte_after_cr >= 0) | |
3606 | src_base--; | |
3607 | break; | |
3608 | } | |
df7492f9 | 3609 | |
119852e7 KH |
3610 | if (byte_after_cr >= 0) |
3611 | c1 = byte_after_cr, byte_after_cr = -1; | |
3612 | else | |
3613 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3614 | if (c1 < 0) |
3615 | goto invalid_code; | |
4ed46869 | 3616 | |
e951386e | 3617 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
4ed46869 | 3618 | { |
e951386e KH |
3619 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
3620 | char_offset++; | |
3621 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | |
3622 | continue; | |
3623 | } | |
3624 | ||
3625 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | |
3626 | { | |
3627 | if (c1 == ISO_CODE_ESC) | |
ec6d2bb8 | 3628 | { |
e951386e KH |
3629 | if (src + 1 >= src_end) |
3630 | goto no_more_source; | |
3631 | *charbuf++ = ISO_CODE_ESC; | |
3632 | char_offset++; | |
3633 | if (src[0] == '%' && src[1] == '@') | |
df7492f9 | 3634 | { |
e951386e KH |
3635 | src += 2; |
3636 | consumed_chars += 2; | |
3637 | char_offset += 2; | |
3638 | /* We are sure charbuf can contain two more chars. */ | |
3639 | *charbuf++ = '%'; | |
3640 | *charbuf++ = '@'; | |
3641 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
df7492f9 | 3642 | } |
4ed46869 | 3643 | } |
e951386e KH |
3644 | else |
3645 | { | |
3646 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
3647 | char_offset++; | |
3648 | } | |
3649 | continue; | |
3650 | } | |
3651 | ||
3652 | if ((cmp_status->state == COMPOSING_RULE | |
3653 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | |
3654 | && c1 != ISO_CODE_ESC) | |
3655 | { | |
3656 | int rule, nbytes; | |
3657 | ||
3658 | DECODE_COMPOSITION_RULE (rule, nbytes); | |
3659 | if (rule < 0) | |
3660 | goto invalid_code; | |
3661 | STORE_COMPOSITION_RULE (rule); | |
3662 | continue; | |
3663 | } | |
3664 | ||
3665 | /* We produce at most one character. */ | |
3666 | switch (iso_code_class [c1]) | |
3667 | { | |
3668 | case ISO_0x20_or_0x7F: | |
df7492f9 KH |
3669 | if (charset_id_0 < 0 |
3670 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3671 | /* This is SPACE or DEL. */ |
3672 | charset = CHARSET_FROM_ID (charset_ascii); | |
3673 | else | |
3674 | charset = CHARSET_FROM_ID (charset_id_0); | |
3675 | break; | |
4ed46869 KH |
3676 | |
3677 | case ISO_graphic_plane_0: | |
134b9549 KH |
3678 | if (charset_id_0 < 0) |
3679 | charset = CHARSET_FROM_ID (charset_ascii); | |
3680 | else | |
3681 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3682 | break; |
3683 | ||
3684 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3685 | if (charset_id_1 < 0 |
3686 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3687 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3688 | goto invalid_code; | |
4ed46869 KH |
3689 | /* This is a graphic character, we fall down ... */ |
3690 | ||
3691 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3692 | if (charset_id_1 < 0) |
3693 | goto invalid_code; | |
3694 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3695 | break; |
3696 | ||
df7492f9 | 3697 | case ISO_control_0: |
119852e7 KH |
3698 | if (eol_crlf && c1 == '\r') |
3699 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 KH |
3700 | MAYBE_FINISH_COMPOSITION (); |
3701 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3702 | break; |
3703 | ||
df7492f9 | 3704 | case ISO_control_1: |
df7492f9 KH |
3705 | goto invalid_code; |
3706 | ||
4ed46869 | 3707 | case ISO_shift_out: |
df7492f9 KH |
3708 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3709 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3710 | goto invalid_code; | |
3711 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3712 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3713 | continue; |
4ed46869 KH |
3714 | |
3715 | case ISO_shift_in: | |
df7492f9 KH |
3716 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3717 | goto invalid_code; | |
3718 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3719 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3720 | continue; |
4ed46869 KH |
3721 | |
3722 | case ISO_single_shift_2_7: | |
a63dba42 KH |
3723 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)) |
3724 | goto invalid_code; | |
4ed46869 | 3725 | case ISO_single_shift_2: |
df7492f9 KH |
3726 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3727 | goto invalid_code; | |
4ed46869 KH |
3728 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3729 | c1 = 'N'; | |
3730 | goto label_escape_sequence; | |
3731 | ||
3732 | case ISO_single_shift_3: | |
df7492f9 KH |
3733 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3734 | goto invalid_code; | |
4ed46869 KH |
3735 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3736 | c1 = 'O'; | |
3737 | goto label_escape_sequence; | |
3738 | ||
3739 | case ISO_control_sequence_introducer: | |
3740 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3741 | c1 = '['; | |
3742 | goto label_escape_sequence; | |
3743 | ||
3744 | case ISO_escape: | |
3745 | ONE_MORE_BYTE (c1); | |
3746 | label_escape_sequence: | |
df7492f9 | 3747 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3748 | designation, direction specification, and character |
3749 | composition specification. */ | |
3750 | switch (c1) | |
3751 | { | |
3752 | case '&': /* revision of following character set */ | |
3753 | ONE_MORE_BYTE (c1); | |
3754 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3755 | goto invalid_code; |
4ed46869 KH |
3756 | ONE_MORE_BYTE (c1); |
3757 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3758 | goto invalid_code; |
4ed46869 KH |
3759 | ONE_MORE_BYTE (c1); |
3760 | goto label_escape_sequence; | |
3761 | ||
3762 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3763 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3764 | goto invalid_code; | |
134b9549 KH |
3765 | { |
3766 | int reg, chars96; | |
3767 | ||
3768 | ONE_MORE_BYTE (c1); | |
3769 | if (c1 >= '@' && c1 <= 'B') | |
3770 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3771 | or JISX0208.1980 */ |
134b9549 KH |
3772 | reg = 0, chars96 = 0; |
3773 | } | |
3774 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3775 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3776 | reg = c1 - 0x28, chars96 = 0; | |
3777 | ONE_MORE_BYTE (c1); | |
3778 | } | |
3779 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3780 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3781 | reg = c1 - 0x2C, chars96 = 1; | |
3782 | ONE_MORE_BYTE (c1); | |
3783 | } | |
3784 | else | |
3785 | goto invalid_code; | |
3786 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3787 | /* We must update these variables now. */ | |
3788 | if (reg == 0) | |
3789 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3790 | else if (reg == 1) | |
3791 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3792 | if (chars96 < 0) | |
3793 | goto invalid_code; | |
3794 | } | |
b73bfc1c | 3795 | continue; |
4ed46869 KH |
3796 | |
3797 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3798 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3799 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3800 | goto invalid_code; | |
3801 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3802 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3803 | continue; |
4ed46869 KH |
3804 | |
3805 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3806 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3807 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3808 | goto invalid_code; | |
3809 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3810 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3811 | continue; |
4ed46869 KH |
3812 | |
3813 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3814 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3815 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3816 | goto invalid_code; | |
134b9549 KH |
3817 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3818 | if (charset_id_2 < 0) | |
3819 | charset = CHARSET_FROM_ID (charset_ascii); | |
3820 | else | |
3821 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3822 | ONE_MORE_BYTE (c1); |
e7046a18 | 3823 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3824 | goto invalid_code; |
4ed46869 KH |
3825 | break; |
3826 | ||
3827 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3828 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3829 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3830 | goto invalid_code; | |
134b9549 KH |
3831 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3832 | if (charset_id_3 < 0) | |
3833 | charset = CHARSET_FROM_ID (charset_ascii); | |
3834 | else | |
3835 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3836 | ONE_MORE_BYTE (c1); |
e7046a18 | 3837 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3838 | goto invalid_code; |
4ed46869 KH |
3839 | break; |
3840 | ||
ec6d2bb8 | 3841 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3842 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3843 | goto invalid_code; | |
e951386e KH |
3844 | if (last_id != charset_ascii) |
3845 | { | |
3846 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | |
3847 | last_id = charset_ascii; | |
3848 | last_offset = char_offset; | |
3849 | } | |
ec6d2bb8 | 3850 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3851 | continue; |
4ed46869 | 3852 | |
ec6d2bb8 | 3853 | case '1': /* end composition */ |
e951386e | 3854 | if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3855 | goto invalid_code; |
3856 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3857 | continue; |
4ed46869 KH |
3858 | |
3859 | case '[': /* specification of direction */ | |
de59072a | 3860 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)) |
df7492f9 | 3861 | goto invalid_code; |
4ed46869 | 3862 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3863 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3864 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3865 | ONE_MORE_BYTE (c1); |
3866 | switch (c1) | |
3867 | { | |
3868 | case ']': /* end of the current direction */ | |
d46c5b12 | 3869 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3870 | |
3871 | case '0': /* end of the current direction */ | |
3872 | case '1': /* start of left-to-right direction */ | |
3873 | ONE_MORE_BYTE (c1); | |
3874 | if (c1 == ']') | |
d46c5b12 | 3875 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3876 | else |
df7492f9 | 3877 | goto invalid_code; |
4ed46869 KH |
3878 | break; |
3879 | ||
3880 | case '2': /* start of right-to-left direction */ | |
3881 | ONE_MORE_BYTE (c1); | |
3882 | if (c1 == ']') | |
d46c5b12 | 3883 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3884 | else |
df7492f9 | 3885 | goto invalid_code; |
4ed46869 KH |
3886 | break; |
3887 | ||
3888 | default: | |
df7492f9 | 3889 | goto invalid_code; |
4ed46869 | 3890 | } |
b73bfc1c | 3891 | continue; |
4ed46869 | 3892 | |
103e0180 | 3893 | case '%': |
103e0180 KH |
3894 | ONE_MORE_BYTE (c1); |
3895 | if (c1 == '/') | |
3896 | { | |
3897 | /* CTEXT extended segment: | |
3898 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3899 | We keep these bytes as is for the moment. | |
3900 | They may be decoded by post-read-conversion. */ | |
3901 | int dim, M, L; | |
4776e638 | 3902 | int size; |
8f924df7 | 3903 | |
103e0180 | 3904 | ONE_MORE_BYTE (dim); |
e951386e KH |
3905 | if (dim < 0 || dim > 4) |
3906 | goto invalid_code; | |
103e0180 | 3907 | ONE_MORE_BYTE (M); |
e951386e KH |
3908 | if (M < 128) |
3909 | goto invalid_code; | |
103e0180 | 3910 | ONE_MORE_BYTE (L); |
e951386e KH |
3911 | if (L < 128) |
3912 | goto invalid_code; | |
103e0180 | 3913 | size = ((M - 128) * 128) + (L - 128); |
e951386e | 3914 | if (charbuf + 6 > charbuf_end) |
4776e638 KH |
3915 | goto break_loop; |
3916 | *charbuf++ = ISO_CODE_ESC; | |
3917 | *charbuf++ = '%'; | |
3918 | *charbuf++ = '/'; | |
3919 | *charbuf++ = dim; | |
3920 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3921 | *charbuf++ = BYTE8_TO_CHAR (L); | |
e951386e | 3922 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
103e0180 KH |
3923 | } |
3924 | else if (c1 == 'G') | |
3925 | { | |
103e0180 KH |
3926 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3927 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3928 | We keep these bytes as is for the moment. | |
3929 | They may be decoded by post-read-conversion. */ | |
e951386e | 3930 | if (charbuf + 3 > charbuf_end) |
4776e638 | 3931 | goto break_loop; |
e951386e KH |
3932 | *charbuf++ = ISO_CODE_ESC; |
3933 | *charbuf++ = '%'; | |
3934 | *charbuf++ = 'G'; | |
3935 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; | |
103e0180 KH |
3936 | } |
3937 | else | |
4776e638 | 3938 | goto invalid_code; |
103e0180 | 3939 | continue; |
4776e638 | 3940 | break; |
103e0180 | 3941 | |
4ed46869 | 3942 | default: |
df7492f9 KH |
3943 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3944 | goto invalid_code; | |
134b9549 KH |
3945 | { |
3946 | int reg, chars96; | |
3947 | ||
3948 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3949 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3950 | reg = c1 - 0x28, chars96 = 0; | |
3951 | ONE_MORE_BYTE (c1); | |
3952 | } | |
3953 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3954 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3955 | reg = c1 - 0x2C, chars96 = 1; | |
3956 | ONE_MORE_BYTE (c1); | |
3957 | } | |
3958 | else | |
3959 | goto invalid_code; | |
3960 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3961 | /* We must update these variables now. */ | |
3962 | if (reg == 0) | |
3963 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3964 | else if (reg == 1) | |
3965 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3966 | if (chars96 < 0) | |
3967 | goto invalid_code; | |
3968 | } | |
b73bfc1c | 3969 | continue; |
4ed46869 | 3970 | } |
b73bfc1c | 3971 | } |
4ed46869 | 3972 | |
e951386e KH |
3973 | if (cmp_status->state == COMPOSING_NO |
3974 | && charset->id != charset_ascii | |
ff0dacd7 KH |
3975 | && last_id != charset->id) |
3976 | { | |
3977 | if (last_id != charset_ascii) | |
69a80ea3 | 3978 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3979 | last_id = charset->id; |
3980 | last_offset = char_offset; | |
3981 | } | |
3982 | ||
b73bfc1c | 3983 | /* Now we know CHARSET and 1st position code C1 of a character. |
cf299835 KH |
3984 | Produce a decoded character while getting 2nd and 3rd |
3985 | position codes C2, C3 if necessary. */ | |
df7492f9 | 3986 | if (CHARSET_DIMENSION (charset) > 1) |
b73bfc1c KH |
3987 | { |
3988 | ONE_MORE_BYTE (c2); | |
cf299835 KH |
3989 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0) |
3990 | || ((c1 & 0x80) != (c2 & 0x80))) | |
b73bfc1c | 3991 | /* C2 is not in a valid range. */ |
df7492f9 | 3992 | goto invalid_code; |
cf299835 KH |
3993 | if (CHARSET_DIMENSION (charset) == 2) |
3994 | c1 = (c1 << 8) | c2; | |
3995 | else | |
df7492f9 | 3996 | { |
cf299835 KH |
3997 | ONE_MORE_BYTE (c3); |
3998 | if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0) | |
3999 | || ((c1 & 0x80) != (c3 & 0x80))) | |
4000 | /* C3 is not in a valid range. */ | |
df7492f9 | 4001 | goto invalid_code; |
cf299835 | 4002 | c1 = (c1 << 16) | (c2 << 8) | c2; |
df7492f9 KH |
4003 | } |
4004 | } | |
cf299835 | 4005 | c1 &= 0x7F7F7F; |
df7492f9 KH |
4006 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); |
4007 | if (c < 0) | |
4008 | { | |
4009 | MAYBE_FINISH_COMPOSITION (); | |
4010 | for (; src_base < src; src_base++, char_offset++) | |
4011 | { | |
4012 | if (ASCII_BYTE_P (*src_base)) | |
4013 | *charbuf++ = *src_base; | |
4014 | else | |
4015 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
4016 | } | |
4017 | } | |
e951386e | 4018 | else if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
4019 | { |
4020 | *charbuf++ = c; | |
4021 | char_offset++; | |
4ed46869 | 4022 | } |
e951386e KH |
4023 | else if ((cmp_status->state == COMPOSING_CHAR |
4024 | ? cmp_status->nchars | |
4025 | : cmp_status->ncomps) | |
4026 | >= MAX_COMPOSITION_COMPONENTS) | |
781d7a48 | 4027 | { |
e951386e KH |
4028 | /* Too long composition. */ |
4029 | MAYBE_FINISH_COMPOSITION (); | |
4030 | *charbuf++ = c; | |
4031 | char_offset++; | |
4ed46869 | 4032 | } |
e951386e KH |
4033 | else |
4034 | STORE_COMPOSITION_CHAR (c); | |
4ed46869 KH |
4035 | continue; |
4036 | ||
df7492f9 KH |
4037 | invalid_code: |
4038 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 4039 | src = src_base; |
df7492f9 KH |
4040 | consumed_chars = consumed_chars_base; |
4041 | ONE_MORE_BYTE (c); | |
065e3595 | 4042 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4043 | char_offset++; |
df7492f9 | 4044 | coding->errors++; |
4776e638 KH |
4045 | continue; |
4046 | ||
4047 | break_loop: | |
4048 | break; | |
4ed46869 | 4049 | } |
fb88bf2d | 4050 | |
df7492f9 | 4051 | no_more_source: |
e951386e KH |
4052 | if (cmp_status->state != COMPOSING_NO) |
4053 | { | |
4054 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
4055 | MAYBE_FINISH_COMPOSITION (); | |
4056 | else | |
4057 | { | |
4058 | charbuf -= cmp_status->length; | |
4059 | for (i = 0; i < cmp_status->length; i++) | |
4060 | cmp_status->carryover[i] = charbuf[i]; | |
4061 | } | |
4062 | } | |
4063 | else if (last_id != charset_ascii) | |
69a80ea3 | 4064 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4065 | coding->consumed_char += consumed_chars_base; |
4066 | coding->consumed = src_base - coding->source; | |
4067 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4068 | } |
4069 | ||
b73bfc1c | 4070 | |
f4dee582 | 4071 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
4072 | |
4073 | /* | |
f4dee582 | 4074 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 4075 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 4076 | variant has the following specifications: |
df7492f9 | 4077 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
4078 | 2. Allows short-form designation? |
4079 | 3. ASCII should be designated to G0 before control characters? | |
4080 | 4. ASCII should be designated to G0 at end of line? | |
4081 | 5. 7-bit environment or 8-bit environment? | |
4082 | 6. Use locking-shift? | |
4083 | 7. Use Single-shift? | |
4084 | And the following two are only for Japanese: | |
4085 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
4086 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
4087 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
4088 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 4089 | details. |
4ed46869 KH |
4090 | */ |
4091 | ||
4092 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
4093 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
4094 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
4095 | designation sequence of short-form. */ | |
4ed46869 KH |
4096 | |
4097 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
4098 | do { \ | |
df7492f9 | 4099 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
4100 | char *intermediate_char_94 = "()*+"; \ |
4101 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
4102 | int revision = -1; \ |
4103 | int c; \ | |
4104 | \ | |
4105 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 4106 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
4107 | \ |
4108 | if (revision >= 0) \ | |
70c22245 | 4109 | { \ |
df7492f9 KH |
4110 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
4111 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 4112 | } \ |
df7492f9 | 4113 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
4114 | if (CHARSET_DIMENSION (charset) == 1) \ |
4115 | { \ | |
df7492f9 KH |
4116 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
4117 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 4118 | else \ |
df7492f9 KH |
4119 | c = intermediate_char_96[reg]; \ |
4120 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
4121 | } \ |
4122 | else \ | |
4123 | { \ | |
df7492f9 KH |
4124 | EMIT_ONE_ASCII_BYTE ('$'); \ |
4125 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 4126 | { \ |
df7492f9 | 4127 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
4128 | || reg != 0 \ |
4129 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 4130 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
4131 | } \ |
4132 | else \ | |
df7492f9 | 4133 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 4134 | } \ |
df7492f9 KH |
4135 | EMIT_ONE_ASCII_BYTE (final_char); \ |
4136 | \ | |
4137 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
4138 | } while (0) |
4139 | ||
df7492f9 | 4140 | |
4ed46869 KH |
4141 | /* The following two macros produce codes (control character or escape |
4142 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
4143 | single-shift-3). */ | |
4144 | ||
df7492f9 KH |
4145 | #define ENCODE_SINGLE_SHIFT_2 \ |
4146 | do { \ | |
4147 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4148 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
4149 | else \ | |
4150 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
4151 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4152 | } while (0) |
4153 | ||
df7492f9 KH |
4154 | |
4155 | #define ENCODE_SINGLE_SHIFT_3 \ | |
4156 | do { \ | |
4157 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4158 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
4159 | else \ | |
4160 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
4161 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4162 | } while (0) |
4163 | ||
df7492f9 | 4164 | |
4ed46869 KH |
4165 | /* The following four macros produce codes (control character or |
4166 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
4167 | shift-out, locking-shift-2, and locking-shift-3). */ | |
4168 | ||
df7492f9 KH |
4169 | #define ENCODE_SHIFT_IN \ |
4170 | do { \ | |
4171 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
4172 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
4173 | } while (0) |
4174 | ||
df7492f9 KH |
4175 | |
4176 | #define ENCODE_SHIFT_OUT \ | |
4177 | do { \ | |
4178 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
4179 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
4180 | } while (0) |
4181 | ||
df7492f9 KH |
4182 | |
4183 | #define ENCODE_LOCKING_SHIFT_2 \ | |
4184 | do { \ | |
4185 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4186 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
4187 | } while (0) |
4188 | ||
df7492f9 KH |
4189 | |
4190 | #define ENCODE_LOCKING_SHIFT_3 \ | |
4191 | do { \ | |
4192 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4193 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
4194 | } while (0) |
4195 | ||
df7492f9 | 4196 | |
f4dee582 RS |
4197 | /* Produce codes for a DIMENSION1 character whose character set is |
4198 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
4199 | sequences are also produced in advance if necessary. */ |
4200 | ||
6e85d753 KH |
4201 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
4202 | do { \ | |
df7492f9 | 4203 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4204 | \ |
4205 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
4206 | && id == charset_ascii) \ | |
4207 | { \ | |
4208 | id = charset_jisx0201_roman; \ | |
4209 | charset = CHARSET_FROM_ID (id); \ | |
4210 | } \ | |
4211 | \ | |
df7492f9 | 4212 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4213 | { \ |
df7492f9 KH |
4214 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4215 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 4216 | else \ |
df7492f9 KH |
4217 | EMIT_ONE_BYTE (c1 | 0x80); \ |
4218 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4219 | break; \ |
4220 | } \ | |
df7492f9 | 4221 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4222 | { \ |
df7492f9 | 4223 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
4224 | break; \ |
4225 | } \ | |
df7492f9 | 4226 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4227 | { \ |
df7492f9 | 4228 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
4229 | break; \ |
4230 | } \ | |
6e85d753 KH |
4231 | else \ |
4232 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4233 | must invoke it, or, at first, designate it to some graphic \ | |
4234 | register. Then repeat the loop to actually produce the \ | |
4235 | character. */ \ | |
df7492f9 KH |
4236 | dst = encode_invocation_designation (charset, coding, dst, \ |
4237 | &produced_chars); \ | |
4ed46869 KH |
4238 | } while (1) |
4239 | ||
df7492f9 | 4240 | |
f4dee582 RS |
4241 | /* Produce codes for a DIMENSION2 character whose character set is |
4242 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
4243 | invocation codes are also produced in advance if necessary. */ |
4244 | ||
6e85d753 KH |
4245 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
4246 | do { \ | |
df7492f9 | 4247 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4248 | \ |
4249 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
4250 | && id == charset_jisx0208) \ | |
4251 | { \ | |
4252 | id = charset_jisx0208_1978; \ | |
4253 | charset = CHARSET_FROM_ID (id); \ | |
4254 | } \ | |
4255 | \ | |
df7492f9 | 4256 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4257 | { \ |
df7492f9 KH |
4258 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4259 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 4260 | else \ |
df7492f9 KH |
4261 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
4262 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4263 | break; \ |
4264 | } \ | |
df7492f9 | 4265 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4266 | { \ |
df7492f9 | 4267 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
4268 | break; \ |
4269 | } \ | |
df7492f9 | 4270 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4271 | { \ |
df7492f9 | 4272 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
4273 | break; \ |
4274 | } \ | |
6e85d753 KH |
4275 | else \ |
4276 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4277 | must invoke it, or, at first, designate it to some graphic \ | |
4278 | register. Then repeat the loop to actually produce the \ | |
4279 | character. */ \ | |
df7492f9 KH |
4280 | dst = encode_invocation_designation (charset, coding, dst, \ |
4281 | &produced_chars); \ | |
4ed46869 KH |
4282 | } while (1) |
4283 | ||
05e6f5dc | 4284 | |
df7492f9 KH |
4285 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
4286 | do { \ | |
1a4990fb | 4287 | int code = ENCODE_CHAR ((charset), (c)); \ |
df7492f9 KH |
4288 | \ |
4289 | if (CHARSET_DIMENSION (charset) == 1) \ | |
4290 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
4291 | else \ | |
4292 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 4293 | } while (0) |
bdd9fb48 | 4294 | |
05e6f5dc | 4295 | |
4ed46869 | 4296 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 4297 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
4298 | Return new DST. */ |
4299 | ||
4300 | unsigned char * | |
cf84bb53 JB |
4301 | encode_invocation_designation (struct charset *charset, |
4302 | struct coding_system *coding, | |
4303 | unsigned char *dst, int *p_nchars) | |
4ed46869 | 4304 | { |
df7492f9 KH |
4305 | int multibytep = coding->dst_multibyte; |
4306 | int produced_chars = *p_nchars; | |
4ed46869 | 4307 | int reg; /* graphic register number */ |
df7492f9 | 4308 | int id = CHARSET_ID (charset); |
4ed46869 KH |
4309 | |
4310 | /* At first, check designations. */ | |
4311 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 4312 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
4313 | break; |
4314 | ||
4315 | if (reg >= 4) | |
4316 | { | |
4317 | /* CHARSET is not yet designated to any graphic registers. */ | |
4318 | /* At first check the requested designation. */ | |
df7492f9 KH |
4319 | reg = CODING_ISO_REQUEST (coding, id); |
4320 | if (reg < 0) | |
1ba9e4ab KH |
4321 | /* Since CHARSET requests no special designation, designate it |
4322 | to graphic register 0. */ | |
4ed46869 KH |
4323 | reg = 0; |
4324 | ||
4325 | ENCODE_DESIGNATION (charset, reg, coding); | |
4326 | } | |
4327 | ||
df7492f9 KH |
4328 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
4329 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
4330 | { |
4331 | /* Since the graphic register REG is not invoked to any graphic | |
4332 | planes, invoke it to graphic plane 0. */ | |
4333 | switch (reg) | |
4334 | { | |
4335 | case 0: /* graphic register 0 */ | |
4336 | ENCODE_SHIFT_IN; | |
4337 | break; | |
4338 | ||
4339 | case 1: /* graphic register 1 */ | |
4340 | ENCODE_SHIFT_OUT; | |
4341 | break; | |
4342 | ||
4343 | case 2: /* graphic register 2 */ | |
df7492f9 | 4344 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4345 | ENCODE_SINGLE_SHIFT_2; |
4346 | else | |
4347 | ENCODE_LOCKING_SHIFT_2; | |
4348 | break; | |
4349 | ||
4350 | case 3: /* graphic register 3 */ | |
df7492f9 | 4351 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4352 | ENCODE_SINGLE_SHIFT_3; |
4353 | else | |
4354 | ENCODE_LOCKING_SHIFT_3; | |
4355 | break; | |
4356 | } | |
4357 | } | |
b73bfc1c | 4358 | |
df7492f9 | 4359 | *p_nchars = produced_chars; |
4ed46869 KH |
4360 | return dst; |
4361 | } | |
4362 | ||
df7492f9 KH |
4363 | /* The following three macros produce codes for indicating direction |
4364 | of text. */ | |
4365 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 4366 | do { \ |
df7492f9 KH |
4367 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
4368 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 4369 | else \ |
df7492f9 | 4370 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
4371 | } while (0) |
4372 | ||
ec6d2bb8 | 4373 | |
df7492f9 KH |
4374 | #define ENCODE_DIRECTION_R2L() \ |
4375 | do { \ | |
4376 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
4377 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
4378 | } while (0) |
4379 | ||
ec6d2bb8 | 4380 | |
df7492f9 | 4381 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 4382 | do { \ |
df7492f9 KH |
4383 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
4384 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 4385 | } while (0) |
4ed46869 | 4386 | |
4ed46869 KH |
4387 | |
4388 | /* Produce codes for designation and invocation to reset the graphic | |
4389 | planes and registers to initial state. */ | |
df7492f9 KH |
4390 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4391 | do { \ | |
4392 | int reg; \ | |
4393 | struct charset *charset; \ | |
4394 | \ | |
4395 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4396 | ENCODE_SHIFT_IN; \ | |
4397 | for (reg = 0; reg < 4; reg++) \ | |
4398 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4399 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4400 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4401 | { \ | |
4402 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4403 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4404 | } \ | |
4ed46869 KH |
4405 | } while (0) |
4406 | ||
df7492f9 | 4407 | |
bdd9fb48 | 4408 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 4409 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
4410 | |
4411 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4412 | find all the necessary designations. */ |
4413 | ||
b73bfc1c | 4414 | static unsigned char * |
cf84bb53 JB |
4415 | encode_designation_at_bol (struct coding_system *coding, int *charbuf, |
4416 | int *charbuf_end, unsigned char *dst) | |
e0e989f6 | 4417 | { |
df7492f9 | 4418 | struct charset *charset; |
bdd9fb48 KH |
4419 | /* Table of charsets to be designated to each graphic register. */ |
4420 | int r[4]; | |
df7492f9 KH |
4421 | int c, found = 0, reg; |
4422 | int produced_chars = 0; | |
4423 | int multibytep = coding->dst_multibyte; | |
4424 | Lisp_Object attrs; | |
4425 | Lisp_Object charset_list; | |
4426 | ||
4427 | attrs = CODING_ID_ATTRS (coding->id); | |
4428 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4429 | if (EQ (charset_list, Qiso_2022)) | |
4430 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4431 | |
4432 | for (reg = 0; reg < 4; reg++) | |
4433 | r[reg] = -1; | |
4434 | ||
b73bfc1c | 4435 | while (found < 4) |
e0e989f6 | 4436 | { |
df7492f9 KH |
4437 | int id; |
4438 | ||
4439 | c = *charbuf++; | |
b73bfc1c KH |
4440 | if (c == '\n') |
4441 | break; | |
df7492f9 KH |
4442 | charset = char_charset (c, charset_list, NULL); |
4443 | id = CHARSET_ID (charset); | |
4444 | reg = CODING_ISO_REQUEST (coding, id); | |
4445 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4446 | { |
4447 | found++; | |
df7492f9 | 4448 | r[reg] = id; |
bdd9fb48 | 4449 | } |
bdd9fb48 KH |
4450 | } |
4451 | ||
4452 | if (found) | |
4453 | { | |
4454 | for (reg = 0; reg < 4; reg++) | |
4455 | if (r[reg] >= 0 | |
df7492f9 KH |
4456 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4457 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4458 | } |
b73bfc1c KH |
4459 | |
4460 | return dst; | |
e0e989f6 KH |
4461 | } |
4462 | ||
4ed46869 KH |
4463 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4464 | ||
df7492f9 | 4465 | static int |
971de7fb | 4466 | encode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 4467 | { |
df7492f9 KH |
4468 | int multibytep = coding->dst_multibyte; |
4469 | int *charbuf = coding->charbuf; | |
4470 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4471 | unsigned char *dst = coding->destination + coding->produced; | |
4472 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4473 | int safe_room = 16; | |
4474 | int bol_designation | |
4475 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
4476 | && CODING_ISO_BOL (coding)); | |
4477 | int produced_chars = 0; | |
4478 | Lisp_Object attrs, eol_type, charset_list; | |
4479 | int ascii_compatible; | |
b73bfc1c | 4480 | int c; |
ff0dacd7 | 4481 | int preferred_charset_id = -1; |
05e6f5dc | 4482 | |
24a73b0a | 4483 | CODING_GET_INFO (coding, attrs, charset_list); |
0a9564cb | 4484 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
24a73b0a KH |
4485 | if (VECTORP (eol_type)) |
4486 | eol_type = Qunix; | |
4487 | ||
004068e4 | 4488 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4489 | /* Charset list may have been changed. */ |
287c57d7 | 4490 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
1b3b981b | 4491 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
0eecad43 | 4492 | |
df7492f9 | 4493 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 4494 | |
df7492f9 | 4495 | while (charbuf < charbuf_end) |
4ed46869 | 4496 | { |
df7492f9 | 4497 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4498 | |
df7492f9 | 4499 | if (bol_designation) |
b73bfc1c | 4500 | { |
df7492f9 | 4501 | unsigned char *dst_prev = dst; |
4ed46869 | 4502 | |
bdd9fb48 | 4503 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
4504 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
4505 | bol_designation = 0; | |
4506 | /* We are sure that designation sequences are all ASCII bytes. */ | |
4507 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
4508 | } |
4509 | ||
df7492f9 | 4510 | c = *charbuf++; |
ec6d2bb8 | 4511 | |
ff0dacd7 KH |
4512 | if (c < 0) |
4513 | { | |
4514 | /* Handle an annotation. */ | |
4515 | switch (*charbuf) | |
ec6d2bb8 | 4516 | { |
ff0dacd7 KH |
4517 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4518 | /* Not yet implemented. */ | |
4519 | break; | |
4520 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4521 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4522 | if (preferred_charset_id >= 0 |
4523 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4524 | charset_list))) | |
4525 | preferred_charset_id = -1; | |
4526 | break; | |
4527 | default: | |
4528 | abort (); | |
4ed46869 | 4529 | } |
ff0dacd7 KH |
4530 | charbuf += -c - 1; |
4531 | continue; | |
4ed46869 | 4532 | } |
ec6d2bb8 | 4533 | |
b73bfc1c KH |
4534 | /* Now encode the character C. */ |
4535 | if (c < 0x20 || c == 0x7F) | |
4536 | { | |
df7492f9 KH |
4537 | if (c == '\n' |
4538 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4539 | { |
df7492f9 KH |
4540 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4541 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4542 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4543 | { |
df7492f9 KH |
4544 | int i; |
4545 | ||
4546 | for (i = 0; i < 4; i++) | |
4547 | CODING_ISO_DESIGNATION (coding, i) | |
4548 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4549 | } |
df7492f9 KH |
4550 | bol_designation |
4551 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 4552 | } |
df7492f9 KH |
4553 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4554 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4555 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4556 | } |
df7492f9 | 4557 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4558 | { |
df7492f9 KH |
4559 | if (ascii_compatible) |
4560 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4561 | else |
19a8d9e0 | 4562 | { |
bf16eb23 KH |
4563 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4564 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4565 | } |
4ed46869 | 4566 | } |
16eafb5d | 4567 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4568 | { |
16eafb5d KH |
4569 | c = CHAR_TO_BYTE8 (c); |
4570 | EMIT_ONE_BYTE (c); | |
88993dfd | 4571 | } |
b73bfc1c | 4572 | else |
df7492f9 | 4573 | { |
ff0dacd7 | 4574 | struct charset *charset; |
b73bfc1c | 4575 | |
ff0dacd7 KH |
4576 | if (preferred_charset_id >= 0) |
4577 | { | |
4578 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
4579 | if (! CHAR_CHARSET_P (c, charset)) | |
4580 | charset = char_charset (c, charset_list, NULL); | |
4581 | } | |
4582 | else | |
4583 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
4584 | if (!charset) |
4585 | { | |
41cbe562 KH |
4586 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4587 | { | |
4588 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4589 | charset = CHARSET_FROM_ID (charset_ascii); | |
4590 | } | |
4591 | else | |
4592 | { | |
4593 | c = coding->default_char; | |
4594 | charset = char_charset (c, charset_list, NULL); | |
4595 | } | |
df7492f9 KH |
4596 | } |
4597 | ENCODE_ISO_CHARACTER (charset, c); | |
4598 | } | |
84fbb8a0 | 4599 | } |
b73bfc1c | 4600 | |
df7492f9 KH |
4601 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4602 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4603 | { | |
4604 | ASSURE_DESTINATION (safe_room); | |
4605 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4606 | } | |
065e3595 | 4607 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4608 | CODING_ISO_BOL (coding) = bol_designation; |
4609 | coding->produced_char += produced_chars; | |
4610 | coding->produced = dst - coding->destination; | |
4611 | return 0; | |
4ed46869 KH |
4612 | } |
4613 | ||
4614 | \f | |
df7492f9 | 4615 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4616 | |
df7492f9 | 4617 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4618 | quite widely. So, for the moment, Emacs supports them in the bare |
4619 | C code. But, in the future, they may be supported only by CCL. */ | |
4620 | ||
4621 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4622 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4623 | as is. A character of charset katakana-jisx0201 is encoded by | |
4624 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4625 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4626 | so that it fit in the range below. |
4ed46869 KH |
4627 | |
4628 | --- CODE RANGE of SJIS --- | |
4629 | (character set) (range) | |
4630 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4631 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4632 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4633 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4634 | ------------------------------- |
4635 | ||
4636 | */ | |
4637 | ||
4638 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4639 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4640 | character set and is encoded in two-byte. |
4ed46869 KH |
4641 | |
4642 | --- CODE RANGE of BIG5 --- | |
4643 | (character set) (range) | |
4644 | ASCII 0x00 .. 0x7F | |
4645 | Big5 (1st byte) 0xA1 .. 0xFE | |
4646 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4647 | -------------------------- | |
4648 | ||
df7492f9 | 4649 | */ |
4ed46869 KH |
4650 | |
4651 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4652 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 4653 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 4654 | |
0a28aafb | 4655 | static int |
cf84bb53 JB |
4656 | detect_coding_sjis (struct coding_system *coding, |
4657 | struct coding_detection_info *detect_info) | |
4ed46869 | 4658 | { |
065e3595 | 4659 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4660 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4661 | int multibytep = coding->src_multibyte; |
4662 | int consumed_chars = 0; | |
4663 | int found = 0; | |
b73bfc1c | 4664 | int c; |
f07190ca KH |
4665 | Lisp_Object attrs, charset_list; |
4666 | int max_first_byte_of_2_byte_code; | |
4667 | ||
4668 | CODING_GET_INFO (coding, attrs, charset_list); | |
4669 | max_first_byte_of_2_byte_code | |
4670 | = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF); | |
df7492f9 | 4671 | |
ff0dacd7 | 4672 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4673 | /* A coding system of this category is always ASCII compatible. */ |
4674 | src += coding->head_ascii; | |
4ed46869 | 4675 | |
b73bfc1c | 4676 | while (1) |
4ed46869 | 4677 | { |
065e3595 | 4678 | src_base = src; |
df7492f9 | 4679 | ONE_MORE_BYTE (c); |
682169fe KH |
4680 | if (c < 0x80) |
4681 | continue; | |
f07190ca KH |
4682 | if ((c >= 0x81 && c <= 0x9F) |
4683 | || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code)) | |
4ed46869 | 4684 | { |
df7492f9 | 4685 | ONE_MORE_BYTE (c); |
682169fe | 4686 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4687 | break; |
ff0dacd7 | 4688 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4689 | } |
df7492f9 | 4690 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4691 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4692 | else |
4693 | break; | |
4ed46869 | 4694 | } |
ff0dacd7 | 4695 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4696 | return 0; |
4697 | ||
4698 | no_more_source: | |
065e3595 | 4699 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4700 | { |
ff0dacd7 | 4701 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 4702 | return 0; |
4ed46869 | 4703 | } |
ff0dacd7 KH |
4704 | detect_info->found |= found; |
4705 | return 1; | |
4ed46869 KH |
4706 | } |
4707 | ||
4708 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4709 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 4710 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 4711 | |
0a28aafb | 4712 | static int |
cf84bb53 JB |
4713 | detect_coding_big5 (struct coding_system *coding, |
4714 | struct coding_detection_info *detect_info) | |
4ed46869 | 4715 | { |
065e3595 | 4716 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4717 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4718 | int multibytep = coding->src_multibyte; |
4719 | int consumed_chars = 0; | |
4720 | int found = 0; | |
b73bfc1c | 4721 | int c; |
fa42c37f | 4722 | |
ff0dacd7 | 4723 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4724 | /* A coding system of this category is always ASCII compatible. */ |
4725 | src += coding->head_ascii; | |
fa42c37f | 4726 | |
b73bfc1c | 4727 | while (1) |
fa42c37f | 4728 | { |
065e3595 | 4729 | src_base = src; |
df7492f9 KH |
4730 | ONE_MORE_BYTE (c); |
4731 | if (c < 0x80) | |
fa42c37f | 4732 | continue; |
df7492f9 | 4733 | if (c >= 0xA1) |
fa42c37f | 4734 | { |
df7492f9 KH |
4735 | ONE_MORE_BYTE (c); |
4736 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4737 | return 0; |
ff0dacd7 | 4738 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4739 | } |
df7492f9 KH |
4740 | else |
4741 | break; | |
fa42c37f | 4742 | } |
ff0dacd7 | 4743 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4744 | return 0; |
fa42c37f | 4745 | |
df7492f9 | 4746 | no_more_source: |
065e3595 | 4747 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4748 | { |
ff0dacd7 | 4749 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4750 | return 0; |
4751 | } | |
ff0dacd7 KH |
4752 | detect_info->found |= found; |
4753 | return 1; | |
fa42c37f KH |
4754 | } |
4755 | ||
4ed46869 KH |
4756 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4757 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4758 | |
b73bfc1c | 4759 | static void |
971de7fb | 4760 | decode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4761 | { |
8f924df7 KH |
4762 | const unsigned char *src = coding->source + coding->consumed; |
4763 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4764 | const unsigned char *src_base; | |
69a80ea3 | 4765 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
4766 | /* We may produce one charset annocation in one loop and one more at |
4767 | the end. */ | |
69a80ea3 | 4768 | int *charbuf_end |
df80c7f0 | 4769 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
4770 | int consumed_chars = 0, consumed_chars_base; |
4771 | int multibytep = coding->src_multibyte; | |
4772 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4773 | struct charset *charset_kanji2; |
24a73b0a | 4774 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4775 | int char_offset = coding->produced_char; |
4776 | int last_offset = char_offset; | |
4777 | int last_id = charset_ascii; | |
0a9564cb EZ |
4778 | int eol_crlf = |
4779 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4780 | int byte_after_cr = -1; |
a5d301df | 4781 | |
24a73b0a | 4782 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4783 | |
4784 | val = charset_list; | |
4785 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4786 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4787 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4788 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4789 | |
b73bfc1c | 4790 | while (1) |
4ed46869 | 4791 | { |
df7492f9 | 4792 | int c, c1; |
24a73b0a | 4793 | struct charset *charset; |
fa42c37f | 4794 | |
b73bfc1c | 4795 | src_base = src; |
df7492f9 | 4796 | consumed_chars_base = consumed_chars; |
fa42c37f | 4797 | |
df7492f9 | 4798 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4799 | { |
4800 | if (byte_after_cr >= 0) | |
4801 | src_base--; | |
4802 | break; | |
4803 | } | |
df7492f9 | 4804 | |
119852e7 KH |
4805 | if (byte_after_cr >= 0) |
4806 | c = byte_after_cr, byte_after_cr = -1; | |
4807 | else | |
4808 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4809 | if (c < 0) |
4810 | goto invalid_code; | |
24a73b0a | 4811 | if (c < 0x80) |
119852e7 KH |
4812 | { |
4813 | if (eol_crlf && c == '\r') | |
4814 | ONE_MORE_BYTE (byte_after_cr); | |
4815 | charset = charset_roman; | |
4816 | } | |
57a47f8a | 4817 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4818 | goto invalid_code; |
57a47f8a KH |
4819 | else if (c >= 0xA1 && c <= 0xDF) |
4820 | { | |
4821 | /* SJIS -> JISX0201-Kana */ | |
4822 | c &= 0x7F; | |
4823 | charset = charset_kana; | |
4824 | } | |
4825 | else if (c <= 0xEF) | |
df7492f9 | 4826 | { |
57a47f8a KH |
4827 | /* SJIS -> JISX0208 */ |
4828 | ONE_MORE_BYTE (c1); | |
4829 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4830 | goto invalid_code; |
57a47f8a KH |
4831 | c = (c << 8) | c1; |
4832 | SJIS_TO_JIS (c); | |
4833 | charset = charset_kanji; | |
4834 | } | |
4835 | else if (c <= 0xFC && charset_kanji2) | |
4836 | { | |
c6876370 | 4837 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4838 | ONE_MORE_BYTE (c1); |
4839 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4840 | goto invalid_code; |
57a47f8a KH |
4841 | c = (c << 8) | c1; |
4842 | SJIS_TO_JIS2 (c); | |
4843 | charset = charset_kanji2; | |
df7492f9 | 4844 | } |
57a47f8a KH |
4845 | else |
4846 | goto invalid_code; | |
24a73b0a KH |
4847 | if (charset->id != charset_ascii |
4848 | && last_id != charset->id) | |
4849 | { | |
4850 | if (last_id != charset_ascii) | |
69a80ea3 | 4851 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4852 | last_id = charset->id; |
4853 | last_offset = char_offset; | |
4854 | } | |
4855 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4856 | *charbuf++ = c; |
ff0dacd7 | 4857 | char_offset++; |
df7492f9 | 4858 | continue; |
b73bfc1c | 4859 | |
df7492f9 KH |
4860 | invalid_code: |
4861 | src = src_base; | |
4862 | consumed_chars = consumed_chars_base; | |
4863 | ONE_MORE_BYTE (c); | |
065e3595 | 4864 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4865 | char_offset++; |
df7492f9 KH |
4866 | coding->errors++; |
4867 | } | |
fa42c37f | 4868 | |
df7492f9 | 4869 | no_more_source: |
ff0dacd7 | 4870 | if (last_id != charset_ascii) |
69a80ea3 | 4871 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4872 | coding->consumed_char += consumed_chars_base; |
4873 | coding->consumed = src_base - coding->source; | |
4874 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4875 | } |
4876 | ||
b73bfc1c | 4877 | static void |
971de7fb | 4878 | decode_coding_big5 (struct coding_system *coding) |
4ed46869 | 4879 | { |
8f924df7 KH |
4880 | const unsigned char *src = coding->source + coding->consumed; |
4881 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4882 | const unsigned char *src_base; | |
69a80ea3 | 4883 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
4884 | /* We may produce one charset annocation in one loop and one more at |
4885 | the end. */ | |
69a80ea3 | 4886 | int *charbuf_end |
df80c7f0 | 4887 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
4888 | int consumed_chars = 0, consumed_chars_base; |
4889 | int multibytep = coding->src_multibyte; | |
4890 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4891 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4892 | int char_offset = coding->produced_char; |
4893 | int last_offset = char_offset; | |
4894 | int last_id = charset_ascii; | |
0a9564cb EZ |
4895 | int eol_crlf = |
4896 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4897 | int byte_after_cr = -1; |
df7492f9 | 4898 | |
24a73b0a | 4899 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4900 | val = charset_list; |
4901 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4902 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4903 | |
b73bfc1c | 4904 | while (1) |
4ed46869 | 4905 | { |
df7492f9 | 4906 | int c, c1; |
24a73b0a | 4907 | struct charset *charset; |
b73bfc1c KH |
4908 | |
4909 | src_base = src; | |
df7492f9 KH |
4910 | consumed_chars_base = consumed_chars; |
4911 | ||
4912 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4913 | { |
4914 | if (byte_after_cr >= 0) | |
4915 | src_base--; | |
4916 | break; | |
4917 | } | |
df7492f9 | 4918 | |
119852e7 | 4919 | if (byte_after_cr >= 0) |
14daee73 | 4920 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4921 | else |
4922 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4923 | |
065e3595 KH |
4924 | if (c < 0) |
4925 | goto invalid_code; | |
24a73b0a | 4926 | if (c < 0x80) |
119852e7 | 4927 | { |
14daee73 | 4928 | if (eol_crlf && c == '\r') |
119852e7 KH |
4929 | ONE_MORE_BYTE (byte_after_cr); |
4930 | charset = charset_roman; | |
4931 | } | |
24a73b0a | 4932 | else |
4ed46869 | 4933 | { |
24a73b0a KH |
4934 | /* BIG5 -> Big5 */ |
4935 | if (c < 0xA1 || c > 0xFE) | |
4936 | goto invalid_code; | |
4937 | ONE_MORE_BYTE (c1); | |
4938 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4939 | goto invalid_code; | |
4940 | c = c << 8 | c1; | |
4941 | charset = charset_big5; | |
4ed46869 | 4942 | } |
24a73b0a KH |
4943 | if (charset->id != charset_ascii |
4944 | && last_id != charset->id) | |
df7492f9 | 4945 | { |
24a73b0a | 4946 | if (last_id != charset_ascii) |
69a80ea3 | 4947 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4948 | last_id = charset->id; |
4949 | last_offset = char_offset; | |
4ed46869 | 4950 | } |
24a73b0a | 4951 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4952 | *charbuf++ = c; |
ff0dacd7 | 4953 | char_offset++; |
fb88bf2d KH |
4954 | continue; |
4955 | ||
df7492f9 | 4956 | invalid_code: |
4ed46869 | 4957 | src = src_base; |
df7492f9 KH |
4958 | consumed_chars = consumed_chars_base; |
4959 | ONE_MORE_BYTE (c); | |
065e3595 | 4960 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4961 | char_offset++; |
df7492f9 | 4962 | coding->errors++; |
fb88bf2d | 4963 | } |
d46c5b12 | 4964 | |
df7492f9 | 4965 | no_more_source: |
ff0dacd7 | 4966 | if (last_id != charset_ascii) |
69a80ea3 | 4967 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4968 | coding->consumed_char += consumed_chars_base; |
4969 | coding->consumed = src_base - coding->source; | |
4970 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4971 | } |
4972 | ||
4973 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4974 | This function can encode charsets `ascii', `katakana-jisx0201', |
4975 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4976 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4977 | (i.e. do not have extended leading-codes). Characters of other |
4978 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4979 | SJIS text, else encode BIG5 text. */ | |
4980 | ||
df7492f9 | 4981 | static int |
971de7fb | 4982 | encode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4983 | { |
df7492f9 KH |
4984 | int multibytep = coding->dst_multibyte; |
4985 | int *charbuf = coding->charbuf; | |
4986 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4987 | unsigned char *dst = coding->destination + coding->produced; | |
4988 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4989 | int safe_room = 4; | |
4990 | int produced_chars = 0; | |
24a73b0a | 4991 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4992 | int ascii_compatible; |
4993 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4994 | struct charset *charset_kanji2; |
df7492f9 | 4995 | int c; |
a5d301df | 4996 | |
24a73b0a | 4997 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4998 | val = charset_list; |
4999 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
5000 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
5001 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
5002 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 5003 | |
df7492f9 | 5004 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 5005 | |
df7492f9 KH |
5006 | while (charbuf < charbuf_end) |
5007 | { | |
5008 | ASSURE_DESTINATION (safe_room); | |
5009 | c = *charbuf++; | |
b73bfc1c | 5010 | /* Now encode the character C. */ |
df7492f9 KH |
5011 | if (ASCII_CHAR_P (c) && ascii_compatible) |
5012 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
5013 | else if (CHAR_BYTE8_P (c)) |
5014 | { | |
5015 | c = CHAR_TO_BYTE8 (c); | |
5016 | EMIT_ONE_BYTE (c); | |
5017 | } | |
df7492f9 | 5018 | else |
b73bfc1c | 5019 | { |
df7492f9 KH |
5020 | unsigned code; |
5021 | struct charset *charset = char_charset (c, charset_list, &code); | |
5022 | ||
5023 | if (!charset) | |
4ed46869 | 5024 | { |
41cbe562 | 5025 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 5026 | { |
41cbe562 KH |
5027 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
5028 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 5029 | } |
41cbe562 | 5030 | else |
b73bfc1c | 5031 | { |
41cbe562 KH |
5032 | c = coding->default_char; |
5033 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 5034 | } |
b73bfc1c | 5035 | } |
df7492f9 KH |
5036 | if (code == CHARSET_INVALID_CODE (charset)) |
5037 | abort (); | |
5038 | if (charset == charset_kanji) | |
5039 | { | |
5040 | int c1, c2; | |
5041 | JIS_TO_SJIS (code); | |
5042 | c1 = code >> 8, c2 = code & 0xFF; | |
5043 | EMIT_TWO_BYTES (c1, c2); | |
5044 | } | |
5045 | else if (charset == charset_kana) | |
5046 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
5047 | else if (charset_kanji2 && charset == charset_kanji2) |
5048 | { | |
5049 | int c1, c2; | |
5050 | ||
5051 | c1 = code >> 8; | |
f07190ca KH |
5052 | if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25) |
5053 | || c1 == 0x28 | |
57a47f8a KH |
5054 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) |
5055 | { | |
5056 | JIS_TO_SJIS2 (code); | |
5057 | c1 = code >> 8, c2 = code & 0xFF; | |
5058 | EMIT_TWO_BYTES (c1, c2); | |
5059 | } | |
5060 | else | |
5061 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
5062 | } | |
df7492f9 KH |
5063 | else |
5064 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
5065 | } | |
5066 | } | |
065e3595 | 5067 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5068 | coding->produced_char += produced_chars; |
5069 | coding->produced = dst - coding->destination; | |
5070 | return 0; | |
5071 | } | |
5072 | ||
5073 | static int | |
971de7fb | 5074 | encode_coding_big5 (struct coding_system *coding) |
df7492f9 KH |
5075 | { |
5076 | int multibytep = coding->dst_multibyte; | |
5077 | int *charbuf = coding->charbuf; | |
5078 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5079 | unsigned char *dst = coding->destination + coding->produced; | |
5080 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5081 | int safe_room = 4; | |
5082 | int produced_chars = 0; | |
24a73b0a | 5083 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
5084 | int ascii_compatible; |
5085 | struct charset *charset_roman, *charset_big5; | |
5086 | int c; | |
5087 | ||
24a73b0a | 5088 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
5089 | val = charset_list; |
5090 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
5091 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
5092 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
5093 | ||
5094 | while (charbuf < charbuf_end) | |
5095 | { | |
5096 | ASSURE_DESTINATION (safe_room); | |
5097 | c = *charbuf++; | |
5098 | /* Now encode the character C. */ | |
5099 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
5100 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
5101 | else if (CHAR_BYTE8_P (c)) |
5102 | { | |
5103 | c = CHAR_TO_BYTE8 (c); | |
5104 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
5105 | } |
5106 | else | |
5107 | { | |
df7492f9 KH |
5108 | unsigned code; |
5109 | struct charset *charset = char_charset (c, charset_list, &code); | |
5110 | ||
5111 | if (! charset) | |
b73bfc1c | 5112 | { |
41cbe562 | 5113 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 5114 | { |
41cbe562 KH |
5115 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
5116 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 5117 | } |
41cbe562 | 5118 | else |
0eecad43 | 5119 | { |
41cbe562 KH |
5120 | c = coding->default_char; |
5121 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 5122 | } |
4ed46869 | 5123 | } |
df7492f9 KH |
5124 | if (code == CHARSET_INVALID_CODE (charset)) |
5125 | abort (); | |
5126 | if (charset == charset_big5) | |
b73bfc1c | 5127 | { |
df7492f9 KH |
5128 | int c1, c2; |
5129 | ||
5130 | c1 = code >> 8, c2 = code & 0xFF; | |
5131 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 5132 | } |
df7492f9 KH |
5133 | else |
5134 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 5135 | } |
4ed46869 | 5136 | } |
065e3595 | 5137 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5138 | coding->produced_char += produced_chars; |
5139 | coding->produced = dst - coding->destination; | |
5140 | return 0; | |
4ed46869 KH |
5141 | } |
5142 | ||
5143 | \f | |
df7492f9 | 5144 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
5145 | |
5146 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
5147 | Check if a text is encoded in a coding system of which | |
5148 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 5149 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 5150 | |
0a28aafb | 5151 | static int |
cf84bb53 JB |
5152 | detect_coding_ccl (struct coding_system *coding, |
5153 | struct coding_detection_info *detect_info) | |
1397dc18 | 5154 | { |
065e3595 | 5155 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5156 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5157 | int multibytep = coding->src_multibyte; |
5158 | int consumed_chars = 0; | |
5159 | int found = 0; | |
0e219d54 | 5160 | unsigned char *valids; |
df7492f9 KH |
5161 | int head_ascii = coding->head_ascii; |
5162 | Lisp_Object attrs; | |
5163 | ||
ff0dacd7 KH |
5164 | detect_info->checked |= CATEGORY_MASK_CCL; |
5165 | ||
df7492f9 | 5166 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 5167 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
5168 | attrs = CODING_ID_ATTRS (coding->id); |
5169 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
5170 | src += head_ascii; | |
1397dc18 | 5171 | |
b73bfc1c | 5172 | while (1) |
1397dc18 | 5173 | { |
df7492f9 | 5174 | int c; |
065e3595 KH |
5175 | |
5176 | src_base = src; | |
df7492f9 | 5177 | ONE_MORE_BYTE (c); |
065e3595 | 5178 | if (c < 0 || ! valids[c]) |
df7492f9 | 5179 | break; |
ff0dacd7 KH |
5180 | if ((valids[c] > 1)) |
5181 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 5182 | } |
ff0dacd7 | 5183 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
5184 | return 0; |
5185 | ||
5186 | no_more_source: | |
ff0dacd7 KH |
5187 | detect_info->found |= found; |
5188 | return 1; | |
df7492f9 KH |
5189 | } |
5190 | ||
5191 | static void | |
971de7fb | 5192 | decode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5193 | { |
7c78e542 | 5194 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 5195 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
5196 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5197 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
5198 | int consumed_chars = 0; |
5199 | int multibytep = coding->src_multibyte; | |
d0396581 | 5200 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 | 5201 | int source_charbuf[1024]; |
fbdc1721 | 5202 | int source_byteidx[1025]; |
24a73b0a | 5203 | Lisp_Object attrs, charset_list; |
df7492f9 | 5204 | |
24a73b0a | 5205 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5206 | |
d0396581 | 5207 | while (1) |
df7492f9 | 5208 | { |
7c78e542 | 5209 | const unsigned char *p = src; |
df7492f9 KH |
5210 | int i = 0; |
5211 | ||
5212 | if (multibytep) | |
fbdc1721 KH |
5213 | { |
5214 | while (i < 1024 && p < src_end) | |
5215 | { | |
5216 | source_byteidx[i] = p - src; | |
5217 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
5218 | } | |
5219 | source_byteidx[i] = p - src; | |
5220 | } | |
df7492f9 KH |
5221 | else |
5222 | while (i < 1024 && p < src_end) | |
5223 | source_charbuf[i++] = *p++; | |
8f924df7 | 5224 | |
df7492f9 | 5225 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
d0396581 KH |
5226 | ccl->last_block = 1; |
5227 | ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf, | |
5228 | charset_list); | |
5229 | charbuf += ccl->produced; | |
fbdc1721 | 5230 | if (multibytep) |
d0396581 | 5231 | src += source_byteidx[ccl->consumed]; |
df7492f9 | 5232 | else |
d0396581 KH |
5233 | src += ccl->consumed; |
5234 | consumed_chars += ccl->consumed; | |
5235 | if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC) | |
df7492f9 KH |
5236 | break; |
5237 | } | |
5238 | ||
d0396581 | 5239 | switch (ccl->status) |
df7492f9 KH |
5240 | { |
5241 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5242 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5243 | break; |
5244 | case CCL_STAT_SUSPEND_BY_DST: | |
d0396581 | 5245 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5246 | break; |
5247 | case CCL_STAT_QUIT: | |
5248 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5249 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5250 | break; |
5251 | default: | |
065e3595 | 5252 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5253 | break; |
5254 | } | |
5255 | coding->consumed_char += consumed_chars; | |
5256 | coding->consumed = src - coding->source; | |
5257 | coding->charbuf_used = charbuf - coding->charbuf; | |
5258 | } | |
5259 | ||
5260 | static int | |
971de7fb | 5261 | encode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5262 | { |
fb608df3 | 5263 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 KH |
5264 | int multibytep = coding->dst_multibyte; |
5265 | int *charbuf = coding->charbuf; | |
5266 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5267 | unsigned char *dst = coding->destination + coding->produced; | |
5268 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 KH |
5269 | int destination_charbuf[1024]; |
5270 | int i, produced_chars = 0; | |
24a73b0a | 5271 | Lisp_Object attrs, charset_list; |
df7492f9 | 5272 | |
24a73b0a | 5273 | CODING_GET_INFO (coding, attrs, charset_list); |
fb608df3 KH |
5274 | if (coding->consumed_char == coding->src_chars |
5275 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
5276 | ccl->last_block = 1; | |
df7492f9 | 5277 | |
8cffd3e7 | 5278 | while (charbuf < charbuf_end) |
df7492f9 | 5279 | { |
fb608df3 | 5280 | ccl_driver (ccl, charbuf, destination_charbuf, |
8cffd3e7 | 5281 | charbuf_end - charbuf, 1024, charset_list); |
df7492f9 | 5282 | if (multibytep) |
8cffd3e7 | 5283 | { |
fb608df3 KH |
5284 | ASSURE_DESTINATION (ccl->produced * 2); |
5285 | for (i = 0; i < ccl->produced; i++) | |
8cffd3e7 KH |
5286 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); |
5287 | } | |
df7492f9 KH |
5288 | else |
5289 | { | |
fb608df3 KH |
5290 | ASSURE_DESTINATION (ccl->produced); |
5291 | for (i = 0; i < ccl->produced; i++) | |
df7492f9 | 5292 | *dst++ = destination_charbuf[i] & 0xFF; |
fb608df3 | 5293 | produced_chars += ccl->produced; |
df7492f9 | 5294 | } |
fb608df3 KH |
5295 | charbuf += ccl->consumed; |
5296 | if (ccl->status == CCL_STAT_QUIT | |
5297 | || ccl->status == CCL_STAT_INVALID_CMD) | |
8cffd3e7 | 5298 | break; |
df7492f9 KH |
5299 | } |
5300 | ||
fb608df3 | 5301 | switch (ccl->status) |
df7492f9 KH |
5302 | { |
5303 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5304 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5305 | break; |
5306 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 5307 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5308 | break; |
5309 | case CCL_STAT_QUIT: | |
5310 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5311 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5312 | break; |
5313 | default: | |
065e3595 | 5314 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5315 | break; |
1397dc18 | 5316 | } |
df7492f9 KH |
5317 | |
5318 | coding->produced_char += produced_chars; | |
5319 | coding->produced = dst - coding->destination; | |
5320 | return 0; | |
1397dc18 KH |
5321 | } |
5322 | ||
df7492f9 | 5323 | |
1397dc18 | 5324 | \f |
df7492f9 | 5325 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 5326 | |
b73bfc1c | 5327 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 5328 | |
b73bfc1c | 5329 | static void |
971de7fb | 5330 | decode_coding_raw_text (struct coding_system *coding) |
4ed46869 | 5331 | { |
0a9564cb EZ |
5332 | int eol_crlf = |
5333 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5334 | |
df7492f9 | 5335 | coding->chars_at_source = 1; |
119852e7 KH |
5336 | coding->consumed_char = coding->src_chars; |
5337 | coding->consumed = coding->src_bytes; | |
5338 | if (eol_crlf && coding->source[coding->src_bytes - 1] == '\r') | |
5339 | { | |
5340 | coding->consumed_char--; | |
5341 | coding->consumed--; | |
5342 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
5343 | } | |
5344 | else | |
5345 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 5346 | } |
4ed46869 | 5347 | |
df7492f9 | 5348 | static int |
971de7fb | 5349 | encode_coding_raw_text (struct coding_system *coding) |
df7492f9 KH |
5350 | { |
5351 | int multibytep = coding->dst_multibyte; | |
5352 | int *charbuf = coding->charbuf; | |
5353 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5354 | unsigned char *dst = coding->destination + coding->produced; | |
5355 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
a0ed9b27 | 5356 | int produced_chars = 0; |
b73bfc1c KH |
5357 | int c; |
5358 | ||
df7492f9 | 5359 | if (multibytep) |
b73bfc1c | 5360 | { |
df7492f9 | 5361 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5362 | |
df7492f9 KH |
5363 | if (coding->src_multibyte) |
5364 | while (charbuf < charbuf_end) | |
5365 | { | |
5366 | ASSURE_DESTINATION (safe_room); | |
5367 | c = *charbuf++; | |
5368 | if (ASCII_CHAR_P (c)) | |
5369 | EMIT_ONE_ASCII_BYTE (c); | |
5370 | else if (CHAR_BYTE8_P (c)) | |
5371 | { | |
5372 | c = CHAR_TO_BYTE8 (c); | |
5373 | EMIT_ONE_BYTE (c); | |
5374 | } | |
5375 | else | |
5376 | { | |
5377 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5378 | |
df7492f9 KH |
5379 | CHAR_STRING_ADVANCE (c, p1); |
5380 | while (p0 < p1) | |
9d123124 KH |
5381 | { |
5382 | EMIT_ONE_BYTE (*p0); | |
5383 | p0++; | |
5384 | } | |
df7492f9 KH |
5385 | } |
5386 | } | |
b73bfc1c | 5387 | else |
df7492f9 KH |
5388 | while (charbuf < charbuf_end) |
5389 | { | |
5390 | ASSURE_DESTINATION (safe_room); | |
5391 | c = *charbuf++; | |
5392 | EMIT_ONE_BYTE (c); | |
5393 | } | |
5394 | } | |
5395 | else | |
4ed46869 | 5396 | { |
df7492f9 | 5397 | if (coding->src_multibyte) |
d46c5b12 | 5398 | { |
df7492f9 KH |
5399 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5400 | ||
5401 | while (charbuf < charbuf_end) | |
d46c5b12 | 5402 | { |
df7492f9 KH |
5403 | ASSURE_DESTINATION (safe_room); |
5404 | c = *charbuf++; | |
5405 | if (ASCII_CHAR_P (c)) | |
5406 | *dst++ = c; | |
5407 | else if (CHAR_BYTE8_P (c)) | |
5408 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5409 | else |
df7492f9 | 5410 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5411 | } |
5412 | } | |
df7492f9 KH |
5413 | else |
5414 | { | |
5415 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5416 | while (charbuf < charbuf_end && dst < dst_end) | |
5417 | *dst++ = *charbuf++; | |
8f924df7 | 5418 | } |
319a3947 | 5419 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5420 | } |
065e3595 | 5421 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5422 | coding->produced_char += produced_chars; |
df7492f9 KH |
5423 | coding->produced = dst - coding->destination; |
5424 | return 0; | |
4ed46869 KH |
5425 | } |
5426 | ||
ff0dacd7 KH |
5427 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
5428 | Check if a text is encoded in a charset-based coding system. If it | |
5429 | is, return 1, else return 0. */ | |
5430 | ||
0a28aafb | 5431 | static int |
cf84bb53 JB |
5432 | detect_coding_charset (struct coding_system *coding, |
5433 | struct coding_detection_info *detect_info) | |
1397dc18 | 5434 | { |
065e3595 | 5435 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5436 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5437 | int multibytep = coding->src_multibyte; |
5438 | int consumed_chars = 0; | |
07295713 | 5439 | Lisp_Object attrs, valids, name; |
584948ac | 5440 | int found = 0; |
716b3fa0 | 5441 | int head_ascii = coding->head_ascii; |
07295713 | 5442 | int check_latin_extra = 0; |
1397dc18 | 5443 | |
ff0dacd7 KH |
5444 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5445 | ||
df7492f9 KH |
5446 | coding = &coding_categories[coding_category_charset]; |
5447 | attrs = CODING_ID_ATTRS (coding->id); | |
5448 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 | 5449 | name = CODING_ID_NAME (coding->id); |
237aabf4 JR |
5450 | if (strncmp ((char *) SDATA (SYMBOL_NAME (name)), |
5451 | "iso-8859-", sizeof ("iso-8859-") - 1) == 0 | |
5452 | || strncmp ((char *) SDATA (SYMBOL_NAME (name)), | |
5453 | "iso-latin-", sizeof ("iso-latin-") - 1) == 0) | |
07295713 | 5454 | check_latin_extra = 1; |
237aabf4 | 5455 | |
df7492f9 | 5456 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5457 | src += head_ascii; |
1397dc18 | 5458 | |
b73bfc1c | 5459 | while (1) |
1397dc18 | 5460 | { |
df7492f9 | 5461 | int c; |
716b3fa0 KH |
5462 | Lisp_Object val; |
5463 | struct charset *charset; | |
5464 | int dim, idx; | |
1397dc18 | 5465 | |
065e3595 | 5466 | src_base = src; |
df7492f9 | 5467 | ONE_MORE_BYTE (c); |
065e3595 KH |
5468 | if (c < 0) |
5469 | continue; | |
716b3fa0 KH |
5470 | val = AREF (valids, c); |
5471 | if (NILP (val)) | |
df7492f9 | 5472 | break; |
584948ac | 5473 | if (c >= 0x80) |
07295713 KH |
5474 | { |
5475 | if (c < 0xA0 | |
237aabf4 JR |
5476 | && check_latin_extra |
5477 | && (!VECTORP (Vlatin_extra_code_table) | |
9f0526cb | 5478 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))) |
07295713 KH |
5479 | break; |
5480 | found = CATEGORY_MASK_CHARSET; | |
5481 | } | |
716b3fa0 KH |
5482 | if (INTEGERP (val)) |
5483 | { | |
5484 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5485 | dim = CHARSET_DIMENSION (charset); | |
5486 | for (idx = 1; idx < dim; idx++) | |
5487 | { | |
5488 | if (src == src_end) | |
5489 | goto too_short; | |
5490 | ONE_MORE_BYTE (c); | |
3ed051d4 | 5491 | if (c < charset->code_space[(dim - 1 - idx) * 2] |
716b3fa0 KH |
5492 | || c > charset->code_space[(dim - 1 - idx) * 2 + 1]) |
5493 | break; | |
5494 | } | |
5495 | if (idx < dim) | |
5496 | break; | |
5497 | } | |
5498 | else | |
5499 | { | |
5500 | idx = 1; | |
5501 | for (; CONSP (val); val = XCDR (val)) | |
5502 | { | |
5503 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5504 | dim = CHARSET_DIMENSION (charset); | |
5505 | while (idx < dim) | |
5506 | { | |
5507 | if (src == src_end) | |
5508 | goto too_short; | |
5509 | ONE_MORE_BYTE (c); | |
5510 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5511 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5512 | break; | |
5513 | idx++; | |
5514 | } | |
5515 | if (idx == dim) | |
5516 | { | |
5517 | val = Qnil; | |
5518 | break; | |
5519 | } | |
5520 | } | |
5521 | if (CONSP (val)) | |
5522 | break; | |
5523 | } | |
df7492f9 | 5524 | } |
716b3fa0 | 5525 | too_short: |
ff0dacd7 | 5526 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5527 | return 0; |
4ed46869 | 5528 | |
df7492f9 | 5529 | no_more_source: |
ff0dacd7 KH |
5530 | detect_info->found |= found; |
5531 | return 1; | |
df7492f9 | 5532 | } |
b73bfc1c | 5533 | |
b73bfc1c | 5534 | static void |
971de7fb | 5535 | decode_coding_charset (struct coding_system *coding) |
4ed46869 | 5536 | { |
8f924df7 KH |
5537 | const unsigned char *src = coding->source + coding->consumed; |
5538 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5539 | const unsigned char *src_base; | |
69a80ea3 | 5540 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
5541 | /* We may produce one charset annocation in one loop and one more at |
5542 | the end. */ | |
69a80ea3 | 5543 | int *charbuf_end |
df80c7f0 | 5544 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
5545 | int consumed_chars = 0, consumed_chars_base; |
5546 | int multibytep = coding->src_multibyte; | |
24a73b0a | 5547 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
5548 | int char_offset = coding->produced_char; |
5549 | int last_offset = char_offset; | |
5550 | int last_id = charset_ascii; | |
0a9564cb EZ |
5551 | int eol_crlf = |
5552 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5553 | int byte_after_cr = -1; |
df7492f9 | 5554 | |
24a73b0a | 5555 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 5556 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5557 | |
df7492f9 | 5558 | while (1) |
4ed46869 | 5559 | { |
4eb6d3f1 | 5560 | int c; |
24a73b0a KH |
5561 | Lisp_Object val; |
5562 | struct charset *charset; | |
5563 | int dim; | |
5564 | int len = 1; | |
5565 | unsigned code; | |
df7492f9 KH |
5566 | |
5567 | src_base = src; | |
5568 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5569 | |
df7492f9 | 5570 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5571 | { |
5572 | if (byte_after_cr >= 0) | |
5573 | src_base--; | |
5574 | break; | |
5575 | } | |
df7492f9 | 5576 | |
119852e7 KH |
5577 | if (byte_after_cr >= 0) |
5578 | { | |
5579 | c = byte_after_cr; | |
5580 | byte_after_cr = -1; | |
5581 | } | |
5582 | else | |
5583 | { | |
5584 | ONE_MORE_BYTE (c); | |
5585 | if (eol_crlf && c == '\r') | |
5586 | ONE_MORE_BYTE (byte_after_cr); | |
5587 | } | |
065e3595 KH |
5588 | if (c < 0) |
5589 | goto invalid_code; | |
24a73b0a KH |
5590 | code = c; |
5591 | ||
5592 | val = AREF (valids, c); | |
1b17adfd | 5593 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5594 | goto invalid_code; |
5595 | if (INTEGERP (val)) | |
d46c5b12 | 5596 | { |
24a73b0a KH |
5597 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5598 | dim = CHARSET_DIMENSION (charset); | |
5599 | while (len < dim) | |
b73bfc1c | 5600 | { |
24a73b0a KH |
5601 | ONE_MORE_BYTE (c); |
5602 | code = (code << 8) | c; | |
5603 | len++; | |
b73bfc1c | 5604 | } |
24a73b0a KH |
5605 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5606 | charset, code, c); | |
d46c5b12 | 5607 | } |
df7492f9 | 5608 | else |
d46c5b12 | 5609 | { |
24a73b0a KH |
5610 | /* VAL is a list of charset IDs. It is assured that the |
5611 | list is sorted by charset dimensions (smaller one | |
5612 | comes first). */ | |
5613 | while (CONSP (val)) | |
4eb6d3f1 | 5614 | { |
24a73b0a | 5615 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5616 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5617 | while (len < dim) |
4eb6d3f1 | 5618 | { |
acb2a965 KH |
5619 | ONE_MORE_BYTE (c); |
5620 | code = (code << 8) | c; | |
f9d71dcd | 5621 | len++; |
4eb6d3f1 | 5622 | } |
24a73b0a KH |
5623 | CODING_DECODE_CHAR (coding, src, src_base, |
5624 | src_end, charset, code, c); | |
5625 | if (c >= 0) | |
5626 | break; | |
5627 | val = XCDR (val); | |
ff0dacd7 | 5628 | } |
d46c5b12 | 5629 | } |
24a73b0a KH |
5630 | if (c < 0) |
5631 | goto invalid_code; | |
5632 | if (charset->id != charset_ascii | |
5633 | && last_id != charset->id) | |
5634 | { | |
5635 | if (last_id != charset_ascii) | |
69a80ea3 | 5636 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5637 | last_id = charset->id; |
5638 | last_offset = char_offset; | |
5639 | } | |
5640 | ||
df7492f9 | 5641 | *charbuf++ = c; |
ff0dacd7 | 5642 | char_offset++; |
df7492f9 KH |
5643 | continue; |
5644 | ||
5645 | invalid_code: | |
5646 | src = src_base; | |
5647 | consumed_chars = consumed_chars_base; | |
5648 | ONE_MORE_BYTE (c); | |
065e3595 | 5649 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5650 | char_offset++; |
df7492f9 | 5651 | coding->errors++; |
4ed46869 KH |
5652 | } |
5653 | ||
df7492f9 | 5654 | no_more_source: |
ff0dacd7 | 5655 | if (last_id != charset_ascii) |
69a80ea3 | 5656 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5657 | coding->consumed_char += consumed_chars_base; |
5658 | coding->consumed = src_base - coding->source; | |
5659 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5660 | } |
5661 | ||
df7492f9 | 5662 | static int |
971de7fb | 5663 | encode_coding_charset (struct coding_system *coding) |
4ed46869 | 5664 | { |
df7492f9 KH |
5665 | int multibytep = coding->dst_multibyte; |
5666 | int *charbuf = coding->charbuf; | |
5667 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5668 | unsigned char *dst = coding->destination + coding->produced; | |
5669 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5670 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
5671 | int produced_chars = 0; | |
24a73b0a | 5672 | Lisp_Object attrs, charset_list; |
df7492f9 | 5673 | int ascii_compatible; |
b73bfc1c | 5674 | int c; |
b73bfc1c | 5675 | |
24a73b0a | 5676 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5677 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5678 | |
df7492f9 | 5679 | while (charbuf < charbuf_end) |
4ed46869 | 5680 | { |
4eb6d3f1 | 5681 | struct charset *charset; |
df7492f9 | 5682 | unsigned code; |
8f924df7 | 5683 | |
df7492f9 KH |
5684 | ASSURE_DESTINATION (safe_room); |
5685 | c = *charbuf++; | |
5686 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5687 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5688 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5689 | { |
16eafb5d KH |
5690 | c = CHAR_TO_BYTE8 (c); |
5691 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5692 | } |
d46c5b12 | 5693 | else |
b73bfc1c | 5694 | { |
4eb6d3f1 KH |
5695 | charset = char_charset (c, charset_list, &code); |
5696 | if (charset) | |
5697 | { | |
5698 | if (CHARSET_DIMENSION (charset) == 1) | |
5699 | EMIT_ONE_BYTE (code); | |
5700 | else if (CHARSET_DIMENSION (charset) == 2) | |
5701 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5702 | else if (CHARSET_DIMENSION (charset) == 3) | |
5703 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5704 | else | |
5705 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5706 | (code >> 8) & 0xFF, code & 0xFF); | |
5707 | } | |
5708 | else | |
41cbe562 KH |
5709 | { |
5710 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5711 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5712 | else | |
5713 | c = coding->default_char; | |
5714 | EMIT_ONE_BYTE (c); | |
5715 | } | |
4ed46869 | 5716 | } |
4ed46869 KH |
5717 | } |
5718 | ||
065e3595 | 5719 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5720 | coding->produced_char += produced_chars; |
5721 | coding->produced = dst - coding->destination; | |
5722 | return 0; | |
4ed46869 KH |
5723 | } |
5724 | ||
5725 | \f | |
1397dc18 | 5726 | /*** 7. C library functions ***/ |
4ed46869 | 5727 | |
df7492f9 KH |
5728 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5729 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5730 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5731 | |
ec6d2bb8 | 5732 | void |
971de7fb | 5733 | setup_coding_system (Lisp_Object coding_system, struct coding_system *coding) |
4ed46869 | 5734 | { |
df7492f9 KH |
5735 | Lisp_Object attrs; |
5736 | Lisp_Object eol_type; | |
5737 | Lisp_Object coding_type; | |
4608c386 | 5738 | Lisp_Object val; |
4ed46869 | 5739 | |
df7492f9 | 5740 | if (NILP (coding_system)) |
ae6f73fa | 5741 | coding_system = Qundecided; |
c07c8e12 | 5742 | |
df7492f9 | 5743 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5744 | |
df7492f9 | 5745 | attrs = CODING_ID_ATTRS (coding->id); |
0a9564cb | 5746 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
1f5dbf34 | 5747 | |
df7492f9 KH |
5748 | coding->mode = 0; |
5749 | coding->head_ascii = -1; | |
4a015c45 KH |
5750 | if (VECTORP (eol_type)) |
5751 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5752 | | CODING_REQUIRE_DETECTION_MASK); | |
5753 | else if (! EQ (eol_type, Qunix)) | |
5754 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5755 | | CODING_REQUIRE_ENCODING_MASK); | |
5756 | else | |
5757 | coding->common_flags = 0; | |
5e5c78be KH |
5758 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5759 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5760 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5761 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5762 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5763 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5764 | |
df7492f9 | 5765 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 | 5766 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5767 | coding->safe_charsets = SDATA (val); |
df7492f9 | 5768 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
624bda09 | 5769 | coding->carryover_bytes = 0; |
4608c386 | 5770 | |
df7492f9 KH |
5771 | coding_type = CODING_ATTR_TYPE (attrs); |
5772 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5773 | { |
df7492f9 KH |
5774 | coding->detector = NULL; |
5775 | coding->decoder = decode_coding_raw_text; | |
5776 | coding->encoder = encode_coding_raw_text; | |
5777 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5778 | } |
df7492f9 | 5779 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5780 | { |
df7492f9 KH |
5781 | int i; |
5782 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5783 | ||
5784 | /* Invoke graphic register 0 to plane 0. */ | |
5785 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5786 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5787 | CODING_ISO_INVOCATION (coding, 1) | |
5788 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5789 | /* Setup the initial status of designation. */ | |
5790 | for (i = 0; i < 4; i++) | |
5791 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5792 | /* Not single shifting initially. */ | |
5793 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5794 | /* Beginning of buffer should also be regarded as bol. */ | |
5795 | CODING_ISO_BOL (coding) = 1; | |
5796 | coding->detector = detect_coding_iso_2022; | |
5797 | coding->decoder = decode_coding_iso_2022; | |
5798 | coding->encoder = encode_coding_iso_2022; | |
5799 | if (flags & CODING_ISO_FLAG_SAFE) | |
5800 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5801 | coding->common_flags |
df7492f9 KH |
5802 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5803 | | CODING_REQUIRE_FLUSHING_MASK); | |
5804 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5805 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5806 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5807 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5808 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5809 | { | |
5810 | setup_iso_safe_charsets (attrs); | |
5811 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 5812 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5813 | coding->safe_charsets = SDATA (val); |
df7492f9 KH |
5814 | } |
5815 | CODING_ISO_FLAGS (coding) = flags; | |
e951386e KH |
5816 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; |
5817 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | |
5818 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | |
5819 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
d46c5b12 | 5820 | } |
df7492f9 | 5821 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5822 | { |
df7492f9 KH |
5823 | coding->detector = detect_coding_charset; |
5824 | coding->decoder = decode_coding_charset; | |
5825 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5826 | coding->common_flags |
df7492f9 | 5827 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5828 | } |
df7492f9 | 5829 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5830 | { |
a470d443 KH |
5831 | val = AREF (attrs, coding_attr_utf_bom); |
5832 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5833 | : EQ (val, Qt) ? utf_with_bom | |
5834 | : utf_without_bom); | |
df7492f9 KH |
5835 | coding->detector = detect_coding_utf_8; |
5836 | coding->decoder = decode_coding_utf_8; | |
5837 | coding->encoder = encode_coding_utf_8; | |
5838 | coding->common_flags | |
5839 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5840 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5841 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5842 | } |
5843 | else if (EQ (coding_type, Qutf_16)) | |
5844 | { | |
a470d443 KH |
5845 | val = AREF (attrs, coding_attr_utf_bom); |
5846 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5847 | : EQ (val, Qt) ? utf_with_bom | |
5848 | : utf_without_bom); | |
df7492f9 | 5849 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5850 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5851 | : utf_16_little_endian); |
e19c3639 | 5852 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5853 | coding->detector = detect_coding_utf_16; |
5854 | coding->decoder = decode_coding_utf_16; | |
5855 | coding->encoder = encode_coding_utf_16; | |
5856 | coding->common_flags | |
5857 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5858 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5859 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5860 | } |
df7492f9 | 5861 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5862 | { |
df7492f9 KH |
5863 | coding->detector = detect_coding_ccl; |
5864 | coding->decoder = decode_coding_ccl; | |
5865 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5866 | coding->common_flags |
df7492f9 KH |
5867 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5868 | | CODING_REQUIRE_FLUSHING_MASK); | |
5869 | } | |
5870 | else if (EQ (coding_type, Qemacs_mule)) | |
5871 | { | |
5872 | coding->detector = detect_coding_emacs_mule; | |
5873 | coding->decoder = decode_coding_emacs_mule; | |
5874 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5875 | coding->common_flags |
df7492f9 | 5876 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
e951386e | 5877 | coding->spec.emacs_mule.full_support = 1; |
df7492f9 KH |
5878 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) |
5879 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5880 | { | |
5881 | Lisp_Object tail, safe_charsets; | |
5882 | int max_charset_id = 0; | |
5883 | ||
5884 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5885 | tail = XCDR (tail)) | |
5886 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5887 | max_charset_id = XFASTINT (XCAR (tail)); | |
1b3b981b AS |
5888 | safe_charsets = make_uninit_string (max_charset_id + 1); |
5889 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
5890 | for (tail = Vemacs_mule_charset_list; CONSP (tail); |
5891 | tail = XCDR (tail)) | |
8f924df7 | 5892 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5893 | coding->max_charset_id = max_charset_id; |
1b3b981b | 5894 | coding->safe_charsets = SDATA (safe_charsets); |
e951386e | 5895 | coding->spec.emacs_mule.full_support = 1; |
df7492f9 | 5896 | } |
e951386e KH |
5897 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; |
5898 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | |
df7492f9 KH |
5899 | } |
5900 | else if (EQ (coding_type, Qshift_jis)) | |
5901 | { | |
5902 | coding->detector = detect_coding_sjis; | |
5903 | coding->decoder = decode_coding_sjis; | |
5904 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5905 | coding->common_flags |
df7492f9 KH |
5906 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5907 | } | |
5908 | else if (EQ (coding_type, Qbig5)) | |
5909 | { | |
5910 | coding->detector = detect_coding_big5; | |
5911 | coding->decoder = decode_coding_big5; | |
5912 | coding->encoder = encode_coding_big5; | |
c952af22 | 5913 | coding->common_flags |
df7492f9 KH |
5914 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5915 | } | |
5916 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5917 | { |
df7492f9 KH |
5918 | coding->detector = NULL; |
5919 | coding->decoder = decode_coding_raw_text; | |
5920 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5921 | if (! EQ (eol_type, Qunix)) |
5922 | { | |
5923 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5924 | if (! VECTORP (eol_type)) | |
5925 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5926 | } | |
5927 | ||
4ed46869 | 5928 | } |
4ed46869 | 5929 | |
df7492f9 | 5930 | return; |
4ed46869 KH |
5931 | } |
5932 | ||
0ff61e78 KH |
5933 | /* Return a list of charsets supported by CODING. */ |
5934 | ||
5935 | Lisp_Object | |
971de7fb | 5936 | coding_charset_list (struct coding_system *coding) |
0ff61e78 | 5937 | { |
35befdaa | 5938 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5939 | |
5940 | CODING_GET_INFO (coding, attrs, charset_list); | |
5941 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5942 | { | |
5943 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5944 | ||
5945 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5946 | charset_list = Viso_2022_charset_list; | |
5947 | } | |
5948 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5949 | { | |
5950 | charset_list = Vemacs_mule_charset_list; | |
5951 | } | |
5952 | return charset_list; | |
5953 | } | |
5954 | ||
5955 | ||
e9f91ece KH |
5956 | /* Return a list of charsets supported by CODING-SYSTEM. */ |
5957 | ||
5958 | Lisp_Object | |
971de7fb | 5959 | coding_system_charset_list (Lisp_Object coding_system) |
e9f91ece KH |
5960 | { |
5961 | int id; | |
5962 | Lisp_Object attrs, charset_list; | |
5963 | ||
5964 | CHECK_CODING_SYSTEM_GET_ID (coding_system, id); | |
5965 | attrs = CODING_ID_ATTRS (id); | |
5966 | ||
5967 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5968 | { | |
5969 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5970 | ||
5971 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5972 | charset_list = Viso_2022_charset_list; | |
5973 | else | |
5974 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5975 | } | |
5976 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5977 | { | |
5978 | charset_list = Vemacs_mule_charset_list; | |
5979 | } | |
5980 | else | |
5981 | { | |
5982 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5983 | } | |
5984 | return charset_list; | |
5985 | } | |
5986 | ||
5987 | ||
df7492f9 KH |
5988 | /* Return raw-text or one of its subsidiaries that has the same |
5989 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5990 | |
df7492f9 | 5991 | Lisp_Object |
971de7fb | 5992 | raw_text_coding_system (Lisp_Object coding_system) |
ec6d2bb8 | 5993 | { |
0be8721c | 5994 | Lisp_Object spec, attrs; |
df7492f9 | 5995 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5996 | |
d3e4cb56 KH |
5997 | if (NILP (coding_system)) |
5998 | return Qraw_text; | |
df7492f9 KH |
5999 | spec = CODING_SYSTEM_SPEC (coding_system); |
6000 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 6001 | |
df7492f9 KH |
6002 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
6003 | return coding_system; | |
ec6d2bb8 | 6004 | |
df7492f9 KH |
6005 | eol_type = AREF (spec, 2); |
6006 | if (VECTORP (eol_type)) | |
6007 | return Qraw_text; | |
6008 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
6009 | raw_text_eol_type = AREF (spec, 2); | |
6010 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
6011 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
6012 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
6013 | } |
6014 | ||
54f78171 | 6015 | |
df7492f9 KH |
6016 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
6017 | does, return one of the subsidiary that has the same eol-spec as | |
fcbcfb64 KH |
6018 | PARENT. Otherwise, return CODING_SYSTEM. If PARENT is nil, |
6019 | inherit end-of-line format from the system's setting | |
6020 | (system_eol_type). */ | |
df7492f9 KH |
6021 | |
6022 | Lisp_Object | |
971de7fb | 6023 | coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent) |
54f78171 | 6024 | { |
3e139625 | 6025 | Lisp_Object spec, eol_type; |
54f78171 | 6026 | |
d3e4cb56 KH |
6027 | if (NILP (coding_system)) |
6028 | coding_system = Qraw_text; | |
df7492f9 | 6029 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 6030 | eol_type = AREF (spec, 2); |
fcbcfb64 | 6031 | if (VECTORP (eol_type)) |
df7492f9 | 6032 | { |
df7492f9 KH |
6033 | Lisp_Object parent_eol_type; |
6034 | ||
fcbcfb64 KH |
6035 | if (! NILP (parent)) |
6036 | { | |
6037 | Lisp_Object parent_spec; | |
6038 | ||
4a015c45 | 6039 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 KH |
6040 | parent_eol_type = AREF (parent_spec, 2); |
6041 | } | |
6042 | else | |
6043 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
6044 | if (EQ (parent_eol_type, Qunix)) |
6045 | coding_system = AREF (eol_type, 0); | |
6046 | else if (EQ (parent_eol_type, Qdos)) | |
6047 | coding_system = AREF (eol_type, 1); | |
6048 | else if (EQ (parent_eol_type, Qmac)) | |
6049 | coding_system = AREF (eol_type, 2); | |
54f78171 | 6050 | } |
df7492f9 | 6051 | return coding_system; |
54f78171 KH |
6052 | } |
6053 | ||
4ed46869 KH |
6054 | /* Emacs has a mechanism to automatically detect a coding system if it |
6055 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
6056 | it's impossible to distinguish some coding systems accurately | |
6057 | because they use the same range of codes. So, at first, coding | |
6058 | systems are categorized into 7, those are: | |
6059 | ||
0ef69138 | 6060 | o coding-category-emacs-mule |
4ed46869 KH |
6061 | |
6062 | The category for a coding system which has the same code range | |
6063 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 6064 | symbol) `emacs-mule' by default. |
4ed46869 KH |
6065 | |
6066 | o coding-category-sjis | |
6067 | ||
6068 | The category for a coding system which has the same code range | |
6069 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 6070 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
6071 | |
6072 | o coding-category-iso-7 | |
6073 | ||
6074 | The category for a coding system which has the same code range | |
7717c392 | 6075 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
6076 | shift and single shift functions. This can encode/decode all |
6077 | charsets. Assigned the coding-system (Lisp symbol) | |
6078 | `iso-2022-7bit' by default. | |
6079 | ||
6080 | o coding-category-iso-7-tight | |
6081 | ||
6082 | Same as coding-category-iso-7 except that this can | |
6083 | encode/decode only the specified charsets. | |
4ed46869 KH |
6084 | |
6085 | o coding-category-iso-8-1 | |
6086 | ||
6087 | The category for a coding system which has the same code range | |
6088 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6089 | for DIMENSION1 charset. This doesn't use any locking shift |
6090 | and single shift functions. Assigned the coding-system (Lisp | |
6091 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
6092 | |
6093 | o coding-category-iso-8-2 | |
6094 | ||
6095 | The category for a coding system which has the same code range | |
6096 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6097 | for DIMENSION2 charset. This doesn't use any locking shift |
6098 | and single shift functions. Assigned the coding-system (Lisp | |
6099 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 6100 | |
7717c392 | 6101 | o coding-category-iso-7-else |
4ed46869 KH |
6102 | |
6103 | The category for a coding system which has the same code range | |
df7492f9 | 6104 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
6105 | single shift functions. Assigned the coding-system (Lisp |
6106 | symbol) `iso-2022-7bit-lock' by default. | |
6107 | ||
6108 | o coding-category-iso-8-else | |
6109 | ||
6110 | The category for a coding system which has the same code range | |
df7492f9 | 6111 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
6112 | single shift functions. Assigned the coding-system (Lisp |
6113 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
6114 | |
6115 | o coding-category-big5 | |
6116 | ||
6117 | The category for a coding system which has the same code range | |
6118 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6119 | `cn-big5' by default. |
4ed46869 | 6120 | |
fa42c37f KH |
6121 | o coding-category-utf-8 |
6122 | ||
6123 | The category for a coding system which has the same code range | |
6e76ae91 | 6124 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
6125 | symbol) `utf-8' by default. |
6126 | ||
6127 | o coding-category-utf-16-be | |
6128 | ||
6129 | The category for a coding system in which a text has an | |
6130 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
6131 | endian at the head. Assigned the coding-system (Lisp symbol) | |
6132 | `utf-16-be' by default. | |
6133 | ||
6134 | o coding-category-utf-16-le | |
6135 | ||
6136 | The category for a coding system in which a text has an | |
6137 | Unicode signature (cf. Unicode Standard) in the order of | |
6138 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
6139 | symbol) `utf-16-le' by default. | |
6140 | ||
1397dc18 KH |
6141 | o coding-category-ccl |
6142 | ||
6143 | The category for a coding system of which encoder/decoder is | |
6144 | written in CCL programs. The default value is nil, i.e., no | |
6145 | coding system is assigned. | |
6146 | ||
4ed46869 KH |
6147 | o coding-category-binary |
6148 | ||
6149 | The category for a coding system not categorized in any of the | |
6150 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6151 | `no-conversion' by default. |
4ed46869 KH |
6152 | |
6153 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 6154 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
6155 | What Emacs does actually is to detect a category of coding system. |
6156 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 6157 | decide only one possible category, it selects a category of the |
4ed46869 KH |
6158 | highest priority. Priorities of categories are also specified by a |
6159 | user in a Lisp variable `coding-category-list'. | |
6160 | ||
6161 | */ | |
6162 | ||
df7492f9 KH |
6163 | #define EOL_SEEN_NONE 0 |
6164 | #define EOL_SEEN_LF 1 | |
6165 | #define EOL_SEEN_CR 2 | |
6166 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 6167 | |
ff0dacd7 KH |
6168 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
6169 | SOURCE is encoded. If CATEGORY is one of | |
6170 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
6171 | two-byte, else they are encoded by one-byte. | |
6172 | ||
6173 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 6174 | |
bc4bc72a | 6175 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
6176 | |
6177 | static int | |
cf84bb53 JB |
6178 | detect_eol (const unsigned char *source, EMACS_INT src_bytes, |
6179 | enum coding_category category) | |
4ed46869 | 6180 | { |
f6cbaf43 | 6181 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 6182 | unsigned char c; |
df7492f9 KH |
6183 | int total = 0; |
6184 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 6185 | |
89528eb3 | 6186 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 6187 | { |
df7492f9 | 6188 | int msb, lsb; |
fa42c37f | 6189 | |
89528eb3 KH |
6190 | msb = category == (coding_category_utf_16_le |
6191 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 6192 | lsb = 1 - msb; |
fa42c37f | 6193 | |
df7492f9 | 6194 | while (src + 1 < src_end) |
fa42c37f | 6195 | { |
df7492f9 KH |
6196 | c = src[lsb]; |
6197 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 6198 | { |
df7492f9 KH |
6199 | int this_eol; |
6200 | ||
6201 | if (c == '\n') | |
6202 | this_eol = EOL_SEEN_LF; | |
6203 | else if (src + 3 >= src_end | |
6204 | || src[msb + 2] != 0 | |
6205 | || src[lsb + 2] != '\n') | |
6206 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 6207 | else |
75f4f1ac EZ |
6208 | { |
6209 | this_eol = EOL_SEEN_CRLF; | |
6210 | src += 2; | |
6211 | } | |
df7492f9 KH |
6212 | |
6213 | if (eol_seen == EOL_SEEN_NONE) | |
6214 | /* This is the first end-of-line. */ | |
6215 | eol_seen = this_eol; | |
6216 | else if (eol_seen != this_eol) | |
fa42c37f | 6217 | { |
75f4f1ac EZ |
6218 | /* The found type is different from what found before. |
6219 | Allow for stray ^M characters in DOS EOL files. */ | |
6220 | if (eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF | |
6221 | || eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR) | |
6222 | eol_seen = EOL_SEEN_CRLF; | |
6223 | else | |
6224 | { | |
6225 | eol_seen = EOL_SEEN_LF; | |
6226 | break; | |
6227 | } | |
fa42c37f | 6228 | } |
df7492f9 KH |
6229 | if (++total == MAX_EOL_CHECK_COUNT) |
6230 | break; | |
fa42c37f | 6231 | } |
df7492f9 | 6232 | src += 2; |
fa42c37f | 6233 | } |
bcf26d6a | 6234 | } |
d46c5b12 | 6235 | else |
c4825358 | 6236 | { |
df7492f9 | 6237 | while (src < src_end) |
27901516 | 6238 | { |
df7492f9 KH |
6239 | c = *src++; |
6240 | if (c == '\n' || c == '\r') | |
6241 | { | |
6242 | int this_eol; | |
d46c5b12 | 6243 | |
df7492f9 KH |
6244 | if (c == '\n') |
6245 | this_eol = EOL_SEEN_LF; | |
6246 | else if (src >= src_end || *src != '\n') | |
6247 | this_eol = EOL_SEEN_CR; | |
6248 | else | |
6249 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 6250 | |
df7492f9 KH |
6251 | if (eol_seen == EOL_SEEN_NONE) |
6252 | /* This is the first end-of-line. */ | |
6253 | eol_seen = this_eol; | |
6254 | else if (eol_seen != this_eol) | |
6255 | { | |
75f4f1ac EZ |
6256 | /* The found type is different from what found before. |
6257 | Allow for stray ^M characters in DOS EOL files. */ | |
6258 | if (eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF | |
6259 | || eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR) | |
6260 | eol_seen = EOL_SEEN_CRLF; | |
6261 | else | |
6262 | { | |
6263 | eol_seen = EOL_SEEN_LF; | |
6264 | break; | |
6265 | } | |
df7492f9 KH |
6266 | } |
6267 | if (++total == MAX_EOL_CHECK_COUNT) | |
6268 | break; | |
6269 | } | |
6270 | } | |
73be902c | 6271 | } |
df7492f9 | 6272 | return eol_seen; |
73be902c KH |
6273 | } |
6274 | ||
df7492f9 | 6275 | |
24a73b0a | 6276 | static Lisp_Object |
971de7fb | 6277 | adjust_coding_eol_type (struct coding_system *coding, int eol_seen) |
73be902c | 6278 | { |
0be8721c | 6279 | Lisp_Object eol_type; |
8f924df7 | 6280 | |
df7492f9 KH |
6281 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6282 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
6283 | { |
6284 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6285 | eol_type = Qunix; | |
6286 | } | |
6f197c07 | 6287 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
6288 | { |
6289 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
6290 | eol_type = Qdos; | |
6291 | } | |
6f197c07 | 6292 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
6293 | { |
6294 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
6295 | eol_type = Qmac; | |
6296 | } | |
6297 | return eol_type; | |
d46c5b12 | 6298 | } |
4ed46869 | 6299 | |
df7492f9 KH |
6300 | /* Detect how a text specified in CODING is encoded. If a coding |
6301 | system is detected, update fields of CODING by the detected coding | |
6302 | system. */ | |
0a28aafb | 6303 | |
df7492f9 | 6304 | void |
971de7fb | 6305 | detect_coding (struct coding_system *coding) |
d46c5b12 | 6306 | { |
8f924df7 | 6307 | const unsigned char *src, *src_end; |
73cce38d | 6308 | int saved_mode = coding->mode; |
d46c5b12 | 6309 | |
df7492f9 KH |
6310 | coding->consumed = coding->consumed_char = 0; |
6311 | coding->produced = coding->produced_char = 0; | |
6312 | coding_set_source (coding); | |
1c3478b0 | 6313 | |
df7492f9 | 6314 | src_end = coding->source + coding->src_bytes; |
c0e16b14 | 6315 | coding->head_ascii = 0; |
1c3478b0 | 6316 | |
df7492f9 KH |
6317 | /* If we have not yet decided the text encoding type, detect it |
6318 | now. */ | |
6319 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 6320 | { |
df7492f9 | 6321 | int c, i; |
6cb21a4f | 6322 | struct coding_detection_info detect_info; |
2f3cbb32 | 6323 | int null_byte_found = 0, eight_bit_found = 0; |
df7492f9 | 6324 | |
6cb21a4f | 6325 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 6326 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 6327 | { |
df7492f9 | 6328 | c = *src; |
6cb21a4f | 6329 | if (c & 0x80) |
6cb21a4f | 6330 | { |
2f3cbb32 | 6331 | eight_bit_found = 1; |
2f3cbb32 KH |
6332 | if (null_byte_found) |
6333 | break; | |
6334 | } | |
6335 | else if (c < 0x20) | |
6336 | { | |
6337 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
6338 | && ! inhibit_iso_escape_detection | |
6339 | && ! detect_info.checked) | |
6cb21a4f | 6340 | { |
2f3cbb32 KH |
6341 | if (detect_coding_iso_2022 (coding, &detect_info)) |
6342 | { | |
6343 | /* We have scanned the whole data. */ | |
6344 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
6345 | { |
6346 | /* We didn't find an 8-bit code. We may | |
6347 | have found a null-byte, but it's very | |
ce5b453a | 6348 | rare that a binary file conforms to |
c0e16b14 KH |
6349 | ISO-2022. */ |
6350 | src = src_end; | |
6351 | coding->head_ascii = src - coding->source; | |
6352 | } | |
6353 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
6354 | break; |
6355 | } | |
6356 | } | |
97b1b294 | 6357 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
6358 | { |
6359 | null_byte_found = 1; | |
6360 | if (eight_bit_found) | |
6361 | break; | |
6cb21a4f | 6362 | } |
c006c0c8 KH |
6363 | if (! eight_bit_found) |
6364 | coding->head_ascii++; | |
6cb21a4f | 6365 | } |
c006c0c8 | 6366 | else if (! eight_bit_found) |
c0e16b14 | 6367 | coding->head_ascii++; |
d46c5b12 | 6368 | } |
df7492f9 | 6369 | |
2f3cbb32 KH |
6370 | if (null_byte_found || eight_bit_found |
6371 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 6372 | || detect_info.found) |
d46c5b12 | 6373 | { |
ff0dacd7 KH |
6374 | enum coding_category category; |
6375 | struct coding_system *this; | |
df7492f9 | 6376 | |
6cb21a4f KH |
6377 | if (coding->head_ascii == coding->src_bytes) |
6378 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
6379 | for (i = 0; i < coding_category_raw_text; i++) | |
6380 | { | |
6381 | category = coding_priorities[i]; | |
6382 | this = coding_categories + category; | |
6383 | if (detect_info.found & (1 << category)) | |
24a73b0a | 6384 | break; |
6cb21a4f KH |
6385 | } |
6386 | else | |
2f3cbb32 KH |
6387 | { |
6388 | if (null_byte_found) | |
ff0dacd7 | 6389 | { |
2f3cbb32 KH |
6390 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
6391 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 6392 | } |
2f3cbb32 KH |
6393 | for (i = 0; i < coding_category_raw_text; i++) |
6394 | { | |
6395 | category = coding_priorities[i]; | |
6396 | this = coding_categories + category; | |
6397 | if (this->id < 0) | |
6398 | { | |
6399 | /* No coding system of this category is defined. */ | |
6400 | detect_info.rejected |= (1 << category); | |
6401 | } | |
6402 | else if (category >= coding_category_raw_text) | |
6403 | continue; | |
6404 | else if (detect_info.checked & (1 << category)) | |
6405 | { | |
6406 | if (detect_info.found & (1 << category)) | |
6407 | break; | |
6408 | } | |
6409 | else if ((*(this->detector)) (coding, &detect_info) | |
6410 | && detect_info.found & (1 << category)) | |
6411 | { | |
6412 | if (category == coding_category_utf_16_auto) | |
6413 | { | |
6414 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6415 | category = coding_category_utf_16_le; | |
6416 | else | |
6417 | category = coding_category_utf_16_be; | |
6418 | } | |
6419 | break; | |
6420 | } | |
6421 | } | |
2f3cbb32 | 6422 | } |
c0e16b14 KH |
6423 | |
6424 | if (i < coding_category_raw_text) | |
6425 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6426 | else if (null_byte_found) | |
6427 | setup_coding_system (Qno_conversion, coding); | |
6428 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) | |
6429 | == CATEGORY_MASK_ANY) | |
6430 | setup_coding_system (Qraw_text, coding); | |
6431 | else if (detect_info.rejected) | |
6432 | for (i = 0; i < coding_category_raw_text; i++) | |
6433 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6434 | { | |
6435 | this = coding_categories + coding_priorities[i]; | |
6436 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6437 | break; | |
6438 | } | |
d46c5b12 | 6439 | } |
b73bfc1c | 6440 | } |
a470d443 KH |
6441 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6442 | == coding_category_utf_8_auto) | |
6443 | { | |
6444 | Lisp_Object coding_systems; | |
6445 | struct coding_detection_info detect_info; | |
6446 | ||
6447 | coding_systems | |
6448 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6449 | detect_info.found = detect_info.rejected = 0; | |
6450 | coding->head_ascii = 0; | |
6451 | if (CONSP (coding_systems) | |
6452 | && detect_coding_utf_8 (coding, &detect_info)) | |
6453 | { | |
6454 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6455 | setup_coding_system (XCAR (coding_systems), coding); | |
6456 | else | |
6457 | setup_coding_system (XCDR (coding_systems), coding); | |
6458 | } | |
6459 | } | |
24a73b0a KH |
6460 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6461 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6462 | { |
6463 | Lisp_Object coding_systems; | |
6464 | struct coding_detection_info detect_info; | |
6465 | ||
6466 | coding_systems | |
a470d443 | 6467 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6468 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6469 | coding->head_ascii = 0; |
b49a1807 | 6470 | if (CONSP (coding_systems) |
24a73b0a | 6471 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6472 | { |
6473 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6474 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 6475 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
6476 | setup_coding_system (XCDR (coding_systems), coding); |
6477 | } | |
6478 | } | |
73cce38d | 6479 | coding->mode = saved_mode; |
4ed46869 | 6480 | } |
4ed46869 | 6481 | |
d46c5b12 | 6482 | |
aaaf0b1e | 6483 | static void |
971de7fb | 6484 | decode_eol (struct coding_system *coding) |
aaaf0b1e | 6485 | { |
24a73b0a KH |
6486 | Lisp_Object eol_type; |
6487 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6488 | |
24a73b0a | 6489 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
0a9564cb | 6490 | if (EQ (eol_type, Qunix) || inhibit_eol_conversion) |
24a73b0a KH |
6491 | return; |
6492 | ||
6493 | if (NILP (coding->dst_object)) | |
6494 | pbeg = coding->destination; | |
6495 | else | |
6496 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6497 | pend = pbeg + coding->produced; | |
6498 | ||
6499 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6500 | { |
df7492f9 | 6501 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6502 | |
24a73b0a | 6503 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6504 | { |
df7492f9 KH |
6505 | if (*p == '\n') |
6506 | eol_seen |= EOL_SEEN_LF; | |
6507 | else if (*p == '\r') | |
aaaf0b1e | 6508 | { |
df7492f9 | 6509 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6510 | { |
df7492f9 KH |
6511 | eol_seen |= EOL_SEEN_CRLF; |
6512 | p++; | |
aaaf0b1e | 6513 | } |
aaaf0b1e | 6514 | else |
df7492f9 | 6515 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6516 | } |
aaaf0b1e | 6517 | } |
75f4f1ac EZ |
6518 | /* Handle DOS-style EOLs in a file with stray ^M characters. */ |
6519 | if ((eol_seen & EOL_SEEN_CRLF) != 0 | |
6520 | && (eol_seen & EOL_SEEN_CR) != 0 | |
6521 | && (eol_seen & EOL_SEEN_LF) == 0) | |
6522 | eol_seen = EOL_SEEN_CRLF; | |
6523 | else if (eol_seen != EOL_SEEN_NONE | |
24a73b0a KH |
6524 | && eol_seen != EOL_SEEN_LF |
6525 | && eol_seen != EOL_SEEN_CRLF | |
6526 | && eol_seen != EOL_SEEN_CR) | |
6527 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6528 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6529 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6530 | } |
d46c5b12 | 6531 | |
24a73b0a | 6532 | if (EQ (eol_type, Qmac)) |
27901516 | 6533 | { |
24a73b0a | 6534 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6535 | if (*p == '\r') |
6536 | *p = '\n'; | |
4ed46869 | 6537 | } |
24a73b0a | 6538 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6539 | { |
24a73b0a | 6540 | int n = 0; |
b73bfc1c | 6541 | |
24a73b0a KH |
6542 | if (NILP (coding->dst_object)) |
6543 | { | |
4347441b KH |
6544 | /* Start deleting '\r' from the tail to minimize the memory |
6545 | movement. */ | |
24a73b0a KH |
6546 | for (p = pend - 2; p >= pbeg; p--) |
6547 | if (*p == '\r') | |
6548 | { | |
72af86bd | 6549 | memmove (p, p + 1, pend-- - p - 1); |
24a73b0a KH |
6550 | n++; |
6551 | } | |
6552 | } | |
6553 | else | |
6554 | { | |
4347441b KH |
6555 | int pos_byte = coding->dst_pos_byte; |
6556 | int pos = coding->dst_pos; | |
6557 | int pos_end = pos + coding->produced_char - 1; | |
6558 | ||
6559 | while (pos < pos_end) | |
6560 | { | |
6561 | p = BYTE_POS_ADDR (pos_byte); | |
6562 | if (*p == '\r' && p[1] == '\n') | |
6563 | { | |
6564 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6565 | n++; | |
6566 | pos_end--; | |
6567 | } | |
6568 | pos++; | |
69b8522d KH |
6569 | if (coding->dst_multibyte) |
6570 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6571 | else | |
6572 | pos_byte++; | |
4347441b | 6573 | } |
24a73b0a KH |
6574 | } |
6575 | coding->produced -= n; | |
6576 | coding->produced_char -= n; | |
aaaf0b1e | 6577 | } |
4ed46869 KH |
6578 | } |
6579 | ||
7d64c6ad | 6580 | |
a6f87d34 KH |
6581 | /* Return a translation table (or list of them) from coding system |
6582 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
6583 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 6584 | |
e6a54062 | 6585 | static Lisp_Object |
971de7fb | 6586 | get_translation_table (Lisp_Object attrs, int encodep, int *max_lookup) |
7d64c6ad KH |
6587 | { |
6588 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6589 | Lisp_Object val; |
7d64c6ad | 6590 | |
4bed5909 CY |
6591 | if (NILP (Venable_character_translation)) |
6592 | { | |
6593 | if (max_lookup) | |
6594 | *max_lookup = 0; | |
6595 | return Qnil; | |
6596 | } | |
7d64c6ad KH |
6597 | if (encodep) |
6598 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6599 | standard = Vstandard_translation_table_for_encode; | |
6600 | else | |
6601 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6602 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6603 | if (NILP (translation_table)) |
09ee6fdd KH |
6604 | translation_table = standard; |
6605 | else | |
a6f87d34 | 6606 | { |
09ee6fdd KH |
6607 | if (SYMBOLP (translation_table)) |
6608 | translation_table = Fget (translation_table, Qtranslation_table); | |
6609 | else if (CONSP (translation_table)) | |
6610 | { | |
6611 | translation_table = Fcopy_sequence (translation_table); | |
6612 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6613 | if (SYMBOLP (XCAR (val))) | |
6614 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6615 | } | |
6616 | if (CHAR_TABLE_P (standard)) | |
6617 | { | |
6618 | if (CONSP (translation_table)) | |
6619 | translation_table = nconc2 (translation_table, | |
6620 | Fcons (standard, Qnil)); | |
6621 | else | |
6622 | translation_table = Fcons (translation_table, | |
6623 | Fcons (standard, Qnil)); | |
6624 | } | |
a6f87d34 | 6625 | } |
2170c8f0 KH |
6626 | |
6627 | if (max_lookup) | |
09ee6fdd | 6628 | { |
2170c8f0 KH |
6629 | *max_lookup = 1; |
6630 | if (CHAR_TABLE_P (translation_table) | |
6631 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6632 | { | |
6633 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6634 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6635 | *max_lookup = XFASTINT (val); | |
6636 | } | |
6637 | else if (CONSP (translation_table)) | |
6638 | { | |
6639 | Lisp_Object tail, val; | |
09ee6fdd | 6640 | |
2170c8f0 KH |
6641 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6642 | if (CHAR_TABLE_P (XCAR (tail)) | |
6643 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6644 | { | |
6645 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
6646 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6647 | *max_lookup = XFASTINT (val); | |
6648 | } | |
6649 | } | |
a6f87d34 | 6650 | } |
7d64c6ad KH |
6651 | return translation_table; |
6652 | } | |
6653 | ||
09ee6fdd KH |
6654 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6655 | do { \ | |
6656 | trans = Qnil; \ | |
6657 | if (CHAR_TABLE_P (table)) \ | |
6658 | { \ | |
6659 | trans = CHAR_TABLE_REF (table, c); \ | |
6660 | if (CHARACTERP (trans)) \ | |
6661 | c = XFASTINT (trans), trans = Qnil; \ | |
6662 | } \ | |
6663 | else if (CONSP (table)) \ | |
6664 | { \ | |
6665 | Lisp_Object tail; \ | |
6666 | \ | |
6667 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6668 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6669 | { \ | |
6670 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6671 | if (CHARACTERP (trans)) \ | |
6672 | c = XFASTINT (trans), trans = Qnil; \ | |
6673 | else if (! NILP (trans)) \ | |
6674 | break; \ | |
6675 | } \ | |
6676 | } \ | |
e6a54062 KH |
6677 | } while (0) |
6678 | ||
7d64c6ad | 6679 | |
e951386e KH |
6680 | /* Return a translation of character(s) at BUF according to TRANS. |
6681 | TRANS is TO-CHAR or ((FROM . TO) ...) where | |
6682 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | |
6683 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | |
6684 | translation is found, and Qnil if not found.. | |
6685 | If BUF is too short to lookup characters in FROM, return Qt. */ | |
6686 | ||
69a80ea3 | 6687 | static Lisp_Object |
971de7fb | 6688 | get_translation (Lisp_Object trans, int *buf, int *buf_end) |
69a80ea3 | 6689 | { |
e951386e KH |
6690 | |
6691 | if (INTEGERP (trans)) | |
6692 | return trans; | |
6693 | for (; CONSP (trans); trans = XCDR (trans)) | |
69a80ea3 | 6694 | { |
e951386e KH |
6695 | Lisp_Object val = XCAR (trans); |
6696 | Lisp_Object from = XCAR (val); | |
6697 | int len = ASIZE (from); | |
6698 | int i; | |
69a80ea3 | 6699 | |
e951386e | 6700 | for (i = 0; i < len; i++) |
69a80ea3 | 6701 | { |
e951386e KH |
6702 | if (buf + i == buf_end) |
6703 | return Qt; | |
6704 | if (XINT (AREF (from, i)) != buf[i]) | |
6705 | break; | |
69a80ea3 | 6706 | } |
e951386e KH |
6707 | if (i == len) |
6708 | return val; | |
69a80ea3 | 6709 | } |
e951386e | 6710 | return Qnil; |
69a80ea3 KH |
6711 | } |
6712 | ||
6713 | ||
d46c5b12 | 6714 | static int |
cf84bb53 JB |
6715 | produce_chars (struct coding_system *coding, Lisp_Object translation_table, |
6716 | int last_block) | |
4ed46869 | 6717 | { |
df7492f9 KH |
6718 | unsigned char *dst = coding->destination + coding->produced; |
6719 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
119852e7 KH |
6720 | EMACS_INT produced; |
6721 | EMACS_INT produced_chars = 0; | |
69a80ea3 | 6722 | int carryover = 0; |
4ed46869 | 6723 | |
df7492f9 | 6724 | if (! coding->chars_at_source) |
4ed46869 | 6725 | { |
119852e7 | 6726 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6727 | int *buf = coding->charbuf; |
6728 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6729 | |
db274c7a KH |
6730 | if (EQ (coding->src_object, coding->dst_object)) |
6731 | { | |
6732 | coding_set_source (coding); | |
6733 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6734 | } | |
4ed46869 | 6735 | |
df7492f9 | 6736 | while (buf < buf_end) |
4ed46869 | 6737 | { |
69a80ea3 | 6738 | int c = *buf, i; |
bc4bc72a | 6739 | |
df7492f9 KH |
6740 | if (c >= 0) |
6741 | { | |
69a80ea3 KH |
6742 | int from_nchars = 1, to_nchars = 1; |
6743 | Lisp_Object trans = Qnil; | |
6744 | ||
09ee6fdd | 6745 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6746 | if (! NILP (trans)) |
69a80ea3 | 6747 | { |
e951386e KH |
6748 | trans = get_translation (trans, buf, buf_end); |
6749 | if (INTEGERP (trans)) | |
6750 | c = XINT (trans); | |
6751 | else if (CONSP (trans)) | |
6752 | { | |
6753 | from_nchars = ASIZE (XCAR (trans)); | |
6754 | trans = XCDR (trans); | |
6755 | if (INTEGERP (trans)) | |
6756 | c = XINT (trans); | |
6757 | else | |
6758 | { | |
6759 | to_nchars = ASIZE (trans); | |
6760 | c = XINT (AREF (trans, 0)); | |
6761 | } | |
6762 | } | |
6763 | else if (EQ (trans, Qt) && ! last_block) | |
69a80ea3 | 6764 | break; |
69a80ea3 KH |
6765 | } |
6766 | ||
6767 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
6768 | { | |
6769 | dst = alloc_destination (coding, | |
6770 | buf_end - buf | |
6771 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
6772 | dst); | |
db274c7a KH |
6773 | if (EQ (coding->src_object, coding->dst_object)) |
6774 | { | |
6775 | coding_set_source (coding); | |
e951386e KH |
6776 | dst_end = (((unsigned char *) coding->source) |
6777 | + coding->consumed); | |
db274c7a KH |
6778 | } |
6779 | else | |
6780 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
6781 | } |
6782 | ||
433f7f87 | 6783 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 6784 | { |
433f7f87 KH |
6785 | if (i > 0) |
6786 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
6787 | if (coding->dst_multibyte |
6788 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 6789 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
6790 | else |
6791 | *dst++ = CHAR_TO_BYTE8 (c); | |
6792 | } | |
6793 | produced_chars += to_nchars; | |
e951386e | 6794 | buf += from_nchars; |
d46c5b12 | 6795 | } |
df7492f9 | 6796 | else |
69a80ea3 KH |
6797 | /* This is an annotation datum. (-C) is the length. */ |
6798 | buf += -c; | |
4ed46869 | 6799 | } |
69a80ea3 | 6800 | carryover = buf_end - buf; |
4ed46869 | 6801 | } |
fa42c37f | 6802 | else |
fa42c37f | 6803 | { |
119852e7 | 6804 | /* Source characters are at coding->source. */ |
8f924df7 | 6805 | const unsigned char *src = coding->source; |
119852e7 | 6806 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 6807 | |
db274c7a KH |
6808 | if (EQ (coding->dst_object, coding->src_object)) |
6809 | dst_end = (unsigned char *) src; | |
df7492f9 | 6810 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 6811 | { |
df7492f9 | 6812 | if (coding->src_multibyte) |
fa42c37f | 6813 | { |
71c81426 | 6814 | int multibytep = 1; |
4533845d | 6815 | EMACS_INT consumed_chars = 0; |
d46c5b12 | 6816 | |
df7492f9 KH |
6817 | while (1) |
6818 | { | |
8f924df7 | 6819 | const unsigned char *src_base = src; |
df7492f9 | 6820 | int c; |
b73bfc1c | 6821 | |
df7492f9 | 6822 | ONE_MORE_BYTE (c); |
119852e7 | 6823 | if (dst == dst_end) |
df7492f9 | 6824 | { |
119852e7 KH |
6825 | if (EQ (coding->src_object, coding->dst_object)) |
6826 | dst_end = (unsigned char *) src; | |
6827 | if (dst == dst_end) | |
df7492f9 | 6828 | { |
119852e7 KH |
6829 | EMACS_INT offset = src - coding->source; |
6830 | ||
6831 | dst = alloc_destination (coding, src_end - src + 1, | |
6832 | dst); | |
6833 | dst_end = coding->destination + coding->dst_bytes; | |
6834 | coding_set_source (coding); | |
6835 | src = coding->source + offset; | |
6836 | src_end = coding->source + coding->src_bytes; | |
db274c7a KH |
6837 | if (EQ (coding->src_object, coding->dst_object)) |
6838 | dst_end = (unsigned char *) src; | |
df7492f9 | 6839 | } |
df7492f9 KH |
6840 | } |
6841 | *dst++ = c; | |
6842 | produced_chars++; | |
6843 | } | |
6844 | no_more_source: | |
6845 | ; | |
fa42c37f KH |
6846 | } |
6847 | else | |
df7492f9 KH |
6848 | while (src < src_end) |
6849 | { | |
71c81426 | 6850 | int multibytep = 1; |
df7492f9 | 6851 | int c = *src++; |
b73bfc1c | 6852 | |
df7492f9 KH |
6853 | if (dst >= dst_end - 1) |
6854 | { | |
2c78b7e1 | 6855 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 6856 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
6857 | if (dst >= dst_end - 1) |
6858 | { | |
119852e7 | 6859 | EMACS_INT offset = src - coding->source; |
db274c7a | 6860 | EMACS_INT more_bytes; |
119852e7 | 6861 | |
db274c7a KH |
6862 | if (EQ (coding->src_object, coding->dst_object)) |
6863 | more_bytes = ((src_end - src) / 2) + 2; | |
6864 | else | |
6865 | more_bytes = src_end - src + 2; | |
6866 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
6867 | dst_end = coding->destination + coding->dst_bytes; |
6868 | coding_set_source (coding); | |
119852e7 | 6869 | src = coding->source + offset; |
2c78b7e1 | 6870 | src_end = coding->source + coding->src_bytes; |
db274c7a KH |
6871 | if (EQ (coding->src_object, coding->dst_object)) |
6872 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 6873 | } |
df7492f9 KH |
6874 | } |
6875 | EMIT_ONE_BYTE (c); | |
6876 | } | |
d46c5b12 | 6877 | } |
df7492f9 KH |
6878 | else |
6879 | { | |
6880 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 6881 | { |
119852e7 | 6882 | EMACS_INT require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 6883 | |
df7492f9 | 6884 | if (require > 0) |
fa42c37f | 6885 | { |
df7492f9 KH |
6886 | EMACS_INT offset = src - coding->source; |
6887 | ||
6888 | dst = alloc_destination (coding, require, dst); | |
6889 | coding_set_source (coding); | |
6890 | src = coding->source + offset; | |
6891 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
6892 | } |
6893 | } | |
119852e7 | 6894 | produced_chars = coding->consumed_char; |
df7492f9 | 6895 | while (src < src_end) |
14daee73 | 6896 | *dst++ = *src++; |
fa42c37f KH |
6897 | } |
6898 | } | |
6899 | ||
df7492f9 | 6900 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 6901 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
df7492f9 KH |
6902 | insert_from_gap (produced_chars, produced); |
6903 | coding->produced += produced; | |
6904 | coding->produced_char += produced_chars; | |
69a80ea3 | 6905 | return carryover; |
fa42c37f KH |
6906 | } |
6907 | ||
ff0dacd7 KH |
6908 | /* Compose text in CODING->object according to the annotation data at |
6909 | CHARBUF. CHARBUF is an array: | |
e951386e | 6910 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
df7492f9 | 6911 | */ |
4ed46869 | 6912 | |
df7492f9 | 6913 | static INLINE void |
971de7fb | 6914 | produce_composition (struct coding_system *coding, int *charbuf, EMACS_INT pos) |
4ed46869 | 6915 | { |
df7492f9 | 6916 | int len; |
69a80ea3 | 6917 | EMACS_INT to; |
df7492f9 | 6918 | enum composition_method method; |
df7492f9 | 6919 | Lisp_Object components; |
fa42c37f | 6920 | |
e951386e | 6921 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
69a80ea3 | 6922 | to = pos + charbuf[2]; |
e951386e | 6923 | method = (enum composition_method) (charbuf[4]); |
d46c5b12 | 6924 | |
df7492f9 KH |
6925 | if (method == COMPOSITION_RELATIVE) |
6926 | components = Qnil; | |
e951386e | 6927 | else |
d46c5b12 | 6928 | { |
df7492f9 | 6929 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
e951386e | 6930 | int i, j; |
b73bfc1c | 6931 | |
e951386e KH |
6932 | if (method == COMPOSITION_WITH_RULE) |
6933 | len = charbuf[2] * 3 - 2; | |
6934 | charbuf += MAX_ANNOTATION_LENGTH; | |
6935 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | |
6936 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | |
9ffd559c | 6937 | { |
e951386e KH |
6938 | if (charbuf[i] >= 0) |
6939 | args[j] = make_number (charbuf[i]); | |
6940 | else | |
6941 | { | |
6942 | i++; | |
6943 | args[j] = make_number (charbuf[i] % 0x100); | |
6944 | } | |
9ffd559c | 6945 | } |
e951386e | 6946 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
d46c5b12 | 6947 | } |
69a80ea3 | 6948 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6949 | } |
6950 | ||
d46c5b12 | 6951 | |
ff0dacd7 KH |
6952 | /* Put `charset' property on text in CODING->object according to |
6953 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6954 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6955 | */ |
d46c5b12 | 6956 | |
ff0dacd7 | 6957 | static INLINE void |
971de7fb | 6958 | produce_charset (struct coding_system *coding, int *charbuf, EMACS_INT pos) |
d46c5b12 | 6959 | { |
69a80ea3 KH |
6960 | EMACS_INT from = pos - charbuf[2]; |
6961 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 6962 | |
69a80ea3 | 6963 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6964 | Qcharset, CHARSET_NAME (charset), |
6965 | coding->dst_object); | |
d46c5b12 KH |
6966 | } |
6967 | ||
d46c5b12 | 6968 | |
df7492f9 KH |
6969 | #define CHARBUF_SIZE 0x4000 |
6970 | ||
6971 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6972 | do { \ | |
8510724d | 6973 | int size = CHARBUF_SIZE; \ |
df7492f9 KH |
6974 | \ |
6975 | coding->charbuf = NULL; \ | |
6976 | while (size > 1024) \ | |
6977 | { \ | |
6978 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
6979 | if (coding->charbuf) \ | |
6980 | break; \ | |
6981 | size >>= 1; \ | |
6982 | } \ | |
6983 | if (! coding->charbuf) \ | |
6984 | { \ | |
065e3595 | 6985 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
6986 | return coding->result; \ |
6987 | } \ | |
6988 | coding->charbuf_size = size; \ | |
6989 | } while (0) | |
4ed46869 | 6990 | |
d46c5b12 KH |
6991 | |
6992 | static void | |
971de7fb | 6993 | produce_annotation (struct coding_system *coding, EMACS_INT pos) |
d46c5b12 | 6994 | { |
df7492f9 KH |
6995 | int *charbuf = coding->charbuf; |
6996 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6997 | |
ff0dacd7 KH |
6998 | if (NILP (coding->dst_object)) |
6999 | return; | |
d46c5b12 | 7000 | |
df7492f9 | 7001 | while (charbuf < charbuf_end) |
a84f1519 | 7002 | { |
df7492f9 | 7003 | if (*charbuf >= 0) |
e951386e | 7004 | pos++, charbuf++; |
d46c5b12 | 7005 | else |
d46c5b12 | 7006 | { |
df7492f9 | 7007 | int len = -*charbuf; |
e951386e KH |
7008 | |
7009 | if (len > 2) | |
7010 | switch (charbuf[1]) | |
7011 | { | |
7012 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
7013 | produce_composition (coding, charbuf, pos); | |
7014 | break; | |
7015 | case CODING_ANNOTATE_CHARSET_MASK: | |
7016 | produce_charset (coding, charbuf, pos); | |
7017 | break; | |
7018 | } | |
df7492f9 | 7019 | charbuf += len; |
d46c5b12 | 7020 | } |
a84f1519 | 7021 | } |
d46c5b12 KH |
7022 | } |
7023 | ||
df7492f9 KH |
7024 | /* Decode the data at CODING->src_object into CODING->dst_object. |
7025 | CODING->src_object is a buffer, a string, or nil. | |
7026 | CODING->dst_object is a buffer. | |
d46c5b12 | 7027 | |
df7492f9 KH |
7028 | If CODING->src_object is a buffer, it must be the current buffer. |
7029 | In this case, if CODING->src_pos is positive, it is a position of | |
7030 | the source text in the buffer, otherwise, the source text is in the | |
7031 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
7032 | the text from GPT (which must be the same as PT). If this is the | |
7033 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7034 | negative. | |
d46c5b12 | 7035 | |
b6828792 | 7036 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 7037 | that string. |
d46c5b12 | 7038 | |
df7492f9 KH |
7039 | If CODING->src_object is nil, CODING->source must already point to |
7040 | the non-relocatable memory area. In this case, CODING->src_pos is | |
7041 | an offset from CODING->source. | |
73be902c | 7042 | |
df7492f9 KH |
7043 | The decoded data is inserted at the current point of the buffer |
7044 | CODING->dst_object. | |
7045 | */ | |
d46c5b12 | 7046 | |
df7492f9 | 7047 | static int |
971de7fb | 7048 | decode_coding (struct coding_system *coding) |
d46c5b12 | 7049 | { |
df7492f9 | 7050 | Lisp_Object attrs; |
24a73b0a | 7051 | Lisp_Object undo_list; |
7d64c6ad | 7052 | Lisp_Object translation_table; |
d0396581 | 7053 | struct ccl_spec cclspec; |
69a80ea3 KH |
7054 | int carryover; |
7055 | int i; | |
d46c5b12 | 7056 | |
df7492f9 KH |
7057 | if (BUFFERP (coding->src_object) |
7058 | && coding->src_pos > 0 | |
7059 | && coding->src_pos < GPT | |
7060 | && coding->src_pos + coding->src_chars > GPT) | |
7061 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 7062 | |
24a73b0a | 7063 | undo_list = Qt; |
df7492f9 | 7064 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 7065 | { |
df7492f9 KH |
7066 | if (current_buffer != XBUFFER (coding->dst_object)) |
7067 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7068 | if (GPT != PT) | |
7069 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
7070 | undo_list = current_buffer->undo_list; |
7071 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
7072 | } |
7073 | ||
df7492f9 KH |
7074 | coding->consumed = coding->consumed_char = 0; |
7075 | coding->produced = coding->produced_char = 0; | |
7076 | coding->chars_at_source = 0; | |
065e3595 | 7077 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 7078 | coding->errors = 0; |
1c3478b0 | 7079 | |
df7492f9 KH |
7080 | ALLOC_CONVERSION_WORK_AREA (coding); |
7081 | ||
7082 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 7083 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 7084 | |
69a80ea3 | 7085 | carryover = 0; |
d0396581 KH |
7086 | if (coding->decoder == decode_coding_ccl) |
7087 | { | |
7088 | coding->spec.ccl = &cclspec; | |
7089 | setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding)); | |
7090 | } | |
df7492f9 | 7091 | do |
b73bfc1c | 7092 | { |
69a80ea3 KH |
7093 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
7094 | ||
df7492f9 KH |
7095 | coding_set_source (coding); |
7096 | coding->annotated = 0; | |
69a80ea3 | 7097 | coding->charbuf_used = carryover; |
df7492f9 | 7098 | (*(coding->decoder)) (coding); |
df7492f9 | 7099 | coding_set_destination (coding); |
69a80ea3 | 7100 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 7101 | if (coding->annotated) |
69a80ea3 KH |
7102 | produce_annotation (coding, pos); |
7103 | for (i = 0; i < carryover; i++) | |
7104 | coding->charbuf[i] | |
7105 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 7106 | } |
d0396581 KH |
7107 | while (coding->result == CODING_RESULT_INSUFFICIENT_DST |
7108 | || (coding->consumed < coding->src_bytes | |
7109 | && (coding->result == CODING_RESULT_SUCCESS | |
7110 | || coding->result == CODING_RESULT_INVALID_SRC))); | |
d46c5b12 | 7111 | |
69a80ea3 KH |
7112 | if (carryover > 0) |
7113 | { | |
7114 | coding_set_destination (coding); | |
7115 | coding->charbuf_used = carryover; | |
7116 | produce_chars (coding, translation_table, 1); | |
7117 | } | |
7118 | ||
df7492f9 KH |
7119 | coding->carryover_bytes = 0; |
7120 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 7121 | { |
df7492f9 | 7122 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 7123 | const unsigned char *src; |
df7492f9 KH |
7124 | |
7125 | coding_set_source (coding); | |
7126 | coding_set_destination (coding); | |
7127 | src = coding->source + coding->consumed; | |
7128 | ||
7129 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 7130 | { |
df7492f9 KH |
7131 | /* Flush out unprocessed data as binary chars. We are sure |
7132 | that the number of data is less than the size of | |
7133 | coding->charbuf. */ | |
065e3595 | 7134 | coding->charbuf_used = 0; |
b2dab6c8 JR |
7135 | coding->chars_at_source = 0; |
7136 | ||
df7492f9 | 7137 | while (nbytes-- > 0) |
1c3478b0 | 7138 | { |
df7492f9 | 7139 | int c = *src++; |
98725083 | 7140 | |
1c91457d KH |
7141 | if (c & 0x80) |
7142 | c = BYTE8_TO_CHAR (c); | |
7143 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 7144 | } |
f6cbaf43 | 7145 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 7146 | } |
d46c5b12 | 7147 | else |
df7492f9 KH |
7148 | { |
7149 | /* Record unprocessed bytes in coding->carryover. We are | |
7150 | sure that the number of data is less than the size of | |
7151 | coding->carryover. */ | |
7152 | unsigned char *p = coding->carryover; | |
7153 | ||
f289d375 KH |
7154 | if (nbytes > sizeof coding->carryover) |
7155 | nbytes = sizeof coding->carryover; | |
df7492f9 KH |
7156 | coding->carryover_bytes = nbytes; |
7157 | while (nbytes-- > 0) | |
7158 | *p++ = *src++; | |
1c3478b0 | 7159 | } |
df7492f9 | 7160 | coding->consumed = coding->src_bytes; |
b73bfc1c | 7161 | } |
69f76525 | 7162 | |
0a9564cb EZ |
7163 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix) |
7164 | && !inhibit_eol_conversion) | |
4347441b | 7165 | decode_eol (coding); |
24a73b0a KH |
7166 | if (BUFFERP (coding->dst_object)) |
7167 | { | |
7168 | current_buffer->undo_list = undo_list; | |
7169 | record_insert (coding->dst_pos, coding->produced_char); | |
7170 | } | |
73be902c | 7171 | return coding->result; |
4ed46869 KH |
7172 | } |
7173 | ||
aaaf0b1e | 7174 | |
e1c23804 | 7175 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
7176 | ending before LIMIT of CODING->src_object (buffer or string), store |
7177 | the data in BUF, set *STOP to a starting position of the next | |
7178 | composition (if any) or to LIMIT, and return the address of the | |
7179 | next element of BUF. | |
7180 | ||
7181 | If such an annotation is not found, set *STOP to a starting | |
7182 | position of a composition after POS (if any) or to LIMIT, and | |
7183 | return BUF. */ | |
7184 | ||
7185 | static INLINE int * | |
cf84bb53 JB |
7186 | handle_composition_annotation (EMACS_INT pos, EMACS_INT limit, |
7187 | struct coding_system *coding, int *buf, | |
7188 | EMACS_INT *stop) | |
aaaf0b1e | 7189 | { |
ff0dacd7 KH |
7190 | EMACS_INT start, end; |
7191 | Lisp_Object prop; | |
aaaf0b1e | 7192 | |
ff0dacd7 KH |
7193 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
7194 | || end > limit) | |
7195 | *stop = limit; | |
7196 | else if (start > pos) | |
7197 | *stop = start; | |
7198 | else | |
aaaf0b1e | 7199 | { |
ff0dacd7 | 7200 | if (start == pos) |
aaaf0b1e | 7201 | { |
ff0dacd7 KH |
7202 | /* We found a composition. Store the corresponding |
7203 | annotation data in BUF. */ | |
7204 | int *head = buf; | |
7205 | enum composition_method method = COMPOSITION_METHOD (prop); | |
7206 | int nchars = COMPOSITION_LENGTH (prop); | |
7207 | ||
e951386e | 7208 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
ff0dacd7 | 7209 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 7210 | { |
ff0dacd7 KH |
7211 | Lisp_Object components; |
7212 | int len, i, i_byte; | |
7213 | ||
7214 | components = COMPOSITION_COMPONENTS (prop); | |
7215 | if (VECTORP (components)) | |
aaaf0b1e | 7216 | { |
ff0dacd7 KH |
7217 | len = XVECTOR (components)->size; |
7218 | for (i = 0; i < len; i++) | |
7219 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 7220 | } |
ff0dacd7 | 7221 | else if (STRINGP (components)) |
aaaf0b1e | 7222 | { |
8f924df7 | 7223 | len = SCHARS (components); |
ff0dacd7 KH |
7224 | i = i_byte = 0; |
7225 | while (i < len) | |
7226 | { | |
7227 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
7228 | buf++; | |
7229 | } | |
7230 | } | |
7231 | else if (INTEGERP (components)) | |
7232 | { | |
7233 | len = 1; | |
7234 | *buf++ = XINT (components); | |
7235 | } | |
7236 | else if (CONSP (components)) | |
7237 | { | |
7238 | for (len = 0; CONSP (components); | |
7239 | len++, components = XCDR (components)) | |
7240 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 7241 | } |
aaaf0b1e | 7242 | else |
ff0dacd7 KH |
7243 | abort (); |
7244 | *head -= len; | |
aaaf0b1e | 7245 | } |
aaaf0b1e | 7246 | } |
ff0dacd7 KH |
7247 | |
7248 | if (find_composition (end, limit, &start, &end, &prop, | |
7249 | coding->src_object) | |
7250 | && end <= limit) | |
7251 | *stop = start; | |
7252 | else | |
7253 | *stop = limit; | |
aaaf0b1e | 7254 | } |
ff0dacd7 KH |
7255 | return buf; |
7256 | } | |
7257 | ||
7258 | ||
e1c23804 | 7259 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
7260 | CODING->src_object (buffer of string), store the data in BUF, set |
7261 | *STOP to the position where the value of `charset' property changes | |
7262 | (limiting by LIMIT), and return the address of the next element of | |
7263 | BUF. | |
7264 | ||
7265 | If the property value is nil, set *STOP to the position where the | |
7266 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
7267 | ||
7268 | static INLINE int * | |
cf84bb53 JB |
7269 | handle_charset_annotation (EMACS_INT pos, EMACS_INT limit, |
7270 | struct coding_system *coding, int *buf, | |
7271 | EMACS_INT *stop) | |
ff0dacd7 KH |
7272 | { |
7273 | Lisp_Object val, next; | |
7274 | int id; | |
7275 | ||
7276 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
7277 | if (! NILP (val) && CHARSETP (val)) | |
7278 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
7279 | else | |
7280 | id = -1; | |
69a80ea3 | 7281 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
7282 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
7283 | coding->src_object, | |
7284 | make_number (limit)); | |
7285 | *stop = XINT (next); | |
7286 | return buf; | |
7287 | } | |
7288 | ||
7289 | ||
df7492f9 | 7290 | static void |
cf84bb53 JB |
7291 | consume_chars (struct coding_system *coding, Lisp_Object translation_table, |
7292 | int max_lookup) | |
df7492f9 KH |
7293 | { |
7294 | int *buf = coding->charbuf; | |
ff0dacd7 | 7295 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 7296 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 7297 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
7298 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
7299 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
7300 | int multibytep = coding->src_multibyte; |
7301 | Lisp_Object eol_type; | |
7302 | int c; | |
ff0dacd7 | 7303 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 7304 | int *lookup_buf = NULL; |
433f7f87 KH |
7305 | |
7306 | if (! NILP (translation_table)) | |
09ee6fdd | 7307 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 7308 | |
0a9564cb | 7309 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
df7492f9 KH |
7310 | if (VECTORP (eol_type)) |
7311 | eol_type = Qunix; | |
88993dfd | 7312 | |
df7492f9 KH |
7313 | /* Note: composition handling is not yet implemented. */ |
7314 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 7315 | |
0b5670c9 KH |
7316 | if (NILP (coding->src_object)) |
7317 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 7318 | else |
0b5670c9 KH |
7319 | { |
7320 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
7321 | stop = stop_composition = pos; | |
7322 | else | |
7323 | stop = stop_composition = end_pos; | |
7324 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
7325 | stop = stop_charset = pos; | |
7326 | else | |
7327 | stop_charset = end_pos; | |
7328 | } | |
ec6d2bb8 | 7329 | |
24a73b0a | 7330 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 7331 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 7332 | while (buf < buf_end) |
aaaf0b1e | 7333 | { |
433f7f87 KH |
7334 | Lisp_Object trans; |
7335 | ||
df7492f9 | 7336 | if (pos == stop) |
ec6d2bb8 | 7337 | { |
df7492f9 KH |
7338 | if (pos == end_pos) |
7339 | break; | |
ff0dacd7 KH |
7340 | if (pos == stop_composition) |
7341 | buf = handle_composition_annotation (pos, end_pos, coding, | |
7342 | buf, &stop_composition); | |
7343 | if (pos == stop_charset) | |
7344 | buf = handle_charset_annotation (pos, end_pos, coding, | |
7345 | buf, &stop_charset); | |
7346 | stop = (stop_composition < stop_charset | |
7347 | ? stop_composition : stop_charset); | |
df7492f9 KH |
7348 | } |
7349 | ||
7350 | if (! multibytep) | |
4776e638 | 7351 | { |
d3e4cb56 | 7352 | EMACS_INT bytes; |
aaaf0b1e | 7353 | |
4d1e6632 KH |
7354 | if (coding->encoder == encode_coding_raw_text |
7355 | || coding->encoder == encode_coding_ccl) | |
ea29edf2 KH |
7356 | c = *src++, pos++; |
7357 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 7358 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 7359 | else |
f03caae0 | 7360 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 7361 | } |
df7492f9 | 7362 | else |
db274c7a | 7363 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
7364 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
7365 | c = '\n'; | |
7366 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 7367 | { |
df7492f9 | 7368 | if (c == '\n') |
aaaf0b1e | 7369 | { |
df7492f9 KH |
7370 | if (EQ (eol_type, Qdos)) |
7371 | *buf++ = '\r'; | |
7372 | else | |
7373 | c = '\r'; | |
aaaf0b1e KH |
7374 | } |
7375 | } | |
433f7f87 | 7376 | |
e6a54062 | 7377 | trans = Qnil; |
09ee6fdd | 7378 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 7379 | if (NILP (trans)) |
433f7f87 KH |
7380 | *buf++ = c; |
7381 | else | |
7382 | { | |
7383 | int from_nchars = 1, to_nchars = 1; | |
7384 | int *lookup_buf_end; | |
7385 | const unsigned char *p = src; | |
7386 | int i; | |
7387 | ||
7388 | lookup_buf[0] = c; | |
7389 | for (i = 1; i < max_lookup && p < src_end; i++) | |
7390 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
7391 | lookup_buf_end = lookup_buf + i; | |
e951386e KH |
7392 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
7393 | if (INTEGERP (trans)) | |
7394 | c = XINT (trans); | |
7395 | else if (CONSP (trans)) | |
7396 | { | |
7397 | from_nchars = ASIZE (XCAR (trans)); | |
7398 | trans = XCDR (trans); | |
7399 | if (INTEGERP (trans)) | |
7400 | c = XINT (trans); | |
7401 | else | |
7402 | { | |
7403 | to_nchars = ASIZE (trans); | |
7404 | if (buf + to_nchars > buf_end) | |
7405 | break; | |
7406 | c = XINT (AREF (trans, 0)); | |
7407 | } | |
7408 | } | |
7409 | else | |
433f7f87 | 7410 | break; |
e951386e | 7411 | *buf++ = c; |
433f7f87 KH |
7412 | for (i = 1; i < to_nchars; i++) |
7413 | *buf++ = XINT (AREF (trans, i)); | |
7414 | for (i = 1; i < from_nchars; i++, pos++) | |
7415 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7416 | } | |
aaaf0b1e | 7417 | } |
ec6d2bb8 | 7418 | |
df7492f9 KH |
7419 | coding->consumed = src - coding->source; |
7420 | coding->consumed_char = pos - coding->src_pos; | |
7421 | coding->charbuf_used = buf - coding->charbuf; | |
7422 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7423 | } |
7424 | ||
4ed46869 | 7425 | |
df7492f9 KH |
7426 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7427 | CODING->src_object is a buffer or a string. | |
7428 | CODING->dst_object is a buffer or nil. | |
7429 | ||
7430 | If CODING->src_object is a buffer, it must be the current buffer. | |
7431 | In this case, if CODING->src_pos is positive, it is a position of | |
7432 | the source text in the buffer, otherwise. the source text is in the | |
7433 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7434 | the text from GPT (which must be the same as PT). If this is the | |
7435 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7436 | negative and CODING should not have `pre-write-conversion'. | |
7437 | ||
7438 | If CODING->src_object is a string, CODING should not have | |
7439 | `pre-write-conversion'. | |
7440 | ||
7441 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7442 | the current point of that buffer. | |
7443 | ||
7444 | If CODING->dst_object is nil, the encoded data is placed at the | |
7445 | memory area specified by CODING->destination. */ | |
7446 | ||
7447 | static int | |
971de7fb | 7448 | encode_coding (struct coding_system *coding) |
4ed46869 | 7449 | { |
df7492f9 | 7450 | Lisp_Object attrs; |
7d64c6ad | 7451 | Lisp_Object translation_table; |
09ee6fdd | 7452 | int max_lookup; |
fb608df3 | 7453 | struct ccl_spec cclspec; |
9861e777 | 7454 | |
df7492f9 | 7455 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7456 | if (coding->encoder == encode_coding_raw_text) |
7457 | translation_table = Qnil, max_lookup = 0; | |
7458 | else | |
7459 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7460 | |
df7492f9 | 7461 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7462 | { |
df7492f9 KH |
7463 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7464 | coding->dst_multibyte | |
7465 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 7466 | } |
4ed46869 | 7467 | |
b73bfc1c | 7468 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7469 | coding->produced = coding->produced_char = 0; |
065e3595 | 7470 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7471 | coding->errors = 0; |
b73bfc1c | 7472 | |
df7492f9 | 7473 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7474 | |
fb608df3 KH |
7475 | if (coding->encoder == encode_coding_ccl) |
7476 | { | |
7477 | coding->spec.ccl = &cclspec; | |
7478 | setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding)); | |
7479 | } | |
df7492f9 KH |
7480 | do { |
7481 | coding_set_source (coding); | |
09ee6fdd | 7482 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7483 | coding_set_destination (coding); |
7484 | (*(coding->encoder)) (coding); | |
7485 | } while (coding->consumed_char < coding->src_chars); | |
7486 | ||
284201e4 | 7487 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
df7492f9 KH |
7488 | insert_from_gap (coding->produced_char, coding->produced); |
7489 | ||
7490 | return (coding->result); | |
ec6d2bb8 KH |
7491 | } |
7492 | ||
fb88bf2d | 7493 | |
24a73b0a KH |
7494 | /* Name (or base name) of work buffer for code conversion. */ |
7495 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7496 | |
24a73b0a KH |
7497 | /* A working buffer used by the top level conversion. Once it is |
7498 | created, it is never destroyed. It has the name | |
7499 | Vcode_conversion_workbuf_name. The other working buffers are | |
7500 | destroyed after the use is finished, and their names are modified | |
7501 | versions of Vcode_conversion_workbuf_name. */ | |
7502 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7503 | |
24a73b0a KH |
7504 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
7505 | static int reused_workbuf_in_use; | |
4ed46869 | 7506 | |
24a73b0a KH |
7507 | |
7508 | /* Return a working buffer of code convesion. MULTIBYTE specifies the | |
7509 | multibyteness of returning buffer. */ | |
b73bfc1c | 7510 | |
f6cbaf43 | 7511 | static Lisp_Object |
971de7fb | 7512 | make_conversion_work_buffer (int multibyte) |
df7492f9 | 7513 | { |
24a73b0a KH |
7514 | Lisp_Object name, workbuf; |
7515 | struct buffer *current; | |
4ed46869 | 7516 | |
24a73b0a | 7517 | if (reused_workbuf_in_use++) |
065e3595 KH |
7518 | { |
7519 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7520 | workbuf = Fget_buffer_create (name); | |
7521 | } | |
df7492f9 | 7522 | else |
065e3595 | 7523 | { |
159bd5a2 | 7524 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7525 | Vcode_conversion_reused_workbuf |
7526 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7527 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7528 | } |
24a73b0a KH |
7529 | current = current_buffer; |
7530 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7531 | /* We can't allow modification hooks to run in the work buffer. For |
7532 | instance, directory_files_internal assumes that file decoding | |
7533 | doesn't compile new regexps. */ | |
7534 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7535 | Ferase_buffer (); |
df7492f9 | 7536 | current_buffer->undo_list = Qt; |
24a73b0a | 7537 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 7538 | set_buffer_internal (current); |
24a73b0a | 7539 | return workbuf; |
df7492f9 | 7540 | } |
d46c5b12 | 7541 | |
24a73b0a | 7542 | |
4776e638 | 7543 | static Lisp_Object |
971de7fb | 7544 | code_conversion_restore (Lisp_Object arg) |
4776e638 | 7545 | { |
24a73b0a | 7546 | Lisp_Object current, workbuf; |
948bdcf3 | 7547 | struct gcpro gcpro1; |
24a73b0a | 7548 | |
948bdcf3 | 7549 | GCPRO1 (arg); |
24a73b0a KH |
7550 | current = XCAR (arg); |
7551 | workbuf = XCDR (arg); | |
7552 | if (! NILP (workbuf)) | |
7553 | { | |
7554 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7555 | reused_workbuf_in_use = 0; | |
7556 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
7557 | Fkill_buffer (workbuf); | |
7558 | } | |
7559 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7560 | UNGCPRO; |
4776e638 KH |
7561 | return Qnil; |
7562 | } | |
b73bfc1c | 7563 | |
24a73b0a | 7564 | Lisp_Object |
971de7fb | 7565 | code_conversion_save (int with_work_buf, int multibyte) |
df7492f9 | 7566 | { |
24a73b0a | 7567 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7568 | |
4776e638 | 7569 | if (with_work_buf) |
24a73b0a KH |
7570 | workbuf = make_conversion_work_buffer (multibyte); |
7571 | record_unwind_protect (code_conversion_restore, | |
7572 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7573 | return workbuf; |
df7492f9 | 7574 | } |
d46c5b12 | 7575 | |
df7492f9 | 7576 | int |
cf84bb53 JB |
7577 | decode_coding_gap (struct coding_system *coding, |
7578 | EMACS_INT chars, EMACS_INT bytes) | |
df7492f9 | 7579 | { |
1a4990fb | 7580 | int count = SPECPDL_INDEX (); |
5e5c78be | 7581 | Lisp_Object attrs; |
fb88bf2d | 7582 | |
24a73b0a | 7583 | code_conversion_save (0, 0); |
ec6d2bb8 | 7584 | |
24a73b0a | 7585 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7586 | coding->src_chars = chars; |
7587 | coding->src_bytes = bytes; | |
7588 | coding->src_pos = -chars; | |
7589 | coding->src_pos_byte = -bytes; | |
7590 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7591 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7592 | coding->dst_pos = PT; |
7593 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 7594 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
4ed46869 | 7595 | |
df7492f9 KH |
7596 | if (CODING_REQUIRE_DETECTION (coding)) |
7597 | detect_coding (coding); | |
8f924df7 | 7598 | |
9286b333 | 7599 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7600 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7601 | decode_coding (coding); |
287c57d7 | 7602 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7603 | |
5e5c78be KH |
7604 | attrs = CODING_ID_ATTRS (coding->id); |
7605 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 7606 | { |
5e5c78be KH |
7607 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
7608 | Lisp_Object val; | |
7609 | ||
7610 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7611 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7612 | make_number (coding->produced_char)); | |
5e5c78be KH |
7613 | CHECK_NATNUM (val); |
7614 | coding->produced_char += Z - prev_Z; | |
7615 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7616 | } |
4ed46869 | 7617 | |
df7492f9 | 7618 | unbind_to (count, Qnil); |
b73bfc1c KH |
7619 | return coding->result; |
7620 | } | |
52d41803 | 7621 | |
4ed46869 | 7622 | int |
cf84bb53 JB |
7623 | encode_coding_gap (struct coding_system *coding, |
7624 | EMACS_INT chars, EMACS_INT bytes) | |
4ed46869 | 7625 | { |
1a4990fb | 7626 | int count = SPECPDL_INDEX (); |
4ed46869 | 7627 | |
24a73b0a | 7628 | code_conversion_save (0, 0); |
4ed46869 | 7629 | |
24a73b0a | 7630 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7631 | coding->src_chars = chars; |
7632 | coding->src_bytes = bytes; | |
7633 | coding->src_pos = -chars; | |
7634 | coding->src_pos_byte = -bytes; | |
7635 | coding->src_multibyte = chars < bytes; | |
7636 | coding->dst_object = coding->src_object; | |
7637 | coding->dst_pos = PT; | |
7638 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 7639 | |
df7492f9 | 7640 | encode_coding (coding); |
b73bfc1c | 7641 | |
df7492f9 KH |
7642 | unbind_to (count, Qnil); |
7643 | return coding->result; | |
7644 | } | |
4ed46869 | 7645 | |
d46c5b12 | 7646 | |
df7492f9 KH |
7647 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7648 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7649 | |
df7492f9 | 7650 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7651 | |
df7492f9 KH |
7652 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7653 | are positions in the buffer. | |
b73bfc1c | 7654 | |
df7492f9 KH |
7655 | If it is a string, the text is at the beginning of the string. |
7656 | FROM and TO are indices to the string. | |
4ed46869 | 7657 | |
df7492f9 KH |
7658 | If it is nil, the text is at coding->source. FROM and TO are |
7659 | indices to coding->source. | |
bb10be8b | 7660 | |
df7492f9 | 7661 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7662 | |
df7492f9 KH |
7663 | If it is a buffer, the decoded text is inserted at point of the |
7664 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7665 | is deleted. | |
4ed46869 | 7666 | |
df7492f9 KH |
7667 | If it is Qt, a string is made from the decoded text, and |
7668 | set in CODING->dst_object. | |
d46c5b12 | 7669 | |
df7492f9 | 7670 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7671 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7672 | CODING->destination by xmalloc. If the decoded text is longer than |
7673 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7674 | */ | |
d46c5b12 | 7675 | |
df7492f9 | 7676 | void |
cf84bb53 JB |
7677 | decode_coding_object (struct coding_system *coding, |
7678 | Lisp_Object src_object, | |
7679 | EMACS_INT from, EMACS_INT from_byte, | |
7680 | EMACS_INT to, EMACS_INT to_byte, | |
7681 | Lisp_Object dst_object) | |
d46c5b12 | 7682 | { |
1a4990fb | 7683 | int count = SPECPDL_INDEX (); |
df7492f9 KH |
7684 | unsigned char *destination; |
7685 | EMACS_INT dst_bytes; | |
7686 | EMACS_INT chars = to - from; | |
7687 | EMACS_INT bytes = to_byte - from_byte; | |
7688 | Lisp_Object attrs; | |
4776e638 | 7689 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7690 | int need_marker_adjustment = 0; |
b3bfad50 | 7691 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7692 | |
b3bfad50 | 7693 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 7694 | |
df7492f9 | 7695 | if (NILP (dst_object)) |
d46c5b12 | 7696 | { |
df7492f9 KH |
7697 | destination = coding->destination; |
7698 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 7699 | } |
93dec019 | 7700 | |
df7492f9 KH |
7701 | coding->src_object = src_object; |
7702 | coding->src_chars = chars; | |
7703 | coding->src_bytes = bytes; | |
7704 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 7705 | |
df7492f9 | 7706 | if (STRINGP (src_object)) |
d46c5b12 | 7707 | { |
df7492f9 KH |
7708 | coding->src_pos = from; |
7709 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7710 | } |
df7492f9 | 7711 | else if (BUFFERP (src_object)) |
88993dfd | 7712 | { |
df7492f9 KH |
7713 | set_buffer_internal (XBUFFER (src_object)); |
7714 | if (from != GPT) | |
7715 | move_gap_both (from, from_byte); | |
7716 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 7717 | { |
64cedb0c KH |
7718 | struct Lisp_Marker *tail; |
7719 | ||
7720 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7721 | { | |
7722 | tail->need_adjustment | |
7723 | = tail->charpos == (tail->insertion_type ? from : to); | |
7724 | need_marker_adjustment |= tail->need_adjustment; | |
7725 | } | |
4776e638 | 7726 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 7727 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 7728 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
7729 | del_range_both (from, from_byte, to, to_byte, 1); |
7730 | coding->src_pos = -chars; | |
7731 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 7732 | } |
df7492f9 | 7733 | else |
fb88bf2d | 7734 | { |
df7492f9 KH |
7735 | coding->src_pos = from; |
7736 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 7737 | } |
88993dfd KH |
7738 | } |
7739 | ||
df7492f9 KH |
7740 | if (CODING_REQUIRE_DETECTION (coding)) |
7741 | detect_coding (coding); | |
7742 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 7743 | |
2cb26057 KH |
7744 | if (EQ (dst_object, Qt) |
7745 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
7746 | && NILP (dst_object))) | |
b73bfc1c | 7747 | { |
a1567c45 SM |
7748 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
7749 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
7750 | coding->dst_pos = BEG; |
7751 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 7752 | } |
df7492f9 | 7753 | else if (BUFFERP (dst_object)) |
d46c5b12 | 7754 | { |
24a73b0a | 7755 | code_conversion_save (0, 0); |
df7492f9 KH |
7756 | coding->dst_object = dst_object; |
7757 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
7758 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
7759 | coding->dst_multibyte | |
7760 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
7761 | } |
7762 | else | |
7763 | { | |
24a73b0a | 7764 | code_conversion_save (0, 0); |
df7492f9 | 7765 | coding->dst_object = Qnil; |
0154725e SM |
7766 | /* Most callers presume this will return a multibyte result, and they |
7767 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
7768 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 7769 | coding->dst_multibyte = 1; |
d46c5b12 KH |
7770 | } |
7771 | ||
df7492f9 | 7772 | decode_coding (coding); |
fa46990e | 7773 | |
df7492f9 KH |
7774 | if (BUFFERP (coding->dst_object)) |
7775 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 7776 | |
df7492f9 | 7777 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 7778 | { |
b3bfad50 | 7779 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
df7492f9 | 7780 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 7781 | Lisp_Object val; |
d46c5b12 | 7782 | |
c0cc7f7f | 7783 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
7784 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7785 | old_deactivate_mark); | |
d4850d67 KH |
7786 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
7787 | make_number (coding->produced_char)); | |
df7492f9 KH |
7788 | UNGCPRO; |
7789 | CHECK_NATNUM (val); | |
7790 | coding->produced_char += Z - prev_Z; | |
7791 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 7792 | } |
de79a6a5 | 7793 | |
df7492f9 | 7794 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 7795 | { |
df7492f9 KH |
7796 | coding->dst_object = Fbuffer_string (); |
7797 | } | |
7798 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
7799 | { | |
7800 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7801 | if (dst_bytes < coding->produced) | |
7802 | { | |
b3bfad50 | 7803 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
7804 | if (! destination) |
7805 | { | |
065e3595 | 7806 | record_conversion_result (coding, |
ebaf11b6 | 7807 | CODING_RESULT_INSUFFICIENT_MEM); |
df7492f9 KH |
7808 | unbind_to (count, Qnil); |
7809 | return; | |
7810 | } | |
7811 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
7812 | move_gap_both (BEGV, BEGV_BYTE); | |
72af86bd | 7813 | memcpy (destination, BEGV_ADDR, coding->produced); |
df7492f9 | 7814 | coding->destination = destination; |
d46c5b12 | 7815 | } |
ec6d2bb8 | 7816 | } |
b73bfc1c | 7817 | |
4776e638 KH |
7818 | if (saved_pt >= 0) |
7819 | { | |
7820 | /* This is the case of: | |
7821 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7822 | As we have moved PT while replacing the original buffer | |
7823 | contents, we must recover it now. */ | |
7824 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 7825 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
7826 | if (saved_pt < from) |
7827 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7828 | else if (saved_pt < from + chars) | |
7829 | TEMP_SET_PT_BOTH (from, from_byte); | |
7830 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
7831 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
7832 | saved_pt_byte + (coding->produced - bytes)); | |
7833 | else | |
7834 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
7835 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7836 | |
7837 | if (need_marker_adjustment) | |
7838 | { | |
7839 | struct Lisp_Marker *tail; | |
7840 | ||
7841 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7842 | if (tail->need_adjustment) | |
7843 | { | |
7844 | tail->need_adjustment = 0; | |
7845 | if (tail->insertion_type) | |
7846 | { | |
7847 | tail->bytepos = from_byte; | |
7848 | tail->charpos = from; | |
7849 | } | |
7850 | else | |
7851 | { | |
7852 | tail->bytepos = from_byte + coding->produced; | |
7853 | tail->charpos | |
7854 | = (NILP (current_buffer->enable_multibyte_characters) | |
7855 | ? tail->bytepos : from + coding->produced_char); | |
7856 | } | |
7857 | } | |
7858 | } | |
d46c5b12 | 7859 | } |
4776e638 | 7860 | |
b3bfad50 | 7861 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 7862 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
7863 | } |
7864 | ||
d46c5b12 | 7865 | |
df7492f9 | 7866 | void |
cf84bb53 JB |
7867 | encode_coding_object (struct coding_system *coding, |
7868 | Lisp_Object src_object, | |
7869 | EMACS_INT from, EMACS_INT from_byte, | |
7870 | EMACS_INT to, EMACS_INT to_byte, | |
7871 | Lisp_Object dst_object) | |
d46c5b12 | 7872 | { |
1a4990fb | 7873 | int count = SPECPDL_INDEX (); |
df7492f9 KH |
7874 | EMACS_INT chars = to - from; |
7875 | EMACS_INT bytes = to_byte - from_byte; | |
7876 | Lisp_Object attrs; | |
4776e638 | 7877 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7878 | int need_marker_adjustment = 0; |
c02d943b | 7879 | int kill_src_buffer = 0; |
b3bfad50 | 7880 | Lisp_Object old_deactivate_mark; |
df7492f9 | 7881 | |
b3bfad50 | 7882 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
7883 | |
7884 | coding->src_object = src_object; | |
7885 | coding->src_chars = chars; | |
7886 | coding->src_bytes = bytes; | |
7887 | coding->src_multibyte = chars < bytes; | |
7888 | ||
7889 | attrs = CODING_ID_ATTRS (coding->id); | |
7890 | ||
64cedb0c KH |
7891 | if (EQ (src_object, dst_object)) |
7892 | { | |
7893 | struct Lisp_Marker *tail; | |
7894 | ||
7895 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7896 | { | |
7897 | tail->need_adjustment | |
7898 | = tail->charpos == (tail->insertion_type ? from : to); | |
7899 | need_marker_adjustment |= tail->need_adjustment; | |
7900 | } | |
7901 | } | |
7902 | ||
df7492f9 | 7903 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 7904 | { |
24a73b0a | 7905 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
7906 | set_buffer_internal (XBUFFER (coding->src_object)); |
7907 | if (STRINGP (src_object)) | |
7908 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
7909 | else if (BUFFERP (src_object)) | |
7910 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
7911 | else | |
7912 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 7913 | |
df7492f9 KH |
7914 | if (EQ (src_object, dst_object)) |
7915 | { | |
7916 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 7917 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
7918 | del_range_both (from, from_byte, to, to_byte, 1); |
7919 | set_buffer_internal (XBUFFER (coding->src_object)); | |
7920 | } | |
7921 | ||
d4850d67 KH |
7922 | { |
7923 | Lisp_Object args[3]; | |
b3bfad50 | 7924 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 7925 | |
b3bfad50 KH |
7926 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7927 | old_deactivate_mark); | |
d4850d67 KH |
7928 | args[0] = CODING_ATTR_PRE_WRITE (attrs); |
7929 | args[1] = make_number (BEG); | |
7930 | args[2] = make_number (Z); | |
7931 | safe_call (3, args); | |
b3bfad50 | 7932 | UNGCPRO; |
d4850d67 | 7933 | } |
c02d943b KH |
7934 | if (XBUFFER (coding->src_object) != current_buffer) |
7935 | kill_src_buffer = 1; | |
ac87bbef | 7936 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7937 | if (BEG != GPT) |
7938 | move_gap_both (BEG, BEG_BYTE); | |
7939 | coding->src_chars = Z - BEG; | |
7940 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
7941 | coding->src_pos = BEG; | |
7942 | coding->src_pos_byte = BEG_BYTE; | |
7943 | coding->src_multibyte = Z < Z_BYTE; | |
7944 | } | |
7945 | else if (STRINGP (src_object)) | |
d46c5b12 | 7946 | { |
24a73b0a | 7947 | code_conversion_save (0, 0); |
df7492f9 KH |
7948 | coding->src_pos = from; |
7949 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 7950 | } |
df7492f9 | 7951 | else if (BUFFERP (src_object)) |
b73bfc1c | 7952 | { |
24a73b0a | 7953 | code_conversion_save (0, 0); |
df7492f9 | 7954 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 7955 | if (EQ (src_object, dst_object)) |
d46c5b12 | 7956 | { |
4776e638 | 7957 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
7958 | coding->src_object = del_range_1 (from, to, 1, 1); |
7959 | coding->src_pos = 0; | |
7960 | coding->src_pos_byte = 0; | |
d46c5b12 | 7961 | } |
df7492f9 | 7962 | else |
d46c5b12 | 7963 | { |
ff0dacd7 KH |
7964 | if (from < GPT && to >= GPT) |
7965 | move_gap_both (from, from_byte); | |
df7492f9 KH |
7966 | coding->src_pos = from; |
7967 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7968 | } |
d46c5b12 | 7969 | } |
4776e638 | 7970 | else |
24a73b0a | 7971 | code_conversion_save (0, 0); |
d46c5b12 | 7972 | |
df7492f9 | 7973 | if (BUFFERP (dst_object)) |
88993dfd | 7974 | { |
df7492f9 | 7975 | coding->dst_object = dst_object; |
28f67a95 KH |
7976 | if (EQ (src_object, dst_object)) |
7977 | { | |
7978 | coding->dst_pos = from; | |
7979 | coding->dst_pos_byte = from_byte; | |
7980 | } | |
7981 | else | |
7982 | { | |
319a3947 KH |
7983 | struct buffer *current = current_buffer; |
7984 | ||
7985 | set_buffer_temp (XBUFFER (dst_object)); | |
7986 | coding->dst_pos = PT; | |
7987 | coding->dst_pos_byte = PT_BYTE; | |
7988 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
7989 | set_buffer_temp (current); | |
28f67a95 | 7990 | } |
df7492f9 KH |
7991 | coding->dst_multibyte |
7992 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 7993 | } |
df7492f9 | 7994 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 7995 | { |
df7492f9 | 7996 | coding->dst_object = Qnil; |
df7492f9 | 7997 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
7998 | if (coding->dst_bytes == 0) |
7999 | coding->dst_bytes = 1; | |
8000 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 8001 | coding->dst_multibyte = 0; |
d46c5b12 KH |
8002 | } |
8003 | else | |
8004 | { | |
df7492f9 KH |
8005 | coding->dst_object = Qnil; |
8006 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
8007 | } |
8008 | ||
df7492f9 | 8009 | encode_coding (coding); |
d46c5b12 | 8010 | |
df7492f9 | 8011 | if (EQ (dst_object, Qt)) |
d46c5b12 | 8012 | { |
df7492f9 KH |
8013 | if (BUFFERP (coding->dst_object)) |
8014 | coding->dst_object = Fbuffer_string (); | |
8015 | else | |
d46c5b12 | 8016 | { |
df7492f9 KH |
8017 | coding->dst_object |
8018 | = make_unibyte_string ((char *) coding->destination, | |
8019 | coding->produced); | |
8020 | xfree (coding->destination); | |
d46c5b12 | 8021 | } |
4ed46869 | 8022 | } |
d46c5b12 | 8023 | |
4776e638 KH |
8024 | if (saved_pt >= 0) |
8025 | { | |
8026 | /* This is the case of: | |
8027 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
8028 | As we have moved PT while replacing the original buffer | |
8029 | contents, we must recover it now. */ | |
8030 | set_buffer_internal (XBUFFER (src_object)); | |
8031 | if (saved_pt < from) | |
8032 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
8033 | else if (saved_pt < from + chars) | |
8034 | TEMP_SET_PT_BOTH (from, from_byte); | |
8035 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
8036 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
8037 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 8038 | else |
4776e638 KH |
8039 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
8040 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
8041 | |
8042 | if (need_marker_adjustment) | |
8043 | { | |
8044 | struct Lisp_Marker *tail; | |
8045 | ||
8046 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
8047 | if (tail->need_adjustment) | |
8048 | { | |
8049 | tail->need_adjustment = 0; | |
8050 | if (tail->insertion_type) | |
8051 | { | |
8052 | tail->bytepos = from_byte; | |
8053 | tail->charpos = from; | |
8054 | } | |
8055 | else | |
8056 | { | |
8057 | tail->bytepos = from_byte + coding->produced; | |
8058 | tail->charpos | |
8059 | = (NILP (current_buffer->enable_multibyte_characters) | |
8060 | ? tail->bytepos : from + coding->produced_char); | |
8061 | } | |
8062 | } | |
8063 | } | |
4776e638 KH |
8064 | } |
8065 | ||
c02d943b KH |
8066 | if (kill_src_buffer) |
8067 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
8068 | |
8069 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 8070 | unbind_to (count, Qnil); |
b73bfc1c KH |
8071 | } |
8072 | ||
df7492f9 | 8073 | |
b73bfc1c | 8074 | Lisp_Object |
971de7fb | 8075 | preferred_coding_system (void) |
b73bfc1c | 8076 | { |
df7492f9 | 8077 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 8078 | |
df7492f9 | 8079 | return CODING_ID_NAME (id); |
4ed46869 KH |
8080 | } |
8081 | ||
8082 | \f | |
8083 | #ifdef emacs | |
1397dc18 | 8084 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 8085 | |
4ed46869 | 8086 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 8087 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 8088 | See the documentation of `define-coding-system' for information |
48b0f3ae | 8089 | about coding-system objects. */) |
5842a27b | 8090 | (Lisp_Object object) |
4ed46869 | 8091 | { |
d4a1d553 JB |
8092 | if (NILP (object) |
8093 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 8094 | return Qt; |
d4a1d553 JB |
8095 | if (! SYMBOLP (object) |
8096 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
8097 | return Qnil; |
8098 | return Qt; | |
4ed46869 KH |
8099 | } |
8100 | ||
9d991de8 RS |
8101 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
8102 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae | 8103 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
5842a27b | 8104 | (Lisp_Object prompt) |
4ed46869 | 8105 | { |
e0e989f6 | 8106 | Lisp_Object val; |
9d991de8 RS |
8107 | do |
8108 | { | |
4608c386 KH |
8109 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
8110 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 8111 | } |
8f924df7 | 8112 | while (SCHARS (val) == 0); |
e0e989f6 | 8113 | return (Fintern (val, Qnil)); |
4ed46869 KH |
8114 | } |
8115 | ||
9b787f3e | 8116 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 8117 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
8118 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
8119 | Ignores case when completing coding systems (all Emacs coding systems | |
8120 | are lower-case). */) | |
5842a27b | 8121 | (Lisp_Object prompt, Lisp_Object default_coding_system) |
4ed46869 | 8122 | { |
f44d27ce | 8123 | Lisp_Object val; |
c7183fb8 GM |
8124 | int count = SPECPDL_INDEX (); |
8125 | ||
9b787f3e | 8126 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 8127 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 8128 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 8129 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
8130 | Qt, Qnil, Qcoding_system_history, |
8131 | default_coding_system, Qnil); | |
c7183fb8 | 8132 | unbind_to (count, Qnil); |
8f924df7 | 8133 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
8134 | } |
8135 | ||
8136 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
8137 | 1, 1, 0, | |
48b0f3ae | 8138 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
8139 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
8140 | It is valid if it is nil or a symbol defined as a coding system by the | |
8141 | function `define-coding-system'. */) | |
5842a27b | 8142 | (Lisp_Object coding_system) |
4ed46869 | 8143 | { |
44e8490d KH |
8144 | Lisp_Object define_form; |
8145 | ||
8146 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
8147 | if (! NILP (define_form)) | |
8148 | { | |
8149 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
8150 | safe_eval (define_form); | |
8151 | } | |
4ed46869 KH |
8152 | if (!NILP (Fcoding_system_p (coding_system))) |
8153 | return coding_system; | |
fcad4ec4 | 8154 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 8155 | } |
df7492f9 | 8156 | |
3a73fa5d | 8157 | \f |
89528eb3 KH |
8158 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
8159 | HIGHEST is nonzero, return the coding system of the highest | |
8160 | priority among the detected coding systems. Otherwize return a | |
8161 | list of detected coding systems sorted by their priorities. If | |
8162 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
8163 | multibyte form but contains only ASCII and eight-bit chars. | |
8164 | Otherwise, the bytes are raw bytes. | |
8165 | ||
8166 | CODING-SYSTEM controls the detection as below: | |
8167 | ||
8168 | If it is nil, detect both text-format and eol-format. If the | |
8169 | text-format part of CODING-SYSTEM is already specified | |
8170 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
8171 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
8172 | detect only text-format. */ | |
8173 | ||
d46c5b12 | 8174 | Lisp_Object |
cf84bb53 JB |
8175 | detect_coding_system (const unsigned char *src, |
8176 | EMACS_INT src_chars, EMACS_INT src_bytes, | |
8177 | int highest, int multibytep, | |
8178 | Lisp_Object coding_system) | |
4ed46869 | 8179 | { |
8f924df7 | 8180 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 8181 | Lisp_Object attrs, eol_type; |
4533845d | 8182 | Lisp_Object val = Qnil; |
df7492f9 | 8183 | struct coding_system coding; |
89528eb3 | 8184 | int id; |
ff0dacd7 | 8185 | struct coding_detection_info detect_info; |
24a73b0a | 8186 | enum coding_category base_category; |
2f3cbb32 | 8187 | int null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 8188 | |
df7492f9 KH |
8189 | if (NILP (coding_system)) |
8190 | coding_system = Qundecided; | |
8191 | setup_coding_system (coding_system, &coding); | |
8192 | attrs = CODING_ID_ATTRS (coding.id); | |
8193 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 8194 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 8195 | |
df7492f9 | 8196 | coding.source = src; |
24a73b0a | 8197 | coding.src_chars = src_chars; |
df7492f9 KH |
8198 | coding.src_bytes = src_bytes; |
8199 | coding.src_multibyte = multibytep; | |
8200 | coding.consumed = 0; | |
89528eb3 | 8201 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 8202 | coding.head_ascii = 0; |
d46c5b12 | 8203 | |
ff0dacd7 | 8204 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 8205 | |
89528eb3 | 8206 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
8207 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
8208 | if (base_category == coding_category_undecided) | |
4ed46869 | 8209 | { |
ff0dacd7 KH |
8210 | enum coding_category category; |
8211 | struct coding_system *this; | |
8212 | int c, i; | |
88993dfd | 8213 | |
24a73b0a | 8214 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 8215 | for (; src < src_end; src++) |
4ed46869 | 8216 | { |
df7492f9 | 8217 | c = *src; |
6cb21a4f | 8218 | if (c & 0x80) |
6cb21a4f | 8219 | { |
2f3cbb32 | 8220 | eight_bit_found = 1; |
2f3cbb32 KH |
8221 | if (null_byte_found) |
8222 | break; | |
8223 | } | |
c0e16b14 | 8224 | else if (c < 0x20) |
2f3cbb32 KH |
8225 | { |
8226 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
8227 | && ! inhibit_iso_escape_detection | |
8228 | && ! detect_info.checked) | |
6cb21a4f | 8229 | { |
2f3cbb32 KH |
8230 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
8231 | { | |
8232 | /* We have scanned the whole data. */ | |
8233 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
8234 | { |
8235 | /* We didn't find an 8-bit code. We may | |
8236 | have found a null-byte, but it's very | |
8237 | rare that a binary file confirm to | |
8238 | ISO-2022. */ | |
8239 | src = src_end; | |
8240 | coding.head_ascii = src - coding.source; | |
8241 | } | |
8242 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
8243 | break; |
8244 | } | |
8245 | } | |
97b1b294 | 8246 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
8247 | { |
8248 | null_byte_found = 1; | |
8249 | if (eight_bit_found) | |
8250 | break; | |
6cb21a4f | 8251 | } |
c006c0c8 KH |
8252 | if (! eight_bit_found) |
8253 | coding.head_ascii++; | |
6cb21a4f | 8254 | } |
c006c0c8 | 8255 | else if (! eight_bit_found) |
c0e16b14 | 8256 | coding.head_ascii++; |
4ed46869 | 8257 | } |
88993dfd | 8258 | |
2f3cbb32 KH |
8259 | if (null_byte_found || eight_bit_found |
8260 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
8261 | || detect_info.found) |
8262 | { | |
2f3cbb32 | 8263 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
8264 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
8265 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 8266 | { |
6cb21a4f | 8267 | category = coding_priorities[i]; |
c7266f4a | 8268 | this = coding_categories + category; |
6cb21a4f | 8269 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
8270 | break; |
8271 | } | |
6cb21a4f | 8272 | else |
2f3cbb32 KH |
8273 | { |
8274 | if (null_byte_found) | |
8275 | { | |
8276 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
8277 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
8278 | } | |
8279 | for (i = 0; i < coding_category_raw_text; i++) | |
8280 | { | |
8281 | category = coding_priorities[i]; | |
8282 | this = coding_categories + category; | |
6cb21a4f | 8283 | |
2f3cbb32 KH |
8284 | if (this->id < 0) |
8285 | { | |
8286 | /* No coding system of this category is defined. */ | |
8287 | detect_info.rejected |= (1 << category); | |
8288 | } | |
8289 | else if (category >= coding_category_raw_text) | |
8290 | continue; | |
8291 | else if (detect_info.checked & (1 << category)) | |
8292 | { | |
8293 | if (highest | |
8294 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 8295 | break; |
2f3cbb32 KH |
8296 | } |
8297 | else if ((*(this->detector)) (&coding, &detect_info) | |
8298 | && highest | |
8299 | && (detect_info.found & (1 << category))) | |
8300 | { | |
8301 | if (category == coding_category_utf_16_auto) | |
8302 | { | |
8303 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8304 | category = coding_category_utf_16_le; | |
8305 | else | |
8306 | category = coding_category_utf_16_be; | |
8307 | } | |
8308 | break; | |
8309 | } | |
8310 | } | |
8311 | } | |
6cb21a4f | 8312 | } |
ec6d2bb8 | 8313 | |
4cddb209 KH |
8314 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
8315 | || null_byte_found) | |
ec6d2bb8 | 8316 | { |
ff0dacd7 | 8317 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 8318 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
8319 | val = Fcons (make_number (id), Qnil); |
8320 | } | |
ff0dacd7 | 8321 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 8322 | { |
ff0dacd7 | 8323 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
8324 | id = coding_categories[coding_category_undecided].id; |
8325 | val = Fcons (make_number (id), Qnil); | |
8326 | } | |
8327 | else if (highest) | |
8328 | { | |
ff0dacd7 | 8329 | if (detect_info.found) |
ec6d2bb8 | 8330 | { |
ff0dacd7 KH |
8331 | detect_info.found = 1 << category; |
8332 | val = Fcons (make_number (this->id), Qnil); | |
8333 | } | |
8334 | else | |
8335 | for (i = 0; i < coding_category_raw_text; i++) | |
8336 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
8337 | { | |
8338 | detect_info.found = 1 << coding_priorities[i]; | |
8339 | id = coding_categories[coding_priorities[i]].id; | |
8340 | val = Fcons (make_number (id), Qnil); | |
8341 | break; | |
8342 | } | |
8343 | } | |
89528eb3 KH |
8344 | else |
8345 | { | |
ff0dacd7 KH |
8346 | int mask = detect_info.rejected | detect_info.found; |
8347 | int found = 0; | |
ec6d2bb8 | 8348 | |
89528eb3 | 8349 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
8350 | { |
8351 | category = coding_priorities[i]; | |
8352 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 8353 | { |
ff0dacd7 KH |
8354 | found |= 1 << category; |
8355 | id = coding_categories[category].id; | |
c7266f4a KH |
8356 | if (id >= 0) |
8357 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
8358 | } |
8359 | } | |
8360 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
8361 | { | |
8362 | category = coding_priorities[i]; | |
8363 | if (detect_info.found & (1 << category)) | |
8364 | { | |
8365 | id = coding_categories[category].id; | |
8366 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 8367 | } |
ec6d2bb8 | 8368 | } |
ff0dacd7 | 8369 | detect_info.found |= found; |
ec6d2bb8 | 8370 | } |
ec6d2bb8 | 8371 | } |
a470d443 KH |
8372 | else if (base_category == coding_category_utf_8_auto) |
8373 | { | |
8374 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
8375 | { | |
8376 | struct coding_system *this; | |
8377 | ||
8378 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
8379 | this = coding_categories + coding_category_utf_8_sig; | |
8380 | else | |
8381 | this = coding_categories + coding_category_utf_8_nosig; | |
8382 | val = Fcons (make_number (this->id), Qnil); | |
8383 | } | |
8384 | } | |
24a73b0a KH |
8385 | else if (base_category == coding_category_utf_16_auto) |
8386 | { | |
8387 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
8388 | { | |
24a73b0a KH |
8389 | struct coding_system *this; |
8390 | ||
8391 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8392 | this = coding_categories + coding_category_utf_16_le; | |
8393 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
8394 | this = coding_categories + coding_category_utf_16_be; | |
8395 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
8396 | this = coding_categories + coding_category_utf_16_be_nosig; | |
8397 | else | |
8398 | this = coding_categories + coding_category_utf_16_le_nosig; | |
8399 | val = Fcons (make_number (this->id), Qnil); | |
8400 | } | |
8401 | } | |
df7492f9 KH |
8402 | else |
8403 | { | |
ff0dacd7 | 8404 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 8405 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8406 | } |
df7492f9 | 8407 | |
89528eb3 | 8408 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8409 | { |
4533845d | 8410 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8411 | Lisp_Object tail; |
8412 | ||
89528eb3 KH |
8413 | if (VECTORP (eol_type)) |
8414 | { | |
ff0dacd7 | 8415 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8416 | { |
8417 | if (null_byte_found) | |
8418 | normal_eol = EOL_SEEN_LF; | |
8419 | else | |
8420 | normal_eol = detect_eol (coding.source, src_bytes, | |
8421 | coding_category_raw_text); | |
8422 | } | |
ff0dacd7 KH |
8423 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8424 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8425 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8426 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8427 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8428 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8429 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8430 | coding_category_utf_16_le); | |
8431 | } | |
8432 | else | |
8433 | { | |
8434 | if (EQ (eol_type, Qunix)) | |
8435 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8436 | else if (EQ (eol_type, Qdos)) | |
8437 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8438 | else | |
8439 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8440 | } | |
8441 | ||
df7492f9 KH |
8442 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8443 | { | |
89528eb3 | 8444 | enum coding_category category; |
df7492f9 | 8445 | int this_eol; |
89528eb3 KH |
8446 | |
8447 | id = XINT (XCAR (tail)); | |
8448 | attrs = CODING_ID_ATTRS (id); | |
8449 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8450 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8451 | if (VECTORP (eol_type)) |
8452 | { | |
89528eb3 KH |
8453 | if (category == coding_category_utf_16_be |
8454 | || category == coding_category_utf_16_be_nosig) | |
8455 | this_eol = utf_16_be_eol; | |
8456 | else if (category == coding_category_utf_16_le | |
8457 | || category == coding_category_utf_16_le_nosig) | |
8458 | this_eol = utf_16_le_eol; | |
df7492f9 | 8459 | else |
89528eb3 KH |
8460 | this_eol = normal_eol; |
8461 | ||
df7492f9 KH |
8462 | if (this_eol == EOL_SEEN_LF) |
8463 | XSETCAR (tail, AREF (eol_type, 0)); | |
8464 | else if (this_eol == EOL_SEEN_CRLF) | |
8465 | XSETCAR (tail, AREF (eol_type, 1)); | |
8466 | else if (this_eol == EOL_SEEN_CR) | |
8467 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8468 | else |
8469 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8470 | } |
89528eb3 KH |
8471 | else |
8472 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8473 | } |
8474 | } | |
ec6d2bb8 | 8475 | |
4533845d | 8476 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8477 | } |
8478 | ||
ec6d2bb8 | 8479 | |
d46c5b12 KH |
8480 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8481 | 2, 3, 0, | |
48b0f3ae PJ |
8482 | doc: /* Detect coding system of the text in the region between START and END. |
8483 | Return a list of possible coding systems ordered by priority. | |
b811c52b KH |
8484 | The coding systems to try and their priorities follows what |
8485 | the function `coding-system-priority-list' (which see) returns. | |
ec6d2bb8 | 8486 | |
12e0131a | 8487 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8488 | characters as ESC), it returns a list of single element `undecided' |
8489 | or its subsidiary coding system according to a detected end-of-line | |
8490 | format. | |
ec6d2bb8 | 8491 | |
48b0f3ae PJ |
8492 | If optional argument HIGHEST is non-nil, return the coding system of |
8493 | highest priority. */) | |
5842a27b | 8494 | (Lisp_Object start, Lisp_Object end, Lisp_Object highest) |
d46c5b12 KH |
8495 | { |
8496 | int from, to; | |
8497 | int from_byte, to_byte; | |
ec6d2bb8 | 8498 | |
b7826503 PJ |
8499 | CHECK_NUMBER_COERCE_MARKER (start); |
8500 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 8501 | |
d46c5b12 KH |
8502 | validate_region (&start, &end); |
8503 | from = XINT (start), to = XINT (end); | |
8504 | from_byte = CHAR_TO_BYTE (from); | |
8505 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8506 | |
d46c5b12 KH |
8507 | if (from < GPT && to >= GPT) |
8508 | move_gap_both (to, to_byte); | |
c210f766 | 8509 | |
d46c5b12 | 8510 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8511 | to - from, to_byte - from_byte, |
0a28aafb KH |
8512 | !NILP (highest), |
8513 | !NILP (current_buffer | |
df7492f9 KH |
8514 | ->enable_multibyte_characters), |
8515 | Qnil); | |
ec6d2bb8 KH |
8516 | } |
8517 | ||
d46c5b12 KH |
8518 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8519 | 1, 2, 0, | |
48b0f3ae PJ |
8520 | doc: /* Detect coding system of the text in STRING. |
8521 | Return a list of possible coding systems ordered by priority. | |
67ceab9d KH |
8522 | The coding systems to try and their priorities follows what |
8523 | the function `coding-system-priority-list' (which see) returns. | |
fb88bf2d | 8524 | |
12e0131a | 8525 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8526 | characters as ESC), it returns a list of single element `undecided' |
8527 | or its subsidiary coding system according to a detected end-of-line | |
8528 | format. | |
d46c5b12 | 8529 | |
48b0f3ae PJ |
8530 | If optional argument HIGHEST is non-nil, return the coding system of |
8531 | highest priority. */) | |
5842a27b | 8532 | (Lisp_Object string, Lisp_Object highest) |
d46c5b12 | 8533 | { |
b7826503 | 8534 | CHECK_STRING (string); |
b73bfc1c | 8535 | |
24a73b0a KH |
8536 | return detect_coding_system (SDATA (string), |
8537 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8538 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8539 | Qnil); |
4ed46869 | 8540 | } |
4ed46869 | 8541 | |
b73bfc1c | 8542 | |
df7492f9 | 8543 | static INLINE int |
971de7fb | 8544 | char_encodable_p (int c, Lisp_Object attrs) |
05e6f5dc | 8545 | { |
df7492f9 | 8546 | Lisp_Object tail; |
df7492f9 | 8547 | struct charset *charset; |
7d64c6ad | 8548 | Lisp_Object translation_table; |
d46c5b12 | 8549 | |
7d64c6ad | 8550 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8551 | if (! NILP (translation_table)) |
7d64c6ad | 8552 | c = translate_char (translation_table, c); |
df7492f9 KH |
8553 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8554 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8555 | { |
df7492f9 KH |
8556 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8557 | if (CHAR_CHARSET_P (c, charset)) | |
8558 | break; | |
e133c8fa | 8559 | } |
df7492f9 | 8560 | return (! NILP (tail)); |
05e6f5dc | 8561 | } |
83fa074f | 8562 | |
fb88bf2d | 8563 | |
df7492f9 KH |
8564 | /* Return a list of coding systems that safely encode the text between |
8565 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8566 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8567 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8568 | unibyte, return t. */ |
e077cc80 | 8569 | |
df7492f9 KH |
8570 | DEFUN ("find-coding-systems-region-internal", |
8571 | Ffind_coding_systems_region_internal, | |
8572 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8573 | doc: /* Internal use only. */) | |
5842a27b | 8574 | (Lisp_Object start, Lisp_Object end, Lisp_Object exclude) |
df7492f9 KH |
8575 | { |
8576 | Lisp_Object coding_attrs_list, safe_codings; | |
8577 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 8578 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8579 | int c; |
0e727afa | 8580 | Lisp_Object tail, elt, work_table; |
d46c5b12 | 8581 | |
df7492f9 KH |
8582 | if (STRINGP (start)) |
8583 | { | |
8584 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8585 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8586 | return Qt; |
8587 | start_byte = 0; | |
8f924df7 | 8588 | end_byte = SBYTES (start); |
df7492f9 KH |
8589 | } |
8590 | else | |
d46c5b12 | 8591 | { |
df7492f9 KH |
8592 | CHECK_NUMBER_COERCE_MARKER (start); |
8593 | CHECK_NUMBER_COERCE_MARKER (end); | |
8594 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8595 | args_out_of_range (start, end); | |
8596 | if (NILP (current_buffer->enable_multibyte_characters)) | |
8597 | return Qt; | |
8598 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8599 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8600 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8601 | return Qt; | |
d46c5b12 | 8602 | |
e1c23804 | 8603 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8604 | { |
e1c23804 DL |
8605 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8606 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8607 | else |
e1c23804 | 8608 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8609 | } |
8610 | } | |
8611 | ||
df7492f9 KH |
8612 | coding_attrs_list = Qnil; |
8613 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8614 | if (NILP (exclude) | |
8615 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8616 | { | |
8617 | Lisp_Object attrs; | |
d46c5b12 | 8618 | |
df7492f9 KH |
8619 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
8620 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
8621 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
8622 | { |
8623 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8624 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8625 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8626 | } | |
df7492f9 | 8627 | } |
d46c5b12 | 8628 | |
df7492f9 | 8629 | if (STRINGP (start)) |
8f924df7 | 8630 | p = pbeg = SDATA (start); |
df7492f9 KH |
8631 | else |
8632 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8633 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8634 | |
df7492f9 KH |
8635 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8636 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8637 | |
0e727afa | 8638 | work_table = Fmake_char_table (Qnil, Qnil); |
05e6f5dc | 8639 | while (p < pend) |
72d1a715 | 8640 | { |
df7492f9 KH |
8641 | if (ASCII_BYTE_P (*p)) |
8642 | p++; | |
72d1a715 RS |
8643 | else |
8644 | { | |
df7492f9 | 8645 | c = STRING_CHAR_ADVANCE (p); |
0e727afa YM |
8646 | if (!NILP (char_table_ref (work_table, c))) |
8647 | /* This character was already checked. Ignore it. */ | |
8648 | continue; | |
12410ef1 | 8649 | |
df7492f9 KH |
8650 | charset_map_loaded = 0; |
8651 | for (tail = coding_attrs_list; CONSP (tail);) | |
8652 | { | |
8653 | elt = XCAR (tail); | |
8654 | if (NILP (elt)) | |
8655 | tail = XCDR (tail); | |
8656 | else if (char_encodable_p (c, elt)) | |
8657 | tail = XCDR (tail); | |
8658 | else if (CONSP (XCDR (tail))) | |
8659 | { | |
8660 | XSETCAR (tail, XCAR (XCDR (tail))); | |
8661 | XSETCDR (tail, XCDR (XCDR (tail))); | |
8662 | } | |
8663 | else | |
8664 | { | |
8665 | XSETCAR (tail, Qnil); | |
8666 | tail = XCDR (tail); | |
8667 | } | |
8668 | } | |
8669 | if (charset_map_loaded) | |
8670 | { | |
8671 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 8672 | |
df7492f9 | 8673 | if (STRINGP (start)) |
8f924df7 | 8674 | pbeg = SDATA (start); |
df7492f9 KH |
8675 | else |
8676 | pbeg = BYTE_POS_ADDR (start_byte); | |
8677 | p = pbeg + p_offset; | |
8678 | pend = pbeg + pend_offset; | |
8679 | } | |
0e727afa | 8680 | char_table_set (work_table, c, Qt); |
df7492f9 | 8681 | } |
ec6d2bb8 | 8682 | } |
fb88bf2d | 8683 | |
988b3759 | 8684 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
8685 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
8686 | if (! NILP (XCAR (tail))) | |
8687 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 8688 | |
05e6f5dc KH |
8689 | return safe_codings; |
8690 | } | |
4956c225 | 8691 | |
d46c5b12 | 8692 | |
8f924df7 KH |
8693 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
8694 | Sunencodable_char_position, 3, 5, 0, | |
8695 | doc: /* | |
8696 | Return position of first un-encodable character in a region. | |
d4a1d553 | 8697 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 8698 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 8699 | |
8f924df7 KH |
8700 | If optional 4th argument COUNT is non-nil, it specifies at most how |
8701 | many un-encodable characters to search. In this case, the value is a | |
8702 | list of positions. | |
d46c5b12 | 8703 | |
8f924df7 KH |
8704 | If optional 5th argument STRING is non-nil, it is a string to search |
8705 | for un-encodable characters. In that case, START and END are indexes | |
8706 | to the string. */) | |
5842a27b | 8707 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object count, Lisp_Object string) |
8f924df7 KH |
8708 | { |
8709 | int n; | |
8710 | struct coding_system coding; | |
7d64c6ad | 8711 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
8712 | Lisp_Object positions; |
8713 | int from, to; | |
8714 | const unsigned char *p, *stop, *pend; | |
8715 | int ascii_compatible; | |
fb88bf2d | 8716 | |
8f924df7 KH |
8717 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
8718 | attrs = CODING_ID_ATTRS (coding.id); | |
8719 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
8720 | return Qnil; | |
8721 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
8722 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 8723 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 8724 | |
8f924df7 KH |
8725 | if (NILP (string)) |
8726 | { | |
8727 | validate_region (&start, &end); | |
8728 | from = XINT (start); | |
8729 | to = XINT (end); | |
8730 | if (NILP (current_buffer->enable_multibyte_characters) | |
8731 | || (ascii_compatible | |
8732 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
8733 | return Qnil; | |
8734 | p = CHAR_POS_ADDR (from); | |
8735 | pend = CHAR_POS_ADDR (to); | |
8736 | if (from < GPT && to >= GPT) | |
8737 | stop = GPT_ADDR; | |
8738 | else | |
8739 | stop = pend; | |
8740 | } | |
8741 | else | |
8742 | { | |
8743 | CHECK_STRING (string); | |
8744 | CHECK_NATNUM (start); | |
8745 | CHECK_NATNUM (end); | |
8746 | from = XINT (start); | |
8747 | to = XINT (end); | |
8748 | if (from > to | |
8749 | || to > SCHARS (string)) | |
8750 | args_out_of_range_3 (string, start, end); | |
8751 | if (! STRING_MULTIBYTE (string)) | |
8752 | return Qnil; | |
8753 | p = SDATA (string) + string_char_to_byte (string, from); | |
8754 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
8755 | if (ascii_compatible && (to - from) == (pend - p)) | |
8756 | return Qnil; | |
8757 | } | |
f2558efd | 8758 | |
8f924df7 KH |
8759 | if (NILP (count)) |
8760 | n = 1; | |
8761 | else | |
b73bfc1c | 8762 | { |
8f924df7 KH |
8763 | CHECK_NATNUM (count); |
8764 | n = XINT (count); | |
b73bfc1c KH |
8765 | } |
8766 | ||
8f924df7 KH |
8767 | positions = Qnil; |
8768 | while (1) | |
d46c5b12 | 8769 | { |
8f924df7 | 8770 | int c; |
ec6d2bb8 | 8771 | |
8f924df7 KH |
8772 | if (ascii_compatible) |
8773 | while (p < stop && ASCII_BYTE_P (*p)) | |
8774 | p++, from++; | |
8775 | if (p >= stop) | |
0e79d667 | 8776 | { |
8f924df7 KH |
8777 | if (p >= pend) |
8778 | break; | |
8779 | stop = pend; | |
8780 | p = GAP_END_ADDR; | |
0e79d667 | 8781 | } |
ec6d2bb8 | 8782 | |
8f924df7 KH |
8783 | c = STRING_CHAR_ADVANCE (p); |
8784 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
8785 | && ! char_charset (translate_char (translation_table, c), |
8786 | charset_list, NULL)) | |
ec6d2bb8 | 8787 | { |
8f924df7 KH |
8788 | positions = Fcons (make_number (from), positions); |
8789 | n--; | |
8790 | if (n == 0) | |
8791 | break; | |
ec6d2bb8 KH |
8792 | } |
8793 | ||
8f924df7 KH |
8794 | from++; |
8795 | } | |
d46c5b12 | 8796 | |
8f924df7 KH |
8797 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
8798 | } | |
d46c5b12 | 8799 | |
d46c5b12 | 8800 | |
df7492f9 KH |
8801 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
8802 | Scheck_coding_systems_region, 3, 3, 0, | |
8803 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 8804 | |
df7492f9 KH |
8805 | START and END are buffer positions specifying the region. |
8806 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 8807 | |
df7492f9 | 8808 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 8809 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
8810 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
8811 | characters are found. | |
93dec019 | 8812 | |
df7492f9 KH |
8813 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
8814 | value is nil. | |
93dec019 | 8815 | |
df7492f9 KH |
8816 | START may be a string. In that case, check if the string is |
8817 | encodable, and the value contains indices to the string instead of | |
5704f39a KH |
8818 | buffer positions. END is ignored. |
8819 | ||
4c1958f4 | 8820 | If the current buffer (or START if it is a string) is unibyte, the value |
5704f39a | 8821 | is nil. */) |
5842a27b | 8822 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system_list) |
05e6f5dc | 8823 | { |
df7492f9 KH |
8824 | Lisp_Object list; |
8825 | EMACS_INT start_byte, end_byte; | |
8826 | int pos; | |
7c78e542 | 8827 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8828 | int c; |
7d64c6ad | 8829 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 8830 | |
05e6f5dc KH |
8831 | if (STRINGP (start)) |
8832 | { | |
df7492f9 | 8833 | if (!STRING_MULTIBYTE (start) |
4c1958f4 | 8834 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8835 | return Qnil; |
8836 | start_byte = 0; | |
8f924df7 | 8837 | end_byte = SBYTES (start); |
df7492f9 | 8838 | pos = 0; |
d46c5b12 | 8839 | } |
05e6f5dc | 8840 | else |
b73bfc1c | 8841 | { |
b7826503 PJ |
8842 | CHECK_NUMBER_COERCE_MARKER (start); |
8843 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
8844 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
8845 | args_out_of_range (start, end); | |
8846 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
8847 | return Qnil; |
8848 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8849 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8850 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
5704f39a | 8851 | return Qnil; |
df7492f9 | 8852 | |
e1c23804 | 8853 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 8854 | { |
e1c23804 DL |
8855 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8856 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8857 | else |
e1c23804 | 8858 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 8859 | } |
e1c23804 | 8860 | pos = XINT (start); |
b73bfc1c | 8861 | } |
7553d0e1 | 8862 | |
df7492f9 KH |
8863 | list = Qnil; |
8864 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 8865 | { |
df7492f9 | 8866 | elt = XCAR (tail); |
7d64c6ad | 8867 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
8868 | ASET (attrs, coding_attr_trans_tbl, |
8869 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 8870 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
8871 | } |
8872 | ||
df7492f9 | 8873 | if (STRINGP (start)) |
8f924df7 | 8874 | p = pbeg = SDATA (start); |
72d1a715 | 8875 | else |
df7492f9 KH |
8876 | p = pbeg = BYTE_POS_ADDR (start_byte); |
8877 | pend = p + (end_byte - start_byte); | |
4ed46869 | 8878 | |
df7492f9 KH |
8879 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
8880 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 8881 | |
df7492f9 | 8882 | while (p < pend) |
d46c5b12 | 8883 | { |
df7492f9 KH |
8884 | if (ASCII_BYTE_P (*p)) |
8885 | p++; | |
e133c8fa | 8886 | else |
05e6f5dc | 8887 | { |
df7492f9 KH |
8888 | c = STRING_CHAR_ADVANCE (p); |
8889 | ||
8890 | charset_map_loaded = 0; | |
8891 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
8892 | { | |
8893 | elt = XCDR (XCAR (tail)); | |
8894 | if (! char_encodable_p (c, XCAR (elt))) | |
8895 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
8896 | } | |
8897 | if (charset_map_loaded) | |
8898 | { | |
8899 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
8900 | ||
8901 | if (STRINGP (start)) | |
8f924df7 | 8902 | pbeg = SDATA (start); |
df7492f9 KH |
8903 | else |
8904 | pbeg = BYTE_POS_ADDR (start_byte); | |
8905 | p = pbeg + p_offset; | |
8906 | pend = pbeg + pend_offset; | |
8907 | } | |
05e6f5dc | 8908 | } |
df7492f9 | 8909 | pos++; |
d46c5b12 | 8910 | } |
4ed46869 | 8911 | |
df7492f9 KH |
8912 | tail = list; |
8913 | list = Qnil; | |
8914 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 8915 | { |
df7492f9 KH |
8916 | elt = XCAR (tail); |
8917 | if (CONSP (XCDR (XCDR (elt)))) | |
8918 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
8919 | list); | |
ec6d2bb8 | 8920 | } |
2b4f9037 | 8921 | |
df7492f9 | 8922 | return list; |
d46c5b12 KH |
8923 | } |
8924 | ||
3fd9494b | 8925 | |
b73bfc1c | 8926 | Lisp_Object |
cf84bb53 JB |
8927 | code_convert_region (Lisp_Object start, Lisp_Object end, |
8928 | Lisp_Object coding_system, Lisp_Object dst_object, | |
8929 | int encodep, int norecord) | |
4ed46869 | 8930 | { |
3a73fa5d | 8931 | struct coding_system coding; |
df7492f9 KH |
8932 | EMACS_INT from, from_byte, to, to_byte; |
8933 | Lisp_Object src_object; | |
4ed46869 | 8934 | |
b7826503 PJ |
8935 | CHECK_NUMBER_COERCE_MARKER (start); |
8936 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
8937 | if (NILP (coding_system)) |
8938 | coding_system = Qno_conversion; | |
8939 | else | |
8940 | CHECK_CODING_SYSTEM (coding_system); | |
8941 | src_object = Fcurrent_buffer (); | |
8942 | if (NILP (dst_object)) | |
8943 | dst_object = src_object; | |
8944 | else if (! EQ (dst_object, Qt)) | |
8945 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 8946 | |
d46c5b12 KH |
8947 | validate_region (&start, &end); |
8948 | from = XFASTINT (start); | |
df7492f9 | 8949 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 8950 | to = XFASTINT (end); |
df7492f9 | 8951 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 8952 | |
df7492f9 KH |
8953 | setup_coding_system (coding_system, &coding); |
8954 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 8955 | |
df7492f9 KH |
8956 | if (encodep) |
8957 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8958 | dst_object); | |
8959 | else | |
8960 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8961 | dst_object); | |
8962 | if (! norecord) | |
8963 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 8964 | |
df7492f9 KH |
8965 | return (BUFFERP (dst_object) |
8966 | ? make_number (coding.produced_char) | |
8967 | : coding.dst_object); | |
4031e2bf | 8968 | } |
78108bcd | 8969 | |
4ed46869 | 8970 | |
4031e2bf | 8971 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 8972 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 8973 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
8974 | When called from a program, takes four arguments: |
8975 | START, END, CODING-SYSTEM, and DESTINATION. | |
8976 | START and END are buffer positions. | |
8844fa83 | 8977 | |
df7492f9 | 8978 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 8979 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
8980 | If buffer, the decoded text is inserted in that buffer after point (point |
8981 | does not move). | |
446dcd75 | 8982 | In those cases, the length of the decoded text is returned. |
319a3947 | 8983 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 8984 | |
48b0f3ae PJ |
8985 | This function sets `last-coding-system-used' to the precise coding system |
8986 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8987 | not fully specified.) */) |
5842a27b | 8988 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
4031e2bf | 8989 | { |
df7492f9 | 8990 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 8991 | } |
8844fa83 | 8992 | |
3a73fa5d | 8993 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
8994 | 3, 4, "r\nzCoding system: ", |
8995 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
8996 | When called from a program, takes four arguments: |
8997 | START, END, CODING-SYSTEM and DESTINATION. | |
8998 | START and END are buffer positions. | |
d46c5b12 | 8999 | |
df7492f9 KH |
9000 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
9001 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
9002 | If buffer, the encoded text is inserted in that buffer after point (point |
9003 | does not move). | |
446dcd75 | 9004 | In those cases, the length of the encoded text is returned. |
319a3947 | 9005 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 9006 | |
48b0f3ae PJ |
9007 | This function sets `last-coding-system-used' to the precise coding system |
9008 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 9009 | not fully specified.) */) |
5842a27b | 9010 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
3a73fa5d | 9011 | { |
df7492f9 | 9012 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
9013 | } |
9014 | ||
9015 | Lisp_Object | |
6f704c76 DN |
9016 | code_convert_string (Lisp_Object string, Lisp_Object coding_system, |
9017 | Lisp_Object dst_object, int encodep, int nocopy, int norecord) | |
b73bfc1c | 9018 | { |
4031e2bf | 9019 | struct coding_system coding; |
df7492f9 | 9020 | EMACS_INT chars, bytes; |
ec6d2bb8 | 9021 | |
b7826503 | 9022 | CHECK_STRING (string); |
d46c5b12 | 9023 | if (NILP (coding_system)) |
4956c225 | 9024 | { |
df7492f9 KH |
9025 | if (! norecord) |
9026 | Vlast_coding_system_used = Qno_conversion; | |
9027 | if (NILP (dst_object)) | |
9028 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 9029 | } |
b73bfc1c | 9030 | |
df7492f9 KH |
9031 | if (NILP (coding_system)) |
9032 | coding_system = Qno_conversion; | |
9033 | else | |
9034 | CHECK_CODING_SYSTEM (coding_system); | |
9035 | if (NILP (dst_object)) | |
9036 | dst_object = Qt; | |
9037 | else if (! EQ (dst_object, Qt)) | |
9038 | CHECK_BUFFER (dst_object); | |
73be902c | 9039 | |
df7492f9 | 9040 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 9041 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
9042 | chars = SCHARS (string); |
9043 | bytes = SBYTES (string); | |
df7492f9 KH |
9044 | if (encodep) |
9045 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9046 | else | |
9047 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9048 | if (! norecord) | |
9049 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 9050 | |
df7492f9 KH |
9051 | return (BUFFERP (dst_object) |
9052 | ? make_number (coding.produced_char) | |
9053 | : coding.dst_object); | |
4ed46869 | 9054 | } |
73be902c | 9055 | |
b73bfc1c | 9056 | |
ecec61c1 | 9057 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 9058 | Do not set Vlast_coding_system_used. |
4ed46869 | 9059 | |
ec6d2bb8 KH |
9060 | This function is called only from macros DECODE_FILE and |
9061 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 9062 | |
ecec61c1 | 9063 | Lisp_Object |
cf84bb53 JB |
9064 | code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system, |
9065 | int encodep) | |
4ed46869 | 9066 | { |
0be8721c | 9067 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
9068 | } |
9069 | ||
4ed46869 | 9070 | |
df7492f9 KH |
9071 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
9072 | 2, 4, 0, | |
9073 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
9074 | ||
9075 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
9076 | if the decoding operation is trivial. | |
ecec61c1 | 9077 | |
d4a1d553 | 9078 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
9079 | inserted in that buffer after point (point does not move). In this |
9080 | case, the return value is the length of the decoded text. | |
ecec61c1 | 9081 | |
df7492f9 KH |
9082 | This function sets `last-coding-system-used' to the precise coding system |
9083 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 9084 | not fully specified.) */) |
5842a27b | 9085 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9086 | { |
df7492f9 KH |
9087 | return code_convert_string (string, coding_system, buffer, |
9088 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
9089 | } |
9090 | ||
df7492f9 KH |
9091 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
9092 | 2, 4, 0, | |
9093 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
9094 | ||
9095 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
9096 | itself if the encoding operation is trivial. | |
9097 | ||
d4a1d553 | 9098 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
9099 | inserted in that buffer after point (point does not move). In this |
9100 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
9101 | |
9102 | This function sets `last-coding-system-used' to the precise coding system | |
9103 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
9104 | not fully specified.) */) | |
5842a27b | 9105 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9106 | { |
df7492f9 | 9107 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 9108 | 1, ! NILP (nocopy), 1); |
4ed46869 | 9109 | } |
df7492f9 | 9110 | |
3a73fa5d | 9111 | \f |
4ed46869 | 9112 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
9113 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
9114 | Return the corresponding character. */) | |
5842a27b | 9115 | (Lisp_Object code) |
4ed46869 | 9116 | { |
df7492f9 KH |
9117 | Lisp_Object spec, attrs, val; |
9118 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
9119 | int c; | |
4ed46869 | 9120 | |
df7492f9 KH |
9121 | CHECK_NATNUM (code); |
9122 | c = XFASTINT (code); | |
9123 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9124 | attrs = AREF (spec, 0); | |
4ed46869 | 9125 | |
df7492f9 KH |
9126 | if (ASCII_BYTE_P (c) |
9127 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9128 | return code; | |
4ed46869 | 9129 | |
df7492f9 KH |
9130 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9131 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
9132 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
9133 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 9134 | |
df7492f9 KH |
9135 | if (c <= 0x7F) |
9136 | charset = charset_roman; | |
9137 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 9138 | { |
df7492f9 KH |
9139 | charset = charset_kana; |
9140 | c -= 0x80; | |
4ed46869 | 9141 | } |
55ab7be3 | 9142 | else |
4ed46869 | 9143 | { |
004068e4 | 9144 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
9145 | |
9146 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
9147 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
9148 | error ("Invalid code: %d", code); | |
9149 | SJIS_TO_JIS (c); | |
9150 | charset = charset_kanji; | |
4ed46869 | 9151 | } |
df7492f9 KH |
9152 | c = DECODE_CHAR (charset, c); |
9153 | if (c < 0) | |
9154 | error ("Invalid code: %d", code); | |
9155 | return make_number (c); | |
93dec019 | 9156 | } |
4ed46869 | 9157 | |
48b0f3ae | 9158 | |
4ed46869 | 9159 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 9160 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae | 9161 | Return the corresponding code in SJIS. */) |
5842a27b | 9162 | (Lisp_Object ch) |
4ed46869 | 9163 | { |
df7492f9 KH |
9164 | Lisp_Object spec, attrs, charset_list; |
9165 | int c; | |
9166 | struct charset *charset; | |
9167 | unsigned code; | |
48b0f3ae | 9168 | |
df7492f9 KH |
9169 | CHECK_CHARACTER (ch); |
9170 | c = XFASTINT (ch); | |
9171 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9172 | attrs = AREF (spec, 0); | |
9173 | ||
9174 | if (ASCII_CHAR_P (c) | |
9175 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9176 | return ch; | |
9177 | ||
9178 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9179 | charset = char_charset (c, charset_list, &code); | |
9180 | if (code == CHARSET_INVALID_CODE (charset)) | |
9181 | error ("Can't encode by shift_jis encoding: %d", c); | |
9182 | JIS_TO_SJIS (code); | |
9183 | ||
9184 | return make_number (code); | |
4ed46869 KH |
9185 | } |
9186 | ||
9187 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
9188 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
9189 | Return the corresponding character. */) | |
5842a27b | 9190 | (Lisp_Object code) |
d46c5b12 | 9191 | { |
df7492f9 KH |
9192 | Lisp_Object spec, attrs, val; |
9193 | struct charset *charset_roman, *charset_big5, *charset; | |
9194 | int c; | |
6289dd10 | 9195 | |
df7492f9 KH |
9196 | CHECK_NATNUM (code); |
9197 | c = XFASTINT (code); | |
9198 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9199 | attrs = AREF (spec, 0); | |
4ed46869 | 9200 | |
df7492f9 KH |
9201 | if (ASCII_BYTE_P (c) |
9202 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9203 | return code; | |
6289dd10 | 9204 | |
df7492f9 KH |
9205 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9206 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
9207 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 9208 | |
df7492f9 KH |
9209 | if (c <= 0x7F) |
9210 | charset = charset_roman; | |
c28a9453 KH |
9211 | else |
9212 | { | |
df7492f9 KH |
9213 | int b1 = c >> 8, b2 = c & 0x7F; |
9214 | if (b1 < 0xA1 || b1 > 0xFE | |
9215 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
9216 | error ("Invalid code: %d", code); | |
9217 | charset = charset_big5; | |
c28a9453 | 9218 | } |
df7492f9 KH |
9219 | c = DECODE_CHAR (charset, (unsigned )c); |
9220 | if (c < 0) | |
9221 | error ("Invalid code: %d", code); | |
9222 | return make_number (c); | |
d46c5b12 | 9223 | } |
6289dd10 | 9224 | |
4ed46869 | 9225 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 9226 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae | 9227 | Return the corresponding character code in Big5. */) |
5842a27b | 9228 | (Lisp_Object ch) |
4ed46869 | 9229 | { |
df7492f9 KH |
9230 | Lisp_Object spec, attrs, charset_list; |
9231 | struct charset *charset; | |
9232 | int c; | |
9233 | unsigned code; | |
9234 | ||
9235 | CHECK_CHARACTER (ch); | |
9236 | c = XFASTINT (ch); | |
9237 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9238 | attrs = AREF (spec, 0); | |
9239 | if (ASCII_CHAR_P (c) | |
9240 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9241 | return ch; | |
9242 | ||
9243 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9244 | charset = char_charset (c, charset_list, &code); | |
9245 | if (code == CHARSET_INVALID_CODE (charset)) | |
9246 | error ("Can't encode by Big5 encoding: %d", c); | |
9247 | ||
9248 | return make_number (code); | |
4ed46869 | 9249 | } |
48b0f3ae | 9250 | |
3a73fa5d | 9251 | \f |
002fdb44 | 9252 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 9253 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9254 | doc: /* Internal use only. */) |
5842a27b | 9255 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9256 | { |
6ed8eeff | 9257 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); |
b7826503 | 9258 | CHECK_SYMBOL (coding_system); |
b8299c66 | 9259 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 9260 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 9261 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
df7492f9 | 9262 | /* Characer composition should be disabled. */ |
c73bd236 | 9263 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
9264 | terminal_coding->src_multibyte = 1; |
9265 | terminal_coding->dst_multibyte = 0; | |
4ed46869 KH |
9266 | return Qnil; |
9267 | } | |
9268 | ||
c4825358 KH |
9269 | DEFUN ("set-safe-terminal-coding-system-internal", |
9270 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 9271 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 9272 | doc: /* Internal use only. */) |
5842a27b | 9273 | (Lisp_Object coding_system) |
d46c5b12 | 9274 | { |
b7826503 | 9275 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
9276 | setup_coding_system (Fcheck_coding_system (coding_system), |
9277 | &safe_terminal_coding); | |
df7492f9 KH |
9278 | /* Characer composition should be disabled. */ |
9279 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
9280 | safe_terminal_coding.src_multibyte = 1; |
9281 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
9282 | return Qnil; |
9283 | } | |
4ed46869 | 9284 | |
002fdb44 | 9285 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 9286 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff | 9287 | doc: /* Return coding system specified for terminal output on the given terminal. |
708e05dc | 9288 | TERMINAL may be a terminal object, a frame, or nil for the selected |
6ed8eeff | 9289 | frame's terminal device. */) |
5842a27b | 9290 | (Lisp_Object terminal) |
4ed46869 | 9291 | { |
985773c9 MB |
9292 | struct coding_system *terminal_coding |
9293 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
9294 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 9295 | |
ae6f73fa | 9296 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 9297 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
9298 | } |
9299 | ||
002fdb44 | 9300 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 9301 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9302 | doc: /* Internal use only. */) |
5842a27b | 9303 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9304 | { |
6ed8eeff | 9305 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 9306 | CHECK_SYMBOL (coding_system); |
624bda09 KH |
9307 | if (NILP (coding_system)) |
9308 | coding_system = Qno_conversion; | |
9309 | else | |
9310 | Fcheck_coding_system (coding_system); | |
9311 | setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t)); | |
df7492f9 | 9312 | /* Characer composition should be disabled. */ |
c73bd236 MB |
9313 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
9314 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
9315 | return Qnil; |
9316 | } | |
9317 | ||
9318 | DEFUN ("keyboard-coding-system", | |
985773c9 | 9319 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 9320 | doc: /* Return coding system specified for decoding keyboard input. */) |
5842a27b | 9321 | (Lisp_Object terminal) |
4ed46869 | 9322 | { |
985773c9 MB |
9323 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
9324 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
9325 | } |
9326 | ||
4ed46869 | 9327 | \f |
a5d301df KH |
9328 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
9329 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
9330 | doc: /* Choose a coding system for an operation based on the target name. |
9331 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
9332 | DECODING-SYSTEM is the coding system to use for decoding | |
9333 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
9334 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 9335 | |
48b0f3ae PJ |
9336 | The first argument OPERATION specifies an I/O primitive: |
9337 | For file I/O, `insert-file-contents' or `write-region'. | |
9338 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
9339 | For network I/O, `open-network-stream'. | |
05e6f5dc | 9340 | |
48b0f3ae PJ |
9341 | The remaining arguments should be the same arguments that were passed |
9342 | to the primitive. Depending on which primitive, one of those arguments | |
9343 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
9344 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 9345 | |
48b0f3ae | 9346 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 9347 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 9348 | For process I/O, TARGET is a process name. |
d4a1d553 | 9349 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 9350 | |
d4a1d553 | 9351 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
9352 | `file-coding-system-alist', `process-coding-system-alist', |
9353 | or `network-coding-system-alist' depending on OPERATION. | |
9354 | They may specify a coding system, a cons of coding systems, | |
9355 | or a function symbol to call. | |
9356 | In the last case, we call the function with one argument, | |
9357 | which is a list of all the arguments given to this function. | |
1011c487 MB |
9358 | If the function can't decide a coding system, it can return |
9359 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 9360 | |
b883cdb2 MB |
9361 | If OPERATION is `insert-file-contents', the argument corresponding to |
9362 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
9363 | file name to look up, and BUFFER is a buffer that contains the file's | |
9364 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
9365 | function to call for FILENAME, that function should examine the | |
9366 | contents of BUFFER instead of reading the file. | |
9367 | ||
d918f936 | 9368 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
5842a27b | 9369 | (int nargs, Lisp_Object *args) |
6b89e3aa | 9370 | { |
4ed46869 KH |
9371 | Lisp_Object operation, target_idx, target, val; |
9372 | register Lisp_Object chain; | |
177c0ea7 | 9373 | |
4ed46869 KH |
9374 | if (nargs < 2) |
9375 | error ("Too few arguments"); | |
9376 | operation = args[0]; | |
9377 | if (!SYMBOLP (operation) | |
9378 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
3ed051d4 | 9379 | error ("Invalid first argument"); |
4ed46869 KH |
9380 | if (nargs < 1 + XINT (target_idx)) |
9381 | error ("Too few arguments for operation: %s", | |
8f924df7 | 9382 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
9383 | target = args[XINT (target_idx) + 1]; |
9384 | if (!(STRINGP (target) | |
091a0ff0 KH |
9385 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
9386 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 9387 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
df7492f9 | 9388 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
091a0ff0 KH |
9389 | if (CONSP (target)) |
9390 | target = XCAR (target); | |
4ed46869 | 9391 | |
2e34157c RS |
9392 | chain = ((EQ (operation, Qinsert_file_contents) |
9393 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9394 | ? Vfile_coding_system_alist |
2e34157c | 9395 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9396 | ? Vnetwork_coding_system_alist |
9397 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9398 | if (NILP (chain)) |
9399 | return Qnil; | |
9400 | ||
03699b14 | 9401 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9402 | { |
f44d27ce | 9403 | Lisp_Object elt; |
6b89e3aa | 9404 | |
df7492f9 | 9405 | elt = XCAR (chain); |
4ed46869 KH |
9406 | if (CONSP (elt) |
9407 | && ((STRINGP (target) | |
03699b14 KR |
9408 | && STRINGP (XCAR (elt)) |
9409 | && fast_string_match (XCAR (elt), target) >= 0) | |
9410 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9411 | { |
03699b14 | 9412 | val = XCDR (elt); |
b19fd4c5 KH |
9413 | /* Here, if VAL is both a valid coding system and a valid |
9414 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9415 | if (CONSP (val)) |
9416 | return val; | |
9417 | if (! SYMBOLP (val)) | |
9418 | return Qnil; | |
9419 | if (! NILP (Fcoding_system_p (val))) | |
9420 | return Fcons (val, val); | |
b19fd4c5 | 9421 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9422 | { |
e2b97060 MB |
9423 | /* We use call1 rather than safe_call1 |
9424 | so as to get bug reports about functions called here | |
9425 | which don't handle the current interface. */ | |
9426 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9427 | if (CONSP (val)) |
9428 | return val; | |
9429 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9430 | return Fcons (val, val); | |
6b89e3aa | 9431 | } |
02ba4723 | 9432 | return Qnil; |
6b89e3aa KH |
9433 | } |
9434 | } | |
4ed46869 | 9435 | return Qnil; |
6b89e3aa KH |
9436 | } |
9437 | ||
df7492f9 | 9438 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9439 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9440 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9441 | If multiple coding systems belong to the same category, |
a3181084 DL |
9442 | all but the first one are ignored. |
9443 | ||
d4a1d553 | 9444 | usage: (set-coding-system-priority &rest coding-systems) */) |
5842a27b | 9445 | (int nargs, Lisp_Object *args) |
df7492f9 KH |
9446 | { |
9447 | int i, j; | |
9448 | int changed[coding_category_max]; | |
9449 | enum coding_category priorities[coding_category_max]; | |
9450 | ||
72af86bd | 9451 | memset (changed, 0, sizeof changed); |
6b89e3aa | 9452 | |
df7492f9 | 9453 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9454 | { |
df7492f9 KH |
9455 | enum coding_category category; |
9456 | Lisp_Object spec, attrs; | |
6b89e3aa | 9457 | |
df7492f9 KH |
9458 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9459 | attrs = AREF (spec, 0); | |
9460 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9461 | if (changed[category]) | |
9462 | /* Ignore this coding system because a coding system of the | |
9463 | same category already had a higher priority. */ | |
9464 | continue; | |
9465 | changed[category] = 1; | |
9466 | priorities[j++] = category; | |
9467 | if (coding_categories[category].id >= 0 | |
9468 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9469 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9470 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9471 | } |
6b89e3aa | 9472 | |
df7492f9 KH |
9473 | /* Now we have decided top J priorities. Reflect the order of the |
9474 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9475 | |
df7492f9 | 9476 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9477 | { |
df7492f9 KH |
9478 | while (j < coding_category_max |
9479 | && changed[coding_priorities[j]]) | |
9480 | j++; | |
9481 | if (j == coding_category_max) | |
9482 | abort (); | |
9483 | priorities[i] = coding_priorities[j]; | |
9484 | } | |
6b89e3aa | 9485 | |
72af86bd | 9486 | memcpy (coding_priorities, priorities, sizeof priorities); |
177c0ea7 | 9487 | |
ff563fce KH |
9488 | /* Update `coding-category-list'. */ |
9489 | Vcoding_category_list = Qnil; | |
9490 | for (i = coding_category_max - 1; i >= 0; i--) | |
9491 | Vcoding_category_list | |
9492 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9493 | Vcoding_category_list); | |
6b89e3aa | 9494 | |
df7492f9 | 9495 | return Qnil; |
6b89e3aa KH |
9496 | } |
9497 | ||
df7492f9 KH |
9498 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9499 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 | 9500 | doc: /* Return a list of coding systems ordered by their priorities. |
b811c52b KH |
9501 | The list contains a subset of coding systems; i.e. coding systems |
9502 | assigned to each coding category (see `coding-category-list'). | |
9503 | ||
da7db224 | 9504 | HIGHESTP non-nil means just return the highest priority one. */) |
5842a27b | 9505 | (Lisp_Object highestp) |
d46c5b12 KH |
9506 | { |
9507 | int i; | |
df7492f9 | 9508 | Lisp_Object val; |
6b89e3aa | 9509 | |
df7492f9 | 9510 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9511 | { |
df7492f9 KH |
9512 | enum coding_category category = coding_priorities[i]; |
9513 | int id = coding_categories[category].id; | |
9514 | Lisp_Object attrs; | |
068a9dbd | 9515 | |
df7492f9 KH |
9516 | if (id < 0) |
9517 | continue; | |
9518 | attrs = CODING_ID_ATTRS (id); | |
9519 | if (! NILP (highestp)) | |
9520 | return CODING_ATTR_BASE_NAME (attrs); | |
9521 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9522 | } | |
9523 | return Fnreverse (val); | |
9524 | } | |
068a9dbd | 9525 | |
91433552 | 9526 | static const char *const suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9527 | |
9528 | static Lisp_Object | |
971de7fb | 9529 | make_subsidiaries (Lisp_Object base) |
068a9dbd | 9530 | { |
df7492f9 | 9531 | Lisp_Object subsidiaries; |
8f924df7 | 9532 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
9533 | char *buf = (char *) alloca (base_name_len + 6); |
9534 | int i; | |
068a9dbd | 9535 | |
72af86bd | 9536 | memcpy (buf, SDATA (SYMBOL_NAME (base)), base_name_len); |
df7492f9 KH |
9537 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
9538 | for (i = 0; i < 3; i++) | |
068a9dbd | 9539 | { |
72af86bd | 9540 | memcpy (buf + base_name_len, suffixes[i], strlen (suffixes[i]) + 1); |
df7492f9 | 9541 | ASET (subsidiaries, i, intern (buf)); |
068a9dbd | 9542 | } |
df7492f9 | 9543 | return subsidiaries; |
068a9dbd KH |
9544 | } |
9545 | ||
9546 | ||
df7492f9 KH |
9547 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9548 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9549 | doc: /* For internal use only. |
9550 | usage: (define-coding-system-internal ...) */) | |
5842a27b | 9551 | (int nargs, Lisp_Object *args) |
068a9dbd | 9552 | { |
df7492f9 KH |
9553 | Lisp_Object name; |
9554 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9555 | Lisp_Object attrs; /* Vector of attributes. */ | |
9556 | Lisp_Object eol_type; | |
9557 | Lisp_Object aliases; | |
9558 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9559 | enum coding_category category; | |
9560 | Lisp_Object tail, val; | |
9561 | int max_charset_id = 0; | |
9562 | int i; | |
068a9dbd | 9563 | |
df7492f9 KH |
9564 | if (nargs < coding_arg_max) |
9565 | goto short_args; | |
068a9dbd | 9566 | |
df7492f9 | 9567 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9568 | |
df7492f9 KH |
9569 | name = args[coding_arg_name]; |
9570 | CHECK_SYMBOL (name); | |
9571 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 9572 | |
df7492f9 KH |
9573 | val = args[coding_arg_mnemonic]; |
9574 | if (! STRINGP (val)) | |
9575 | CHECK_CHARACTER (val); | |
9576 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 9577 | |
df7492f9 KH |
9578 | coding_type = args[coding_arg_coding_type]; |
9579 | CHECK_SYMBOL (coding_type); | |
9580 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 9581 | |
df7492f9 KH |
9582 | charset_list = args[coding_arg_charset_list]; |
9583 | if (SYMBOLP (charset_list)) | |
9584 | { | |
9585 | if (EQ (charset_list, Qiso_2022)) | |
9586 | { | |
9587 | if (! EQ (coding_type, Qiso_2022)) | |
9588 | error ("Invalid charset-list"); | |
9589 | charset_list = Viso_2022_charset_list; | |
9590 | } | |
9591 | else if (EQ (charset_list, Qemacs_mule)) | |
9592 | { | |
9593 | if (! EQ (coding_type, Qemacs_mule)) | |
9594 | error ("Invalid charset-list"); | |
9595 | charset_list = Vemacs_mule_charset_list; | |
9596 | } | |
9597 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
9598 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9599 | max_charset_id = XFASTINT (XCAR (tail)); | |
9600 | } | |
068a9dbd KH |
9601 | else |
9602 | { | |
df7492f9 | 9603 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9604 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9605 | { |
df7492f9 KH |
9606 | struct charset *charset; |
9607 | ||
985773c9 | 9608 | val = XCAR (tail); |
df7492f9 KH |
9609 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9610 | if (EQ (coding_type, Qiso_2022) | |
9611 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9612 | : EQ (coding_type, Qemacs_mule) | |
9613 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9614 | : 0) | |
9615 | error ("Can't handle charset `%s'", | |
8f924df7 | 9616 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9617 | |
8f924df7 | 9618 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9619 | if (max_charset_id < charset->id) |
9620 | max_charset_id = charset->id; | |
068a9dbd KH |
9621 | } |
9622 | } | |
df7492f9 | 9623 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 9624 | |
1b3b981b AS |
9625 | safe_charsets = make_uninit_string (max_charset_id + 1); |
9626 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 | 9627 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8f924df7 | 9628 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 9629 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 9630 | |
584948ac | 9631 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 9632 | |
df7492f9 | 9633 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 9634 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9635 | CHECK_SYMBOL (val); |
df7492f9 | 9636 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 9637 | |
df7492f9 | 9638 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 9639 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9640 | CHECK_SYMBOL (val); |
df7492f9 | 9641 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 9642 | |
df7492f9 KH |
9643 | val = args[coding_arg_post_read_conversion]; |
9644 | CHECK_SYMBOL (val); | |
9645 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 9646 | |
df7492f9 KH |
9647 | val = args[coding_arg_pre_write_conversion]; |
9648 | CHECK_SYMBOL (val); | |
9649 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 9650 | |
df7492f9 KH |
9651 | val = args[coding_arg_default_char]; |
9652 | if (NILP (val)) | |
9653 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
9654 | else | |
9655 | { | |
8f924df7 | 9656 | CHECK_CHARACTER (val); |
df7492f9 KH |
9657 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
9658 | } | |
4031e2bf | 9659 | |
8f924df7 KH |
9660 | val = args[coding_arg_for_unibyte]; |
9661 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 9662 | |
df7492f9 KH |
9663 | val = args[coding_arg_plist]; |
9664 | CHECK_LIST (val); | |
9665 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 9666 | |
df7492f9 KH |
9667 | if (EQ (coding_type, Qcharset)) |
9668 | { | |
c7c66a95 KH |
9669 | /* Generate a lisp vector of 256 elements. Each element is nil, |
9670 | integer, or a list of charset IDs. | |
3a73fa5d | 9671 | |
c7c66a95 KH |
9672 | If Nth element is nil, the byte code N is invalid in this |
9673 | coding system. | |
4ed46869 | 9674 | |
c7c66a95 KH |
9675 | If Nth element is a number NUM, N is the first byte of a |
9676 | charset whose ID is NUM. | |
4ed46869 | 9677 | |
c7c66a95 KH |
9678 | If Nth element is a list of charset IDs, N is the first byte |
9679 | of one of them. The list is sorted by dimensions of the | |
2bc515e4 | 9680 | charsets. A charset of smaller dimension comes firtst. */ |
df7492f9 | 9681 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 9682 | |
5c99c2e6 | 9683 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9684 | { |
c7c66a95 KH |
9685 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
9686 | int dim = CHARSET_DIMENSION (charset); | |
9687 | int idx = (dim - 1) * 4; | |
4ed46869 | 9688 | |
5c99c2e6 | 9689 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 9690 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 9691 | |
15d143f7 KH |
9692 | for (i = charset->code_space[idx]; |
9693 | i <= charset->code_space[idx + 1]; i++) | |
9694 | { | |
c7c66a95 KH |
9695 | Lisp_Object tmp, tmp2; |
9696 | int dim2; | |
ec6d2bb8 | 9697 | |
c7c66a95 KH |
9698 | tmp = AREF (val, i); |
9699 | if (NILP (tmp)) | |
9700 | tmp = XCAR (tail); | |
9701 | else if (NUMBERP (tmp)) | |
9702 | { | |
9703 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
9704 | if (dim < dim2) | |
c7c66a95 | 9705 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
9706 | else |
9707 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 9708 | } |
15d143f7 | 9709 | else |
c7c66a95 KH |
9710 | { |
9711 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
9712 | { | |
9713 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
9714 | if (dim < dim2) | |
9715 | break; | |
9716 | } | |
9717 | if (NILP (tmp2)) | |
9718 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
9719 | else | |
9720 | { | |
9721 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
9722 | XSETCAR (tmp2, XCAR (tail)); | |
9723 | } | |
9724 | } | |
9725 | ASET (val, i, tmp); | |
15d143f7 | 9726 | } |
df7492f9 KH |
9727 | } |
9728 | ASET (attrs, coding_attr_charset_valids, val); | |
9729 | category = coding_category_charset; | |
9730 | } | |
9731 | else if (EQ (coding_type, Qccl)) | |
9732 | { | |
9733 | Lisp_Object valids; | |
ecec61c1 | 9734 | |
df7492f9 KH |
9735 | if (nargs < coding_arg_ccl_max) |
9736 | goto short_args; | |
ecec61c1 | 9737 | |
df7492f9 KH |
9738 | val = args[coding_arg_ccl_decoder]; |
9739 | CHECK_CCL_PROGRAM (val); | |
9740 | if (VECTORP (val)) | |
9741 | val = Fcopy_sequence (val); | |
9742 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 9743 | |
df7492f9 KH |
9744 | val = args[coding_arg_ccl_encoder]; |
9745 | CHECK_CCL_PROGRAM (val); | |
9746 | if (VECTORP (val)) | |
9747 | val = Fcopy_sequence (val); | |
9748 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 9749 | |
df7492f9 KH |
9750 | val = args[coding_arg_ccl_valids]; |
9751 | valids = Fmake_string (make_number (256), make_number (0)); | |
9752 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
9753 | { | |
8dcbea82 | 9754 | int from, to; |
ecec61c1 | 9755 | |
df7492f9 KH |
9756 | val = Fcar (tail); |
9757 | if (INTEGERP (val)) | |
8dcbea82 KH |
9758 | { |
9759 | from = to = XINT (val); | |
9760 | if (from < 0 || from > 255) | |
9761 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
9762 | } | |
df7492f9 KH |
9763 | else |
9764 | { | |
df7492f9 | 9765 | CHECK_CONS (val); |
8f924df7 KH |
9766 | CHECK_NATNUM_CAR (val); |
9767 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 9768 | from = XINT (XCAR (val)); |
8f924df7 | 9769 | if (from > 255) |
8dcbea82 KH |
9770 | args_out_of_range_3 (XCAR (val), |
9771 | make_number (0), make_number (255)); | |
df7492f9 | 9772 | to = XINT (XCDR (val)); |
8dcbea82 KH |
9773 | if (to < from || to > 255) |
9774 | args_out_of_range_3 (XCDR (val), | |
9775 | XCAR (val), make_number (255)); | |
df7492f9 | 9776 | } |
8dcbea82 | 9777 | for (i = from; i <= to; i++) |
8f924df7 | 9778 | SSET (valids, i, 1); |
df7492f9 KH |
9779 | } |
9780 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 9781 | |
df7492f9 | 9782 | category = coding_category_ccl; |
55ab7be3 | 9783 | } |
df7492f9 | 9784 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 9785 | { |
df7492f9 | 9786 | Lisp_Object bom, endian; |
4ed46869 | 9787 | |
584948ac | 9788 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 9789 | |
df7492f9 KH |
9790 | if (nargs < coding_arg_utf16_max) |
9791 | goto short_args; | |
4ed46869 | 9792 | |
df7492f9 KH |
9793 | bom = args[coding_arg_utf16_bom]; |
9794 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9795 | { | |
9796 | CHECK_CONS (bom); | |
8f924df7 KH |
9797 | val = XCAR (bom); |
9798 | CHECK_CODING_SYSTEM (val); | |
9799 | val = XCDR (bom); | |
9800 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 9801 | } |
a470d443 | 9802 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
9803 | |
9804 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
9805 | CHECK_SYMBOL (endian); |
9806 | if (NILP (endian)) | |
9807 | endian = Qbig; | |
9808 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 9809 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
9810 | ASET (attrs, coding_attr_utf_16_endian, endian); |
9811 | ||
9812 | category = (CONSP (bom) | |
9813 | ? coding_category_utf_16_auto | |
9814 | : NILP (bom) | |
b49a1807 | 9815 | ? (EQ (endian, Qbig) |
df7492f9 KH |
9816 | ? coding_category_utf_16_be_nosig |
9817 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 9818 | : (EQ (endian, Qbig) |
df7492f9 KH |
9819 | ? coding_category_utf_16_be |
9820 | : coding_category_utf_16_le)); | |
9821 | } | |
9822 | else if (EQ (coding_type, Qiso_2022)) | |
9823 | { | |
9824 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 9825 | int i; |
1397dc18 | 9826 | |
df7492f9 KH |
9827 | if (nargs < coding_arg_iso2022_max) |
9828 | goto short_args; | |
9829 | ||
9830 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
9831 | CHECK_VECTOR (initial); | |
9832 | for (i = 0; i < 4; i++) | |
9833 | { | |
9834 | val = Faref (initial, make_number (i)); | |
9835 | if (! NILP (val)) | |
9836 | { | |
584948ac KH |
9837 | struct charset *charset; |
9838 | ||
9839 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
9840 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
9841 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
9842 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9843 | } |
9844 | else | |
9845 | ASET (initial, i, make_number (-1)); | |
9846 | } | |
9847 | ||
9848 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
9849 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
9850 | CHECK_NUMBER_CAR (reg_usage); |
9851 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
9852 | |
9853 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
9854 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 9855 | { |
df7492f9 | 9856 | int id; |
8f924df7 | 9857 | Lisp_Object tmp; |
df7492f9 KH |
9858 | |
9859 | val = Fcar (tail); | |
9860 | CHECK_CONS (val); | |
8f924df7 KH |
9861 | tmp = XCAR (val); |
9862 | CHECK_CHARSET_GET_ID (tmp, id); | |
9863 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
9864 | if (XINT (XCDR (val)) >= 4) |
9865 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 9866 | XSETCAR (val, make_number (id)); |
1397dc18 | 9867 | } |
4ed46869 | 9868 | |
df7492f9 KH |
9869 | flags = args[coding_arg_iso2022_flags]; |
9870 | CHECK_NATNUM (flags); | |
9871 | i = XINT (flags); | |
9872 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
9873 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
9874 | ||
9875 | ASET (attrs, coding_attr_iso_initial, initial); | |
9876 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
9877 | ASET (attrs, coding_attr_iso_request, request); | |
9878 | ASET (attrs, coding_attr_iso_flags, flags); | |
9879 | setup_iso_safe_charsets (attrs); | |
9880 | ||
9881 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
9882 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
9883 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
9884 | ? coding_category_iso_7_else | |
9885 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
9886 | ? coding_category_iso_7 | |
9887 | : coding_category_iso_7_tight); | |
9888 | else | |
9889 | { | |
9890 | int id = XINT (AREF (initial, 1)); | |
9891 | ||
c6fb6e98 | 9892 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
9893 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
9894 | || id < 0) | |
9895 | ? coding_category_iso_8_else | |
9896 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
9897 | ? coding_category_iso_8_1 | |
9898 | : coding_category_iso_8_2); | |
9899 | } | |
0ce7886f KH |
9900 | if (category != coding_category_iso_8_1 |
9901 | && category != coding_category_iso_8_2) | |
9902 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
9903 | } |
9904 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 9905 | { |
df7492f9 KH |
9906 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
9907 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 9908 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 9909 | category = coding_category_emacs_mule; |
c28a9453 | 9910 | } |
df7492f9 | 9911 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 9912 | { |
df7492f9 KH |
9913 | |
9914 | struct charset *charset; | |
9915 | ||
7d64c6ad | 9916 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 9917 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 9918 | error ("There should be three or four charsets"); |
df7492f9 KH |
9919 | |
9920 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9921 | if (CHARSET_DIMENSION (charset) != 1) | |
9922 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9923 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
9924 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
9925 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9926 | |
9927 | charset_list = XCDR (charset_list); | |
9928 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9929 | if (CHARSET_DIMENSION (charset) != 1) | |
9930 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9931 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
9932 | |
9933 | charset_list = XCDR (charset_list); | |
9934 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9935 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
9936 | error ("Dimension of charset %s is not two", |
9937 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9938 | ||
9939 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
9940 | if (! NILP (charset_list)) |
9941 | { | |
9942 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9943 | if (CHARSET_DIMENSION (charset) != 2) | |
9944 | error ("Dimension of charset %s is not two", | |
9945 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9946 | } | |
df7492f9 KH |
9947 | |
9948 | category = coding_category_sjis; | |
9949 | Vsjis_coding_system = name; | |
c28a9453 | 9950 | } |
df7492f9 KH |
9951 | else if (EQ (coding_type, Qbig5)) |
9952 | { | |
9953 | struct charset *charset; | |
4ed46869 | 9954 | |
df7492f9 KH |
9955 | if (XINT (Flength (charset_list)) != 2) |
9956 | error ("There should be just two charsets"); | |
9957 | ||
9958 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9959 | if (CHARSET_DIMENSION (charset) != 1) | |
9960 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9961 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
9962 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
9963 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9964 | |
9965 | charset_list = XCDR (charset_list); | |
9966 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9967 | if (CHARSET_DIMENSION (charset) != 2) | |
9968 | error ("Dimension of charset %s is not two", | |
8f924df7 | 9969 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 9970 | |
df7492f9 KH |
9971 | category = coding_category_big5; |
9972 | Vbig5_coding_system = name; | |
9973 | } | |
9974 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 9975 | { |
584948ac KH |
9976 | category = coding_category_raw_text; |
9977 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 9978 | } |
df7492f9 | 9979 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 9980 | { |
a470d443 KH |
9981 | Lisp_Object bom; |
9982 | ||
584948ac | 9983 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
a470d443 KH |
9984 | |
9985 | if (nargs < coding_arg_utf8_max) | |
9986 | goto short_args; | |
9987 | ||
9988 | bom = args[coding_arg_utf8_bom]; | |
9989 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9990 | { | |
9991 | CHECK_CONS (bom); | |
9992 | val = XCAR (bom); | |
9993 | CHECK_CODING_SYSTEM (val); | |
9994 | val = XCDR (bom); | |
9995 | CHECK_CODING_SYSTEM (val); | |
9996 | } | |
9997 | ASET (attrs, coding_attr_utf_bom, bom); | |
9998 | ||
9999 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
10000 | : NILP (bom) ? coding_category_utf_8_nosig | |
10001 | : coding_category_utf_8_sig); | |
4ed46869 | 10002 | } |
df7492f9 KH |
10003 | else if (EQ (coding_type, Qundecided)) |
10004 | category = coding_category_undecided; | |
4ed46869 | 10005 | else |
df7492f9 | 10006 | error ("Invalid coding system type: %s", |
8f924df7 | 10007 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 10008 | |
df7492f9 | 10009 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
10010 | CODING_ATTR_PLIST (attrs) |
10011 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
10012 | CODING_ATTR_PLIST (attrs))); | |
35befdaa | 10013 | CODING_ATTR_PLIST (attrs) |
3ed051d4 | 10014 | = Fcons (QCascii_compatible_p, |
35befdaa KH |
10015 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), |
10016 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 10017 | |
df7492f9 KH |
10018 | eol_type = args[coding_arg_eol_type]; |
10019 | if (! NILP (eol_type) | |
10020 | && ! EQ (eol_type, Qunix) | |
10021 | && ! EQ (eol_type, Qdos) | |
10022 | && ! EQ (eol_type, Qmac)) | |
10023 | error ("Invalid eol-type"); | |
4ed46869 | 10024 | |
df7492f9 | 10025 | aliases = Fcons (name, Qnil); |
4ed46869 | 10026 | |
df7492f9 KH |
10027 | if (NILP (eol_type)) |
10028 | { | |
10029 | eol_type = make_subsidiaries (name); | |
10030 | for (i = 0; i < 3; i++) | |
1397dc18 | 10031 | { |
df7492f9 KH |
10032 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
10033 | ||
10034 | this_name = AREF (eol_type, i); | |
10035 | this_aliases = Fcons (this_name, Qnil); | |
10036 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
10037 | this_spec = Fmake_vector (make_number (3), attrs); | |
10038 | ASET (this_spec, 1, this_aliases); | |
10039 | ASET (this_spec, 2, this_eol_type); | |
10040 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
10041 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
10042 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
10043 | if (NILP (val)) | |
10044 | Vcoding_system_alist | |
10045 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
10046 | Vcoding_system_alist); | |
1397dc18 | 10047 | } |
d46c5b12 | 10048 | } |
4ed46869 | 10049 | |
df7492f9 KH |
10050 | spec_vec = Fmake_vector (make_number (3), attrs); |
10051 | ASET (spec_vec, 1, aliases); | |
10052 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 10053 | |
df7492f9 KH |
10054 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
10055 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
10056 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
10057 | if (NILP (val)) | |
10058 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
10059 | Vcoding_system_alist); | |
48b0f3ae | 10060 | |
df7492f9 KH |
10061 | { |
10062 | int id = coding_categories[category].id; | |
48b0f3ae | 10063 | |
df7492f9 KH |
10064 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
10065 | setup_coding_system (name, &coding_categories[category]); | |
10066 | } | |
48b0f3ae | 10067 | |
d46c5b12 | 10068 | return Qnil; |
48b0f3ae | 10069 | |
df7492f9 KH |
10070 | short_args: |
10071 | return Fsignal (Qwrong_number_of_arguments, | |
10072 | Fcons (intern ("define-coding-system-internal"), | |
10073 | make_number (nargs))); | |
d46c5b12 | 10074 | } |
4ed46869 | 10075 | |
d6925f38 | 10076 | |
a6f87d34 KH |
10077 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
10078 | 3, 3, 0, | |
10079 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
5842a27b | 10080 | (Lisp_Object coding_system, Lisp_Object prop, Lisp_Object val) |
a6f87d34 | 10081 | { |
3dbe7859 | 10082 | Lisp_Object spec, attrs; |
a6f87d34 KH |
10083 | |
10084 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10085 | attrs = AREF (spec, 0); | |
10086 | if (EQ (prop, QCmnemonic)) | |
10087 | { | |
10088 | if (! STRINGP (val)) | |
10089 | CHECK_CHARACTER (val); | |
10090 | CODING_ATTR_MNEMONIC (attrs) = val; | |
10091 | } | |
2133e2d1 | 10092 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
10093 | { |
10094 | if (NILP (val)) | |
10095 | val = make_number (' '); | |
10096 | else | |
10097 | CHECK_CHARACTER (val); | |
10098 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
10099 | } | |
10100 | else if (EQ (prop, QCdecode_translation_table)) | |
10101 | { | |
10102 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10103 | CHECK_SYMBOL (val); | |
10104 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
10105 | } | |
10106 | else if (EQ (prop, QCencode_translation_table)) | |
10107 | { | |
10108 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10109 | CHECK_SYMBOL (val); | |
10110 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
10111 | } | |
10112 | else if (EQ (prop, QCpost_read_conversion)) | |
10113 | { | |
10114 | CHECK_SYMBOL (val); | |
10115 | CODING_ATTR_POST_READ (attrs) = val; | |
10116 | } | |
10117 | else if (EQ (prop, QCpre_write_conversion)) | |
10118 | { | |
10119 | CHECK_SYMBOL (val); | |
10120 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
10121 | } | |
35befdaa KH |
10122 | else if (EQ (prop, QCascii_compatible_p)) |
10123 | { | |
10124 | CODING_ATTR_ASCII_COMPAT (attrs) = val; | |
10125 | } | |
a6f87d34 KH |
10126 | |
10127 | CODING_ATTR_PLIST (attrs) | |
10128 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
10129 | return val; | |
10130 | } | |
10131 | ||
10132 | ||
df7492f9 KH |
10133 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
10134 | Sdefine_coding_system_alias, 2, 2, 0, | |
10135 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
5842a27b | 10136 | (Lisp_Object alias, Lisp_Object coding_system) |
66cfb530 | 10137 | { |
583f71ca | 10138 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 10139 | |
df7492f9 KH |
10140 | CHECK_SYMBOL (alias); |
10141 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10142 | aliases = AREF (spec, 1); | |
d4a1d553 | 10143 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
10144 | element is a base coding system. Append ALIAS at the tail of the |
10145 | list. */ | |
df7492f9 KH |
10146 | while (!NILP (XCDR (aliases))) |
10147 | aliases = XCDR (aliases); | |
8f924df7 | 10148 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 10149 | |
df7492f9 KH |
10150 | eol_type = AREF (spec, 2); |
10151 | if (VECTORP (eol_type)) | |
4ed46869 | 10152 | { |
df7492f9 KH |
10153 | Lisp_Object subsidiaries; |
10154 | int i; | |
4ed46869 | 10155 | |
df7492f9 KH |
10156 | subsidiaries = make_subsidiaries (alias); |
10157 | for (i = 0; i < 3; i++) | |
10158 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
10159 | AREF (eol_type, i)); | |
4ed46869 | 10160 | } |
df7492f9 KH |
10161 | |
10162 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 10163 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
10164 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
10165 | if (NILP (val)) | |
10166 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
10167 | Vcoding_system_alist); | |
66cfb530 | 10168 | |
4ed46869 KH |
10169 | return Qnil; |
10170 | } | |
10171 | ||
df7492f9 KH |
10172 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
10173 | 1, 1, 0, | |
10174 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 10175 | Any alias or subsidiary coding system is not a base coding system. */) |
5842a27b | 10176 | (Lisp_Object coding_system) |
d46c5b12 | 10177 | { |
df7492f9 | 10178 | Lisp_Object spec, attrs; |
d46c5b12 | 10179 | |
df7492f9 KH |
10180 | if (NILP (coding_system)) |
10181 | return (Qno_conversion); | |
10182 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10183 | attrs = AREF (spec, 0); | |
10184 | return CODING_ATTR_BASE_NAME (attrs); | |
10185 | } | |
1397dc18 | 10186 | |
df7492f9 KH |
10187 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
10188 | 1, 1, 0, | |
10189 | doc: "Return the property list of CODING-SYSTEM.") | |
5842a27b | 10190 | (Lisp_Object coding_system) |
df7492f9 KH |
10191 | { |
10192 | Lisp_Object spec, attrs; | |
1397dc18 | 10193 | |
df7492f9 KH |
10194 | if (NILP (coding_system)) |
10195 | coding_system = Qno_conversion; | |
10196 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10197 | attrs = AREF (spec, 0); | |
10198 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
10199 | } |
10200 | ||
df7492f9 KH |
10201 | |
10202 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
10203 | 1, 1, 0, | |
da7db224 | 10204 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
5842a27b | 10205 | (Lisp_Object coding_system) |
66cfb530 | 10206 | { |
df7492f9 | 10207 | Lisp_Object spec; |
84d60297 | 10208 | |
df7492f9 KH |
10209 | if (NILP (coding_system)) |
10210 | coding_system = Qno_conversion; | |
10211 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 10212 | return AREF (spec, 1); |
df7492f9 | 10213 | } |
66cfb530 | 10214 | |
df7492f9 KH |
10215 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
10216 | Scoding_system_eol_type, 1, 1, 0, | |
10217 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 10218 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 10219 | |
df7492f9 KH |
10220 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
10221 | and CR respectively. | |
66cfb530 | 10222 | |
df7492f9 KH |
10223 | A vector value indicates that a format of end-of-line should be |
10224 | detected automatically. Nth element of the vector is the subsidiary | |
10225 | coding system whose eol-type is N. */) | |
5842a27b | 10226 | (Lisp_Object coding_system) |
6b89e3aa | 10227 | { |
df7492f9 KH |
10228 | Lisp_Object spec, eol_type; |
10229 | int n; | |
6b89e3aa | 10230 | |
df7492f9 KH |
10231 | if (NILP (coding_system)) |
10232 | coding_system = Qno_conversion; | |
10233 | if (! CODING_SYSTEM_P (coding_system)) | |
10234 | return Qnil; | |
10235 | spec = CODING_SYSTEM_SPEC (coding_system); | |
10236 | eol_type = AREF (spec, 2); | |
10237 | if (VECTORP (eol_type)) | |
10238 | return Fcopy_sequence (eol_type); | |
10239 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
10240 | return make_number (n); | |
6b89e3aa KH |
10241 | } |
10242 | ||
4ed46869 KH |
10243 | #endif /* emacs */ |
10244 | ||
10245 | \f | |
1397dc18 | 10246 | /*** 9. Post-amble ***/ |
4ed46869 | 10247 | |
dfcf069d | 10248 | void |
971de7fb | 10249 | init_coding_once (void) |
4ed46869 KH |
10250 | { |
10251 | int i; | |
10252 | ||
df7492f9 KH |
10253 | for (i = 0; i < coding_category_max; i++) |
10254 | { | |
10255 | coding_categories[i].id = -1; | |
10256 | coding_priorities[i] = i; | |
10257 | } | |
4ed46869 KH |
10258 | |
10259 | /* ISO2022 specific initialize routine. */ | |
10260 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 10261 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
10262 | for (i = 0x21; i < 0x7F; i++) |
10263 | iso_code_class[i] = ISO_graphic_plane_0; | |
10264 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 10265 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
10266 | for (i = 0xA1; i < 0xFF; i++) |
10267 | iso_code_class[i] = ISO_graphic_plane_1; | |
10268 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
10269 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
10270 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
10271 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
10272 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
10273 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
10274 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
10275 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
10276 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
10277 | ||
df7492f9 KH |
10278 | for (i = 0; i < 256; i++) |
10279 | { | |
10280 | emacs_mule_bytes[i] = 1; | |
10281 | } | |
7c78e542 KH |
10282 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
10283 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
10284 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
10285 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
10286 | } |
10287 | ||
10288 | #ifdef emacs | |
10289 | ||
dfcf069d | 10290 | void |
971de7fb | 10291 | syms_of_coding (void) |
e0e989f6 | 10292 | { |
df7492f9 | 10293 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
10294 | { |
10295 | Lisp_Object args[2]; | |
10296 | args[0] = QCtest; | |
10297 | args[1] = Qeq; | |
10298 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
10299 | } | |
df7492f9 KH |
10300 | |
10301 | staticpro (&Vsjis_coding_system); | |
10302 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 10303 | |
df7492f9 KH |
10304 | staticpro (&Vbig5_coding_system); |
10305 | Vbig5_coding_system = Qnil; | |
10306 | ||
24a73b0a KH |
10307 | staticpro (&Vcode_conversion_reused_workbuf); |
10308 | Vcode_conversion_reused_workbuf = Qnil; | |
10309 | ||
10310 | staticpro (&Vcode_conversion_workbuf_name); | |
d67b4f80 | 10311 | Vcode_conversion_workbuf_name = make_pure_c_string (" *code-conversion-work*"); |
e0e989f6 | 10312 | |
24a73b0a | 10313 | reused_workbuf_in_use = 0; |
df7492f9 KH |
10314 | |
10315 | DEFSYM (Qcharset, "charset"); | |
10316 | DEFSYM (Qtarget_idx, "target-idx"); | |
10317 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
10318 | Fset (Qcoding_system_history, Qnil); |
10319 | ||
9ce27fde | 10320 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 10321 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 10322 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
10323 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
10324 | ||
df7492f9 | 10325 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 10326 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
10327 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
10328 | ||
df7492f9 | 10329 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 10330 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10331 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
10332 | ||
df7492f9 | 10333 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 10334 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10335 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
10336 | ||
df7492f9 | 10337 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 10338 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
10339 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
10340 | ||
df7492f9 KH |
10341 | DEFSYM (Qcoding_system, "coding-system"); |
10342 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 10343 | |
df7492f9 KH |
10344 | DEFSYM (Qeol_type, "eol-type"); |
10345 | DEFSYM (Qunix, "unix"); | |
10346 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 10347 | |
df7492f9 KH |
10348 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
10349 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
10350 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
10351 | DEFSYM (Qdefault_char, "default-char"); | |
10352 | DEFSYM (Qundecided, "undecided"); | |
10353 | DEFSYM (Qno_conversion, "no-conversion"); | |
10354 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 10355 | |
df7492f9 | 10356 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 10357 | |
df7492f9 | 10358 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 10359 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 10360 | |
df7492f9 | 10361 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
10362 | DEFSYM (Qbig, "big"); |
10363 | DEFSYM (Qlittle, "little"); | |
27901516 | 10364 | |
df7492f9 KH |
10365 | DEFSYM (Qshift_jis, "shift-jis"); |
10366 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 10367 | |
df7492f9 | 10368 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 10369 | |
df7492f9 | 10370 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 | 10371 | Fput (Qcoding_system_error, Qerror_conditions, |
d67b4f80 | 10372 | pure_cons (Qcoding_system_error, pure_cons (Qerror, Qnil))); |
4ed46869 | 10373 | Fput (Qcoding_system_error, Qerror_message, |
d67b4f80 | 10374 | make_pure_c_string ("Invalid coding system")); |
4ed46869 | 10375 | |
05e6f5dc KH |
10376 | /* Intern this now in case it isn't already done. |
10377 | Setting this variable twice is harmless. | |
10378 | But don't staticpro it here--that is done in alloc.c. */ | |
d67b4f80 | 10379 | Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots"); |
70c22245 | 10380 | |
df7492f9 | 10381 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 10382 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
10383 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
10384 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10385 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10386 | |
df7492f9 | 10387 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10388 | |
df7492f9 | 10389 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10390 | |
01378f49 | 10391 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10392 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10393 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10394 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10395 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10396 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10397 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10398 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10399 | |
df7492f9 KH |
10400 | Vcoding_category_table |
10401 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10402 | staticpro (&Vcoding_category_table); | |
10403 | /* Followings are target of code detection. */ | |
10404 | ASET (Vcoding_category_table, coding_category_iso_7, | |
d67b4f80 | 10405 | intern_c_string ("coding-category-iso-7")); |
df7492f9 | 10406 | ASET (Vcoding_category_table, coding_category_iso_7_tight, |
d67b4f80 | 10407 | intern_c_string ("coding-category-iso-7-tight")); |
df7492f9 | 10408 | ASET (Vcoding_category_table, coding_category_iso_8_1, |
d67b4f80 | 10409 | intern_c_string ("coding-category-iso-8-1")); |
df7492f9 | 10410 | ASET (Vcoding_category_table, coding_category_iso_8_2, |
d67b4f80 | 10411 | intern_c_string ("coding-category-iso-8-2")); |
df7492f9 | 10412 | ASET (Vcoding_category_table, coding_category_iso_7_else, |
d67b4f80 | 10413 | intern_c_string ("coding-category-iso-7-else")); |
df7492f9 | 10414 | ASET (Vcoding_category_table, coding_category_iso_8_else, |
d67b4f80 | 10415 | intern_c_string ("coding-category-iso-8-else")); |
a470d443 | 10416 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
d67b4f80 | 10417 | intern_c_string ("coding-category-utf-8-auto")); |
a470d443 | 10418 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, |
d67b4f80 | 10419 | intern_c_string ("coding-category-utf-8")); |
a470d443 | 10420 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
d67b4f80 | 10421 | intern_c_string ("coding-category-utf-8-sig")); |
df7492f9 | 10422 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
d67b4f80 | 10423 | intern_c_string ("coding-category-utf-16-be")); |
ff563fce | 10424 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
d67b4f80 | 10425 | intern_c_string ("coding-category-utf-16-auto")); |
df7492f9 | 10426 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
d67b4f80 | 10427 | intern_c_string ("coding-category-utf-16-le")); |
df7492f9 | 10428 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, |
d67b4f80 | 10429 | intern_c_string ("coding-category-utf-16-be-nosig")); |
df7492f9 | 10430 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, |
d67b4f80 | 10431 | intern_c_string ("coding-category-utf-16-le-nosig")); |
df7492f9 | 10432 | ASET (Vcoding_category_table, coding_category_charset, |
d67b4f80 | 10433 | intern_c_string ("coding-category-charset")); |
df7492f9 | 10434 | ASET (Vcoding_category_table, coding_category_sjis, |
d67b4f80 | 10435 | intern_c_string ("coding-category-sjis")); |
df7492f9 | 10436 | ASET (Vcoding_category_table, coding_category_big5, |
d67b4f80 | 10437 | intern_c_string ("coding-category-big5")); |
df7492f9 | 10438 | ASET (Vcoding_category_table, coding_category_ccl, |
d67b4f80 | 10439 | intern_c_string ("coding-category-ccl")); |
df7492f9 | 10440 | ASET (Vcoding_category_table, coding_category_emacs_mule, |
d67b4f80 | 10441 | intern_c_string ("coding-category-emacs-mule")); |
df7492f9 KH |
10442 | /* Followings are NOT target of code detection. */ |
10443 | ASET (Vcoding_category_table, coding_category_raw_text, | |
d67b4f80 | 10444 | intern_c_string ("coding-category-raw-text")); |
df7492f9 | 10445 | ASET (Vcoding_category_table, coding_category_undecided, |
d67b4f80 | 10446 | intern_c_string ("coding-category-undecided")); |
ecf488bc | 10447 | |
065e3595 KH |
10448 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
10449 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
10450 | DEFSYM (Qinvalid_source, "invalid-source"); | |
10451 | DEFSYM (Qinterrupted, "interrupted"); | |
10452 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 10453 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10454 | |
4ed46869 KH |
10455 | defsubr (&Scoding_system_p); |
10456 | defsubr (&Sread_coding_system); | |
10457 | defsubr (&Sread_non_nil_coding_system); | |
10458 | defsubr (&Scheck_coding_system); | |
10459 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10460 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10461 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10462 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10463 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10464 | defsubr (&Sdecode_coding_region); |
10465 | defsubr (&Sencode_coding_region); | |
10466 | defsubr (&Sdecode_coding_string); | |
10467 | defsubr (&Sencode_coding_string); | |
10468 | defsubr (&Sdecode_sjis_char); | |
10469 | defsubr (&Sencode_sjis_char); | |
10470 | defsubr (&Sdecode_big5_char); | |
10471 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10472 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10473 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10474 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10475 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10476 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10477 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10478 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10479 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10480 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10481 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10482 | defsubr (&Scoding_system_base); |
10483 | defsubr (&Scoding_system_plist); | |
10484 | defsubr (&Scoding_system_aliases); | |
10485 | defsubr (&Scoding_system_eol_type); | |
10486 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10487 | |
4608c386 | 10488 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
10489 | doc: /* List of coding systems. |
10490 | ||
10491 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10492 | updated by the functions `define-coding-system' and |
48b0f3ae | 10493 | `define-coding-system-alias'. */); |
4608c386 KH |
10494 | Vcoding_system_list = Qnil; |
10495 | ||
10496 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
10497 | doc: /* Alist of coding system names. |
10498 | Each element is one element list of coding system name. | |
446dcd75 | 10499 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10500 | |
10501 | Do not alter the value of this variable manually. This variable should be | |
10502 | updated by the functions `make-coding-system' and | |
10503 | `define-coding-system-alias'. */); | |
4608c386 KH |
10504 | Vcoding_system_alist = Qnil; |
10505 | ||
4ed46869 | 10506 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
10507 | doc: /* List of coding-categories (symbols) ordered by priority. |
10508 | ||
10509 | On detecting a coding system, Emacs tries code detection algorithms | |
10510 | associated with each coding-category one by one in this order. When | |
10511 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10512 | system bound to the corresponding coding-category is selected. |
10513 | ||
42205607 | 10514 | Don't modify this variable directly, but use `set-coding-priority'. */); |
4ed46869 KH |
10515 | { |
10516 | int i; | |
10517 | ||
10518 | Vcoding_category_list = Qnil; | |
df7492f9 | 10519 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10520 | Vcoding_category_list |
d46c5b12 KH |
10521 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
10522 | Vcoding_category_list); | |
4ed46869 KH |
10523 | } |
10524 | ||
10525 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
10526 | doc: /* Specify the coding system for read operations. |
10527 | It is useful to bind this variable with `let', but do not set it globally. | |
10528 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10529 | If not, an appropriate element is used from one of the coding system alists. |
10530 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10531 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10532 | Vcoding_system_for_read = Qnil; |
10533 | ||
10534 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
10535 | doc: /* Specify the coding system for write operations. |
10536 | Programs bind this variable with `let', but you should not set it globally. | |
10537 | If the value is a coding system, it is used for encoding of output, | |
10538 | when writing it to a file and when sending it to a file or subprocess. | |
10539 | ||
10540 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10541 | is used from one of the coding system alists. |
10542 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10543 | `process-coding-system-alist', and `network-coding-system-alist'. |
10544 | For output to files, if the above procedure does not specify a coding system, | |
10545 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10546 | Vcoding_system_for_write = Qnil; |
10547 | ||
10548 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
10549 | doc: /* |
10550 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10551 | Vlast_coding_system_used = Qnil; |
10552 | ||
065e3595 KH |
10553 | DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error, |
10554 | doc: /* | |
10555 | Error status of the last code conversion. | |
10556 | ||
10557 | When an error was detected in the last code conversion, this variable | |
10558 | is set to one of the following symbols. | |
10559 | `insufficient-source' | |
10560 | `inconsistent-eol' | |
10561 | `invalid-source' | |
10562 | `interrupted' | |
10563 | `insufficient-memory' | |
10564 | When no error was detected, the value doesn't change. So, to check | |
10565 | the error status of a code conversion by this variable, you must | |
10566 | explicitly set this variable to nil before performing code | |
10567 | conversion. */); | |
10568 | Vlast_code_conversion_error = Qnil; | |
10569 | ||
9ce27fde | 10570 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
10571 | doc: /* |
10572 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10573 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10574 | such conversion. */); | |
9ce27fde KH |
10575 | inhibit_eol_conversion = 0; |
10576 | ||
ed29121d | 10577 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
10578 | doc: /* |
10579 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10580 | Bind it to t if the process output is to be treated as if it were a file |
10581 | read from some filesystem. */); | |
ed29121d EZ |
10582 | inherit_process_coding_system = 0; |
10583 | ||
02ba4723 | 10584 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
10585 | doc: /* |
10586 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10587 | The format is ((PATTERN . VAL) ...), |
10588 | where PATTERN is a regular expression matching a file name, | |
10589 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10590 | If VAL is a coding system, it is used for both decoding and encoding | |
10591 | the file contents. | |
10592 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10593 | and the cdr part is used for encoding. | |
10594 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10595 | or a cons of coding systems which are used as above. The function is |
10596 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10597 | `find-operation-coding-system' was called. If the function can't decide |
10598 | a coding system, it can return `undecided' so that the normal | |
10599 | code-detection is performed. | |
48b0f3ae PJ |
10600 | |
10601 | See also the function `find-operation-coding-system' | |
10602 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10603 | Vfile_coding_system_alist = Qnil; |
10604 | ||
10605 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
10606 | doc: /* |
10607 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
10608 | The format is ((PATTERN . VAL) ...), |
10609 | where PATTERN is a regular expression matching a program name, | |
10610 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10611 | If VAL is a coding system, it is used for both decoding what received | |
10612 | from the program and encoding what sent to the program. | |
10613 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10614 | and the cdr part is used for encoding. | |
10615 | If VAL is a function symbol, the function must return a coding system | |
10616 | or a cons of coding systems which are used as above. | |
10617 | ||
10618 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
10619 | Vprocess_coding_system_alist = Qnil; |
10620 | ||
10621 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
10622 | doc: /* |
10623 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
10624 | The format is ((PATTERN . VAL) ...), |
10625 | where PATTERN is a regular expression matching a network service name | |
10626 | or is a port number to connect to, | |
10627 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10628 | If VAL is a coding system, it is used for both decoding what received | |
10629 | from the network stream and encoding what sent to the network stream. | |
10630 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10631 | and the cdr part is used for encoding. | |
10632 | If VAL is a function symbol, the function must return a coding system | |
10633 | or a cons of coding systems which are used as above. | |
10634 | ||
10635 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 10636 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 10637 | |
68c45bf0 | 10638 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
10639 | doc: /* Coding system to use with system messages. |
10640 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
10641 | Vlocale_coding_system = Qnil; |
10642 | ||
005f0d35 | 10643 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 10644 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
10645 | doc: /* |
10646 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
d67b4f80 | 10647 | eol_mnemonic_unix = make_pure_c_string (":"); |
4ed46869 | 10648 | |
7722baf9 | 10649 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
10650 | doc: /* |
10651 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
d67b4f80 | 10652 | eol_mnemonic_dos = make_pure_c_string ("\\"); |
4ed46869 | 10653 | |
7722baf9 | 10654 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
10655 | doc: /* |
10656 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
d67b4f80 | 10657 | eol_mnemonic_mac = make_pure_c_string ("/"); |
4ed46869 | 10658 | |
7722baf9 | 10659 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
10660 | doc: /* |
10661 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
d67b4f80 | 10662 | eol_mnemonic_undecided = make_pure_c_string (":"); |
4ed46869 | 10663 | |
84fbb8a0 | 10664 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
10665 | doc: /* |
10666 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 10667 | Venable_character_translation = Qt; |
bdd9fb48 | 10668 | |
f967223b | 10669 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
10670 | &Vstandard_translation_table_for_decode, |
10671 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 10672 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 10673 | |
f967223b | 10674 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
10675 | &Vstandard_translation_table_for_encode, |
10676 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 10677 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 10678 | |
df7492f9 | 10679 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
10680 | doc: /* Alist of charsets vs revision numbers. |
10681 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
10682 | designate it with the escape sequence identifying revision (cdr part |
10683 | of the element). */); | |
10684 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
10685 | |
10686 | DEFVAR_LISP ("default-process-coding-system", | |
10687 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
10688 | doc: /* Cons of coding systems used for process I/O by default. |
10689 | The car part is used for decoding a process output, | |
10690 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 10691 | Vdefault_process_coding_system = Qnil; |
c4825358 | 10692 | |
3f003981 | 10693 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
10694 | doc: /* |
10695 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
10696 | This is a vector of length 256. |
10697 | If Nth element is non-nil, the existence of code N in a file | |
10698 | \(or output of subprocess) doesn't prevent it to be detected as | |
10699 | a coding system of ISO 2022 variant which has a flag | |
10700 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
10701 | or reading output of a subprocess. | |
446dcd75 | 10702 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 10703 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
10704 | |
10705 | DEFVAR_LISP ("select-safe-coding-system-function", | |
10706 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
10707 | doc: /* |
10708 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
10709 | |
10710 | If set, this function is called to force a user to select a proper | |
10711 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
10712 | coding system used in each operation can't encode the text. The |
10713 | function should take care that the buffer is not modified while | |
10714 | the coding system is being selected. | |
48b0f3ae PJ |
10715 | |
10716 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
10717 | Vselect_safe_coding_system_function = Qnil; |
10718 | ||
5d5bf4d8 KH |
10719 | DEFVAR_BOOL ("coding-system-require-warning", |
10720 | &coding_system_require_warning, | |
10721 | doc: /* Internal use only. | |
6b89e3aa KH |
10722 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
10723 | called even if `coding-system-for-write' is non-nil. The command | |
10724 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
10725 | coding_system_require_warning = 0; |
10726 | ||
10727 | ||
22ab2303 | 10728 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 10729 | &inhibit_iso_escape_detection, |
df7492f9 | 10730 | doc: /* |
97b1b294 | 10731 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 10732 | |
97b1b294 EZ |
10733 | When Emacs reads text, it tries to detect how the text is encoded. |
10734 | This code detection is sensitive to escape sequences. If Emacs sees | |
10735 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
10736 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
10737 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
10738 | |
10739 | However, there may be a case that you want to read escape sequences in | |
10740 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
10741 | Then the code detection will ignore any escape sequences, and no text is |
10742 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
10743 | escape sequences become visible in a buffer. |
10744 | ||
10745 | The default value is nil, and it is strongly recommended not to change | |
10746 | it. That is because many Emacs Lisp source files that contain | |
10747 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
10748 | in Emacs's distribution, and they won't be decoded correctly on | |
10749 | reading if you suppress escape sequence detection. | |
10750 | ||
10751 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 10752 | to explicitly specify some coding system that doesn't use ISO-2022 |
48b0f3ae | 10753 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 10754 | inhibit_iso_escape_detection = 0; |
002fdb44 | 10755 | |
97b1b294 EZ |
10756 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
10757 | &inhibit_null_byte_detection, | |
10758 | doc: /* If non-nil, Emacs ignores null bytes on code detection. | |
10759 | By default, Emacs treats it as binary data, and does not attempt to | |
10760 | decode it. The effect is as if you specified `no-conversion' for | |
10761 | reading that text. | |
10762 | ||
10763 | Set this to non-nil when a regular text happens to include null bytes. | |
10764 | Examples are Index nodes of Info files and null-byte delimited output | |
10765 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
10766 | decode text as usual. */); | |
10767 | inhibit_null_byte_detection = 0; | |
10768 | ||
002fdb44 | 10769 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, |
15c8f9d1 | 10770 | doc: /* Char table for translating self-inserting characters. |
446dcd75 | 10771 | This is applied to the result of input methods, not their input. |
8434d0b8 EZ |
10772 | See also `keyboard-translate-table'. |
10773 | ||
10774 | Use of this variable for character code unification was rendered | |
10775 | obsolete in Emacs 23.1 and later, since Unicode is now the basis of | |
10776 | internal character representation. */); | |
002fdb44 | 10777 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 10778 | |
2c78b7e1 KH |
10779 | { |
10780 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 10781 | Lisp_Object plist[16]; |
2c78b7e1 KH |
10782 | int i; |
10783 | ||
10784 | for (i = 0; i < coding_arg_max; i++) | |
10785 | args[i] = Qnil; | |
10786 | ||
d67b4f80 | 10787 | plist[0] = intern_c_string (":name"); |
2c78b7e1 | 10788 | plist[1] = args[coding_arg_name] = Qno_conversion; |
d67b4f80 | 10789 | plist[2] = intern_c_string (":mnemonic"); |
2c78b7e1 | 10790 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); |
d67b4f80 | 10791 | plist[4] = intern_c_string (":coding-type"); |
2c78b7e1 | 10792 | plist[5] = args[coding_arg_coding_type] = Qraw_text; |
d67b4f80 | 10793 | plist[6] = intern_c_string (":ascii-compatible-p"); |
2c78b7e1 | 10794 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; |
d67b4f80 | 10795 | plist[8] = intern_c_string (":default-char"); |
2c78b7e1 | 10796 | plist[9] = args[coding_arg_default_char] = make_number (0); |
d67b4f80 | 10797 | plist[10] = intern_c_string (":for-unibyte"); |
8f924df7 | 10798 | plist[11] = args[coding_arg_for_unibyte] = Qt; |
d67b4f80 DN |
10799 | plist[12] = intern_c_string (":docstring"); |
10800 | plist[13] = make_pure_c_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
10801 | \n\ |
10802 | When you visit a file with this coding, the file is read into a\n\ | |
10803 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
10804 | character."); | |
d67b4f80 | 10805 | plist[14] = intern_c_string (":eol-type"); |
8f924df7 KH |
10806 | plist[15] = args[coding_arg_eol_type] = Qunix; |
10807 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 10808 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
10809 | |
10810 | plist[1] = args[coding_arg_name] = Qundecided; | |
10811 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
10812 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
10813 | /* This is already set. | |
35befdaa | 10814 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
d67b4f80 | 10815 | plist[8] = intern_c_string (":charset-list"); |
ae6f73fa KH |
10816 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); |
10817 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
d67b4f80 | 10818 | plist[13] = make_pure_c_string ("No conversion on encoding, automatic conversion on decoding."); |
ae6f73fa KH |
10819 | plist[15] = args[coding_arg_eol_type] = Qnil; |
10820 | args[coding_arg_plist] = Flist (16, plist); | |
10821 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
10822 | } |
10823 | ||
2c78b7e1 | 10824 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
10825 | |
10826 | { | |
10827 | int i; | |
10828 | ||
10829 | for (i = 0; i < coding_category_max; i++) | |
10830 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
10831 | } | |
1a4990fb | 10832 | #if defined (DOS_NT) |
fcbcfb64 KH |
10833 | system_eol_type = Qdos; |
10834 | #else | |
10835 | system_eol_type = Qunix; | |
10836 | #endif | |
10837 | staticpro (&system_eol_type); | |
4ed46869 KH |
10838 | } |
10839 | ||
68c45bf0 | 10840 | char * |
971de7fb | 10841 | emacs_strerror (int error_number) |
68c45bf0 PE |
10842 | { |
10843 | char *str; | |
10844 | ||
ca9c0567 | 10845 | synchronize_system_messages_locale (); |
68c45bf0 PE |
10846 | str = strerror (error_number); |
10847 | ||
10848 | if (! NILP (Vlocale_coding_system)) | |
10849 | { | |
10850 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
10851 | Vlocale_coding_system, | |
10852 | 0); | |
d5db4077 | 10853 | str = (char *) SDATA (dec); |
68c45bf0 PE |
10854 | } |
10855 | ||
10856 | return str; | |
10857 | } | |
10858 | ||
4ed46869 | 10859 | #endif /* emacs */ |
9ffd559c KH |
10860 | |
10861 | /* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d | |
10862 | (do not change this comment) */ |