1 |
/* Coding system handler (conversion, detection, and etc). |
2 |
Copyright (C) 1995,97,1998,2002,2003 Electrotechnical Laboratory, JAPAN. |
3 |
Licensed to the Free Software Foundation. |
4 |
Copyright (C) 2001,2002,2003 Free Software Foundation, Inc. |
5 |
|
6 |
This file is part of GNU Emacs. |
7 |
|
8 |
GNU Emacs is free software; you can redistribute it and/or modify |
9 |
it under the terms of the GNU General Public License as published by |
10 |
the Free Software Foundation; either version 2, or (at your option) |
11 |
any later version. |
12 |
|
13 |
GNU Emacs is distributed in the hope that it will be useful, |
14 |
but WITHOUT ANY WARRANTY; without even the implied warranty of |
15 |
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
16 |
GNU General Public License for more details. |
17 |
|
18 |
You should have received a copy of the GNU General Public License |
19 |
along with GNU Emacs; see the file COPYING. If not, write to |
20 |
the Free Software Foundation, Inc., 59 Temple Place - Suite 330, |
21 |
Boston, MA 02111-1307, USA. */ |
22 |
|
23 |
/*** TABLE OF CONTENTS *** |
24 |
|
25 |
0. General comments |
26 |
1. Preamble |
27 |
2. Emacs' internal format (emacs-mule) handlers |
28 |
3. ISO2022 handlers |
29 |
4. Shift-JIS and BIG5 handlers |
30 |
5. CCL handlers |
31 |
6. End-of-line handlers |
32 |
7. C library functions |
33 |
8. Emacs Lisp library functions |
34 |
9. Post-amble |
35 |
|
36 |
*/ |
37 |
|
38 |
/*** 0. General comments ***/ |
39 |
|
40 |
|
41 |
/*** GENERAL NOTE on CODING SYSTEMS *** |
42 |
|
43 |
A coding system is an encoding mechanism for one or more character |
44 |
sets. Here's a list of coding systems which Emacs can handle. When |
45 |
we say "decode", it means converting some other coding system to |
46 |
Emacs' internal format (emacs-mule), and when we say "encode", |
47 |
it means converting the coding system emacs-mule to some other |
48 |
coding system. |
49 |
|
50 |
0. Emacs' internal format (emacs-mule) |
51 |
|
52 |
Emacs itself holds a multi-lingual character in buffers and strings |
53 |
in a special format. Details are described in section 2. |
54 |
|
55 |
1. ISO2022 |
56 |
|
57 |
The most famous coding system for multiple character sets. X's |
58 |
Compound Text, various EUCs (Extended Unix Code), and coding |
59 |
systems used in Internet communication such as ISO-2022-JP are |
60 |
all variants of ISO2022. Details are described in section 3. |
61 |
|
62 |
2. SJIS (or Shift-JIS or MS-Kanji-Code) |
63 |
|
64 |
A coding system to encode character sets: ASCII, JISX0201, and |
65 |
JISX0208. Widely used for PC's in Japan. Details are described in |
66 |
section 4. |
67 |
|
68 |
3. BIG5 |
69 |
|
70 |
A coding system to encode the character sets ASCII and Big5. Widely |
71 |
used for Chinese (mainly in Taiwan and Hong Kong). Details are |
72 |
described in section 4. In this file, when we write "BIG5" |
73 |
(all uppercase), we mean the coding system, and when we write |
74 |
"Big5" (capitalized), we mean the character set. |
75 |
|
76 |
4. Raw text |
77 |
|
78 |
A coding system for text containing random 8-bit code. Emacs does |
79 |
no code conversion on such text except for end-of-line format. |
80 |
|
81 |
5. Other |
82 |
|
83 |
If a user wants to read/write text encoded in a coding system not |
84 |
listed above, he can supply a decoder and an encoder for it as CCL |
85 |
(Code Conversion Language) programs. Emacs executes the CCL program |
86 |
while reading/writing. |
87 |
|
88 |
Emacs represents a coding system by a Lisp symbol that has a property |
89 |
`coding-system'. But, before actually using the coding system, the |
90 |
information about it is set in a structure of type `struct |
91 |
coding_system' for rapid processing. See section 6 for more details. |
92 |
|
93 |
*/ |
94 |
|
95 |
/*** GENERAL NOTES on END-OF-LINE FORMAT *** |
96 |
|
97 |
How end-of-line of text is encoded depends on the operating system. |
98 |
For instance, Unix's format is just one byte of `line-feed' code, |
99 |
whereas DOS's format is two-byte sequence of `carriage-return' and |
100 |
`line-feed' codes. MacOS's format is usually one byte of |
101 |
`carriage-return'. |
102 |
|
103 |
Since text character encoding and end-of-line encoding are |
104 |
independent, any coding system described above can have any |
105 |
end-of-line format. So Emacs has information about end-of-line |
106 |
format in each coding-system. See section 6 for more details. |
107 |
|
108 |
*/ |
109 |
|
110 |
/*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
111 |
|
112 |
These functions check if a text between SRC and SRC_END is encoded |
113 |
in the coding system category XXX. Each returns an integer value in |
114 |
which appropriate flag bits for the category XXX are set. The flag |
115 |
bits are defined in macros CODING_CATEGORY_MASK_XXX. Below is the |
116 |
template for these functions. If MULTIBYTEP is nonzero, 8-bit codes |
117 |
of the range 0x80..0x9F are in multibyte form. */ |
118 |
#if 0 |
119 |
int |
120 |
detect_coding_emacs_mule (src, src_end, multibytep) |
121 |
unsigned char *src, *src_end; |
122 |
int multibytep; |
123 |
{ |
124 |
... |
125 |
} |
126 |
#endif |
127 |
|
128 |
/*** GENERAL NOTES on `decode_coding_XXX ()' functions *** |
129 |
|
130 |
These functions decode SRC_BYTES length of unibyte text at SOURCE |
131 |
encoded in CODING to Emacs' internal format. The resulting |
132 |
multibyte text goes to a place pointed to by DESTINATION, the length |
133 |
of which should not exceed DST_BYTES. |
134 |
|
135 |
These functions set the information about original and decoded texts |
136 |
in the members `produced', `produced_char', `consumed', and |
137 |
`consumed_char' of the structure *CODING. They also set the member |
138 |
`result' to one of CODING_FINISH_XXX indicating how the decoding |
139 |
finished. |
140 |
|
141 |
DST_BYTES zero means that the source area and destination area are |
142 |
overlapped, which means that we can produce a decoded text until it |
143 |
reaches the head of the not-yet-decoded source text. |
144 |
|
145 |
Below is a template for these functions. */ |
146 |
#if 0 |
147 |
static void |
148 |
decode_coding_XXX (coding, source, destination, src_bytes, dst_bytes) |
149 |
struct coding_system *coding; |
150 |
unsigned char *source, *destination; |
151 |
int src_bytes, dst_bytes; |
152 |
{ |
153 |
... |
154 |
} |
155 |
#endif |
156 |
|
157 |
/*** GENERAL NOTES on `encode_coding_XXX ()' functions *** |
158 |
|
159 |
These functions encode SRC_BYTES length text at SOURCE from Emacs' |
160 |
internal multibyte format to CODING. The resulting unibyte text |
161 |
goes to a place pointed to by DESTINATION, the length of which |
162 |
should not exceed DST_BYTES. |
163 |
|
164 |
These functions set the information about original and encoded texts |
165 |
in the members `produced', `produced_char', `consumed', and |
166 |
`consumed_char' of the structure *CODING. They also set the member |
167 |
`result' to one of CODING_FINISH_XXX indicating how the encoding |
168 |
finished. |
169 |
|
170 |
DST_BYTES zero means that the source area and destination area are |
171 |
overlapped, which means that we can produce encoded text until it |
172 |
reaches at the head of the not-yet-encoded source text. |
173 |
|
174 |
Below is a template for these functions. */ |
175 |
#if 0 |
176 |
static void |
177 |
encode_coding_XXX (coding, source, destination, src_bytes, dst_bytes) |
178 |
struct coding_system *coding; |
179 |
unsigned char *source, *destination; |
180 |
int src_bytes, dst_bytes; |
181 |
{ |
182 |
... |
183 |
} |
184 |
#endif |
185 |
|
186 |
/*** COMMONLY USED MACROS ***/ |
187 |
|
188 |
/* The following two macros ONE_MORE_BYTE and TWO_MORE_BYTES safely |
189 |
get one, two, and three bytes from the source text respectively. |
190 |
If there are not enough bytes in the source, they jump to |
191 |
`label_end_of_loop'. The caller should set variables `coding', |
192 |
`src' and `src_end' to appropriate pointer in advance. These |
193 |
macros are called from decoding routines `decode_coding_XXX', thus |
194 |
it is assumed that the source text is unibyte. */ |
195 |
|
196 |
#define ONE_MORE_BYTE(c1) \ |
197 |
do { \ |
198 |
if (src >= src_end) \ |
199 |
{ \ |
200 |
coding->result = CODING_FINISH_INSUFFICIENT_SRC; \ |
201 |
goto label_end_of_loop; \ |
202 |
} \ |
203 |
c1 = *src++; \ |
204 |
} while (0) |
205 |
|
206 |
#define TWO_MORE_BYTES(c1, c2) \ |
207 |
do { \ |
208 |
if (src + 1 >= src_end) \ |
209 |
{ \ |
210 |
coding->result = CODING_FINISH_INSUFFICIENT_SRC; \ |
211 |
goto label_end_of_loop; \ |
212 |
} \ |
213 |
c1 = *src++; \ |
214 |
c2 = *src++; \ |
215 |
} while (0) |
216 |
|
217 |
|
218 |
/* Like ONE_MORE_BYTE, but 8-bit bytes of data at SRC are in multibyte |
219 |
form if MULTIBYTEP is nonzero. */ |
220 |
|
221 |
#define ONE_MORE_BYTE_CHECK_MULTIBYTE(c1, multibytep) \ |
222 |
do { \ |
223 |
if (src >= src_end) \ |
224 |
{ \ |
225 |
coding->result = CODING_FINISH_INSUFFICIENT_SRC; \ |
226 |
goto label_end_of_loop; \ |
227 |
} \ |
228 |
c1 = *src++; \ |
229 |
if (multibytep && c1 == LEADING_CODE_8_BIT_CONTROL) \ |
230 |
c1 = *src++ - 0x20; \ |
231 |
} while (0) |
232 |
|
233 |
/* Set C to the next character at the source text pointed by `src'. |
234 |
If there are not enough characters in the source, jump to |
235 |
`label_end_of_loop'. The caller should set variables `coding' |
236 |
`src', `src_end', and `translation_table' to appropriate pointers |
237 |
in advance. This macro is used in encoding routines |
238 |
`encode_coding_XXX', thus it assumes that the source text is in |
239 |
multibyte form except for 8-bit characters. 8-bit characters are |
240 |
in multibyte form if coding->src_multibyte is nonzero, else they |
241 |
are represented by a single byte. */ |
242 |
|
243 |
#define ONE_MORE_CHAR(c) \ |
244 |
do { \ |
245 |
int len = src_end - src; \ |
246 |
int bytes; \ |
247 |
if (len <= 0) \ |
248 |
{ \ |
249 |
coding->result = CODING_FINISH_INSUFFICIENT_SRC; \ |
250 |
goto label_end_of_loop; \ |
251 |
} \ |
252 |
if (coding->src_multibyte \ |
253 |
|| UNIBYTE_STR_AS_MULTIBYTE_P (src, len, bytes)) \ |
254 |
c = STRING_CHAR_AND_LENGTH (src, len, bytes); \ |
255 |
else \ |
256 |
c = *src, bytes = 1; \ |
257 |
if (!NILP (translation_table)) \ |
258 |
c = translate_char (translation_table, c, -1, 0, 0); \ |
259 |
src += bytes; \ |
260 |
} while (0) |
261 |
|
262 |
|
263 |
/* Produce a multibyte form of character C to `dst'. Jump to |
264 |
`label_end_of_loop' if there's not enough space at `dst'. |
265 |
|
266 |
If we are now in the middle of a composition sequence, the decoded |
267 |
character may be ALTCHAR (for the current composition). In that |
268 |
case, the character goes to coding->cmp_data->data instead of |
269 |
`dst'. |
270 |
|
271 |
This macro is used in decoding routines. */ |
272 |
|
273 |
#define EMIT_CHAR(c) \ |
274 |
do { \ |
275 |
if (! COMPOSING_P (coding) \ |
276 |
|| coding->composing == COMPOSITION_RELATIVE \ |
277 |
|| coding->composing == COMPOSITION_WITH_RULE) \ |
278 |
{ \ |
279 |
int bytes = CHAR_BYTES (c); \ |
280 |
if ((dst + bytes) > (dst_bytes ? dst_end : src)) \ |
281 |
{ \ |
282 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; \ |
283 |
goto label_end_of_loop; \ |
284 |
} \ |
285 |
dst += CHAR_STRING (c, dst); \ |
286 |
coding->produced_char++; \ |
287 |
} \ |
288 |
\ |
289 |
if (COMPOSING_P (coding) \ |
290 |
&& coding->composing != COMPOSITION_RELATIVE) \ |
291 |
{ \ |
292 |
CODING_ADD_COMPOSITION_COMPONENT (coding, c); \ |
293 |
coding->composition_rule_follows \ |
294 |
= coding->composing != COMPOSITION_WITH_ALTCHARS; \ |
295 |
} \ |
296 |
} while (0) |
297 |
|
298 |
|
299 |
#define EMIT_ONE_BYTE(c) \ |
300 |
do { \ |
301 |
if (dst >= (dst_bytes ? dst_end : src)) \ |
302 |
{ \ |
303 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; \ |
304 |
goto label_end_of_loop; \ |
305 |
} \ |
306 |
*dst++ = c; \ |
307 |
} while (0) |
308 |
|
309 |
#define EMIT_TWO_BYTES(c1, c2) \ |
310 |
do { \ |
311 |
if (dst + 2 > (dst_bytes ? dst_end : src)) \ |
312 |
{ \ |
313 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; \ |
314 |
goto label_end_of_loop; \ |
315 |
} \ |
316 |
*dst++ = c1, *dst++ = c2; \ |
317 |
} while (0) |
318 |
|
319 |
#define EMIT_BYTES(from, to) \ |
320 |
do { \ |
321 |
if (dst + (to - from) > (dst_bytes ? dst_end : src)) \ |
322 |
{ \ |
323 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; \ |
324 |
goto label_end_of_loop; \ |
325 |
} \ |
326 |
while (from < to) \ |
327 |
*dst++ = *from++; \ |
328 |
} while (0) |
329 |
|
330 |
|
331 |
/*** 1. Preamble ***/ |
332 |
|
333 |
#ifdef emacs |
334 |
#include <config.h> |
335 |
#endif |
336 |
|
337 |
#include <stdio.h> |
338 |
|
339 |
#ifdef emacs |
340 |
|
341 |
#include "lisp.h" |
342 |
#include "buffer.h" |
343 |
#include "charset.h" |
344 |
#include "composite.h" |
345 |
#include "ccl.h" |
346 |
#include "coding.h" |
347 |
#include "window.h" |
348 |
#include "intervals.h" |
349 |
|
350 |
#else /* not emacs */ |
351 |
|
352 |
#include "mulelib.h" |
353 |
|
354 |
#endif /* not emacs */ |
355 |
|
356 |
Lisp_Object Qcoding_system, Qeol_type; |
357 |
Lisp_Object Qbuffer_file_coding_system; |
358 |
Lisp_Object Qpost_read_conversion, Qpre_write_conversion; |
359 |
Lisp_Object Qno_conversion, Qundecided; |
360 |
Lisp_Object Qcoding_system_history; |
361 |
Lisp_Object Qsafe_chars; |
362 |
Lisp_Object Qvalid_codes; |
363 |
|
364 |
extern Lisp_Object Qinsert_file_contents, Qwrite_region; |
365 |
Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; |
366 |
Lisp_Object Qstart_process, Qopen_network_stream; |
367 |
Lisp_Object Qtarget_idx; |
368 |
|
369 |
/* If a symbol has this property, evaluate the value to define the |
370 |
symbol as a coding system. */ |
371 |
Lisp_Object Qcoding_system_define_form; |
372 |
|
373 |
Lisp_Object Vselect_safe_coding_system_function; |
374 |
|
375 |
int coding_system_require_warning; |
376 |
|
377 |
/* Mnemonic string for each format of end-of-line. */ |
378 |
Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; |
379 |
/* Mnemonic string to indicate format of end-of-line is not yet |
380 |
decided. */ |
381 |
Lisp_Object eol_mnemonic_undecided; |
382 |
|
383 |
/* Format of end-of-line decided by system. This is CODING_EOL_LF on |
384 |
Unix, CODING_EOL_CRLF on DOS/Windows, and CODING_EOL_CR on Mac. */ |
385 |
int system_eol_type; |
386 |
|
387 |
#ifdef emacs |
388 |
|
389 |
/* Information about which coding system is safe for which chars. |
390 |
The value has the form (GENERIC-LIST . NON-GENERIC-ALIST). |
391 |
|
392 |
GENERIC-LIST is a list of generic coding systems which can encode |
393 |
any characters. |
394 |
|
395 |
NON-GENERIC-ALIST is an alist of non generic coding systems vs the |
396 |
corresponding char table that contains safe chars. */ |
397 |
Lisp_Object Vcoding_system_safe_chars; |
398 |
|
399 |
Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
400 |
|
401 |
Lisp_Object Qcoding_system_p, Qcoding_system_error; |
402 |
|
403 |
/* Coding system emacs-mule and raw-text are for converting only |
404 |
end-of-line format. */ |
405 |
Lisp_Object Qemacs_mule, Qraw_text; |
406 |
|
407 |
Lisp_Object Qutf_8; |
408 |
|
409 |
/* Coding-systems are handed between Emacs Lisp programs and C internal |
410 |
routines by the following three variables. */ |
411 |
/* Coding-system for reading files and receiving data from process. */ |
412 |
Lisp_Object Vcoding_system_for_read; |
413 |
/* Coding-system for writing files and sending data to process. */ |
414 |
Lisp_Object Vcoding_system_for_write; |
415 |
/* Coding-system actually used in the latest I/O. */ |
416 |
Lisp_Object Vlast_coding_system_used; |
417 |
|
418 |
/* A vector of length 256 which contains information about special |
419 |
Latin codes (especially for dealing with Microsoft codes). */ |
420 |
Lisp_Object Vlatin_extra_code_table; |
421 |
|
422 |
/* Flag to inhibit code conversion of end-of-line format. */ |
423 |
int inhibit_eol_conversion; |
424 |
|
425 |
/* Flag to inhibit ISO2022 escape sequence detection. */ |
426 |
int inhibit_iso_escape_detection; |
427 |
|
428 |
/* Flag to make buffer-file-coding-system inherit from process-coding. */ |
429 |
int inherit_process_coding_system; |
430 |
|
431 |
/* Coding system to be used to encode text for terminal display. */ |
432 |
struct coding_system terminal_coding; |
433 |
|
434 |
/* Coding system to be used to encode text for terminal display when |
435 |
terminal coding system is nil. */ |
436 |
struct coding_system safe_terminal_coding; |
437 |
|
438 |
/* Coding system of what is sent from terminal keyboard. */ |
439 |
struct coding_system keyboard_coding; |
440 |
|
441 |
/* Default coding system to be used to write a file. */ |
442 |
struct coding_system default_buffer_file_coding; |
443 |
|
444 |
Lisp_Object Vfile_coding_system_alist; |
445 |
Lisp_Object Vprocess_coding_system_alist; |
446 |
Lisp_Object Vnetwork_coding_system_alist; |
447 |
|
448 |
Lisp_Object Vlocale_coding_system; |
449 |
|
450 |
#endif /* emacs */ |
451 |
|
452 |
Lisp_Object Qcoding_category, Qcoding_category_index; |
453 |
|
454 |
/* List of symbols `coding-category-xxx' ordered by priority. */ |
455 |
Lisp_Object Vcoding_category_list; |
456 |
|
457 |
/* Table of coding categories (Lisp symbols). */ |
458 |
Lisp_Object Vcoding_category_table; |
459 |
|
460 |
/* Table of names of symbol for each coding-category. */ |
461 |
char *coding_category_name[CODING_CATEGORY_IDX_MAX] = { |
462 |
"coding-category-emacs-mule", |
463 |
"coding-category-sjis", |
464 |
"coding-category-iso-7", |
465 |
"coding-category-iso-7-tight", |
466 |
"coding-category-iso-8-1", |
467 |
"coding-category-iso-8-2", |
468 |
"coding-category-iso-7-else", |
469 |
"coding-category-iso-8-else", |
470 |
"coding-category-ccl", |
471 |
"coding-category-big5", |
472 |
"coding-category-utf-8", |
473 |
"coding-category-utf-16-be", |
474 |
"coding-category-utf-16-le", |
475 |
"coding-category-raw-text", |
476 |
"coding-category-binary" |
477 |
}; |
478 |
|
479 |
/* Table of pointers to coding systems corresponding to each coding |
480 |
categories. */ |
481 |
struct coding_system *coding_system_table[CODING_CATEGORY_IDX_MAX]; |
482 |
|
483 |
/* Table of coding category masks. Nth element is a mask for a coding |
484 |
category of which priority is Nth. */ |
485 |
static |
486 |
int coding_priorities[CODING_CATEGORY_IDX_MAX]; |
487 |
|
488 |
/* Flag to tell if we look up translation table on character code |
489 |
conversion. */ |
490 |
Lisp_Object Venable_character_translation; |
491 |
/* Standard translation table to look up on decoding (reading). */ |
492 |
Lisp_Object Vstandard_translation_table_for_decode; |
493 |
/* Standard translation table to look up on encoding (writing). */ |
494 |
Lisp_Object Vstandard_translation_table_for_encode; |
495 |
|
496 |
Lisp_Object Qtranslation_table; |
497 |
Lisp_Object Qtranslation_table_id; |
498 |
Lisp_Object Qtranslation_table_for_decode; |
499 |
Lisp_Object Qtranslation_table_for_encode; |
500 |
|
501 |
/* Alist of charsets vs revision number. */ |
502 |
Lisp_Object Vcharset_revision_alist; |
503 |
|
504 |
/* Default coding systems used for process I/O. */ |
505 |
Lisp_Object Vdefault_process_coding_system; |
506 |
|
507 |
/* Char table for translating Quail and self-inserting input. */ |
508 |
Lisp_Object Vtranslation_table_for_input; |
509 |
|
510 |
/* Global flag to tell that we can't call post-read-conversion and |
511 |
pre-write-conversion functions. Usually the value is zero, but it |
512 |
is set to 1 temporarily while such functions are running. This is |
513 |
to avoid infinite recursive call. */ |
514 |
static int inhibit_pre_post_conversion; |
515 |
|
516 |
Lisp_Object Qchar_coding_system; |
517 |
|
518 |
/* Return `safe-chars' property of CODING_SYSTEM (symbol). Don't check |
519 |
its validity. */ |
520 |
|
521 |
Lisp_Object |
522 |
coding_safe_chars (coding_system) |
523 |
Lisp_Object coding_system; |
524 |
{ |
525 |
Lisp_Object coding_spec, plist, safe_chars; |
526 |
|
527 |
coding_spec = Fget (coding_system, Qcoding_system); |
528 |
plist = XVECTOR (coding_spec)->contents[3]; |
529 |
safe_chars = Fplist_get (XVECTOR (coding_spec)->contents[3], Qsafe_chars); |
530 |
return (CHAR_TABLE_P (safe_chars) ? safe_chars : Qt); |
531 |
} |
532 |
|
533 |
#define CODING_SAFE_CHAR_P(safe_chars, c) \ |
534 |
(EQ (safe_chars, Qt) || !NILP (CHAR_TABLE_REF (safe_chars, c))) |
535 |
|
536 |
|
537 |
/*** 2. Emacs internal format (emacs-mule) handlers ***/ |
538 |
|
539 |
/* Emacs' internal format for representation of multiple character |
540 |
sets is a kind of multi-byte encoding, i.e. characters are |
541 |
represented by variable-length sequences of one-byte codes. |
542 |
|
543 |
ASCII characters and control characters (e.g. `tab', `newline') are |
544 |
represented by one-byte sequences which are their ASCII codes, in |
545 |
the range 0x00 through 0x7F. |
546 |
|
547 |
8-bit characters of the range 0x80..0x9F are represented by |
548 |
two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit |
549 |
code + 0x20). |
550 |
|
551 |
8-bit characters of the range 0xA0..0xFF are represented by |
552 |
one-byte sequences which are their 8-bit code. |
553 |
|
554 |
The other characters are represented by a sequence of `base |
555 |
leading-code', optional `extended leading-code', and one or two |
556 |
`position-code's. The length of the sequence is determined by the |
557 |
base leading-code. Leading-code takes the range 0x81 through 0x9D, |
558 |
whereas extended leading-code and position-code take the range 0xA0 |
559 |
through 0xFF. See `charset.h' for more details about leading-code |
560 |
and position-code. |
561 |
|
562 |
--- CODE RANGE of Emacs' internal format --- |
563 |
character set range |
564 |
------------- ----- |
565 |
ascii 0x00..0x7F |
566 |
eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF |
567 |
eight-bit-graphic 0xA0..0xBF |
568 |
ELSE 0x81..0x9D + [0xA0..0xFF]+ |
569 |
--------------------------------------------- |
570 |
|
571 |
As this is the internal character representation, the format is |
572 |
usually not used externally (i.e. in a file or in a data sent to a |
573 |
process). But, it is possible to have a text externally in this |
574 |
format (i.e. by encoding by the coding system `emacs-mule'). |
575 |
|
576 |
In that case, a sequence of one-byte codes has a slightly different |
577 |
form. |
578 |
|
579 |
Firstly, all characters in eight-bit-control are represented by |
580 |
one-byte sequences which are their 8-bit code. |
581 |
|
582 |
Next, character composition data are represented by the byte |
583 |
sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., |
584 |
where, |
585 |
METHOD is 0xF0 plus one of composition method (enum |
586 |
composition_method), |
587 |
|
588 |
BYTES is 0xA0 plus the byte length of these composition data, |
589 |
|
590 |
CHARS is 0xA0 plus the number of characters composed by these |
591 |
data, |
592 |
|
593 |
COMPONENTs are characters of multibyte form or composition |
594 |
rules encoded by two-byte of ASCII codes. |
595 |
|
596 |
In addition, for backward compatibility, the following formats are |
597 |
also recognized as composition data on decoding. |
598 |
|
599 |
0x80 MSEQ ... |
600 |
0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ |
601 |
|
602 |
Here, |
603 |
MSEQ is a multibyte form but in these special format: |
604 |
ASCII: 0xA0 ASCII_CODE+0x80, |
605 |
other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., |
606 |
RULE is a one byte code of the range 0xA0..0xF0 that |
607 |
represents a composition rule. |
608 |
*/ |
609 |
|
610 |
enum emacs_code_class_type emacs_code_class[256]; |
611 |
|
612 |
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
613 |
Check if a text is encoded in Emacs' internal format. If it is, |
614 |
return CODING_CATEGORY_MASK_EMACS_MULE, else return 0. */ |
615 |
|
616 |
static int |
617 |
detect_coding_emacs_mule (src, src_end, multibytep) |
618 |
unsigned char *src, *src_end; |
619 |
int multibytep; |
620 |
{ |
621 |
unsigned char c; |
622 |
int composing = 0; |
623 |
/* Dummy for ONE_MORE_BYTE. */ |
624 |
struct coding_system dummy_coding; |
625 |
struct coding_system *coding = &dummy_coding; |
626 |
|
627 |
while (1) |
628 |
{ |
629 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
630 |
|
631 |
if (composing) |
632 |
{ |
633 |
if (c < 0xA0) |
634 |
composing = 0; |
635 |
else if (c == 0xA0) |
636 |
{ |
637 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
638 |
c &= 0x7F; |
639 |
} |
640 |
else |
641 |
c -= 0x20; |
642 |
} |
643 |
|
644 |
if (c < 0x20) |
645 |
{ |
646 |
if (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) |
647 |
return 0; |
648 |
} |
649 |
else if (c >= 0x80 && c < 0xA0) |
650 |
{ |
651 |
if (c == 0x80) |
652 |
/* Old leading code for a composite character. */ |
653 |
composing = 1; |
654 |
else |
655 |
{ |
656 |
unsigned char *src_base = src - 1; |
657 |
int bytes; |
658 |
|
659 |
if (!UNIBYTE_STR_AS_MULTIBYTE_P (src_base, src_end - src_base, |
660 |
bytes)) |
661 |
return 0; |
662 |
src = src_base + bytes; |
663 |
} |
664 |
} |
665 |
} |
666 |
label_end_of_loop: |
667 |
return CODING_CATEGORY_MASK_EMACS_MULE; |
668 |
} |
669 |
|
670 |
|
671 |
/* Record the starting position START and METHOD of one composition. */ |
672 |
|
673 |
#define CODING_ADD_COMPOSITION_START(coding, start, method) \ |
674 |
do { \ |
675 |
struct composition_data *cmp_data = coding->cmp_data; \ |
676 |
int *data = cmp_data->data + cmp_data->used; \ |
677 |
coding->cmp_data_start = cmp_data->used; \ |
678 |
data[0] = -1; \ |
679 |
data[1] = cmp_data->char_offset + start; \ |
680 |
data[3] = (int) method; \ |
681 |
cmp_data->used += 4; \ |
682 |
} while (0) |
683 |
|
684 |
/* Record the ending position END of the current composition. */ |
685 |
|
686 |
#define CODING_ADD_COMPOSITION_END(coding, end) \ |
687 |
do { \ |
688 |
struct composition_data *cmp_data = coding->cmp_data; \ |
689 |
int *data = cmp_data->data + coding->cmp_data_start; \ |
690 |
data[0] = cmp_data->used - coding->cmp_data_start; \ |
691 |
data[2] = cmp_data->char_offset + end; \ |
692 |
} while (0) |
693 |
|
694 |
/* Record one COMPONENT (alternate character or composition rule). */ |
695 |
|
696 |
#define CODING_ADD_COMPOSITION_COMPONENT(coding, component) \ |
697 |
do { \ |
698 |
coding->cmp_data->data[coding->cmp_data->used++] = component; \ |
699 |
if (coding->cmp_data->used - coding->cmp_data_start \ |
700 |
== COMPOSITION_DATA_MAX_BUNCH_LENGTH) \ |
701 |
{ \ |
702 |
CODING_ADD_COMPOSITION_END (coding, coding->produced_char); \ |
703 |
coding->composing = COMPOSITION_NO; \ |
704 |
} \ |
705 |
} while (0) |
706 |
|
707 |
|
708 |
/* Get one byte from a data pointed by SRC and increment SRC. If SRC |
709 |
is not less than SRC_END, return -1 without incrementing Src. */ |
710 |
|
711 |
#define SAFE_ONE_MORE_BYTE() (src >= src_end ? -1 : *src++) |
712 |
|
713 |
|
714 |
/* Decode a character represented as a component of composition |
715 |
sequence of Emacs 20 style at SRC. Set C to that character, store |
716 |
its multibyte form sequence at P, and set P to the end of that |
717 |
sequence. If no valid character is found, set C to -1. */ |
718 |
|
719 |
#define DECODE_EMACS_MULE_COMPOSITION_CHAR(c, p) \ |
720 |
do { \ |
721 |
int bytes; \ |
722 |
\ |
723 |
c = SAFE_ONE_MORE_BYTE (); \ |
724 |
if (c < 0) \ |
725 |
break; \ |
726 |
if (CHAR_HEAD_P (c)) \ |
727 |
c = -1; \ |
728 |
else if (c == 0xA0) \ |
729 |
{ \ |
730 |
c = SAFE_ONE_MORE_BYTE (); \ |
731 |
if (c < 0xA0) \ |
732 |
c = -1; \ |
733 |
else \ |
734 |
{ \ |
735 |
c -= 0xA0; \ |
736 |
*p++ = c; \ |
737 |
} \ |
738 |
} \ |
739 |
else if (BASE_LEADING_CODE_P (c - 0x20)) \ |
740 |
{ \ |
741 |
unsigned char *p0 = p; \ |
742 |
\ |
743 |
c -= 0x20; \ |
744 |
*p++ = c; \ |
745 |
bytes = BYTES_BY_CHAR_HEAD (c); \ |
746 |
while (--bytes) \ |
747 |
{ \ |
748 |
c = SAFE_ONE_MORE_BYTE (); \ |
749 |
if (c < 0) \ |
750 |
break; \ |
751 |
*p++ = c; \ |
752 |
} \ |
753 |
if (UNIBYTE_STR_AS_MULTIBYTE_P (p0, p - p0, bytes) \ |
754 |
|| (coding->flags /* We are recovering a file. */ \ |
755 |
&& p0[0] == LEADING_CODE_8_BIT_CONTROL \ |
756 |
&& ! CHAR_HEAD_P (p0[1]))) \ |
757 |
c = STRING_CHAR (p0, bytes); \ |
758 |
else \ |
759 |
c = -1; \ |
760 |
} \ |
761 |
else \ |
762 |
c = -1; \ |
763 |
} while (0) |
764 |
|
765 |
|
766 |
/* Decode a composition rule represented as a component of composition |
767 |
sequence of Emacs 20 style at SRC. Set C to the rule. If not |
768 |
valid rule is found, set C to -1. */ |
769 |
|
770 |
#define DECODE_EMACS_MULE_COMPOSITION_RULE(c) \ |
771 |
do { \ |
772 |
c = SAFE_ONE_MORE_BYTE (); \ |
773 |
c -= 0xA0; \ |
774 |
if (c < 0 || c >= 81) \ |
775 |
c = -1; \ |
776 |
else \ |
777 |
{ \ |
778 |
gref = c / 9, nref = c % 9; \ |
779 |
c = COMPOSITION_ENCODE_RULE (gref, nref); \ |
780 |
} \ |
781 |
} while (0) |
782 |
|
783 |
|
784 |
/* Decode composition sequence encoded by `emacs-mule' at the source |
785 |
pointed by SRC. SRC_END is the end of source. Store information |
786 |
of the composition in CODING->cmp_data. |
787 |
|
788 |
For backward compatibility, decode also a composition sequence of |
789 |
Emacs 20 style. In that case, the composition sequence contains |
790 |
characters that should be extracted into a buffer or string. Store |
791 |
those characters at *DESTINATION in multibyte form. |
792 |
|
793 |
If we encounter an invalid byte sequence, return 0. |
794 |
If we encounter an insufficient source or destination, or |
795 |
insufficient space in CODING->cmp_data, return 1. |
796 |
Otherwise, return consumed bytes in the source. |
797 |
|
798 |
*/ |
799 |
static INLINE int |
800 |
decode_composition_emacs_mule (coding, src, src_end, |
801 |
destination, dst_end, dst_bytes) |
802 |
struct coding_system *coding; |
803 |
unsigned char *src, *src_end, **destination, *dst_end; |
804 |
int dst_bytes; |
805 |
{ |
806 |
unsigned char *dst = *destination; |
807 |
int method, data_len, nchars; |
808 |
unsigned char *src_base = src++; |
809 |
/* Store components of composition. */ |
810 |
int component[COMPOSITION_DATA_MAX_BUNCH_LENGTH]; |
811 |
int ncomponent; |
812 |
/* Store multibyte form of characters to be composed. This is for |
813 |
Emacs 20 style composition sequence. */ |
814 |
unsigned char buf[MAX_COMPOSITION_COMPONENTS * MAX_MULTIBYTE_LENGTH]; |
815 |
unsigned char *bufp = buf; |
816 |
int c, i, gref, nref; |
817 |
|
818 |
if (coding->cmp_data->used + COMPOSITION_DATA_MAX_BUNCH_LENGTH |
819 |
>= COMPOSITION_DATA_SIZE) |
820 |
{ |
821 |
coding->result = CODING_FINISH_INSUFFICIENT_CMP; |
822 |
return -1; |
823 |
} |
824 |
|
825 |
ONE_MORE_BYTE (c); |
826 |
if (c - 0xF0 >= COMPOSITION_RELATIVE |
827 |
&& c - 0xF0 <= COMPOSITION_WITH_RULE_ALTCHARS) |
828 |
{ |
829 |
int with_rule; |
830 |
|
831 |
method = c - 0xF0; |
832 |
with_rule = (method == COMPOSITION_WITH_RULE |
833 |
|| method == COMPOSITION_WITH_RULE_ALTCHARS); |
834 |
ONE_MORE_BYTE (c); |
835 |
data_len = c - 0xA0; |
836 |
if (data_len < 4 |
837 |
|| src_base + data_len > src_end) |
838 |
return 0; |
839 |
ONE_MORE_BYTE (c); |
840 |
nchars = c - 0xA0; |
841 |
if (c < 1) |
842 |
return 0; |
843 |
for (ncomponent = 0; src < src_base + data_len; ncomponent++) |
844 |
{ |
845 |
/* If it is longer than this, it can't be valid. */ |
846 |
if (ncomponent >= COMPOSITION_DATA_MAX_BUNCH_LENGTH) |
847 |
return 0; |
848 |
|
849 |
if (ncomponent % 2 && with_rule) |
850 |
{ |
851 |
ONE_MORE_BYTE (gref); |
852 |
gref -= 32; |
853 |
ONE_MORE_BYTE (nref); |
854 |
nref -= 32; |
855 |
c = COMPOSITION_ENCODE_RULE (gref, nref); |
856 |
} |
857 |
else |
858 |
{ |
859 |
int bytes; |
860 |
if (UNIBYTE_STR_AS_MULTIBYTE_P (src, src_end - src, bytes) |
861 |
|| (coding->flags /* We are recovering a file. */ |
862 |
&& src[0] == LEADING_CODE_8_BIT_CONTROL |
863 |
&& ! CHAR_HEAD_P (src[1]))) |
864 |
c = STRING_CHAR (src, bytes); |
865 |
else |
866 |
c = *src, bytes = 1; |
867 |
src += bytes; |
868 |
} |
869 |
component[ncomponent] = c; |
870 |
} |
871 |
} |
872 |
else |
873 |
{ |
874 |
/* This may be an old Emacs 20 style format. See the comment at |
875 |
the section 2 of this file. */ |
876 |
while (src < src_end && !CHAR_HEAD_P (*src)) src++; |
877 |
if (src == src_end |
878 |
&& !(coding->mode & CODING_MODE_LAST_BLOCK)) |
879 |
goto label_end_of_loop; |
880 |
|
881 |
src_end = src; |
882 |
src = src_base + 1; |
883 |
if (c < 0xC0) |
884 |
{ |
885 |
method = COMPOSITION_RELATIVE; |
886 |
for (ncomponent = 0; ncomponent < MAX_COMPOSITION_COMPONENTS;) |
887 |
{ |
888 |
DECODE_EMACS_MULE_COMPOSITION_CHAR (c, bufp); |
889 |
if (c < 0) |
890 |
break; |
891 |
component[ncomponent++] = c; |
892 |
} |
893 |
if (ncomponent < 2) |
894 |
return 0; |
895 |
nchars = ncomponent; |
896 |
} |
897 |
else if (c == 0xFF) |
898 |
{ |
899 |
method = COMPOSITION_WITH_RULE; |
900 |
src++; |
901 |
DECODE_EMACS_MULE_COMPOSITION_CHAR (c, bufp); |
902 |
if (c < 0) |
903 |
return 0; |
904 |
component[0] = c; |
905 |
for (ncomponent = 1; |
906 |
ncomponent < MAX_COMPOSITION_COMPONENTS * 2 - 1;) |
907 |
{ |
908 |
DECODE_EMACS_MULE_COMPOSITION_RULE (c); |
909 |
if (c < 0) |
910 |
break; |
911 |
component[ncomponent++] = c; |
912 |
DECODE_EMACS_MULE_COMPOSITION_CHAR (c, bufp); |
913 |
if (c < 0) |
914 |
break; |
915 |
component[ncomponent++] = c; |
916 |
} |
917 |
if (ncomponent < 3) |
918 |
return 0; |
919 |
nchars = (ncomponent + 1) / 2; |
920 |
} |
921 |
else |
922 |
return 0; |
923 |
} |
924 |
|
925 |
if (buf == bufp || dst + (bufp - buf) <= (dst_bytes ? dst_end : src)) |
926 |
{ |
927 |
CODING_ADD_COMPOSITION_START (coding, coding->produced_char, method); |
928 |
for (i = 0; i < ncomponent; i++) |
929 |
CODING_ADD_COMPOSITION_COMPONENT (coding, component[i]); |
930 |
CODING_ADD_COMPOSITION_END (coding, coding->produced_char + nchars); |
931 |
if (buf < bufp) |
932 |
{ |
933 |
unsigned char *p = buf; |
934 |
EMIT_BYTES (p, bufp); |
935 |
*destination += bufp - buf; |
936 |
coding->produced_char += nchars; |
937 |
} |
938 |
return (src - src_base); |
939 |
} |
940 |
label_end_of_loop: |
941 |
return -1; |
942 |
} |
943 |
|
944 |
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
945 |
|
946 |
static void |
947 |
decode_coding_emacs_mule (coding, source, destination, src_bytes, dst_bytes) |
948 |
struct coding_system *coding; |
949 |
unsigned char *source, *destination; |
950 |
int src_bytes, dst_bytes; |
951 |
{ |
952 |
unsigned char *src = source; |
953 |
unsigned char *src_end = source + src_bytes; |
954 |
unsigned char *dst = destination; |
955 |
unsigned char *dst_end = destination + dst_bytes; |
956 |
/* SRC_BASE remembers the start position in source in each loop. |
957 |
The loop will be exited when there's not enough source code, or |
958 |
when there's not enough destination area to produce a |
959 |
character. */ |
960 |
unsigned char *src_base; |
961 |
|
962 |
coding->produced_char = 0; |
963 |
while ((src_base = src) < src_end) |
964 |
{ |
965 |
unsigned char tmp[MAX_MULTIBYTE_LENGTH], *p; |
966 |
int bytes; |
967 |
|
968 |
if (*src == '\r') |
969 |
{ |
970 |
int c = *src++; |
971 |
|
972 |
if (coding->eol_type == CODING_EOL_CR) |
973 |
c = '\n'; |
974 |
else if (coding->eol_type == CODING_EOL_CRLF) |
975 |
{ |
976 |
ONE_MORE_BYTE (c); |
977 |
if (c != '\n') |
978 |
{ |
979 |
src--; |
980 |
c = '\r'; |
981 |
} |
982 |
} |
983 |
*dst++ = c; |
984 |
coding->produced_char++; |
985 |
continue; |
986 |
} |
987 |
else if (*src == '\n') |
988 |
{ |
989 |
if ((coding->eol_type == CODING_EOL_CR |
990 |
|| coding->eol_type == CODING_EOL_CRLF) |
991 |
&& coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) |
992 |
{ |
993 |
coding->result = CODING_FINISH_INCONSISTENT_EOL; |
994 |
goto label_end_of_loop; |
995 |
} |
996 |
*dst++ = *src++; |
997 |
coding->produced_char++; |
998 |
continue; |
999 |
} |
1000 |
else if (*src == 0x80 && coding->cmp_data) |
1001 |
{ |
1002 |
/* Start of composition data. */ |
1003 |
int consumed = decode_composition_emacs_mule (coding, src, src_end, |
1004 |
&dst, dst_end, |
1005 |
dst_bytes); |
1006 |
if (consumed < 0) |
1007 |
goto label_end_of_loop; |
1008 |
else if (consumed > 0) |
1009 |
{ |
1010 |
src += consumed; |
1011 |
continue; |
1012 |
} |
1013 |
bytes = CHAR_STRING (*src, tmp); |
1014 |
p = tmp; |
1015 |
src++; |
1016 |
} |
1017 |
else if (UNIBYTE_STR_AS_MULTIBYTE_P (src, src_end - src, bytes) |
1018 |
|| (coding->flags /* We are recovering a file. */ |
1019 |
&& src[0] == LEADING_CODE_8_BIT_CONTROL |
1020 |
&& ! CHAR_HEAD_P (src[1]))) |
1021 |
{ |
1022 |
p = src; |
1023 |
src += bytes; |
1024 |
} |
1025 |
else |
1026 |
{ |
1027 |
int i, c; |
1028 |
|
1029 |
bytes = BYTES_BY_CHAR_HEAD (*src); |
1030 |
src++; |
1031 |
for (i = 1; i < bytes; i++) |
1032 |
{ |
1033 |
ONE_MORE_BYTE (c); |
1034 |
if (CHAR_HEAD_P (c)) |
1035 |
break; |
1036 |
} |
1037 |
if (i < bytes) |
1038 |
{ |
1039 |
bytes = CHAR_STRING (*src_base, tmp); |
1040 |
p = tmp; |
1041 |
src = src_base + 1; |
1042 |
} |
1043 |
else |
1044 |
{ |
1045 |
p = src_base; |
1046 |
} |
1047 |
} |
1048 |
if (dst + bytes >= (dst_bytes ? dst_end : src)) |
1049 |
{ |
1050 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; |
1051 |
break; |
1052 |
} |
1053 |
while (bytes--) *dst++ = *p++; |
1054 |
coding->produced_char++; |
1055 |
} |
1056 |
label_end_of_loop: |
1057 |
coding->consumed = coding->consumed_char = src_base - source; |
1058 |
coding->produced = dst - destination; |
1059 |
} |
1060 |
|
1061 |
|
1062 |
/* Encode composition data stored at DATA into a special byte sequence |
1063 |
starting by 0x80. Update CODING->cmp_data_start and maybe |
1064 |
CODING->cmp_data for the next call. */ |
1065 |
|
1066 |
#define ENCODE_COMPOSITION_EMACS_MULE(coding, data) \ |
1067 |
do { \ |
1068 |
unsigned char buf[1024], *p0 = buf, *p; \ |
1069 |
int len = data[0]; \ |
1070 |
int i; \ |
1071 |
\ |
1072 |
buf[0] = 0x80; \ |
1073 |
buf[1] = 0xF0 + data[3]; /* METHOD */ \ |
1074 |
buf[3] = 0xA0 + (data[2] - data[1]); /* COMPOSED-CHARS */ \ |
1075 |
p = buf + 4; \ |
1076 |
if (data[3] == COMPOSITION_WITH_RULE \ |
1077 |
|| data[3] == COMPOSITION_WITH_RULE_ALTCHARS) \ |
1078 |
{ \ |
1079 |
p += CHAR_STRING (data[4], p); \ |
1080 |
for (i = 5; i < len; i += 2) \ |
1081 |
{ \ |
1082 |
int gref, nref; \ |
1083 |
COMPOSITION_DECODE_RULE (data[i], gref, nref); \ |
1084 |
*p++ = 0x20 + gref; \ |
1085 |
*p++ = 0x20 + nref; \ |
1086 |
p += CHAR_STRING (data[i + 1], p); \ |
1087 |
} \ |
1088 |
} \ |
1089 |
else \ |
1090 |
{ \ |
1091 |
for (i = 4; i < len; i++) \ |
1092 |
p += CHAR_STRING (data[i], p); \ |
1093 |
} \ |
1094 |
buf[2] = 0xA0 + (p - buf); /* COMPONENTS-BYTES */ \ |
1095 |
\ |
1096 |
if (dst + (p - buf) + 4 > (dst_bytes ? dst_end : src)) \ |
1097 |
{ \ |
1098 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; \ |
1099 |
goto label_end_of_loop; \ |
1100 |
} \ |
1101 |
while (p0 < p) \ |
1102 |
*dst++ = *p0++; \ |
1103 |
coding->cmp_data_start += data[0]; \ |
1104 |
if (coding->cmp_data_start == coding->cmp_data->used \ |
1105 |
&& coding->cmp_data->next) \ |
1106 |
{ \ |
1107 |
coding->cmp_data = coding->cmp_data->next; \ |
1108 |
coding->cmp_data_start = 0; \ |
1109 |
} \ |
1110 |
} while (0) |
1111 |
|
1112 |
|
1113 |
static void encode_eol P_ ((struct coding_system *, const unsigned char *, |
1114 |
unsigned char *, int, int)); |
1115 |
|
1116 |
static void |
1117 |
encode_coding_emacs_mule (coding, source, destination, src_bytes, dst_bytes) |
1118 |
struct coding_system *coding; |
1119 |
unsigned char *source, *destination; |
1120 |
int src_bytes, dst_bytes; |
1121 |
{ |
1122 |
unsigned char *src = source; |
1123 |
unsigned char *src_end = source + src_bytes; |
1124 |
unsigned char *dst = destination; |
1125 |
unsigned char *dst_end = destination + dst_bytes; |
1126 |
unsigned char *src_base; |
1127 |
int c; |
1128 |
int char_offset; |
1129 |
int *data; |
1130 |
|
1131 |
Lisp_Object translation_table; |
1132 |
|
1133 |
translation_table = Qnil; |
1134 |
|
1135 |
/* Optimization for the case that there's no composition. */ |
1136 |
if (!coding->cmp_data || coding->cmp_data->used == 0) |
1137 |
{ |
1138 |
encode_eol (coding, source, destination, src_bytes, dst_bytes); |
1139 |
return; |
1140 |
} |
1141 |
|
1142 |
char_offset = coding->cmp_data->char_offset; |
1143 |
data = coding->cmp_data->data + coding->cmp_data_start; |
1144 |
while (1) |
1145 |
{ |
1146 |
src_base = src; |
1147 |
|
1148 |
/* If SRC starts a composition, encode the information about the |
1149 |
composition in advance. */ |
1150 |
if (coding->cmp_data_start < coding->cmp_data->used |
1151 |
&& char_offset + coding->consumed_char == data[1]) |
1152 |
{ |
1153 |
ENCODE_COMPOSITION_EMACS_MULE (coding, data); |
1154 |
char_offset = coding->cmp_data->char_offset; |
1155 |
data = coding->cmp_data->data + coding->cmp_data_start; |
1156 |
} |
1157 |
|
1158 |
ONE_MORE_CHAR (c); |
1159 |
if (c == '\n' && (coding->eol_type == CODING_EOL_CRLF |
1160 |
|| coding->eol_type == CODING_EOL_CR)) |
1161 |
{ |
1162 |
if (coding->eol_type == CODING_EOL_CRLF) |
1163 |
EMIT_TWO_BYTES ('\r', c); |
1164 |
else |
1165 |
EMIT_ONE_BYTE ('\r'); |
1166 |
} |
1167 |
else if (SINGLE_BYTE_CHAR_P (c)) |
1168 |
{ |
1169 |
if (coding->flags && ! ASCII_BYTE_P (c)) |
1170 |
{ |
1171 |
/* As we are auto saving, retain the multibyte form for |
1172 |
8-bit chars. */ |
1173 |
unsigned char buf[MAX_MULTIBYTE_LENGTH]; |
1174 |
int bytes = CHAR_STRING (c, buf); |
1175 |
|
1176 |
if (bytes == 1) |
1177 |
EMIT_ONE_BYTE (buf[0]); |
1178 |
else |
1179 |
EMIT_TWO_BYTES (buf[0], buf[1]); |
1180 |
} |
1181 |
else |
1182 |
EMIT_ONE_BYTE (c); |
1183 |
} |
1184 |
else |
1185 |
EMIT_BYTES (src_base, src); |
1186 |
coding->consumed_char++; |
1187 |
} |
1188 |
label_end_of_loop: |
1189 |
coding->consumed = src_base - source; |
1190 |
coding->produced = coding->produced_char = dst - destination; |
1191 |
return; |
1192 |
} |
1193 |
|
1194 |
|
1195 |
/*** 3. ISO2022 handlers ***/ |
1196 |
|
1197 |
/* The following note describes the coding system ISO2022 briefly. |
1198 |
Since the intention of this note is to help understand the |
1199 |
functions in this file, some parts are NOT ACCURATE or are OVERLY |
1200 |
SIMPLIFIED. For thorough understanding, please refer to the |
1201 |
original document of ISO2022. This is equivalent to the standard |
1202 |
ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
1203 |
|
1204 |
ISO2022 provides many mechanisms to encode several character sets |
1205 |
in 7-bit and 8-bit environments. For 7-bit environments, all text |
1206 |
is encoded using bytes less than 128. This may make the encoded |
1207 |
text a little bit longer, but the text passes more easily through |
1208 |
several types of gateway, some of which strip off the MSB (Most |
1209 |
Significant Bit). |
1210 |
|
1211 |
There are two kinds of character sets: control character sets and |
1212 |
graphic character sets. The former contain control characters such |
1213 |
as `newline' and `escape' to provide control functions (control |
1214 |
functions are also provided by escape sequences). The latter |
1215 |
contain graphic characters such as 'A' and '-'. Emacs recognizes |
1216 |
two control character sets and many graphic character sets. |
1217 |
|
1218 |
Graphic character sets are classified into one of the following |
1219 |
four classes, according to the number of bytes (DIMENSION) and |
1220 |
number of characters in one dimension (CHARS) of the set: |
1221 |
- DIMENSION1_CHARS94 |
1222 |
- DIMENSION1_CHARS96 |
1223 |
- DIMENSION2_CHARS94 |
1224 |
- DIMENSION2_CHARS96 |
1225 |
|
1226 |
In addition, each character set is assigned an identification tag, |
1227 |
unique for each set, called the "final character" (denoted as <F> |
1228 |
hereafter). The <F> of each character set is decided by ECMA(*) |
1229 |
when it is registered in ISO. The code range of <F> is 0x30..0x7F |
1230 |
(0x30..0x3F are for private use only). |
1231 |
|
1232 |
Note (*): ECMA = European Computer Manufacturers Association |
1233 |
|
1234 |
Here are examples of graphic character sets [NAME(<F>)]: |
1235 |
o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
1236 |
o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... |
1237 |
o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... |
1238 |
o DIMENSION2_CHARS96 -- none for the moment |
1239 |
|
1240 |
A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
1241 |
C0 [0x00..0x1F] -- control character plane 0 |
1242 |
GL [0x20..0x7F] -- graphic character plane 0 |
1243 |
C1 [0x80..0x9F] -- control character plane 1 |
1244 |
GR [0xA0..0xFF] -- graphic character plane 1 |
1245 |
|
1246 |
A control character set is directly designated and invoked to C0 or |
1247 |
C1 by an escape sequence. The most common case is that: |
1248 |
- ISO646's control character set is designated/invoked to C0, and |
1249 |
- ISO6429's control character set is designated/invoked to C1, |
1250 |
and usually these designations/invocations are omitted in encoded |
1251 |
text. In a 7-bit environment, only C0 can be used, and a control |
1252 |
character for C1 is encoded by an appropriate escape sequence to |
1253 |
fit into the environment. All control characters for C1 are |
1254 |
defined to have corresponding escape sequences. |
1255 |
|
1256 |
A graphic character set is at first designated to one of four |
1257 |
graphic registers (G0 through G3), then these graphic registers are |
1258 |
invoked to GL or GR. These designations and invocations can be |
1259 |
done independently. The most common case is that G0 is invoked to |
1260 |
GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
1261 |
these invocations and designations are omitted in encoded text. |
1262 |
In a 7-bit environment, only GL can be used. |
1263 |
|
1264 |
When a graphic character set of CHARS94 is invoked to GL, codes |
1265 |
0x20 and 0x7F of the GL area work as control characters SPACE and |
1266 |
DEL respectively, and codes 0xA0 and 0xFF of the GR area should not |
1267 |
be used. |
1268 |
|
1269 |
There are two ways of invocation: locking-shift and single-shift. |
1270 |
With locking-shift, the invocation lasts until the next different |
1271 |
invocation, whereas with single-shift, the invocation affects the |
1272 |
following character only and doesn't affect the locking-shift |
1273 |
state. Invocations are done by the following control characters or |
1274 |
escape sequences: |
1275 |
|
1276 |
---------------------------------------------------------------------- |
1277 |
abbrev function cntrl escape seq description |
1278 |
---------------------------------------------------------------------- |
1279 |
SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
1280 |
SO/LS1 (shift-out) 0x0E none invoke G1 into GL |
1281 |
LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL |
1282 |
LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL |
1283 |
LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) |
1284 |
LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) |
1285 |
LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) |
1286 |
SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char |
1287 |
SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char |
1288 |
---------------------------------------------------------------------- |
1289 |
(*) These are not used by any known coding system. |
1290 |
|
1291 |
Control characters for these functions are defined by macros |
1292 |
ISO_CODE_XXX in `coding.h'. |
1293 |
|
1294 |
Designations are done by the following escape sequences: |
1295 |
---------------------------------------------------------------------- |
1296 |
escape sequence description |
1297 |
---------------------------------------------------------------------- |
1298 |
ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 |
1299 |
ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 |
1300 |
ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 |
1301 |
ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 |
1302 |
ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) |
1303 |
ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 |
1304 |
ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 |
1305 |
ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 |
1306 |
ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) |
1307 |
ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 |
1308 |
ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 |
1309 |
ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 |
1310 |
ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) |
1311 |
ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 |
1312 |
ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 |
1313 |
ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 |
1314 |
---------------------------------------------------------------------- |
1315 |
|
1316 |
In this list, "DIMENSION1_CHARS94<F>" means a graphic character set |
1317 |
of dimension 1, chars 94, and final character <F>, etc... |
1318 |
|
1319 |
Note (*): Although these designations are not allowed in ISO2022, |
1320 |
Emacs accepts them on decoding, and produces them on encoding |
1321 |
CHARS96 character sets in a coding system which is characterized as |
1322 |
7-bit environment, non-locking-shift, and non-single-shift. |
1323 |
|
1324 |
Note (**): If <F> is '@', 'A', or 'B', the intermediate character |
1325 |
'(' can be omitted. We refer to this as "short-form" hereafter. |
1326 |
|
1327 |
Now you may notice that there are a lot of ways of encoding the |
1328 |
same multilingual text in ISO2022. Actually, there exist many |
1329 |
coding systems such as Compound Text (used in X11's inter client |
1330 |
communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
1331 |
(used in Korean Internet), EUC (Extended UNIX Code, used in Asian |
1332 |
localized platforms), and all of these are variants of ISO2022. |
1333 |
|
1334 |
In addition to the above, Emacs handles two more kinds of escape |
1335 |
sequences: ISO6429's direction specification and Emacs' private |
1336 |
sequence for specifying character composition. |
1337 |
|
1338 |
ISO6429's direction specification takes the following form: |
1339 |
o CSI ']' -- end of the current direction |
1340 |
o CSI '0' ']' -- end of the current direction |
1341 |
o CSI '1' ']' -- start of left-to-right text |
1342 |
o CSI '2' ']' -- start of right-to-left text |
1343 |
The control character CSI (0x9B: control sequence introducer) is |
1344 |
abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
1345 |
|
1346 |
Character composition specification takes the following form: |
1347 |
o ESC '0' -- start relative composition |
1348 |
o ESC '1' -- end composition |
1349 |
o ESC '2' -- start rule-base composition (*) |
1350 |
o ESC '3' -- start relative composition with alternate chars (**) |
1351 |
o ESC '4' -- start rule-base composition with alternate chars (**) |
1352 |
Since these are not standard escape sequences of any ISO standard, |
1353 |
the use of them with these meanings is restricted to Emacs only. |
1354 |
|
1355 |
(*) This form is used only in Emacs 20.5 and older versions, |
1356 |
but the newer versions can safely decode it. |
1357 |
(**) This form is used only in Emacs 21.1 and newer versions, |
1358 |
and the older versions can't decode it. |
1359 |
|
1360 |
Here's a list of example usages of these composition escape |
1361 |
sequences (categorized by `enum composition_method'). |
1362 |
|
1363 |
COMPOSITION_RELATIVE: |
1364 |
ESC 0 CHAR [ CHAR ] ESC 1 |
1365 |
COMPOSITION_WITH_RULE: |
1366 |
ESC 2 CHAR [ RULE CHAR ] ESC 1 |
1367 |
COMPOSITION_WITH_ALTCHARS: |
1368 |
ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
1369 |
COMPOSITION_WITH_RULE_ALTCHARS: |
1370 |
ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
1371 |
|
1372 |
enum iso_code_class_type iso_code_class[256]; |
1373 |
|
1374 |
#define CHARSET_OK(idx, charset, c) \ |
1375 |
(coding_system_table[idx] \ |
1376 |
&& (charset == CHARSET_ASCII \ |
1377 |
|| (safe_chars = coding_safe_chars (coding_system_table[idx]->symbol), \ |
1378 |
CODING_SAFE_CHAR_P (safe_chars, c))) \ |
1379 |
&& (CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding_system_table[idx], \ |
1380 |
charset) \ |
1381 |
!= CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION)) |
1382 |
|
1383 |
#define SHIFT_OUT_OK(idx) \ |
1384 |
(CODING_SPEC_ISO_INITIAL_DESIGNATION (coding_system_table[idx], 1) >= 0) |
1385 |
|
1386 |
#define COMPOSITION_OK(idx) \ |
1387 |
(coding_system_table[idx]->composing != COMPOSITION_DISABLED) |
1388 |
|
1389 |
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
1390 |
Check if a text is encoded in ISO2022. If it is, return an |
1391 |
integer in which appropriate flag bits any of: |
1392 |
CODING_CATEGORY_MASK_ISO_7 |
1393 |
CODING_CATEGORY_MASK_ISO_7_TIGHT |
1394 |
CODING_CATEGORY_MASK_ISO_8_1 |
1395 |
CODING_CATEGORY_MASK_ISO_8_2 |
1396 |
CODING_CATEGORY_MASK_ISO_7_ELSE |
1397 |
CODING_CATEGORY_MASK_ISO_8_ELSE |
1398 |
are set. If a code which should never appear in ISO2022 is found, |
1399 |
returns 0. */ |
1400 |
|
1401 |
static int |
1402 |
detect_coding_iso2022 (src, src_end, multibytep) |
1403 |
unsigned char *src, *src_end; |
1404 |
int multibytep; |
1405 |
{ |
1406 |
int mask = CODING_CATEGORY_MASK_ISO; |
1407 |
int mask_found = 0; |
1408 |
int reg[4], shift_out = 0, single_shifting = 0; |
1409 |
int c, c1, charset; |
1410 |
/* Dummy for ONE_MORE_BYTE. */ |
1411 |
struct coding_system dummy_coding; |
1412 |
struct coding_system *coding = &dummy_coding; |
1413 |
Lisp_Object safe_chars; |
1414 |
|
1415 |
reg[0] = CHARSET_ASCII, reg[1] = reg[2] = reg[3] = -1; |
1416 |
while (mask && src < src_end) |
1417 |
{ |
1418 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
1419 |
retry: |
1420 |
switch (c) |
1421 |
{ |
1422 |
case ISO_CODE_ESC: |
1423 |
if (inhibit_iso_escape_detection) |
1424 |
break; |
1425 |
single_shifting = 0; |
1426 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
1427 |
if (c >= '(' && c <= '/') |
1428 |
{ |
1429 |
/* Designation sequence for a charset of dimension 1. */ |
1430 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep); |
1431 |
if (c1 < ' ' || c1 >= 0x80 |
1432 |
|| (charset = iso_charset_table[0][c >= ','][c1]) < 0) |
1433 |
/* Invalid designation sequence. Just ignore. */ |
1434 |
break; |
1435 |
reg[(c - '(') % 4] = charset; |
1436 |
} |
1437 |
else if (c == '$') |
1438 |
{ |
1439 |
/* Designation sequence for a charset of dimension 2. */ |
1440 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
1441 |
if (c >= '@' && c <= 'B') |
1442 |
/* Designation for JISX0208.1978, GB2312, or JISX0208. */ |
1443 |
reg[0] = charset = iso_charset_table[1][0][c]; |
1444 |
else if (c >= '(' && c <= '/') |
1445 |
{ |
1446 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep); |
1447 |
if (c1 < ' ' || c1 >= 0x80 |
1448 |
|| (charset = iso_charset_table[1][c >= ','][c1]) < 0) |
1449 |
/* Invalid designation sequence. Just ignore. */ |
1450 |
break; |
1451 |
reg[(c - '(') % 4] = charset; |
1452 |
} |
1453 |
else |
1454 |
/* Invalid designation sequence. Just ignore. */ |
1455 |
break; |
1456 |
} |
1457 |
else if (c == 'N' || c == 'O') |
1458 |
{ |
1459 |
/* ESC <Fe> for SS2 or SS3. */ |
1460 |
mask &= CODING_CATEGORY_MASK_ISO_7_ELSE; |
1461 |
break; |
1462 |
} |
1463 |
else if (c >= '0' && c <= '4') |
1464 |
{ |
1465 |
/* ESC <Fp> for start/end composition. */ |
1466 |
if (COMPOSITION_OK (CODING_CATEGORY_IDX_ISO_7)) |
1467 |
mask_found |= CODING_CATEGORY_MASK_ISO_7; |
1468 |
else |
1469 |
mask &= ~CODING_CATEGORY_MASK_ISO_7; |
1470 |
if (COMPOSITION_OK (CODING_CATEGORY_IDX_ISO_7_TIGHT)) |
1471 |
mask_found |= CODING_CATEGORY_MASK_ISO_7_TIGHT; |
1472 |
else |
1473 |
mask &= ~CODING_CATEGORY_MASK_ISO_7_TIGHT; |
1474 |
if (COMPOSITION_OK (CODING_CATEGORY_IDX_ISO_8_1)) |
1475 |
mask_found |= CODING_CATEGORY_MASK_ISO_8_1; |
1476 |
else |
1477 |
mask &= ~CODING_CATEGORY_MASK_ISO_8_1; |
1478 |
if (COMPOSITION_OK (CODING_CATEGORY_IDX_ISO_8_2)) |
1479 |
mask_found |= CODING_CATEGORY_MASK_ISO_8_2; |
1480 |
else |
1481 |
mask &= ~CODING_CATEGORY_MASK_ISO_8_2; |
1482 |
if (COMPOSITION_OK (CODING_CATEGORY_IDX_ISO_7_ELSE)) |
1483 |
mask_found |= CODING_CATEGORY_MASK_ISO_7_ELSE; |
1484 |
else |
1485 |
mask &= ~CODING_CATEGORY_MASK_ISO_7_ELSE; |
1486 |
if (COMPOSITION_OK (CODING_CATEGORY_IDX_ISO_8_ELSE)) |
1487 |
mask_found |= CODING_CATEGORY_MASK_ISO_8_ELSE; |
1488 |
else |
1489 |
mask &= ~CODING_CATEGORY_MASK_ISO_8_ELSE; |
1490 |
break; |
1491 |
} |
1492 |
else |
1493 |
/* Invalid escape sequence. Just ignore. */ |
1494 |
break; |
1495 |
|
1496 |
/* We found a valid designation sequence for CHARSET. */ |
1497 |
mask &= ~CODING_CATEGORY_MASK_ISO_8BIT; |
1498 |
c = MAKE_CHAR (charset, 0, 0); |
1499 |
if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7, charset, c)) |
1500 |
mask_found |= CODING_CATEGORY_MASK_ISO_7; |
1501 |
else |
1502 |
mask &= ~CODING_CATEGORY_MASK_ISO_7; |
1503 |
if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7_TIGHT, charset, c)) |
1504 |
mask_found |= CODING_CATEGORY_MASK_ISO_7_TIGHT; |
1505 |
else |
1506 |
mask &= ~CODING_CATEGORY_MASK_ISO_7_TIGHT; |
1507 |
if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7_ELSE, charset, c)) |
1508 |
mask_found |= CODING_CATEGORY_MASK_ISO_7_ELSE; |
1509 |
else |
1510 |
mask &= ~CODING_CATEGORY_MASK_ISO_7_ELSE; |
1511 |
if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_8_ELSE, charset, c)) |
1512 |
mask_found |= CODING_CATEGORY_MASK_ISO_8_ELSE; |
1513 |
else |
1514 |
mask &= ~CODING_CATEGORY_MASK_ISO_8_ELSE; |
1515 |
break; |
1516 |
|
1517 |
case ISO_CODE_SO: |
1518 |
if (inhibit_iso_escape_detection) |
1519 |
break; |
1520 |
single_shifting = 0; |
1521 |
if (shift_out == 0 |
1522 |
&& (reg[1] >= 0 |
1523 |
|| SHIFT_OUT_OK (CODING_CATEGORY_IDX_ISO_7_ELSE) |
1524 |
|| SHIFT_OUT_OK (CODING_CATEGORY_IDX_ISO_8_ELSE))) |
1525 |
{ |
1526 |
/* Locking shift out. */ |
1527 |
mask &= ~CODING_CATEGORY_MASK_ISO_7BIT; |
1528 |
mask_found |= CODING_CATEGORY_MASK_ISO_SHIFT; |
1529 |
} |
1530 |
break; |
1531 |
|
1532 |
case ISO_CODE_SI: |
1533 |
if (inhibit_iso_escape_detection) |
1534 |
break; |
1535 |
single_shifting = 0; |
1536 |
if (shift_out == 1) |
1537 |
{ |
1538 |
/* Locking shift in. */ |
1539 |
mask &= ~CODING_CATEGORY_MASK_ISO_7BIT; |
1540 |
mask_found |= CODING_CATEGORY_MASK_ISO_SHIFT; |
1541 |
} |
1542 |
break; |
1543 |
|
1544 |
case ISO_CODE_CSI: |
1545 |
single_shifting = 0; |
1546 |
case ISO_CODE_SS2: |
1547 |
case ISO_CODE_SS3: |
1548 |
{ |
1549 |
int newmask = CODING_CATEGORY_MASK_ISO_8_ELSE; |
1550 |
|
1551 |
if (inhibit_iso_escape_detection) |
1552 |
break; |
1553 |
if (c != ISO_CODE_CSI) |
1554 |
{ |
1555 |
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags |
1556 |
& CODING_FLAG_ISO_SINGLE_SHIFT) |
1557 |
newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
1558 |
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags |
1559 |
& CODING_FLAG_ISO_SINGLE_SHIFT) |
1560 |
newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
1561 |
single_shifting = 1; |
1562 |
} |
1563 |
if (VECTORP (Vlatin_extra_code_table) |
1564 |
&& !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) |
1565 |
{ |
1566 |
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags |
1567 |
& CODING_FLAG_ISO_LATIN_EXTRA) |
1568 |
newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
1569 |
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags |
1570 |
& CODING_FLAG_ISO_LATIN_EXTRA) |
1571 |
newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
1572 |
} |
1573 |
mask &= newmask; |
1574 |
mask_found |= newmask; |
1575 |
} |
1576 |
break; |
1577 |
|
1578 |
default: |
1579 |
if (c < 0x80) |
1580 |
{ |
1581 |
single_shifting = 0; |
1582 |
break; |
1583 |
} |
1584 |
else if (c < 0xA0) |
1585 |
{ |
1586 |
single_shifting = 0; |
1587 |
if (VECTORP (Vlatin_extra_code_table) |
1588 |
&& !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) |
1589 |
{ |
1590 |
int newmask = 0; |
1591 |
|
1592 |
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags |
1593 |
& CODING_FLAG_ISO_LATIN_EXTRA) |
1594 |
newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
1595 |
if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags |
1596 |
& CODING_FLAG_ISO_LATIN_EXTRA) |
1597 |
newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
1598 |
mask &= newmask; |
1599 |
mask_found |= newmask; |
1600 |
} |
1601 |
else |
1602 |
return 0; |
1603 |
} |
1604 |
else |
1605 |
{ |
1606 |
mask &= ~(CODING_CATEGORY_MASK_ISO_7BIT |
1607 |
| CODING_CATEGORY_MASK_ISO_7_ELSE); |
1608 |
mask_found |= CODING_CATEGORY_MASK_ISO_8_1; |
1609 |
/* Check the length of succeeding codes of the range |
1610 |
0xA0..0FF. If the byte length is odd, we exclude |
1611 |
CODING_CATEGORY_MASK_ISO_8_2. We can check this only |
1612 |
when we are not single shifting. */ |
1613 |
if (!single_shifting |
1614 |
&& mask & CODING_CATEGORY_MASK_ISO_8_2) |
1615 |
{ |
1616 |
int i = 1; |
1617 |
|
1618 |
c = -1; |
1619 |
while (src < src_end) |
1620 |
{ |
1621 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
1622 |
if (c < 0xA0) |
1623 |
break; |
1624 |
i++; |
1625 |
} |
1626 |
|
1627 |
if (i & 1 && src < src_end) |
1628 |
mask &= ~CODING_CATEGORY_MASK_ISO_8_2; |
1629 |
else |
1630 |
mask_found |= CODING_CATEGORY_MASK_ISO_8_2; |
1631 |
if (c >= 0) |
1632 |
/* This means that we have read one extra byte. */ |
1633 |
goto retry; |
1634 |
} |
1635 |
} |
1636 |
break; |
1637 |
} |
1638 |
} |
1639 |
label_end_of_loop: |
1640 |
return (mask & mask_found); |
1641 |
} |
1642 |
|
1643 |
/* Decode a character of which charset is CHARSET, the 1st position |
1644 |
code is C1, the 2nd position code is C2, and return the decoded |
1645 |
character code. If the variable `translation_table' is non-nil, |
1646 |
returned the translated code. */ |
1647 |
|
1648 |
#define DECODE_ISO_CHARACTER(charset, c1, c2) \ |
1649 |
(NILP (translation_table) \ |
1650 |
? MAKE_CHAR (charset, c1, c2) \ |
1651 |
: translate_char (translation_table, -1, charset, c1, c2)) |
1652 |
|
1653 |
/* Set designation state into CODING. */ |
1654 |
#define DECODE_DESIGNATION(reg, dimension, chars, final_char) \ |
1655 |
do { \ |
1656 |
int charset, c; \ |
1657 |
\ |
1658 |
if (final_char < '0' || final_char >= 128) \ |
1659 |
goto label_invalid_code; \ |
1660 |
charset = ISO_CHARSET_TABLE (make_number (dimension), \ |
1661 |
make_number (chars), \ |
1662 |
make_number (final_char)); \ |
1663 |
c = MAKE_CHAR (charset, 0, 0); \ |
1664 |
if (charset >= 0 \ |
1665 |
&& (CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) == reg \ |
1666 |
|| CODING_SAFE_CHAR_P (safe_chars, c))) \ |
1667 |
{ \ |
1668 |
if (coding->spec.iso2022.last_invalid_designation_register == 0 \ |
1669 |
&& reg == 0 \ |
1670 |
&& charset == CHARSET_ASCII) \ |
1671 |
{ \ |
1672 |
/* We should insert this designation sequence as is so \ |
1673 |
that it is surely written back to a file. */ \ |
1674 |
coding->spec.iso2022.last_invalid_designation_register = -1; \ |
1675 |
goto label_invalid_code; \ |
1676 |
} \ |
1677 |
coding->spec.iso2022.last_invalid_designation_register = -1; \ |
1678 |
if ((coding->mode & CODING_MODE_DIRECTION) \ |
1679 |
&& CHARSET_REVERSE_CHARSET (charset) >= 0) \ |
1680 |
charset = CHARSET_REVERSE_CHARSET (charset); \ |
1681 |
CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \ |
1682 |
} \ |
1683 |
else \ |
1684 |
{ \ |
1685 |
coding->spec.iso2022.last_invalid_designation_register = reg; \ |
1686 |
goto label_invalid_code; \ |
1687 |
} \ |
1688 |
} while (0) |
1689 |
|
1690 |
/* Allocate a memory block for storing information about compositions. |
1691 |
The block is chained to the already allocated blocks. */ |
1692 |
|
1693 |
void |
1694 |
coding_allocate_composition_data (coding, char_offset) |
1695 |
struct coding_system *coding; |
1696 |
int char_offset; |
1697 |
{ |
1698 |
struct composition_data *cmp_data |
1699 |
= (struct composition_data *) xmalloc (sizeof *cmp_data); |
1700 |
|
1701 |
cmp_data->char_offset = char_offset; |
1702 |
cmp_data->used = 0; |
1703 |
cmp_data->prev = coding->cmp_data; |
1704 |
cmp_data->next = NULL; |
1705 |
if (coding->cmp_data) |
1706 |
coding->cmp_data->next = cmp_data; |
1707 |
coding->cmp_data = cmp_data; |
1708 |
coding->cmp_data_start = 0; |
1709 |
coding->composing = COMPOSITION_NO; |
1710 |
} |
1711 |
|
1712 |
/* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
1713 |
ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
1714 |
ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 |
1715 |
ESC 3 : altchar composition : ESC 3 ALT ... ESC 0 CHAR ... ESC 1 |
1716 |
ESC 4 : alt&rule composition : ESC 4 ALT RULE .. ALT ESC 0 CHAR ... ESC 1 |
1717 |
*/ |
1718 |
|
1719 |
#define DECODE_COMPOSITION_START(c1) \ |
1720 |
do { \ |
1721 |
if (coding->composing == COMPOSITION_DISABLED) \ |
1722 |
{ \ |
1723 |
*dst++ = ISO_CODE_ESC; \ |
1724 |
*dst++ = c1 & 0x7f; \ |
1725 |
coding->produced_char += 2; \ |
1726 |
} \ |
1727 |
else if (!COMPOSING_P (coding)) \ |
1728 |
{ \ |
1729 |
/* This is surely the start of a composition. We must be sure \ |
1730 |
that coding->cmp_data has enough space to store the \ |
1731 |
information about the composition. If not, terminate the \ |
1732 |
current decoding loop, allocate one more memory block for \ |
1733 |
coding->cmp_data in the caller, then start the decoding \ |
1734 |
loop again. We can't allocate memory here directly because \ |
1735 |
it may cause buffer/string relocation. */ \ |
1736 |
if (!coding->cmp_data \ |
1737 |
|| (coding->cmp_data->used + COMPOSITION_DATA_MAX_BUNCH_LENGTH \ |
1738 |
>= COMPOSITION_DATA_SIZE)) \ |
1739 |
{ \ |
1740 |
coding->result = CODING_FINISH_INSUFFICIENT_CMP; \ |
1741 |
goto label_end_of_loop; \ |
1742 |
} \ |
1743 |
coding->composing = (c1 == '0' ? COMPOSITION_RELATIVE \ |
1744 |
: c1 == '2' ? COMPOSITION_WITH_RULE \ |
1745 |
: c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ |
1746 |
: COMPOSITION_WITH_RULE_ALTCHARS); \ |
1747 |
CODING_ADD_COMPOSITION_START (coding, coding->produced_char, \ |
1748 |
coding->composing); \ |
1749 |
coding->composition_rule_follows = 0; \ |
1750 |
} \ |
1751 |
else \ |
1752 |
{ \ |
1753 |
/* We are already handling a composition. If the method is \ |
1754 |
the following two, the codes following the current escape \ |
1755 |
sequence are actual characters stored in a buffer. */ \ |
1756 |
if (coding->composing == COMPOSITION_WITH_ALTCHARS \ |
1757 |
|| coding->composing == COMPOSITION_WITH_RULE_ALTCHARS) \ |
1758 |
{ \ |
1759 |
coding->composing = COMPOSITION_RELATIVE; \ |
1760 |
coding->composition_rule_follows = 0; \ |
1761 |
} \ |
1762 |
} \ |
1763 |
} while (0) |
1764 |
|
1765 |
/* Handle composition end sequence ESC 1. */ |
1766 |
|
1767 |
#define DECODE_COMPOSITION_END(c1) \ |
1768 |
do { \ |
1769 |
if (! COMPOSING_P (coding)) \ |
1770 |
{ \ |
1771 |
*dst++ = ISO_CODE_ESC; \ |
1772 |
*dst++ = c1; \ |
1773 |
coding->produced_char += 2; \ |
1774 |
} \ |
1775 |
else \ |
1776 |
{ \ |
1777 |
CODING_ADD_COMPOSITION_END (coding, coding->produced_char); \ |
1778 |
coding->composing = COMPOSITION_NO; \ |
1779 |
} \ |
1780 |
} while (0) |
1781 |
|
1782 |
/* Decode a composition rule from the byte C1 (and maybe one more byte |
1783 |
from SRC) and store one encoded composition rule in |
1784 |
coding->cmp_data. */ |
1785 |
|
1786 |
#define DECODE_COMPOSITION_RULE(c1) \ |
1787 |
do { \ |
1788 |
int rule = 0; \ |
1789 |
(c1) -= 32; \ |
1790 |
if (c1 < 81) /* old format (before ver.21) */ \ |
1791 |
{ \ |
1792 |
int gref = (c1) / 9; \ |
1793 |
int nref = (c1) % 9; \ |
1794 |
if (gref == 4) gref = 10; \ |
1795 |
if (nref == 4) nref = 10; \ |
1796 |
rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
1797 |
} \ |
1798 |
else if (c1 < 93) /* new format (after ver.21) */ \ |
1799 |
{ \ |
1800 |
ONE_MORE_BYTE (c2); \ |
1801 |
rule = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
1802 |
} \ |
1803 |
CODING_ADD_COMPOSITION_COMPONENT (coding, rule); \ |
1804 |
coding->composition_rule_follows = 0; \ |
1805 |
} while (0) |
1806 |
|
1807 |
|
1808 |
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1809 |
|
1810 |
static void |
1811 |
decode_coding_iso2022 (coding, source, destination, src_bytes, dst_bytes) |
1812 |
struct coding_system *coding; |
1813 |
unsigned char *source, *destination; |
1814 |
int src_bytes, dst_bytes; |
1815 |
{ |
1816 |
unsigned char *src = source; |
1817 |
unsigned char *src_end = source + src_bytes; |
1818 |
unsigned char *dst = destination; |
1819 |
unsigned char *dst_end = destination + dst_bytes; |
1820 |
/* Charsets invoked to graphic plane 0 and 1 respectively. */ |
1821 |
int charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
1822 |
int charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1); |
1823 |
/* SRC_BASE remembers the start position in source in each loop. |
1824 |
The loop will be exited when there's not enough source code |
1825 |
(within macro ONE_MORE_BYTE), or when there's not enough |
1826 |
destination area to produce a character (within macro |
1827 |
EMIT_CHAR). */ |
1828 |
unsigned char *src_base; |
1829 |
int c, charset; |
1830 |
Lisp_Object translation_table; |
1831 |
Lisp_Object safe_chars; |
1832 |
|
1833 |
safe_chars = coding_safe_chars (coding->symbol); |
1834 |
|
1835 |
if (NILP (Venable_character_translation)) |
1836 |
translation_table = Qnil; |
1837 |
else |
1838 |
{ |
1839 |
translation_table = coding->translation_table_for_decode; |
1840 |
if (NILP (translation_table)) |
1841 |
translation_table = Vstandard_translation_table_for_decode; |
1842 |
} |
1843 |
|
1844 |
coding->result = CODING_FINISH_NORMAL; |
1845 |
|
1846 |
while (1) |
1847 |
{ |
1848 |
int c1, c2 = 0; |
1849 |
|
1850 |
src_base = src; |
1851 |
ONE_MORE_BYTE (c1); |
1852 |
|
1853 |
/* We produce no character or one character. */ |
1854 |
switch (iso_code_class [c1]) |
1855 |
{ |
1856 |
case ISO_0x20_or_0x7F: |
1857 |
if (COMPOSING_P (coding) && coding->composition_rule_follows) |
1858 |
{ |
1859 |
DECODE_COMPOSITION_RULE (c1); |
1860 |
continue; |
1861 |
} |
1862 |
if (charset0 < 0 || CHARSET_CHARS (charset0) == 94) |
1863 |
{ |
1864 |
/* This is SPACE or DEL. */ |
1865 |
charset = CHARSET_ASCII; |
1866 |
break; |
1867 |
} |
1868 |
/* This is a graphic character, we fall down ... */ |
1869 |
|
1870 |
case ISO_graphic_plane_0: |
1871 |
if (COMPOSING_P (coding) && coding->composition_rule_follows) |
1872 |
{ |
1873 |
DECODE_COMPOSITION_RULE (c1); |
1874 |
continue; |
1875 |
} |
1876 |
charset = charset0; |
1877 |
break; |
1878 |
|
1879 |
case ISO_0xA0_or_0xFF: |
1880 |
if (charset1 < 0 || CHARSET_CHARS (charset1) == 94 |
1881 |
|| coding->flags & CODING_FLAG_ISO_SEVEN_BITS) |
1882 |
goto label_invalid_code; |
1883 |
/* This is a graphic character, we fall down ... */ |
1884 |
|
1885 |
case ISO_graphic_plane_1: |
1886 |
if (charset1 < 0) |
1887 |
goto label_invalid_code; |
1888 |
charset = charset1; |
1889 |
break; |
1890 |
|
1891 |
case ISO_control_0: |
1892 |
if (COMPOSING_P (coding)) |
1893 |
DECODE_COMPOSITION_END ('1'); |
1894 |
|
1895 |
/* All ISO2022 control characters in this class have the |
1896 |
same representation in Emacs internal format. */ |
1897 |
if (c1 == '\n' |
1898 |
&& (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) |
1899 |
&& (coding->eol_type == CODING_EOL_CR |
1900 |
|| coding->eol_type == CODING_EOL_CRLF)) |
1901 |
{ |
1902 |
coding->result = CODING_FINISH_INCONSISTENT_EOL; |
1903 |
goto label_end_of_loop; |
1904 |
} |
1905 |
charset = CHARSET_ASCII; |
1906 |
break; |
1907 |
|
1908 |
case ISO_control_1: |
1909 |
if (COMPOSING_P (coding)) |
1910 |
DECODE_COMPOSITION_END ('1'); |
1911 |
goto label_invalid_code; |
1912 |
|
1913 |
case ISO_carriage_return: |
1914 |
if (COMPOSING_P (coding)) |
1915 |
DECODE_COMPOSITION_END ('1'); |
1916 |
|
1917 |
if (coding->eol_type == CODING_EOL_CR) |
1918 |
c1 = '\n'; |
1919 |
else if (coding->eol_type == CODING_EOL_CRLF) |
1920 |
{ |
1921 |
ONE_MORE_BYTE (c1); |
1922 |
if (c1 != ISO_CODE_LF) |
1923 |
{ |
1924 |
src--; |
1925 |
c1 = '\r'; |
1926 |
} |
1927 |
} |
1928 |
charset = CHARSET_ASCII; |
1929 |
break; |
1930 |
|
1931 |
case ISO_shift_out: |
1932 |
if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT) |
1933 |
|| CODING_SPEC_ISO_DESIGNATION (coding, 1) < 0) |
1934 |
goto label_invalid_code; |
1935 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 1; |
1936 |
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
1937 |
continue; |
1938 |
|
1939 |
case ISO_shift_in: |
1940 |
if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT)) |
1941 |
goto label_invalid_code; |
1942 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; |
1943 |
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
1944 |
continue; |
1945 |
|
1946 |
case ISO_single_shift_2_7: |
1947 |
case ISO_single_shift_2: |
1948 |
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)) |
1949 |
goto label_invalid_code; |
1950 |
/* SS2 is handled as an escape sequence of ESC 'N' */ |
1951 |
c1 = 'N'; |
1952 |
goto label_escape_sequence; |
1953 |
|
1954 |
case ISO_single_shift_3: |
1955 |
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)) |
1956 |
goto label_invalid_code; |
1957 |
/* SS2 is handled as an escape sequence of ESC 'O' */ |
1958 |
c1 = 'O'; |
1959 |
goto label_escape_sequence; |
1960 |
|
1961 |
case ISO_control_sequence_introducer: |
1962 |
/* CSI is handled as an escape sequence of ESC '[' ... */ |
1963 |
c1 = '['; |
1964 |
goto label_escape_sequence; |
1965 |
|
1966 |
case ISO_escape: |
1967 |
ONE_MORE_BYTE (c1); |
1968 |
label_escape_sequence: |
1969 |
/* Escape sequences handled by Emacs are invocation, |
1970 |
designation, direction specification, and character |
1971 |
composition specification. */ |
1972 |
switch (c1) |
1973 |
{ |
1974 |
case '&': /* revision of following character set */ |
1975 |
ONE_MORE_BYTE (c1); |
1976 |
if (!(c1 >= '@' && c1 <= '~')) |
1977 |
goto label_invalid_code; |
1978 |
ONE_MORE_BYTE (c1); |
1979 |
if (c1 != ISO_CODE_ESC) |
1980 |
goto label_invalid_code; |
1981 |
ONE_MORE_BYTE (c1); |
1982 |
goto label_escape_sequence; |
1983 |
|
1984 |
case '$': /* designation of 2-byte character set */ |
1985 |
if (! (coding->flags & CODING_FLAG_ISO_DESIGNATION)) |
1986 |
goto label_invalid_code; |
1987 |
ONE_MORE_BYTE (c1); |
1988 |
if (c1 >= '@' && c1 <= 'B') |
1989 |
{ /* designation of JISX0208.1978, GB2312.1980, |
1990 |
or JISX0208.1980 */ |
1991 |
DECODE_DESIGNATION (0, 2, 94, c1); |
1992 |
} |
1993 |
else if (c1 >= 0x28 && c1 <= 0x2B) |
1994 |
{ /* designation of DIMENSION2_CHARS94 character set */ |
1995 |
ONE_MORE_BYTE (c2); |
1996 |
DECODE_DESIGNATION (c1 - 0x28, 2, 94, c2); |
1997 |
} |
1998 |
else if (c1 >= 0x2C && c1 <= 0x2F) |
1999 |
{ /* designation of DIMENSION2_CHARS96 character set */ |
2000 |
ONE_MORE_BYTE (c2); |
2001 |
DECODE_DESIGNATION (c1 - 0x2C, 2, 96, c2); |
2002 |
} |
2003 |
else |
2004 |
goto label_invalid_code; |
2005 |
/* We must update these variables now. */ |
2006 |
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
2007 |
charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1); |
2008 |
continue; |
2009 |
|
2010 |
case 'n': /* invocation of locking-shift-2 */ |
2011 |
if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT) |
2012 |
|| CODING_SPEC_ISO_DESIGNATION (coding, 2) < 0) |
2013 |
goto label_invalid_code; |
2014 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 2; |
2015 |
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
2016 |
continue; |
2017 |
|
2018 |
case 'o': /* invocation of locking-shift-3 */ |
2019 |
if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT) |
2020 |
|| CODING_SPEC_ISO_DESIGNATION (coding, 3) < 0) |
2021 |
goto label_invalid_code; |
2022 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 3; |
2023 |
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
2024 |
continue; |
2025 |
|
2026 |
case 'N': /* invocation of single-shift-2 */ |
2027 |
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
2028 |
|| CODING_SPEC_ISO_DESIGNATION (coding, 2) < 0) |
2029 |
goto label_invalid_code; |
2030 |
charset = CODING_SPEC_ISO_DESIGNATION (coding, 2); |
2031 |
ONE_MORE_BYTE (c1); |
2032 |
if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
2033 |
goto label_invalid_code; |
2034 |
break; |
2035 |
|
2036 |
case 'O': /* invocation of single-shift-3 */ |
2037 |
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
2038 |
|| CODING_SPEC_ISO_DESIGNATION (coding, 3) < 0) |
2039 |
goto label_invalid_code; |
2040 |
charset = CODING_SPEC_ISO_DESIGNATION (coding, 3); |
2041 |
ONE_MORE_BYTE (c1); |
2042 |
if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
2043 |
goto label_invalid_code; |
2044 |
break; |
2045 |
|
2046 |
case '0': case '2': case '3': case '4': /* start composition */ |
2047 |
DECODE_COMPOSITION_START (c1); |
2048 |
continue; |
2049 |
|
2050 |
case '1': /* end composition */ |
2051 |
DECODE_COMPOSITION_END (c1); |
2052 |
continue; |
2053 |
|
2054 |
case '[': /* specification of direction */ |
2055 |
if (coding->flags & CODING_FLAG_ISO_NO_DIRECTION) |
2056 |
goto label_invalid_code; |
2057 |
/* For the moment, nested direction is not supported. |
2058 |
So, `coding->mode & CODING_MODE_DIRECTION' zero means |
2059 |
left-to-right, and nonzero means right-to-left. */ |
2060 |
ONE_MORE_BYTE (c1); |
2061 |
switch (c1) |
2062 |
{ |
2063 |
case ']': /* end of the current direction */ |
2064 |
coding->mode &= ~CODING_MODE_DIRECTION; |
2065 |
|
2066 |
case '0': /* end of the current direction */ |
2067 |
case '1': /* start of left-to-right direction */ |
2068 |
ONE_MORE_BYTE (c1); |
2069 |
if (c1 == ']') |
2070 |
coding->mode &= ~CODING_MODE_DIRECTION; |
2071 |
else |
2072 |
goto label_invalid_code; |
2073 |
break; |
2074 |
|
2075 |
case '2': /* start of right-to-left direction */ |
2076 |
ONE_MORE_BYTE (c1); |
2077 |
if (c1 == ']') |
2078 |
coding->mode |= CODING_MODE_DIRECTION; |
2079 |
else |
2080 |
goto label_invalid_code; |
2081 |
break; |
2082 |
|
2083 |
default: |
2084 |
goto label_invalid_code; |
2085 |
} |
2086 |
continue; |
2087 |
|
2088 |
case '%': |
2089 |
if (COMPOSING_P (coding)) |
2090 |
DECODE_COMPOSITION_END ('1'); |
2091 |
ONE_MORE_BYTE (c1); |
2092 |
if (c1 == '/') |
2093 |
{ |
2094 |
/* CTEXT extended segment: |
2095 |
ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- |
2096 |
We keep these bytes as is for the moment. |
2097 |
They may be decoded by post-read-conversion. */ |
2098 |
int dim, M, L; |
2099 |
int size, required; |
2100 |
int produced_chars; |
2101 |
|
2102 |
ONE_MORE_BYTE (dim); |
2103 |
ONE_MORE_BYTE (M); |
2104 |
ONE_MORE_BYTE (L); |
2105 |
size = ((M - 128) * 128) + (L - 128); |
2106 |
required = 8 + size * 2; |
2107 |
if (dst + required > (dst_bytes ? dst_end : src)) |
2108 |
goto label_end_of_loop; |
2109 |
*dst++ = ISO_CODE_ESC; |
2110 |
*dst++ = '%'; |
2111 |
*dst++ = '/'; |
2112 |
*dst++ = dim; |
2113 |
produced_chars = 4; |
2114 |
dst += CHAR_STRING (M, dst), produced_chars++; |
2115 |
dst += CHAR_STRING (L, dst), produced_chars++; |
2116 |
while (size-- > 0) |
2117 |
{ |
2118 |
ONE_MORE_BYTE (c1); |
2119 |
dst += CHAR_STRING (c1, dst), produced_chars++; |
2120 |
} |
2121 |
coding->produced_char += produced_chars; |
2122 |
} |
2123 |
else if (c1 == 'G') |
2124 |
{ |
2125 |
unsigned char *d = dst; |
2126 |
int produced_chars; |
2127 |
|
2128 |
/* XFree86 extension for embedding UTF-8 in CTEXT: |
2129 |
ESC % G --UTF-8-BYTES-- ESC % @ |
2130 |
We keep these bytes as is for the moment. |
2131 |
They may be decoded by post-read-conversion. */ |
2132 |
if (d + 6 > (dst_bytes ? dst_end : src)) |
2133 |
goto label_end_of_loop; |
2134 |
*d++ = ISO_CODE_ESC; |
2135 |
*d++ = '%'; |
2136 |
*d++ = 'G'; |
2137 |
produced_chars = 3; |
2138 |
while (d + 1 < (dst_bytes ? dst_end : src)) |
2139 |
{ |
2140 |
ONE_MORE_BYTE (c1); |
2141 |
if (c1 == ISO_CODE_ESC |
2142 |
&& src + 1 < src_end |
2143 |
&& src[0] == '%' |
2144 |
&& src[1] == '@') |
2145 |
{ |
2146 |
src += 2; |
2147 |
break; |
2148 |
} |
2149 |
d += CHAR_STRING (c1, d), produced_chars++; |
2150 |
} |
2151 |
if (d + 3 > (dst_bytes ? dst_end : src)) |
2152 |
goto label_end_of_loop; |
2153 |
*d++ = ISO_CODE_ESC; |
2154 |
*d++ = '%'; |
2155 |
*d++ = '@'; |
2156 |
dst = d; |
2157 |
coding->produced_char += produced_chars + 3; |
2158 |
} |
2159 |
else |
2160 |
goto label_invalid_code; |
2161 |
continue; |
2162 |
|
2163 |
default: |
2164 |
if (! (coding->flags & CODING_FLAG_ISO_DESIGNATION)) |
2165 |
goto label_invalid_code; |
2166 |
if (c1 >= 0x28 && c1 <= 0x2B) |
2167 |
{ /* designation of DIMENSION1_CHARS94 character set */ |
2168 |
ONE_MORE_BYTE (c2); |
2169 |
DECODE_DESIGNATION (c1 - 0x28, 1, 94, c2); |
2170 |
} |
2171 |
else if (c1 >= 0x2C && c1 <= 0x2F) |
2172 |
{ /* designation of DIMENSION1_CHARS96 character set */ |
2173 |
ONE_MORE_BYTE (c2); |
2174 |
DECODE_DESIGNATION (c1 - 0x2C, 1, 96, c2); |
2175 |
} |
2176 |
else |
2177 |
goto label_invalid_code; |
2178 |
/* We must update these variables now. */ |
2179 |
charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
2180 |
charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1); |
2181 |
continue; |
2182 |
} |
2183 |
} |
2184 |
|
2185 |
/* Now we know CHARSET and 1st position code C1 of a character. |
2186 |
Produce a multibyte sequence for that character while getting |
2187 |
2nd position code C2 if necessary. */ |
2188 |
if (CHARSET_DIMENSION (charset) == 2) |
2189 |
{ |
2190 |
ONE_MORE_BYTE (c2); |
2191 |
if (c1 < 0x80 ? c2 < 0x20 || c2 >= 0x80 : c2 < 0xA0) |
2192 |
/* C2 is not in a valid range. */ |
2193 |
goto label_invalid_code; |
2194 |
} |
2195 |
c = DECODE_ISO_CHARACTER (charset, c1, c2); |
2196 |
EMIT_CHAR (c); |
2197 |
continue; |
2198 |
|
2199 |
label_invalid_code: |
2200 |
coding->errors++; |
2201 |
if (COMPOSING_P (coding)) |
2202 |
DECODE_COMPOSITION_END ('1'); |
2203 |
src = src_base; |
2204 |
c = *src++; |
2205 |
EMIT_CHAR (c); |
2206 |
} |
2207 |
|
2208 |
label_end_of_loop: |
2209 |
coding->consumed = coding->consumed_char = src_base - source; |
2210 |
coding->produced = dst - destination; |
2211 |
return; |
2212 |
} |
2213 |
|
2214 |
|
2215 |
/* ISO2022 encoding stuff. */ |
2216 |
|
2217 |
/* |
2218 |
It is not enough to say just "ISO2022" on encoding, we have to |
2219 |
specify more details. In Emacs, each ISO2022 coding system |
2220 |
variant has the following specifications: |
2221 |
1. Initial designation to G0 through G3. |
2222 |
2. Allows short-form designation? |
2223 |
3. ASCII should be designated to G0 before control characters? |
2224 |
4. ASCII should be designated to G0 at end of line? |
2225 |
5. 7-bit environment or 8-bit environment? |
2226 |
6. Use locking-shift? |
2227 |
7. Use Single-shift? |
2228 |
And the following two are only for Japanese: |
2229 |
8. Use ASCII in place of JIS0201-1976-Roman? |
2230 |
9. Use JISX0208-1983 in place of JISX0208-1978? |
2231 |
These specifications are encoded in `coding->flags' as flag bits |
2232 |
defined by macros CODING_FLAG_ISO_XXX. See `coding.h' for more |
2233 |
details. |
2234 |
*/ |
2235 |
|
2236 |
/* Produce codes (escape sequence) for designating CHARSET to graphic |
2237 |
register REG at DST, and increment DST. If <final-char> of CHARSET is |
2238 |
'@', 'A', or 'B' and the coding system CODING allows, produce |
2239 |
designation sequence of short-form. */ |
2240 |
|
2241 |
#define ENCODE_DESIGNATION(charset, reg, coding) \ |
2242 |
do { \ |
2243 |
unsigned char final_char = CHARSET_ISO_FINAL_CHAR (charset); \ |
2244 |
char *intermediate_char_94 = "()*+"; \ |
2245 |
char *intermediate_char_96 = ",-./"; \ |
2246 |
int revision = CODING_SPEC_ISO_REVISION_NUMBER(coding, charset); \ |
2247 |
\ |
2248 |
if (revision < 255) \ |
2249 |
{ \ |
2250 |
*dst++ = ISO_CODE_ESC; \ |
2251 |
*dst++ = '&'; \ |
2252 |
*dst++ = '@' + revision; \ |
2253 |
} \ |
2254 |
*dst++ = ISO_CODE_ESC; \ |
2255 |
if (CHARSET_DIMENSION (charset) == 1) \ |
2256 |
{ \ |
2257 |
if (CHARSET_CHARS (charset) == 94) \ |
2258 |
*dst++ = (unsigned char) (intermediate_char_94[reg]); \ |
2259 |
else \ |
2260 |
*dst++ = (unsigned char) (intermediate_char_96[reg]); \ |
2261 |
} \ |
2262 |
else \ |
2263 |
{ \ |
2264 |
*dst++ = '$'; \ |
2265 |
if (CHARSET_CHARS (charset) == 94) \ |
2266 |
{ \ |
2267 |
if (! (coding->flags & CODING_FLAG_ISO_SHORT_FORM) \ |
2268 |
|| reg != 0 \ |
2269 |
|| final_char < '@' || final_char > 'B') \ |
2270 |
*dst++ = (unsigned char) (intermediate_char_94[reg]); \ |
2271 |
} \ |
2272 |
else \ |
2273 |
*dst++ = (unsigned char) (intermediate_char_96[reg]); \ |
2274 |
} \ |
2275 |
*dst++ = final_char; \ |
2276 |
CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \ |
2277 |
} while (0) |
2278 |
|
2279 |
/* The following two macros produce codes (control character or escape |
2280 |
sequence) for ISO2022 single-shift functions (single-shift-2 and |
2281 |
single-shift-3). */ |
2282 |
|
2283 |
#define ENCODE_SINGLE_SHIFT_2 \ |
2284 |
do { \ |
2285 |
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
2286 |
*dst++ = ISO_CODE_ESC, *dst++ = 'N'; \ |
2287 |
else \ |
2288 |
*dst++ = ISO_CODE_SS2; \ |
2289 |
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \ |
2290 |
} while (0) |
2291 |
|
2292 |
#define ENCODE_SINGLE_SHIFT_3 \ |
2293 |
do { \ |
2294 |
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
2295 |
*dst++ = ISO_CODE_ESC, *dst++ = 'O'; \ |
2296 |
else \ |
2297 |
*dst++ = ISO_CODE_SS3; \ |
2298 |
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \ |
2299 |
} while (0) |
2300 |
|
2301 |
/* The following four macros produce codes (control character or |
2302 |
escape sequence) for ISO2022 locking-shift functions (shift-in, |
2303 |
shift-out, locking-shift-2, and locking-shift-3). */ |
2304 |
|
2305 |
#define ENCODE_SHIFT_IN \ |
2306 |
do { \ |
2307 |
*dst++ = ISO_CODE_SI; \ |
2308 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; \ |
2309 |
} while (0) |
2310 |
|
2311 |
#define ENCODE_SHIFT_OUT \ |
2312 |
do { \ |
2313 |
*dst++ = ISO_CODE_SO; \ |
2314 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 1; \ |
2315 |
} while (0) |
2316 |
|
2317 |
#define ENCODE_LOCKING_SHIFT_2 \ |
2318 |
do { \ |
2319 |
*dst++ = ISO_CODE_ESC, *dst++ = 'n'; \ |
2320 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 2; \ |
2321 |
} while (0) |
2322 |
|
2323 |
#define ENCODE_LOCKING_SHIFT_3 \ |
2324 |
do { \ |
2325 |
*dst++ = ISO_CODE_ESC, *dst++ = 'o'; \ |
2326 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 3; \ |
2327 |
} while (0) |
2328 |
|
2329 |
/* Produce codes for a DIMENSION1 character whose character set is |
2330 |
CHARSET and whose position-code is C1. Designation and invocation |
2331 |
sequences are also produced in advance if necessary. */ |
2332 |
|
2333 |
#define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
2334 |
do { \ |
2335 |
if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \ |
2336 |
{ \ |
2337 |
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
2338 |
*dst++ = c1 & 0x7F; \ |
2339 |
else \ |
2340 |
*dst++ = c1 | 0x80; \ |
2341 |
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \ |
2342 |
break; \ |
2343 |
} \ |
2344 |
else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \ |
2345 |
{ \ |
2346 |
*dst++ = c1 & 0x7F; \ |
2347 |
break; \ |
2348 |
} \ |
2349 |
else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \ |
2350 |
{ \ |
2351 |
*dst++ = c1 | 0x80; \ |
2352 |
break; \ |
2353 |
} \ |
2354 |
else \ |
2355 |
/* Since CHARSET is not yet invoked to any graphic planes, we \ |
2356 |
must invoke it, or, at first, designate it to some graphic \ |
2357 |
register. Then repeat the loop to actually produce the \ |
2358 |
character. */ \ |
2359 |
dst = encode_invocation_designation (charset, coding, dst); \ |
2360 |
} while (1) |
2361 |
|
2362 |
/* Produce codes for a DIMENSION2 character whose character set is |
2363 |
CHARSET and whose position-codes are C1 and C2. Designation and |
2364 |
invocation codes are also produced in advance if necessary. */ |
2365 |
|
2366 |
#define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
2367 |
do { \ |
2368 |
if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \ |
2369 |
{ \ |
2370 |
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
2371 |
*dst++ = c1 & 0x7F, *dst++ = c2 & 0x7F; \ |
2372 |
else \ |
2373 |
*dst++ = c1 | 0x80, *dst++ = c2 | 0x80; \ |
2374 |
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \ |
2375 |
break; \ |
2376 |
} \ |
2377 |
else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \ |
2378 |
{ \ |
2379 |
*dst++ = c1 & 0x7F, *dst++= c2 & 0x7F; \ |
2380 |
break; \ |
2381 |
} \ |
2382 |
else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \ |
2383 |
{ \ |
2384 |
*dst++ = c1 | 0x80, *dst++= c2 | 0x80; \ |
2385 |
break; \ |
2386 |
} \ |
2387 |
else \ |
2388 |
/* Since CHARSET is not yet invoked to any graphic planes, we \ |
2389 |
must invoke it, or, at first, designate it to some graphic \ |
2390 |
register. Then repeat the loop to actually produce the \ |
2391 |
character. */ \ |
2392 |
dst = encode_invocation_designation (charset, coding, dst); \ |
2393 |
} while (1) |
2394 |
|
2395 |
#define ENCODE_ISO_CHARACTER(c) \ |
2396 |
do { \ |
2397 |
int charset, c1, c2; \ |
2398 |
\ |
2399 |
SPLIT_CHAR (c, charset, c1, c2); \ |
2400 |
if (CHARSET_DEFINED_P (charset)) \ |
2401 |
{ \ |
2402 |
if (CHARSET_DIMENSION (charset) == 1) \ |
2403 |
{ \ |
2404 |
if (charset == CHARSET_ASCII \ |
2405 |
&& coding->flags & CODING_FLAG_ISO_USE_ROMAN) \ |
2406 |
charset = charset_latin_jisx0201; \ |
2407 |
ENCODE_ISO_CHARACTER_DIMENSION1 (charset, c1); \ |
2408 |
} \ |
2409 |
else \ |
2410 |
{ \ |
2411 |
if (charset == charset_jisx0208 \ |
2412 |
&& coding->flags & CODING_FLAG_ISO_USE_OLDJIS) \ |
2413 |
charset = charset_jisx0208_1978; \ |
2414 |
ENCODE_ISO_CHARACTER_DIMENSION2 (charset, c1, c2); \ |
2415 |
} \ |
2416 |
} \ |
2417 |
else \ |
2418 |
{ \ |
2419 |
*dst++ = c1; \ |
2420 |
if (c2 >= 0) \ |
2421 |
*dst++ = c2; \ |
2422 |
} \ |
2423 |
} while (0) |
2424 |
|
2425 |
|
2426 |
/* Instead of encoding character C, produce one or two `?'s. */ |
2427 |
|
2428 |
#define ENCODE_UNSAFE_CHARACTER(c) \ |
2429 |
do { \ |
2430 |
ENCODE_ISO_CHARACTER (CODING_REPLACEMENT_CHARACTER); \ |
2431 |
if (CHARSET_WIDTH (CHAR_CHARSET (c)) > 1) \ |
2432 |
ENCODE_ISO_CHARACTER (CODING_REPLACEMENT_CHARACTER); \ |
2433 |
} while (0) |
2434 |
|
2435 |
|
2436 |
/* Produce designation and invocation codes at a place pointed by DST |
2437 |
to use CHARSET. The element `spec.iso2022' of *CODING is updated. |
2438 |
Return new DST. */ |
2439 |
|
2440 |
unsigned char * |
2441 |
encode_invocation_designation (charset, coding, dst) |
2442 |
int charset; |
2443 |
struct coding_system *coding; |
2444 |
unsigned char *dst; |
2445 |
{ |
2446 |
int reg; /* graphic register number */ |
2447 |
|
2448 |
/* At first, check designations. */ |
2449 |
for (reg = 0; reg < 4; reg++) |
2450 |
if (charset == CODING_SPEC_ISO_DESIGNATION (coding, reg)) |
2451 |
break; |
2452 |
|
2453 |
if (reg >= 4) |
2454 |
{ |
2455 |
/* CHARSET is not yet designated to any graphic registers. */ |
2456 |
/* At first check the requested designation. */ |
2457 |
reg = CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset); |
2458 |
if (reg == CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION) |
2459 |
/* Since CHARSET requests no special designation, designate it |
2460 |
to graphic register 0. */ |
2461 |
reg = 0; |
2462 |
|
2463 |
ENCODE_DESIGNATION (charset, reg, coding); |
2464 |
} |
2465 |
|
2466 |
if (CODING_SPEC_ISO_INVOCATION (coding, 0) != reg |
2467 |
&& CODING_SPEC_ISO_INVOCATION (coding, 1) != reg) |
2468 |
{ |
2469 |
/* Since the graphic register REG is not invoked to any graphic |
2470 |
planes, invoke it to graphic plane 0. */ |
2471 |
switch (reg) |
2472 |
{ |
2473 |
case 0: /* graphic register 0 */ |
2474 |
ENCODE_SHIFT_IN; |
2475 |
break; |
2476 |
|
2477 |
case 1: /* graphic register 1 */ |
2478 |
ENCODE_SHIFT_OUT; |
2479 |
break; |
2480 |
|
2481 |
case 2: /* graphic register 2 */ |
2482 |
if (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
2483 |
ENCODE_SINGLE_SHIFT_2; |
2484 |
else |
2485 |
ENCODE_LOCKING_SHIFT_2; |
2486 |
break; |
2487 |
|
2488 |
case 3: /* graphic register 3 */ |
2489 |
if (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
2490 |
ENCODE_SINGLE_SHIFT_3; |
2491 |
else |
2492 |
ENCODE_LOCKING_SHIFT_3; |
2493 |
break; |
2494 |
} |
2495 |
} |
2496 |
|
2497 |
return dst; |
2498 |
} |
2499 |
|
2500 |
/* Produce 2-byte codes for encoded composition rule RULE. */ |
2501 |
|
2502 |
#define ENCODE_COMPOSITION_RULE(rule) \ |
2503 |
do { \ |
2504 |
int gref, nref; \ |
2505 |
COMPOSITION_DECODE_RULE (rule, gref, nref); \ |
2506 |
*dst++ = 32 + 81 + gref; \ |
2507 |
*dst++ = 32 + nref; \ |
2508 |
} while (0) |
2509 |
|
2510 |
/* Produce codes for indicating the start of a composition sequence |
2511 |
(ESC 0, ESC 3, or ESC 4). DATA points to an array of integers |
2512 |
which specify information about the composition. See the comment |
2513 |
in coding.h for the format of DATA. */ |
2514 |
|
2515 |
#define ENCODE_COMPOSITION_START(coding, data) \ |
2516 |
do { \ |
2517 |
coding->composing = data[3]; \ |
2518 |
*dst++ = ISO_CODE_ESC; \ |
2519 |
if (coding->composing == COMPOSITION_RELATIVE) \ |
2520 |
*dst++ = '0'; \ |
2521 |
else \ |
2522 |
{ \ |
2523 |
*dst++ = (coding->composing == COMPOSITION_WITH_ALTCHARS \ |
2524 |
? '3' : '4'); \ |
2525 |
coding->cmp_data_index = coding->cmp_data_start + 4; \ |
2526 |
coding->composition_rule_follows = 0; \ |
2527 |
} \ |
2528 |
} while (0) |
2529 |
|
2530 |
/* Produce codes for indicating the end of the current composition. */ |
2531 |
|
2532 |
#define ENCODE_COMPOSITION_END(coding, data) \ |
2533 |
do { \ |
2534 |
*dst++ = ISO_CODE_ESC; \ |
2535 |
*dst++ = '1'; \ |
2536 |
coding->cmp_data_start += data[0]; \ |
2537 |
coding->composing = COMPOSITION_NO; \ |
2538 |
if (coding->cmp_data_start == coding->cmp_data->used \ |
2539 |
&& coding->cmp_data->next) \ |
2540 |
{ \ |
2541 |
coding->cmp_data = coding->cmp_data->next; \ |
2542 |
coding->cmp_data_start = 0; \ |
2543 |
} \ |
2544 |
} while (0) |
2545 |
|
2546 |
/* Produce composition start sequence ESC 0. Here, this sequence |
2547 |
doesn't mean the start of a new composition but means that we have |
2548 |
just produced components (alternate chars and composition rules) of |
2549 |
the composition and the actual text follows in SRC. */ |
2550 |
|
2551 |
#define ENCODE_COMPOSITION_FAKE_START(coding) \ |
2552 |
do { \ |
2553 |
*dst++ = ISO_CODE_ESC; \ |
2554 |
*dst++ = '0'; \ |
2555 |
coding->composing = COMPOSITION_RELATIVE; \ |
2556 |
} while (0) |
2557 |
|
2558 |
/* The following three macros produce codes for indicating direction |
2559 |
of text. */ |
2560 |
#define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ |
2561 |
do { \ |
2562 |
if (coding->flags == CODING_FLAG_ISO_SEVEN_BITS) \ |
2563 |
*dst++ = ISO_CODE_ESC, *dst++ = '['; \ |
2564 |
else \ |
2565 |
*dst++ = ISO_CODE_CSI; \ |
2566 |
} while (0) |
2567 |
|
2568 |
#define ENCODE_DIRECTION_R2L \ |
2569 |
ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst), *dst++ = '2', *dst++ = ']' |
2570 |
|
2571 |
#define ENCODE_DIRECTION_L2R \ |
2572 |
ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst), *dst++ = '0', *dst++ = ']' |
2573 |
|
2574 |
/* Produce codes for designation and invocation to reset the graphic |
2575 |
planes and registers to initial state. */ |
2576 |
#define ENCODE_RESET_PLANE_AND_REGISTER \ |
2577 |
do { \ |
2578 |
int reg; \ |
2579 |
if (CODING_SPEC_ISO_INVOCATION (coding, 0) != 0) \ |
2580 |
ENCODE_SHIFT_IN; \ |
2581 |
for (reg = 0; reg < 4; reg++) \ |
2582 |
if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg) >= 0 \ |
2583 |
&& (CODING_SPEC_ISO_DESIGNATION (coding, reg) \ |
2584 |
!= CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg))) \ |
2585 |
ENCODE_DESIGNATION \ |
2586 |
(CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg), reg, coding); \ |
2587 |
} while (0) |
2588 |
|
2589 |
/* Produce designation sequences of charsets in the line started from |
2590 |
SRC to a place pointed by DST, and return updated DST. |
2591 |
|
2592 |
If the current block ends before any end-of-line, we may fail to |
2593 |
find all the necessary designations. */ |
2594 |
|
2595 |
static unsigned char * |
2596 |
encode_designation_at_bol (coding, translation_table, src, src_end, dst) |
2597 |
struct coding_system *coding; |
2598 |
Lisp_Object translation_table; |
2599 |
unsigned char *src, *src_end, *dst; |
2600 |
{ |
2601 |
int charset, c, found = 0, reg; |
2602 |
/* Table of charsets to be designated to each graphic register. */ |
2603 |
int r[4]; |
2604 |
|
2605 |
for (reg = 0; reg < 4; reg++) |
2606 |
r[reg] = -1; |
2607 |
|
2608 |
while (found < 4) |
2609 |
{ |
2610 |
ONE_MORE_CHAR (c); |
2611 |
if (c == '\n') |
2612 |
break; |
2613 |
|
2614 |
charset = CHAR_CHARSET (c); |
2615 |
reg = CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset); |
2616 |
if (reg != CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION && r[reg] < 0) |
2617 |
{ |
2618 |
found++; |
2619 |
r[reg] = charset; |
2620 |
} |
2621 |
} |
2622 |
|
2623 |
label_end_of_loop: |
2624 |
if (found) |
2625 |
{ |
2626 |
for (reg = 0; reg < 4; reg++) |
2627 |
if (r[reg] >= 0 |
2628 |
&& CODING_SPEC_ISO_DESIGNATION (coding, reg) != r[reg]) |
2629 |
ENCODE_DESIGNATION (r[reg], reg, coding); |
2630 |
} |
2631 |
|
2632 |
return dst; |
2633 |
} |
2634 |
|
2635 |
/* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
2636 |
|
2637 |
static void |
2638 |
encode_coding_iso2022 (coding, source, destination, src_bytes, dst_bytes) |
2639 |
struct coding_system *coding; |
2640 |
unsigned char *source, *destination; |
2641 |
int src_bytes, dst_bytes; |
2642 |
{ |
2643 |
unsigned char *src = source; |
2644 |
unsigned char *src_end = source + src_bytes; |
2645 |
unsigned char *dst = destination; |
2646 |
unsigned char *dst_end = destination + dst_bytes; |
2647 |
/* Since the maximum bytes produced by each loop is 20, we subtract 19 |
2648 |
from DST_END to assure overflow checking is necessary only at the |
2649 |
head of loop. */ |
2650 |
unsigned char *adjusted_dst_end = dst_end - 19; |
2651 |
/* SRC_BASE remembers the start position in source in each loop. |
2652 |
The loop will be exited when there's not enough source text to |
2653 |
analyze multi-byte codes (within macro ONE_MORE_CHAR), or when |
2654 |
there's not enough destination area to produce encoded codes |
2655 |
(within macro EMIT_BYTES). */ |
2656 |
unsigned char *src_base; |
2657 |
int c; |
2658 |
Lisp_Object translation_table; |
2659 |
Lisp_Object safe_chars; |
2660 |
|
2661 |
if (coding->flags & CODING_FLAG_ISO_SAFE) |
2662 |
coding->mode |= CODING_MODE_INHIBIT_UNENCODABLE_CHAR; |
2663 |
|
2664 |
safe_chars = coding_safe_chars (coding->symbol); |
2665 |
|
2666 |
if (NILP (Venable_character_translation)) |
2667 |
translation_table = Qnil; |
2668 |
else |
2669 |
{ |
2670 |
translation_table = coding->translation_table_for_encode; |
2671 |
if (NILP (translation_table)) |
2672 |
translation_table = Vstandard_translation_table_for_encode; |
2673 |
} |
2674 |
|
2675 |
coding->consumed_char = 0; |
2676 |
coding->errors = 0; |
2677 |
while (1) |
2678 |
{ |
2679 |
src_base = src; |
2680 |
|
2681 |
if (dst >= (dst_bytes ? adjusted_dst_end : (src - 19))) |
2682 |
{ |
2683 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; |
2684 |
break; |
2685 |
} |
2686 |
|
2687 |
if (coding->flags & CODING_FLAG_ISO_DESIGNATE_AT_BOL |
2688 |
&& CODING_SPEC_ISO_BOL (coding)) |
2689 |
{ |
2690 |
/* We have to produce designation sequences if any now. */ |
2691 |
dst = encode_designation_at_bol (coding, translation_table, |
2692 |
src, src_end, dst); |
2693 |
CODING_SPEC_ISO_BOL (coding) = 0; |
2694 |
} |
2695 |
|
2696 |
/* Check composition start and end. */ |
2697 |
if (coding->composing != COMPOSITION_DISABLED |
2698 |
&& coding->cmp_data_start < coding->cmp_data->used) |
2699 |
{ |
2700 |
struct composition_data *cmp_data = coding->cmp_data; |
2701 |
int *data = cmp_data->data + coding->cmp_data_start; |
2702 |
int this_pos = cmp_data->char_offset + coding->consumed_char; |
2703 |
|
2704 |
if (coding->composing == COMPOSITION_RELATIVE) |
2705 |
{ |
2706 |
if (this_pos == data[2]) |
2707 |
{ |
2708 |
ENCODE_COMPOSITION_END (coding, data); |
2709 |
cmp_data = coding->cmp_data; |
2710 |
data = cmp_data->data + coding->cmp_data_start; |
2711 |
} |
2712 |
} |
2713 |
else if (COMPOSING_P (coding)) |
2714 |
{ |
2715 |
/* COMPOSITION_WITH_ALTCHARS or COMPOSITION_WITH_RULE_ALTCHAR */ |
2716 |
if (coding->cmp_data_index == coding->cmp_data_start + data[0]) |
2717 |
/* We have consumed components of the composition. |
2718 |
What follows in SRC is the composition's base |
2719 |
text. */ |
2720 |
ENCODE_COMPOSITION_FAKE_START (coding); |
2721 |
else |
2722 |
{ |
2723 |
int c = cmp_data->data[coding->cmp_data_index++]; |
2724 |
if (coding->composition_rule_follows) |
2725 |
{ |
2726 |
ENCODE_COMPOSITION_RULE (c); |
2727 |
coding->composition_rule_follows = 0; |
2728 |
} |
2729 |
else |
2730 |
{ |
2731 |
if (coding->mode & CODING_MODE_INHIBIT_UNENCODABLE_CHAR |
2732 |
&& ! CODING_SAFE_CHAR_P (safe_chars, c)) |
2733 |
ENCODE_UNSAFE_CHARACTER (c); |
2734 |
else |
2735 |
ENCODE_ISO_CHARACTER (c); |
2736 |
if (coding->composing == COMPOSITION_WITH_RULE_ALTCHARS) |
2737 |
coding->composition_rule_follows = 1; |
2738 |
} |
2739 |
continue; |
2740 |
} |
2741 |
} |
2742 |
if (!COMPOSING_P (coding)) |
2743 |
{ |
2744 |
if (this_pos == data[1]) |
2745 |
{ |
2746 |
ENCODE_COMPOSITION_START (coding, data); |
2747 |
continue; |
2748 |
} |
2749 |
} |
2750 |
} |
2751 |
|
2752 |
ONE_MORE_CHAR (c); |
2753 |
|
2754 |
/* Now encode the character C. */ |
2755 |
if (c < 0x20 || c == 0x7F) |
2756 |
{ |
2757 |
if (c == '\r') |
2758 |
{ |
2759 |
if (! (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
2760 |
{ |
2761 |
if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL) |
2762 |
ENCODE_RESET_PLANE_AND_REGISTER; |
2763 |
*dst++ = c; |
2764 |
continue; |
2765 |
} |
2766 |
/* fall down to treat '\r' as '\n' ... */ |
2767 |
c = '\n'; |
2768 |
} |
2769 |
if (c == '\n') |
2770 |
{ |
2771 |
if (coding->flags & CODING_FLAG_ISO_RESET_AT_EOL) |
2772 |
ENCODE_RESET_PLANE_AND_REGISTER; |
2773 |
if (coding->flags & CODING_FLAG_ISO_INIT_AT_BOL) |
2774 |
bcopy (coding->spec.iso2022.initial_designation, |
2775 |
coding->spec.iso2022.current_designation, |
2776 |
sizeof coding->spec.iso2022.initial_designation); |
2777 |
if (coding->eol_type == CODING_EOL_LF |
2778 |
|| coding->eol_type == CODING_EOL_UNDECIDED) |
2779 |
*dst++ = ISO_CODE_LF; |
2780 |
else if (coding->eol_type == CODING_EOL_CRLF) |
2781 |
*dst++ = ISO_CODE_CR, *dst++ = ISO_CODE_LF; |
2782 |
else |
2783 |
*dst++ = ISO_CODE_CR; |
2784 |
CODING_SPEC_ISO_BOL (coding) = 1; |
2785 |
} |
2786 |
else |
2787 |
{ |
2788 |
if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL) |
2789 |
ENCODE_RESET_PLANE_AND_REGISTER; |
2790 |
*dst++ = c; |
2791 |
} |
2792 |
} |
2793 |
else if (ASCII_BYTE_P (c)) |
2794 |
ENCODE_ISO_CHARACTER (c); |
2795 |
else if (SINGLE_BYTE_CHAR_P (c)) |
2796 |
{ |
2797 |
*dst++ = c; |
2798 |
coding->errors++; |
2799 |
} |
2800 |
else if (coding->mode & CODING_MODE_INHIBIT_UNENCODABLE_CHAR |
2801 |
&& ! CODING_SAFE_CHAR_P (safe_chars, c)) |
2802 |
ENCODE_UNSAFE_CHARACTER (c); |
2803 |
else |
2804 |
ENCODE_ISO_CHARACTER (c); |
2805 |
|
2806 |
coding->consumed_char++; |
2807 |
} |
2808 |
|
2809 |
label_end_of_loop: |
2810 |
coding->consumed = src_base - source; |
2811 |
coding->produced = coding->produced_char = dst - destination; |
2812 |
} |
2813 |
|
2814 |
|
2815 |
/*** 4. SJIS and BIG5 handlers ***/ |
2816 |
|
2817 |
/* Although SJIS and BIG5 are not ISO coding systems, they are used |
2818 |
quite widely. So, for the moment, Emacs supports them in the bare |
2819 |
C code. But, in the future, they may be supported only by CCL. */ |
2820 |
|
2821 |
/* SJIS is a coding system encoding three character sets: ASCII, right |
2822 |
half of JISX0201-Kana, and JISX0208. An ASCII character is encoded |
2823 |
as is. A character of charset katakana-jisx0201 is encoded by |
2824 |
"position-code + 0x80". A character of charset japanese-jisx0208 |
2825 |
is encoded in 2-byte but two position-codes are divided and shifted |
2826 |
so that it fits in the range below. |
2827 |
|
2828 |
--- CODE RANGE of SJIS --- |
2829 |
(character set) (range) |
2830 |
ASCII 0x00 .. 0x7F |
2831 |
KATAKANA-JISX0201 0xA1 .. 0xDF |
2832 |
JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
2833 |
(2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
2834 |
------------------------------- |
2835 |
|
2836 |
*/ |
2837 |
|
2838 |
/* BIG5 is a coding system encoding two character sets: ASCII and |
2839 |
Big5. An ASCII character is encoded as is. Big5 is a two-byte |
2840 |
character set and is encoded in two bytes. |
2841 |
|
2842 |
--- CODE RANGE of BIG5 --- |
2843 |
(character set) (range) |
2844 |
ASCII 0x00 .. 0x7F |
2845 |
Big5 (1st byte) 0xA1 .. 0xFE |
2846 |
(2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE |
2847 |
-------------------------- |
2848 |
|
2849 |
Since the number of characters in Big5 is larger than maximum |
2850 |
characters in Emacs' charset (96x96), it can't be handled as one |
2851 |
charset. So, in Emacs, Big5 is divided into two: `charset-big5-1' |
2852 |
and `charset-big5-2'. Both are DIMENSION2 and CHARS94. The former |
2853 |
contains frequently used characters and the latter contains less |
2854 |
frequently used characters. */ |
2855 |
|
2856 |
/* Macros to decode or encode a character of Big5 in BIG5. B1 and B2 |
2857 |
are the 1st and 2nd position-codes of Big5 in BIG5 coding system. |
2858 |
C1 and C2 are the 1st and 2nd position-codes of Emacs' internal |
2859 |
format. CHARSET is `charset_big5_1' or `charset_big5_2'. */ |
2860 |
|
2861 |
/* Number of Big5 characters which have the same code in 1st byte. */ |
2862 |
#define BIG5_SAME_ROW (0xFF - 0xA1 + 0x7F - 0x40) |
2863 |
|
2864 |
#define DECODE_BIG5(b1, b2, charset, c1, c2) \ |
2865 |
do { \ |
2866 |
unsigned int temp \ |
2867 |
= (b1 - 0xA1) * BIG5_SAME_ROW + b2 - (b2 < 0x7F ? 0x40 : 0x62); \ |
2868 |
if (b1 < 0xC9) \ |
2869 |
charset = charset_big5_1; \ |
2870 |
else \ |
2871 |
{ \ |
2872 |
charset = charset_big5_2; \ |
2873 |
temp -= (0xC9 - 0xA1) * BIG5_SAME_ROW; \ |
2874 |
} \ |
2875 |
c1 = temp / (0xFF - 0xA1) + 0x21; \ |
2876 |
c2 = temp % (0xFF - 0xA1) + 0x21; \ |
2877 |
} while (0) |
2878 |
|
2879 |
#define ENCODE_BIG5(charset, c1, c2, b1, b2) \ |
2880 |
do { \ |
2881 |
unsigned int temp = (c1 - 0x21) * (0xFF - 0xA1) + (c2 - 0x21); \ |
2882 |
if (charset == charset_big5_2) \ |
2883 |
temp += BIG5_SAME_ROW * (0xC9 - 0xA1); \ |
2884 |
b1 = temp / BIG5_SAME_ROW + 0xA1; \ |
2885 |
b2 = temp % BIG5_SAME_ROW; \ |
2886 |
b2 += b2 < 0x3F ? 0x40 : 0x62; \ |
2887 |
} while (0) |
2888 |
|
2889 |
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
2890 |
Check if a text is encoded in SJIS. If it is, return |
2891 |
CODING_CATEGORY_MASK_SJIS, else return 0. */ |
2892 |
|
2893 |
static int |
2894 |
detect_coding_sjis (src, src_end, multibytep) |
2895 |
unsigned char *src, *src_end; |
2896 |
int multibytep; |
2897 |
{ |
2898 |
int c; |
2899 |
/* Dummy for ONE_MORE_BYTE. */ |
2900 |
struct coding_system dummy_coding; |
2901 |
struct coding_system *coding = &dummy_coding; |
2902 |
|
2903 |
while (1) |
2904 |
{ |
2905 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
2906 |
if (c < 0x80) |
2907 |
continue; |
2908 |
if (c == 0x80 || c == 0xA0 || c > 0xEF) |
2909 |
return 0; |
2910 |
if (c <= 0x9F || c >= 0xE0) |
2911 |
{ |
2912 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
2913 |
if (c < 0x40 || c == 0x7F || c > 0xFC) |
2914 |
return 0; |
2915 |
} |
2916 |
} |
2917 |
label_end_of_loop: |
2918 |
return CODING_CATEGORY_MASK_SJIS; |
2919 |
} |
2920 |
|
2921 |
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
2922 |
Check if a text is encoded in BIG5. If it is, return |
2923 |
CODING_CATEGORY_MASK_BIG5, else return 0. */ |
2924 |
|
2925 |
static int |
2926 |
detect_coding_big5 (src, src_end, multibytep) |
2927 |
unsigned char *src, *src_end; |
2928 |
int multibytep; |
2929 |
{ |
2930 |
int c; |
2931 |
/* Dummy for ONE_MORE_BYTE. */ |
2932 |
struct coding_system dummy_coding; |
2933 |
struct coding_system *coding = &dummy_coding; |
2934 |
|
2935 |
while (1) |
2936 |
{ |
2937 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
2938 |
if (c < 0x80) |
2939 |
continue; |
2940 |
if (c < 0xA1 || c > 0xFE) |
2941 |
return 0; |
2942 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
2943 |
if (c < 0x40 || (c > 0x7F && c < 0xA1) || c > 0xFE) |
2944 |
return 0; |
2945 |
} |
2946 |
label_end_of_loop: |
2947 |
return CODING_CATEGORY_MASK_BIG5; |
2948 |
} |
2949 |
|
2950 |
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
2951 |
Check if a text is encoded in UTF-8. If it is, return |
2952 |
CODING_CATEGORY_MASK_UTF_8, else return 0. */ |
2953 |
|
2954 |
#define UTF_8_1_OCTET_P(c) ((c) < 0x80) |
2955 |
#define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) |
2956 |
#define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) |
2957 |
#define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) |
2958 |
#define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) |
2959 |
#define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) |
2960 |
#define UTF_8_6_OCTET_LEADING_P(c) (((c) & 0xFE) == 0xFC) |
2961 |
|
2962 |
static int |
2963 |
detect_coding_utf_8 (src, src_end, multibytep) |
2964 |
unsigned char *src, *src_end; |
2965 |
int multibytep; |
2966 |
{ |
2967 |
unsigned char c; |
2968 |
int seq_maybe_bytes; |
2969 |
/* Dummy for ONE_MORE_BYTE. */ |
2970 |
struct coding_system dummy_coding; |
2971 |
struct coding_system *coding = &dummy_coding; |
2972 |
|
2973 |
while (1) |
2974 |
{ |
2975 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
2976 |
if (UTF_8_1_OCTET_P (c)) |
2977 |
continue; |
2978 |
else if (UTF_8_2_OCTET_LEADING_P (c)) |
2979 |
seq_maybe_bytes = 1; |
2980 |
else if (UTF_8_3_OCTET_LEADING_P (c)) |
2981 |
seq_maybe_bytes = 2; |
2982 |
else if (UTF_8_4_OCTET_LEADING_P (c)) |
2983 |
seq_maybe_bytes = 3; |
2984 |
else if (UTF_8_5_OCTET_LEADING_P (c)) |
2985 |
seq_maybe_bytes = 4; |
2986 |
else if (UTF_8_6_OCTET_LEADING_P (c)) |
2987 |
seq_maybe_bytes = 5; |
2988 |
else |
2989 |
return 0; |
2990 |
|
2991 |
do |
2992 |
{ |
2993 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
2994 |
if (!UTF_8_EXTRA_OCTET_P (c)) |
2995 |
return 0; |
2996 |
seq_maybe_bytes--; |
2997 |
} |
2998 |
while (seq_maybe_bytes > 0); |
2999 |
} |
3000 |
|
3001 |
label_end_of_loop: |
3002 |
return CODING_CATEGORY_MASK_UTF_8; |
3003 |
} |
3004 |
|
3005 |
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
3006 |
Check if a text is encoded in UTF-16 Big Endian (endian == 1) or |
3007 |
Little Endian (otherwise). If it is, return |
3008 |
CODING_CATEGORY_MASK_UTF_16_BE or CODING_CATEGORY_MASK_UTF_16_LE, |
3009 |
else return 0. */ |
3010 |
|
3011 |
#define UTF_16_INVALID_P(val) \ |
3012 |
(((val) == 0xFFFE) \ |
3013 |
|| ((val) == 0xFFFF)) |
3014 |
|
3015 |
#define UTF_16_HIGH_SURROGATE_P(val) \ |
3016 |
(((val) & 0xD800) == 0xD800) |
3017 |
|
3018 |
#define UTF_16_LOW_SURROGATE_P(val) \ |
3019 |
(((val) & 0xDC00) == 0xDC00) |
3020 |
|
3021 |
static int |
3022 |
detect_coding_utf_16 (src, src_end, multibytep) |
3023 |
unsigned char *src, *src_end; |
3024 |
int multibytep; |
3025 |
{ |
3026 |
unsigned char c1, c2; |
3027 |
/* Dummy for ONE_MORE_BYTE_CHECK_MULTIBYTE. */ |
3028 |
struct coding_system dummy_coding; |
3029 |
struct coding_system *coding = &dummy_coding; |
3030 |
|
3031 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c1, multibytep); |
3032 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c2, multibytep); |
3033 |
|
3034 |
if ((c1 == 0xFF) && (c2 == 0xFE)) |
3035 |
return CODING_CATEGORY_MASK_UTF_16_LE; |
3036 |
else if ((c1 == 0xFE) && (c2 == 0xFF)) |
3037 |
return CODING_CATEGORY_MASK_UTF_16_BE; |
3038 |
|
3039 |
label_end_of_loop: |
3040 |
return 0; |
3041 |
} |
3042 |
|
3043 |
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
3044 |
If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ |
3045 |
|
3046 |
static void |
3047 |
decode_coding_sjis_big5 (coding, source, destination, |
3048 |
src_bytes, dst_bytes, sjis_p) |
3049 |
struct coding_system *coding; |
3050 |
unsigned char *source, *destination; |
3051 |
int src_bytes, dst_bytes; |
3052 |
int sjis_p; |
3053 |
{ |
3054 |
unsigned char *src = source; |
3055 |
unsigned char *src_end = source + src_bytes; |
3056 |
unsigned char *dst = destination; |
3057 |
unsigned char *dst_end = destination + dst_bytes; |
3058 |
/* SRC_BASE remembers the start position in source in each loop. |
3059 |
The loop will be exited when there's not enough source code |
3060 |
(within macro ONE_MORE_BYTE), or when there's not enough |
3061 |
destination area to produce a character (within macro |
3062 |
EMIT_CHAR). */ |
3063 |
unsigned char *src_base; |
3064 |
Lisp_Object translation_table; |
3065 |
|
3066 |
if (NILP (Venable_character_translation)) |
3067 |
translation_table = Qnil; |
3068 |
else |
3069 |
{ |
3070 |
translation_table = coding->translation_table_for_decode; |
3071 |
if (NILP (translation_table)) |
3072 |
translation_table = Vstandard_translation_table_for_decode; |
3073 |
} |
3074 |
|
3075 |
coding->produced_char = 0; |
3076 |
while (1) |
3077 |
{ |
3078 |
int c, charset, c1, c2 = 0; |
3079 |
|
3080 |
src_base = src; |
3081 |
ONE_MORE_BYTE (c1); |
3082 |
|
3083 |
if (c1 < 0x80) |
3084 |
{ |
3085 |
charset = CHARSET_ASCII; |
3086 |
if (c1 < 0x20) |
3087 |
{ |
3088 |
if (c1 == '\r') |
3089 |
{ |
3090 |
if (coding->eol_type == CODING_EOL_CRLF) |
3091 |
{ |
3092 |
ONE_MORE_BYTE (c2); |
3093 |
if (c2 == '\n') |
3094 |
c1 = c2; |
3095 |
else |
3096 |
/* To process C2 again, SRC is subtracted by 1. */ |
3097 |
src--; |
3098 |
} |
3099 |
else if (coding->eol_type == CODING_EOL_CR) |
3100 |
c1 = '\n'; |
3101 |
} |
3102 |
else if (c1 == '\n' |
3103 |
&& (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) |
3104 |
&& (coding->eol_type == CODING_EOL_CR |
3105 |
|| coding->eol_type == CODING_EOL_CRLF)) |
3106 |
{ |
3107 |
coding->result = CODING_FINISH_INCONSISTENT_EOL; |
3108 |
goto label_end_of_loop; |
3109 |
} |
3110 |
} |
3111 |
} |
3112 |
else |
3113 |
{ |
3114 |
if (sjis_p) |
3115 |
{ |
3116 |
if (c1 == 0x80 || c1 == 0xA0 || c1 > 0xEF) |
3117 |
goto label_invalid_code; |
3118 |
if (c1 <= 0x9F || c1 >= 0xE0) |
3119 |
{ |
3120 |
/* SJIS -> JISX0208 */ |
3121 |
ONE_MORE_BYTE (c2); |
3122 |
if (c2 < 0x40 || c2 == 0x7F || c2 > 0xFC) |
3123 |
goto label_invalid_code; |
3124 |
DECODE_SJIS (c1, c2, c1, c2); |
3125 |
charset = charset_jisx0208; |
3126 |
} |
3127 |
else |
3128 |
/* SJIS -> JISX0201-Kana */ |
3129 |
charset = charset_katakana_jisx0201; |
3130 |
} |
3131 |
else |
3132 |
{ |
3133 |
/* BIG5 -> Big5 */ |
3134 |
if (c1 < 0xA0 || c1 > 0xFE) |
3135 |
goto label_invalid_code; |
3136 |
ONE_MORE_BYTE (c2); |
3137 |
if (c2 < 0x40 || (c2 > 0x7E && c2 < 0xA1) || c2 > 0xFE) |
3138 |
goto label_invalid_code; |
3139 |
DECODE_BIG5 (c1, c2, charset, c1, c2); |
3140 |
} |
3141 |
} |
3142 |
|
3143 |
c = DECODE_ISO_CHARACTER (charset, c1, c2); |
3144 |
EMIT_CHAR (c); |
3145 |
continue; |
3146 |
|
3147 |
label_invalid_code: |
3148 |
coding->errors++; |
3149 |
src = src_base; |
3150 |
c = *src++; |
3151 |
EMIT_CHAR (c); |
3152 |
} |
3153 |
|
3154 |
label_end_of_loop: |
3155 |
coding->consumed = coding->consumed_char = src_base - source; |
3156 |
coding->produced = dst - destination; |
3157 |
return; |
3158 |
} |
3159 |
|
3160 |
/* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". |
3161 |
This function can encode charsets `ascii', `katakana-jisx0201', |
3162 |
`japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We |
3163 |
are sure that all these charsets are registered as official charset |
3164 |
(i.e. do not have extended leading-codes). Characters of other |
3165 |
charsets are produced without any encoding. If SJIS_P is 1, encode |
3166 |
SJIS text, else encode BIG5 text. */ |
3167 |
|
3168 |
static void |
3169 |
encode_coding_sjis_big5 (coding, source, destination, |
3170 |
src_bytes, dst_bytes, sjis_p) |
3171 |
struct coding_system *coding; |
3172 |
unsigned char *source, *destination; |
3173 |
int src_bytes, dst_bytes; |
3174 |
int sjis_p; |
3175 |
{ |
3176 |
unsigned char *src = source; |
3177 |
unsigned char *src_end = source + src_bytes; |
3178 |
unsigned char *dst = destination; |
3179 |
unsigned char *dst_end = destination + dst_bytes; |
3180 |
/* SRC_BASE remembers the start position in source in each loop. |
3181 |
The loop will be exited when there's not enough source text to |
3182 |
analyze multi-byte codes (within macro ONE_MORE_CHAR), or when |
3183 |
there's not enough destination area to produce encoded codes |
3184 |
(within macro EMIT_BYTES). */ |
3185 |
unsigned char *src_base; |
3186 |
Lisp_Object translation_table; |
3187 |
|
3188 |
if (NILP (Venable_character_translation)) |
3189 |
translation_table = Qnil; |
3190 |
else |
3191 |
{ |
3192 |
translation_table = coding->translation_table_for_encode; |
3193 |
if (NILP (translation_table)) |
3194 |
translation_table = Vstandard_translation_table_for_encode; |
3195 |
} |
3196 |
|
3197 |
while (1) |
3198 |
{ |
3199 |
int c, charset, c1, c2; |
3200 |
|
3201 |
src_base = src; |
3202 |
ONE_MORE_CHAR (c); |
3203 |
|
3204 |
/* Now encode the character C. */ |
3205 |
if (SINGLE_BYTE_CHAR_P (c)) |
3206 |
{ |
3207 |
switch (c) |
3208 |
{ |
3209 |
case '\r': |
3210 |
if (!(coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
3211 |
{ |
3212 |
EMIT_ONE_BYTE (c); |
3213 |
break; |
3214 |
} |
3215 |
c = '\n'; |
3216 |
case '\n': |
3217 |
if (coding->eol_type == CODING_EOL_CRLF) |
3218 |
{ |
3219 |
EMIT_TWO_BYTES ('\r', c); |
3220 |
break; |
3221 |
} |
3222 |
else if (coding->eol_type == CODING_EOL_CR) |
3223 |
c = '\r'; |
3224 |
default: |
3225 |
EMIT_ONE_BYTE (c); |
3226 |
} |
3227 |
} |
3228 |
else |
3229 |
{ |
3230 |
SPLIT_CHAR (c, charset, c1, c2); |
3231 |
if (sjis_p) |
3232 |
{ |
3233 |
if (charset == charset_jisx0208 |
3234 |
|| charset == charset_jisx0208_1978) |
3235 |
{ |
3236 |
ENCODE_SJIS (c1, c2, c1, c2); |
3237 |
EMIT_TWO_BYTES (c1, c2); |
3238 |
} |
3239 |
else if (charset == charset_katakana_jisx0201) |
3240 |
EMIT_ONE_BYTE (c1 | 0x80); |
3241 |
else if (charset == charset_latin_jisx0201) |
3242 |
EMIT_ONE_BYTE (c1); |
3243 |
else if (coding->mode & CODING_MODE_INHIBIT_UNENCODABLE_CHAR) |
3244 |
{ |
3245 |
EMIT_ONE_BYTE (CODING_REPLACEMENT_CHARACTER); |
3246 |
if (CHARSET_WIDTH (charset) > 1) |
3247 |
EMIT_ONE_BYTE (CODING_REPLACEMENT_CHARACTER); |
3248 |
} |
3249 |
else |
3250 |
/* There's no way other than producing the internal |
3251 |
codes as is. */ |
3252 |
EMIT_BYTES (src_base, src); |
3253 |
} |
3254 |
else |
3255 |
{ |
3256 |
if (charset == charset_big5_1 || charset == charset_big5_2) |
3257 |
{ |
3258 |
ENCODE_BIG5 (charset, c1, c2, c1, c2); |
3259 |
EMIT_TWO_BYTES (c1, c2); |
3260 |
} |
3261 |
else if (coding->mode & CODING_MODE_INHIBIT_UNENCODABLE_CHAR) |
3262 |
{ |
3263 |
EMIT_ONE_BYTE (CODING_REPLACEMENT_CHARACTER); |
3264 |
if (CHARSET_WIDTH (charset) > 1) |
3265 |
EMIT_ONE_BYTE (CODING_REPLACEMENT_CHARACTER); |
3266 |
} |
3267 |
else |
3268 |
/* There's no way other than producing the internal |
3269 |
codes as is. */ |
3270 |
EMIT_BYTES (src_base, src); |
3271 |
} |
3272 |
} |
3273 |
coding->consumed_char++; |
3274 |
} |
3275 |
|
3276 |
label_end_of_loop: |
3277 |
coding->consumed = src_base - source; |
3278 |
coding->produced = coding->produced_char = dst - destination; |
3279 |
} |
3280 |
|
3281 |
|
3282 |
/*** 5. CCL handlers ***/ |
3283 |
|
3284 |
/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
3285 |
Check if a text is encoded in a coding system of which |
3286 |
encoder/decoder are written in CCL program. If it is, return |
3287 |
CODING_CATEGORY_MASK_CCL, else return 0. */ |
3288 |
|
3289 |
static int |
3290 |
detect_coding_ccl (src, src_end, multibytep) |
3291 |
unsigned char *src, *src_end; |
3292 |
int multibytep; |
3293 |
{ |
3294 |
unsigned char *valid; |
3295 |
int c; |
3296 |
/* Dummy for ONE_MORE_BYTE. */ |
3297 |
struct coding_system dummy_coding; |
3298 |
struct coding_system *coding = &dummy_coding; |
3299 |
|
3300 |
/* No coding system is assigned to coding-category-ccl. */ |
3301 |
if (!coding_system_table[CODING_CATEGORY_IDX_CCL]) |
3302 |
return 0; |
3303 |
|
3304 |
valid = coding_system_table[CODING_CATEGORY_IDX_CCL]->spec.ccl.valid_codes; |
3305 |
while (1) |
3306 |
{ |
3307 |
ONE_MORE_BYTE_CHECK_MULTIBYTE (c, multibytep); |
3308 |
if (! valid[c]) |
3309 |
return 0; |
3310 |
} |
3311 |
label_end_of_loop: |
3312 |
return CODING_CATEGORY_MASK_CCL; |
3313 |
} |
3314 |
|
3315 |
|
3316 |
/*** 6. End-of-line handlers ***/ |
3317 |
|
3318 |
/* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3319 |
|
3320 |
static void |
3321 |
decode_eol (coding, source, destination, src_bytes, dst_bytes) |
3322 |
struct coding_system *coding; |
3323 |
unsigned char *source, *destination; |
3324 |
int src_bytes, dst_bytes; |
3325 |
{ |
3326 |
unsigned char *src = source; |
3327 |
unsigned char *dst = destination; |
3328 |
unsigned char *src_end = src + src_bytes; |
3329 |
unsigned char *dst_end = dst + dst_bytes; |
3330 |
Lisp_Object translation_table; |
3331 |
/* SRC_BASE remembers the start position in source in each loop. |
3332 |
The loop will be exited when there's not enough source code |
3333 |
(within macro ONE_MORE_BYTE), or when there's not enough |
3334 |
destination area to produce a character (within macro |
3335 |
EMIT_CHAR). */ |
3336 |
unsigned char *src_base; |
3337 |
int c; |
3338 |
|
3339 |
translation_table = Qnil; |
3340 |
switch (coding->eol_type) |
3341 |
{ |
3342 |
case CODING_EOL_CRLF: |
3343 |
while (1) |
3344 |
{ |
3345 |
src_base = src; |
3346 |
ONE_MORE_BYTE (c); |
3347 |
if (c == '\r') |
3348 |
{ |
3349 |
ONE_MORE_BYTE (c); |
3350 |
if (c != '\n') |
3351 |
{ |
3352 |
src--; |
3353 |
c = '\r'; |
3354 |
} |
3355 |
} |
3356 |
else if (c == '\n' |
3357 |
&& (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL)) |
3358 |
{ |
3359 |
coding->result = CODING_FINISH_INCONSISTENT_EOL; |
3360 |
goto label_end_of_loop; |
3361 |
} |
3362 |
EMIT_CHAR (c); |
3363 |
} |
3364 |
break; |
3365 |
|
3366 |
case CODING_EOL_CR: |
3367 |
while (1) |
3368 |
{ |
3369 |
src_base = src; |
3370 |
ONE_MORE_BYTE (c); |
3371 |
if (c == '\n') |
3372 |
{ |
3373 |
if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) |
3374 |
{ |
3375 |
coding->result = CODING_FINISH_INCONSISTENT_EOL; |
3376 |
goto label_end_of_loop; |
3377 |
} |
3378 |
} |
3379 |
else if (c == '\r') |
3380 |
c = '\n'; |
3381 |
EMIT_CHAR (c); |
3382 |
} |
3383 |
break; |
3384 |
|
3385 |
default: /* no need for EOL handling */ |
3386 |
while (1) |
3387 |
{ |
3388 |
src_base = src; |
3389 |
ONE_MORE_BYTE (c); |
3390 |
EMIT_CHAR (c); |
3391 |
} |
3392 |
} |
3393 |
|
3394 |
label_end_of_loop: |
3395 |
coding->consumed = coding->consumed_char = src_base - source; |
3396 |
coding->produced = dst - destination; |
3397 |
return; |
3398 |
} |
3399 |
|
3400 |
/* See "GENERAL NOTES about `encode_coding_XXX ()' functions". Encode |
3401 |
format of end-of-line according to `coding->eol_type'. It also |
3402 |
convert multibyte form 8-bit characters to unibyte if |
3403 |
CODING->src_multibyte is nonzero. If `coding->mode & |
3404 |
CODING_MODE_SELECTIVE_DISPLAY' is nonzero, code '\r' in source text |
3405 |
also means end-of-line. */ |
3406 |
|
3407 |
static void |
3408 |
encode_eol (coding, source, destination, src_bytes, dst_bytes) |
3409 |
struct coding_system *coding; |
3410 |
const unsigned char *source; |
3411 |
unsigned char *destination; |
3412 |
int src_bytes, dst_bytes; |
3413 |
{ |
3414 |
const unsigned char *src = source; |
3415 |
unsigned char *dst = destination; |
3416 |
const unsigned char *src_end = src + src_bytes; |
3417 |
unsigned char *dst_end = dst + dst_bytes; |
3418 |
Lisp_Object translation_table; |
3419 |
/* SRC_BASE remembers the start position in source in each loop. |
3420 |
The loop will be exited when there's not enough source text to |
3421 |
analyze multi-byte codes (within macro ONE_MORE_CHAR), or when |
3422 |
there's not enough destination area to produce encoded codes |
3423 |
(within macro EMIT_BYTES). */ |
3424 |
const unsigned char *src_base; |
3425 |
unsigned char *tmp; |
3426 |
int c; |
3427 |
int selective_display = coding->mode & CODING_MODE_SELECTIVE_DISPLAY; |
3428 |
|
3429 |
translation_table = Qnil; |
3430 |
if (coding->src_multibyte |
3431 |
&& *(src_end - 1) == LEADING_CODE_8_BIT_CONTROL) |
3432 |
{ |
3433 |
src_end--; |
3434 |
src_bytes--; |
3435 |
coding->result = CODING_FINISH_INSUFFICIENT_SRC; |
3436 |
} |
3437 |
|
3438 |
if (coding->eol_type == CODING_EOL_CRLF) |
3439 |
{ |
3440 |
while (src < src_end) |
3441 |
{ |
3442 |
src_base = src; |
3443 |
c = *src++; |
3444 |
if (c >= 0x20) |
3445 |
EMIT_ONE_BYTE (c); |
3446 |
else if (c == '\n' || (c == '\r' && selective_display)) |
3447 |
EMIT_TWO_BYTES ('\r', '\n'); |
3448 |
else |
3449 |
EMIT_ONE_BYTE (c); |
3450 |
} |
3451 |
src_base = src; |
3452 |
label_end_of_loop: |
3453 |
; |
3454 |
} |
3455 |
else |
3456 |
{ |
3457 |
if (!dst_bytes || src_bytes <= dst_bytes) |
3458 |
{ |
3459 |
safe_bcopy (src, dst, src_bytes); |
3460 |
src_base = src_end; |
3461 |
dst += src_bytes; |
3462 |
} |
3463 |
else |
3464 |
{ |
3465 |
if (coding->src_multibyte |
3466 |
&& *(src + dst_bytes - 1) == LEADING_CODE_8_BIT_CONTROL) |
3467 |
dst_bytes--; |
3468 |
safe_bcopy (src, dst, dst_bytes); |
3469 |
src_base = src + dst_bytes; |
3470 |
dst = destination + dst_bytes; |
3471 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; |
3472 |
} |
3473 |
if (coding->eol_type == CODING_EOL_CR) |
3474 |
{ |
3475 |
for (tmp = destination; tmp < dst; tmp++) |
3476 |
if (*tmp == '\n') *tmp = '\r'; |
3477 |
} |
3478 |
else if (selective_display) |
3479 |
{ |
3480 |
for (tmp = destination; tmp < dst; tmp++) |
3481 |
if (*tmp == '\r') *tmp = '\n'; |
3482 |
} |
3483 |
} |
3484 |
if (coding->src_multibyte) |
3485 |
dst = destination + str_as_unibyte (destination, dst - destination); |
3486 |
|
3487 |
coding->consumed = src_base - source; |
3488 |
coding->produced = dst - destination; |
3489 |
coding->produced_char = coding->produced; |
3490 |
} |
3491 |
|
3492 |
|
3493 |
/*** 7. C library functions ***/ |
3494 |
|
3495 |
/* In Emacs Lisp, a coding system is represented by a Lisp symbol which |
3496 |
has a property `coding-system'. The value of this property is a |
3497 |
vector of length 5 (called the coding-vector). Among elements of |
3498 |
this vector, the first (element[0]) and the fifth (element[4]) |
3499 |
carry important information for decoding/encoding. Before |
3500 |
decoding/encoding, this information should be set in fields of a |
3501 |
structure of type `coding_system'. |
3502 |
|
3503 |
The value of the property `coding-system' can be a symbol of another |
3504 |
subsidiary coding-system. In that case, Emacs gets coding-vector |
3505 |
from that symbol. |
3506 |
|
3507 |
`element[0]' contains information to be set in `coding->type'. The |
3508 |
value and its meaning is as follows: |
3509 |
|
3510 |
0 -- coding_type_emacs_mule |
3511 |
1 -- coding_type_sjis |
3512 |
2 -- coding_type_iso2022 |
3513 |
3 -- coding_type_big5 |
3514 |
4 -- coding_type_ccl encoder/decoder written in CCL |
3515 |
nil -- coding_type_no_conversion |
3516 |
t -- coding_type_undecided (automatic conversion on decoding, |
3517 |
no-conversion on encoding) |
3518 |
|
3519 |
`element[4]' contains information to be set in `coding->flags' and |
3520 |
`coding->spec'. The meaning varies by `coding->type'. |
3521 |
|
3522 |
If `coding->type' is `coding_type_iso2022', element[4] is a vector |
3523 |
of length 32 (of which the first 13 sub-elements are used now). |
3524 |
Meanings of these sub-elements are: |
3525 |
|
3526 |
sub-element[N] where N is 0 through 3: to be set in `coding->spec.iso2022' |
3527 |
If the value is an integer of valid charset, the charset is |
3528 |
assumed to be designated to graphic register N initially. |
3529 |
|
3530 |
If the value is minus, it is a minus value of charset which |
3531 |
reserves graphic register N, which means that the charset is |
3532 |
not designated initially but should be designated to graphic |
3533 |
register N just before encoding a character in that charset. |
3534 |
|
3535 |
If the value is nil, graphic register N is never used on |
3536 |
encoding. |
3537 |
|
3538 |
sub-element[N] where N is 4 through 11: to be set in `coding->flags' |
3539 |
Each value takes t or nil. See the section ISO2022 of |
3540 |
`coding.h' for more information. |
3541 |
|
3542 |
If `coding->type' is `coding_type_big5', element[4] is t to denote |
3543 |
BIG5-ETen or nil to denote BIG5-HKU. |
3544 |
|
3545 |
If `coding->type' takes the other value, element[4] is ignored. |
3546 |
|
3547 |
Emacs Lisp's coding systems also carry information about format of |
3548 |
end-of-line in a value of property `eol-type'. If the value is |
3549 |
integer, 0 means CODING_EOL_LF, 1 means CODING_EOL_CRLF, and 2 |
3550 |
means CODING_EOL_CR. If it is not integer, it should be a vector |
3551 |
of subsidiary coding systems of which property `eol-type' has one |
3552 |
of the above values. |
3553 |
|
3554 |
*/ |
3555 |
|
3556 |
/* Extract information for decoding/encoding from CODING_SYSTEM_SYMBOL |
3557 |
and set it in CODING. If CODING_SYSTEM_SYMBOL is invalid, CODING |
3558 |
is setup so that no conversion is necessary and return -1, else |
3559 |
return 0. */ |
3560 |
|
3561 |
int |
3562 |
setup_coding_system (coding_system, coding) |
3563 |
Lisp_Object coding_system; |
3564 |
struct coding_system *coding; |
3565 |
{ |
3566 |
Lisp_Object coding_spec, coding_type, eol_type, plist; |
3567 |
Lisp_Object val; |
3568 |
|
3569 |
/* At first, zero clear all members. */ |
3570 |
bzero (coding, sizeof (struct coding_system)); |
3571 |
|
3572 |
/* Initialize some fields required for all kinds of coding systems. */ |
3573 |
coding->symbol = coding_system; |
3574 |
coding->heading_ascii = -1; |
3575 |
coding->post_read_conversion = coding->pre_write_conversion = Qnil; |
3576 |
coding->composing = COMPOSITION_DISABLED; |
3577 |
coding->cmp_data = NULL; |
3578 |
|
3579 |
if (NILP (coding_system)) |
3580 |
goto label_invalid_coding_system; |
3581 |
|
3582 |
coding_spec = Fget (coding_system, Qcoding_system); |
3583 |
|
3584 |
if (!VECTORP (coding_spec) |
3585 |
|| XVECTOR (coding_spec)->size != 5 |
3586 |
|| !CONSP (XVECTOR (coding_spec)->contents[3])) |
3587 |
goto label_invalid_coding_system; |
3588 |
|
3589 |
eol_type = inhibit_eol_conversion ? Qnil : Fget (coding_system, Qeol_type); |
3590 |
if (VECTORP (eol_type)) |
3591 |
{ |
3592 |
coding->eol_type = CODING_EOL_UNDECIDED; |
3593 |
coding->common_flags = CODING_REQUIRE_DETECTION_MASK; |
3594 |
} |
3595 |
else if (XFASTINT (eol_type) == 1) |
3596 |
{ |
3597 |
coding->eol_type = CODING_EOL_CRLF; |
3598 |
coding->common_flags |
3599 |
= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
3600 |
} |
3601 |
else if (XFASTINT (eol_type) == 2) |
3602 |
{ |
3603 |
coding->eol_type = CODING_EOL_CR; |
3604 |
coding->common_flags |
3605 |
= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
3606 |
} |
3607 |
else |
3608 |
coding->eol_type = CODING_EOL_LF; |
3609 |
|
3610 |
coding_type = XVECTOR (coding_spec)->contents[0]; |
3611 |
/* Try short cut. */ |
3612 |
if (SYMBOLP (coding_type)) |
3613 |
{ |
3614 |
if (EQ (coding_type, Qt)) |
3615 |
{ |
3616 |
coding->type = coding_type_undecided; |
3617 |
coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
3618 |
} |
3619 |
else |
3620 |
coding->type = coding_type_no_conversion; |
3621 |
/* Initialize this member. Any thing other than |
3622 |
CODING_CATEGORY_IDX_UTF_16_BE and |
3623 |
CODING_CATEGORY_IDX_UTF_16_LE are ok because they have |
3624 |
special treatment in detect_eol. */ |
3625 |
coding->category_idx = CODING_CATEGORY_IDX_EMACS_MULE; |
3626 |
|
3627 |
return 0; |
3628 |
} |
3629 |
|
3630 |
/* Get values of coding system properties: |
3631 |
`post-read-conversion', `pre-write-conversion', |
3632 |
`translation-table-for-decode', `translation-table-for-encode'. */ |
3633 |
plist = XVECTOR (coding_spec)->contents[3]; |
3634 |
/* Pre & post conversion functions should be disabled if |
3635 |
inhibit_eol_conversion is nonzero. This is the case that a code |
3636 |
conversion function is called while those functions are running. */ |
3637 |
if (! inhibit_pre_post_conversion) |
3638 |
{ |
3639 |
coding->post_read_conversion = Fplist_get (plist, Qpost_read_conversion); |
3640 |
coding->pre_write_conversion = Fplist_get (plist, Qpre_write_conversion); |
3641 |
} |
3642 |
val = Fplist_get (plist, Qtranslation_table_for_decode); |
3643 |
if (SYMBOLP (val)) |
3644 |
val = Fget (val, Qtranslation_table_for_decode); |
3645 |
coding->translation_table_for_decode = CHAR_TABLE_P (val) ? val : Qnil; |
3646 |
val = Fplist_get (plist, Qtranslation_table_for_encode); |
3647 |
if (SYMBOLP (val)) |
3648 |
val = Fget (val, Qtranslation_table_for_encode); |
3649 |
coding->translation_table_for_encode = CHAR_TABLE_P (val) ? val : Qnil; |
3650 |
val = Fplist_get (plist, Qcoding_category); |
3651 |
if (!NILP (val)) |
3652 |
{ |
3653 |
val = Fget (val, Qcoding_category_index); |
3654 |
if (INTEGERP (val)) |
3655 |
coding->category_idx = XINT (val); |
3656 |
else |
3657 |
goto label_invalid_coding_system; |
3658 |
} |
3659 |
else |
3660 |
goto label_invalid_coding_system; |
3661 |
|
3662 |
/* If the coding system has non-nil `composition' property, enable |
3663 |
composition handling. */ |
3664 |
val = Fplist_get (plist, Qcomposition); |
3665 |
if (!NILP (val)) |
3666 |
coding->composing = COMPOSITION_NO; |
3667 |
|
3668 |
switch (XFASTINT (coding_type)) |
3669 |
{ |
3670 |
case 0: |
3671 |
coding->type = coding_type_emacs_mule; |
3672 |
coding->common_flags |
3673 |
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
3674 |
if (!NILP (coding->post_read_conversion)) |
3675 |
coding->common_flags |= CODING_REQUIRE_DECODING_MASK; |
3676 |
if (!NILP (coding->pre_write_conversion)) |
3677 |
coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; |
3678 |
break; |
3679 |
|
3680 |
case 1: |
3681 |
coding->type = coding_type_sjis; |
3682 |
coding->common_flags |
3683 |
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
3684 |
break; |
3685 |
|
3686 |
case 2: |
3687 |
coding->type = coding_type_iso2022; |
3688 |
coding->common_flags |
3689 |
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
3690 |
{ |
3691 |
Lisp_Object val, temp; |
3692 |
Lisp_Object *flags; |
3693 |
int i, charset, reg_bits = 0; |
3694 |
|
3695 |
val = XVECTOR (coding_spec)->contents[4]; |
3696 |
|
3697 |
if (!VECTORP (val) || XVECTOR (val)->size != 32) |
3698 |
goto label_invalid_coding_system; |
3699 |
|
3700 |
flags = XVECTOR (val)->contents; |
3701 |
coding->flags |
3702 |
= ((NILP (flags[4]) ? 0 : CODING_FLAG_ISO_SHORT_FORM) |
3703 |
| (NILP (flags[5]) ? 0 : CODING_FLAG_ISO_RESET_AT_EOL) |
3704 |
| (NILP (flags[6]) ? 0 : CODING_FLAG_ISO_RESET_AT_CNTL) |
3705 |
| (NILP (flags[7]) ? 0 : CODING_FLAG_ISO_SEVEN_BITS) |
3706 |
| (NILP (flags[8]) ? 0 : CODING_FLAG_ISO_LOCKING_SHIFT) |
3707 |
| (NILP (flags[9]) ? 0 : CODING_FLAG_ISO_SINGLE_SHIFT) |
3708 |
| (NILP (flags[10]) ? 0 : CODING_FLAG_ISO_USE_ROMAN) |
3709 |
| (NILP (flags[11]) ? 0 : CODING_FLAG_ISO_USE_OLDJIS) |
3710 |
| (NILP (flags[12]) ? 0 : CODING_FLAG_ISO_NO_DIRECTION) |
3711 |
| (NILP (flags[13]) ? 0 : CODING_FLAG_ISO_INIT_AT_BOL) |
3712 |
| (NILP (flags[14]) ? 0 : CODING_FLAG_ISO_DESIGNATE_AT_BOL) |
3713 |
| (NILP (flags[15]) ? 0 : CODING_FLAG_ISO_SAFE) |
3714 |
| (NILP (flags[16]) ? 0 : CODING_FLAG_ISO_LATIN_EXTRA) |
3715 |
); |
3716 |
|
3717 |
/* Invoke graphic register 0 to plane 0. */ |
3718 |
CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; |
3719 |
/* Invoke graphic register 1 to plane 1 if we can use full 8-bit. */ |
3720 |
CODING_SPEC_ISO_INVOCATION (coding, 1) |
3721 |
= (coding->flags & CODING_FLAG_ISO_SEVEN_BITS ? -1 : 1); |
3722 |
/* Not single shifting at first. */ |
3723 |
CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; |
3724 |
/* Beginning of buffer should also be regarded as bol. */ |
3725 |
CODING_SPEC_ISO_BOL (coding) = 1; |
3726 |
|
3727 |
for (charset = 0; charset <= MAX_CHARSET; charset++) |
3728 |
CODING_SPEC_ISO_REVISION_NUMBER (coding, charset) = 255; |
3729 |
val = Vcharset_revision_alist; |
3730 |
while (CONSP (val)) |
3731 |
{ |
3732 |
charset = get_charset_id (Fcar_safe (XCAR (val))); |
3733 |
if (charset >= 0 |
3734 |
&& (temp = Fcdr_safe (XCAR (val)), INTEGERP (temp)) |
3735 |
&& (i = XINT (temp), (i >= 0 && (i + '@') < 128))) |
3736 |
CODING_SPEC_ISO_REVISION_NUMBER (coding, charset) = i; |
3737 |
val = XCDR (val); |
3738 |
} |
3739 |
|
3740 |
/* Checks FLAGS[REG] (REG = 0, 1, 2 3) and decide designations. |
3741 |
FLAGS[REG] can be one of below: |
3742 |
integer CHARSET: CHARSET occupies register I, |
3743 |
t: designate nothing to REG initially, but can be used |
3744 |
by any charsets, |
3745 |
list of integer, nil, or t: designate the first |
3746 |
element (if integer) to REG initially, the remaining |
3747 |
elements (if integer) is designated to REG on request, |
3748 |
if an element is t, REG can be used by any charsets, |
3749 |
nil: REG is never used. */ |
3750 |
for (charset = 0; charset <= MAX_CHARSET; charset++) |
3751 |
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
3752 |
= CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION; |
3753 |
for (i = 0; i < 4; i++) |
3754 |
{ |
3755 |
if ((INTEGERP (flags[i]) |
3756 |
&& (charset = XINT (flags[i]), CHARSET_VALID_P (charset))) |
3757 |
|| (charset = get_charset_id (flags[i])) >= 0) |
3758 |
{ |
3759 |
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = charset; |
3760 |
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) = i; |
3761 |
} |
3762 |
else if (EQ (flags[i], Qt)) |
3763 |
{ |
3764 |
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; |
3765 |
reg_bits |= 1 << i; |
3766 |
coding->flags |= CODING_FLAG_ISO_DESIGNATION; |
3767 |
} |
3768 |
else if (CONSP (flags[i])) |
3769 |
{ |
3770 |
Lisp_Object tail; |
3771 |
tail = flags[i]; |
3772 |
|
3773 |
coding->flags |= CODING_FLAG_ISO_DESIGNATION; |
3774 |
if ((INTEGERP (XCAR (tail)) |
3775 |
&& (charset = XINT (XCAR (tail)), |
3776 |
CHARSET_VALID_P (charset))) |
3777 |
|| (charset = get_charset_id (XCAR (tail))) >= 0) |
3778 |
{ |
3779 |
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = charset; |
3780 |
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) =i; |
3781 |
} |
3782 |
else |
3783 |
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; |
3784 |
tail = XCDR (tail); |
3785 |
while (CONSP (tail)) |
3786 |
{ |
3787 |
if ((INTEGERP (XCAR (tail)) |
3788 |
&& (charset = XINT (XCAR (tail)), |
3789 |
CHARSET_VALID_P (charset))) |
3790 |
|| (charset = get_charset_id (XCAR (tail))) >= 0) |
3791 |
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
3792 |
= i; |
3793 |
else if (EQ (XCAR (tail), Qt)) |
3794 |
reg_bits |= 1 << i; |
3795 |
tail = XCDR (tail); |
3796 |
} |
3797 |
} |
3798 |
else |
3799 |
CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; |
3800 |
|
3801 |
CODING_SPEC_ISO_DESIGNATION (coding, i) |
3802 |
= CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i); |
3803 |
} |
3804 |
|
3805 |
if (reg_bits && ! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT)) |
3806 |
{ |
3807 |
/* REG 1 can be used only by locking shift in 7-bit env. */ |
3808 |
if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) |
3809 |
reg_bits &= ~2; |
3810 |
if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)) |
3811 |
/* Without any shifting, only REG 0 and 1 can be used. */ |
3812 |
reg_bits &= 3; |
3813 |
} |
3814 |
|
3815 |
if (reg_bits) |
3816 |
for (charset = 0; charset <= MAX_CHARSET; charset++) |
3817 |
{ |
3818 |
if (CHARSET_DEFINED_P (charset) |
3819 |
&& (CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
3820 |
== CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION)) |
3821 |
{ |
3822 |
/* There exist some default graphic registers to be |
3823 |
used by CHARSET. */ |
3824 |
|
3825 |
/* We had better avoid designating a charset of |
3826 |
CHARS96 to REG 0 as far as possible. */ |
3827 |
if (CHARSET_CHARS (charset) == 96) |
3828 |
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
3829 |
= (reg_bits & 2 |
3830 |
? 1 : (reg_bits & 4 ? 2 : (reg_bits & 8 ? 3 : 0))); |
3831 |
else |
3832 |
CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
3833 |
= (reg_bits & 1 |
3834 |
? 0 : (reg_bits & 2 ? 1 : (reg_bits & 4 ? 2 : 3))); |
3835 |
} |
3836 |
} |
3837 |
} |
3838 |
coding->common_flags |= CODING_REQUIRE_FLUSHING_MASK; |
3839 |
coding->spec.iso2022.last_invalid_designation_register = -1; |
3840 |
break; |
3841 |
|
3842 |
case 3: |
3843 |
coding->type = coding_type_big5; |
3844 |
coding->common_flags |
3845 |
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
3846 |
coding->flags |
3847 |
= (NILP (XVECTOR (coding_spec)->contents[4]) |
3848 |
? CODING_FLAG_BIG5_HKU |
3849 |
: CODING_FLAG_BIG5_ETEN); |
3850 |
break; |
3851 |
|
3852 |
case 4: |
3853 |
coding->type = coding_type_ccl; |
3854 |
coding->common_flags |
3855 |
|= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; |
3856 |
{ |
3857 |
val = XVECTOR (coding_spec)->contents[4]; |
3858 |
if (! CONSP (val) |
3859 |
|| setup_ccl_program (&(coding->spec.ccl.decoder), |
3860 |
XCAR (val)) < 0 |
3861 |
|| setup_ccl_program (&(coding->spec.ccl.encoder), |
3862 |
XCDR (val)) < 0) |
3863 |
goto label_invalid_coding_system; |
3864 |
|
3865 |
bzero (coding->spec.ccl.valid_codes, 256); |
3866 |
val = Fplist_get (plist, Qvalid_codes); |
3867 |
if (CONSP (val)) |
3868 |
{ |
3869 |
Lisp_Object this; |
3870 |
|
3871 |
for (; CONSP (val); val = XCDR (val)) |
3872 |
{ |
3873 |
this = XCAR (val); |
3874 |
if (INTEGERP (this) |
3875 |
&& XINT (this) >= 0 && XINT (this) < 256) |
3876 |
coding->spec.ccl.valid_codes[XINT (this)] = 1; |
3877 |
else if (CONSP (this) |
3878 |
&& INTEGERP (XCAR (this)) |
3879 |
&& INTEGERP (XCDR (this))) |
3880 |
{ |
3881 |
int start = XINT (XCAR (this)); |
3882 |
int end = XINT (XCDR (this)); |
3883 |
|
3884 |
if (start >= 0 && start <= end && end < 256) |
3885 |
while (start <= end) |
3886 |
coding->spec.ccl.valid_codes[start++] = 1; |
3887 |
} |
3888 |
} |
3889 |
} |
3890 |
} |
3891 |
coding->common_flags |= CODING_REQUIRE_FLUSHING_MASK; |
3892 |
coding->spec.ccl.cr_carryover = 0; |
3893 |
coding->spec.ccl.eight_bit_carryover[0] = 0; |
3894 |
break; |
3895 |
|
3896 |
case 5: |
3897 |
coding->type = coding_type_raw_text; |
3898 |
break; |
3899 |
|
3900 |
default: |
3901 |
goto label_invalid_coding_system; |
3902 |
} |
3903 |
return 0; |
3904 |
|
3905 |
label_invalid_coding_system: |
3906 |
coding->type = coding_type_no_conversion; |
3907 |
coding->category_idx = CODING_CATEGORY_IDX_BINARY; |
3908 |
coding->common_flags = 0; |
3909 |
coding->eol_type = CODING_EOL_LF; |
3910 |
coding->pre_write_conversion = coding->post_read_conversion = Qnil; |
3911 |
return -1; |
3912 |
} |
3913 |
|
3914 |
/* Free memory blocks allocated for storing composition information. */ |
3915 |
|
3916 |
void |
3917 |
coding_free_composition_data (coding) |
3918 |
struct coding_system *coding; |
3919 |
{ |
3920 |
struct composition_data *cmp_data = coding->cmp_data, *next; |
3921 |
|
3922 |
if (!cmp_data) |
3923 |
return; |
3924 |
/* Memory blocks are chained. At first, rewind to the first, then, |
3925 |
free blocks one by one. */ |
3926 |
while (cmp_data->prev) |
3927 |
cmp_data = cmp_data->prev; |
3928 |
while (cmp_data) |
3929 |
{ |
3930 |
next = cmp_data->next; |
3931 |
xfree (cmp_data); |
3932 |
cmp_data = next; |
3933 |
} |
3934 |
coding->cmp_data = NULL; |
3935 |
} |
3936 |
|
3937 |
/* Set `char_offset' member of all memory blocks pointed by |
3938 |
coding->cmp_data to POS. */ |
3939 |
|
3940 |
void |
3941 |
coding_adjust_composition_offset (coding, pos) |
3942 |
struct coding_system *coding; |
3943 |
int pos; |
3944 |
{ |
3945 |
struct composition_data *cmp_data; |
3946 |
|
3947 |
for (cmp_data = coding->cmp_data; cmp_data; cmp_data = cmp_data->next) |
3948 |
cmp_data->char_offset = pos; |
3949 |
} |
3950 |
|
3951 |
/* Setup raw-text or one of its subsidiaries in the structure |
3952 |
coding_system CODING according to the already setup value eol_type |
3953 |
in CODING. CODING should be setup for some coding system in |
3954 |
advance. */ |
3955 |
|
3956 |
void |
3957 |
setup_raw_text_coding_system (coding) |
3958 |
struct coding_system *coding; |
3959 |
{ |
3960 |
if (coding->type != coding_type_raw_text) |
3961 |
{ |
3962 |
coding->symbol = Qraw_text; |
3963 |
coding->type = coding_type_raw_text; |
3964 |
if (coding->eol_type != CODING_EOL_UNDECIDED) |
3965 |
{ |
3966 |
Lisp_Object subsidiaries; |
3967 |
subsidiaries = Fget (Qraw_text, Qeol_type); |
3968 |
|
3969 |
if (VECTORP (subsidiaries) |
3970 |
&& XVECTOR (subsidiaries)->size == 3) |
3971 |
coding->symbol |
3972 |
= XVECTOR (subsidiaries)->contents[coding->eol_type]; |
3973 |
} |
3974 |
setup_coding_system (coding->symbol, coding); |
3975 |
} |
3976 |
return; |
3977 |
} |
3978 |
|
3979 |
/* Emacs has a mechanism to automatically detect a coding system if it |
3980 |
is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, |
3981 |
it's impossible to distinguish some coding systems accurately |
3982 |
because they use the same range of codes. So, at first, coding |
3983 |
systems are categorized into 7, those are: |
3984 |
|
3985 |
o coding-category-emacs-mule |
3986 |
|
3987 |
The category for a coding system which has the same code range |
3988 |
as Emacs' internal format. Assigned the coding-system (Lisp |
3989 |
symbol) `emacs-mule' by default. |
3990 |
|
3991 |
o coding-category-sjis |
3992 |
|
3993 |
The category for a coding system which has the same code range |
3994 |
as SJIS. Assigned the coding-system (Lisp |
3995 |
symbol) `japanese-shift-jis' by default. |
3996 |
|
3997 |
o coding-category-iso-7 |
3998 |
|
3999 |
The category for a coding system which has the same code range |
4000 |
as ISO2022 of 7-bit environment. This doesn't use any locking |
4001 |
shift and single shift functions. This can encode/decode all |
4002 |
charsets. Assigned the coding-system (Lisp symbol) |
4003 |
`iso-2022-7bit' by default. |
4004 |
|
4005 |
o coding-category-iso-7-tight |
4006 |
|
4007 |
Same as coding-category-iso-7 except that this can |
4008 |
encode/decode only the specified charsets. |
4009 |
|
4010 |
o coding-category-iso-8-1 |
4011 |
|
4012 |
The category for a coding system which has the same code range |
4013 |
as ISO2022 of 8-bit environment and graphic plane 1 used only |
4014 |
for DIMENSION1 charset. This doesn't use any locking shift |
4015 |
and single shift functions. Assigned the coding-system (Lisp |
4016 |
symbol) `iso-latin-1' by default. |
4017 |
|
4018 |
o coding-category-iso-8-2 |
4019 |
|
4020 |
The category for a coding system which has the same code range |
4021 |
as ISO2022 of 8-bit environment and graphic plane 1 used only |
4022 |
for DIMENSION2 charset. This doesn't use any locking shift |
4023 |
and single shift functions. Assigned the coding-system (Lisp |
4024 |
symbol) `japanese-iso-8bit' by default. |
4025 |
|
4026 |
o coding-category-iso-7-else |
4027 |
|
4028 |
The category for a coding system which has the same code range |
4029 |
as ISO2022 of 7-bit environment but uses locking shift or |
4030 |
single shift functions. Assigned the coding-system (Lisp |
4031 |
symbol) `iso-2022-7bit-lock' by default. |
4032 |
|
4033 |
o coding-category-iso-8-else |
4034 |
|
4035 |
The category for a coding system which has the same code range |
4036 |
as ISO2022 of 8-bit environment but uses locking shift or |
4037 |
single shift functions. Assigned the coding-system (Lisp |
4038 |
symbol) `iso-2022-8bit-ss2' by default. |
4039 |
|
4040 |
o coding-category-big5 |
4041 |
|
4042 |
The category for a coding system which has the same code range |
4043 |
as BIG5. Assigned the coding-system (Lisp symbol) |
4044 |
`cn-big5' by default. |
4045 |
|
4046 |
o coding-category-utf-8 |
4047 |
|
4048 |
The category for a coding system which has the same code range |
4049 |
as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
4050 |
symbol) `utf-8' by default. |
4051 |
|
4052 |
o coding-category-utf-16-be |
4053 |
|
4054 |
The category for a coding system in which a text has an |
4055 |
Unicode signature (cf. Unicode Standard) in the order of BIG |
4056 |
endian at the head. Assigned the coding-system (Lisp symbol) |
4057 |
`utf-16-be' by default. |
4058 |
|
4059 |
o coding-category-utf-16-le |
4060 |
|
4061 |
The category for a coding system in which a text has an |
4062 |
Unicode signature (cf. Unicode Standard) in the order of |
4063 |
LITTLE endian at the head. Assigned the coding-system (Lisp |
4064 |
symbol) `utf-16-le' by default. |
4065 |
|
4066 |
o coding-category-ccl |
4067 |
|
4068 |
The category for a coding system of which encoder/decoder is |
4069 |
written in CCL programs. The default value is nil, i.e., no |
4070 |
coding system is assigned. |
4071 |
|
4072 |
o coding-category-binary |
4073 |
|
4074 |
The category for a coding system not categorized in any of the |
4075 |
above. Assigned the coding-system (Lisp symbol) |
4076 |
`no-conversion' by default. |
4077 |
|
4078 |
Each of them is a Lisp symbol and the value is an actual |
4079 |
`coding-system' (this is also a Lisp symbol) assigned by a user. |
4080 |
What Emacs does actually is to detect a category of coding system. |
4081 |
Then, it uses a `coding-system' assigned to it. If Emacs can't |
4082 |
decide a single possible category, it selects a category of the |
4083 |
highest priority. Priorities of categories are also specified by a |
4084 |
user in a Lisp variable `coding-category-list'. |
4085 |
|
4086 |
*/ |
4087 |
|
4088 |
static |
4089 |
int ascii_skip_code[256]; |
4090 |
|
4091 |
/* Detect how a text of length SRC_BYTES pointed by SOURCE is encoded. |
4092 |
If it detects possible coding systems, return an integer in which |
4093 |
appropriate flag bits are set. Flag bits are defined by macros |
4094 |
CODING_CATEGORY_MASK_XXX in `coding.h'. If PRIORITIES is non-NULL, |
4095 |
it should point the table `coding_priorities'. In that case, only |
4096 |
the flag bit for a coding system of the highest priority is set in |
4097 |
the returned value. If MULTIBYTEP is nonzero, 8-bit codes of the |
4098 |
range 0x80..0x9F are in multibyte form. |
4099 |
|
4100 |
How many ASCII characters are at the head is returned as *SKIP. */ |
4101 |
|
4102 |
static int |
4103 |
detect_coding_mask (source, src_bytes, priorities, skip, multibytep) |
4104 |
unsigned char *source; |
4105 |
int src_bytes, *priorities, *skip; |
4106 |
int multibytep; |
4107 |
{ |
4108 |
register unsigned char c; |
4109 |
unsigned char *src = source, *src_end = source + src_bytes; |
4110 |
unsigned int mask, utf16_examined_p, iso2022_examined_p; |
4111 |
int i; |
4112 |
|
4113 |
/* At first, skip all ASCII characters and control characters except |
4114 |
for three ISO2022 specific control characters. */ |
4115 |
ascii_skip_code[ISO_CODE_SO] = 0; |
4116 |
ascii_skip_code[ISO_CODE_SI] = 0; |
4117 |
ascii_skip_code[ISO_CODE_ESC] = 0; |
4118 |
|
4119 |
label_loop_detect_coding: |
4120 |
while (src < src_end && ascii_skip_code[*src]) src++; |
4121 |
*skip = src - source; |
4122 |
|
4123 |
if (src >= src_end) |
4124 |
/* We found nothing other than ASCII. There's nothing to do. */ |
4125 |
return 0; |
4126 |
|
4127 |
c = *src; |
4128 |
/* The text seems to be encoded in some multilingual coding system. |
4129 |
Now, try to find in which coding system the text is encoded. */ |
4130 |
if (c < 0x80) |
4131 |
{ |
4132 |
/* i.e. (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) */ |
4133 |
/* C is an ISO2022 specific control code of C0. */ |
4134 |
mask = detect_coding_iso2022 (src, src_end, multibytep); |
4135 |
if (mask == 0) |
4136 |
{ |
4137 |
/* No valid ISO2022 code follows C. Try again. */ |
4138 |
src++; |
4139 |
if (c == ISO_CODE_ESC) |
4140 |
ascii_skip_code[ISO_CODE_ESC] = 1; |
4141 |
else |
4142 |
ascii_skip_code[ISO_CODE_SO] = ascii_skip_code[ISO_CODE_SI] = 1; |
4143 |
goto label_loop_detect_coding; |
4144 |
} |
4145 |
if (priorities) |
4146 |
{ |
4147 |
for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++) |
4148 |
{ |
4149 |
if (mask & priorities[i]) |
4150 |
return priorities[i]; |
4151 |
} |
4152 |
return CODING_CATEGORY_MASK_RAW_TEXT; |
4153 |
} |
4154 |
} |
4155 |
else |
4156 |
{ |
4157 |
int try; |
4158 |
|
4159 |
if (multibytep && c == LEADING_CODE_8_BIT_CONTROL) |
4160 |
c = src[1] - 0x20; |
4161 |
|
4162 |
if (c < 0xA0) |
4163 |
{ |
4164 |
/* C is the first byte of SJIS character code, |
4165 |
or a leading-code of Emacs' internal format (emacs-mule), |
4166 |
or the first byte of UTF-16. */ |
4167 |
try = (CODING_CATEGORY_MASK_SJIS |
4168 |
| CODING_CATEGORY_MASK_EMACS_MULE |
4169 |
| CODING_CATEGORY_MASK_UTF_16_BE |
4170 |
| CODING_CATEGORY_MASK_UTF_16_LE); |
4171 |
|
4172 |
/* Or, if C is a special latin extra code, |
4173 |
or is an ISO2022 specific control code of C1 (SS2 or SS3), |
4174 |
or is an ISO2022 control-sequence-introducer (CSI), |
4175 |
we should also consider the possibility of ISO2022 codings. */ |
4176 |
if ((VECTORP (Vlatin_extra_code_table) |
4177 |
&& !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) |
4178 |
|| (c == ISO_CODE_SS2 || c == ISO_CODE_SS3) |
4179 |
|| (c == ISO_CODE_CSI |
4180 |
&& (src < src_end |
4181 |
&& (*src == ']' |
4182 |
|| ((*src == '0' || *src == '1' || *src == '2') |
4183 |
&& src + 1 < src_end |
4184 |
&& src[1] == ']'))))) |
4185 |
try |= (CODING_CATEGORY_MASK_ISO_8_ELSE |
4186 |
| CODING_CATEGORY_MASK_ISO_8BIT); |
4187 |
} |
4188 |
else |
4189 |
/* C is a character of ISO2022 in graphic plane right, |
4190 |
or a SJIS's 1-byte character code (i.e. JISX0201), |
4191 |
or the first byte of BIG5's 2-byte code, |
4192 |
or the first byte of UTF-8/16. */ |
4193 |
try = (CODING_CATEGORY_MASK_ISO_8_ELSE |
4194 |
| CODING_CATEGORY_MASK_ISO_8BIT |
4195 |
| CODING_CATEGORY_MASK_SJIS |
4196 |
| CODING_CATEGORY_MASK_BIG5 |
4197 |
| CODING_CATEGORY_MASK_UTF_8 |
4198 |
| CODING_CATEGORY_MASK_UTF_16_BE |
4199 |
| CODING_CATEGORY_MASK_UTF_16_LE); |
4200 |
|
4201 |
/* Or, we may have to consider the possibility of CCL. */ |
4202 |
if (coding_system_table[CODING_CATEGORY_IDX_CCL] |
4203 |
&& (coding_system_table[CODING_CATEGORY_IDX_CCL] |
4204 |
->spec.ccl.valid_codes)[c]) |
4205 |
try |= CODING_CATEGORY_MASK_CCL; |
4206 |
|
4207 |
mask = 0; |
4208 |
utf16_examined_p = iso2022_examined_p = 0; |
4209 |
if (priorities) |
4210 |
{ |
4211 |
for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++) |
4212 |
{ |
4213 |
if (!iso2022_examined_p |
4214 |
&& (priorities[i] & try & CODING_CATEGORY_MASK_ISO)) |
4215 |
{ |
4216 |
mask |= detect_coding_iso2022 (src, src_end, multibytep); |
4217 |
iso2022_examined_p = 1; |
4218 |
} |
4219 |
else if (priorities[i] & try & CODING_CATEGORY_MASK_SJIS) |
4220 |
mask |= detect_coding_sjis (src, src_end, multibytep); |
4221 |
else if (priorities[i] & try & CODING_CATEGORY_MASK_UTF_8) |
4222 |
mask |= detect_coding_utf_8 (src, src_end, multibytep); |
4223 |
else if (!utf16_examined_p |
4224 |
&& (priorities[i] & try & |
4225 |
CODING_CATEGORY_MASK_UTF_16_BE_LE)) |
4226 |
{ |
4227 |
mask |= detect_coding_utf_16 (src, src_end, multibytep); |
4228 |
utf16_examined_p = 1; |
4229 |
} |
4230 |
else if (priorities[i] & try & CODING_CATEGORY_MASK_BIG5) |
4231 |
mask |= detect_coding_big5 (src, src_end, multibytep); |
4232 |
else if (priorities[i] & try & CODING_CATEGORY_MASK_EMACS_MULE) |
4233 |
mask |= detect_coding_emacs_mule (src, src_end, multibytep); |
4234 |
else if (priorities[i] & try & CODING_CATEGORY_MASK_CCL) |
4235 |
mask |= detect_coding_ccl (src, src_end, multibytep); |
4236 |
else if (priorities[i] & CODING_CATEGORY_MASK_RAW_TEXT) |
4237 |
mask |= CODING_CATEGORY_MASK_RAW_TEXT; |
4238 |
else if (priorities[i] & CODING_CATEGORY_MASK_BINARY) |
4239 |
mask |= CODING_CATEGORY_MASK_BINARY; |
4240 |
if (mask & priorities[i]) |
4241 |
return priorities[i]; |
4242 |
} |
4243 |
return CODING_CATEGORY_MASK_RAW_TEXT; |
4244 |
} |
4245 |
if (try & CODING_CATEGORY_MASK_ISO) |
4246 |
mask |= detect_coding_iso2022 (src, src_end, multibytep); |
4247 |
if (try & CODING_CATEGORY_MASK_SJIS) |
4248 |
mask |= detect_coding_sjis (src, src_end, multibytep); |
4249 |
if (try & CODING_CATEGORY_MASK_BIG5) |
4250 |
mask |= detect_coding_big5 (src, src_end, multibytep); |
4251 |
if (try & CODING_CATEGORY_MASK_UTF_8) |
4252 |
mask |= detect_coding_utf_8 (src, src_end, multibytep); |
4253 |
if (try & CODING_CATEGORY_MASK_UTF_16_BE_LE) |
4254 |
mask |= detect_coding_utf_16 (src, src_end, multibytep); |
4255 |
if (try & CODING_CATEGORY_MASK_EMACS_MULE) |
4256 |
mask |= detect_coding_emacs_mule (src, src_end, multibytep); |
4257 |
if (try & CODING_CATEGORY_MASK_CCL) |
4258 |
mask |= detect_coding_ccl (src, src_end, multibytep); |
4259 |
} |
4260 |
return (mask | CODING_CATEGORY_MASK_RAW_TEXT | CODING_CATEGORY_MASK_BINARY); |
4261 |
} |
4262 |
|
4263 |
/* Detect how a text of length SRC_BYTES pointed by SRC is encoded. |
4264 |
The information of the detected coding system is set in CODING. */ |
4265 |
|
4266 |
void |
4267 |
detect_coding (coding, src, src_bytes) |
4268 |
struct coding_system *coding; |
4269 |
const unsigned char *src; |
4270 |
int src_bytes; |
4271 |
{ |
4272 |
unsigned int idx; |
4273 |
int skip, mask; |
4274 |
Lisp_Object val; |
4275 |
|
4276 |
val = Vcoding_category_list; |
4277 |
mask = detect_coding_mask (src, src_bytes, coding_priorities, &skip, |
4278 |
coding->src_multibyte); |
4279 |
coding->heading_ascii = skip; |
4280 |
|
4281 |
if (!mask) return; |
4282 |
|
4283 |
/* We found a single coding system of the highest priority in MASK. */ |
4284 |
idx = 0; |
4285 |
while (mask && ! (mask & 1)) mask >>= 1, idx++; |
4286 |
if (! mask) |
4287 |
idx = CODING_CATEGORY_IDX_RAW_TEXT; |
4288 |
|
4289 |
val = SYMBOL_VALUE (XVECTOR (Vcoding_category_table)->contents[idx]); |
4290 |
|
4291 |
if (coding->eol_type != CODING_EOL_UNDECIDED) |
4292 |
{ |
4293 |
Lisp_Object tmp; |
4294 |
|
4295 |
tmp = Fget (val, Qeol_type); |
4296 |
if (VECTORP (tmp)) |
4297 |
val = XVECTOR (tmp)->contents[coding->eol_type]; |
4298 |
} |
4299 |
|
4300 |
/* Setup this new coding system while preserving some slots. */ |
4301 |
{ |
4302 |
int src_multibyte = coding->src_multibyte; |
4303 |
int dst_multibyte = coding->dst_multibyte; |
4304 |
|
4305 |
setup_coding_system (val, coding); |
4306 |
coding->src_multibyte = src_multibyte; |
4307 |
coding->dst_multibyte = dst_multibyte; |
4308 |
coding->heading_ascii = skip; |
4309 |
} |
4310 |
} |
4311 |
|
4312 |
/* Detect how end-of-line of a text of length SRC_BYTES pointed by |
4313 |
SOURCE is encoded. Return one of CODING_EOL_LF, CODING_EOL_CRLF, |
4314 |
CODING_EOL_CR, and CODING_EOL_UNDECIDED. |
4315 |
|
4316 |
How many non-eol characters are at the head is returned as *SKIP. */ |
4317 |
|
4318 |
#define MAX_EOL_CHECK_COUNT 3 |
4319 |
|
4320 |
static int |
4321 |
detect_eol_type (source, src_bytes, skip) |
4322 |
unsigned char *source; |
4323 |
int src_bytes, *skip; |
4324 |
{ |
4325 |
unsigned char *src = source, *src_end = src + src_bytes; |
4326 |
unsigned char c; |
4327 |
int total = 0; /* How many end-of-lines are found so far. */ |
4328 |
int eol_type = CODING_EOL_UNDECIDED; |
4329 |
int this_eol_type; |
4330 |
|
4331 |
*skip = 0; |
4332 |
|
4333 |
while (src < src_end && total < MAX_EOL_CHECK_COUNT) |
4334 |
{ |
4335 |
c = *src++; |
4336 |
if (c == '\n' || c == '\r') |
4337 |
{ |
4338 |
if (*skip == 0) |
4339 |
*skip = src - 1 - source; |
4340 |
total++; |
4341 |
if (c == '\n') |
4342 |
this_eol_type = CODING_EOL_LF; |
4343 |
else if (src >= src_end || *src != '\n') |
4344 |
this_eol_type = CODING_EOL_CR; |
4345 |
else |
4346 |
this_eol_type = CODING_EOL_CRLF, src++; |
4347 |
|
4348 |
if (eol_type == CODING_EOL_UNDECIDED) |
4349 |
/* This is the first end-of-line. */ |
4350 |
eol_type = this_eol_type; |
4351 |
else if (eol_type != this_eol_type) |
4352 |
{ |
4353 |
/* The found type is different from what found before. */ |
4354 |
eol_type = CODING_EOL_INCONSISTENT; |
4355 |
break; |
4356 |
} |
4357 |
} |
4358 |
} |
4359 |
|
4360 |
if (*skip == 0) |
4361 |
*skip = src_end - source; |
4362 |
return eol_type; |
4363 |
} |
4364 |
|
4365 |
/* Like detect_eol_type, but detect EOL type in 2-octet |
4366 |
big-endian/little-endian format for coding systems utf-16-be and |
4367 |
utf-16-le. */ |
4368 |
|
4369 |
static int |
4370 |
detect_eol_type_in_2_octet_form (source, src_bytes, skip, big_endian_p) |
4371 |
unsigned char *source; |
4372 |
int src_bytes, *skip, big_endian_p; |
4373 |
{ |
4374 |
unsigned char *src = source, *src_end = src + src_bytes; |
4375 |
unsigned int c1, c2; |
4376 |
int total = 0; /* How many end-of-lines are found so far. */ |
4377 |
int eol_type = CODING_EOL_UNDECIDED; |
4378 |
int this_eol_type; |
4379 |
int msb, lsb; |
4380 |
|
4381 |
if (big_endian_p) |
4382 |
msb = 0, lsb = 1; |
4383 |
else |
4384 |
msb = 1, lsb = 0; |
4385 |
|
4386 |
*skip = 0; |
4387 |
|
4388 |
while ((src + 1) < src_end && total < MAX_EOL_CHECK_COUNT) |
4389 |
{ |
4390 |
c1 = (src[msb] << 8) | (src[lsb]); |
4391 |
src += 2; |
4392 |
|
4393 |
if (c1 == '\n' || c1 == '\r') |
4394 |
{ |
4395 |
if (*skip == 0) |
4396 |
*skip = src - 2 - source; |
4397 |
total++; |
4398 |
if (c1 == '\n') |
4399 |
{ |
4400 |
this_eol_type = CODING_EOL_LF; |
4401 |
} |
4402 |
else |
4403 |
{ |
4404 |
if ((src + 1) >= src_end) |
4405 |
{ |
4406 |
this_eol_type = CODING_EOL_CR; |
4407 |
} |
4408 |
else |
4409 |
{ |
4410 |
c2 = (src[msb] << 8) | (src[lsb]); |
4411 |
if (c2 == '\n') |
4412 |
this_eol_type = CODING_EOL_CRLF, src += 2; |
4413 |
else |
4414 |
this_eol_type = CODING_EOL_CR; |
4415 |
} |
4416 |
} |
4417 |
|
4418 |
if (eol_type == CODING_EOL_UNDECIDED) |
4419 |
/* This is the first end-of-line. */ |
4420 |
eol_type = this_eol_type; |
4421 |
else if (eol_type != this_eol_type) |
4422 |
{ |
4423 |
/* The found type is different from what found before. */ |
4424 |
eol_type = CODING_EOL_INCONSISTENT; |
4425 |
break; |
4426 |
} |
4427 |
} |
4428 |
} |
4429 |
|
4430 |
if (*skip == 0) |
4431 |
*skip = src_end - source; |
4432 |
return eol_type; |
4433 |
} |
4434 |
|
4435 |
/* Detect how end-of-line of a text of length SRC_BYTES pointed by SRC |
4436 |
is encoded. If it detects an appropriate format of end-of-line, it |
4437 |
sets the information in *CODING. */ |
4438 |
|
4439 |
void |
4440 |
detect_eol (coding, src, src_bytes) |
4441 |
struct coding_system *coding; |
4442 |
const unsigned char *src; |
4443 |
int src_bytes; |
4444 |
{ |
4445 |
Lisp_Object val; |
4446 |
int skip; |
4447 |
int eol_type; |
4448 |
|
4449 |
switch (coding->category_idx) |
4450 |
{ |
4451 |
case CODING_CATEGORY_IDX_UTF_16_BE: |
4452 |
eol_type = detect_eol_type_in_2_octet_form (src, src_bytes, &skip, 1); |
4453 |
break; |
4454 |
case CODING_CATEGORY_IDX_UTF_16_LE: |
4455 |
eol_type = detect_eol_type_in_2_octet_form (src, src_bytes, &skip, 0); |
4456 |
break; |
4457 |
default: |
4458 |
eol_type = detect_eol_type (src, src_bytes, &skip); |
4459 |
break; |
4460 |
} |
4461 |
|
4462 |
if (coding->heading_ascii > skip) |
4463 |
coding->heading_ascii = skip; |
4464 |
else |
4465 |
skip = coding->heading_ascii; |
4466 |
|
4467 |
if (eol_type == CODING_EOL_UNDECIDED) |
4468 |
return; |
4469 |
if (eol_type == CODING_EOL_INCONSISTENT) |
4470 |
{ |
4471 |
#if 0 |
4472 |
/* This code is suppressed until we find a better way to |
4473 |
distinguish raw text file and binary file. */ |
4474 |
|
4475 |
/* If we have already detected that the coding is raw-text, the |
4476 |
coding should actually be no-conversion. */ |
4477 |
if (coding->type == coding_type_raw_text) |
4478 |
{ |
4479 |
setup_coding_system (Qno_conversion, coding); |
4480 |
return; |
4481 |
} |
4482 |
/* Else, let's decode only text code anyway. */ |
4483 |
#endif /* 0 */ |
4484 |
eol_type = CODING_EOL_LF; |
4485 |
} |
4486 |
|
4487 |
val = Fget (coding->symbol, Qeol_type); |
4488 |
if (VECTORP (val) && XVECTOR (val)->size == 3) |
4489 |
{ |
4490 |
int src_multibyte = coding->src_multibyte; |
4491 |
int dst_multibyte = coding->dst_multibyte; |
4492 |
struct composition_data *cmp_data = coding->cmp_data; |
4493 |
|
4494 |
setup_coding_system (XVECTOR (val)->contents[eol_type], coding); |
4495 |
coding->src_multibyte = src_multibyte; |
4496 |
coding->dst_multibyte = dst_multibyte; |
4497 |
coding->heading_ascii = skip; |
4498 |
coding->cmp_data = cmp_data; |
4499 |
} |
4500 |
} |
4501 |
|
4502 |
#define CONVERSION_BUFFER_EXTRA_ROOM 256 |
4503 |
|
4504 |
#define DECODING_BUFFER_MAG(coding) \ |
4505 |
(coding->type == coding_type_iso2022 \ |
4506 |
? 3 \ |
4507 |
: (coding->type == coding_type_ccl \ |
4508 |
? coding->spec.ccl.decoder.buf_magnification \ |
4509 |
: 2)) |
4510 |
|
4511 |
/* Return maximum size (bytes) of a buffer enough for decoding |
4512 |
SRC_BYTES of text encoded in CODING. */ |
4513 |
|
4514 |
int |
4515 |
decoding_buffer_size (coding, src_bytes) |
4516 |
struct coding_system *coding; |
4517 |
int src_bytes; |
4518 |
{ |
4519 |
return (src_bytes * DECODING_BUFFER_MAG (coding) |
4520 |
+ CONVERSION_BUFFER_EXTRA_ROOM); |
4521 |
} |
4522 |
|
4523 |
/* Return maximum size (bytes) of a buffer enough for encoding |
4524 |
SRC_BYTES of text to CODING. */ |
4525 |
|
4526 |
int |
4527 |
encoding_buffer_size (coding, src_bytes) |
4528 |
struct coding_system *coding; |
4529 |
int src_bytes; |
4530 |
{ |
4531 |
int magnification; |
4532 |
|
4533 |
if (coding->type == coding_type_ccl) |
4534 |
{ |
4535 |
magnification = coding->spec.ccl.encoder.buf_magnification; |
4536 |
if (coding->eol_type == CODING_EOL_CRLF) |
4537 |
magnification *= 2; |
4538 |
} |
4539 |
else if (CODING_REQUIRE_ENCODING (coding)) |
4540 |
magnification = 3; |
4541 |
else |
4542 |
magnification = 1; |
4543 |
|
4544 |
return (src_bytes * magnification + CONVERSION_BUFFER_EXTRA_ROOM); |
4545 |
} |
4546 |
|
4547 |
/* Working buffer for code conversion. */ |
4548 |
struct conversion_buffer |
4549 |
{ |
4550 |
int size; /* size of data. */ |
4551 |
int on_stack; /* 1 if allocated by alloca. */ |
4552 |
unsigned char *data; |
4553 |
}; |
4554 |
|
4555 |
/* Allocate LEN bytes of memory for BUF (struct conversion_buffer). */ |
4556 |
#define allocate_conversion_buffer(buf, len) \ |
4557 |
do { \ |
4558 |
if (len < MAX_ALLOCA) \ |
4559 |
{ \ |
4560 |
buf.data = (unsigned char *) alloca (len); \ |
4561 |
buf.on_stack = 1; \ |
4562 |
} \ |
4563 |
else \ |
4564 |
{ \ |
4565 |
buf.data = (unsigned char *) xmalloc (len); \ |
4566 |
buf.on_stack = 0; \ |
4567 |
} \ |
4568 |
buf.size = len; \ |
4569 |
} while (0) |
4570 |
|
4571 |
/* Double the allocated memory for *BUF. */ |
4572 |
static void |
4573 |
extend_conversion_buffer (buf) |
4574 |
struct conversion_buffer *buf; |
4575 |
{ |
4576 |
if (buf->on_stack) |
4577 |
{ |
4578 |
unsigned char *save = buf->data; |
4579 |
buf->data = (unsigned char *) xmalloc (buf->size * 2); |
4580 |
bcopy (save, buf->data, buf->size); |
4581 |
buf->on_stack = 0; |
4582 |
} |
4583 |
else |
4584 |
{ |
4585 |
buf->data = (unsigned char *) xrealloc (buf->data, buf->size * 2); |
4586 |
} |
4587 |
buf->size *= 2; |
4588 |
} |
4589 |
|
4590 |
/* Free the allocated memory for BUF if it is not on stack. */ |
4591 |
static void |
4592 |
free_conversion_buffer (buf) |
4593 |
struct conversion_buffer *buf; |
4594 |
{ |
4595 |
if (!buf->on_stack) |
4596 |
xfree (buf->data); |
4597 |
} |
4598 |
|
4599 |
int |
4600 |
ccl_coding_driver (coding, source, destination, src_bytes, dst_bytes, encodep) |
4601 |
struct coding_system *coding; |
4602 |
unsigned char *source, *destination; |
4603 |
int src_bytes, dst_bytes, encodep; |
4604 |
{ |
4605 |
struct ccl_program *ccl |
4606 |
= encodep ? &coding->spec.ccl.encoder : &coding->spec.ccl.decoder; |
4607 |
unsigned char *dst = destination; |
4608 |
|
4609 |
ccl->suppress_error = coding->suppress_error; |
4610 |
ccl->last_block = coding->mode & CODING_MODE_LAST_BLOCK; |
4611 |
if (encodep) |
4612 |
{ |
4613 |
/* On encoding, EOL format is converted within ccl_driver. For |
4614 |
that, setup proper information in the structure CCL. */ |
4615 |
ccl->eol_type = coding->eol_type; |
4616 |
if (ccl->eol_type ==CODING_EOL_UNDECIDED) |
4617 |
ccl->eol_type = CODING_EOL_LF; |
4618 |
ccl->cr_consumed = coding->spec.ccl.cr_carryover; |
4619 |
ccl->eight_bit_control = coding->dst_multibyte; |
4620 |
} |
4621 |
else |
4622 |
ccl->eight_bit_control = 1; |
4623 |
ccl->multibyte = coding->src_multibyte; |
4624 |
if (coding->spec.ccl.eight_bit_carryover[0] != 0) |
4625 |
{ |
4626 |
/* Move carryover bytes to DESTINATION. */ |
4627 |
unsigned char *p = coding->spec.ccl.eight_bit_carryover; |
4628 |
while (*p) |
4629 |
*dst++ = *p++; |
4630 |
coding->spec.ccl.eight_bit_carryover[0] = 0; |
4631 |
if (dst_bytes) |
4632 |
dst_bytes -= dst - destination; |
4633 |
} |
4634 |
|
4635 |
coding->produced = (ccl_driver (ccl, source, dst, src_bytes, dst_bytes, |
4636 |
&(coding->consumed)) |
4637 |
+ dst - destination); |
4638 |
|
4639 |
if (encodep) |
4640 |
{ |
4641 |
coding->produced_char = coding->produced; |
4642 |
coding->spec.ccl.cr_carryover = ccl->cr_consumed; |
4643 |
} |
4644 |
else if (!ccl->eight_bit_control) |
4645 |
{ |
4646 |
/* The produced bytes forms a valid multibyte sequence. */ |
4647 |
coding->produced_char |
4648 |
= multibyte_chars_in_text (destination, coding->produced); |
4649 |
coding->spec.ccl.eight_bit_carryover[0] = 0; |
4650 |
} |
4651 |
else |
4652 |
{ |
4653 |
/* On decoding, the destination should always multibyte. But, |
4654 |
CCL program might have been generated an invalid multibyte |
4655 |
sequence. Here we make such a sequence valid as |
4656 |
multibyte. */ |
4657 |
int bytes |
4658 |
= dst_bytes ? dst_bytes : source + coding->consumed - destination; |
4659 |
|
4660 |
if ((coding->consumed < src_bytes |
4661 |
|| !ccl->last_block) |
4662 |
&& coding->produced >= 1 |
4663 |
&& destination[coding->produced - 1] >= 0x80) |
4664 |
{ |
4665 |
/* We should not convert the tailing 8-bit codes to |
4666 |
multibyte form even if they doesn't form a valid |
4667 |
multibyte sequence. They may form a valid sequence in |
4668 |
the next call. */ |
4669 |
int carryover = 0; |
4670 |
|
4671 |
if (destination[coding->produced - 1] < 0xA0) |
4672 |
carryover = 1; |
4673 |
else if (coding->produced >= 2) |
4674 |
{ |
4675 |
if (destination[coding->produced - 2] >= 0x80) |
4676 |
{ |
4677 |
if (destination[coding->produced - 2] < 0xA0) |
4678 |
carryover = 2; |
4679 |
else if (coding->produced >= 3 |
4680 |
&& destination[coding->produced - 3] >= 0x80 |
4681 |
&& destination[coding->produced - 3] < 0xA0) |
4682 |
carryover = 3; |
4683 |
} |
4684 |
} |
4685 |
if (carryover > 0) |
4686 |
{ |
4687 |
BCOPY_SHORT (destination + coding->produced - carryover, |
4688 |
coding->spec.ccl.eight_bit_carryover, |
4689 |
carryover); |
4690 |
coding->spec.ccl.eight_bit_carryover[carryover] = 0; |
4691 |
coding->produced -= carryover; |
4692 |
} |
4693 |
} |
4694 |
coding->produced = str_as_multibyte (destination, bytes, |
4695 |
coding->produced, |
4696 |
&(coding->produced_char)); |
4697 |
} |
4698 |
|
4699 |
switch (ccl->status) |
4700 |
{ |
4701 |
case CCL_STAT_SUSPEND_BY_SRC: |
4702 |
coding->result = CODING_FINISH_INSUFFICIENT_SRC; |
4703 |
break; |
4704 |
case CCL_STAT_SUSPEND_BY_DST: |
4705 |
coding->result = CODING_FINISH_INSUFFICIENT_DST; |
4706 |
break; |
4707 |
case CCL_STAT_QUIT: |
4708 |
case CCL_STAT_INVALID_CMD: |
4709 |
coding->result = CODING_FINISH_INTERRUPT; |
4710 |
break; |
4711 |
default: |
4712 |
coding->result = CODING_FINISH_NORMAL; |
4713 |
break; |
4714 |
} |
4715 |
return coding->result; |
4716 |
} |
4717 |
|
4718 |
/* Decode EOL format of the text at PTR of BYTES length destructively |
4719 |
according to CODING->eol_type. This is called after the CCL |
4720 |
program produced a decoded text at PTR. If we do CRLF->LF |
4721 |
conversion, update CODING->produced and CODING->produced_char. */ |
4722 |
|
4723 |
static void |
4724 |
decode_eol_post_ccl (coding, ptr, bytes) |
4725 |
struct coding_system *coding; |
4726 |
unsigned char *ptr; |
4727 |
int bytes; |
4728 |
{ |
4729 |
Lisp_Object val, saved_coding_symbol; |
4730 |
unsigned char *pend = ptr + bytes; |
4731 |
int dummy; |
4732 |
|
4733 |
/* Remember the current coding system symbol. We set it back when |
4734 |
an inconsistent EOL is found so that `last-coding-system-used' is |
4735 |
set to the coding system that doesn't specify EOL conversion. */ |
4736 |
saved_coding_symbol = coding->symbol; |
4737 |
|
4738 |
coding->spec.ccl.cr_carryover = 0; |
4739 |
if (coding->eol_type == CODING_EOL_UNDECIDED) |
4740 |
{ |
4741 |
/* Here, to avoid the call of setup_coding_system, we directly |
4742 |
call detect_eol_type. */ |
4743 |
coding->eol_type = detect_eol_type (ptr, bytes, &dummy); |
4744 |
if (coding->eol_type == CODING_EOL_INCONSISTENT) |
4745 |
coding->eol_type = CODING_EOL_LF; |
4746 |
if (coding->eol_type != CODING_EOL_UNDECIDED) |
4747 |
{ |
4748 |
val = Fget (coding->symbol, Qeol_type); |
4749 |
if (VECTORP (val) && XVECTOR (val)->size == 3) |
4750 |
coding->symbol = XVECTOR (val)->contents[coding->eol_type]; |
4751 |
} |
4752 |
coding->mode |= CODING_MODE_INHIBIT_INCONSISTENT_EOL; |
4753 |
} |
4754 |
|
4755 |
if (coding->eol_type == CODING_EOL_LF |
4756 |
|| coding->eol_type == CODING_EOL_UNDECIDED) |
4757 |
{ |
4758 |
/* We have nothing to do. */ |
4759 |
ptr = pend; |
4760 |
} |
4761 |
else if (coding->eol_type == CODING_EOL_CRLF) |
4762 |
{ |
4763 |
unsigned char *pstart = ptr, *p = ptr; |
4764 |
|
4765 |
if (! (coding->mode & CODING_MODE_LAST_BLOCK) |
4766 |
&& *(pend - 1) == '\r') |
4767 |
{ |
4768 |
/* If the last character is CR, we can't handle it here |
4769 |
because LF will be in the not-yet-decoded source text. |
4770 |
Record that the CR is not yet processed. */ |
4771 |
coding->spec.ccl.cr_carryover = 1; |
4772 |
coding->produced--; |
4773 |
coding->produced_char--; |
4774 |
pend--; |
4775 |
} |
4776 |
while (ptr < pend) |
4777 |
{ |
4778 |
if (*ptr == '\r') |
4779 |
{ |
4780 |
if (ptr + 1 < pend && *(ptr + 1) == '\n') |
4781 |
{ |
4782 |
*p++ = '\n'; |
4783 |
ptr += 2; |
4784 |
} |
4785 |
else |
4786 |
{ |
4787 |
if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) |
4788 |
goto undo_eol_conversion; |
4789 |
*p++ = *ptr++; |
4790 |
} |
4791 |
} |
4792 |
else if (*ptr == '\n' |
4793 |
&& coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) |
4794 |
goto undo_eol_conversion; |
4795 |
else |
4796 |
*p++ = *ptr++; |
4797 |
continue; |
4798 |
|
4799 |
undo_eol_conversion: |
4800 |
/* We have faced with inconsistent EOL format at PTR. |
4801 |
Convert all LFs before PTR back to CRLFs. */ |
4802 |
for (p--, ptr--; p >= pstart; p--) |
4803 |
{ |
4804 |
if (*p == '\n') |
4805 |
*ptr-- = '\n', *ptr-- = '\r'; |
4806 |
else |
4807 |
*ptr-- = *p; |
4808 |
} |
4809 |
/* If carryover is recorded, cancel it because we don't |
4810 |
convert CRLF anymore. */ |
4811 |
if (coding->spec.ccl.cr_carryover) |
4812 |
{ |
4813 |
coding->spec.ccl.cr_carryover = 0; |
4814 |
coding->produced++; |
4815 |
coding->produced_char++; |
4816 |
pend++; |
4817 |
} |
4818 |
p = ptr = pend; |
4819 |
coding->eol_type = CODING_EOL_LF; |
4820 |
coding->symbol = saved_coding_symbol; |
4821 |
} |
4822 |
if (p < pend) |
4823 |
{ |
4824 |
/* As each two-byte sequence CRLF was converted to LF, (PEND |
4825 |
- P) is the number of deleted characters. */ |
4826 |
coding->produced -= pend - p; |
4827 |
coding->produced_char -= pend - p; |
4828 |
} |
4829 |
} |
4830 |
else /* i.e. coding->eol_type == CODING_EOL_CR */ |
4831 |
{ |
4832 |
unsigned char *p = ptr; |
4833 |
|
4834 |
for (; ptr < pend; ptr++) |
4835 |
{ |
4836 |
if (*ptr == '\r') |
4837 |
*ptr = '\n'; |
4838 |
else if (*ptr == '\n' |
4839 |
&& coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) |
4840 |
{ |
4841 |
for (; p < ptr; p++) |
4842 |
{ |
4843 |
if (*p == '\n') |
4844 |
*p = '\r'; |
4845 |
} |
4846 |
ptr = pend; |
4847 |
coding->eol_type = CODING_EOL_LF; |
4848 |
coding->symbol = saved_coding_symbol; |
4849 |
} |
4850 |
} |
4851 |
} |
4852 |
} |
4853 |
|
4854 |
/* See "GENERAL NOTES about `decode_coding_XXX ()' functions". Before |
4855 |
decoding, it may detect coding system and format of end-of-line if |
4856 |
those are not yet decided. The source should be unibyte, the |
4857 |
result is multibyte if CODING->dst_multibyte is nonzero, else |
4858 |
unibyte. */ |
4859 |
|
4860 |
int |
4861 |
decode_coding (coding, source, destination, src_bytes, dst_bytes) |
4862 |
struct coding_system *coding; |
4863 |
const unsigned char *source; |
4864 |
unsigned char *destination; |
4865 |
int src_bytes, dst_bytes; |
4866 |
{ |
4867 |
int extra = 0; |
4868 |
|
4869 |
if (coding->type == coding_type_undecided) |
4870 |
detect_coding (coding, source, src_bytes); |
4871 |
|
4872 |
if (coding->eol_type == CODING_EOL_UNDECIDED |
4873 |
&& coding->type != coding_type_ccl) |
4874 |
{ |
4875 |
detect_eol (coding, source, src_bytes); |
4876 |
/* We had better recover the original eol format if we |
4877 |
encounter an inconsistent eol format while decoding. */ |
4878 |
coding->mode |= CODING_MODE_INHIBIT_INCONSISTENT_EOL; |
4879 |
} |
4880 |
|
4881 |
coding->produced = coding->produced_char = 0; |
4882 |
coding->consumed = coding->consumed_char = 0; |
4883 |
coding->errors = 0; |
4884 |
coding->result = CODING_FINISH_NORMAL; |
4885 |
|
4886 |
switch (coding->type) |
4887 |
{ |
4888 |
case coding_type_sjis: |
4889 |
decode_coding_sjis_big5 (coding, source, destination, |
4890 |
src_bytes, dst_bytes, 1); |
4891 |
break; |
4892 |
|
4893 |
case coding_type_iso2022: |
4894 |
decode_coding_iso2022 (coding, source, destination, |
4895 |
src_bytes, dst_bytes); |
4896 |
break; |
4897 |
|
4898 |
case coding_type_big5: |
4899 |
decode_coding_sjis_big5 (coding, source, destination, |
4900 |
src_bytes, dst_bytes, 0); |
4901 |
break; |
4902 |
|
4903 |
case coding_type_emacs_mule: |
4904 |
decode_coding_emacs_mule (coding, source, destination, |
4905 |
src_bytes, dst_bytes); |
4906 |
break; |
4907 |
|
4908 |
case coding_type_ccl: |
4909 |
if (coding->spec.ccl.cr_carryover) |
4910 |
{ |
4911 |
/* Put the CR which was not processed by the previous call |
4912 |
of decode_eol_post_ccl in DESTINATION. It will be |
4913 |
decoded together with the following LF by the call to |
4914 |
decode_eol_post_ccl below. */ |
4915 |
*destination = '\r'; |
4916 |
coding->produced++; |
4917 |
coding->produced_char++; |
4918 |
dst_bytes--; |
4919 |
extra = coding->spec.ccl.cr_carryover; |
4920 |
} |
4921 |
ccl_coding_driver (coding, source, destination + extra, |
4922 |
src_bytes, dst_bytes, 0); |
4923 |
if (coding->eol_type != CODING_EOL_LF) |
4924 |
{ |
4925 |
coding->produced += extra; |
4926 |
coding->produced_char += extra; |
4927 |
decode_eol_post_ccl (coding, destination, coding->produced); |
4928 |
} |
4929 |
break; |
4930 |
|
4931 |
default: |
4932 |
decode_eol (coding, source, destination, src_bytes, dst_bytes); |
4933 |
} |
4934 |
|
4935 |
if (coding->result == CODING_FINISH_INSUFFICIENT_SRC |
4936 |
&& coding->mode & CODING_MODE_LAST_BLOCK |
4937 |
&& coding->consumed == src_bytes) |
4938 |
coding->result = CODING_FINISH_NORMAL; |
4939 |
|
4940 |
if (coding->mode & CODING_MODE_LAST_BLOCK |
4941 |
&& coding->result == CODING_FINISH_INSUFFICIENT_SRC) |
4942 |
{ |
4943 |
const unsigned char *src = source + coding->consumed; |
4944 |
unsigned char *dst = destination + coding->produced; |
4945 |
|
4946 |
src_bytes -= coding->consumed; |
4947 |
coding->errors++; |
4948 |
if (COMPOSING_P (coding)) |
4949 |
DECODE_COMPOSITION_END ('1'); |
4950 |
while (src_bytes--) |
4951 |
{ |
4952 |
int c = *src++; |
4953 |
dst += CHAR_STRING (c, dst); |
4954 |
coding->produced_char++; |
4955 |
} |
4956 |
coding->consumed = coding->consumed_char = src - source; |
4957 |
coding->produced = dst - destination; |
4958 |
coding->result = CODING_FINISH_NORMAL; |
4959 |
} |
4960 |
|
4961 |
if (!coding->dst_multibyte) |
4962 |
{ |
4963 |
coding->produced = str_as_unibyte (destination, coding->produced); |
4964 |
coding->produced_char = coding->produced; |
4965 |
} |
4966 |
|
4967 |
return coding->result; |
4968 |
} |
4969 |
|
4970 |
/* See "GENERAL NOTES about `encode_coding_XXX ()' functions". The |
4971 |
multibyteness of the source is CODING->src_multibyte, the |
4972 |
multibyteness of the result is always unibyte. */ |
4973 |
|
4974 |
int |
4975 |
encode_coding (coding, source, destination, src_bytes, dst_bytes) |
4976 |
struct coding_system *coding; |
4977 |
const unsigned char *source; |
4978 |
unsigned char *destination; |
4979 |
int src_bytes, dst_bytes; |
4980 |
{ |
4981 |
coding->produced = coding->produced_char = 0; |
4982 |
coding->consumed = coding->consumed_char = 0; |
4983 |
coding->errors = 0; |
4984 |
coding->result = CODING_FINISH_NORMAL; |
4985 |
|
4986 |
switch (coding->type) |
4987 |
{ |
4988 |
case coding_type_sjis: |
4989 |
encode_coding_sjis_big5 (coding, source, destination, |
4990 |
src_bytes, dst_bytes, 1); |
4991 |
break; |
4992 |
|
4993 |
case coding_type_iso2022: |
4994 |
encode_coding_iso2022 (coding, source, destination, |
4995 |
src_bytes, dst_bytes); |
4996 |
break; |
4997 |
|
4998 |
case coding_type_big5: |
4999 |
encode_coding_sjis_big5 (coding, source, destination, |
5000 |
src_bytes, dst_bytes, 0); |
5001 |
break; |
5002 |
|
5003 |
case coding_type_emacs_mule: |
5004 |
encode_coding_emacs_mule (coding, source, destination, |
5005 |
src_bytes, dst_bytes); |
5006 |
break; |
5007 |
|
5008 |
case coding_type_ccl: |
5009 |
ccl_coding_driver (coding, source, destination, |
5010 |
src_bytes, dst_bytes, 1); |
5011 |
break; |
5012 |
|
5013 |
default: |
5014 |
encode_eol (coding, source, destination, src_bytes, dst_bytes); |
5015 |
} |
5016 |
|
5017 |
if (coding->mode & CODING_MODE_LAST_BLOCK |
5018 |
&& coding->result == CODING_FINISH_INSUFFICIENT_SRC) |
5019 |
{ |
5020 |
const unsigned char *src = source + coding->consumed; |
5021 |
unsigned char *dst = destination + coding->produced; |
5022 |
|
5023 |
if (coding->type == coding_type_iso2022) |
5024 |
ENCODE_RESET_PLANE_AND_REGISTER; |
5025 |
if (COMPOSING_P (coding)) |
5026 |
*dst++ = ISO_CODE_ESC, *dst++ = '1'; |
5027 |
if (coding->consumed < src_bytes) |
5028 |
{ |
5029 |
int len = src_bytes - coding->consumed; |
5030 |
|
5031 |
BCOPY_SHORT (src, dst, len); |
5032 |
if (coding->src_multibyte) |
5033 |
len = str_as_unibyte (dst, len); |
5034 |
dst += len; |
5035 |
coding->consumed = src_bytes; |
5036 |
} |
5037 |
coding->produced = coding->produced_char = dst - destination; |
5038 |
coding->result = CODING_FINISH_NORMAL; |
5039 |
} |
5040 |
|
5041 |
if (coding->result == CODING_FINISH_INSUFFICIENT_SRC |
5042 |
&& coding->consumed == src_bytes) |
5043 |
coding->result = CODING_FINISH_NORMAL; |
5044 |
|
5045 |
return coding->result; |
5046 |
} |
5047 |
|
5048 |
/* Scan text in the region between *BEG and *END (byte positions), |
5049 |
skip characters which we don't have to decode by coding system |
5050 |
CODING at the head and tail, then set *BEG and *END to the region |
5051 |
of the text we actually have to convert. The caller should move |
5052 |
the gap out of the region in advance if the region is from a |
5053 |
buffer. |
5054 |
|
5055 |
If STR is not NULL, *BEG and *END are indices into STR. */ |
5056 |
|
5057 |
static void |
5058 |
shrink_decoding_region (beg, end, coding, str) |
5059 |
int *beg, *end; |
5060 |
struct coding_system *coding; |
5061 |
unsigned char *str; |
5062 |
{ |
5063 |
unsigned char *begp_orig, *begp, *endp_orig, *endp, c; |
5064 |
int eol_conversion; |
5065 |
Lisp_Object translation_table; |
5066 |
|
5067 |
if (coding->type == coding_type_ccl |
5068 |
|| coding->type == coding_type_undecided |
5069 |
|| coding->eol_type != CODING_EOL_LF |
5070 |
|| !NILP (coding->post_read_conversion) |
5071 |
|| coding->composing != COMPOSITION_DISABLED) |
5072 |
{ |
5073 |
/* We can't skip any data. */ |
5074 |
return; |
5075 |
} |
5076 |
if (coding->type == coding_type_no_conversion |
5077 |
|| coding->type == coding_type_raw_text |
5078 |
|| coding->type == coding_type_emacs_mule) |
5079 |
{ |
5080 |
/* We need no conversion, but don't have to skip any data here. |
5081 |
Decoding routine handles them effectively anyway. */ |
5082 |
return; |
5083 |
} |
5084 |
|
5085 |
translation_table = coding->translation_table_for_decode; |
5086 |
if (NILP (translation_table) && !NILP (Venable_character_translation)) |
5087 |
translation_table = Vstandard_translation_table_for_decode; |
5088 |
if (CHAR_TABLE_P (translation_table)) |
5089 |
{ |
5090 |
int i; |
5091 |
for (i = 0; i < 128; i++) |
5092 |
if (!NILP (CHAR_TABLE_REF (translation_table, i))) |
5093 |
break; |
5094 |
if (i < 128) |
5095 |
/* Some ASCII character should be translated. We give up |
5096 |
shrinking. */ |
5097 |
return; |
5098 |
} |
5099 |
|
5100 |
if (coding->heading_ascii >= 0) |
5101 |
/* Detection routine has already found how much we can skip at the |
5102 |
head. */ |
5103 |
*beg += coding->heading_ascii; |
5104 |
|
5105 |
if (str) |
5106 |
{ |
5107 |
begp_orig = begp = str + *beg; |
5108 |
endp_orig = endp = str + *end; |
5109 |
} |
5110 |
else |
5111 |
{ |
5112 |
begp_orig = begp = BYTE_POS_ADDR (*beg); |
5113 |
endp_orig = endp = begp + *end - *beg; |
5114 |
} |
5115 |
|
5116 |
eol_conversion = (coding->eol_type == CODING_EOL_CR |
5117 |
|| coding->eol_type == CODING_EOL_CRLF); |
5118 |
|
5119 |
switch (coding->type) |
5120 |
{ |
5121 |
case coding_type_sjis: |
5122 |
case coding_type_big5: |
5123 |
/* We can skip all ASCII characters at the head. */ |
5124 |
if (coding->heading_ascii < 0) |
5125 |
{ |
5126 |
if (eol_conversion) |
5127 |
while (begp < endp && *begp < 0x80 && *begp != '\r') begp++; |
5128 |
else |
5129 |
while (begp < endp && *begp < 0x80) begp++; |
5130 |
} |
5131 |
/* We can skip all ASCII characters at the tail except for the |
5132 |
second byte of SJIS or BIG5 code. */ |
5133 |
if (eol_conversion) |
5134 |
while (begp < endp && endp[-1] < 0x80 && endp[-1] != '\r') endp--; |
5135 |
else |
5136 |
while (begp < endp && endp[-1] < 0x80) endp--; |
5137 |
/* Do not consider LF as ascii if preceded by CR, since that |
5138 |
confuses eol decoding. */ |
5139 |
if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n') |
5140 |
endp++; |
5141 |
if (begp < endp && endp < endp_orig && endp[-1] >= 0x80) |
5142 |
endp++; |
5143 |
break; |
5144 |
|
5145 |
case coding_type_iso2022: |
5146 |
if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, 0) != CHARSET_ASCII) |
5147 |
/* We can't skip any data. */ |
5148 |
break; |
5149 |
if (coding->heading_ascii < 0) |
5150 |
{ |
5151 |
/* We can skip all ASCII characters at the head except for a |
5152 |
few control codes. */ |
5153 |
while (begp < endp && (c = *begp) < 0x80 |
5154 |
&& c != ISO_CODE_CR && c != ISO_CODE_SO |
5155 |
&& c != ISO_CODE_SI && c != ISO_CODE_ESC |
5156 |
&& (!eol_conversion || c != ISO_CODE_LF)) |
5157 |
begp++; |
5158 |
} |
5159 |
switch (coding->category_idx) |
5160 |
{ |
5161 |
case CODING_CATEGORY_IDX_ISO_8_1: |
5162 |
case CODING_CATEGORY_IDX_ISO_8_2: |
5163 |
/* We can skip all ASCII characters at the tail. */ |
5164 |
if (eol_conversion) |
5165 |
while (begp < endp && (c = endp[-1]) < 0x80 && c != '\r') endp--; |
5166 |
else |
5167 |
while (begp < endp && endp[-1] < 0x80) endp--; |
5168 |
/* Do not consider LF as ascii if preceded by CR, since that |
5169 |
confuses eol decoding. */ |
5170 |
if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n') |
5171 |
endp++; |
5172 |
break; |
5173 |
|
5174 |
case CODING_CATEGORY_IDX_ISO_7: |
5175 |
case CODING_CATEGORY_IDX_ISO_7_TIGHT: |
5176 |
{ |
5177 |
/* We can skip all characters at the tail except for 8-bit |
5178 |
codes and ESC and the following 2-byte at the tail. */ |
5179 |
unsigned char *eight_bit = NULL; |
5180 |
|
5181 |
if (eol_conversion) |
5182 |
while (begp < endp |
5183 |
&& (c = endp[-1]) != ISO_CODE_ESC && c != '\r') |
5184 |
{ |
5185 |
if (!eight_bit && c & 0x80) eight_bit = endp; |
5186 |
endp--; |
5187 |
} |
5188 |
else |
5189 |
while (begp < endp |
5190 |
&& (c = endp[-1]) != ISO_CODE_ESC) |
5191 |
{ |
5192 |
if (!eight_bit && c & 0x80) eight_bit = endp; |
5193 |
endp--; |
5194 |
} |
5195 |
/* Do not consider LF as ascii if preceded by CR, since that |
5196 |
confuses eol decoding. */ |
5197 |
if (begp < endp && endp < endp_orig |
5198 |
&& endp[-1] == '\r' && endp[0] == '\n') |
5199 |
endp++; |
5200 |
if (begp < endp && endp[-1] == ISO_CODE_ESC) |
5201 |
{ |
5202 |
if (endp + 1 < endp_orig && end[0] == '(' && end[1] == 'B') |
5203 |
/* This is an ASCII designation sequence. We can |
5204 |
surely skip the tail. But, if we have |
5205 |
encountered an 8-bit code, skip only the codes |
5206 |
after that. */ |
5207 |
endp = eight_bit ? eight_bit : endp + 2; |
5208 |
else |
5209 |
/* Hmmm, we can't skip the tail. */ |
5210 |
endp = endp_orig; |
5211 |
} |
5212 |
else if (eight_bit) |
5213 |
endp = eight_bit; |
5214 |
} |
5215 |
} |
5216 |
break; |
5217 |
|
5218 |
default: |
5219 |
abort (); |
5220 |
} |
5221 |
*beg += begp - begp_orig; |
5222 |
*end += endp - endp_orig; |
5223 |
return; |
5224 |
} |
5225 |
|
5226 |
/* Like shrink_decoding_region but for encoding. */ |
5227 |
|
5228 |
static void |
5229 |
shrink_encoding_region (beg, end, coding, str) |
5230 |
int *beg, *end; |
5231 |
struct coding_system *coding; |
5232 |
unsigned char *str; |
5233 |
{ |
5234 |
unsigned char *begp_orig, *begp, *endp_orig, *endp; |
5235 |
int eol_conversion; |
5236 |
Lisp_Object translation_table; |
5237 |
|
5238 |
if (coding->type == coding_type_ccl |
5239 |
|| coding->eol_type == CODING_EOL_CRLF |
5240 |
|| coding->eol_type == CODING_EOL_CR |
5241 |
|| (coding->cmp_data && coding->cmp_data->used > 0)) |
5242 |
{ |
5243 |
/* We can't skip any data. */ |
5244 |
return; |
5245 |
} |
5246 |
if (coding->type == coding_type_no_conversion |
5247 |
|| coding->type == coding_type_raw_text |
5248 |
|| coding->type == coding_type_emacs_mule |
5249 |
|| coding->type == coding_type_undecided) |
5250 |
{ |
5251 |
/* We need no conversion, but don't have to skip any data here. |
5252 |
Encoding routine handles them effectively anyway. */ |
5253 |
return; |
5254 |
} |
5255 |
|
5256 |
translation_table = coding->translation_table_for_encode; |
5257 |
if (NILP (translation_table) && !NILP (Venable_character_translation)) |
5258 |
translation_table = Vstandard_translation_table_for_encode; |
5259 |
if (CHAR_TABLE_P (translation_table)) |
5260 |
{ |
5261 |
int i; |
5262 |
for (i = 0; i < 128; i++) |
5263 |
if (!NILP (CHAR_TABLE_REF (translation_table, i))) |
5264 |
break; |
5265 |
if (i < 128) |
5266 |
/* Some ASCII character should be translated. We give up |
5267 |
shrinking. */ |
5268 |
return; |
5269 |
} |
5270 |
|
5271 |
if (str) |
5272 |
{ |
5273 |
begp_orig = begp = str + *beg; |
5274 |
endp_orig = endp = str + *end; |
5275 |
} |
5276 |
else |
5277 |
{ |
5278 |
begp_orig = begp = BYTE_POS_ADDR (*beg); |
5279 |
endp_orig = endp = begp + *end - *beg; |
5280 |
} |
5281 |
|
5282 |
eol_conversion = (coding->eol_type == CODING_EOL_CR |
5283 |
|| coding->eol_type == CODING_EOL_CRLF); |
5284 |
|
5285 |
/* Here, we don't have to check coding->pre_write_conversion because |
5286 |
the caller is expected to have handled it already. */ |
5287 |
switch (coding->type) |
5288 |
{ |
5289 |
case coding_type_iso2022: |
5290 |
if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, 0) != CHARSET_ASCII) |
5291 |
/* We can't skip any data. */ |
5292 |
break; |
5293 |
if (coding->flags & CODING_FLAG_ISO_DESIGNATE_AT_BOL) |
5294 |
{ |
5295 |
unsigned char *bol = begp; |
5296 |
while (begp < endp && *begp < 0x80) |
5297 |
{ |
5298 |
begp++; |
5299 |
if (begp[-1] == '\n') |
5300 |
bol = begp; |
5301 |
} |
5302 |
begp = bol; |
5303 |
goto label_skip_tail; |
5304 |
} |
5305 |
/* fall down ... */ |
5306 |
|
5307 |
case coding_type_sjis: |
5308 |
case coding_type_big5: |
5309 |
/* We can skip all ASCII characters at the head and tail. */ |
5310 |
if (eol_conversion) |
5311 |
while (begp < endp && *begp < 0x80 && *begp != '\n') begp++; |
5312 |
else |
5313 |
while (begp < endp && *begp < 0x80) begp++; |
5314 |
label_skip_tail: |
5315 |
if (eol_conversion) |
5316 |
while (begp < endp && endp[-1] < 0x80 && endp[-1] != '\n') endp--; |
5317 |
else |
5318 |
while (begp < endp && *(endp - 1) < 0x80) endp--; |
5319 |
break; |
5320 |
|
5321 |
default: |
5322 |
abort (); |
5323 |
} |
5324 |
|
5325 |
*beg += begp - begp_orig; |
5326 |
*end += endp - endp_orig; |
5327 |
return; |
5328 |
} |
5329 |
|
5330 |
/* As shrinking conversion region requires some overhead, we don't try |
5331 |
shrinking if the length of conversion region is less than this |
5332 |
value. */ |
5333 |
static int shrink_conversion_region_threshhold = 1024; |
5334 |
|
5335 |
#define SHRINK_CONVERSION_REGION(beg, end, coding, str, encodep) \ |
5336 |
do { \ |
5337 |
if (*(end) - *(beg) > shrink_conversion_region_threshhold) \ |
5338 |
{ \ |
5339 |
if (encodep) shrink_encoding_region (beg, end, coding, str); \ |
5340 |
else shrink_decoding_region (beg, end, coding, str); \ |
5341 |
} \ |
5342 |
} while (0) |
5343 |
|
5344 |
static Lisp_Object |
5345 |
code_convert_region_unwind (arg) |
5346 |
Lisp_Object arg; |
5347 |
{ |
5348 |
inhibit_pre_post_conversion = 0; |
5349 |
Vlast_coding_system_used = arg; |
5350 |
return Qnil; |
5351 |
} |
5352 |
|
5353 |
/* Store information about all compositions in the range FROM and TO |
5354 |
of OBJ in memory blocks pointed by CODING->cmp_data. OBJ is a |
5355 |
buffer or a string, defaults to the current buffer. */ |
5356 |
|
5357 |
void |
5358 |
coding_save_composition (coding, from, to, obj) |
5359 |
struct coding_system *coding; |
5360 |
int from, to; |
5361 |
Lisp_Object obj; |
5362 |
{ |
5363 |
Lisp_Object prop; |
5364 |
int start, end; |
5365 |
|
5366 |
if (coding->composing == COMPOSITION_DISABLED) |
5367 |
return; |
5368 |
if (!coding->cmp_data) |
5369 |
coding_allocate_composition_data (coding, from); |
5370 |
if (!find_composition (from, to, &start, &end, &prop, obj) |
5371 |
|| end > to) |
5372 |
return; |
5373 |
if (start < from |
5374 |
&& (!find_composition (end, to, &start, &end, &prop, obj) |
5375 |
|| end > to)) |
5376 |
return; |
5377 |
coding->composing = COMPOSITION_NO; |
5378 |
do |
5379 |
{ |
5380 |
if (COMPOSITION_VALID_P (start, end, prop)) |
5381 |
{ |
5382 |
enum composition_method method = COMPOSITION_METHOD (prop); |
5383 |
if (coding->cmp_data->used + COMPOSITION_DATA_MAX_BUNCH_LENGTH |
5384 |
>= COMPOSITION_DATA_SIZE) |
5385 |
coding_allocate_composition_data (coding, from); |
5386 |
/* For relative composition, we remember start and end |
5387 |
positions, for the other compositions, we also remember |
5388 |
components. */ |
5389 |
CODING_ADD_COMPOSITION_START (coding, start - from, method); |
5390 |
if (method != COMPOSITION_RELATIVE) |
5391 |
{ |
5392 |
/* We must store a*/ |
5393 |
Lisp_Object val, ch; |
5394 |
|
5395 |
val = COMPOSITION_COMPONENTS (prop); |
5396 |
if (CONSP (val)) |
5397 |
while (CONSP (val)) |
5398 |
{ |
5399 |
ch = XCAR (val), val = XCDR (val); |
5400 |
CODING_ADD_COMPOSITION_COMPONENT (coding, XINT (ch)); |
5401 |
} |
5402 |
else if (VECTORP (val) || STRINGP (val)) |
5403 |
{ |
5404 |
int len = (VECTORP (val) |
5405 |
? XVECTOR (val)->size : SCHARS (val)); |
5406 |
int i; |
5407 |
for (i = 0; i < len; i++) |
5408 |
{ |
5409 |
ch = (STRINGP (val) |
5410 |
? Faref (val, make_number (i)) |
5411 |
: XVECTOR (val)->contents[i]); |
5412 |
CODING_ADD_COMPOSITION_COMPONENT (coding, XINT (ch)); |
5413 |
} |
5414 |
} |
5415 |
else /* INTEGERP (val) */ |
5416 |
CODING_ADD_COMPOSITION_COMPONENT (coding, XINT (val)); |
5417 |
} |
5418 |
CODING_ADD_COMPOSITION_END (coding, end - from); |
5419 |
} |
5420 |
start = end; |
5421 |
} |
5422 |
while (start < to |
5423 |
&& find_composition (start, to, &start, &end, &prop, obj) |
5424 |
&& end <= to); |
5425 |
|
5426 |
/* Make coding->cmp_data point to the first memory block. */ |
5427 |
while (coding->cmp_data->prev) |
5428 |
coding->cmp_data = coding->cmp_data->prev; |
5429 |
coding->cmp_data_start = 0; |
5430 |
} |
5431 |
|
5432 |
/* Reflect the saved information about compositions to OBJ. |
5433 |
CODING->cmp_data points to a memory block for the information. OBJ |
5434 |
is a buffer or a string, defaults to the current buffer. */ |
5435 |
|
5436 |
void |
5437 |
coding_restore_composition (coding, obj) |
5438 |
struct coding_system *coding; |
5439 |
Lisp_Object obj; |
5440 |
{ |
5441 |
struct composition_data *cmp_data = coding->cmp_data; |
5442 |
|
5443 |
if (!cmp_data) |
5444 |
return; |
5445 |
|
5446 |
while (cmp_data->prev) |
5447 |
cmp_data = cmp_data->prev; |
5448 |
|
5449 |
while (cmp_data) |
5450 |
{ |
5451 |
int i; |
5452 |
|
5453 |
for (i = 0; i < cmp_data->used && cmp_data->data[i] > 0; |
5454 |
i += cmp_data->data[i]) |
5455 |
{ |
5456 |
int *data = cmp_data->data + i; |
5457 |
enum composition_method method = (enum composition_method) data[3]; |
5458 |
Lisp_Object components; |
5459 |
|
5460 |
if (data[0] < 0 || i + data[0] > cmp_data->used) |
5461 |
/* Invalid composition data. */ |
5462 |
break; |
5463 |
|
5464 |
if (method == COMPOSITION_RELATIVE) |
5465 |
components = Qnil; |
5466 |
else |
5467 |
{ |
5468 |
int len = data[0] - 4, j; |
5469 |
Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
5470 |
|
5471 |
if (method == COMPOSITION_WITH_RULE_ALTCHARS |
5472 |
&& len % 2 == 0) |
5473 |
len --; |
5474 |
if (len < 1) |
5475 |
/* Invalid composition data. */ |
5476 |
break; |
5477 |
for (j = 0; j < len; j++) |
5478 |
args[j] = make_number (data[4 + j]); |
5479 |
components = (method == COMPOSITION_WITH_ALTCHARS |
5480 |
? Fstring (len, args) |
5481 |
: Fvector (len, args)); |
5482 |
} |
5483 |
compose_text (data[1], data[2], components, Qnil, obj); |
5484 |
} |
5485 |
cmp_data = cmp_data->next; |
5486 |
} |
5487 |
} |
5488 |
|
5489 |
/* Decode (if ENCODEP is zero) or encode (if ENCODEP is nonzero) the |
5490 |
text from FROM to TO (byte positions are FROM_BYTE and TO_BYTE) by |
5491 |
coding system CODING, and return the status code of code conversion |
5492 |
(currently, this value has no meaning). |
5493 |
|
5494 |
How many characters (and bytes) are converted to how many |
5495 |
characters (and bytes) are recorded in members of the structure |
5496 |
CODING. |
5497 |
|
5498 |
If REPLACE is nonzero, we do various things as if the original text |
5499 |
is deleted and a new text is inserted. See the comments in |
5500 |
replace_range (insdel.c) to know what we are doing. |
5501 |
|
5502 |
If REPLACE is zero, it is assumed that the source text is unibyte. |
5503 |
Otherwise, it is assumed that the source text is multibyte. */ |
5504 |
|
5505 |
int |
5506 |
code_convert_region (from, from_byte, to, to_byte, coding, encodep, replace) |
5507 |
int from, from_byte, to, to_byte, encodep, replace; |
5508 |
struct coding_system *coding; |
5509 |
{ |
5510 |
int len = to - from, len_byte = to_byte - from_byte; |
5511 |
int nchars_del = 0, nbytes_del = 0; |
5512 |
int require, inserted, inserted_byte; |
5513 |
int head_skip, tail_skip, total_skip = 0; |
5514 |
Lisp_Object saved_coding_symbol; |
5515 |
int first = 1; |
5516 |
unsigned char *src, *dst; |
5517 |
Lisp_Object deletion; |
5518 |
int orig_point = PT, orig_len = len; |
5519 |
int prev_Z; |
5520 |
int multibyte_p = !NILP (current_buffer->enable_multibyte_characters); |
5521 |
|
5522 |
deletion = Qnil; |
5523 |
saved_coding_symbol = coding->symbol; |
5524 |
|
5525 |
if (from < PT && PT < to) |
5526 |
{ |
5527 |
TEMP_SET_PT_BOTH (from, from_byte); |
5528 |
orig_point = from; |
5529 |
} |
5530 |
|
5531 |
if (replace) |
5532 |
{ |
5533 |
int saved_from = from; |
5534 |
int saved_inhibit_modification_hooks; |
5535 |
|
5536 |
prepare_to_modify_buffer (from, to, &from); |
5537 |
if (saved_from != from) |
5538 |
{ |
5539 |
to = from + len; |
5540 |
from_byte = CHAR_TO_BYTE (from), to_byte = CHAR_TO_BYTE (to); |
5541 |
len_byte = to_byte - from_byte; |
5542 |
} |
5543 |
|
5544 |
/* The code conversion routine can not preserve text properties |
5545 |
for now. So, we must remove all text properties in the |
5546 |
region. Here, we must suppress all modification hooks. */ |
5547 |
saved_inhibit_modification_hooks = inhibit_modification_hooks; |
5548 |
inhibit_modification_hooks = 1; |
5549 |
Fset_text_properties (make_number (from), make_number (to), Qnil, Qnil); |
5550 |
inhibit_modification_hooks = saved_inhibit_modification_hooks; |
5551 |
} |
5552 |
|
5553 |
if (! encodep && CODING_REQUIRE_DETECTION (coding)) |
5554 |
{ |
5555 |
/* We must detect encoding of text and eol format. */ |
5556 |
|
5557 |
if (from < GPT && to > GPT) |
5558 |
move_gap_both (from, from_byte); |
5559 |
if (coding->type == coding_type_undecided) |
5560 |
{ |
5561 |
detect_coding (coding, BYTE_POS_ADDR (from_byte), len_byte); |
5562 |
if (coding->type == coding_type_undecided) |
5563 |
{ |
5564 |
/* It seems that the text contains only ASCII, but we |
5565 |
should not leave it undecided because the deeper |
5566 |
decoding routine (decode_coding) tries to detect the |
5567 |
encodings again in vain. */ |
5568 |
coding->type = coding_type_emacs_mule; |
5569 |
coding->category_idx = CODING_CATEGORY_IDX_EMACS_MULE; |
5570 |
/* As emacs-mule decoder will handle composition, we |
5571 |
need this setting to allocate coding->cmp_data |
5572 |
later. */ |
5573 |
coding->composing = COMPOSITION_NO; |
5574 |
} |
5575 |
} |
5576 |
if (coding->eol_type == CODING_EOL_UNDECIDED |
5577 |
&& coding->type != coding_type_ccl) |
5578 |
{ |
5579 |
detect_eol (coding, BYTE_POS_ADDR (from_byte), len_byte); |
5580 |
if (coding->eol_type == CODING_EOL_UNDECIDED) |
5581 |
coding->eol_type = CODING_EOL_LF; |
5582 |
/* We had better recover the original eol format if we |
5583 |
encounter an inconsistent eol format while decoding. */ |
5584 |
coding->mode |= CODING_MODE_INHIBIT_INCONSISTENT_EOL; |
5585 |
} |
5586 |
} |
5587 |
|
5588 |
/* Now we convert the text. */ |
5589 |
|
5590 |
/* For encoding, we must process pre-write-conversion in advance. */ |
5591 |
if (! inhibit_pre_post_conversion |
5592 |
&& encodep |
5593 |
&& SYMBOLP (coding->pre_write_conversion) |
5594 |
&& ! NILP (Ffboundp (coding->pre_write_conversion))) |
5595 |
{ |
5596 |
/* The function in pre-write-conversion may put a new text in a |
5597 |
new buffer. */ |
5598 |
struct buffer *prev = current_buffer; |
5599 |
Lisp_Object new; |
5600 |
|
5601 |
record_unwind_protect (code_convert_region_unwind, |
5602 |
Vlast_coding_system_used); |
5603 |
/* We should not call any more pre-write/post-read-conversion |
5604 |
functions while this pre-write-conversion is running. */ |
5605 |
inhibit_pre_post_conversion = 1; |
5606 |
call2 (coding->pre_write_conversion, |
5607 |
make_number (from), make_number (to)); |
5608 |
inhibit_pre_post_conversion = 0; |
5609 |
/* Discard the unwind protect. */ |
5610 |
specpdl_ptr--; |
5611 |
|
5612 |
if (current_buffer != prev) |
5613 |
{ |
5614 |
len = ZV - BEGV; |
5615 |
new = Fcurrent_buffer (); |
5616 |
set_buffer_internal_1 (prev); |
5617 |
del_range_2 (from, from_byte, to, to_byte, 0); |
5618 |
TEMP_SET_PT_BOTH (from, from_byte); |
5619 |
insert_from_buffer (XBUFFER (new), 1, len, 0); |
5620 |
Fkill_buffer (new); |
5621 |
if (orig_point >= to) |
5622 |
orig_point += len - orig_len; |
5623 |
else if (orig_point > from) |
5624 |
orig_point = from; |
5625 |
orig_len = len; |
5626 |
to = from + len; |
5627 |
from_byte = CHAR_TO_BYTE (from); |
5628 |
to_byte = CHAR_TO_BYTE (to); |
5629 |
len_byte = to_byte - from_byte; |
5630 |
TEMP_SET_PT_BOTH (from, from_byte); |
5631 |
} |
5632 |
} |
5633 |
|
5634 |
if (replace) |
5635 |
{ |
5636 |
if (! EQ (current_buffer->undo_list, Qt)) |
5637 |
deletion = make_buffer_string_both (from, from_byte, to, to_byte, 1); |
5638 |
else |
5639 |
{ |
5640 |
nchars_del = to - from; |
5641 |
nbytes_del = to_byte - from_byte; |
5642 |
} |
5643 |
} |
5644 |
|
5645 |
if (coding->composing != COMPOSITION_DISABLED) |
5646 |
{ |
5647 |
if (encodep) |
5648 |
coding_save_composition (coding, from, to, Fcurrent_buffer ()); |
5649 |
else |
5650 |
coding_allocate_composition_data (coding, from); |
5651 |
} |
5652 |
|
5653 |
/* Try to skip the heading and tailing ASCIIs. We can't skip them |
5654 |
if we must run CCL program or there are compositions to |
5655 |
encode. */ |
5656 |
if (coding->type != coding_type_ccl |
5657 |
&& (! coding->cmp_data || coding->cmp_data->used == 0)) |
5658 |
{ |
5659 |
int from_byte_orig = from_byte, to_byte_orig = to_byte; |
5660 |
|
5661 |
if (from < GPT && GPT < to) |
5662 |
move_gap_both (from, from_byte); |
5663 |
SHRINK_CONVERSION_REGION (&from_byte, &to_byte, coding, NULL, encodep); |
5664 |
if (from_byte == to_byte |
5665 |
&& (encodep || NILP (coding->post_read_conversion)) |
5666 |
&& ! CODING_REQUIRE_FLUSHING (coding)) |
5667 |
{ |
5668 |
coding->produced = len_byte; |
5669 |
coding->produced_char = len; |
5670 |
if (!replace) |
5671 |
/* We must record and adjust for this new text now. */ |
5672 |
adjust_after_insert (from, from_byte_orig, to, to_byte_orig, len); |
5673 |
coding_free_composition_data (coding); |
5674 |
return 0; |
5675 |
} |
5676 |
|
5677 |
head_skip = from_byte - from_byte_orig; |
5678 |
tail_skip = to_byte_orig - to_byte; |
5679 |
total_skip = head_skip + tail_skip; |
5680 |
from += head_skip; |
5681 |
to -= tail_skip; |
5682 |
len -= total_skip; len_byte -= total_skip; |
5683 |
} |
5684 |
|
5685 |
/* For conversion, we must put the gap before the text in addition to |
5686 |
making the gap larger for efficient decoding. The required gap |
5687 |
size starts from 2000 which is the magic number used in make_gap. |
5688 |
But, after one batch of conversion, it will be incremented if we |
5689 |
find that it is not enough . */ |
5690 |
require = 2000; |
5691 |
|
5692 |
if (GAP_SIZE < require) |
5693 |
make_gap (require - GAP_SIZE); |
5694 |
move_gap_both (from, from_byte); |
5695 |
|
5696 |
inserted = inserted_byte = 0; |
5697 |
|
5698 |
GAP_SIZE += len_byte; |
5699 |
ZV -= len; |
5700 |
Z -= len; |
5701 |
ZV_BYTE -= len_byte; |
5702 |
Z_BYTE -= len_byte; |
5703 |
|
5704 |
if (GPT - BEG < BEG_UNCHANGED) |
5705 |
BEG_UNCHANGED = GPT - BEG; |
5706 |
if (Z - GPT < END_UNCHANGED) |
5707 |
END_UNCHANGED = Z - GPT; |
5708 |
|
5709 |
if (!encodep && coding->src_multibyte) |
5710 |
{ |
5711 |
/* Decoding routines expects that the source text is unibyte. |
5712 |
We must convert 8-bit characters of multibyte form to |
5713 |
unibyte. */ |
5714 |
int len_byte_orig = len_byte; |
5715 |
len_byte = str_as_unibyte (GAP_END_ADDR - len_byte, len_byte); |
5716 |
if (len_byte < len_byte_orig) |
5717 |
safe_bcopy (GAP_END_ADDR - len_byte_orig, GAP_END_ADDR - len_byte, |
5718 |
len_byte); |
5719 |
coding->src_multibyte = 0; |
5720 |
} |
5721 |
|
5722 |
for (;;) |
5723 |
{ |
5724 |
int result; |
5725 |
|
5726 |
/* The buffer memory is now: |
5727 |
+--------+converted-text+---------+-------original-text-------+---+ |
5728 |
|<-from->|<--inserted-->|---------|<--------len_byte--------->|---| |
5729 |
|<---------------------- GAP ----------------------->| */ |
5730 |
src = GAP_END_ADDR - len_byte; |
5731 |
dst = GPT_ADDR + inserted_byte; |
5732 |
|
5733 |
if (encodep) |
5734 |
result = encode_coding (coding, src, dst, len_byte, 0); |
5735 |
else |
5736 |
{ |
5737 |
if (coding->composing != COMPOSITION_DISABLED) |
5738 |
coding->cmp_data->char_offset = from + inserted; |
5739 |
result = decode_coding (coding, src, dst, len_byte, 0); |
5740 |
} |
5741 |
|
5742 |
/* The buffer memory is now: |
5743 |
+--------+-------converted-text----+--+------original-text----+---+ |
5744 |
|<-from->|<-inserted->|<-produced->|--|<-(len_byte-consumed)->|---| |
5745 |
|<---------------------- GAP ----------------------->| */ |
5746 |
|
5747 |
inserted += coding->produced_char; |
5748 |
inserted_byte += coding->produced; |
5749 |
len_byte -= coding->consumed; |
5750 |
|
5751 |
if (result == CODING_FINISH_INSUFFICIENT_CMP) |
5752 |
{ |
5753 |
coding_allocate_composition_data (coding, from + inserted); |
5754 |
continue; |
5755 |
} |
5756 |
|
5757 |
src += coding->consumed; |
5758 |
dst += coding->produced; |
5759 |
|
5760 |
if (result == CODING_FINISH_NORMAL) |
5761 |
{ |
5762 |
src += len_byte; |
5763 |
break; |
5764 |
} |
5765 |
if (! encodep && result == CODING_FINISH_INCONSISTENT_EOL) |
5766 |
{ |
5767 |
unsigned char *pend = dst, *p = pend - inserted_byte; |
5768 |
Lisp_Object eol_type; |
5769 |
|
5770 |
/* Encode LFs back to the original eol format (CR or CRLF). */ |
5771 |
if (coding->eol_type == CODING_EOL_CR) |
5772 |
{ |
5773 |
while (p < pend) if (*p++ == '\n') p[-1] = '\r'; |
5774 |
} |
5775 |
else |
5776 |
{ |
5777 |
int count = 0; |
5778 |
|
5779 |
while (p < pend) if (*p++ == '\n') count++; |
5780 |
if (src - dst < count) |
5781 |
{ |
5782 |
/* We don't have sufficient room for encoding LFs |
5783 |
back to CRLF. We must record converted and |
5784 |
not-yet-converted text back to the buffer |
5785 |
content, enlarge the gap, then record them out of |
5786 |
the buffer contents again. */ |
5787 |
int add = len_byte + inserted_byte; |
5788 |
|
5789 |
GAP_SIZE -= add; |
5790 |
ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; |
5791 |
GPT += inserted_byte; GPT_BYTE += inserted_byte; |
5792 |
make_gap (count - GAP_SIZE); |
5793 |
GAP_SIZE += add; |
5794 |
ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; |
5795 |
GPT -= inserted_byte; GPT_BYTE -= inserted_byte; |
5796 |
/* Don't forget to update SRC, DST, and PEND. */ |
5797 |
src = GAP_END_ADDR - len_byte; |
5798 |
dst = GPT_ADDR + inserted_byte; |
5799 |
pend = dst; |
5800 |
} |
5801 |
inserted += count; |
5802 |
inserted_byte += count; |
5803 |
coding->produced += count; |
5804 |
p = dst = pend + count; |
5805 |
while (count) |
5806 |
{ |
5807 |
*--p = *--pend; |
5808 |
if (*p == '\n') count--, *--p = '\r'; |
5809 |
} |
5810 |
} |
5811 |
|
5812 |
/* Suppress eol-format conversion in the further conversion. */ |
5813 |
coding->eol_type = CODING_EOL_LF; |
5814 |
|
5815 |
/* Set the coding system symbol to that for Unix-like EOL. */ |
5816 |
eol_type = Fget (saved_coding_symbol, Qeol_type); |
5817 |
if (VECTORP (eol_type) |
5818 |
&& XVECTOR (eol_type)->size == 3 |
5819 |
&& SYMBOLP (XVECTOR (eol_type)->contents[CODING_EOL_LF])) |
5820 |
coding->symbol = XVECTOR (eol_type)->contents[CODING_EOL_LF]; |
5821 |
else |
5822 |
coding->symbol = saved_coding_symbol; |
5823 |
|
5824 |
continue; |
5825 |
} |
5826 |
if (len_byte <= 0) |
5827 |
{ |
5828 |
if (coding->type != coding_type_ccl |
5829 |
|| coding->mode & CODING_MODE_LAST_BLOCK) |
5830 |
break; |
5831 |
coding->mode |= CODING_MODE_LAST_BLOCK; |
5832 |
continue; |
5833 |
} |
5834 |
if (result == CODING_FINISH_INSUFFICIENT_SRC) |
5835 |
{ |
5836 |
/* The source text ends in invalid codes. Let's just |
5837 |
make them valid buffer contents, and finish conversion. */ |
5838 |
if (multibyte_p) |
5839 |
{ |
5840 |
unsigned char *start = dst; |
5841 |
|
5842 |
inserted += len_byte; |
5843 |
while (len_byte--) |
5844 |
{ |
5845 |
int c = *src++; |
5846 |
dst += CHAR_STRING (c, dst); |
5847 |
} |
5848 |
|
5849 |
inserted_byte += dst - start; |
5850 |
} |
5851 |
else |
5852 |
{ |
5853 |
inserted += len_byte; |
5854 |
inserted_byte += len_byte; |
5855 |
while (len_byte--) |
5856 |
*dst++ = *src++; |
5857 |
} |
5858 |
break; |
5859 |
} |
5860 |
if (result == CODING_FINISH_INTERRUPT) |
5861 |
{ |
5862 |
/* The conversion procedure was interrupted by a user. */ |
5863 |
break; |
5864 |
} |
5865 |
/* Now RESULT == CODING_FINISH_INSUFFICIENT_DST */ |
5866 |
if (coding->consumed < 1) |
5867 |
{ |
5868 |
/* It's quite strange to require more memory without |
5869 |
consuming any bytes. Perhaps CCL program bug. */ |
5870 |
break; |
5871 |
} |
5872 |
if (first) |
5873 |
{ |
5874 |
/* We have just done the first batch of conversion which was |
5875 |
stopped because of insufficient gap. Let's reconsider the |
5876 |
required gap size (i.e. SRT - DST) now. |
5877 |
|
5878 |
We have converted ORIG bytes (== coding->consumed) into |
5879 |
NEW bytes (coding->produced). To convert the remaining |
5880 |
LEN bytes, we may need REQUIRE bytes of gap, where: |
5881 |
REQUIRE + LEN_BYTE = LEN_BYTE * (NEW / ORIG) |
5882 |
REQUIRE = LEN_BYTE * (NEW - ORIG) / ORIG |
5883 |
Here, we are sure that NEW >= ORIG. */ |
5884 |
float ratio; |
5885 |
|
5886 |
if (coding->produced <= coding->consumed) |
5887 |
{ |
5888 |
/* This happens because of CCL-based coding system with |
5889 |
eol-type CRLF. */ |
5890 |
require = 0; |
5891 |
} |
5892 |
else |
5893 |
{ |
5894 |
ratio = (coding->produced - coding->consumed) / coding->consumed; |
5895 |
require = len_byte * ratio; |
5896 |
} |
5897 |
first = 0; |
5898 |
} |
5899 |
if ((src - dst) < (require + 2000)) |
5900 |
{ |
5901 |
/* See the comment above the previous call of make_gap. */ |
5902 |
int add = len_byte + inserted_byte; |
5903 |
|
5904 |
GAP_SIZE -= add; |
5905 |
ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; |
5906 |
GPT += inserted_byte; GPT_BYTE += inserted_byte; |
5907 |
make_gap (require + 2000); |
5908 |
GAP_SIZE += add; |
5909 |
ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; |
5910 |
GPT -= inserted_byte; GPT_BYTE -= inserted_byte; |
5911 |
} |
5912 |
} |
5913 |
if (src - dst > 0) *dst = 0; /* Put an anchor. */ |
5914 |
|
5915 |
if (encodep && coding->dst_multibyte) |
5916 |
{ |
5917 |
/* The output is unibyte. We must convert 8-bit characters to |
5918 |
multibyte form. */ |
5919 |
if (inserted_byte * 2 > GAP_SIZE) |
5920 |
{ |
5921 |
GAP_SIZE -= inserted_byte; |
5922 |
ZV += inserted_byte; Z += inserted_byte; |
5923 |
ZV_BYTE += inserted_byte; Z_BYTE += inserted_byte; |
5924 |
GPT += inserted_byte; GPT_BYTE += inserted_byte; |
5925 |
make_gap (inserted_byte - GAP_SIZE); |
5926 |
GAP_SIZE += inserted_byte; |
5927 |
ZV -= inserted_byte; Z -= inserted_byte; |
5928 |
ZV_BYTE -= inserted_byte; Z_BYTE -= inserted_byte; |
5929 |
GPT -= inserted_byte; GPT_BYTE -= inserted_byte; |
5930 |
} |
5931 |
inserted_byte = str_to_multibyte (GPT_ADDR, GAP_SIZE, inserted_byte); |
5932 |
} |
5933 |
|
5934 |
/* If we shrank the conversion area, adjust it now. */ |
5935 |
if (total_skip > 0) |
5936 |
{ |
5937 |
if (tail_skip > 0) |
5938 |
safe_bcopy (GAP_END_ADDR, GPT_ADDR + inserted_byte, tail_skip); |
5939 |
inserted += total_skip; inserted_byte += total_skip; |
5940 |
GAP_SIZE += total_skip; |
5941 |
GPT -= head_skip; GPT_BYTE -= head_skip; |
5942 |
ZV -= total_skip; ZV_BYTE -= total_skip; |
5943 |
Z -= total_skip; Z_BYTE -= total_skip; |
5944 |
from -= head_skip; from_byte -= head_skip; |
5945 |
to += tail_skip; to_byte += tail_skip; |
5946 |
} |
5947 |
|
5948 |
prev_Z = Z; |
5949 |
if (! EQ (current_buffer->undo_list, Qt)) |
5950 |
adjust_after_replace (from, from_byte, deletion, inserted, inserted_byte); |
5951 |
else |
5952 |
adjust_after_replace_noundo (from, from_byte, nchars_del, nbytes_del, |
5953 |
inserted, inserted_byte); |
5954 |
inserted = Z - prev_Z; |
5955 |
|
5956 |
if (!encodep && coding->cmp_data && coding->cmp_data->used) |
5957 |
coding_restore_composition (coding, Fcurrent_buffer ()); |
5958 |
coding_free_composition_data (coding); |
5959 |
|
5960 |
if (! inhibit_pre_post_conversion |
5961 |
&& ! encodep && ! NILP (coding->post_read_conversion)) |
5962 |
{ |
5963 |
Lisp_Object val; |
5964 |
Lisp_Object saved_coding_system; |
5965 |
|
5966 |
if (from != PT) |
5967 |
TEMP_SET_PT_BOTH (from, from_byte); |
5968 |
prev_Z = Z; |
5969 |
record_unwind_protect (code_convert_region_unwind, |
5970 |
Vlast_coding_system_used); |
5971 |
saved_coding_system = Vlast_coding_system_used; |
5972 |
Vlast_coding_system_used = coding->symbol; |
5973 |
/* We should not call any more pre-write/post-read-conversion |
5974 |
functions while this post-read-conversion is running. */ |
5975 |
inhibit_pre_post_conversion = 1; |
5976 |
val = call1 (coding->post_read_conversion, make_number (inserted)); |
5977 |
inhibit_pre_post_conversion = 0; |
5978 |
coding->symbol = Vlast_coding_system_used; |
5979 |
Vlast_coding_system_used = saved_coding_system; |
5980 |
/* Discard the unwind protect. */ |
5981 |
specpdl_ptr--; |
5982 |
CHECK_NUMBER (val); |
5983 |
inserted += Z - prev_Z; |
5984 |
} |
5985 |
|
5986 |
if (orig_point >= from) |
5987 |
{ |
5988 |
if (orig_point >= from + orig_len) |
5989 |
orig_point += inserted - orig_len; |
5990 |
else |
5991 |
orig_point = from; |
5992 |
TEMP_SET_PT (orig_point); |
5993 |
} |
5994 |
|
5995 |
if (replace) |
5996 |
{ |
5997 |
signal_after_change (from, to - from, inserted); |
5998 |
update_compositions (from, from + inserted, CHECK_BORDER); |
5999 |
} |
6000 |
|
6001 |
{ |
6002 |
coding->consumed = to_byte - from_byte; |
6003 |
coding->consumed_char = to - from; |
6004 |
coding->produced = inserted_byte; |
6005 |
coding->produced_char = inserted; |
6006 |
} |
6007 |
|
6008 |
return 0; |
6009 |
} |
6010 |
|
6011 |
Lisp_Object |
6012 |
run_pre_post_conversion_on_str (str, coding, encodep) |
6013 |
Lisp_Object str; |
6014 |
struct coding_system *coding; |
6015 |
int encodep; |
6016 |
{ |
6017 |
int count = SPECPDL_INDEX (); |
6018 |
struct gcpro gcpro1, gcpro2; |
6019 |
int multibyte = STRING_MULTIBYTE (str); |
6020 |
Lisp_Object buffer; |
6021 |
struct buffer *buf; |
6022 |
Lisp_Object old_deactivate_mark; |
6023 |
|
6024 |
record_unwind_protect (Fset_buffer, Fcurrent_buffer ()); |
6025 |
record_unwind_protect (code_convert_region_unwind, |
6026 |
Vlast_coding_system_used); |
6027 |
/* It is not crucial to specbind this. */ |
6028 |
old_deactivate_mark = Vdeactivate_mark; |
6029 |
GCPRO2 (str, old_deactivate_mark); |
6030 |
|
6031 |
buffer = Fget_buffer_create (build_string (" *code-converting-work*")); |
6032 |
buf = XBUFFER (buffer); |
6033 |
|
6034 |
delete_all_overlays (buf); |
6035 |
buf->directory = current_buffer->directory; |
6036 |
buf->read_only = Qnil; |
6037 |
buf->filename = Qnil; |
6038 |
buf->undo_list = Qt; |
6039 |
eassert (buf->overlays_before == NULL); |
6040 |
eassert (buf->overlays_after == NULL); |
6041 |
|
6042 |
set_buffer_internal (buf); |
6043 |
/* We must insert the contents of STR as is without |
6044 |
unibyte<->multibyte conversion. For that, we adjust the |
6045 |
multibyteness of the working buffer to that of STR. */ |
6046 |
Ferase_buffer (); |
6047 |
buf->enable_multibyte_characters = multibyte ? Qt : Qnil; |
6048 |
|
6049 |
insert_from_string (str, 0, 0, |
6050 |
SCHARS (str), SBYTES (str), 0); |
6051 |
UNGCPRO; |
6052 |
inhibit_pre_post_conversion = 1; |
6053 |
if (encodep) |
6054 |
call2 (coding->pre_write_conversion, make_number (BEG), make_number (Z)); |
6055 |
else |
6056 |
{ |
6057 |
Vlast_coding_system_used = coding->symbol; |
6058 |
TEMP_SET_PT_BOTH (BEG, BEG_BYTE); |
6059 |
call1 (coding->post_read_conversion, make_number (Z - BEG)); |
6060 |
coding->symbol = Vlast_coding_system_used; |
6061 |
} |
6062 |
inhibit_pre_post_conversion = 0; |
6063 |
Vdeactivate_mark = old_deactivate_mark; |
6064 |
str = make_buffer_string (BEG, Z, 1); |
6065 |
return unbind_to (count, str); |
6066 |
} |
6067 |
|
6068 |
Lisp_Object |
6069 |
decode_coding_string (str, coding, nocopy) |
6070 |
Lisp_Object str; |
6071 |
struct coding_system *coding; |
6072 |
int nocopy; |
6073 |
{ |
6074 |
int len; |
6075 |
struct conversion_buffer buf; |
6076 |
int from, to_byte; |
6077 |
Lisp_Object saved_coding_symbol; |
6078 |
int result; |
6079 |
int require_decoding; |
6080 |
int shrinked_bytes = 0; |
6081 |
Lisp_Object newstr; |
6082 |
int consumed, consumed_char, produced, produced_char; |
6083 |
|
6084 |
from = 0; |
6085 |
to_byte = SBYTES (str); |
6086 |
|
6087 |
saved_coding_symbol = coding->symbol; |
6088 |
coding->src_multibyte = STRING_MULTIBYTE (str); |
6089 |
coding->dst_multibyte = 1; |
6090 |
if (CODING_REQUIRE_DETECTION (coding)) |
6091 |
{ |
6092 |
/* See the comments in code_convert_region. */ |
6093 |
if (coding->type == coding_type_undecided) |
6094 |
{ |
6095 |
detect_coding (coding, SDATA (str), to_byte); |
6096 |
if (coding->type == coding_type_undecided) |
6097 |
{ |
6098 |
coding->type = coding_type_emacs_mule; |
6099 |
coding->category_idx = CODING_CATEGORY_IDX_EMACS_MULE; |
6100 |
/* As emacs-mule decoder will handle composition, we |
6101 |
need this setting to allocate coding->cmp_data |
6102 |
later. */ |
6103 |
coding->composing = COMPOSITION_NO; |
6104 |
} |
6105 |
} |
6106 |
if (coding->eol_type == CODING_EOL_UNDECIDED |
6107 |
&& coding->type != coding_type_ccl) |
6108 |
{ |
6109 |
saved_coding_symbol = coding->symbol; |
6110 |
detect_eol (coding, SDATA (str), to_byte); |
6111 |
if (coding->eol_type == CODING_EOL_UNDECIDED) |
6112 |
coding->eol_type = CODING_EOL_LF; |
6113 |
/* We had better recover the original eol format if we |
6114 |
encounter an inconsistent eol format while decoding. */ |
6115 |
coding->mode |= CODING_MODE_INHIBIT_INCONSISTENT_EOL; |
6116 |
} |
6117 |
} |
6118 |
|
6119 |
if (coding->type == coding_type_no_conversion |
6120 |
|| coding->type == coding_type_raw_text) |
6121 |
coding->dst_multibyte = 0; |
6122 |
|
6123 |
require_decoding = CODING_REQUIRE_DECODING (coding); |
6124 |
|
6125 |
if (STRING_MULTIBYTE (str)) |
6126 |
{ |
6127 |
/* Decoding routines expect the source text to be unibyte. */ |
6128 |
str = Fstring_as_unibyte (str); |
6129 |
to_byte = SBYTES (str); |
6130 |
nocopy = 1; |
6131 |
coding->src_multibyte = 0; |
6132 |
} |
6133 |
|
6134 |
/* Try to skip the heading and tailing ASCIIs. */ |
6135 |
if (require_decoding && coding->type != coding_type_ccl) |
6136 |
{ |
6137 |
SHRINK_CONVERSION_REGION (&from, &to_byte, coding, SDATA (str), |
6138 |
0); |
6139 |
if (from == to_byte) |
6140 |
require_decoding = 0; |
6141 |
shrinked_bytes = from + (SBYTES (str) - to_byte); |
6142 |
} |
6143 |
|
6144 |
if (!require_decoding |
6145 |
&& !(SYMBOLP (coding->post_read_conversion) |
6146 |
&& !NILP (Ffboundp (coding->post_read_conversion)))) |
6147 |
{ |
6148 |
coding->consumed = SBYTES (str); |
6149 |
coding->consumed_char = SCHARS (str); |
6150 |
if (coding->dst_multibyte) |
6151 |
{ |
6152 |
str = Fstring_as_multibyte (str); |
6153 |
nocopy = 1; |
6154 |
} |
6155 |
coding->produced = SBYTES (str); |
6156 |
coding->produced_char = SCHARS (str); |
6157 |
return (nocopy ? str : Fcopy_sequence (str)); |
6158 |
} |
6159 |
|
6160 |
if (coding->composing != COMPOSITION_DISABLED) |
6161 |
coding_allocate_composition_data (coding, from); |
6162 |
len = decoding_buffer_size (coding, to_byte - from); |
6163 |
allocate_conversion_buffer (buf, len); |
6164 |
|
6165 |
consumed = consumed_char = produced = produced_char = 0; |
6166 |
while (1) |
6167 |
{ |
6168 |
result = decode_coding (coding, SDATA (str) + from + consumed, |
6169 |
buf.data + produced, to_byte - from - consumed, |
6170 |
buf.size - produced); |
6171 |
consumed += coding->consumed; |
6172 |
consumed_char += coding->consumed_char; |
6173 |
produced += coding->produced; |
6174 |
produced_char += coding->produced_char; |
6175 |
if (result == CODING_FINISH_NORMAL |
6176 |
|| (result == CODING_FINISH_INSUFFICIENT_SRC |
6177 |
&& coding->consumed == 0)) |
6178 |
break; |
6179 |
if (result == CODING_FINISH_INSUFFICIENT_CMP) |
6180 |
coding_allocate_composition_data (coding, from + produced_char); |
6181 |
else if (result == CODING_FINISH_INSUFFICIENT_DST) |
6182 |
extend_conversion_buffer (&buf); |
6183 |
else if (result == CODING_FINISH_INCONSISTENT_EOL) |
6184 |
{ |
6185 |
Lisp_Object eol_type; |
6186 |
|
6187 |
/* Recover the original EOL format. */ |
6188 |
if (coding->eol_type == CODING_EOL_CR) |
6189 |
{ |
6190 |
unsigned char *p; |
6191 |
for (p = buf.data; p < buf.data + produced; p++) |
6192 |
if (*p == '\n') *p = '\r'; |
6193 |
} |
6194 |
else if (coding->eol_type == CODING_EOL_CRLF) |
6195 |
{ |
6196 |
int num_eol = 0; |
6197 |
unsigned char *p0, *p1; |
6198 |
for (p0 = buf.data, p1 = p0 + produced; p0 < p1; p0++) |
6199 |
if (*p0 == '\n') num_eol++; |
6200 |
if (produced + num_eol >= buf.size) |
6201 |
extend_conversion_buffer (&buf); |
6202 |
for (p0 = buf.data + produced, p1 = p0 + num_eol; p0 > buf.data;) |
6203 |
{ |
6204 |
*--p1 = *--p0; |
6205 |
if (*p0 == '\n') *--p1 = '\r'; |
6206 |
} |
6207 |
produced += num_eol; |
6208 |
produced_char += num_eol; |
6209 |
} |
6210 |
/* Suppress eol-format conversion in the further conversion. */ |
6211 |
coding->eol_type = CODING_EOL_LF; |
6212 |
|
6213 |
/* Set the coding system symbol to that for Unix-like EOL. */ |
6214 |
eol_type = Fget (saved_coding_symbol, Qeol_type); |
6215 |
if (VECTORP (eol_type) |
6216 |
&& XVECTOR (eol_type)->size == 3 |
6217 |
&& SYMBOLP (XVECTOR (eol_type)->contents[CODING_EOL_LF])) |
6218 |
coding->symbol = XVECTOR (eol_type)->contents[CODING_EOL_LF]; |
6219 |
else |
6220 |
coding->symbol = saved_coding_symbol; |
6221 |
|
6222 |
|
6223 |
} |
6224 |
} |
6225 |
|
6226 |
coding->consumed = consumed; |
6227 |
coding->consumed_char = consumed_char; |
6228 |
coding->produced = produced; |
6229 |
coding->produced_char = produced_char; |
6230 |
|
6231 |
if (coding->dst_multibyte) |
6232 |
newstr = make_uninit_multibyte_string (produced_char + shrinked_bytes, |
6233 |
produced + shrinked_bytes); |
6234 |
else |
6235 |
newstr = make_uninit_string (produced + shrinked_bytes); |
6236 |
if (from > 0) |
6237 |
STRING_COPYIN (newstr, 0, SDATA (str), from); |
6238 |
STRING_COPYIN (newstr, from, buf.data, produced); |
6239 |
if (shrinked_bytes > from) |
6240 |
STRING_COPYIN (newstr, from + produced, |
6241 |
SDATA (str) + to_byte, |
6242 |
shrinked_bytes - from); |
6243 |
free_conversion_buffer (&buf); |
6244 |
|
6245 |
coding->consumed += shrinked_bytes; |
6246 |
coding->consumed_char += shrinked_bytes; |
6247 |
coding->produced += shrinked_bytes; |
6248 |
coding->produced_char += shrinked_bytes; |
6249 |
|
6250 |
if (coding->cmp_data && coding->cmp_data->used) |
6251 |
coding_restore_composition (coding, newstr); |
6252 |
coding_free_composition_data (coding); |
6253 |
|
6254 |
if (SYMBOLP (coding->post_read_conversion) |
6255 |
&& !NILP (Ffboundp (coding->post_read_conversion))) |
6256 |
newstr = run_pre_post_conversion_on_str (newstr, coding, 0); |
6257 |
|
6258 |
return newstr; |
6259 |
} |
6260 |
|
6261 |
Lisp_Object |
6262 |
encode_coding_string (str, coding, nocopy) |
6263 |
Lisp_Object str; |
6264 |
struct coding_system *coding; |
6265 |
int nocopy; |
6266 |
{ |
6267 |
int len; |
6268 |
struct conversion_buffer buf; |
6269 |
int from, to, to_byte; |
6270 |
int result; |
6271 |
int shrinked_bytes = 0; |
6272 |
Lisp_Object newstr; |
6273 |
int consumed, consumed_char, produced, produced_char; |
6274 |
|
6275 |
if (SYMBOLP (coding->pre_write_conversion) |
6276 |
&& !NILP (Ffboundp (coding->pre_write_conversion))) |
6277 |
str = run_pre_post_conversion_on_str (str, coding, 1); |
6278 |
|
6279 |
from = 0; |
6280 |
to = SCHARS (str); |
6281 |
to_byte = SBYTES (str); |
6282 |
|
6283 |
/* Encoding routines determine the multibyteness of the source text |
6284 |
by coding->src_multibyte. */ |
6285 |
coding->src_multibyte = STRING_MULTIBYTE (str); |
6286 |
coding->dst_multibyte = 0; |
6287 |
if (! CODING_REQUIRE_ENCODING (coding)) |
6288 |
{ |
6289 |
coding->consumed = SBYTES (str); |
6290 |
coding->consumed_char = SCHARS (str); |
6291 |
if (STRING_MULTIBYTE (str)) |
6292 |
{ |
6293 |
str = Fstring_as_unibyte (str); |
6294 |
nocopy = 1; |
6295 |
} |
6296 |
coding->produced = SBYTES (str); |
6297 |
coding->produced_char = SCHARS (str); |
6298 |
return (nocopy ? str : Fcopy_sequence (str)); |
6299 |
} |
6300 |
|
6301 |
if (coding->composing != COMPOSITION_DISABLED) |
6302 |
coding_save_composition (coding, from, to, str); |
6303 |
|
6304 |
/* Try to skip the heading and tailing ASCIIs. We can't skip them |
6305 |
if we must run CCL program or there are compositions to |
6306 |
encode. */ |
6307 |
if (coding->type != coding_type_ccl |
6308 |
&& (! coding->cmp_data || coding->cmp_data->used == 0)) |
6309 |
{ |
6310 |
SHRINK_CONVERSION_REGION (&from, &to_byte, coding, SDATA (str), |
6311 |
1); |
6312 |
if (from == to_byte) |
6313 |
{ |
6314 |
coding_free_composition_data (coding); |
6315 |
return (nocopy ? str : Fcopy_sequence (str)); |
6316 |
} |
6317 |
shrinked_bytes = from + (SBYTES (str) - to_byte); |
6318 |
} |
6319 |
|
6320 |
len = encoding_buffer_size (coding, to_byte - from); |
6321 |
allocate_conversion_buffer (buf, len); |
6322 |
|
6323 |
consumed = consumed_char = produced = produced_char = 0; |
6324 |
while (1) |
6325 |
{ |
6326 |
result = encode_coding (coding, SDATA (str) + from + consumed, |
6327 |
buf.data + produced, to_byte - from - consumed, |
6328 |
buf.size - produced); |
6329 |
consumed += coding->consumed; |
6330 |
consumed_char += coding->consumed_char; |
6331 |
produced += coding->produced; |
6332 |
produced_char += coding->produced_char; |
6333 |
if (result == CODING_FINISH_NORMAL |
6334 |
|| result == CODING_FINISH_INTERRUPT |
6335 |
|| (result == CODING_FINISH_INSUFFICIENT_SRC |
6336 |
&& coding->consumed == 0)) |
6337 |
break; |
6338 |
/* Now result should be CODING_FINISH_INSUFFICIENT_DST. */ |
6339 |
extend_conversion_buffer (&buf); |
6340 |
} |
6341 |
|
6342 |
coding->consumed = consumed; |
6343 |
coding->consumed_char = consumed_char; |
6344 |
coding->produced = produced; |
6345 |
coding->produced_char = produced_char; |
6346 |
|
6347 |
newstr = make_uninit_string (produced + shrinked_bytes); |
6348 |
if (from > 0) |
6349 |
STRING_COPYIN (newstr, 0, SDATA (str), from); |
6350 |
STRING_COPYIN (newstr, from, buf.data, produced); |
6351 |
if (shrinked_bytes > from) |
6352 |
STRING_COPYIN (newstr, from + produced, |
6353 |
SDATA (str) + to_byte, |
6354 |
shrinked_bytes - from); |
6355 |
|
6356 |
free_conversion_buffer (&buf); |
6357 |
coding_free_composition_data (coding); |
6358 |
|
6359 |
return newstr; |
6360 |
} |
6361 |
|
6362 |
|
6363 |
#ifdef emacs |
6364 |
/*** 8. Emacs Lisp library functions ***/ |
6365 |
|
6366 |
DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
6367 |
doc: /* Return t if OBJECT is nil or a coding-system. |
6368 |
See the documentation of `make-coding-system' for information |
6369 |
about coding-system objects. */) |
6370 |
(obj) |
6371 |
Lisp_Object obj; |
6372 |
{ |
6373 |
if (NILP (obj)) |
6374 |
return Qt; |
6375 |
if (!SYMBOLP (obj)) |
6376 |
return Qnil; |
6377 |
if (! NILP (Fget (obj, Qcoding_system_define_form))) |
6378 |
return Qt; |
6379 |
/* Get coding-spec vector for OBJ. */ |
6380 |
obj = Fget (obj, Qcoding_system); |
6381 |
return ((VECTORP (obj) && XVECTOR (obj)->size == 5) |
6382 |
? Qt : Qnil); |
6383 |
} |
6384 |
|
6385 |
DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
6386 |
Sread_non_nil_coding_system, 1, 1, 0, |
6387 |
doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
6388 |
(prompt) |
6389 |
Lisp_Object prompt; |
6390 |
{ |
6391 |
Lisp_Object val; |
6392 |
do |
6393 |
{ |
6394 |
val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
6395 |
Qt, Qnil, Qcoding_system_history, Qnil, Qnil); |
6396 |
} |
6397 |
while (SCHARS (val) == 0); |
6398 |
return (Fintern (val, Qnil)); |
6399 |
} |
6400 |
|
6401 |
DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
6402 |
doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
6403 |
If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */) |
6404 |
(prompt, default_coding_system) |
6405 |
Lisp_Object prompt, default_coding_system; |
6406 |
{ |
6407 |
Lisp_Object val; |
6408 |
if (SYMBOLP (default_coding_system)) |
6409 |
default_coding_system = SYMBOL_NAME (default_coding_system); |
6410 |
val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
6411 |
Qt, Qnil, Qcoding_system_history, |
6412 |
default_coding_system, Qnil); |
6413 |
return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
6414 |
} |
6415 |
|
6416 |
DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, |
6417 |
1, 1, 0, |
6418 |
doc: /* Check validity of CODING-SYSTEM. |
6419 |
If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
6420 |
It is valid if it is nil or a symbol with a non-nil `coding-system' property. |
6421 |
The value of this property should be a vector of length 5. */) |
6422 |
(coding_system) |
6423 |
Lisp_Object coding_system; |
6424 |
{ |
6425 |
Lisp_Object define_form; |
6426 |
|
6427 |
define_form = Fget (coding_system, Qcoding_system_define_form); |
6428 |
if (! NILP (define_form)) |
6429 |
{ |
6430 |
Fput (coding_system, Qcoding_system_define_form, Qnil); |
6431 |
safe_eval (define_form); |
6432 |
} |
6433 |
if (!NILP (Fcoding_system_p (coding_system))) |
6434 |
return coding_system; |
6435 |
while (1) |
6436 |
Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
6437 |
} |
6438 |
|
6439 |
Lisp_Object |
6440 |
detect_coding_system (src, src_bytes, highest, multibytep) |
6441 |
const unsigned char *src; |
6442 |
int src_bytes, highest; |
6443 |
int multibytep; |
6444 |
{ |
6445 |
int coding_mask, eol_type; |
6446 |
Lisp_Object val, tmp; |
6447 |
int dummy; |
6448 |
|
6449 |
coding_mask = detect_coding_mask (src, src_bytes, NULL, &dummy, multibytep); |
6450 |
eol_type = detect_eol_type (src, src_bytes, &dummy); |
6451 |
if (eol_type == CODING_EOL_INCONSISTENT) |
6452 |
eol_type = CODING_EOL_UNDECIDED; |
6453 |
|
6454 |
if (!coding_mask) |
6455 |
{ |
6456 |
val = Qundecided; |
6457 |
if (eol_type != CODING_EOL_UNDECIDED) |
6458 |
{ |
6459 |
Lisp_Object val2; |
6460 |
val2 = Fget (Qundecided, Qeol_type); |
6461 |
if (VECTORP (val2)) |
6462 |
val = XVECTOR (val2)->contents[eol_type]; |
6463 |
} |
6464 |
return (highest ? val : Fcons (val, Qnil)); |
6465 |
} |
6466 |
|
6467 |
/* At first, gather possible coding systems in VAL. */ |
6468 |
val = Qnil; |
6469 |
for (tmp = Vcoding_category_list; CONSP (tmp); tmp = XCDR (tmp)) |
6470 |
{ |
6471 |
Lisp_Object category_val, category_index; |
6472 |
|
6473 |
category_index = Fget (XCAR (tmp), Qcoding_category_index); |
6474 |
category_val = Fsymbol_value (XCAR (tmp)); |
6475 |
if (!NILP (category_val) |
6476 |
&& NATNUMP (category_index) |
6477 |
&& (coding_mask & (1 << XFASTINT (category_index)))) |
6478 |
{ |
6479 |
val = Fcons (category_val, val); |
6480 |
if (highest) |
6481 |
break; |
6482 |
} |
6483 |
} |
6484 |
if (!highest) |
6485 |
val = Fnreverse (val); |
6486 |
|
6487 |
/* Then, replace the elements with subsidiary coding systems. */ |
6488 |
for (tmp = val; CONSP (tmp); tmp = XCDR (tmp)) |
6489 |
{ |
6490 |
if (eol_type != CODING_EOL_UNDECIDED |
6491 |
&& eol_type != CODING_EOL_INCONSISTENT) |
6492 |
{ |
6493 |
Lisp_Object eol; |
6494 |
eol = Fget (XCAR (tmp), Qeol_type); |
6495 |
if (VECTORP (eol)) |
6496 |
XSETCAR (tmp, XVECTOR (eol)->contents[eol_type]); |
6497 |
} |
6498 |
} |
6499 |
return (highest ? XCAR (val) : val); |
6500 |
} |
6501 |
|
6502 |
DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
6503 |
2, 3, 0, |
6504 |
doc: /* Detect how the byte sequence in the region is encoded. |
6505 |
Return a list of possible coding systems used on decoding a byte |
6506 |
sequence containing the bytes in the region between START and END when |
6507 |
the coding system `undecided' is specified. The list is ordered by |
6508 |
priority decided in the current language environment. |
6509 |
|
6510 |
If only ASCII characters are found, it returns a list of single element |
6511 |
`undecided' or its subsidiary coding system according to a detected |
6512 |
end-of-line format. |
6513 |
|
6514 |
If optional argument HIGHEST is non-nil, return the coding system of |
6515 |
highest priority. */) |
6516 |
(start, end, highest) |
6517 |
Lisp_Object start, end, highest; |
6518 |
{ |
6519 |
int from, to; |
6520 |
int from_byte, to_byte; |
6521 |
int include_anchor_byte = 0; |
6522 |
|
6523 |
CHECK_NUMBER_COERCE_MARKER (start); |
6524 |
CHECK_NUMBER_COERCE_MARKER (end); |
6525 |
|
6526 |
validate_region (&start, &end); |
6527 |
from = XINT (start), to = XINT (end); |
6528 |
from_byte = CHAR_TO_BYTE (from); |
6529 |
to_byte = CHAR_TO_BYTE (to); |
6530 |
|
6531 |
if (from < GPT && to >= GPT) |
6532 |
move_gap_both (to, to_byte); |
6533 |
/* If we an anchor byte `\0' follows the region, we include it in |
6534 |
the detecting source. Then code detectors can handle the tailing |
6535 |
byte sequence more accurately. |
6536 |
|
6537 |
Fix me: This is not a perfect solution. It is better that we |
6538 |
add one more argument, say LAST_BLOCK, to all detect_coding_XXX. |
6539 |
*/ |
6540 |
if (to == Z || (to == GPT && GAP_SIZE > 0)) |
6541 |
include_anchor_byte = 1; |
6542 |
return detect_coding_system (BYTE_POS_ADDR (from_byte), |
6543 |
to_byte - from_byte + include_anchor_byte, |
6544 |
!NILP (highest), |
6545 |
!NILP (current_buffer |
6546 |
->enable_multibyte_characters)); |
6547 |
} |
6548 |
|
6549 |
DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
6550 |
1, 2, 0, |
6551 |
doc: /* Detect how the byte sequence in STRING is encoded. |
6552 |
Return a list of possible coding systems used on decoding a byte |
6553 |
sequence containing the bytes in STRING when the coding system |
6554 |
`undecided' is specified. The list is ordered by priority decided in |
6555 |
the current language environment. |
6556 |
|
6557 |
If only ASCII characters are found, it returns a list of single element |
6558 |
`undecided' or its subsidiary coding system according to a detected |
6559 |
end-of-line format. |
6560 |
|
6561 |
If optional argument HIGHEST is non-nil, return the coding system of |
6562 |
highest priority. */) |
6563 |
(string, highest) |
6564 |
Lisp_Object string, highest; |
6565 |
{ |
6566 |
CHECK_STRING (string); |
6567 |
|
6568 |
return detect_coding_system (SDATA (string), |
6569 |
/* "+ 1" is to include the anchor byte |
6570 |
`\0'. With this, code detectors can |
6571 |
handle the tailing bytes more |
6572 |
accurately. */ |
6573 |
SBYTES (string) + 1, |
6574 |
!NILP (highest), |
6575 |
STRING_MULTIBYTE (string)); |
6576 |
} |
6577 |
|
6578 |
/* Subroutine for Fsafe_coding_systems_region_internal. |
6579 |
|
6580 |
Return a list of coding systems that safely encode the multibyte |
6581 |
text between P and PEND. SAFE_CODINGS, if non-nil, is an alist of |
6582 |
possible coding systems. If it is nil, it means that we have not |
6583 |
yet found any coding systems. |
6584 |
|
6585 |
WORK_TABLE a char-table of which element is set to t once the |
6586 |
element is looked up. |
6587 |
|
6588 |
If a non-ASCII single byte char is found, set |
6589 |
*single_byte_char_found to 1. */ |
6590 |
|
6591 |
static Lisp_Object |
6592 |
find_safe_codings (p, pend, safe_codings, work_table, single_byte_char_found) |
6593 |
unsigned char *p, *pend; |
6594 |
Lisp_Object safe_codings, work_table; |
6595 |
int *single_byte_char_found; |
6596 |
{ |
6597 |
int c, len; |
6598 |
Lisp_Object val, ch; |
6599 |
Lisp_Object prev, tail; |
6600 |
|
6601 |
if (NILP (safe_codings)) |
6602 |
goto done_safe_codings; |
6603 |
while (p < pend) |
6604 |
{ |
6605 |
c = STRING_CHAR_AND_LENGTH (p, pend - p, len); |
6606 |
p += len; |
6607 |
if (ASCII_BYTE_P (c)) |
6608 |
/* We can ignore ASCII characters here. */ |
6609 |
continue; |
6610 |
if (SINGLE_BYTE_CHAR_P (c)) |
6611 |
*single_byte_char_found = 1; |
6612 |
/* Check the safe coding systems for C. */ |
6613 |
ch = make_number (c); |
6614 |
val = Faref (work_table, ch); |
6615 |
if (EQ (val, Qt)) |
6616 |
/* This element was already checked. Ignore it. */ |
6617 |
continue; |
6618 |
/* Remember that we checked this element. */ |
6619 |
Faset (work_table, ch, Qt); |
6620 |
|
6621 |
for (prev = tail = safe_codings; CONSP (tail); tail = XCDR (tail)) |
6622 |
{ |
6623 |
Lisp_Object elt, translation_table, hash_table, accept_latin_extra; |
6624 |
int encodable; |
6625 |
|
6626 |
elt = XCAR (tail); |
6627 |
if (CONSP (XCDR (elt))) |
6628 |
{ |
6629 |
/* This entry has this format now: |
6630 |
( CODING SAFE-CHARS TRANSLATION-TABLE HASH-TABLE |
6631 |
ACCEPT-LATIN-EXTRA ) */ |
6632 |
val = XCDR (elt); |
6633 |
encodable = ! NILP (Faref (XCAR (val), ch)); |
6634 |
if (! encodable) |
6635 |
{ |
6636 |
val = XCDR (val); |
6637 |
translation_table = XCAR (val); |
6638 |
hash_table = XCAR (XCDR (val)); |
6639 |
accept_latin_extra = XCAR (XCDR (XCDR (val))); |
6640 |
} |
6641 |
} |
6642 |
else |
6643 |
{ |
6644 |
/* This entry has this format now: ( CODING . SAFE-CHARS) */ |
6645 |
encodable = ! NILP (Faref (XCDR (elt), ch)); |
6646 |
if (! encodable) |
6647 |
{ |
6648 |
/* Transform the format to: |
6649 |
( CODING SAFE-CHARS TRANSLATION-TABLE HASH-TABLE |
6650 |
ACCEPT-LATIN-EXTRA ) */ |
6651 |
val = Fget (XCAR (elt), Qcoding_system); |
6652 |
translation_table |
6653 |
= Fplist_get (AREF (val, 3), |
6654 |
Qtranslation_table_for_encode); |
6655 |
if (SYMBOLP (translation_table)) |
6656 |
translation_table = Fget (translation_table, |
6657 |
Qtranslation_table); |
6658 |
hash_table |
6659 |
= (CHAR_TABLE_P (translation_table) |
6660 |
? XCHAR_TABLE (translation_table)->extras[1] |
6661 |
: Qnil); |
6662 |
accept_latin_extra |
6663 |
= ((EQ (AREF (val, 0), make_number (2)) |
6664 |
&& VECTORP (AREF (val, 4))) |
6665 |
? AREF (AREF (val, 4), 16) |
6666 |
: Qnil); |
6667 |
XSETCAR (tail, list5 (XCAR (elt), XCDR (elt), |
6668 |
translation_table, hash_table, |
6669 |
accept_latin_extra)); |
6670 |
} |
6671 |
} |
6672 |
|
6673 |
if (! encodable |
6674 |
&& ((CHAR_TABLE_P (translation_table) |
6675 |
&& ! NILP (Faref (translation_table, ch))) |
6676 |
|| (HASH_TABLE_P (hash_table) |
6677 |
&& ! NILP (Fgethash (ch, hash_table, Qnil))) |
6678 |
|| (SINGLE_BYTE_CHAR_P (c) |
6679 |
&& ! NILP (accept_latin_extra) |
6680 |
&& VECTORP (Vlatin_extra_code_table) |
6681 |
&& ! NILP (AREF (Vlatin_extra_code_table, c))))) |
6682 |
encodable = 1; |
6683 |
if (encodable) |
6684 |
prev = tail; |
6685 |
else |
6686 |
{ |
6687 |
/* Exclude this coding system from SAFE_CODINGS. */ |
6688 |
if (EQ (tail, safe_codings)) |
6689 |
{ |
6690 |
safe_codings = XCDR (safe_codings); |
6691 |
if (NILP (safe_codings)) |
6692 |
goto done_safe_codings; |
6693 |
} |
6694 |
else |
6695 |
XSETCDR (prev, XCDR (tail)); |
6696 |
} |
6697 |
} |
6698 |
} |
6699 |
|
6700 |
done_safe_codings: |
6701 |
/* If the above loop was terminated before P reaches PEND, it means |
6702 |
SAFE_CODINGS was set to nil. If we have not yet found an |
6703 |
non-ASCII single-byte char, check it now. */ |
6704 |
if (! *single_byte_char_found) |
6705 |
while (p < pend) |
6706 |
{ |
6707 |
c = STRING_CHAR_AND_LENGTH (p, pend - p, len); |
6708 |
p += len; |
6709 |
if (! ASCII_BYTE_P (c) |
6710 |
&& SINGLE_BYTE_CHAR_P (c)) |
6711 |
{ |
6712 |
*single_byte_char_found = 1; |
6713 |
break; |
6714 |
} |
6715 |
} |
6716 |
return safe_codings; |
6717 |
} |
6718 |
|
6719 |
DEFUN ("find-coding-systems-region-internal", |
6720 |
Ffind_coding_systems_region_internal, |
6721 |
Sfind_coding_systems_region_internal, 2, 2, 0, |
6722 |
doc: /* Internal use only. */) |
6723 |
(start, end) |
6724 |
Lisp_Object start, end; |
6725 |
{ |
6726 |
Lisp_Object work_table, safe_codings; |
6727 |
int non_ascii_p = 0; |
6728 |
int single_byte_char_found = 0; |
6729 |
const unsigned char *p1, *p1end, *p2, *p2end, *p; |
6730 |
|
6731 |
if (STRINGP (start)) |
6732 |
{ |
6733 |
if (!STRING_MULTIBYTE (start)) |
6734 |
return Qt; |
6735 |
p1 = SDATA (start), p1end = p1 + SBYTES (start); |
6736 |
p2 = p2end = p1end; |
6737 |
if (SCHARS (start) != SBYTES (start)) |
6738 |
non_ascii_p = 1; |
6739 |
} |
6740 |
else |
6741 |
{ |
6742 |
int from, to, stop; |
6743 |
|
6744 |
CHECK_NUMBER_COERCE_MARKER (start); |
6745 |
CHECK_NUMBER_COERCE_MARKER (end); |
6746 |
if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
6747 |
args_out_of_range (start, end); |
6748 |
if (NILP (current_buffer->enable_multibyte_characters)) |
6749 |
return Qt; |
6750 |
from = CHAR_TO_BYTE (XINT (start)); |
6751 |
to = CHAR_TO_BYTE (XINT (end)); |
6752 |
stop = from < GPT_BYTE && GPT_BYTE < to ? GPT_BYTE : to; |
6753 |
p1 = BYTE_POS_ADDR (from), p1end = p1 + (stop - from); |
6754 |
if (stop == to) |
6755 |
p2 = p2end = p1end; |
6756 |
else |
6757 |
p2 = BYTE_POS_ADDR (stop), p2end = p2 + (to - stop); |
6758 |
if (XINT (end) - XINT (start) != to - from) |
6759 |
non_ascii_p = 1; |
6760 |
} |
6761 |
|
6762 |
if (!non_ascii_p) |
6763 |
{ |
6764 |
/* We are sure that the text contains no multibyte character. |
6765 |
Check if it contains eight-bit-graphic. */ |
6766 |
p = p1; |
6767 |
for (p = p1; p < p1end && ASCII_BYTE_P (*p); p++); |
6768 |
if (p == p1end) |
6769 |
{ |
6770 |
for (p = p2; p < p2end && ASCII_BYTE_P (*p); p++); |
6771 |
if (p == p2end) |
6772 |
return Qt; |
6773 |
} |
6774 |
} |
6775 |
|
6776 |
/* The text contains non-ASCII characters. */ |
6777 |
|
6778 |
work_table = Fmake_char_table (Qchar_coding_system, Qnil); |
6779 |
safe_codings = Fcopy_sequence (XCDR (Vcoding_system_safe_chars)); |
6780 |
|
6781 |
safe_codings = find_safe_codings (p1, p1end, safe_codings, work_table, |
6782 |
&single_byte_char_found); |
6783 |
if (p2 < p2end) |
6784 |
safe_codings = find_safe_codings (p2, p2end, safe_codings, work_table, |
6785 |
&single_byte_char_found); |
6786 |
if (EQ (safe_codings, XCDR (Vcoding_system_safe_chars))) |
6787 |
safe_codings = Qt; |
6788 |
else |
6789 |
{ |
6790 |
/* Turn safe_codings to a list of coding systems... */ |
6791 |
Lisp_Object val; |
6792 |
|
6793 |
if (single_byte_char_found) |
6794 |
/* ... and append these for eight-bit chars. */ |
6795 |
val = Fcons (Qraw_text, |
6796 |
Fcons (Qemacs_mule, Fcons (Qno_conversion, Qnil))); |
6797 |
else |
6798 |
/* ... and append generic coding systems. */ |
6799 |
val = Fcopy_sequence (XCAR (Vcoding_system_safe_chars)); |
6800 |
|
6801 |
for (; CONSP (safe_codings); safe_codings = XCDR (safe_codings)) |
6802 |
val = Fcons (XCAR (XCAR (safe_codings)), val); |
6803 |
safe_codings = val; |
6804 |
} |
6805 |
|
6806 |
return safe_codings; |
6807 |
} |
6808 |
|
6809 |
|
6810 |
/* Search from position POS for such characters that are unencodable |
6811 |
accoding to SAFE_CHARS, and return a list of their positions. P |
6812 |
points where in the memory the character at POS exists. Limit the |
6813 |
search at PEND or when Nth unencodable characters are found. |
6814 |
|
6815 |
If SAFE_CHARS is a char table, an element for an unencodable |
6816 |
character is nil. |
6817 |
|
6818 |
If SAFE_CHARS is nil, all non-ASCII characters are unencodable. |
6819 |
|
6820 |
Otherwise, SAFE_CHARS is t, and only eight-bit-contrl and |
6821 |
eight-bit-graphic characters are unencodable. */ |
6822 |
|
6823 |
static Lisp_Object |
6824 |
unencodable_char_position (safe_chars, pos, p, pend, n) |
6825 |
Lisp_Object safe_chars; |
6826 |
int pos; |
6827 |
unsigned char *p, *pend; |
6828 |
int n; |
6829 |
{ |
6830 |
Lisp_Object pos_list; |
6831 |
|
6832 |
pos_list = Qnil; |
6833 |
while (p < pend) |
6834 |
{ |
6835 |
int len; |
6836 |
int c = STRING_CHAR_AND_LENGTH (p, MAX_MULTIBYTE_LENGTH, len); |
6837 |
|
6838 |
if (c >= 128 |
6839 |
&& (CHAR_TABLE_P (safe_chars) |
6840 |
? NILP (CHAR_TABLE_REF (safe_chars, c)) |
6841 |
: (NILP (safe_chars) || c < 256))) |
6842 |
{ |
6843 |
pos_list = Fcons (make_number (pos), pos_list); |
6844 |
if (--n <= 0) |
6845 |
break; |
6846 |
} |
6847 |
pos++; |
6848 |
p += len; |
6849 |
} |
6850 |
return Fnreverse (pos_list); |
6851 |
} |
6852 |
|
6853 |
|
6854 |
DEFUN ("unencodable-char-position", Funencodable_char_position, |
6855 |
Sunencodable_char_position, 3, 5, 0, |
6856 |
doc: /* |
6857 |
Return position of first un-encodable character in a region. |
6858 |
START and END specfiy the region and CODING-SYSTEM specifies the |
6859 |
encoding to check. Return nil if CODING-SYSTEM does encode the region. |
6860 |
|
6861 |
If optional 4th argument COUNT is non-nil, it specifies at most how |
6862 |
many un-encodable characters to search. In this case, the value is a |
6863 |
list of positions. |
6864 |
|
6865 |
If optional 5th argument STRING is non-nil, it is a string to search |
6866 |
for un-encodable characters. In that case, START and END are indexes |
6867 |
to the string. */) |
6868 |
(start, end, coding_system, count, string) |
6869 |
Lisp_Object start, end, coding_system, count, string; |
6870 |
{ |
6871 |
int n; |
6872 |
Lisp_Object safe_chars; |
6873 |
struct coding_system coding; |
6874 |
Lisp_Object positions; |
6875 |
int from, to; |
6876 |
unsigned char *p, *pend; |
6877 |
|
6878 |
if (NILP (string)) |
6879 |
{ |
6880 |
validate_region (&start, &end); |
6881 |
from = XINT (start); |
6882 |
to = XINT (end); |
6883 |
if (NILP (current_buffer->enable_multibyte_characters)) |
6884 |
return Qnil; |
6885 |
p = CHAR_POS_ADDR (from); |
6886 |
if (to == GPT) |
6887 |
pend = GPT_ADDR; |
6888 |
else |
6889 |
pend = CHAR_POS_ADDR (to); |
6890 |
} |
6891 |
else |
6892 |
{ |
6893 |
CHECK_STRING (string); |
6894 |
CHECK_NATNUM (start); |
6895 |
CHECK_NATNUM (end); |
6896 |
from = XINT (start); |
6897 |
to = XINT (end); |
6898 |
if (from > to |
6899 |
|| to > SCHARS (string)) |
6900 |
args_out_of_range_3 (string, start, end); |
6901 |
if (! STRING_MULTIBYTE (string)) |
6902 |
return Qnil; |
6903 |
p = SDATA (string) + string_char_to_byte (string, from); |
6904 |
pend = SDATA (string) + string_char_to_byte (string, to); |
6905 |
} |
6906 |
|
6907 |
setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
6908 |
|
6909 |
if (NILP (count)) |
6910 |
n = 1; |
6911 |
else |
6912 |
{ |
6913 |
CHECK_NATNUM (count); |
6914 |
n = XINT (count); |
6915 |
} |
6916 |
|
6917 |
if (coding.type == coding_type_no_conversion |
6918 |
|| coding.type == coding_type_raw_text) |
6919 |
return Qnil; |
6920 |
|
6921 |
if (coding.type == coding_type_undecided) |
6922 |
safe_chars = Qnil; |
6923 |
else |
6924 |
safe_chars = coding_safe_chars (coding_system); |
6925 |
|
6926 |
if (STRINGP (string) |
6927 |
|| from >= GPT || to <= GPT) |
6928 |
positions = unencodable_char_position (safe_chars, from, p, pend, n); |
6929 |
else |
6930 |
{ |
6931 |
Lisp_Object args[2]; |
6932 |
|
6933 |
args[0] = unencodable_char_position (safe_chars, from, p, GPT_ADDR, n); |
6934 |
n -= XINT (Flength (args[0])); |
6935 |
if (n <= 0) |
6936 |
positions = args[0]; |
6937 |
else |
6938 |
{ |
6939 |
args[1] = unencodable_char_position (safe_chars, GPT, GAP_END_ADDR, |
6940 |
pend, n); |
6941 |
positions = Fappend (2, args); |
6942 |
} |
6943 |
} |
6944 |
|
6945 |
return (NILP (count) ? Fcar (positions) : positions); |
6946 |
} |
6947 |
|
6948 |
|
6949 |
Lisp_Object |
6950 |
code_convert_region1 (start, end, coding_system, encodep) |
6951 |
Lisp_Object start, end, coding_system; |
6952 |
int encodep; |
6953 |
{ |
6954 |
struct coding_system coding; |
6955 |
int from, to; |
6956 |
|
6957 |
CHECK_NUMBER_COERCE_MARKER (start); |
6958 |
CHECK_NUMBER_COERCE_MARKER (end); |
6959 |
CHECK_SYMBOL (coding_system); |
6960 |
|
6961 |
validate_region (&start, &end); |
6962 |
from = XFASTINT (start); |
6963 |
to = XFASTINT (end); |
6964 |
|
6965 |
if (NILP (coding_system)) |
6966 |
return make_number (to - from); |
6967 |
|
6968 |
if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
6969 |
error ("Invalid coding system: %s", SDATA (SYMBOL_NAME (coding_system))); |
6970 |
|
6971 |
coding.mode |= CODING_MODE_LAST_BLOCK; |
6972 |
coding.src_multibyte = coding.dst_multibyte |
6973 |
= !NILP (current_buffer->enable_multibyte_characters); |
6974 |
code_convert_region (from, CHAR_TO_BYTE (from), to, CHAR_TO_BYTE (to), |
6975 |
&coding, encodep, 1); |
6976 |
Vlast_coding_system_used = coding.symbol; |
6977 |
return make_number (coding.produced_char); |
6978 |
} |
6979 |
|
6980 |
DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
6981 |
3, 3, "r\nzCoding system: ", |
6982 |
doc: /* Decode the current region from the specified coding system. |
6983 |
When called from a program, takes three arguments: |
6984 |
START, END, and CODING-SYSTEM. START and END are buffer positions. |
6985 |
This function sets `last-coding-system-used' to the precise coding system |
6986 |
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is |
6987 |
not fully specified.) |
6988 |
It returns the length of the decoded text. */) |
6989 |
(start, end, coding_system) |
6990 |
Lisp_Object start, end, coding_system; |
6991 |
{ |
6992 |
return code_convert_region1 (start, end, coding_system, 0); |
6993 |
} |
6994 |
|
6995 |
DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
6996 |
3, 3, "r\nzCoding system: ", |
6997 |
doc: /* Encode the current region into the specified coding system. |
6998 |
When called from a program, takes three arguments: |
6999 |
START, END, and CODING-SYSTEM. START and END are buffer positions. |
7000 |
This function sets `last-coding-system-used' to the precise coding system |
7001 |
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is |
7002 |
not fully specified.) |
7003 |
It returns the length of the encoded text. */) |
7004 |
(start, end, coding_system) |
7005 |
Lisp_Object start, end, coding_system; |
7006 |
{ |
7007 |
return code_convert_region1 (start, end, coding_system, 1); |
7008 |
} |
7009 |
|
7010 |
Lisp_Object |
7011 |
code_convert_string1 (string, coding_system, nocopy, encodep) |
7012 |
Lisp_Object string, coding_system, nocopy; |
7013 |
int encodep; |
7014 |
{ |
7015 |
struct coding_system coding; |
7016 |
|
7017 |
CHECK_STRING (string); |
7018 |
CHECK_SYMBOL (coding_system); |
7019 |
|
7020 |
if (NILP (coding_system)) |
7021 |
return (NILP (nocopy) ? Fcopy_sequence (string) : string); |
7022 |
|
7023 |
if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
7024 |
error ("Invalid coding system: %s", SDATA (SYMBOL_NAME (coding_system))); |
7025 |
|
7026 |
coding.mode |= CODING_MODE_LAST_BLOCK; |
7027 |
string = (encodep |
7028 |
? encode_coding_string (string, &coding, !NILP (nocopy)) |
7029 |
: decode_coding_string (string, &coding, !NILP (nocopy))); |
7030 |
Vlast_coding_system_used = coding.symbol; |
7031 |
|
7032 |
return string; |
7033 |
} |
7034 |
|
7035 |
DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
7036 |
2, 3, 0, |
7037 |
doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. |
7038 |
Optional arg NOCOPY non-nil means it is OK to return STRING itself |
7039 |
if the decoding operation is trivial. |
7040 |
This function sets `last-coding-system-used' to the precise coding system |
7041 |
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is |
7042 |
not fully specified.) */) |
7043 |
(string, coding_system, nocopy) |
7044 |
Lisp_Object string, coding_system, nocopy; |
7045 |
{ |
7046 |
return code_convert_string1 (string, coding_system, nocopy, 0); |
7047 |
} |
7048 |
|
7049 |
DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
7050 |
2, 3, 0, |
7051 |
doc: /* Encode STRING to CODING-SYSTEM, and return the result. |
7052 |
Optional arg NOCOPY non-nil means it is OK to return STRING itself |
7053 |
if the encoding operation is trivial. |
7054 |
This function sets `last-coding-system-used' to the precise coding system |
7055 |
used (which may be different from CODING-SYSTEM if CODING-SYSTEM is |
7056 |
not fully specified.) */) |
7057 |
(string, coding_system, nocopy) |
7058 |
Lisp_Object string, coding_system, nocopy; |
7059 |
{ |
7060 |
return code_convert_string1 (string, coding_system, nocopy, 1); |
7061 |
} |
7062 |
|
7063 |
/* Encode or decode STRING according to CODING_SYSTEM. |
7064 |
Do not set Vlast_coding_system_used. |
7065 |
|
7066 |
This function is called only from macros DECODE_FILE and |
7067 |
ENCODE_FILE, thus we ignore character composition. */ |
7068 |
|
7069 |
Lisp_Object |
7070 |
code_convert_string_norecord (string, coding_system, encodep) |
7071 |
Lisp_Object string, coding_system; |
7072 |
int encodep; |
7073 |
{ |
7074 |
struct coding_system coding; |
7075 |
|
7076 |
CHECK_STRING (string); |
7077 |
CHECK_SYMBOL (coding_system); |
7078 |
|
7079 |
if (NILP (coding_system)) |
7080 |
return string; |
7081 |
|
7082 |
if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
7083 |
error ("Invalid coding system: %s", SDATA (SYMBOL_NAME (coding_system))); |
7084 |
|
7085 |
coding.composing = COMPOSITION_DISABLED; |
7086 |
coding.mode |= CODING_MODE_LAST_BLOCK; |
7087 |
return (encodep |
7088 |
? encode_coding_string (string, &coding, 1) |
7089 |
: decode_coding_string (string, &coding, 1)); |
7090 |
} |
7091 |
|
7092 |
DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
7093 |
doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
7094 |
Return the corresponding character. */) |
7095 |
(code) |
7096 |
Lisp_Object code; |
7097 |
{ |
7098 |
unsigned char c1, c2, s1, s2; |
7099 |
Lisp_Object val; |
7100 |
|
7101 |
CHECK_NUMBER (code); |
7102 |
s1 = (XFASTINT (code)) >> 8, s2 = (XFASTINT (code)) & 0xFF; |
7103 |
if (s1 == 0) |
7104 |
{ |
7105 |
if (s2 < 0x80) |
7106 |
XSETFASTINT (val, s2); |
7107 |
else if (s2 >= 0xA0 || s2 <= 0xDF) |
7108 |
XSETFASTINT (val, MAKE_CHAR (charset_katakana_jisx0201, s2, 0)); |
7109 |
else |
7110 |
error ("Invalid Shift JIS code: %x", XFASTINT (code)); |
7111 |
} |
7112 |
else |
7113 |
{ |
7114 |
if ((s1 < 0x80 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF) |
7115 |
|| (s2 < 0x40 || s2 == 0x7F || s2 > 0xFC)) |
7116 |
error ("Invalid Shift JIS code: %x", XFASTINT (code)); |
7117 |
DECODE_SJIS (s1, s2, c1, c2); |
7118 |
XSETFASTINT (val, MAKE_CHAR (charset_jisx0208, c1, c2)); |
7119 |
} |
7120 |
return val; |
7121 |
} |
7122 |
|
7123 |
DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
7124 |
doc: /* Encode a Japanese character CHAR to shift_jis encoding. |
7125 |
Return the corresponding code in SJIS. */) |
7126 |
(ch) |
7127 |
Lisp_Object ch; |
7128 |
{ |
7129 |
int charset, c1, c2, s1, s2; |
7130 |
Lisp_Object val; |
7131 |
|
7132 |
CHECK_NUMBER (ch); |
7133 |
SPLIT_CHAR (XFASTINT (ch), charset, c1, c2); |
7134 |
if (charset == CHARSET_ASCII) |
7135 |
{ |
7136 |
val = ch; |
7137 |
} |
7138 |
else if (charset == charset_jisx0208 |
7139 |
&& c1 > 0x20 && c1 < 0x7F && c2 > 0x20 && c2 < 0x7F) |
7140 |
{ |
7141 |
ENCODE_SJIS (c1, c2, s1, s2); |
7142 |
XSETFASTINT (val, (s1 << 8) | s2); |
7143 |
} |
7144 |
else if (charset == charset_katakana_jisx0201 |
7145 |
&& c1 > 0x20 && c2 < 0xE0) |
7146 |
{ |
7147 |
XSETFASTINT (val, c1 | 0x80); |
7148 |
} |
7149 |
else |
7150 |
error ("Can't encode to shift_jis: %d", XFASTINT (ch)); |
7151 |
return val; |
7152 |
} |
7153 |
|
7154 |
DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, |
7155 |
doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
7156 |
Return the corresponding character. */) |
7157 |
(code) |
7158 |
Lisp_Object code; |
7159 |
{ |
7160 |
int charset; |
7161 |
unsigned char b1, b2, c1, c2; |
7162 |
Lisp_Object val; |
7163 |
|
7164 |
CHECK_NUMBER (code); |
7165 |
b1 = (XFASTINT (code)) >> 8, b2 = (XFASTINT (code)) & 0xFF; |
7166 |
if (b1 == 0) |
7167 |
{ |
7168 |
if (b2 >= 0x80) |
7169 |
error ("Invalid BIG5 code: %x", XFASTINT (code)); |
7170 |
val = code; |
7171 |
} |
7172 |
else |
7173 |
{ |
7174 |
if ((b1 < 0xA1 || b1 > 0xFE) |
7175 |
|| (b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE)) |
7176 |
error ("Invalid BIG5 code: %x", XFASTINT (code)); |
7177 |
DECODE_BIG5 (b1, b2, charset, c1, c2); |
7178 |
XSETFASTINT (val, MAKE_CHAR (charset, c1, c2)); |
7179 |
} |
7180 |
return val; |
7181 |
} |
7182 |
|
7183 |
DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
7184 |
doc: /* Encode the Big5 character CHAR to BIG5 coding system. |
7185 |
Return the corresponding character code in Big5. */) |
7186 |
(ch) |
7187 |
Lisp_Object ch; |
7188 |
{ |
7189 |
int charset, c1, c2, b1, b2; |
7190 |
Lisp_Object val; |
7191 |
|
7192 |
CHECK_NUMBER (ch); |
7193 |
SPLIT_CHAR (XFASTINT (ch), charset, c1, c2); |
7194 |
if (charset == CHARSET_ASCII) |
7195 |
{ |
7196 |
val = ch; |
7197 |
} |
7198 |
else if ((charset == charset_big5_1 |
7199 |
&& (XFASTINT (ch) >= 0x250a1 && XFASTINT (ch) <= 0x271ec)) |
7200 |
|| (charset == charset_big5_2 |
7201 |
&& XFASTINT (ch) >= 0x290a1 && XFASTINT (ch) <= 0x2bdb2)) |
7202 |
{ |
7203 |
ENCODE_BIG5 (charset, c1, c2, b1, b2); |
7204 |
XSETFASTINT (val, (b1 << 8) | b2); |
7205 |
} |
7206 |
else |
7207 |
error ("Can't encode to Big5: %d", XFASTINT (ch)); |
7208 |
return val; |
7209 |
} |
7210 |
|
7211 |
DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
7212 |
Sset_terminal_coding_system_internal, 1, 1, 0, |
7213 |
doc: /* Internal use only. */) |
7214 |
(coding_system) |
7215 |
Lisp_Object coding_system; |
7216 |
{ |
7217 |
CHECK_SYMBOL (coding_system); |
7218 |
setup_coding_system (Fcheck_coding_system (coding_system), &terminal_coding); |
7219 |
/* We had better not send unsafe characters to terminal. */ |
7220 |
terminal_coding.mode |= CODING_MODE_INHIBIT_UNENCODABLE_CHAR; |
7221 |
/* Character composition should be disabled. */ |
7222 |
terminal_coding.composing = COMPOSITION_DISABLED; |
7223 |
/* Error notification should be suppressed. */ |
7224 |
terminal_coding.suppress_error = 1; |
7225 |
terminal_coding.src_multibyte = 1; |
7226 |
terminal_coding.dst_multibyte = 0; |
7227 |
return Qnil; |
7228 |
} |
7229 |
|
7230 |
DEFUN ("set-safe-terminal-coding-system-internal", Fset_safe_terminal_coding_system_internal, |
7231 |
Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
7232 |
doc: /* Internal use only. */) |
7233 |
(coding_system) |
7234 |
Lisp_Object coding_system; |
7235 |
{ |
7236 |
CHECK_SYMBOL (coding_system); |
7237 |
setup_coding_system (Fcheck_coding_system (coding_system), |
7238 |
&safe_terminal_coding); |
7239 |
/* Character composition should be disabled. */ |
7240 |
safe_terminal_coding.composing = COMPOSITION_DISABLED; |
7241 |
/* Error notification should be suppressed. */ |
7242 |
safe_terminal_coding.suppress_error = 1; |
7243 |
safe_terminal_coding.src_multibyte = 1; |
7244 |
safe_terminal_coding.dst_multibyte = 0; |
7245 |
return Qnil; |
7246 |
} |
7247 |
|
7248 |
DEFUN ("terminal-coding-system", Fterminal_coding_system, |
7249 |
Sterminal_coding_system, 0, 0, 0, |
7250 |
doc: /* Return coding system specified for terminal output. */) |
7251 |
() |
7252 |
{ |
7253 |
return terminal_coding.symbol; |
7254 |
} |
7255 |
|
7256 |
DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
7257 |
Sset_keyboard_coding_system_internal, 1, 1, 0, |
7258 |
doc: /* Internal use only. */) |
7259 |
(coding_system) |
7260 |
Lisp_Object coding_system; |
7261 |
{ |
7262 |
CHECK_SYMBOL (coding_system); |
7263 |
setup_coding_system (Fcheck_coding_system (coding_system), &keyboard_coding); |
7264 |
/* Character composition should be disabled. */ |
7265 |
keyboard_coding.composing = COMPOSITION_DISABLED; |
7266 |
return Qnil; |
7267 |
} |
7268 |
|
7269 |
DEFUN ("keyboard-coding-system", Fkeyboard_coding_system, |
7270 |
Skeyboard_coding_system, 0, 0, 0, |
7271 |
doc: /* Return coding system specified for decoding keyboard input. */) |
7272 |
() |
7273 |
{ |
7274 |
return keyboard_coding.symbol; |
7275 |
} |
7276 |
|
7277 |
|
7278 |
DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
7279 |
Sfind_operation_coding_system, 1, MANY, 0, |
7280 |
doc: /* Choose a coding system for an operation based on the target name. |
7281 |
The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). |
7282 |
DECODING-SYSTEM is the coding system to use for decoding |
7283 |
\(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system |
7284 |
for encoding (in case OPERATION does encoding). |
7285 |
|
7286 |
The first argument OPERATION specifies an I/O primitive: |
7287 |
For file I/O, `insert-file-contents' or `write-region'. |
7288 |
For process I/O, `call-process', `call-process-region', or `start-process'. |
7289 |
For network I/O, `open-network-stream'. |
7290 |
|
7291 |
The remaining arguments should be the same arguments that were passed |
7292 |
to the primitive. Depending on which primitive, one of those arguments |
7293 |
is selected as the TARGET. For example, if OPERATION does file I/O, |
7294 |
whichever argument specifies the file name is TARGET. |
7295 |
|
7296 |
TARGET has a meaning which depends on OPERATION: |
7297 |
For file I/O, TARGET is a file name. |
7298 |
For process I/O, TARGET is a process name. |
7299 |
For network I/O, TARGET is a service name or a port number |
7300 |
|
7301 |
This function looks up what specified for TARGET in, |
7302 |
`file-coding-system-alist', `process-coding-system-alist', |
7303 |
or `network-coding-system-alist' depending on OPERATION. |
7304 |
They may specify a coding system, a cons of coding systems, |
7305 |
or a function symbol to call. |
7306 |
In the last case, we call the function with one argument, |
7307 |
which is a list of all the arguments given to this function. |
7308 |
|
7309 |
usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */) |
7310 |
(nargs, args) |
7311 |
int nargs; |
7312 |
Lisp_Object *args; |
7313 |
{ |
7314 |
Lisp_Object operation, target_idx, target, val; |
7315 |
register Lisp_Object chain; |
7316 |
|
7317 |
if (nargs < 2) |
7318 |
error ("Too few arguments"); |
7319 |
operation = args[0]; |
7320 |
if (!SYMBOLP (operation) |
7321 |
|| !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) |
7322 |
error ("Invalid first argument"); |
7323 |
if (nargs < 1 + XINT (target_idx)) |
7324 |
error ("Too few arguments for operation: %s", |
7325 |
SDATA (SYMBOL_NAME (operation))); |
7326 |
/* For write-region, if the 6th argument (i.e. VISIT, the 5th |
7327 |
argument to write-region) is string, it must be treated as a |
7328 |
target file name. */ |
7329 |
if (EQ (operation, Qwrite_region) |
7330 |
&& nargs > 5 |
7331 |
&& STRINGP (args[5])) |
7332 |
target_idx = make_number (4); |
7333 |
target = args[XINT (target_idx) + 1]; |
7334 |
if (!(STRINGP (target) |
7335 |
|| (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
7336 |
error ("Invalid argument %d", XINT (target_idx) + 1); |
7337 |
|
7338 |
chain = ((EQ (operation, Qinsert_file_contents) |
7339 |
|| EQ (operation, Qwrite_region)) |
7340 |
? Vfile_coding_system_alist |
7341 |
: (EQ (operation, Qopen_network_stream) |
7342 |
? Vnetwork_coding_system_alist |
7343 |
: Vprocess_coding_system_alist)); |
7344 |
if (NILP (chain)) |
7345 |
return Qnil; |
7346 |
|
7347 |
for (; CONSP (chain); chain = XCDR (chain)) |
7348 |
{ |
7349 |
Lisp_Object elt; |
7350 |
elt = XCAR (chain); |
7351 |
|
7352 |
if (CONSP (elt) |
7353 |
&& ((STRINGP (target) |
7354 |
&& STRINGP (XCAR (elt)) |
7355 |
&& fast_string_match (XCAR (elt), target) >= 0) |
7356 |
|| (INTEGERP (target) && EQ (target, XCAR (elt))))) |
7357 |
{ |
7358 |
val = XCDR (elt); |
7359 |
/* Here, if VAL is both a valid coding system and a valid |
7360 |
function symbol, we return VAL as a coding system. */ |
7361 |
if (CONSP (val)) |
7362 |
return val; |
7363 |
if (! SYMBOLP (val)) |
7364 |
return Qnil; |
7365 |
if (! NILP (Fcoding_system_p (val))) |
7366 |
return Fcons (val, val); |
7367 |
if (! NILP (Ffboundp (val))) |
7368 |
{ |
7369 |
val = call1 (val, Flist (nargs, args)); |
7370 |
if (CONSP (val)) |
7371 |
return val; |
7372 |
if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) |
7373 |
return Fcons (val, val); |
7374 |
} |
7375 |
return Qnil; |
7376 |
} |
7377 |
} |
7378 |
return Qnil; |
7379 |
} |
7380 |
|
7381 |
DEFUN ("update-coding-systems-internal", Fupdate_coding_systems_internal, |
7382 |
Supdate_coding_systems_internal, 0, 0, 0, |
7383 |
doc: /* Update internal database for ISO2022 and CCL based coding systems. |
7384 |
When values of any coding categories are changed, you must |
7385 |
call this function. */) |
7386 |
() |
7387 |
{ |
7388 |
int i; |
7389 |
|
7390 |
for (i = CODING_CATEGORY_IDX_EMACS_MULE; i < CODING_CATEGORY_IDX_MAX; i++) |
7391 |
{ |
7392 |
Lisp_Object val; |
7393 |
|
7394 |
val = SYMBOL_VALUE (XVECTOR (Vcoding_category_table)->contents[i]); |
7395 |
if (!NILP (val)) |
7396 |
{ |
7397 |
if (! coding_system_table[i]) |
7398 |
coding_system_table[i] = ((struct coding_system *) |
7399 |
xmalloc (sizeof (struct coding_system))); |
7400 |
setup_coding_system (val, coding_system_table[i]); |
7401 |
} |
7402 |
else if (coding_system_table[i]) |
7403 |
{ |
7404 |
xfree (coding_system_table[i]); |
7405 |
coding_system_table[i] = NULL; |
7406 |
} |
7407 |
} |
7408 |
|
7409 |
return Qnil; |
7410 |
} |
7411 |
|
7412 |
DEFUN ("set-coding-priority-internal", Fset_coding_priority_internal, |
7413 |
Sset_coding_priority_internal, 0, 0, 0, |
7414 |
doc: /* Update internal database for the current value of `coding-category-list'. |
7415 |
This function is internal use only. */) |
7416 |
() |
7417 |
{ |
7418 |
int i = 0, idx; |
7419 |
Lisp_Object val; |
7420 |
|
7421 |
val = Vcoding_category_list; |
7422 |
|
7423 |
while (CONSP (val) && i < CODING_CATEGORY_IDX_MAX) |
7424 |
{ |
7425 |
if (! SYMBOLP (XCAR (val))) |
7426 |
break; |
7427 |
idx = XFASTINT (Fget (XCAR (val), Qcoding_category_index)); |
7428 |
if (idx >= CODING_CATEGORY_IDX_MAX) |
7429 |
break; |
7430 |
coding_priorities[i++] = (1 << idx); |
7431 |
val = XCDR (val); |
7432 |
} |
7433 |
/* If coding-category-list is valid and contains all coding |
7434 |
categories, `i' should be CODING_CATEGORY_IDX_MAX now. If not, |
7435 |
the following code saves Emacs from crashing. */ |
7436 |
while (i < CODING_CATEGORY_IDX_MAX) |
7437 |
coding_priorities[i++] = CODING_CATEGORY_MASK_RAW_TEXT; |
7438 |
|
7439 |
return Qnil; |
7440 |
} |
7441 |
|
7442 |
DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
7443 |
Sdefine_coding_system_internal, 1, 1, 0, |
7444 |
doc: /* Register CODING-SYSTEM as a base coding system. |
7445 |
This function is internal use only. */) |
7446 |
(coding_system) |
7447 |
Lisp_Object coding_system; |
7448 |
{ |
7449 |
Lisp_Object safe_chars, slot; |
7450 |
|
7451 |
if (NILP (Fcheck_coding_system (coding_system))) |
7452 |
Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
7453 |
safe_chars = coding_safe_chars (coding_system); |
7454 |
if (! EQ (safe_chars, Qt) && ! CHAR_TABLE_P (safe_chars)) |
7455 |
error ("No valid safe-chars property for %s", |
7456 |
SDATA (SYMBOL_NAME (coding_system))); |
7457 |
if (EQ (safe_chars, Qt)) |
7458 |
{ |
7459 |
if (NILP (Fmemq (coding_system, XCAR (Vcoding_system_safe_chars)))) |
7460 |
XSETCAR (Vcoding_system_safe_chars, |
7461 |
Fcons (coding_system, XCAR (Vcoding_system_safe_chars))); |
7462 |
} |
7463 |
else |
7464 |
{ |
7465 |
slot = Fassq (coding_system, XCDR (Vcoding_system_safe_chars)); |
7466 |
if (NILP (slot)) |
7467 |
XSETCDR (Vcoding_system_safe_chars, |
7468 |
nconc2 (XCDR (Vcoding_system_safe_chars), |
7469 |
Fcons (Fcons (coding_system, safe_chars), Qnil))); |
7470 |
else |
7471 |
XSETCDR (slot, safe_chars); |
7472 |
} |
7473 |
return Qnil; |
7474 |
} |
7475 |
|
7476 |
#endif /* emacs */ |
7477 |
|
7478 |
|
7479 |
/*** 9. Post-amble ***/ |
7480 |
|
7481 |
void |
7482 |
init_coding_once () |
7483 |
{ |
7484 |
int i; |
7485 |
|
7486 |
/* Emacs' internal format specific initialize routine. */ |
7487 |
for (i = 0; i <= 0x20; i++) |
7488 |
emacs_code_class[i] = EMACS_control_code; |
7489 |
emacs_code_class[0x0A] = EMACS_linefeed_code; |
7490 |
emacs_code_class[0x0D] = EMACS_carriage_return_code; |
7491 |
for (i = 0x21 ; i < 0x7F; i++) |
7492 |
emacs_code_class[i] = EMACS_ascii_code; |
7493 |
emacs_code_class[0x7F] = EMACS_control_code; |
7494 |
for (i = 0x80; i < 0xFF; i++) |
7495 |
emacs_code_class[i] = EMACS_invalid_code; |
7496 |
emacs_code_class[LEADING_CODE_PRIVATE_11] = EMACS_leading_code_3; |
7497 |
emacs_code_class[LEADING_CODE_PRIVATE_12] = EMACS_leading_code_3; |
7498 |
emacs_code_class[LEADING_CODE_PRIVATE_21] = EMACS_leading_code_4; |
7499 |
emacs_code_class[LEADING_CODE_PRIVATE_22] = EMACS_leading_code_4; |
7500 |
|
7501 |
/* ISO2022 specific initialize routine. */ |
7502 |
for (i = 0; i < 0x20; i++) |
7503 |
iso_code_class[i] = ISO_control_0; |
7504 |
for (i = 0x21; i < 0x7F; i++) |
7505 |
iso_code_class[i] = ISO_graphic_plane_0; |
7506 |
for (i = 0x80; i < 0xA0; i++) |
7507 |
iso_code_class[i] = ISO_control_1; |
7508 |
for (i = 0xA1; i < 0xFF; i++) |
7509 |
iso_code_class[i] = ISO_graphic_plane_1; |
7510 |
iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; |
7511 |
iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; |
7512 |
iso_code_class[ISO_CODE_CR] = ISO_carriage_return; |
7513 |
iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
7514 |
iso_code_class[ISO_CODE_SI] = ISO_shift_in; |
7515 |
iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; |
7516 |
iso_code_class[ISO_CODE_ESC] = ISO_escape; |
7517 |
iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; |
7518 |
iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; |
7519 |
iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; |
7520 |
|
7521 |
setup_coding_system (Qnil, &keyboard_coding); |
7522 |
setup_coding_system (Qnil, &terminal_coding); |
7523 |
setup_coding_system (Qnil, &safe_terminal_coding); |
7524 |
setup_coding_system (Qnil, &default_buffer_file_coding); |
7525 |
|
7526 |
bzero (coding_system_table, sizeof coding_system_table); |
7527 |
|
7528 |
bzero (ascii_skip_code, sizeof ascii_skip_code); |
7529 |
for (i = 0; i < 128; i++) |
7530 |
ascii_skip_code[i] = 1; |
7531 |
|
7532 |
#if defined (MSDOS) || defined (WINDOWSNT) |
7533 |
system_eol_type = CODING_EOL_CRLF; |
7534 |
#else |
7535 |
system_eol_type = CODING_EOL_LF; |
7536 |
#endif |
7537 |
|
7538 |
inhibit_pre_post_conversion = 0; |
7539 |
} |
7540 |
|
7541 |
#ifdef emacs |
7542 |
|
7543 |
void |
7544 |
syms_of_coding () |
7545 |
{ |
7546 |
Qtarget_idx = intern ("target-idx"); |
7547 |
staticpro (&Qtarget_idx); |
7548 |
|
7549 |
Qcoding_system_history = intern ("coding-system-history"); |
7550 |
staticpro (&Qcoding_system_history); |
7551 |
Fset (Qcoding_system_history, Qnil); |
7552 |
|
7553 |
/* Target FILENAME is the first argument. */ |
7554 |
Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
7555 |
/* Target FILENAME is the third argument. */ |
7556 |
Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
7557 |
|
7558 |
Qcall_process = intern ("call-process"); |
7559 |
staticpro (&Qcall_process); |
7560 |
/* Target PROGRAM is the first argument. */ |
7561 |
Fput (Qcall_process, Qtarget_idx, make_number (0)); |
7562 |
|
7563 |
Qcall_process_region = intern ("call-process-region"); |
7564 |
staticpro (&Qcall_process_region); |
7565 |
/* Target PROGRAM is the third argument. */ |
7566 |
Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
7567 |
|
7568 |
Qstart_process = intern ("start-process"); |
7569 |
staticpro (&Qstart_process); |
7570 |
/* Target PROGRAM is the third argument. */ |
7571 |
Fput (Qstart_process, Qtarget_idx, make_number (2)); |
7572 |
|
7573 |
Qopen_network_stream = intern ("open-network-stream"); |
7574 |
staticpro (&Qopen_network_stream); |
7575 |
/* Target SERVICE is the fourth argument. */ |
7576 |
Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
7577 |
|
7578 |
Qcoding_system = intern ("coding-system"); |
7579 |
staticpro (&Qcoding_system); |
7580 |
|
7581 |
Qeol_type = intern ("eol-type"); |
7582 |
staticpro (&Qeol_type); |
7583 |
|
7584 |
Qbuffer_file_coding_system = intern ("buffer-file-coding-system"); |
7585 |
staticpro (&Qbuffer_file_coding_system); |
7586 |
|
7587 |
Qpost_read_conversion = intern ("post-read-conversion"); |
7588 |
staticpro (&Qpost_read_conversion); |
7589 |
|
7590 |
Qpre_write_conversion = intern ("pre-write-conversion"); |
7591 |
staticpro (&Qpre_write_conversion); |
7592 |
|
7593 |
Qno_conversion = intern ("no-conversion"); |
7594 |
staticpro (&Qno_conversion); |
7595 |
|
7596 |
Qundecided = intern ("undecided"); |
7597 |
staticpro (&Qundecided); |
7598 |
|
7599 |
Qcoding_system_p = intern ("coding-system-p"); |
7600 |
staticpro (&Qcoding_system_p); |
7601 |
|
7602 |
Qcoding_system_error = intern ("coding-system-error"); |
7603 |
staticpro (&Qcoding_system_error); |
7604 |
|
7605 |
Fput (Qcoding_system_error, Qerror_conditions, |
7606 |
Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); |
7607 |
Fput (Qcoding_system_error, Qerror_message, |
7608 |
build_string ("Invalid coding system")); |
7609 |
|
7610 |
Qcoding_category = intern ("coding-category"); |
7611 |
staticpro (&Qcoding_category); |
7612 |
Qcoding_category_index = intern ("coding-category-index"); |
7613 |
staticpro (&Qcoding_category_index); |
7614 |
|
7615 |
Vcoding_category_table |
7616 |
= Fmake_vector (make_number (CODING_CATEGORY_IDX_MAX), Qnil); |
7617 |
staticpro (&Vcoding_category_table); |
7618 |
{ |
7619 |
int i; |
7620 |
for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++) |
7621 |
{ |
7622 |
XVECTOR (Vcoding_category_table)->contents[i] |
7623 |
= intern (coding_category_name[i]); |
7624 |
Fput (XVECTOR (Vcoding_category_table)->contents[i], |
7625 |
Qcoding_category_index, make_number (i)); |
7626 |
} |
7627 |
} |
7628 |
|
7629 |
Vcoding_system_safe_chars = Fcons (Qnil, Qnil); |
7630 |
staticpro (&Vcoding_system_safe_chars); |
7631 |
|
7632 |
Qtranslation_table = intern ("translation-table"); |
7633 |
staticpro (&Qtranslation_table); |
7634 |
Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
7635 |
|
7636 |
Qtranslation_table_id = intern ("translation-table-id"); |
7637 |
staticpro (&Qtranslation_table_id); |
7638 |
|
7639 |
Qtranslation_table_for_decode = intern ("translation-table-for-decode"); |
7640 |
staticpro (&Qtranslation_table_for_decode); |
7641 |
|
7642 |
Qtranslation_table_for_encode = intern ("translation-table-for-encode"); |
7643 |
staticpro (&Qtranslation_table_for_encode); |
7644 |
|
7645 |
Qsafe_chars = intern ("safe-chars"); |
7646 |
staticpro (&Qsafe_chars); |
7647 |
|
7648 |
Qchar_coding_system = intern ("char-coding-system"); |
7649 |
staticpro (&Qchar_coding_system); |
7650 |
|
7651 |
/* Intern this now in case it isn't already done. |
7652 |
Setting this variable twice is harmless. |
7653 |
But don't staticpro it here--that is done in alloc.c. */ |
7654 |
Qchar_table_extra_slots = intern ("char-table-extra-slots"); |
7655 |
Fput (Qsafe_chars, Qchar_table_extra_slots, make_number (0)); |
7656 |
Fput (Qchar_coding_system, Qchar_table_extra_slots, make_number (0)); |
7657 |
|
7658 |
Qvalid_codes = intern ("valid-codes"); |
7659 |
staticpro (&Qvalid_codes); |
7660 |
|
7661 |
Qemacs_mule = intern ("emacs-mule"); |
7662 |
staticpro (&Qemacs_mule); |
7663 |
|
7664 |
Qraw_text = intern ("raw-text"); |
7665 |
staticpro (&Qraw_text); |
7666 |
|
7667 |
Qutf_8 = intern ("utf-8"); |
7668 |
staticpro (&Qutf_8); |
7669 |
|
7670 |
Qcoding_system_define_form = intern ("coding-system-define-form"); |
7671 |
staticpro (&Qcoding_system_define_form); |
7672 |
|
7673 |
defsubr (&Scoding_system_p); |
7674 |
defsubr (&Sread_coding_system); |
7675 |
defsubr (&Sread_non_nil_coding_system); |
7676 |
defsubr (&Scheck_coding_system); |
7677 |
defsubr (&Sdetect_coding_region); |
7678 |
defsubr (&Sdetect_coding_string); |
7679 |
defsubr (&Sfind_coding_systems_region_internal); |
7680 |
defsubr (&Sunencodable_char_position); |
7681 |
defsubr (&Sdecode_coding_region); |
7682 |
defsubr (&Sencode_coding_region); |
7683 |
defsubr (&Sdecode_coding_string); |
7684 |
defsubr (&Sencode_coding_string); |
7685 |
defsubr (&Sdecode_sjis_char); |
7686 |
defsubr (&Sencode_sjis_char); |
7687 |
defsubr (&Sdecode_big5_char); |
7688 |
defsubr (&Sencode_big5_char); |
7689 |
defsubr (&Sset_terminal_coding_system_internal); |
7690 |
defsubr (&Sset_safe_terminal_coding_system_internal); |
7691 |
defsubr (&Sterminal_coding_system); |
7692 |
defsubr (&Sset_keyboard_coding_system_internal); |
7693 |
defsubr (&Skeyboard_coding_system); |
7694 |
defsubr (&Sfind_operation_coding_system); |
7695 |
defsubr (&Supdate_coding_systems_internal); |
7696 |
defsubr (&Sset_coding_priority_internal); |
7697 |
defsubr (&Sdefine_coding_system_internal); |
7698 |
|
7699 |
DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
7700 |
doc: /* List of coding systems. |
7701 |
|
7702 |
Do not alter the value of this variable manually. This variable should be |
7703 |
updated by the functions `make-coding-system' and |
7704 |
`define-coding-system-alias'. */); |
7705 |
Vcoding_system_list = Qnil; |
7706 |
|
7707 |
DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, |
7708 |
doc: /* Alist of coding system names. |
7709 |
Each element is one element list of coding system name. |
7710 |
This variable is given to `completing-read' as TABLE argument. |
7711 |
|
7712 |
Do not alter the value of this variable manually. This variable should be |
7713 |
updated by the functions `make-coding-system' and |
7714 |
`define-coding-system-alias'. */); |
7715 |
Vcoding_system_alist = Qnil; |
7716 |
|
7717 |
DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
7718 |
doc: /* List of coding-categories (symbols) ordered by priority. |
7719 |
|
7720 |
On detecting a coding system, Emacs tries code detection algorithms |
7721 |
associated with each coding-category one by one in this order. When |
7722 |
one algorithm agrees with a byte sequence of source text, the coding |
7723 |
system bound to the corresponding coding-category is selected. */); |
7724 |
{ |
7725 |
int i; |
7726 |
|
7727 |
Vcoding_category_list = Qnil; |
7728 |
for (i = CODING_CATEGORY_IDX_MAX - 1; i >= 0; i--) |
7729 |
Vcoding_category_list |
7730 |
= Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
7731 |
Vcoding_category_list); |
7732 |
} |
7733 |
|
7734 |
DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, |
7735 |
doc: /* Specify the coding system for read operations. |
7736 |
It is useful to bind this variable with `let', but do not set it globally. |
7737 |
If the value is a coding system, it is used for decoding on read operation. |
7738 |
If not, an appropriate element is used from one of the coding system alists: |
7739 |
There are three such tables, `file-coding-system-alist', |
7740 |
`process-coding-system-alist', and `network-coding-system-alist'. */); |
7741 |
Vcoding_system_for_read = Qnil; |
7742 |
|
7743 |
DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, |
7744 |
doc: /* Specify the coding system for write operations. |
7745 |
Programs bind this variable with `let', but you should not set it globally. |
7746 |
If the value is a coding system, it is used for encoding of output, |
7747 |
when writing it to a file and when sending it to a file or subprocess. |
7748 |
|
7749 |
If this does not specify a coding system, an appropriate element |
7750 |
is used from one of the coding system alists: |
7751 |
There are three such tables, `file-coding-system-alist', |
7752 |
`process-coding-system-alist', and `network-coding-system-alist'. |
7753 |
For output to files, if the above procedure does not specify a coding system, |
7754 |
the value of `buffer-file-coding-system' is used. */); |
7755 |
Vcoding_system_for_write = Qnil; |
7756 |
|
7757 |
DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, |
7758 |
doc: /* Coding system used in the latest file or process I/O. |
7759 |
Also set by `encode-coding-region', `decode-coding-region', |
7760 |
`encode-coding-string' and `decode-coding-string'. */); |
7761 |
Vlast_coding_system_used = Qnil; |
7762 |
|
7763 |
DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
7764 |
doc: /* *Non-nil means always inhibit code conversion of end-of-line format. |
7765 |
See info node `Coding Systems' and info node `Text and Binary' concerning |
7766 |
such conversion. */); |
7767 |
inhibit_eol_conversion = 0; |
7768 |
|
7769 |
DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
7770 |
doc: /* Non-nil means process buffer inherits coding system of process output. |
7771 |
Bind it to t if the process output is to be treated as if it were a file |
7772 |
read from some filesystem. */); |
7773 |
inherit_process_coding_system = 0; |
7774 |
|
7775 |
DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
7776 |
doc: /* Alist to decide a coding system to use for a file I/O operation. |
7777 |
The format is ((PATTERN . VAL) ...), |
7778 |
where PATTERN is a regular expression matching a file name, |
7779 |
VAL is a coding system, a cons of coding systems, or a function symbol. |
7780 |
If VAL is a coding system, it is used for both decoding and encoding |
7781 |
the file contents. |
7782 |
If VAL is a cons of coding systems, the car part is used for decoding, |
7783 |
and the cdr part is used for encoding. |
7784 |
If VAL is a function symbol, the function must return a coding system |
7785 |
or a cons of coding systems which are used as above. The function gets |
7786 |
the arguments with which `find-operation-coding-system' was called. |
7787 |
|
7788 |
See also the function `find-operation-coding-system' |
7789 |
and the variable `auto-coding-alist'. */); |
7790 |
Vfile_coding_system_alist = Qnil; |
7791 |
|
7792 |
DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, |
7793 |
doc: /* Alist to decide a coding system to use for a process I/O operation. |
7794 |
The format is ((PATTERN . VAL) ...), |
7795 |
where PATTERN is a regular expression matching a program name, |
7796 |
VAL is a coding system, a cons of coding systems, or a function symbol. |
7797 |
If VAL is a coding system, it is used for both decoding what received |
7798 |
from the program and encoding what sent to the program. |
7799 |
If VAL is a cons of coding systems, the car part is used for decoding, |
7800 |
and the cdr part is used for encoding. |
7801 |
If VAL is a function symbol, the function must return a coding system |
7802 |
or a cons of coding systems which are used as above. |
7803 |
|
7804 |
See also the function `find-operation-coding-system'. */); |
7805 |
Vprocess_coding_system_alist = Qnil; |
7806 |
|
7807 |
DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, |
7808 |
doc: /* Alist to decide a coding system to use for a network I/O operation. |
7809 |
The format is ((PATTERN . VAL) ...), |
7810 |
where PATTERN is a regular expression matching a network service name |
7811 |
or is a port number to connect to, |
7812 |
VAL is a coding system, a cons of coding systems, or a function symbol. |
7813 |
If VAL is a coding system, it is used for both decoding what received |
7814 |
from the network stream and encoding what sent to the network stream. |
7815 |
If VAL is a cons of coding systems, the car part is used for decoding, |
7816 |
and the cdr part is used for encoding. |
7817 |
If VAL is a function symbol, the function must return a coding system |
7818 |
or a cons of coding systems which are used as above. |
7819 |
|
7820 |
See also the function `find-operation-coding-system'. */); |
7821 |
Vnetwork_coding_system_alist = Qnil; |
7822 |
|
7823 |
DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
7824 |
doc: /* Coding system to use with system messages. |
7825 |
Also used for decoding keyboard input on X Window system. */); |
7826 |
Vlocale_coding_system = Qnil; |
7827 |
|
7828 |
/* The eol mnemonics are reset in startup.el system-dependently. */ |
7829 |
DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
7830 |
doc: /* *String displayed in mode line for UNIX-like (LF) end-of-line format. */); |
7831 |
eol_mnemonic_unix = build_string (":"); |
7832 |
|
7833 |
DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
7834 |
doc: /* *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); |
7835 |
eol_mnemonic_dos = build_string ("\\"); |
7836 |
|
7837 |
DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
7838 |
doc: /* *String displayed in mode line for MAC-like (CR) end-of-line format. */); |
7839 |
eol_mnemonic_mac = build_string ("/"); |
7840 |
|
7841 |
DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
7842 |
doc: /* *String displayed in mode line when end-of-line format is not yet determined. */); |
7843 |
eol_mnemonic_undecided = build_string (":"); |
7844 |
|
7845 |
DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
7846 |
doc: /* *Non-nil enables character translation while encoding and decoding. */); |
7847 |
Venable_character_translation = Qt; |
7848 |
|
7849 |
DEFVAR_LISP ("standard-translation-table-for-decode", |
7850 |
&Vstandard_translation_table_for_decode, |
7851 |
doc: /* Table for translating characters while decoding. */); |
7852 |
Vstandard_translation_table_for_decode = Qnil; |
7853 |
|
7854 |
DEFVAR_LISP ("standard-translation-table-for-encode", |
7855 |
&Vstandard_translation_table_for_encode, |
7856 |
doc: /* Table for translating characters while encoding. */); |
7857 |
Vstandard_translation_table_for_encode = Qnil; |
7858 |
|
7859 |
DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_alist, |
7860 |
doc: /* Alist of charsets vs revision numbers. |
7861 |
While encoding, if a charset (car part of an element) is found, |
7862 |
designate it with the escape sequence identifying revision (cdr part of the element). */); |
7863 |
Vcharset_revision_alist = Qnil; |
7864 |
|
7865 |
DEFVAR_LISP ("default-process-coding-system", |
7866 |
&Vdefault_process_coding_system, |
7867 |
doc: /* Cons of coding systems used for process I/O by default. |
7868 |
The car part is used for decoding a process output, |
7869 |
the cdr part is used for encoding a text to be sent to a process. */); |
7870 |
Vdefault_process_coding_system = Qnil; |
7871 |
|
7872 |
DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
7873 |
doc: /* Table of extra Latin codes in the range 128..159 (inclusive). |
7874 |
This is a vector of length 256. |
7875 |
If Nth element is non-nil, the existence of code N in a file |
7876 |
\(or output of subprocess) doesn't prevent it to be detected as |
7877 |
a coding system of ISO 2022 variant which has a flag |
7878 |
`accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file |
7879 |
or reading output of a subprocess. |
7880 |
Only 128th through 159th elements has a meaning. */); |
7881 |
Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
7882 |
|
7883 |
DEFVAR_LISP ("select-safe-coding-system-function", |
7884 |
&Vselect_safe_coding_system_function, |
7885 |
doc: /* Function to call to select safe coding system for encoding a text. |
7886 |
|
7887 |
If set, this function is called to force a user to select a proper |
7888 |
coding system which can encode the text in the case that a default |
7889 |
coding system used in each operation can't encode the text. |
7890 |
|
7891 |
The default value is `select-safe-coding-system' (which see). */); |
7892 |
Vselect_safe_coding_system_function = Qnil; |
7893 |
|
7894 |
DEFVAR_BOOL ("coding-system-require-warning", |
7895 |
&coding_system_require_warning, |
7896 |
doc: /* Internal use only. |
7897 |
If non-nil, on writing a file, `select-safe-coding-system-function' is |
7898 |
called even if `coding-system-for-write' is non-nil. The command |
7899 |
`universal-coding-system-argument' binds this variable to t temporarily. */); |
7900 |
coding_system_require_warning = 0; |
7901 |
|
7902 |
|
7903 |
DEFVAR_BOOL ("inhibit-iso-escape-detection", |
7904 |
&inhibit_iso_escape_detection, |
7905 |
doc: /* If non-nil, Emacs ignores ISO2022's escape sequence on code detection. |
7906 |
|
7907 |
By default, on reading a file, Emacs tries to detect how the text is |
7908 |
encoded. This code detection is sensitive to escape sequences. If |
7909 |
the sequence is valid as ISO2022, the code is determined as one of |
7910 |
the ISO2022 encodings, and the file is decoded by the corresponding |
7911 |
coding system (e.g. `iso-2022-7bit'). |
7912 |
|
7913 |
However, there may be a case that you want to read escape sequences in |
7914 |
a file as is. In such a case, you can set this variable to non-nil. |
7915 |
Then, as the code detection ignores any escape sequences, no file is |
7916 |
detected as encoded in some ISO2022 encoding. The result is that all |
7917 |
escape sequences become visible in a buffer. |
7918 |
|
7919 |
The default value is nil, and it is strongly recommended not to change |
7920 |
it. That is because many Emacs Lisp source files that contain |
7921 |
non-ASCII characters are encoded by the coding system `iso-2022-7bit' |
7922 |
in Emacs's distribution, and they won't be decoded correctly on |
7923 |
reading if you suppress escape sequence detection. |
7924 |
|
7925 |
The other way to read escape sequences in a file without decoding is |
7926 |
to explicitly specify some coding system that doesn't use ISO2022's |
7927 |
escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
7928 |
inhibit_iso_escape_detection = 0; |
7929 |
|
7930 |
DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, |
7931 |
doc: /* Char table for translating self-inserting characters. |
7932 |
This is applied to the result of input methods, not their input. See also |
7933 |
`keyboard-translate-table'. */); |
7934 |
Vtranslation_table_for_input = Qnil; |
7935 |
} |
7936 |
|
7937 |
char * |
7938 |
emacs_strerror (error_number) |
7939 |
int error_number; |
7940 |
{ |
7941 |
char *str; |
7942 |
|
7943 |
synchronize_system_messages_locale (); |
7944 |
str = strerror (error_number); |
7945 |
|
7946 |
if (! NILP (Vlocale_coding_system)) |
7947 |
{ |
7948 |
Lisp_Object dec = code_convert_string_norecord (build_string (str), |
7949 |
Vlocale_coding_system, |
7950 |
0); |
7951 |
str = (char *) SDATA (dec); |
7952 |
} |
7953 |
|
7954 |
return str; |
7955 |
} |
7956 |
|
7957 |
#endif /* emacs */ |
7958 |
|
7959 |
/* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d |
7960 |
(do not change this comment) */ |