Commit | Line | Data |
---|---|---|
4ed46869 | 1 | /* Coding system handler (conversion, detection, and etc). |
4a2f9c6a | 2 | Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. |
203cb916 | 3 | Licensed to the Free Software Foundation. |
4ed46869 | 4 | |
369314dc KH |
5 | This file is part of GNU Emacs. |
6 | ||
7 | GNU Emacs is free software; you can redistribute it and/or modify | |
8 | it under the terms of the GNU General Public License as published by | |
9 | the Free Software Foundation; either version 2, or (at your option) | |
10 | any later version. | |
4ed46869 | 11 | |
369314dc KH |
12 | GNU Emacs is distributed in the hope that it will be useful, |
13 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
14 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
15 | GNU General Public License for more details. | |
4ed46869 | 16 | |
369314dc KH |
17 | You should have received a copy of the GNU General Public License |
18 | along with GNU Emacs; see the file COPYING. If not, write to | |
19 | the Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
20 | Boston, MA 02111-1307, USA. */ | |
4ed46869 KH |
21 | |
22 | /*** TABLE OF CONTENTS *** | |
23 | ||
b73bfc1c | 24 | 0. General comments |
4ed46869 | 25 | 1. Preamble |
0ef69138 | 26 | 2. Emacs' internal format (emacs-mule) handlers |
4ed46869 KH |
27 | 3. ISO2022 handlers |
28 | 4. Shift-JIS and BIG5 handlers | |
1397dc18 KH |
29 | 5. CCL handlers |
30 | 6. End-of-line handlers | |
31 | 7. C library functions | |
32 | 8. Emacs Lisp library functions | |
33 | 9. Post-amble | |
4ed46869 KH |
34 | |
35 | */ | |
36 | ||
b73bfc1c KH |
37 | /*** 0. General comments ***/ |
38 | ||
39 | ||
4ed46869 KH |
40 | /*** GENERAL NOTE on CODING SYSTEM *** |
41 | ||
42 | Coding system is an encoding mechanism of one or more character | |
43 | sets. Here's a list of coding systems which Emacs can handle. When | |
44 | we say "decode", it means converting some other coding system to | |
0ef69138 KH |
45 | Emacs' internal format (emacs-internal), and when we say "encode", |
46 | it means converting the coding system emacs-mule to some other | |
47 | coding system. | |
4ed46869 | 48 | |
0ef69138 | 49 | 0. Emacs' internal format (emacs-mule) |
4ed46869 KH |
50 | |
51 | Emacs itself holds a multi-lingual character in a buffer and a string | |
f4dee582 | 52 | in a special format. Details are described in section 2. |
4ed46869 KH |
53 | |
54 | 1. ISO2022 | |
55 | ||
56 | The most famous coding system for multiple character sets. X's | |
f4dee582 RS |
57 | Compound Text, various EUCs (Extended Unix Code), and coding |
58 | systems used in Internet communication such as ISO-2022-JP are | |
59 | all variants of ISO2022. Details are described in section 3. | |
4ed46869 KH |
60 | |
61 | 2. SJIS (or Shift-JIS or MS-Kanji-Code) | |
62 | ||
63 | A coding system to encode character sets: ASCII, JISX0201, and | |
64 | JISX0208. Widely used for PC's in Japan. Details are described in | |
f4dee582 | 65 | section 4. |
4ed46869 KH |
66 | |
67 | 3. BIG5 | |
68 | ||
69 | A coding system to encode character sets: ASCII and Big5. Widely | |
70 | used by Chinese (mainly in Taiwan and Hong Kong). Details are | |
f4dee582 RS |
71 | described in section 4. In this file, when we write "BIG5" |
72 | (all uppercase), we mean the coding system, and when we write | |
73 | "Big5" (capitalized), we mean the character set. | |
4ed46869 | 74 | |
27901516 KH |
75 | 4. Raw text |
76 | ||
4608c386 KH |
77 | A coding system for a text containing random 8-bit code. Emacs does |
78 | no code conversion on such a text except for end-of-line format. | |
27901516 KH |
79 | |
80 | 5. Other | |
4ed46869 | 81 | |
f4dee582 | 82 | If a user wants to read/write a text encoded in a coding system not |
4ed46869 KH |
83 | listed above, he can supply a decoder and an encoder for it in CCL |
84 | (Code Conversion Language) programs. Emacs executes the CCL program | |
85 | while reading/writing. | |
86 | ||
d46c5b12 KH |
87 | Emacs represents a coding system by a Lisp symbol that has a property |
88 | `coding-system'. But, before actually using the coding system, the | |
4ed46869 | 89 | information about it is set in a structure of type `struct |
f4dee582 | 90 | coding_system' for rapid processing. See section 6 for more details. |
4ed46869 KH |
91 | |
92 | */ | |
93 | ||
94 | /*** GENERAL NOTES on END-OF-LINE FORMAT *** | |
95 | ||
96 | How end-of-line of a text is encoded depends on a system. For | |
97 | instance, Unix's format is just one byte of `line-feed' code, | |
f4dee582 | 98 | whereas DOS's format is two-byte sequence of `carriage-return' and |
d46c5b12 KH |
99 | `line-feed' codes. MacOS's format is usually one byte of |
100 | `carriage-return'. | |
4ed46869 | 101 | |
f4dee582 RS |
102 | Since text characters encoding and end-of-line encoding are |
103 | independent, any coding system described above can take | |
4ed46869 | 104 | any format of end-of-line. So, Emacs has information of format of |
f4dee582 | 105 | end-of-line in each coding-system. See section 6 for more details. |
4ed46869 KH |
106 | |
107 | */ | |
108 | ||
109 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** | |
110 | ||
111 | These functions check if a text between SRC and SRC_END is encoded | |
112 | in the coding system category XXX. Each returns an integer value in | |
113 | which appropriate flag bits for the category XXX is set. The flag | |
114 | bits are defined in macros CODING_CATEGORY_MASK_XXX. Below is the | |
115 | template of these functions. */ | |
116 | #if 0 | |
117 | int | |
0ef69138 | 118 | detect_coding_emacs_mule (src, src_end) |
4ed46869 KH |
119 | unsigned char *src, *src_end; |
120 | { | |
121 | ... | |
122 | } | |
123 | #endif | |
124 | ||
125 | /*** GENERAL NOTES on `decode_coding_XXX ()' functions *** | |
126 | ||
b73bfc1c KH |
127 | These functions decode SRC_BYTES length of unibyte text at SOURCE |
128 | encoded in CODING to Emacs' internal format. The resulting | |
129 | multibyte text goes to a place pointed to by DESTINATION, the length | |
130 | of which should not exceed DST_BYTES. | |
d46c5b12 | 131 | |
b73bfc1c KH |
132 | These functions set the information of original and decoded texts in |
133 | the members produced, produced_char, consumed, and consumed_char of | |
134 | the structure *CODING. They also set the member result to one of | |
135 | CODING_FINISH_XXX indicating how the decoding finished. | |
d46c5b12 KH |
136 | |
137 | DST_BYTES zero means that source area and destination area are | |
138 | overlapped, which means that we can produce a decoded text until it | |
139 | reaches at the head of not-yet-decoded source text. | |
140 | ||
141 | Below is a template of these functions. */ | |
4ed46869 | 142 | #if 0 |
b73bfc1c | 143 | static void |
d46c5b12 | 144 | decode_coding_XXX (coding, source, destination, src_bytes, dst_bytes) |
4ed46869 KH |
145 | struct coding_system *coding; |
146 | unsigned char *source, *destination; | |
147 | int src_bytes, dst_bytes; | |
4ed46869 KH |
148 | { |
149 | ... | |
150 | } | |
151 | #endif | |
152 | ||
153 | /*** GENERAL NOTES on `encode_coding_XXX ()' functions *** | |
154 | ||
0ef69138 | 155 | These functions encode SRC_BYTES length text at SOURCE of Emacs' |
b73bfc1c KH |
156 | internal multibyte format to CODING. The resulting unibyte text |
157 | goes to a place pointed to by DESTINATION, the length of which | |
158 | should not exceed DST_BYTES. | |
d46c5b12 | 159 | |
b73bfc1c KH |
160 | These functions set the information of original and encoded texts in |
161 | the members produced, produced_char, consumed, and consumed_char of | |
162 | the structure *CODING. They also set the member result to one of | |
163 | CODING_FINISH_XXX indicating how the encoding finished. | |
d46c5b12 KH |
164 | |
165 | DST_BYTES zero means that source area and destination area are | |
b73bfc1c KH |
166 | overlapped, which means that we can produce a encoded text until it |
167 | reaches at the head of not-yet-encoded source text. | |
d46c5b12 KH |
168 | |
169 | Below is a template of these functions. */ | |
4ed46869 | 170 | #if 0 |
b73bfc1c | 171 | static void |
d46c5b12 | 172 | encode_coding_XXX (coding, source, destination, src_bytes, dst_bytes) |
4ed46869 KH |
173 | struct coding_system *coding; |
174 | unsigned char *source, *destination; | |
175 | int src_bytes, dst_bytes; | |
4ed46869 KH |
176 | { |
177 | ... | |
178 | } | |
179 | #endif | |
180 | ||
181 | /*** COMMONLY USED MACROS ***/ | |
182 | ||
b73bfc1c KH |
183 | /* The following two macros ONE_MORE_BYTE and TWO_MORE_BYTES safely |
184 | get one, two, and three bytes from the source text respectively. | |
185 | If there are not enough bytes in the source, they jump to | |
186 | `label_end_of_loop'. The caller should set variables `coding', | |
187 | `src' and `src_end' to appropriate pointer in advance. These | |
188 | macros are called from decoding routines `decode_coding_XXX', thus | |
189 | it is assumed that the source text is unibyte. */ | |
4ed46869 | 190 | |
b73bfc1c KH |
191 | #define ONE_MORE_BYTE(c1) \ |
192 | do { \ | |
193 | if (src >= src_end) \ | |
194 | { \ | |
195 | coding->result = CODING_FINISH_INSUFFICIENT_SRC; \ | |
196 | goto label_end_of_loop; \ | |
197 | } \ | |
198 | c1 = *src++; \ | |
4ed46869 KH |
199 | } while (0) |
200 | ||
b73bfc1c KH |
201 | #define TWO_MORE_BYTES(c1, c2) \ |
202 | do { \ | |
203 | if (src + 1 >= src_end) \ | |
204 | { \ | |
205 | coding->result = CODING_FINISH_INSUFFICIENT_SRC; \ | |
206 | goto label_end_of_loop; \ | |
207 | } \ | |
208 | c1 = *src++; \ | |
209 | c2 = *src++; \ | |
4ed46869 KH |
210 | } while (0) |
211 | ||
4ed46869 | 212 | |
b73bfc1c KH |
213 | /* Set C to the next character at the source text pointed by `src'. |
214 | If there are not enough characters in the source, jump to | |
215 | `label_end_of_loop'. The caller should set variables `coding' | |
216 | `src', `src_end', and `translation_table' to appropriate pointers | |
217 | in advance. This macro is used in encoding routines | |
218 | `encode_coding_XXX', thus it assumes that the source text is in | |
219 | multibyte form except for 8-bit characters. 8-bit characters are | |
220 | in multibyte form if coding->src_multibyte is nonzero, else they | |
221 | are represented by a single byte. */ | |
4ed46869 | 222 | |
b73bfc1c KH |
223 | #define ONE_MORE_CHAR(c) \ |
224 | do { \ | |
225 | int len = src_end - src; \ | |
226 | int bytes; \ | |
227 | if (len <= 0) \ | |
228 | { \ | |
229 | coding->result = CODING_FINISH_INSUFFICIENT_SRC; \ | |
230 | goto label_end_of_loop; \ | |
231 | } \ | |
232 | if (coding->src_multibyte \ | |
233 | || UNIBYTE_STR_AS_MULTIBYTE_P (src, len, bytes)) \ | |
234 | c = STRING_CHAR_AND_LENGTH (src, len, bytes); \ | |
235 | else \ | |
236 | c = *src, bytes = 1; \ | |
237 | if (!NILP (translation_table)) \ | |
238 | c = translate_char (translation_table, c, 0, 0, 0); \ | |
239 | src += bytes; \ | |
4ed46869 KH |
240 | } while (0) |
241 | ||
4ed46869 | 242 | |
b73bfc1c KH |
243 | /* Produce a multibyte form of characater C to `dst'. Jump to |
244 | `label_end_of_loop' if there's not enough space at `dst'. | |
245 | ||
246 | If we are now in the middle of composition sequence, the decoded | |
247 | character may be ALTCHAR (for the current composition). In that | |
248 | case, the character goes to coding->cmp_data->data instead of | |
249 | `dst'. | |
250 | ||
251 | This macro is used in decoding routines. */ | |
252 | ||
253 | #define EMIT_CHAR(c) \ | |
4ed46869 | 254 | do { \ |
b73bfc1c KH |
255 | if (! COMPOSING_P (coding) \ |
256 | || coding->composing == COMPOSITION_RELATIVE \ | |
257 | || coding->composing == COMPOSITION_WITH_RULE) \ | |
258 | { \ | |
259 | int bytes = CHAR_BYTES (c); \ | |
260 | if ((dst + bytes) > (dst_bytes ? dst_end : src)) \ | |
261 | { \ | |
262 | coding->result = CODING_FINISH_INSUFFICIENT_DST; \ | |
263 | goto label_end_of_loop; \ | |
264 | } \ | |
265 | dst += CHAR_STRING (c, dst); \ | |
266 | coding->produced_char++; \ | |
267 | } \ | |
ec6d2bb8 | 268 | \ |
b73bfc1c KH |
269 | if (COMPOSING_P (coding) \ |
270 | && coding->composing != COMPOSITION_RELATIVE) \ | |
271 | { \ | |
272 | CODING_ADD_COMPOSITION_COMPONENT (coding, c); \ | |
273 | coding->composition_rule_follows \ | |
274 | = coding->composing != COMPOSITION_WITH_ALTCHARS; \ | |
275 | } \ | |
4ed46869 KH |
276 | } while (0) |
277 | ||
4ed46869 | 278 | |
b73bfc1c KH |
279 | #define EMIT_ONE_BYTE(c) \ |
280 | do { \ | |
281 | if (dst >= (dst_bytes ? dst_end : src)) \ | |
282 | { \ | |
283 | coding->result = CODING_FINISH_INSUFFICIENT_DST; \ | |
284 | goto label_end_of_loop; \ | |
285 | } \ | |
286 | *dst++ = c; \ | |
287 | } while (0) | |
288 | ||
289 | #define EMIT_TWO_BYTES(c1, c2) \ | |
290 | do { \ | |
291 | if (dst + 2 > (dst_bytes ? dst_end : src)) \ | |
292 | { \ | |
293 | coding->result = CODING_FINISH_INSUFFICIENT_DST; \ | |
294 | goto label_end_of_loop; \ | |
295 | } \ | |
296 | *dst++ = c1, *dst++ = c2; \ | |
297 | } while (0) | |
298 | ||
299 | #define EMIT_BYTES(from, to) \ | |
300 | do { \ | |
301 | if (dst + (to - from) > (dst_bytes ? dst_end : src)) \ | |
302 | { \ | |
303 | coding->result = CODING_FINISH_INSUFFICIENT_DST; \ | |
304 | goto label_end_of_loop; \ | |
305 | } \ | |
306 | while (from < to) \ | |
307 | *dst++ = *from++; \ | |
4ed46869 KH |
308 | } while (0) |
309 | ||
310 | \f | |
311 | /*** 1. Preamble ***/ | |
312 | ||
68c45bf0 PE |
313 | #ifdef emacs |
314 | #include <config.h> | |
315 | #endif | |
316 | ||
4ed46869 KH |
317 | #include <stdio.h> |
318 | ||
319 | #ifdef emacs | |
320 | ||
4ed46869 KH |
321 | #include "lisp.h" |
322 | #include "buffer.h" | |
323 | #include "charset.h" | |
ec6d2bb8 | 324 | #include "composite.h" |
4ed46869 KH |
325 | #include "ccl.h" |
326 | #include "coding.h" | |
327 | #include "window.h" | |
328 | ||
329 | #else /* not emacs */ | |
330 | ||
331 | #include "mulelib.h" | |
332 | ||
333 | #endif /* not emacs */ | |
334 | ||
335 | Lisp_Object Qcoding_system, Qeol_type; | |
336 | Lisp_Object Qbuffer_file_coding_system; | |
337 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
27901516 | 338 | Lisp_Object Qno_conversion, Qundecided; |
bb0115a2 | 339 | Lisp_Object Qcoding_system_history; |
70c22245 | 340 | Lisp_Object Qsafe_charsets; |
1397dc18 | 341 | Lisp_Object Qvalid_codes; |
4ed46869 KH |
342 | |
343 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; | |
344 | Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; | |
345 | Lisp_Object Qstart_process, Qopen_network_stream; | |
346 | Lisp_Object Qtarget_idx; | |
347 | ||
d46c5b12 KH |
348 | Lisp_Object Vselect_safe_coding_system_function; |
349 | ||
7722baf9 EZ |
350 | /* Mnemonic string for each format of end-of-line. */ |
351 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
352 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 353 | decided. */ |
7722baf9 | 354 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 | 355 | |
9ce27fde KH |
356 | /* Format of end-of-line decided by system. This is CODING_EOL_LF on |
357 | Unix, CODING_EOL_CRLF on DOS/Windows, and CODING_EOL_CR on Mac. */ | |
358 | int system_eol_type; | |
359 | ||
4ed46869 KH |
360 | #ifdef emacs |
361 | ||
4608c386 KH |
362 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
363 | ||
364 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 365 | |
d46c5b12 KH |
366 | /* Coding system emacs-mule and raw-text are for converting only |
367 | end-of-line format. */ | |
368 | Lisp_Object Qemacs_mule, Qraw_text; | |
9ce27fde | 369 | |
4ed46869 KH |
370 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
371 | routines by the following three variables. */ | |
372 | /* Coding-system for reading files and receiving data from process. */ | |
373 | Lisp_Object Vcoding_system_for_read; | |
374 | /* Coding-system for writing files and sending data to process. */ | |
375 | Lisp_Object Vcoding_system_for_write; | |
376 | /* Coding-system actually used in the latest I/O. */ | |
377 | Lisp_Object Vlast_coding_system_used; | |
378 | ||
c4825358 | 379 | /* A vector of length 256 which contains information about special |
94487c4e | 380 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 381 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 382 | |
9ce27fde KH |
383 | /* Flag to inhibit code conversion of end-of-line format. */ |
384 | int inhibit_eol_conversion; | |
385 | ||
ed29121d EZ |
386 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
387 | int inherit_process_coding_system; | |
388 | ||
c4825358 | 389 | /* Coding system to be used to encode text for terminal display. */ |
4ed46869 KH |
390 | struct coding_system terminal_coding; |
391 | ||
c4825358 KH |
392 | /* Coding system to be used to encode text for terminal display when |
393 | terminal coding system is nil. */ | |
394 | struct coding_system safe_terminal_coding; | |
395 | ||
396 | /* Coding system of what is sent from terminal keyboard. */ | |
4ed46869 KH |
397 | struct coding_system keyboard_coding; |
398 | ||
6bc51348 KH |
399 | /* Default coding system to be used to write a file. */ |
400 | struct coding_system default_buffer_file_coding; | |
401 | ||
02ba4723 KH |
402 | Lisp_Object Vfile_coding_system_alist; |
403 | Lisp_Object Vprocess_coding_system_alist; | |
404 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 405 | |
68c45bf0 PE |
406 | Lisp_Object Vlocale_coding_system; |
407 | ||
4ed46869 KH |
408 | #endif /* emacs */ |
409 | ||
d46c5b12 | 410 | Lisp_Object Qcoding_category, Qcoding_category_index; |
4ed46869 KH |
411 | |
412 | /* List of symbols `coding-category-xxx' ordered by priority. */ | |
413 | Lisp_Object Vcoding_category_list; | |
414 | ||
d46c5b12 KH |
415 | /* Table of coding categories (Lisp symbols). */ |
416 | Lisp_Object Vcoding_category_table; | |
4ed46869 KH |
417 | |
418 | /* Table of names of symbol for each coding-category. */ | |
419 | char *coding_category_name[CODING_CATEGORY_IDX_MAX] = { | |
0ef69138 | 420 | "coding-category-emacs-mule", |
4ed46869 KH |
421 | "coding-category-sjis", |
422 | "coding-category-iso-7", | |
d46c5b12 | 423 | "coding-category-iso-7-tight", |
4ed46869 KH |
424 | "coding-category-iso-8-1", |
425 | "coding-category-iso-8-2", | |
7717c392 KH |
426 | "coding-category-iso-7-else", |
427 | "coding-category-iso-8-else", | |
89fa8b36 | 428 | "coding-category-ccl", |
4ed46869 | 429 | "coding-category-big5", |
fa42c37f KH |
430 | "coding-category-utf-8", |
431 | "coding-category-utf-16-be", | |
432 | "coding-category-utf-16-le", | |
27901516 | 433 | "coding-category-raw-text", |
89fa8b36 | 434 | "coding-category-binary" |
4ed46869 KH |
435 | }; |
436 | ||
66cfb530 | 437 | /* Table of pointers to coding systems corresponding to each coding |
d46c5b12 KH |
438 | categories. */ |
439 | struct coding_system *coding_system_table[CODING_CATEGORY_IDX_MAX]; | |
440 | ||
66cfb530 KH |
441 | /* Table of coding category masks. Nth element is a mask for a coding |
442 | cateogry of which priority is Nth. */ | |
443 | static | |
444 | int coding_priorities[CODING_CATEGORY_IDX_MAX]; | |
445 | ||
f967223b KH |
446 | /* Flag to tell if we look up translation table on character code |
447 | conversion. */ | |
84fbb8a0 | 448 | Lisp_Object Venable_character_translation; |
f967223b KH |
449 | /* Standard translation table to look up on decoding (reading). */ |
450 | Lisp_Object Vstandard_translation_table_for_decode; | |
451 | /* Standard translation table to look up on encoding (writing). */ | |
452 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 453 | |
f967223b KH |
454 | Lisp_Object Qtranslation_table; |
455 | Lisp_Object Qtranslation_table_id; | |
456 | Lisp_Object Qtranslation_table_for_decode; | |
457 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
458 | |
459 | /* Alist of charsets vs revision number. */ | |
460 | Lisp_Object Vcharset_revision_alist; | |
461 | ||
02ba4723 KH |
462 | /* Default coding systems used for process I/O. */ |
463 | Lisp_Object Vdefault_process_coding_system; | |
464 | ||
b843d1ae KH |
465 | /* Global flag to tell that we can't call post-read-conversion and |
466 | pre-write-conversion functions. Usually the value is zero, but it | |
467 | is set to 1 temporarily while such functions are running. This is | |
468 | to avoid infinite recursive call. */ | |
469 | static int inhibit_pre_post_conversion; | |
470 | ||
4ed46869 | 471 | \f |
0ef69138 | 472 | /*** 2. Emacs internal format (emacs-mule) handlers ***/ |
4ed46869 KH |
473 | |
474 | /* Emacs' internal format for encoding multiple character sets is a | |
f4dee582 | 475 | kind of multi-byte encoding, i.e. characters are encoded by |
b73bfc1c KH |
476 | variable-length sequences of one-byte codes. |
477 | ||
478 | ASCII characters and control characters (e.g. `tab', `newline') are | |
479 | represented by one-byte sequences which are their ASCII codes, in | |
480 | the range 0x00 through 0x7F. | |
481 | ||
482 | 8-bit characters of the range 0x80..0x9F are represented by | |
483 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
484 | code + 0x20). | |
485 | ||
486 | 8-bit characters of the range 0xA0..0xFF are represented by | |
487 | one-byte sequences which are their 8-bit code. | |
488 | ||
489 | The other characters are represented by a sequence of `base | |
490 | leading-code', optional `extended leading-code', and one or two | |
491 | `position-code's. The length of the sequence is determined by the | |
492 | base leading-code. Leading-code takes the range 0x80 through 0x9F, | |
493 | whereas extended leading-code and position-code take the range 0xA0 | |
494 | through 0xFF. See `charset.h' for more details about leading-code | |
495 | and position-code. | |
f4dee582 | 496 | |
4ed46869 | 497 | --- CODE RANGE of Emacs' internal format --- |
b73bfc1c KH |
498 | character set range |
499 | ------------- ----- | |
500 | ascii 0x00..0x7F | |
501 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
502 | eight-bit-graphic 0xA0..0xBF | |
503 | ELSE 0x81..0x9F + [0xA0..0xFF]+ | |
4ed46869 KH |
504 | --------------------------------------------- |
505 | ||
506 | */ | |
507 | ||
508 | enum emacs_code_class_type emacs_code_class[256]; | |
509 | ||
4ed46869 KH |
510 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
511 | Check if a text is encoded in Emacs' internal format. If it is, | |
d46c5b12 | 512 | return CODING_CATEGORY_MASK_EMACS_MULE, else return 0. */ |
4ed46869 KH |
513 | |
514 | int | |
0ef69138 | 515 | detect_coding_emacs_mule (src, src_end) |
b73bfc1c | 516 | unsigned char *src, *src_end; |
4ed46869 KH |
517 | { |
518 | unsigned char c; | |
519 | int composing = 0; | |
b73bfc1c KH |
520 | /* Dummy for ONE_MORE_BYTE. */ |
521 | struct coding_system dummy_coding; | |
522 | struct coding_system *coding = &dummy_coding; | |
4ed46869 | 523 | |
b73bfc1c | 524 | while (1) |
4ed46869 | 525 | { |
b73bfc1c | 526 | ONE_MORE_BYTE (c); |
4ed46869 KH |
527 | |
528 | if (composing) | |
529 | { | |
530 | if (c < 0xA0) | |
531 | composing = 0; | |
b73bfc1c KH |
532 | else if (c == 0xA0) |
533 | { | |
534 | ONE_MORE_BYTE (c); | |
535 | c &= 0x7F; | |
536 | } | |
4ed46869 KH |
537 | else |
538 | c -= 0x20; | |
539 | } | |
540 | ||
b73bfc1c | 541 | if (c < 0x20) |
4ed46869 | 542 | { |
4ed46869 KH |
543 | if (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) |
544 | return 0; | |
b73bfc1c KH |
545 | } |
546 | else if (c >= 0x80 && c < 0xA0) | |
547 | { | |
548 | if (c == 0x80) | |
549 | /* Old leading code for a composite character. */ | |
550 | composing = 1; | |
551 | else | |
552 | { | |
553 | unsigned char *src_base = src - 1; | |
554 | int bytes; | |
4ed46869 | 555 | |
b73bfc1c KH |
556 | if (!UNIBYTE_STR_AS_MULTIBYTE_P (src_base, src_end - src_base, |
557 | bytes)) | |
558 | return 0; | |
559 | src = src_base + bytes; | |
560 | } | |
561 | } | |
562 | } | |
563 | label_end_of_loop: | |
564 | return CODING_CATEGORY_MASK_EMACS_MULE; | |
565 | } | |
4ed46869 | 566 | |
4ed46869 | 567 | |
b73bfc1c | 568 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 569 | |
b73bfc1c KH |
570 | static void |
571 | decode_coding_emacs_mule (coding, source, destination, src_bytes, dst_bytes) | |
572 | struct coding_system *coding; | |
573 | unsigned char *source, *destination; | |
574 | int src_bytes, dst_bytes; | |
575 | { | |
576 | unsigned char *src = source; | |
577 | unsigned char *src_end = source + src_bytes; | |
578 | unsigned char *dst = destination; | |
579 | unsigned char *dst_end = destination + dst_bytes; | |
580 | /* SRC_BASE remembers the start position in source in each loop. | |
581 | The loop will be exited when there's not enough source code, or | |
582 | when there's not enough destination area to produce a | |
583 | character. */ | |
584 | unsigned char *src_base; | |
4ed46869 | 585 | |
b73bfc1c KH |
586 | coding->produced_char = 0; |
587 | while (src < src_end) | |
588 | { | |
589 | unsigned char tmp[MAX_MULTIBYTE_LENGTH], *p; | |
590 | int bytes; | |
ec6d2bb8 | 591 | |
b73bfc1c KH |
592 | src_base = src; |
593 | if (UNIBYTE_STR_AS_MULTIBYTE_P (src, src_end - src, bytes)) | |
594 | { | |
595 | p = src; | |
596 | src += bytes; | |
597 | } | |
598 | else | |
599 | { | |
600 | bytes = CHAR_STRING (*src, tmp); | |
601 | p = tmp; | |
602 | src++; | |
603 | } | |
604 | if (dst + bytes >= (dst_bytes ? dst_end : src)) | |
605 | { | |
606 | coding->result = CODING_FINISH_INSUFFICIENT_DST; | |
4ed46869 KH |
607 | break; |
608 | } | |
b73bfc1c KH |
609 | while (bytes--) *dst++ = *p++; |
610 | coding->produced_char++; | |
4ed46869 | 611 | } |
b73bfc1c KH |
612 | coding->consumed = coding->consumed_char = src_base - source; |
613 | coding->produced = dst - destination; | |
4ed46869 KH |
614 | } |
615 | ||
b73bfc1c KH |
616 | #define encode_coding_emacs_mule(coding, source, destination, src_bytes, dst_bytes) \ |
617 | encode_eol (coding, source, destination, src_bytes, dst_bytes) | |
618 | ||
619 | ||
4ed46869 KH |
620 | \f |
621 | /*** 3. ISO2022 handlers ***/ | |
622 | ||
623 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd KH |
624 | Since the intention of this note is to help understand the |
625 | functions in this file, some parts are NOT ACCURATE or OVERLY | |
626 | SIMPLIFIED. For thorough understanding, please refer to the | |
4ed46869 KH |
627 | original document of ISO2022. |
628 | ||
629 | ISO2022 provides many mechanisms to encode several character sets | |
39787efd KH |
630 | in 7-bit and 8-bit environments. For 7-bite environments, all text |
631 | is encoded using bytes less than 128. This may make the encoded | |
632 | text a little bit longer, but the text passes more easily through | |
633 | several gateways, some of which strip off MSB (Most Signigant Bit). | |
b73bfc1c | 634 | |
39787efd | 635 | There are two kinds of character sets: control character set and |
4ed46869 KH |
636 | graphic character set. The former contains control characters such |
637 | as `newline' and `escape' to provide control functions (control | |
39787efd KH |
638 | functions are also provided by escape sequences). The latter |
639 | contains graphic characters such as 'A' and '-'. Emacs recognizes | |
4ed46869 KH |
640 | two control character sets and many graphic character sets. |
641 | ||
642 | Graphic character sets are classified into one of the following | |
39787efd KH |
643 | four classes, according to the number of bytes (DIMENSION) and |
644 | number of characters in one dimension (CHARS) of the set: | |
645 | - DIMENSION1_CHARS94 | |
646 | - DIMENSION1_CHARS96 | |
647 | - DIMENSION2_CHARS94 | |
648 | - DIMENSION2_CHARS96 | |
649 | ||
650 | In addition, each character set is assigned an identification tag, | |
651 | unique for each set, called "final character" (denoted as <F> | |
652 | hereafter). The <F> of each character set is decided by ECMA(*) | |
653 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
654 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
655 | |
656 | Note (*): ECMA = European Computer Manufacturers Association | |
657 | ||
658 | Here are examples of graphic character set [NAME(<F>)]: | |
659 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... | |
660 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
661 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
662 | o DIMENSION2_CHARS96 -- none for the moment | |
663 | ||
39787efd | 664 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
665 | C0 [0x00..0x1F] -- control character plane 0 |
666 | GL [0x20..0x7F] -- graphic character plane 0 | |
667 | C1 [0x80..0x9F] -- control character plane 1 | |
668 | GR [0xA0..0xFF] -- graphic character plane 1 | |
669 | ||
670 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
671 | C1 by an escape sequence. The most common case is that: |
672 | - ISO646's control character set is designated/invoked to C0, and | |
673 | - ISO6429's control character set is designated/invoked to C1, | |
674 | and usually these designations/invocations are omitted in encoded | |
675 | text. In a 7-bit environment, only C0 can be used, and a control | |
676 | character for C1 is encoded by an appropriate escape sequence to | |
677 | fit into the environment. All control characters for C1 are | |
678 | defined to have corresponding escape sequences. | |
4ed46869 KH |
679 | |
680 | A graphic character set is at first designated to one of four | |
681 | graphic registers (G0 through G3), then these graphic registers are | |
682 | invoked to GL or GR. These designations and invocations can be | |
683 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
684 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
685 | these invocations and designations are omitted in encoded text. | |
686 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 687 | |
39787efd KH |
688 | When a graphic character set of CHARS94 is invoked to GL, codes |
689 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
690 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
691 | be used. | |
4ed46869 KH |
692 | |
693 | There are two ways of invocation: locking-shift and single-shift. | |
694 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
695 | invocation, whereas with single-shift, the invocation affects the |
696 | following character only and doesn't affect the locking-shift | |
697 | state. Invocations are done by the following control characters or | |
698 | escape sequences: | |
4ed46869 KH |
699 | |
700 | ---------------------------------------------------------------------- | |
39787efd | 701 | abbrev function cntrl escape seq description |
4ed46869 | 702 | ---------------------------------------------------------------------- |
39787efd KH |
703 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
704 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
705 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
706 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
707 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
708 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
709 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
710 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
711 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 712 | ---------------------------------------------------------------------- |
39787efd KH |
713 | (*) These are not used by any known coding system. |
714 | ||
715 | Control characters for these functions are defined by macros | |
716 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 717 | |
39787efd | 718 | Designations are done by the following escape sequences: |
4ed46869 KH |
719 | ---------------------------------------------------------------------- |
720 | escape sequence description | |
721 | ---------------------------------------------------------------------- | |
722 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
723 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
724 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
725 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
726 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
727 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
728 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
729 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
730 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
731 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
732 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
733 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
734 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
735 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
736 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
737 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
738 | ---------------------------------------------------------------------- | |
739 | ||
740 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 741 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
742 | |
743 | Note (*): Although these designations are not allowed in ISO2022, | |
744 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 745 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
746 | 7-bit environment, non-locking-shift, and non-single-shift. |
747 | ||
748 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
39787efd | 749 | '(' can be omitted. We refer to this as "short-form" hereafter. |
4ed46869 KH |
750 | |
751 | Now you may notice that there are a lot of ways for encoding the | |
39787efd KH |
752 | same multilingual text in ISO2022. Actually, there exist many |
753 | coding systems such as Compound Text (used in X11's inter client | |
754 | communication, ISO-2022-JP (used in Japanese internet), ISO-2022-KR | |
755 | (used in Korean internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
756 | localized platforms), and all of these are variants of ISO2022. |
757 | ||
758 | In addition to the above, Emacs handles two more kinds of escape | |
759 | sequences: ISO6429's direction specification and Emacs' private | |
760 | sequence for specifying character composition. | |
761 | ||
39787efd | 762 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
763 | o CSI ']' -- end of the current direction |
764 | o CSI '0' ']' -- end of the current direction | |
765 | o CSI '1' ']' -- start of left-to-right text | |
766 | o CSI '2' ']' -- start of right-to-left text | |
767 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
768 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
769 | ||
770 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
771 | o ESC '0' -- start relative composition |
772 | o ESC '1' -- end composition | |
773 | o ESC '2' -- start rule-base composition (*) | |
774 | o ESC '3' -- start relative composition with alternate chars (**) | |
775 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c KH |
776 | Since these are not standard escape sequences of any ISO standard, |
777 | the use of them for these meaning is restricted to Emacs only. | |
ec6d2bb8 | 778 | |
b73bfc1c KH |
779 | (*) This form is used only in Emacs 20.5 and the older versions, |
780 | but the newer versions can safely decode it. | |
781 | (**) This form is used only in Emacs 21.1 and the newer versions, | |
782 | and the older versions can't decode it. | |
ec6d2bb8 | 783 | |
b73bfc1c KH |
784 | Here's a list of examples usages of these composition escape |
785 | sequences (categorized by `enum composition_method'). | |
ec6d2bb8 | 786 | |
b73bfc1c | 787 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 788 | ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 789 | COMPOSITOIN_WITH_RULE: |
ec6d2bb8 | 790 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 791 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 792 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 793 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 794 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
795 | |
796 | enum iso_code_class_type iso_code_class[256]; | |
797 | ||
f024b6aa RS |
798 | #define CHARSET_OK(idx, charset) \ |
799 | (coding_system_table[idx] \ | |
800 | && (coding_system_table[idx]->safe_charsets[charset] \ | |
801 | || (CODING_SPEC_ISO_REQUESTED_DESIGNATION \ | |
802 | (coding_system_table[idx], charset) \ | |
803 | != CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION))) | |
d46c5b12 KH |
804 | |
805 | #define SHIFT_OUT_OK(idx) \ | |
806 | (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding_system_table[idx], 1) >= 0) | |
807 | ||
4ed46869 KH |
808 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
809 | Check if a text is encoded in ISO2022. If it is, returns an | |
810 | integer in which appropriate flag bits any of: | |
811 | CODING_CATEGORY_MASK_ISO_7 | |
d46c5b12 | 812 | CODING_CATEGORY_MASK_ISO_7_TIGHT |
4ed46869 KH |
813 | CODING_CATEGORY_MASK_ISO_8_1 |
814 | CODING_CATEGORY_MASK_ISO_8_2 | |
7717c392 KH |
815 | CODING_CATEGORY_MASK_ISO_7_ELSE |
816 | CODING_CATEGORY_MASK_ISO_8_ELSE | |
4ed46869 KH |
817 | are set. If a code which should never appear in ISO2022 is found, |
818 | returns 0. */ | |
819 | ||
820 | int | |
821 | detect_coding_iso2022 (src, src_end) | |
822 | unsigned char *src, *src_end; | |
823 | { | |
d46c5b12 KH |
824 | int mask = CODING_CATEGORY_MASK_ISO; |
825 | int mask_found = 0; | |
f46869e4 | 826 | int reg[4], shift_out = 0, single_shifting = 0; |
d46c5b12 | 827 | int c, c1, i, charset; |
b73bfc1c KH |
828 | /* Dummy for ONE_MORE_BYTE. */ |
829 | struct coding_system dummy_coding; | |
830 | struct coding_system *coding = &dummy_coding; | |
3f003981 | 831 | |
d46c5b12 | 832 | reg[0] = CHARSET_ASCII, reg[1] = reg[2] = reg[3] = -1; |
3f003981 | 833 | while (mask && src < src_end) |
4ed46869 | 834 | { |
b73bfc1c | 835 | ONE_MORE_BYTE (c); |
4ed46869 KH |
836 | switch (c) |
837 | { | |
838 | case ISO_CODE_ESC: | |
f46869e4 | 839 | single_shifting = 0; |
b73bfc1c | 840 | ONE_MORE_BYTE (c); |
d46c5b12 | 841 | if (c >= '(' && c <= '/') |
4ed46869 | 842 | { |
bf9cdd4e | 843 | /* Designation sequence for a charset of dimension 1. */ |
b73bfc1c | 844 | ONE_MORE_BYTE (c1); |
d46c5b12 KH |
845 | if (c1 < ' ' || c1 >= 0x80 |
846 | || (charset = iso_charset_table[0][c >= ','][c1]) < 0) | |
847 | /* Invalid designation sequence. Just ignore. */ | |
848 | break; | |
849 | reg[(c - '(') % 4] = charset; | |
bf9cdd4e KH |
850 | } |
851 | else if (c == '$') | |
852 | { | |
853 | /* Designation sequence for a charset of dimension 2. */ | |
b73bfc1c | 854 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
855 | if (c >= '@' && c <= 'B') |
856 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
d46c5b12 | 857 | reg[0] = charset = iso_charset_table[1][0][c]; |
bf9cdd4e | 858 | else if (c >= '(' && c <= '/') |
bcf26d6a | 859 | { |
b73bfc1c | 860 | ONE_MORE_BYTE (c1); |
d46c5b12 KH |
861 | if (c1 < ' ' || c1 >= 0x80 |
862 | || (charset = iso_charset_table[1][c >= ','][c1]) < 0) | |
863 | /* Invalid designation sequence. Just ignore. */ | |
864 | break; | |
865 | reg[(c - '(') % 4] = charset; | |
bcf26d6a | 866 | } |
bf9cdd4e | 867 | else |
d46c5b12 KH |
868 | /* Invalid designation sequence. Just ignore. */ |
869 | break; | |
870 | } | |
ae9ff118 | 871 | else if (c == 'N' || c == 'O') |
d46c5b12 | 872 | { |
ae9ff118 KH |
873 | /* ESC <Fe> for SS2 or SS3. */ |
874 | mask &= CODING_CATEGORY_MASK_ISO_7_ELSE; | |
d46c5b12 | 875 | break; |
4ed46869 | 876 | } |
ec6d2bb8 KH |
877 | else if (c >= '0' && c <= '4') |
878 | { | |
879 | /* ESC <Fp> for start/end composition. */ | |
880 | mask_found |= CODING_CATEGORY_MASK_ISO; | |
881 | break; | |
882 | } | |
bf9cdd4e | 883 | else |
d46c5b12 KH |
884 | /* Invalid escape sequence. Just ignore. */ |
885 | break; | |
886 | ||
887 | /* We found a valid designation sequence for CHARSET. */ | |
888 | mask &= ~CODING_CATEGORY_MASK_ISO_8BIT; | |
889 | if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7, charset)) | |
890 | mask_found |= CODING_CATEGORY_MASK_ISO_7; | |
891 | else | |
892 | mask &= ~CODING_CATEGORY_MASK_ISO_7; | |
893 | if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7_TIGHT, charset)) | |
894 | mask_found |= CODING_CATEGORY_MASK_ISO_7_TIGHT; | |
895 | else | |
896 | mask &= ~CODING_CATEGORY_MASK_ISO_7_TIGHT; | |
ae9ff118 KH |
897 | if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_7_ELSE, charset)) |
898 | mask_found |= CODING_CATEGORY_MASK_ISO_7_ELSE; | |
899 | else | |
d46c5b12 | 900 | mask &= ~CODING_CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 KH |
901 | if (CHARSET_OK (CODING_CATEGORY_IDX_ISO_8_ELSE, charset)) |
902 | mask_found |= CODING_CATEGORY_MASK_ISO_8_ELSE; | |
903 | else | |
d46c5b12 | 904 | mask &= ~CODING_CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
905 | break; |
906 | ||
4ed46869 | 907 | case ISO_CODE_SO: |
f46869e4 | 908 | single_shifting = 0; |
d46c5b12 KH |
909 | if (shift_out == 0 |
910 | && (reg[1] >= 0 | |
911 | || SHIFT_OUT_OK (CODING_CATEGORY_IDX_ISO_7_ELSE) | |
912 | || SHIFT_OUT_OK (CODING_CATEGORY_IDX_ISO_8_ELSE))) | |
913 | { | |
914 | /* Locking shift out. */ | |
915 | mask &= ~CODING_CATEGORY_MASK_ISO_7BIT; | |
916 | mask_found |= CODING_CATEGORY_MASK_ISO_SHIFT; | |
917 | } | |
e0e989f6 KH |
918 | break; |
919 | ||
d46c5b12 | 920 | case ISO_CODE_SI: |
f46869e4 | 921 | single_shifting = 0; |
d46c5b12 KH |
922 | if (shift_out == 1) |
923 | { | |
924 | /* Locking shift in. */ | |
925 | mask &= ~CODING_CATEGORY_MASK_ISO_7BIT; | |
926 | mask_found |= CODING_CATEGORY_MASK_ISO_SHIFT; | |
927 | } | |
928 | break; | |
929 | ||
4ed46869 | 930 | case ISO_CODE_CSI: |
f46869e4 | 931 | single_shifting = 0; |
4ed46869 KH |
932 | case ISO_CODE_SS2: |
933 | case ISO_CODE_SS3: | |
3f003981 KH |
934 | { |
935 | int newmask = CODING_CATEGORY_MASK_ISO_8_ELSE; | |
936 | ||
70c22245 KH |
937 | if (c != ISO_CODE_CSI) |
938 | { | |
d46c5b12 KH |
939 | if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags |
940 | & CODING_FLAG_ISO_SINGLE_SHIFT) | |
70c22245 | 941 | newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
d46c5b12 KH |
942 | if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags |
943 | & CODING_FLAG_ISO_SINGLE_SHIFT) | |
70c22245 | 944 | newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
f46869e4 | 945 | single_shifting = 1; |
70c22245 | 946 | } |
3f003981 KH |
947 | if (VECTORP (Vlatin_extra_code_table) |
948 | && !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
949 | { | |
d46c5b12 KH |
950 | if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags |
951 | & CODING_FLAG_ISO_LATIN_EXTRA) | |
3f003981 | 952 | newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
d46c5b12 KH |
953 | if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags |
954 | & CODING_FLAG_ISO_LATIN_EXTRA) | |
3f003981 KH |
955 | newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
956 | } | |
957 | mask &= newmask; | |
d46c5b12 | 958 | mask_found |= newmask; |
3f003981 KH |
959 | } |
960 | break; | |
4ed46869 KH |
961 | |
962 | default: | |
963 | if (c < 0x80) | |
f46869e4 KH |
964 | { |
965 | single_shifting = 0; | |
966 | break; | |
967 | } | |
4ed46869 | 968 | else if (c < 0xA0) |
c4825358 | 969 | { |
f46869e4 | 970 | single_shifting = 0; |
3f003981 KH |
971 | if (VECTORP (Vlatin_extra_code_table) |
972 | && !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
c4825358 | 973 | { |
3f003981 KH |
974 | int newmask = 0; |
975 | ||
d46c5b12 KH |
976 | if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_1]->flags |
977 | & CODING_FLAG_ISO_LATIN_EXTRA) | |
3f003981 | 978 | newmask |= CODING_CATEGORY_MASK_ISO_8_1; |
d46c5b12 KH |
979 | if (coding_system_table[CODING_CATEGORY_IDX_ISO_8_2]->flags |
980 | & CODING_FLAG_ISO_LATIN_EXTRA) | |
3f003981 KH |
981 | newmask |= CODING_CATEGORY_MASK_ISO_8_2; |
982 | mask &= newmask; | |
d46c5b12 | 983 | mask_found |= newmask; |
c4825358 | 984 | } |
3f003981 KH |
985 | else |
986 | return 0; | |
c4825358 | 987 | } |
4ed46869 KH |
988 | else |
989 | { | |
7717c392 | 990 | unsigned char *src_begin = src; |
4ed46869 | 991 | |
d46c5b12 | 992 | mask &= ~(CODING_CATEGORY_MASK_ISO_7BIT |
7717c392 | 993 | | CODING_CATEGORY_MASK_ISO_7_ELSE); |
d46c5b12 | 994 | mask_found |= CODING_CATEGORY_MASK_ISO_8_1; |
f46869e4 KH |
995 | /* Check the length of succeeding codes of the range |
996 | 0xA0..0FF. If the byte length is odd, we exclude | |
997 | CODING_CATEGORY_MASK_ISO_8_2. We can check this only | |
998 | when we are not single shifting. */ | |
b73bfc1c KH |
999 | if (!single_shifting |
1000 | && mask & CODING_CATEGORY_MASK_ISO_8_2) | |
f46869e4 | 1001 | { |
b73bfc1c KH |
1002 | int i = 0; |
1003 | while (src < src_end) | |
1004 | { | |
1005 | ONE_MORE_BYTE (c); | |
1006 | if (c < 0xA0) | |
1007 | break; | |
1008 | i++; | |
1009 | } | |
1010 | ||
1011 | if (i & 1 && src < src_end) | |
f46869e4 KH |
1012 | mask &= ~CODING_CATEGORY_MASK_ISO_8_2; |
1013 | else | |
1014 | mask_found |= CODING_CATEGORY_MASK_ISO_8_2; | |
1015 | } | |
4ed46869 KH |
1016 | } |
1017 | break; | |
1018 | } | |
1019 | } | |
b73bfc1c | 1020 | label_end_of_loop: |
d46c5b12 | 1021 | return (mask & mask_found); |
4ed46869 KH |
1022 | } |
1023 | ||
b73bfc1c KH |
1024 | /* Decode a character of which charset is CHARSET, the 1st position |
1025 | code is C1, the 2nd position code is C2, and return the decoded | |
1026 | character code. If the variable `translation_table' is non-nil, | |
1027 | returned the translated code. */ | |
ec6d2bb8 | 1028 | |
b73bfc1c KH |
1029 | #define DECODE_ISO_CHARACTER(charset, c1, c2) \ |
1030 | (NILP (translation_table) \ | |
1031 | ? MAKE_CHAR (charset, c1, c2) \ | |
1032 | : translate_char (translation_table, -1, charset, c1, c2)) | |
4ed46869 KH |
1033 | |
1034 | /* Set designation state into CODING. */ | |
d46c5b12 KH |
1035 | #define DECODE_DESIGNATION(reg, dimension, chars, final_char) \ |
1036 | do { \ | |
944bd420 KH |
1037 | int charset; \ |
1038 | \ | |
1039 | if (final_char < '0' || final_char >= 128) \ | |
1040 | goto label_invalid_code; \ | |
1041 | charset = ISO_CHARSET_TABLE (make_number (dimension), \ | |
1042 | make_number (chars), \ | |
1043 | make_number (final_char)); \ | |
d46c5b12 | 1044 | if (charset >= 0 \ |
704c5781 KH |
1045 | && (CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) == reg \ |
1046 | || coding->safe_charsets[charset])) \ | |
d46c5b12 KH |
1047 | { \ |
1048 | if (coding->spec.iso2022.last_invalid_designation_register == 0 \ | |
1049 | && reg == 0 \ | |
1050 | && charset == CHARSET_ASCII) \ | |
1051 | { \ | |
1052 | /* We should insert this designation sequence as is so \ | |
1053 | that it is surely written back to a file. */ \ | |
1054 | coding->spec.iso2022.last_invalid_designation_register = -1; \ | |
1055 | goto label_invalid_code; \ | |
1056 | } \ | |
1057 | coding->spec.iso2022.last_invalid_designation_register = -1; \ | |
1058 | if ((coding->mode & CODING_MODE_DIRECTION) \ | |
1059 | && CHARSET_REVERSE_CHARSET (charset) >= 0) \ | |
1060 | charset = CHARSET_REVERSE_CHARSET (charset); \ | |
1061 | CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \ | |
1062 | } \ | |
1063 | else \ | |
1064 | { \ | |
1065 | coding->spec.iso2022.last_invalid_designation_register = reg; \ | |
1066 | goto label_invalid_code; \ | |
1067 | } \ | |
4ed46869 KH |
1068 | } while (0) |
1069 | ||
ec6d2bb8 KH |
1070 | /* Allocate a memory block for storing information about compositions. |
1071 | The block is chained to the already allocated blocks. */ | |
d46c5b12 | 1072 | |
33fb63eb | 1073 | void |
ec6d2bb8 | 1074 | coding_allocate_composition_data (coding, char_offset) |
d46c5b12 | 1075 | struct coding_system *coding; |
ec6d2bb8 | 1076 | int char_offset; |
d46c5b12 | 1077 | { |
ec6d2bb8 KH |
1078 | struct composition_data *cmp_data |
1079 | = (struct composition_data *) xmalloc (sizeof *cmp_data); | |
1080 | ||
1081 | cmp_data->char_offset = char_offset; | |
1082 | cmp_data->used = 0; | |
1083 | cmp_data->prev = coding->cmp_data; | |
1084 | cmp_data->next = NULL; | |
1085 | if (coding->cmp_data) | |
1086 | coding->cmp_data->next = cmp_data; | |
1087 | coding->cmp_data = cmp_data; | |
1088 | coding->cmp_data_start = 0; | |
1089 | } | |
d46c5b12 | 1090 | |
ec6d2bb8 KH |
1091 | /* Record the starting position START and METHOD of one composition. */ |
1092 | ||
1093 | #define CODING_ADD_COMPOSITION_START(coding, start, method) \ | |
1094 | do { \ | |
1095 | struct composition_data *cmp_data = coding->cmp_data; \ | |
1096 | int *data = cmp_data->data + cmp_data->used; \ | |
1097 | coding->cmp_data_start = cmp_data->used; \ | |
1098 | data[0] = -1; \ | |
1099 | data[1] = cmp_data->char_offset + start; \ | |
1100 | data[3] = (int) method; \ | |
1101 | cmp_data->used += 4; \ | |
1102 | } while (0) | |
1103 | ||
1104 | /* Record the ending position END of the current composition. */ | |
1105 | ||
1106 | #define CODING_ADD_COMPOSITION_END(coding, end) \ | |
1107 | do { \ | |
1108 | struct composition_data *cmp_data = coding->cmp_data; \ | |
1109 | int *data = cmp_data->data + coding->cmp_data_start; \ | |
1110 | data[0] = cmp_data->used - coding->cmp_data_start; \ | |
1111 | data[2] = cmp_data->char_offset + end; \ | |
1112 | } while (0) | |
1113 | ||
1114 | /* Record one COMPONENT (alternate character or composition rule). */ | |
1115 | ||
1116 | #define CODING_ADD_COMPOSITION_COMPONENT(coding, component) \ | |
1117 | (coding->cmp_data->data[coding->cmp_data->used++] = component) | |
1118 | ||
1119 | /* Handle compositoin start sequence ESC 0, ESC 2, ESC 3, or ESC 4. */ | |
1120 | ||
33fb63eb KH |
1121 | #define DECODE_COMPOSITION_START(c1) \ |
1122 | do { \ | |
1123 | if (coding->composing == COMPOSITION_DISABLED) \ | |
1124 | { \ | |
1125 | *dst++ = ISO_CODE_ESC; \ | |
1126 | *dst++ = c1 & 0x7f; \ | |
1127 | coding->produced_char += 2; \ | |
1128 | } \ | |
1129 | else if (!COMPOSING_P (coding)) \ | |
1130 | { \ | |
1131 | /* This is surely the start of a composition. We must be sure \ | |
1132 | that coding->cmp_data has enough space to store the \ | |
1133 | information about the composition. If not, terminate the \ | |
1134 | current decoding loop, allocate one more memory block for \ | |
1135 | coding->cmp_data in the calller, then start the decoding \ | |
1136 | loop again. We can't allocate memory here directly because \ | |
1137 | it may cause buffer/string relocation. */ \ | |
1138 | if (!coding->cmp_data \ | |
1139 | || (coding->cmp_data->used + COMPOSITION_DATA_MAX_BUNCH_LENGTH \ | |
1140 | >= COMPOSITION_DATA_SIZE)) \ | |
1141 | { \ | |
1142 | coding->result = CODING_FINISH_INSUFFICIENT_CMP; \ | |
1143 | goto label_end_of_loop; \ | |
1144 | } \ | |
1145 | coding->composing = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
1146 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
1147 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
1148 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
1149 | CODING_ADD_COMPOSITION_START (coding, coding->produced_char, \ | |
1150 | coding->composing); \ | |
1151 | coding->composition_rule_follows = 0; \ | |
1152 | } \ | |
1153 | else \ | |
1154 | { \ | |
1155 | /* We are already handling a composition. If the method is \ | |
1156 | the following two, the codes following the current escape \ | |
1157 | sequence are actual characters stored in a buffer. */ \ | |
1158 | if (coding->composing == COMPOSITION_WITH_ALTCHARS \ | |
1159 | || coding->composing == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
1160 | { \ | |
1161 | coding->composing = COMPOSITION_RELATIVE; \ | |
1162 | coding->composition_rule_follows = 0; \ | |
1163 | } \ | |
1164 | } \ | |
ec6d2bb8 KH |
1165 | } while (0) |
1166 | ||
1167 | /* Handle compositoin end sequence ESC 1. */ | |
1168 | ||
1169 | #define DECODE_COMPOSITION_END(c1) \ | |
1170 | do { \ | |
1171 | if (coding->composing == COMPOSITION_DISABLED) \ | |
1172 | { \ | |
1173 | *dst++ = ISO_CODE_ESC; \ | |
1174 | *dst++ = c1; \ | |
1175 | coding->produced_char += 2; \ | |
1176 | } \ | |
1177 | else \ | |
1178 | { \ | |
1179 | CODING_ADD_COMPOSITION_END (coding, coding->produced_char); \ | |
1180 | coding->composing = COMPOSITION_NO; \ | |
1181 | } \ | |
1182 | } while (0) | |
1183 | ||
1184 | /* Decode a composition rule from the byte C1 (and maybe one more byte | |
1185 | from SRC) and store one encoded composition rule in | |
1186 | coding->cmp_data. */ | |
1187 | ||
1188 | #define DECODE_COMPOSITION_RULE(c1) \ | |
1189 | do { \ | |
1190 | int rule = 0; \ | |
1191 | (c1) -= 32; \ | |
1192 | if (c1 < 81) /* old format (before ver.21) */ \ | |
1193 | { \ | |
1194 | int gref = (c1) / 9; \ | |
1195 | int nref = (c1) % 9; \ | |
1196 | if (gref == 4) gref = 10; \ | |
1197 | if (nref == 4) nref = 10; \ | |
1198 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1199 | } \ | |
b73bfc1c | 1200 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
1201 | { \ |
1202 | ONE_MORE_BYTE (c2); \ | |
1203 | rule = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ | |
1204 | } \ | |
1205 | CODING_ADD_COMPOSITION_COMPONENT (coding, rule); \ | |
1206 | coding->composition_rule_follows = 0; \ | |
1207 | } while (0) | |
88993dfd | 1208 | |
d46c5b12 | 1209 | |
4ed46869 KH |
1210 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1211 | ||
b73bfc1c | 1212 | static void |
d46c5b12 | 1213 | decode_coding_iso2022 (coding, source, destination, src_bytes, dst_bytes) |
4ed46869 KH |
1214 | struct coding_system *coding; |
1215 | unsigned char *source, *destination; | |
1216 | int src_bytes, dst_bytes; | |
4ed46869 KH |
1217 | { |
1218 | unsigned char *src = source; | |
1219 | unsigned char *src_end = source + src_bytes; | |
1220 | unsigned char *dst = destination; | |
1221 | unsigned char *dst_end = destination + dst_bytes; | |
4ed46869 KH |
1222 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
1223 | int charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); | |
1224 | int charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1); | |
b73bfc1c KH |
1225 | /* SRC_BASE remembers the start position in source in each loop. |
1226 | The loop will be exited when there's not enough source code | |
1227 | (within macro ONE_MORE_BYTE), or when there's not enough | |
1228 | destination area to produce a character (within macro | |
1229 | EMIT_CHAR). */ | |
1230 | unsigned char *src_base; | |
1231 | int c, charset; | |
1232 | Lisp_Object translation_table; | |
bdd9fb48 | 1233 | |
b73bfc1c KH |
1234 | if (NILP (Venable_character_translation)) |
1235 | translation_table = Qnil; | |
1236 | else | |
1237 | { | |
1238 | translation_table = coding->translation_table_for_decode; | |
1239 | if (NILP (translation_table)) | |
1240 | translation_table = Vstandard_translation_table_for_decode; | |
1241 | } | |
4ed46869 | 1242 | |
b73bfc1c KH |
1243 | coding->result = CODING_FINISH_NORMAL; |
1244 | ||
1245 | while (1) | |
4ed46869 | 1246 | { |
b73bfc1c KH |
1247 | int c1, c2; |
1248 | ||
1249 | src_base = src; | |
1250 | ONE_MORE_BYTE (c1); | |
4ed46869 | 1251 | |
ec6d2bb8 | 1252 | /* We produce no character or one character. */ |
4ed46869 KH |
1253 | switch (iso_code_class [c1]) |
1254 | { | |
1255 | case ISO_0x20_or_0x7F: | |
ec6d2bb8 KH |
1256 | if (COMPOSING_P (coding) && coding->composition_rule_follows) |
1257 | { | |
1258 | DECODE_COMPOSITION_RULE (c1); | |
b73bfc1c | 1259 | continue; |
ec6d2bb8 KH |
1260 | } |
1261 | if (charset0 < 0 || CHARSET_CHARS (charset0) == 94) | |
4ed46869 KH |
1262 | { |
1263 | /* This is SPACE or DEL. */ | |
b73bfc1c | 1264 | charset = CHARSET_ASCII; |
4ed46869 KH |
1265 | break; |
1266 | } | |
1267 | /* This is a graphic character, we fall down ... */ | |
1268 | ||
1269 | case ISO_graphic_plane_0: | |
ec6d2bb8 | 1270 | if (COMPOSING_P (coding) && coding->composition_rule_follows) |
b73bfc1c KH |
1271 | { |
1272 | DECODE_COMPOSITION_RULE (c1); | |
1273 | continue; | |
1274 | } | |
1275 | charset = charset0; | |
4ed46869 KH |
1276 | break; |
1277 | ||
1278 | case ISO_0xA0_or_0xFF: | |
d46c5b12 KH |
1279 | if (charset1 < 0 || CHARSET_CHARS (charset1) == 94 |
1280 | || coding->flags & CODING_FLAG_ISO_SEVEN_BITS) | |
fb88bf2d | 1281 | goto label_invalid_code; |
4ed46869 KH |
1282 | /* This is a graphic character, we fall down ... */ |
1283 | ||
1284 | case ISO_graphic_plane_1: | |
b73bfc1c | 1285 | if (charset1 < 0) |
fb88bf2d | 1286 | goto label_invalid_code; |
b73bfc1c | 1287 | charset = charset1; |
4ed46869 KH |
1288 | break; |
1289 | ||
b73bfc1c | 1290 | case ISO_control_0: |
ec6d2bb8 KH |
1291 | if (COMPOSING_P (coding)) |
1292 | DECODE_COMPOSITION_END ('1'); | |
1293 | ||
4ed46869 KH |
1294 | /* All ISO2022 control characters in this class have the |
1295 | same representation in Emacs internal format. */ | |
d46c5b12 KH |
1296 | if (c1 == '\n' |
1297 | && (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) | |
1298 | && (coding->eol_type == CODING_EOL_CR | |
1299 | || coding->eol_type == CODING_EOL_CRLF)) | |
1300 | { | |
b73bfc1c KH |
1301 | coding->result = CODING_FINISH_INCONSISTENT_EOL; |
1302 | goto label_end_of_loop; | |
d46c5b12 | 1303 | } |
b73bfc1c | 1304 | charset = CHARSET_ASCII; |
4ed46869 KH |
1305 | break; |
1306 | ||
b73bfc1c KH |
1307 | case ISO_control_1: |
1308 | if (COMPOSING_P (coding)) | |
1309 | DECODE_COMPOSITION_END ('1'); | |
1310 | goto label_invalid_code; | |
1311 | ||
4ed46869 | 1312 | case ISO_carriage_return: |
ec6d2bb8 KH |
1313 | if (COMPOSING_P (coding)) |
1314 | DECODE_COMPOSITION_END ('1'); | |
1315 | ||
4ed46869 | 1316 | if (coding->eol_type == CODING_EOL_CR) |
b73bfc1c | 1317 | c1 = '\n'; |
4ed46869 KH |
1318 | else if (coding->eol_type == CODING_EOL_CRLF) |
1319 | { | |
1320 | ONE_MORE_BYTE (c1); | |
b73bfc1c | 1321 | if (c1 != ISO_CODE_LF) |
4ed46869 | 1322 | { |
d46c5b12 KH |
1323 | if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) |
1324 | { | |
b73bfc1c KH |
1325 | coding->result = CODING_FINISH_INCONSISTENT_EOL; |
1326 | goto label_end_of_loop; | |
d46c5b12 | 1327 | } |
4ed46869 | 1328 | src--; |
b73bfc1c | 1329 | c1 = '\r'; |
4ed46869 KH |
1330 | } |
1331 | } | |
b73bfc1c | 1332 | charset = CHARSET_ASCII; |
4ed46869 KH |
1333 | break; |
1334 | ||
1335 | case ISO_shift_out: | |
d46c5b12 KH |
1336 | if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT) |
1337 | || CODING_SPEC_ISO_DESIGNATION (coding, 1) < 0) | |
1338 | goto label_invalid_code; | |
4ed46869 KH |
1339 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 1; |
1340 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); | |
b73bfc1c | 1341 | continue; |
4ed46869 KH |
1342 | |
1343 | case ISO_shift_in: | |
d46c5b12 KH |
1344 | if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT)) |
1345 | goto label_invalid_code; | |
4ed46869 KH |
1346 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; |
1347 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); | |
b73bfc1c | 1348 | continue; |
4ed46869 KH |
1349 | |
1350 | case ISO_single_shift_2_7: | |
1351 | case ISO_single_shift_2: | |
d46c5b12 KH |
1352 | if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)) |
1353 | goto label_invalid_code; | |
4ed46869 KH |
1354 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
1355 | c1 = 'N'; | |
1356 | goto label_escape_sequence; | |
1357 | ||
1358 | case ISO_single_shift_3: | |
d46c5b12 KH |
1359 | if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)) |
1360 | goto label_invalid_code; | |
4ed46869 KH |
1361 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
1362 | c1 = 'O'; | |
1363 | goto label_escape_sequence; | |
1364 | ||
1365 | case ISO_control_sequence_introducer: | |
1366 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
1367 | c1 = '['; | |
1368 | goto label_escape_sequence; | |
1369 | ||
1370 | case ISO_escape: | |
1371 | ONE_MORE_BYTE (c1); | |
1372 | label_escape_sequence: | |
1373 | /* Escape sequences handled by Emacs are invocation, | |
1374 | designation, direction specification, and character | |
1375 | composition specification. */ | |
1376 | switch (c1) | |
1377 | { | |
1378 | case '&': /* revision of following character set */ | |
1379 | ONE_MORE_BYTE (c1); | |
1380 | if (!(c1 >= '@' && c1 <= '~')) | |
d46c5b12 | 1381 | goto label_invalid_code; |
4ed46869 KH |
1382 | ONE_MORE_BYTE (c1); |
1383 | if (c1 != ISO_CODE_ESC) | |
d46c5b12 | 1384 | goto label_invalid_code; |
4ed46869 KH |
1385 | ONE_MORE_BYTE (c1); |
1386 | goto label_escape_sequence; | |
1387 | ||
1388 | case '$': /* designation of 2-byte character set */ | |
d46c5b12 KH |
1389 | if (! (coding->flags & CODING_FLAG_ISO_DESIGNATION)) |
1390 | goto label_invalid_code; | |
4ed46869 KH |
1391 | ONE_MORE_BYTE (c1); |
1392 | if (c1 >= '@' && c1 <= 'B') | |
1393 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 1394 | or JISX0208.1980 */ |
4ed46869 KH |
1395 | DECODE_DESIGNATION (0, 2, 94, c1); |
1396 | } | |
1397 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
1398 | { /* designation of DIMENSION2_CHARS94 character set */ | |
1399 | ONE_MORE_BYTE (c2); | |
1400 | DECODE_DESIGNATION (c1 - 0x28, 2, 94, c2); | |
1401 | } | |
1402 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
1403 | { /* designation of DIMENSION2_CHARS96 character set */ | |
1404 | ONE_MORE_BYTE (c2); | |
1405 | DECODE_DESIGNATION (c1 - 0x2C, 2, 96, c2); | |
1406 | } | |
1407 | else | |
d46c5b12 | 1408 | goto label_invalid_code; |
b73bfc1c KH |
1409 | /* We must update these variables now. */ |
1410 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); | |
1411 | charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1); | |
1412 | continue; | |
4ed46869 KH |
1413 | |
1414 | case 'n': /* invocation of locking-shift-2 */ | |
d46c5b12 KH |
1415 | if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT) |
1416 | || CODING_SPEC_ISO_DESIGNATION (coding, 2) < 0) | |
1417 | goto label_invalid_code; | |
4ed46869 | 1418 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 2; |
e0e989f6 | 1419 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
b73bfc1c | 1420 | continue; |
4ed46869 KH |
1421 | |
1422 | case 'o': /* invocation of locking-shift-3 */ | |
d46c5b12 KH |
1423 | if (! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT) |
1424 | || CODING_SPEC_ISO_DESIGNATION (coding, 3) < 0) | |
1425 | goto label_invalid_code; | |
4ed46869 | 1426 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 3; |
e0e989f6 | 1427 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); |
b73bfc1c | 1428 | continue; |
4ed46869 KH |
1429 | |
1430 | case 'N': /* invocation of single-shift-2 */ | |
d46c5b12 KH |
1431 | if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
1432 | || CODING_SPEC_ISO_DESIGNATION (coding, 2) < 0) | |
1433 | goto label_invalid_code; | |
4ed46869 | 1434 | charset = CODING_SPEC_ISO_DESIGNATION (coding, 2); |
b73bfc1c | 1435 | ONE_MORE_BYTE (c1); |
4ed46869 KH |
1436 | break; |
1437 | ||
1438 | case 'O': /* invocation of single-shift-3 */ | |
d46c5b12 KH |
1439 | if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) |
1440 | || CODING_SPEC_ISO_DESIGNATION (coding, 3) < 0) | |
1441 | goto label_invalid_code; | |
4ed46869 | 1442 | charset = CODING_SPEC_ISO_DESIGNATION (coding, 3); |
b73bfc1c | 1443 | ONE_MORE_BYTE (c1); |
4ed46869 KH |
1444 | break; |
1445 | ||
ec6d2bb8 KH |
1446 | case '0': case '2': case '3': case '4': /* start composition */ |
1447 | DECODE_COMPOSITION_START (c1); | |
b73bfc1c | 1448 | continue; |
4ed46869 | 1449 | |
ec6d2bb8 KH |
1450 | case '1': /* end composition */ |
1451 | DECODE_COMPOSITION_END (c1); | |
b73bfc1c | 1452 | continue; |
4ed46869 KH |
1453 | |
1454 | case '[': /* specification of direction */ | |
d46c5b12 KH |
1455 | if (coding->flags & CODING_FLAG_ISO_NO_DIRECTION) |
1456 | goto label_invalid_code; | |
4ed46869 | 1457 | /* For the moment, nested direction is not supported. |
d46c5b12 KH |
1458 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
1459 | left-to-right, and nozero means right-to-left. */ | |
4ed46869 KH |
1460 | ONE_MORE_BYTE (c1); |
1461 | switch (c1) | |
1462 | { | |
1463 | case ']': /* end of the current direction */ | |
d46c5b12 | 1464 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
1465 | |
1466 | case '0': /* end of the current direction */ | |
1467 | case '1': /* start of left-to-right direction */ | |
1468 | ONE_MORE_BYTE (c1); | |
1469 | if (c1 == ']') | |
d46c5b12 | 1470 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 1471 | else |
d46c5b12 | 1472 | goto label_invalid_code; |
4ed46869 KH |
1473 | break; |
1474 | ||
1475 | case '2': /* start of right-to-left direction */ | |
1476 | ONE_MORE_BYTE (c1); | |
1477 | if (c1 == ']') | |
d46c5b12 | 1478 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 1479 | else |
d46c5b12 | 1480 | goto label_invalid_code; |
4ed46869 KH |
1481 | break; |
1482 | ||
1483 | default: | |
d46c5b12 | 1484 | goto label_invalid_code; |
4ed46869 | 1485 | } |
b73bfc1c | 1486 | continue; |
4ed46869 KH |
1487 | |
1488 | default: | |
d46c5b12 KH |
1489 | if (! (coding->flags & CODING_FLAG_ISO_DESIGNATION)) |
1490 | goto label_invalid_code; | |
4ed46869 KH |
1491 | if (c1 >= 0x28 && c1 <= 0x2B) |
1492 | { /* designation of DIMENSION1_CHARS94 character set */ | |
1493 | ONE_MORE_BYTE (c2); | |
1494 | DECODE_DESIGNATION (c1 - 0x28, 1, 94, c2); | |
1495 | } | |
1496 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
1497 | { /* designation of DIMENSION1_CHARS96 character set */ | |
1498 | ONE_MORE_BYTE (c2); | |
1499 | DECODE_DESIGNATION (c1 - 0x2C, 1, 96, c2); | |
1500 | } | |
1501 | else | |
b73bfc1c KH |
1502 | goto label_invalid_code; |
1503 | /* We must update these variables now. */ | |
1504 | charset0 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 0); | |
1505 | charset1 = CODING_SPEC_ISO_PLANE_CHARSET (coding, 1); | |
1506 | continue; | |
4ed46869 | 1507 | } |
b73bfc1c | 1508 | } |
4ed46869 | 1509 | |
b73bfc1c KH |
1510 | /* Now we know CHARSET and 1st position code C1 of a character. |
1511 | Produce a multibyte sequence for that character while getting | |
1512 | 2nd position code C2 if necessary. */ | |
1513 | if (CHARSET_DIMENSION (charset) == 2) | |
1514 | { | |
1515 | ONE_MORE_BYTE (c2); | |
1516 | if (c1 < 0x80 ? c2 < 0x20 || c2 >= 0x80 : c2 < 0xA0) | |
1517 | /* C2 is not in a valid range. */ | |
1518 | goto label_invalid_code; | |
4ed46869 | 1519 | } |
b73bfc1c KH |
1520 | c = DECODE_ISO_CHARACTER (charset, c1, c2); |
1521 | EMIT_CHAR (c); | |
4ed46869 KH |
1522 | continue; |
1523 | ||
b73bfc1c KH |
1524 | label_invalid_code: |
1525 | coding->errors++; | |
1526 | if (COMPOSING_P (coding)) | |
1527 | DECODE_COMPOSITION_END ('1'); | |
4ed46869 | 1528 | src = src_base; |
b73bfc1c KH |
1529 | c = *src++; |
1530 | EMIT_CHAR (c); | |
4ed46869 | 1531 | } |
fb88bf2d | 1532 | |
b73bfc1c KH |
1533 | label_end_of_loop: |
1534 | coding->consumed = coding->consumed_char = src_base - source; | |
d46c5b12 | 1535 | coding->produced = dst - destination; |
b73bfc1c | 1536 | return; |
4ed46869 KH |
1537 | } |
1538 | ||
b73bfc1c | 1539 | |
f4dee582 | 1540 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
1541 | |
1542 | /* | |
f4dee582 | 1543 | It is not enough to say just "ISO2022" on encoding, we have to |
d46c5b12 | 1544 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 KH |
1545 | variant has the following specifications: |
1546 | 1. Initial designation to G0 thru G3. | |
1547 | 2. Allows short-form designation? | |
1548 | 3. ASCII should be designated to G0 before control characters? | |
1549 | 4. ASCII should be designated to G0 at end of line? | |
1550 | 5. 7-bit environment or 8-bit environment? | |
1551 | 6. Use locking-shift? | |
1552 | 7. Use Single-shift? | |
1553 | And the following two are only for Japanese: | |
1554 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
1555 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
1556 | These specifications are encoded in `coding->flags' as flag bits | |
1557 | defined by macros CODING_FLAG_ISO_XXX. See `coding.h' for more | |
f4dee582 | 1558 | details. |
4ed46869 KH |
1559 | */ |
1560 | ||
1561 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
1562 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
1563 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
1564 | designation sequence of short-form. */ | |
4ed46869 KH |
1565 | |
1566 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
1567 | do { \ | |
1568 | unsigned char final_char = CHARSET_ISO_FINAL_CHAR (charset); \ | |
1569 | char *intermediate_char_94 = "()*+"; \ | |
1570 | char *intermediate_char_96 = ",-./"; \ | |
70c22245 | 1571 | int revision = CODING_SPEC_ISO_REVISION_NUMBER(coding, charset); \ |
b73bfc1c | 1572 | \ |
70c22245 KH |
1573 | if (revision < 255) \ |
1574 | { \ | |
4ed46869 KH |
1575 | *dst++ = ISO_CODE_ESC; \ |
1576 | *dst++ = '&'; \ | |
70c22245 | 1577 | *dst++ = '@' + revision; \ |
4ed46869 | 1578 | } \ |
b73bfc1c | 1579 | *dst++ = ISO_CODE_ESC; \ |
4ed46869 KH |
1580 | if (CHARSET_DIMENSION (charset) == 1) \ |
1581 | { \ | |
1582 | if (CHARSET_CHARS (charset) == 94) \ | |
1583 | *dst++ = (unsigned char) (intermediate_char_94[reg]); \ | |
1584 | else \ | |
1585 | *dst++ = (unsigned char) (intermediate_char_96[reg]); \ | |
1586 | } \ | |
1587 | else \ | |
1588 | { \ | |
1589 | *dst++ = '$'; \ | |
1590 | if (CHARSET_CHARS (charset) == 94) \ | |
1591 | { \ | |
b73bfc1c KH |
1592 | if (! (coding->flags & CODING_FLAG_ISO_SHORT_FORM) \ |
1593 | || reg != 0 \ | |
1594 | || final_char < '@' || final_char > 'B') \ | |
4ed46869 KH |
1595 | *dst++ = (unsigned char) (intermediate_char_94[reg]); \ |
1596 | } \ | |
1597 | else \ | |
b73bfc1c | 1598 | *dst++ = (unsigned char) (intermediate_char_96[reg]); \ |
4ed46869 | 1599 | } \ |
b73bfc1c | 1600 | *dst++ = final_char; \ |
4ed46869 KH |
1601 | CODING_SPEC_ISO_DESIGNATION (coding, reg) = charset; \ |
1602 | } while (0) | |
1603 | ||
1604 | /* The following two macros produce codes (control character or escape | |
1605 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
1606 | single-shift-3). */ | |
1607 | ||
1608 | #define ENCODE_SINGLE_SHIFT_2 \ | |
1609 | do { \ | |
1610 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ | |
1611 | *dst++ = ISO_CODE_ESC, *dst++ = 'N'; \ | |
1612 | else \ | |
b73bfc1c | 1613 | *dst++ = ISO_CODE_SS2; \ |
4ed46869 KH |
1614 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \ |
1615 | } while (0) | |
1616 | ||
fb88bf2d KH |
1617 | #define ENCODE_SINGLE_SHIFT_3 \ |
1618 | do { \ | |
4ed46869 | 1619 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ |
fb88bf2d KH |
1620 | *dst++ = ISO_CODE_ESC, *dst++ = 'O'; \ |
1621 | else \ | |
b73bfc1c | 1622 | *dst++ = ISO_CODE_SS3; \ |
4ed46869 KH |
1623 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 1; \ |
1624 | } while (0) | |
1625 | ||
1626 | /* The following four macros produce codes (control character or | |
1627 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
1628 | shift-out, locking-shift-2, and locking-shift-3). */ | |
1629 | ||
b73bfc1c KH |
1630 | #define ENCODE_SHIFT_IN \ |
1631 | do { \ | |
1632 | *dst++ = ISO_CODE_SI; \ | |
4ed46869 KH |
1633 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; \ |
1634 | } while (0) | |
1635 | ||
b73bfc1c KH |
1636 | #define ENCODE_SHIFT_OUT \ |
1637 | do { \ | |
1638 | *dst++ = ISO_CODE_SO; \ | |
4ed46869 KH |
1639 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 1; \ |
1640 | } while (0) | |
1641 | ||
1642 | #define ENCODE_LOCKING_SHIFT_2 \ | |
1643 | do { \ | |
1644 | *dst++ = ISO_CODE_ESC, *dst++ = 'n'; \ | |
1645 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 2; \ | |
1646 | } while (0) | |
1647 | ||
b73bfc1c KH |
1648 | #define ENCODE_LOCKING_SHIFT_3 \ |
1649 | do { \ | |
1650 | *dst++ = ISO_CODE_ESC, *dst++ = 'o'; \ | |
4ed46869 KH |
1651 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 3; \ |
1652 | } while (0) | |
1653 | ||
f4dee582 RS |
1654 | /* Produce codes for a DIMENSION1 character whose character set is |
1655 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
1656 | sequences are also produced in advance if necessary. */ |
1657 | ||
6e85d753 KH |
1658 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
1659 | do { \ | |
1660 | if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \ | |
1661 | { \ | |
1662 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ | |
1663 | *dst++ = c1 & 0x7F; \ | |
1664 | else \ | |
1665 | *dst++ = c1 | 0x80; \ | |
1666 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
1667 | break; \ | |
1668 | } \ | |
1669 | else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \ | |
1670 | { \ | |
1671 | *dst++ = c1 & 0x7F; \ | |
1672 | break; \ | |
1673 | } \ | |
1674 | else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \ | |
1675 | { \ | |
1676 | *dst++ = c1 | 0x80; \ | |
1677 | break; \ | |
1678 | } \ | |
1679 | else if (coding->flags & CODING_FLAG_ISO_SAFE \ | |
70c22245 | 1680 | && !coding->safe_charsets[charset]) \ |
6e85d753 KH |
1681 | { \ |
1682 | /* We should not encode this character, instead produce one or \ | |
1683 | two `?'s. */ \ | |
1684 | *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \ | |
1685 | if (CHARSET_WIDTH (charset) == 2) \ | |
1686 | *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \ | |
1687 | break; \ | |
1688 | } \ | |
1689 | else \ | |
1690 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
1691 | must invoke it, or, at first, designate it to some graphic \ | |
1692 | register. Then repeat the loop to actually produce the \ | |
1693 | character. */ \ | |
1694 | dst = encode_invocation_designation (charset, coding, dst); \ | |
4ed46869 KH |
1695 | } while (1) |
1696 | ||
f4dee582 RS |
1697 | /* Produce codes for a DIMENSION2 character whose character set is |
1698 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
1699 | invocation codes are also produced in advance if necessary. */ |
1700 | ||
6e85d753 KH |
1701 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
1702 | do { \ | |
1703 | if (CODING_SPEC_ISO_SINGLE_SHIFTING (coding)) \ | |
1704 | { \ | |
1705 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) \ | |
1706 | *dst++ = c1 & 0x7F, *dst++ = c2 & 0x7F; \ | |
1707 | else \ | |
1708 | *dst++ = c1 | 0x80, *dst++ = c2 | 0x80; \ | |
1709 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
1710 | break; \ | |
1711 | } \ | |
1712 | else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 0)) \ | |
1713 | { \ | |
1714 | *dst++ = c1 & 0x7F, *dst++= c2 & 0x7F; \ | |
1715 | break; \ | |
1716 | } \ | |
1717 | else if (charset == CODING_SPEC_ISO_PLANE_CHARSET (coding, 1)) \ | |
1718 | { \ | |
1719 | *dst++ = c1 | 0x80, *dst++= c2 | 0x80; \ | |
1720 | break; \ | |
1721 | } \ | |
1722 | else if (coding->flags & CODING_FLAG_ISO_SAFE \ | |
70c22245 | 1723 | && !coding->safe_charsets[charset]) \ |
6e85d753 KH |
1724 | { \ |
1725 | /* We should not encode this character, instead produce one or \ | |
1726 | two `?'s. */ \ | |
1727 | *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \ | |
1728 | if (CHARSET_WIDTH (charset) == 2) \ | |
1729 | *dst++ = CODING_INHIBIT_CHARACTER_SUBSTITUTION; \ | |
1730 | break; \ | |
1731 | } \ | |
1732 | else \ | |
1733 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
1734 | must invoke it, or, at first, designate it to some graphic \ | |
1735 | register. Then repeat the loop to actually produce the \ | |
1736 | character. */ \ | |
1737 | dst = encode_invocation_designation (charset, coding, dst); \ | |
4ed46869 KH |
1738 | } while (1) |
1739 | ||
6f551029 KH |
1740 | #define ENCODE_ISO_CHARACTER(charset, c1, c2) \ |
1741 | do { \ | |
b73bfc1c | 1742 | int alt_charset = charset; \ |
ec6d2bb8 | 1743 | \ |
b73bfc1c | 1744 | if (CHARSET_DEFINED_P (charset)) \ |
6f551029 | 1745 | { \ |
b73bfc1c | 1746 | if (CHARSET_DIMENSION (charset) == 1) \ |
6f551029 KH |
1747 | { \ |
1748 | if (charset == CHARSET_ASCII \ | |
1749 | && coding->flags & CODING_FLAG_ISO_USE_ROMAN) \ | |
b73bfc1c KH |
1750 | alt_charset = charset_latin_jisx0201; \ |
1751 | ENCODE_ISO_CHARACTER_DIMENSION1 (alt_charset, c1); \ | |
6f551029 KH |
1752 | } \ |
1753 | else \ | |
1754 | { \ | |
1755 | if (charset == charset_jisx0208 \ | |
1756 | && coding->flags & CODING_FLAG_ISO_USE_OLDJIS) \ | |
b73bfc1c KH |
1757 | alt_charset = charset_jisx0208_1978; \ |
1758 | ENCODE_ISO_CHARACTER_DIMENSION2 (alt_charset, c1, c2); \ | |
6f551029 KH |
1759 | } \ |
1760 | } \ | |
1761 | else \ | |
1762 | { \ | |
b73bfc1c KH |
1763 | *dst++ = c1; \ |
1764 | if (c2 >= 0) \ | |
1765 | *dst++ = c2; \ | |
6f551029 | 1766 | } \ |
84fbb8a0 | 1767 | } while (0) |
bdd9fb48 | 1768 | |
4ed46869 KH |
1769 | /* Produce designation and invocation codes at a place pointed by DST |
1770 | to use CHARSET. The element `spec.iso2022' of *CODING is updated. | |
1771 | Return new DST. */ | |
1772 | ||
1773 | unsigned char * | |
1774 | encode_invocation_designation (charset, coding, dst) | |
1775 | int charset; | |
1776 | struct coding_system *coding; | |
1777 | unsigned char *dst; | |
1778 | { | |
1779 | int reg; /* graphic register number */ | |
1780 | ||
1781 | /* At first, check designations. */ | |
1782 | for (reg = 0; reg < 4; reg++) | |
1783 | if (charset == CODING_SPEC_ISO_DESIGNATION (coding, reg)) | |
1784 | break; | |
1785 | ||
1786 | if (reg >= 4) | |
1787 | { | |
1788 | /* CHARSET is not yet designated to any graphic registers. */ | |
1789 | /* At first check the requested designation. */ | |
1790 | reg = CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset); | |
1ba9e4ab KH |
1791 | if (reg == CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION) |
1792 | /* Since CHARSET requests no special designation, designate it | |
1793 | to graphic register 0. */ | |
4ed46869 KH |
1794 | reg = 0; |
1795 | ||
1796 | ENCODE_DESIGNATION (charset, reg, coding); | |
1797 | } | |
1798 | ||
1799 | if (CODING_SPEC_ISO_INVOCATION (coding, 0) != reg | |
1800 | && CODING_SPEC_ISO_INVOCATION (coding, 1) != reg) | |
1801 | { | |
1802 | /* Since the graphic register REG is not invoked to any graphic | |
1803 | planes, invoke it to graphic plane 0. */ | |
1804 | switch (reg) | |
1805 | { | |
1806 | case 0: /* graphic register 0 */ | |
1807 | ENCODE_SHIFT_IN; | |
1808 | break; | |
1809 | ||
1810 | case 1: /* graphic register 1 */ | |
1811 | ENCODE_SHIFT_OUT; | |
1812 | break; | |
1813 | ||
1814 | case 2: /* graphic register 2 */ | |
1815 | if (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) | |
1816 | ENCODE_SINGLE_SHIFT_2; | |
1817 | else | |
1818 | ENCODE_LOCKING_SHIFT_2; | |
1819 | break; | |
1820 | ||
1821 | case 3: /* graphic register 3 */ | |
1822 | if (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT) | |
1823 | ENCODE_SINGLE_SHIFT_3; | |
1824 | else | |
1825 | ENCODE_LOCKING_SHIFT_3; | |
1826 | break; | |
1827 | } | |
1828 | } | |
b73bfc1c | 1829 | |
4ed46869 KH |
1830 | return dst; |
1831 | } | |
1832 | ||
ec6d2bb8 KH |
1833 | /* Produce 2-byte codes for encoded composition rule RULE. */ |
1834 | ||
1835 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
1836 | do { \ | |
1837 | int gref, nref; \ | |
1838 | COMPOSITION_DECODE_RULE (rule, gref, nref); \ | |
1839 | *dst++ = 32 + 81 + gref; \ | |
1840 | *dst++ = 32 + nref; \ | |
1841 | } while (0) | |
1842 | ||
1843 | /* Produce codes for indicating the start of a composition sequence | |
1844 | (ESC 0, ESC 3, or ESC 4). DATA points to an array of integers | |
1845 | which specify information about the composition. See the comment | |
1846 | in coding.h for the format of DATA. */ | |
1847 | ||
1848 | #define ENCODE_COMPOSITION_START(coding, data) \ | |
1849 | do { \ | |
1850 | coding->composing = data[3]; \ | |
1851 | *dst++ = ISO_CODE_ESC; \ | |
1852 | if (coding->composing == COMPOSITION_RELATIVE) \ | |
1853 | *dst++ = '0'; \ | |
1854 | else \ | |
1855 | { \ | |
1856 | *dst++ = (coding->composing == COMPOSITION_WITH_ALTCHARS \ | |
1857 | ? '3' : '4'); \ | |
1858 | coding->cmp_data_index = coding->cmp_data_start + 4; \ | |
1859 | coding->composition_rule_follows = 0; \ | |
1860 | } \ | |
1861 | } while (0) | |
1862 | ||
1863 | /* Produce codes for indicating the end of the current composition. */ | |
1864 | ||
1865 | #define ENCODE_COMPOSITION_END(coding, data) \ | |
1866 | do { \ | |
1867 | *dst++ = ISO_CODE_ESC; \ | |
1868 | *dst++ = '1'; \ | |
1869 | coding->cmp_data_start += data[0]; \ | |
1870 | coding->composing = COMPOSITION_NO; \ | |
1871 | if (coding->cmp_data_start == coding->cmp_data->used \ | |
1872 | && coding->cmp_data->next) \ | |
1873 | { \ | |
1874 | coding->cmp_data = coding->cmp_data->next; \ | |
1875 | coding->cmp_data_start = 0; \ | |
1876 | } \ | |
1877 | } while (0) | |
1878 | ||
1879 | /* Produce composition start sequence ESC 0. Here, this sequence | |
1880 | doesn't mean the start of a new composition but means that we have | |
1881 | just produced components (alternate chars and composition rules) of | |
1882 | the composition and the actual text follows in SRC. */ | |
1883 | ||
1884 | #define ENCODE_COMPOSITION_FAKE_START(coding) \ | |
1885 | do { \ | |
1886 | *dst++ = ISO_CODE_ESC; \ | |
1887 | *dst++ = '0'; \ | |
1888 | coding->composing = COMPOSITION_RELATIVE; \ | |
1889 | } while (0) | |
4ed46869 KH |
1890 | |
1891 | /* The following three macros produce codes for indicating direction | |
1892 | of text. */ | |
b73bfc1c KH |
1893 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ |
1894 | do { \ | |
4ed46869 | 1895 | if (coding->flags == CODING_FLAG_ISO_SEVEN_BITS) \ |
b73bfc1c KH |
1896 | *dst++ = ISO_CODE_ESC, *dst++ = '['; \ |
1897 | else \ | |
1898 | *dst++ = ISO_CODE_CSI; \ | |
4ed46869 KH |
1899 | } while (0) |
1900 | ||
1901 | #define ENCODE_DIRECTION_R2L \ | |
b73bfc1c | 1902 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst), *dst++ = '2', *dst++ = ']' |
4ed46869 KH |
1903 | |
1904 | #define ENCODE_DIRECTION_L2R \ | |
b73bfc1c | 1905 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst), *dst++ = '0', *dst++ = ']' |
4ed46869 KH |
1906 | |
1907 | /* Produce codes for designation and invocation to reset the graphic | |
1908 | planes and registers to initial state. */ | |
e0e989f6 KH |
1909 | #define ENCODE_RESET_PLANE_AND_REGISTER \ |
1910 | do { \ | |
1911 | int reg; \ | |
1912 | if (CODING_SPEC_ISO_INVOCATION (coding, 0) != 0) \ | |
1913 | ENCODE_SHIFT_IN; \ | |
1914 | for (reg = 0; reg < 4; reg++) \ | |
1915 | if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg) >= 0 \ | |
1916 | && (CODING_SPEC_ISO_DESIGNATION (coding, reg) \ | |
1917 | != CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg))) \ | |
1918 | ENCODE_DESIGNATION \ | |
1919 | (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, reg), reg, coding); \ | |
4ed46869 KH |
1920 | } while (0) |
1921 | ||
bdd9fb48 | 1922 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 1923 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
1924 | |
1925 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
1926 | find all the necessary designations. */ |
1927 | ||
b73bfc1c KH |
1928 | static unsigned char * |
1929 | encode_designation_at_bol (coding, translation_table, src, src_end, dst) | |
e0e989f6 | 1930 | struct coding_system *coding; |
b73bfc1c KH |
1931 | Lisp_Object translation_table; |
1932 | unsigned char *src, *src_end, *dst; | |
e0e989f6 | 1933 | { |
bdd9fb48 KH |
1934 | int charset, c, found = 0, reg; |
1935 | /* Table of charsets to be designated to each graphic register. */ | |
1936 | int r[4]; | |
bdd9fb48 KH |
1937 | |
1938 | for (reg = 0; reg < 4; reg++) | |
1939 | r[reg] = -1; | |
1940 | ||
b73bfc1c | 1941 | while (found < 4) |
e0e989f6 | 1942 | { |
b73bfc1c KH |
1943 | ONE_MORE_CHAR (c); |
1944 | if (c == '\n') | |
1945 | break; | |
bdd9fb48 | 1946 | |
b73bfc1c | 1947 | charset = CHAR_CHARSET (c); |
e0e989f6 | 1948 | reg = CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset); |
d46c5b12 | 1949 | if (reg != CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION && r[reg] < 0) |
bdd9fb48 KH |
1950 | { |
1951 | found++; | |
1952 | r[reg] = charset; | |
1953 | } | |
bdd9fb48 KH |
1954 | } |
1955 | ||
b73bfc1c | 1956 | label_end_of_loop: |
bdd9fb48 KH |
1957 | if (found) |
1958 | { | |
1959 | for (reg = 0; reg < 4; reg++) | |
1960 | if (r[reg] >= 0 | |
1961 | && CODING_SPEC_ISO_DESIGNATION (coding, reg) != r[reg]) | |
1962 | ENCODE_DESIGNATION (r[reg], reg, coding); | |
e0e989f6 | 1963 | } |
b73bfc1c KH |
1964 | |
1965 | return dst; | |
e0e989f6 KH |
1966 | } |
1967 | ||
4ed46869 KH |
1968 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
1969 | ||
b73bfc1c | 1970 | static void |
d46c5b12 | 1971 | encode_coding_iso2022 (coding, source, destination, src_bytes, dst_bytes) |
4ed46869 KH |
1972 | struct coding_system *coding; |
1973 | unsigned char *source, *destination; | |
1974 | int src_bytes, dst_bytes; | |
4ed46869 KH |
1975 | { |
1976 | unsigned char *src = source; | |
1977 | unsigned char *src_end = source + src_bytes; | |
1978 | unsigned char *dst = destination; | |
1979 | unsigned char *dst_end = destination + dst_bytes; | |
b73bfc1c | 1980 | /* Since the maximum bytes produced by each loop is 20, we subtract 19 |
4ed46869 KH |
1981 | from DST_END to assure overflow checking is necessary only at the |
1982 | head of loop. */ | |
b73bfc1c KH |
1983 | unsigned char *adjusted_dst_end = dst_end - 19; |
1984 | /* SRC_BASE remembers the start position in source in each loop. | |
1985 | The loop will be exited when there's not enough source text to | |
1986 | analyze multi-byte codes (within macro ONE_MORE_CHAR), or when | |
1987 | there's not enough destination area to produce encoded codes | |
1988 | (within macro EMIT_BYTES). */ | |
1989 | unsigned char *src_base; | |
1990 | int c; | |
1991 | Lisp_Object translation_table; | |
bdd9fb48 | 1992 | |
b73bfc1c KH |
1993 | if (NILP (Venable_character_translation)) |
1994 | translation_table = Qnil; | |
1995 | else | |
1996 | { | |
1997 | translation_table = coding->translation_table_for_encode; | |
1998 | if (NILP (translation_table)) | |
1999 | translation_table = Vstandard_translation_table_for_encode; | |
2000 | } | |
4ed46869 | 2001 | |
d46c5b12 | 2002 | coding->consumed_char = 0; |
b73bfc1c KH |
2003 | coding->errors = 0; |
2004 | while (1) | |
4ed46869 | 2005 | { |
b73bfc1c KH |
2006 | int charset, c1, c2; |
2007 | ||
2008 | src_base = src; | |
2009 | ||
2010 | if (dst >= (dst_bytes ? adjusted_dst_end : (src - 19))) | |
2011 | { | |
2012 | coding->result = CODING_FINISH_INSUFFICIENT_DST; | |
2013 | break; | |
2014 | } | |
4ed46869 | 2015 | |
e0e989f6 KH |
2016 | if (coding->flags & CODING_FLAG_ISO_DESIGNATE_AT_BOL |
2017 | && CODING_SPEC_ISO_BOL (coding)) | |
2018 | { | |
bdd9fb48 | 2019 | /* We have to produce designation sequences if any now. */ |
b73bfc1c KH |
2020 | dst = encode_designation_at_bol (coding, translation_table, |
2021 | src, src_end, dst); | |
e0e989f6 KH |
2022 | CODING_SPEC_ISO_BOL (coding) = 0; |
2023 | } | |
2024 | ||
ec6d2bb8 KH |
2025 | /* Check composition start and end. */ |
2026 | if (coding->composing != COMPOSITION_DISABLED | |
2027 | && coding->cmp_data_start < coding->cmp_data->used) | |
4ed46869 | 2028 | { |
ec6d2bb8 KH |
2029 | struct composition_data *cmp_data = coding->cmp_data; |
2030 | int *data = cmp_data->data + coding->cmp_data_start; | |
2031 | int this_pos = cmp_data->char_offset + coding->consumed_char; | |
2032 | ||
2033 | if (coding->composing == COMPOSITION_RELATIVE) | |
4ed46869 | 2034 | { |
ec6d2bb8 KH |
2035 | if (this_pos == data[2]) |
2036 | { | |
2037 | ENCODE_COMPOSITION_END (coding, data); | |
2038 | cmp_data = coding->cmp_data; | |
2039 | data = cmp_data->data + coding->cmp_data_start; | |
2040 | } | |
4ed46869 | 2041 | } |
ec6d2bb8 | 2042 | else if (COMPOSING_P (coding)) |
4ed46869 | 2043 | { |
ec6d2bb8 KH |
2044 | /* COMPOSITION_WITH_ALTCHARS or COMPOSITION_WITH_RULE_ALTCHAR */ |
2045 | if (coding->cmp_data_index == coding->cmp_data_start + data[0]) | |
2046 | /* We have consumed components of the composition. | |
2047 | What follows in SRC is the compositions's base | |
2048 | text. */ | |
2049 | ENCODE_COMPOSITION_FAKE_START (coding); | |
2050 | else | |
4ed46869 | 2051 | { |
ec6d2bb8 KH |
2052 | int c = cmp_data->data[coding->cmp_data_index++]; |
2053 | if (coding->composition_rule_follows) | |
2054 | { | |
2055 | ENCODE_COMPOSITION_RULE (c); | |
2056 | coding->composition_rule_follows = 0; | |
2057 | } | |
2058 | else | |
2059 | { | |
2060 | SPLIT_CHAR (c, charset, c1, c2); | |
2061 | ENCODE_ISO_CHARACTER (charset, c1, c2); | |
ec6d2bb8 KH |
2062 | if (coding->composing == COMPOSITION_WITH_RULE_ALTCHARS) |
2063 | coding->composition_rule_follows = 1; | |
2064 | } | |
4ed46869 KH |
2065 | continue; |
2066 | } | |
ec6d2bb8 KH |
2067 | } |
2068 | if (!COMPOSING_P (coding)) | |
2069 | { | |
2070 | if (this_pos == data[1]) | |
4ed46869 | 2071 | { |
ec6d2bb8 KH |
2072 | ENCODE_COMPOSITION_START (coding, data); |
2073 | continue; | |
4ed46869 | 2074 | } |
4ed46869 KH |
2075 | } |
2076 | } | |
ec6d2bb8 | 2077 | |
b73bfc1c | 2078 | ONE_MORE_CHAR (c); |
4ed46869 | 2079 | |
b73bfc1c KH |
2080 | /* Now encode the character C. */ |
2081 | if (c < 0x20 || c == 0x7F) | |
2082 | { | |
2083 | if (c == '\r') | |
19a8d9e0 | 2084 | { |
b73bfc1c KH |
2085 | if (! (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
2086 | { | |
2087 | if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL) | |
2088 | ENCODE_RESET_PLANE_AND_REGISTER; | |
2089 | *dst++ = c; | |
2090 | continue; | |
2091 | } | |
2092 | /* fall down to treat '\r' as '\n' ... */ | |
2093 | c = '\n'; | |
19a8d9e0 | 2094 | } |
b73bfc1c | 2095 | if (c == '\n') |
19a8d9e0 | 2096 | { |
b73bfc1c KH |
2097 | if (coding->flags & CODING_FLAG_ISO_RESET_AT_EOL) |
2098 | ENCODE_RESET_PLANE_AND_REGISTER; | |
2099 | if (coding->flags & CODING_FLAG_ISO_INIT_AT_BOL) | |
2100 | bcopy (coding->spec.iso2022.initial_designation, | |
2101 | coding->spec.iso2022.current_designation, | |
2102 | sizeof coding->spec.iso2022.initial_designation); | |
2103 | if (coding->eol_type == CODING_EOL_LF | |
2104 | || coding->eol_type == CODING_EOL_UNDECIDED) | |
2105 | *dst++ = ISO_CODE_LF; | |
2106 | else if (coding->eol_type == CODING_EOL_CRLF) | |
2107 | *dst++ = ISO_CODE_CR, *dst++ = ISO_CODE_LF; | |
2108 | else | |
2109 | *dst++ = ISO_CODE_CR; | |
2110 | CODING_SPEC_ISO_BOL (coding) = 1; | |
19a8d9e0 | 2111 | } |
b73bfc1c | 2112 | else |
19a8d9e0 | 2113 | { |
b73bfc1c KH |
2114 | if (coding->flags & CODING_FLAG_ISO_RESET_AT_CNTL) |
2115 | ENCODE_RESET_PLANE_AND_REGISTER; | |
2116 | *dst++ = c; | |
19a8d9e0 | 2117 | } |
4ed46869 | 2118 | } |
b73bfc1c KH |
2119 | else if (ASCII_BYTE_P (c)) |
2120 | ENCODE_ISO_CHARACTER (CHARSET_ASCII, c, /* dummy */ c1); | |
2121 | else if (SINGLE_BYTE_CHAR_P (c)) | |
88993dfd | 2122 | { |
b73bfc1c KH |
2123 | *dst++ = c; |
2124 | coding->errors++; | |
88993dfd | 2125 | } |
b73bfc1c KH |
2126 | else |
2127 | { | |
2128 | SPLIT_CHAR (c, charset, c1, c2); | |
2129 | ENCODE_ISO_CHARACTER (charset, c1, c2); | |
2130 | } | |
2131 | ||
2132 | coding->consumed_char++; | |
84fbb8a0 | 2133 | } |
b73bfc1c KH |
2134 | |
2135 | label_end_of_loop: | |
2136 | coding->consumed = src_base - source; | |
d46c5b12 | 2137 | coding->produced = coding->produced_char = dst - destination; |
4ed46869 KH |
2138 | } |
2139 | ||
2140 | \f | |
2141 | /*** 4. SJIS and BIG5 handlers ***/ | |
2142 | ||
f4dee582 | 2143 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
2144 | quite widely. So, for the moment, Emacs supports them in the bare |
2145 | C code. But, in the future, they may be supported only by CCL. */ | |
2146 | ||
2147 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
2148 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
2149 | as is. A character of charset katakana-jisx0201 is encoded by | |
2150 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
2151 | is encoded in 2-byte but two position-codes are divided and shifted | |
2152 | so that it fit in the range below. | |
2153 | ||
2154 | --- CODE RANGE of SJIS --- | |
2155 | (character set) (range) | |
2156 | ASCII 0x00 .. 0x7F | |
2157 | KATAKANA-JISX0201 0xA0 .. 0xDF | |
c28a9453 | 2158 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 2159 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
2160 | ------------------------------- |
2161 | ||
2162 | */ | |
2163 | ||
2164 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
2165 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
2166 | character set and is encoded in two-byte. | |
2167 | ||
2168 | --- CODE RANGE of BIG5 --- | |
2169 | (character set) (range) | |
2170 | ASCII 0x00 .. 0x7F | |
2171 | Big5 (1st byte) 0xA1 .. 0xFE | |
2172 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
2173 | -------------------------- | |
2174 | ||
2175 | Since the number of characters in Big5 is larger than maximum | |
2176 | characters in Emacs' charset (96x96), it can't be handled as one | |
2177 | charset. So, in Emacs, Big5 is divided into two: `charset-big5-1' | |
2178 | and `charset-big5-2'. Both are DIMENSION2 and CHARS94. The former | |
2179 | contains frequently used characters and the latter contains less | |
2180 | frequently used characters. */ | |
2181 | ||
2182 | /* Macros to decode or encode a character of Big5 in BIG5. B1 and B2 | |
2183 | are the 1st and 2nd position-codes of Big5 in BIG5 coding system. | |
2184 | C1 and C2 are the 1st and 2nd position-codes of of Emacs' internal | |
2185 | format. CHARSET is `charset_big5_1' or `charset_big5_2'. */ | |
2186 | ||
2187 | /* Number of Big5 characters which have the same code in 1st byte. */ | |
2188 | #define BIG5_SAME_ROW (0xFF - 0xA1 + 0x7F - 0x40) | |
2189 | ||
2190 | #define DECODE_BIG5(b1, b2, charset, c1, c2) \ | |
2191 | do { \ | |
2192 | unsigned int temp \ | |
2193 | = (b1 - 0xA1) * BIG5_SAME_ROW + b2 - (b2 < 0x7F ? 0x40 : 0x62); \ | |
2194 | if (b1 < 0xC9) \ | |
2195 | charset = charset_big5_1; \ | |
2196 | else \ | |
2197 | { \ | |
2198 | charset = charset_big5_2; \ | |
2199 | temp -= (0xC9 - 0xA1) * BIG5_SAME_ROW; \ | |
2200 | } \ | |
2201 | c1 = temp / (0xFF - 0xA1) + 0x21; \ | |
2202 | c2 = temp % (0xFF - 0xA1) + 0x21; \ | |
2203 | } while (0) | |
2204 | ||
2205 | #define ENCODE_BIG5(charset, c1, c2, b1, b2) \ | |
2206 | do { \ | |
2207 | unsigned int temp = (c1 - 0x21) * (0xFF - 0xA1) + (c2 - 0x21); \ | |
2208 | if (charset == charset_big5_2) \ | |
2209 | temp += BIG5_SAME_ROW * (0xC9 - 0xA1); \ | |
2210 | b1 = temp / BIG5_SAME_ROW + 0xA1; \ | |
2211 | b2 = temp % BIG5_SAME_ROW; \ | |
2212 | b2 += b2 < 0x3F ? 0x40 : 0x62; \ | |
2213 | } while (0) | |
2214 | ||
2215 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
2216 | Check if a text is encoded in SJIS. If it is, return | |
2217 | CODING_CATEGORY_MASK_SJIS, else return 0. */ | |
2218 | ||
2219 | int | |
2220 | detect_coding_sjis (src, src_end) | |
2221 | unsigned char *src, *src_end; | |
2222 | { | |
b73bfc1c KH |
2223 | int c; |
2224 | /* Dummy for ONE_MORE_BYTE. */ | |
2225 | struct coding_system dummy_coding; | |
2226 | struct coding_system *coding = &dummy_coding; | |
4ed46869 | 2227 | |
b73bfc1c | 2228 | while (1) |
4ed46869 | 2229 | { |
b73bfc1c | 2230 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2231 | if ((c >= 0x80 && c < 0xA0) || c >= 0xE0) |
2232 | { | |
b73bfc1c KH |
2233 | ONE_MORE_BYTE (c); |
2234 | if (c < 0x40) | |
4ed46869 KH |
2235 | return 0; |
2236 | } | |
2237 | } | |
b73bfc1c | 2238 | label_end_of_loop: |
4ed46869 KH |
2239 | return CODING_CATEGORY_MASK_SJIS; |
2240 | } | |
2241 | ||
2242 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
2243 | Check if a text is encoded in BIG5. If it is, return | |
2244 | CODING_CATEGORY_MASK_BIG5, else return 0. */ | |
2245 | ||
2246 | int | |
2247 | detect_coding_big5 (src, src_end) | |
2248 | unsigned char *src, *src_end; | |
2249 | { | |
b73bfc1c KH |
2250 | int c; |
2251 | /* Dummy for ONE_MORE_BYTE. */ | |
2252 | struct coding_system dummy_coding; | |
2253 | struct coding_system *coding = &dummy_coding; | |
4ed46869 | 2254 | |
b73bfc1c | 2255 | while (1) |
4ed46869 | 2256 | { |
b73bfc1c | 2257 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2258 | if (c >= 0xA1) |
2259 | { | |
b73bfc1c | 2260 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2261 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) |
2262 | return 0; | |
2263 | } | |
2264 | } | |
b73bfc1c | 2265 | label_end_of_loop: |
4ed46869 KH |
2266 | return CODING_CATEGORY_MASK_BIG5; |
2267 | } | |
2268 | ||
fa42c37f KH |
2269 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
2270 | Check if a text is encoded in UTF-8. If it is, return | |
2271 | CODING_CATEGORY_MASK_UTF_8, else return 0. */ | |
2272 | ||
2273 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
2274 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
2275 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
2276 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
2277 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
2278 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
2279 | #define UTF_8_6_OCTET_LEADING_P(c) (((c) & 0xFE) == 0xFC) | |
2280 | ||
2281 | int | |
2282 | detect_coding_utf_8 (src, src_end) | |
2283 | unsigned char *src, *src_end; | |
2284 | { | |
2285 | unsigned char c; | |
2286 | int seq_maybe_bytes; | |
b73bfc1c KH |
2287 | /* Dummy for ONE_MORE_BYTE. */ |
2288 | struct coding_system dummy_coding; | |
2289 | struct coding_system *coding = &dummy_coding; | |
fa42c37f | 2290 | |
b73bfc1c | 2291 | while (1) |
fa42c37f | 2292 | { |
b73bfc1c | 2293 | ONE_MORE_BYTE (c); |
fa42c37f KH |
2294 | if (UTF_8_1_OCTET_P (c)) |
2295 | continue; | |
2296 | else if (UTF_8_2_OCTET_LEADING_P (c)) | |
2297 | seq_maybe_bytes = 1; | |
2298 | else if (UTF_8_3_OCTET_LEADING_P (c)) | |
2299 | seq_maybe_bytes = 2; | |
2300 | else if (UTF_8_4_OCTET_LEADING_P (c)) | |
2301 | seq_maybe_bytes = 3; | |
2302 | else if (UTF_8_5_OCTET_LEADING_P (c)) | |
2303 | seq_maybe_bytes = 4; | |
2304 | else if (UTF_8_6_OCTET_LEADING_P (c)) | |
2305 | seq_maybe_bytes = 5; | |
2306 | else | |
2307 | return 0; | |
2308 | ||
2309 | do | |
2310 | { | |
b73bfc1c | 2311 | ONE_MORE_BYTE (c); |
fa42c37f KH |
2312 | if (!UTF_8_EXTRA_OCTET_P (c)) |
2313 | return 0; | |
2314 | seq_maybe_bytes--; | |
2315 | } | |
2316 | while (seq_maybe_bytes > 0); | |
2317 | } | |
2318 | ||
b73bfc1c | 2319 | label_end_of_loop: |
fa42c37f KH |
2320 | return CODING_CATEGORY_MASK_UTF_8; |
2321 | } | |
2322 | ||
2323 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
2324 | Check if a text is encoded in UTF-16 Big Endian (endian == 1) or | |
2325 | Little Endian (otherwise). If it is, return | |
2326 | CODING_CATEGORY_MASK_UTF_16_BE or CODING_CATEGORY_MASK_UTF_16_LE, | |
2327 | else return 0. */ | |
2328 | ||
2329 | #define UTF_16_INVALID_P(val) \ | |
2330 | (((val) == 0xFFFE) \ | |
2331 | || ((val) == 0xFFFF)) | |
2332 | ||
2333 | #define UTF_16_HIGH_SURROGATE_P(val) \ | |
2334 | (((val) & 0xD800) == 0xD800) | |
2335 | ||
2336 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
2337 | (((val) & 0xDC00) == 0xDC00) | |
2338 | ||
2339 | int | |
2340 | detect_coding_utf_16 (src, src_end) | |
2341 | unsigned char *src, *src_end; | |
2342 | { | |
b73bfc1c KH |
2343 | unsigned char c1, c2; |
2344 | /* Dummy for TWO_MORE_BYTES. */ | |
2345 | struct coding_system dummy_coding; | |
2346 | struct coding_system *coding = &dummy_coding; | |
fa42c37f | 2347 | |
b73bfc1c KH |
2348 | TWO_MORE_BYTES (c1, c2); |
2349 | ||
2350 | if ((c1 == 0xFF) && (c2 == 0xFE)) | |
fa42c37f | 2351 | return CODING_CATEGORY_MASK_UTF_16_LE; |
b73bfc1c | 2352 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
fa42c37f KH |
2353 | return CODING_CATEGORY_MASK_UTF_16_BE; |
2354 | ||
b73bfc1c | 2355 | label_end_of_loop: |
fa42c37f KH |
2356 | return 0; |
2357 | } | |
2358 | ||
4ed46869 KH |
2359 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
2360 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
2361 | ||
b73bfc1c | 2362 | static void |
4ed46869 | 2363 | decode_coding_sjis_big5 (coding, source, destination, |
d46c5b12 | 2364 | src_bytes, dst_bytes, sjis_p) |
4ed46869 KH |
2365 | struct coding_system *coding; |
2366 | unsigned char *source, *destination; | |
2367 | int src_bytes, dst_bytes; | |
4ed46869 KH |
2368 | int sjis_p; |
2369 | { | |
2370 | unsigned char *src = source; | |
2371 | unsigned char *src_end = source + src_bytes; | |
2372 | unsigned char *dst = destination; | |
2373 | unsigned char *dst_end = destination + dst_bytes; | |
b73bfc1c KH |
2374 | /* SRC_BASE remembers the start position in source in each loop. |
2375 | The loop will be exited when there's not enough source code | |
2376 | (within macro ONE_MORE_BYTE), or when there's not enough | |
2377 | destination area to produce a character (within macro | |
2378 | EMIT_CHAR). */ | |
2379 | unsigned char *src_base; | |
2380 | Lisp_Object translation_table; | |
a5d301df | 2381 | |
b73bfc1c KH |
2382 | if (NILP (Venable_character_translation)) |
2383 | translation_table = Qnil; | |
2384 | else | |
2385 | { | |
2386 | translation_table = coding->translation_table_for_decode; | |
2387 | if (NILP (translation_table)) | |
2388 | translation_table = Vstandard_translation_table_for_decode; | |
2389 | } | |
4ed46869 | 2390 | |
d46c5b12 | 2391 | coding->produced_char = 0; |
b73bfc1c | 2392 | while (1) |
4ed46869 | 2393 | { |
b73bfc1c KH |
2394 | int c, charset, c1, c2; |
2395 | ||
2396 | src_base = src; | |
2397 | ONE_MORE_BYTE (c1); | |
2398 | ||
2399 | if (c1 < 0x80) | |
4ed46869 | 2400 | { |
b73bfc1c KH |
2401 | charset = CHARSET_ASCII; |
2402 | if (c1 < 0x20) | |
4ed46869 | 2403 | { |
b73bfc1c | 2404 | if (c1 == '\r') |
d46c5b12 | 2405 | { |
b73bfc1c | 2406 | if (coding->eol_type == CODING_EOL_CRLF) |
d46c5b12 | 2407 | { |
b73bfc1c KH |
2408 | ONE_MORE_BYTE (c2); |
2409 | if (c2 == '\n') | |
2410 | c1 = c2; | |
2411 | else if (coding->mode | |
2412 | & CODING_MODE_INHIBIT_INCONSISTENT_EOL) | |
2413 | { | |
2414 | coding->result = CODING_FINISH_INCONSISTENT_EOL; | |
2415 | goto label_end_of_loop; | |
2416 | } | |
2417 | else | |
2418 | /* To process C2 again, SRC is subtracted by 1. */ | |
2419 | src--; | |
d46c5b12 | 2420 | } |
b73bfc1c KH |
2421 | else if (coding->eol_type == CODING_EOL_CR) |
2422 | c1 = '\n'; | |
2423 | } | |
2424 | else if (c1 == '\n' | |
2425 | && (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) | |
2426 | && (coding->eol_type == CODING_EOL_CR | |
2427 | || coding->eol_type == CODING_EOL_CRLF)) | |
2428 | { | |
2429 | coding->result = CODING_FINISH_INCONSISTENT_EOL; | |
2430 | goto label_end_of_loop; | |
d46c5b12 | 2431 | } |
4ed46869 | 2432 | } |
4ed46869 | 2433 | } |
54f78171 | 2434 | else |
b73bfc1c | 2435 | { |
4ed46869 KH |
2436 | if (sjis_p) |
2437 | { | |
b73bfc1c KH |
2438 | if (c1 >= 0xF0) |
2439 | goto label_invalid_code; | |
2440 | if (c1 < 0xA0 || c1 >= 0xE0) | |
fb88bf2d | 2441 | { |
54f78171 KH |
2442 | /* SJIS -> JISX0208 */ |
2443 | ONE_MORE_BYTE (c2); | |
b73bfc1c KH |
2444 | if (c2 < 0x40 || c2 == 0x7F || c2 > 0xFC) |
2445 | goto label_invalid_code; | |
2446 | DECODE_SJIS (c1, c2, c1, c2); | |
2447 | charset = charset_jisx0208; | |
5e34de15 | 2448 | } |
fb88bf2d | 2449 | else |
b73bfc1c KH |
2450 | /* SJIS -> JISX0201-Kana */ |
2451 | charset = charset_katakana_jisx0201; | |
4ed46869 | 2452 | } |
fb88bf2d | 2453 | else |
fb88bf2d | 2454 | { |
54f78171 | 2455 | /* BIG5 -> Big5 */ |
b73bfc1c KH |
2456 | if (c1 < 0xA1 || c1 > 0xFE) |
2457 | goto label_invalid_code; | |
2458 | ONE_MORE_BYTE (c2); | |
2459 | if (c2 < 0x40 || (c2 > 0x7E && c2 < 0xA1) || c2 > 0xFE) | |
2460 | goto label_invalid_code; | |
2461 | DECODE_BIG5 (c1, c2, charset, c1, c2); | |
4ed46869 KH |
2462 | } |
2463 | } | |
4ed46869 | 2464 | |
b73bfc1c KH |
2465 | c = DECODE_ISO_CHARACTER (charset, c1, c2); |
2466 | EMIT_CHAR (c); | |
fb88bf2d KH |
2467 | continue; |
2468 | ||
b73bfc1c KH |
2469 | label_invalid_code: |
2470 | coding->errors++; | |
4ed46869 | 2471 | src = src_base; |
b73bfc1c KH |
2472 | c = *src++; |
2473 | EMIT_CHAR (c); | |
fb88bf2d | 2474 | } |
d46c5b12 | 2475 | |
b73bfc1c KH |
2476 | label_end_of_loop: |
2477 | coding->consumed = coding->consumed_char = src_base - source; | |
d46c5b12 | 2478 | coding->produced = dst - destination; |
b73bfc1c | 2479 | return; |
4ed46869 KH |
2480 | } |
2481 | ||
2482 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
2483 | This function can encode charsets `ascii', `katakana-jisx0201', |
2484 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
2485 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
2486 | (i.e. do not have extended leading-codes). Characters of other |
2487 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
2488 | SJIS text, else encode BIG5 text. */ | |
2489 | ||
b73bfc1c | 2490 | static void |
4ed46869 | 2491 | encode_coding_sjis_big5 (coding, source, destination, |
d46c5b12 | 2492 | src_bytes, dst_bytes, sjis_p) |
4ed46869 KH |
2493 | struct coding_system *coding; |
2494 | unsigned char *source, *destination; | |
2495 | int src_bytes, dst_bytes; | |
4ed46869 KH |
2496 | int sjis_p; |
2497 | { | |
2498 | unsigned char *src = source; | |
2499 | unsigned char *src_end = source + src_bytes; | |
2500 | unsigned char *dst = destination; | |
2501 | unsigned char *dst_end = destination + dst_bytes; | |
b73bfc1c KH |
2502 | /* SRC_BASE remembers the start position in source in each loop. |
2503 | The loop will be exited when there's not enough source text to | |
2504 | analyze multi-byte codes (within macro ONE_MORE_CHAR), or when | |
2505 | there's not enough destination area to produce encoded codes | |
2506 | (within macro EMIT_BYTES). */ | |
2507 | unsigned char *src_base; | |
2508 | Lisp_Object translation_table; | |
4ed46869 | 2509 | |
b73bfc1c KH |
2510 | if (NILP (Venable_character_translation)) |
2511 | translation_table = Qnil; | |
2512 | else | |
4ed46869 | 2513 | { |
b73bfc1c KH |
2514 | translation_table = coding->translation_table_for_decode; |
2515 | if (NILP (translation_table)) | |
2516 | translation_table = Vstandard_translation_table_for_decode; | |
2517 | } | |
a5d301df | 2518 | |
b73bfc1c KH |
2519 | while (1) |
2520 | { | |
2521 | int c, charset, c1, c2; | |
4ed46869 | 2522 | |
b73bfc1c KH |
2523 | src_base = src; |
2524 | ONE_MORE_CHAR (c); | |
2525 | ||
2526 | /* Now encode the character C. */ | |
2527 | if (SINGLE_BYTE_CHAR_P (c)) | |
2528 | { | |
2529 | switch (c) | |
4ed46869 | 2530 | { |
b73bfc1c KH |
2531 | case '\r': |
2532 | if (!coding->mode & CODING_MODE_SELECTIVE_DISPLAY) | |
2533 | { | |
2534 | EMIT_ONE_BYTE (c); | |
2535 | break; | |
2536 | } | |
2537 | c = '\n'; | |
2538 | case '\n': | |
2539 | if (coding->eol_type == CODING_EOL_CRLF) | |
2540 | { | |
2541 | EMIT_TWO_BYTES ('\r', c); | |
2542 | break; | |
2543 | } | |
2544 | else if (coding->eol_type == CODING_EOL_CR) | |
2545 | c = '\r'; | |
2546 | default: | |
2547 | EMIT_ONE_BYTE (c); | |
2548 | } | |
2549 | } | |
2550 | else | |
2551 | { | |
2552 | SPLIT_CHAR (c, charset, c1, c2); | |
2553 | if (sjis_p) | |
2554 | { | |
2555 | if (charset == charset_jisx0208 | |
2556 | || charset == charset_jisx0208_1978) | |
2557 | { | |
2558 | ENCODE_SJIS (c1, c2, c1, c2); | |
2559 | EMIT_TWO_BYTES (c1, c2); | |
2560 | } | |
2561 | else if (charset == charset_latin_jisx0201) | |
2562 | EMIT_ONE_BYTE (c1); | |
2563 | else | |
2564 | /* There's no way other than producing the internal | |
2565 | codes as is. */ | |
2566 | EMIT_BYTES (src_base, src); | |
4ed46869 | 2567 | } |
4ed46869 | 2568 | else |
b73bfc1c KH |
2569 | { |
2570 | if (charset == charset_big5_1 || charset == charset_big5_2) | |
2571 | { | |
2572 | ENCODE_BIG5 (charset, c1, c2, c1, c2); | |
2573 | EMIT_TWO_BYTES (c1, c2); | |
2574 | } | |
2575 | else | |
2576 | /* There's no way other than producing the internal | |
2577 | codes as is. */ | |
2578 | EMIT_BYTES (src_base, src); | |
2579 | } | |
4ed46869 | 2580 | } |
b73bfc1c | 2581 | coding->consumed_char++; |
4ed46869 KH |
2582 | } |
2583 | ||
b73bfc1c KH |
2584 | label_end_of_loop: |
2585 | coding->consumed = src_base - source; | |
d46c5b12 | 2586 | coding->produced = coding->produced_char = dst - destination; |
4ed46869 KH |
2587 | } |
2588 | ||
2589 | \f | |
1397dc18 KH |
2590 | /*** 5. CCL handlers ***/ |
2591 | ||
2592 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
2593 | Check if a text is encoded in a coding system of which | |
2594 | encoder/decoder are written in CCL program. If it is, return | |
2595 | CODING_CATEGORY_MASK_CCL, else return 0. */ | |
2596 | ||
2597 | int | |
2598 | detect_coding_ccl (src, src_end) | |
2599 | unsigned char *src, *src_end; | |
2600 | { | |
2601 | unsigned char *valid; | |
b73bfc1c KH |
2602 | int c; |
2603 | /* Dummy for ONE_MORE_BYTE. */ | |
2604 | struct coding_system dummy_coding; | |
2605 | struct coding_system *coding = &dummy_coding; | |
1397dc18 KH |
2606 | |
2607 | /* No coding system is assigned to coding-category-ccl. */ | |
2608 | if (!coding_system_table[CODING_CATEGORY_IDX_CCL]) | |
2609 | return 0; | |
2610 | ||
2611 | valid = coding_system_table[CODING_CATEGORY_IDX_CCL]->spec.ccl.valid_codes; | |
b73bfc1c | 2612 | while (1) |
1397dc18 | 2613 | { |
b73bfc1c KH |
2614 | ONE_MORE_BYTE (c); |
2615 | if (! valid[c]) | |
2616 | return 0; | |
1397dc18 | 2617 | } |
b73bfc1c | 2618 | label_end_of_loop: |
1397dc18 KH |
2619 | return CODING_CATEGORY_MASK_CCL; |
2620 | } | |
2621 | ||
2622 | \f | |
2623 | /*** 6. End-of-line handlers ***/ | |
4ed46869 | 2624 | |
b73bfc1c | 2625 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 2626 | |
b73bfc1c | 2627 | static void |
d46c5b12 | 2628 | decode_eol (coding, source, destination, src_bytes, dst_bytes) |
4ed46869 KH |
2629 | struct coding_system *coding; |
2630 | unsigned char *source, *destination; | |
2631 | int src_bytes, dst_bytes; | |
4ed46869 KH |
2632 | { |
2633 | unsigned char *src = source; | |
4ed46869 | 2634 | unsigned char *dst = destination; |
b73bfc1c KH |
2635 | unsigned char *src_end = src + src_bytes; |
2636 | unsigned char *dst_end = dst + dst_bytes; | |
2637 | Lisp_Object translation_table; | |
2638 | /* SRC_BASE remembers the start position in source in each loop. | |
2639 | The loop will be exited when there's not enough source code | |
2640 | (within macro ONE_MORE_BYTE), or when there's not enough | |
2641 | destination area to produce a character (within macro | |
2642 | EMIT_CHAR). */ | |
2643 | unsigned char *src_base; | |
2644 | int c; | |
2645 | ||
2646 | translation_table = Qnil; | |
4ed46869 KH |
2647 | switch (coding->eol_type) |
2648 | { | |
2649 | case CODING_EOL_CRLF: | |
b73bfc1c | 2650 | while (1) |
d46c5b12 | 2651 | { |
b73bfc1c KH |
2652 | src_base = src; |
2653 | ONE_MORE_BYTE (c); | |
2654 | if (c == '\r') | |
fb88bf2d | 2655 | { |
b73bfc1c KH |
2656 | ONE_MORE_BYTE (c); |
2657 | if (c != '\n') | |
2658 | { | |
2659 | if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) | |
2660 | { | |
2661 | coding->result = CODING_FINISH_INCONSISTENT_EOL; | |
2662 | goto label_end_of_loop; | |
2663 | } | |
2664 | src--; | |
2665 | c = '\r'; | |
2666 | } | |
fb88bf2d | 2667 | } |
b73bfc1c KH |
2668 | else if (c == '\n' |
2669 | && (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL)) | |
d46c5b12 | 2670 | { |
b73bfc1c KH |
2671 | coding->result = CODING_FINISH_INCONSISTENT_EOL; |
2672 | goto label_end_of_loop; | |
d46c5b12 | 2673 | } |
b73bfc1c | 2674 | EMIT_CHAR (c); |
d46c5b12 | 2675 | } |
b73bfc1c KH |
2676 | break; |
2677 | ||
2678 | case CODING_EOL_CR: | |
2679 | while (1) | |
d46c5b12 | 2680 | { |
b73bfc1c KH |
2681 | src_base = src; |
2682 | ONE_MORE_BYTE (c); | |
2683 | if (c == '\n') | |
2684 | { | |
2685 | if (coding->mode & CODING_MODE_INHIBIT_INCONSISTENT_EOL) | |
2686 | { | |
2687 | coding->result = CODING_FINISH_INCONSISTENT_EOL; | |
2688 | goto label_end_of_loop; | |
2689 | } | |
2690 | } | |
2691 | else if (c == '\r') | |
2692 | c = '\n'; | |
2693 | EMIT_CHAR (c); | |
d46c5b12 | 2694 | } |
4ed46869 KH |
2695 | break; |
2696 | ||
b73bfc1c KH |
2697 | default: /* no need for EOL handling */ |
2698 | while (1) | |
d46c5b12 | 2699 | { |
b73bfc1c KH |
2700 | src_base = src; |
2701 | ONE_MORE_BYTE (c); | |
2702 | EMIT_CHAR (c); | |
d46c5b12 | 2703 | } |
4ed46869 KH |
2704 | } |
2705 | ||
b73bfc1c KH |
2706 | label_end_of_loop: |
2707 | coding->consumed = coding->consumed_char = src_base - source; | |
2708 | coding->produced = dst - destination; | |
2709 | return; | |
4ed46869 KH |
2710 | } |
2711 | ||
2712 | /* See "GENERAL NOTES about `encode_coding_XXX ()' functions". Encode | |
b73bfc1c KH |
2713 | format of end-of-line according to `coding->eol_type'. It also |
2714 | convert multibyte form 8-bit characers to unibyte if | |
2715 | CODING->src_multibyte is nonzero. If `coding->mode & | |
2716 | CODING_MODE_SELECTIVE_DISPLAY' is nonzero, code '\r' in source text | |
2717 | also means end-of-line. */ | |
4ed46869 | 2718 | |
b73bfc1c | 2719 | static void |
d46c5b12 | 2720 | encode_eol (coding, source, destination, src_bytes, dst_bytes) |
4ed46869 KH |
2721 | struct coding_system *coding; |
2722 | unsigned char *source, *destination; | |
2723 | int src_bytes, dst_bytes; | |
4ed46869 KH |
2724 | { |
2725 | unsigned char *src = source; | |
2726 | unsigned char *dst = destination; | |
b73bfc1c KH |
2727 | unsigned char *src_end = src + src_bytes; |
2728 | unsigned char *dst_end = dst + dst_bytes; | |
2729 | Lisp_Object translation_table; | |
2730 | /* SRC_BASE remembers the start position in source in each loop. | |
2731 | The loop will be exited when there's not enough source text to | |
2732 | analyze multi-byte codes (within macro ONE_MORE_CHAR), or when | |
2733 | there's not enough destination area to produce encoded codes | |
2734 | (within macro EMIT_BYTES). */ | |
2735 | unsigned char *src_base; | |
2736 | int c; | |
2737 | int selective_display = coding->mode & CODING_MODE_SELECTIVE_DISPLAY; | |
2738 | ||
2739 | translation_table = Qnil; | |
2740 | if (coding->src_multibyte | |
2741 | && *(src_end - 1) == LEADING_CODE_8_BIT_CONTROL) | |
2742 | { | |
2743 | src_end--; | |
2744 | src_bytes--; | |
2745 | coding->result = CODING_FINISH_INSUFFICIENT_SRC; | |
2746 | } | |
fb88bf2d | 2747 | |
d46c5b12 KH |
2748 | if (coding->eol_type == CODING_EOL_CRLF) |
2749 | { | |
b73bfc1c | 2750 | while (src < src_end) |
d46c5b12 | 2751 | { |
b73bfc1c | 2752 | src_base = src; |
d46c5b12 | 2753 | c = *src++; |
b73bfc1c KH |
2754 | if (c >= 0x20) |
2755 | EMIT_ONE_BYTE (c); | |
2756 | else if (c == '\n' || (c == '\r' && selective_display)) | |
2757 | EMIT_TWO_BYTES ('\r', '\n'); | |
d46c5b12 | 2758 | else |
b73bfc1c | 2759 | EMIT_ONE_BYTE (c); |
d46c5b12 | 2760 | } |
ff2b1ea9 | 2761 | src_base = src; |
b73bfc1c | 2762 | label_end_of_loop: |
005f0d35 | 2763 | ; |
d46c5b12 KH |
2764 | } |
2765 | else | |
4ed46869 | 2766 | { |
b73bfc1c | 2767 | if (src_bytes <= dst_bytes) |
4ed46869 | 2768 | { |
b73bfc1c KH |
2769 | safe_bcopy (src, dst, src_bytes); |
2770 | src_base = src_end; | |
2771 | dst += src_bytes; | |
d46c5b12 | 2772 | } |
d46c5b12 | 2773 | else |
b73bfc1c KH |
2774 | { |
2775 | if (coding->src_multibyte | |
2776 | && *(src + dst_bytes - 1) == LEADING_CODE_8_BIT_CONTROL) | |
2777 | dst_bytes--; | |
2778 | safe_bcopy (src, dst, dst_bytes); | |
2779 | src_base = src + dst_bytes; | |
2780 | dst = destination + dst_bytes; | |
2781 | coding->result = CODING_FINISH_INSUFFICIENT_DST; | |
2782 | } | |
993824c9 | 2783 | if (coding->eol_type == CODING_EOL_CR) |
d46c5b12 | 2784 | { |
b73bfc1c KH |
2785 | for (src = destination; src < dst; src++) |
2786 | if (*src == '\n') *src = '\r'; | |
d46c5b12 | 2787 | } |
b73bfc1c | 2788 | else if (selective_display) |
d46c5b12 | 2789 | { |
b73bfc1c KH |
2790 | for (src = destination; src < dst; src++) |
2791 | if (*src == '\r') *src = '\n'; | |
4ed46869 | 2792 | } |
4ed46869 | 2793 | } |
b73bfc1c KH |
2794 | if (coding->src_multibyte) |
2795 | dst = destination + str_as_unibyte (destination, dst - destination); | |
4ed46869 | 2796 | |
b73bfc1c KH |
2797 | coding->consumed = src_base - source; |
2798 | coding->produced = dst - destination; | |
4ed46869 KH |
2799 | } |
2800 | ||
2801 | \f | |
1397dc18 | 2802 | /*** 7. C library functions ***/ |
4ed46869 KH |
2803 | |
2804 | /* In Emacs Lisp, coding system is represented by a Lisp symbol which | |
2805 | has a property `coding-system'. The value of this property is a | |
2806 | vector of length 5 (called as coding-vector). Among elements of | |
2807 | this vector, the first (element[0]) and the fifth (element[4]) | |
2808 | carry important information for decoding/encoding. Before | |
2809 | decoding/encoding, this information should be set in fields of a | |
2810 | structure of type `coding_system'. | |
2811 | ||
2812 | A value of property `coding-system' can be a symbol of another | |
2813 | subsidiary coding-system. In that case, Emacs gets coding-vector | |
2814 | from that symbol. | |
2815 | ||
2816 | `element[0]' contains information to be set in `coding->type'. The | |
2817 | value and its meaning is as follows: | |
2818 | ||
0ef69138 KH |
2819 | 0 -- coding_type_emacs_mule |
2820 | 1 -- coding_type_sjis | |
2821 | 2 -- coding_type_iso2022 | |
2822 | 3 -- coding_type_big5 | |
2823 | 4 -- coding_type_ccl encoder/decoder written in CCL | |
2824 | nil -- coding_type_no_conversion | |
2825 | t -- coding_type_undecided (automatic conversion on decoding, | |
2826 | no-conversion on encoding) | |
4ed46869 KH |
2827 | |
2828 | `element[4]' contains information to be set in `coding->flags' and | |
2829 | `coding->spec'. The meaning varies by `coding->type'. | |
2830 | ||
2831 | If `coding->type' is `coding_type_iso2022', element[4] is a vector | |
2832 | of length 32 (of which the first 13 sub-elements are used now). | |
2833 | Meanings of these sub-elements are: | |
2834 | ||
2835 | sub-element[N] where N is 0 through 3: to be set in `coding->spec.iso2022' | |
2836 | If the value is an integer of valid charset, the charset is | |
2837 | assumed to be designated to graphic register N initially. | |
2838 | ||
2839 | If the value is minus, it is a minus value of charset which | |
2840 | reserves graphic register N, which means that the charset is | |
2841 | not designated initially but should be designated to graphic | |
2842 | register N just before encoding a character in that charset. | |
2843 | ||
2844 | If the value is nil, graphic register N is never used on | |
2845 | encoding. | |
2846 | ||
2847 | sub-element[N] where N is 4 through 11: to be set in `coding->flags' | |
2848 | Each value takes t or nil. See the section ISO2022 of | |
2849 | `coding.h' for more information. | |
2850 | ||
2851 | If `coding->type' is `coding_type_big5', element[4] is t to denote | |
2852 | BIG5-ETen or nil to denote BIG5-HKU. | |
2853 | ||
2854 | If `coding->type' takes the other value, element[4] is ignored. | |
2855 | ||
2856 | Emacs Lisp's coding system also carries information about format of | |
2857 | end-of-line in a value of property `eol-type'. If the value is | |
2858 | integer, 0 means CODING_EOL_LF, 1 means CODING_EOL_CRLF, and 2 | |
2859 | means CODING_EOL_CR. If it is not integer, it should be a vector | |
2860 | of subsidiary coding systems of which property `eol-type' has one | |
2861 | of above values. | |
2862 | ||
2863 | */ | |
2864 | ||
2865 | /* Extract information for decoding/encoding from CODING_SYSTEM_SYMBOL | |
2866 | and set it in CODING. If CODING_SYSTEM_SYMBOL is invalid, CODING | |
2867 | is setup so that no conversion is necessary and return -1, else | |
2868 | return 0. */ | |
2869 | ||
2870 | int | |
e0e989f6 KH |
2871 | setup_coding_system (coding_system, coding) |
2872 | Lisp_Object coding_system; | |
4ed46869 KH |
2873 | struct coding_system *coding; |
2874 | { | |
d46c5b12 | 2875 | Lisp_Object coding_spec, coding_type, eol_type, plist; |
4608c386 | 2876 | Lisp_Object val; |
70c22245 | 2877 | int i; |
4ed46869 | 2878 | |
d46c5b12 | 2879 | /* Initialize some fields required for all kinds of coding systems. */ |
774324d6 | 2880 | coding->symbol = coding_system; |
d46c5b12 KH |
2881 | coding->common_flags = 0; |
2882 | coding->mode = 0; | |
2883 | coding->heading_ascii = -1; | |
2884 | coding->post_read_conversion = coding->pre_write_conversion = Qnil; | |
ec6d2bb8 KH |
2885 | coding->composing = COMPOSITION_DISABLED; |
2886 | coding->cmp_data = NULL; | |
1f5dbf34 KH |
2887 | |
2888 | if (NILP (coding_system)) | |
2889 | goto label_invalid_coding_system; | |
2890 | ||
4608c386 | 2891 | coding_spec = Fget (coding_system, Qcoding_system); |
1f5dbf34 | 2892 | |
4608c386 KH |
2893 | if (!VECTORP (coding_spec) |
2894 | || XVECTOR (coding_spec)->size != 5 | |
2895 | || !CONSP (XVECTOR (coding_spec)->contents[3])) | |
4ed46869 | 2896 | goto label_invalid_coding_system; |
4608c386 | 2897 | |
d46c5b12 KH |
2898 | eol_type = inhibit_eol_conversion ? Qnil : Fget (coding_system, Qeol_type); |
2899 | if (VECTORP (eol_type)) | |
2900 | { | |
2901 | coding->eol_type = CODING_EOL_UNDECIDED; | |
2902 | coding->common_flags = CODING_REQUIRE_DETECTION_MASK; | |
2903 | } | |
2904 | else if (XFASTINT (eol_type) == 1) | |
2905 | { | |
2906 | coding->eol_type = CODING_EOL_CRLF; | |
2907 | coding->common_flags | |
2908 | = CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; | |
2909 | } | |
2910 | else if (XFASTINT (eol_type) == 2) | |
2911 | { | |
2912 | coding->eol_type = CODING_EOL_CR; | |
2913 | coding->common_flags | |
2914 | = CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; | |
2915 | } | |
2916 | else | |
2917 | coding->eol_type = CODING_EOL_LF; | |
2918 | ||
2919 | coding_type = XVECTOR (coding_spec)->contents[0]; | |
2920 | /* Try short cut. */ | |
2921 | if (SYMBOLP (coding_type)) | |
2922 | { | |
2923 | if (EQ (coding_type, Qt)) | |
2924 | { | |
2925 | coding->type = coding_type_undecided; | |
2926 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
2927 | } | |
2928 | else | |
2929 | coding->type = coding_type_no_conversion; | |
2930 | return 0; | |
2931 | } | |
2932 | ||
d46c5b12 KH |
2933 | /* Get values of coding system properties: |
2934 | `post-read-conversion', `pre-write-conversion', | |
f967223b | 2935 | `translation-table-for-decode', `translation-table-for-encode'. */ |
4608c386 | 2936 | plist = XVECTOR (coding_spec)->contents[3]; |
b843d1ae KH |
2937 | /* Pre & post conversion functions should be disabled if |
2938 | inhibit_eol_conversion is nozero. This is the case that a code | |
2939 | conversion function is called while those functions are running. */ | |
2940 | if (! inhibit_pre_post_conversion) | |
2941 | { | |
2942 | coding->post_read_conversion = Fplist_get (plist, Qpost_read_conversion); | |
2943 | coding->pre_write_conversion = Fplist_get (plist, Qpre_write_conversion); | |
2944 | } | |
f967223b | 2945 | val = Fplist_get (plist, Qtranslation_table_for_decode); |
4608c386 | 2946 | if (SYMBOLP (val)) |
f967223b KH |
2947 | val = Fget (val, Qtranslation_table_for_decode); |
2948 | coding->translation_table_for_decode = CHAR_TABLE_P (val) ? val : Qnil; | |
2949 | val = Fplist_get (plist, Qtranslation_table_for_encode); | |
4608c386 | 2950 | if (SYMBOLP (val)) |
f967223b KH |
2951 | val = Fget (val, Qtranslation_table_for_encode); |
2952 | coding->translation_table_for_encode = CHAR_TABLE_P (val) ? val : Qnil; | |
d46c5b12 KH |
2953 | val = Fplist_get (plist, Qcoding_category); |
2954 | if (!NILP (val)) | |
2955 | { | |
2956 | val = Fget (val, Qcoding_category_index); | |
2957 | if (INTEGERP (val)) | |
2958 | coding->category_idx = XINT (val); | |
2959 | else | |
2960 | goto label_invalid_coding_system; | |
2961 | } | |
2962 | else | |
2963 | goto label_invalid_coding_system; | |
4608c386 | 2964 | |
70c22245 KH |
2965 | val = Fplist_get (plist, Qsafe_charsets); |
2966 | if (EQ (val, Qt)) | |
2967 | { | |
2968 | for (i = 0; i <= MAX_CHARSET; i++) | |
2969 | coding->safe_charsets[i] = 1; | |
2970 | } | |
2971 | else | |
2972 | { | |
2973 | bzero (coding->safe_charsets, MAX_CHARSET + 1); | |
2974 | while (CONSP (val)) | |
2975 | { | |
03699b14 | 2976 | if ((i = get_charset_id (XCAR (val))) >= 0) |
70c22245 | 2977 | coding->safe_charsets[i] = 1; |
03699b14 | 2978 | val = XCDR (val); |
70c22245 KH |
2979 | } |
2980 | } | |
2981 | ||
ec6d2bb8 KH |
2982 | /* If the coding system has non-nil `composition' property, enable |
2983 | composition handling. */ | |
2984 | val = Fplist_get (plist, Qcomposition); | |
2985 | if (!NILP (val)) | |
2986 | coding->composing = COMPOSITION_NO; | |
2987 | ||
d46c5b12 | 2988 | switch (XFASTINT (coding_type)) |
4ed46869 KH |
2989 | { |
2990 | case 0: | |
0ef69138 | 2991 | coding->type = coding_type_emacs_mule; |
c952af22 KH |
2992 | if (!NILP (coding->post_read_conversion)) |
2993 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
2994 | if (!NILP (coding->pre_write_conversion)) | |
2995 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
4ed46869 KH |
2996 | break; |
2997 | ||
2998 | case 1: | |
2999 | coding->type = coding_type_sjis; | |
c952af22 KH |
3000 | coding->common_flags |
3001 | |= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; | |
4ed46869 KH |
3002 | break; |
3003 | ||
3004 | case 2: | |
3005 | coding->type = coding_type_iso2022; | |
c952af22 KH |
3006 | coding->common_flags |
3007 | |= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; | |
4ed46869 | 3008 | { |
70c22245 | 3009 | Lisp_Object val, temp; |
4ed46869 | 3010 | Lisp_Object *flags; |
d46c5b12 | 3011 | int i, charset, reg_bits = 0; |
4ed46869 | 3012 | |
4608c386 | 3013 | val = XVECTOR (coding_spec)->contents[4]; |
f44d27ce | 3014 | |
4ed46869 KH |
3015 | if (!VECTORP (val) || XVECTOR (val)->size != 32) |
3016 | goto label_invalid_coding_system; | |
3017 | ||
3018 | flags = XVECTOR (val)->contents; | |
3019 | coding->flags | |
3020 | = ((NILP (flags[4]) ? 0 : CODING_FLAG_ISO_SHORT_FORM) | |
3021 | | (NILP (flags[5]) ? 0 : CODING_FLAG_ISO_RESET_AT_EOL) | |
3022 | | (NILP (flags[6]) ? 0 : CODING_FLAG_ISO_RESET_AT_CNTL) | |
3023 | | (NILP (flags[7]) ? 0 : CODING_FLAG_ISO_SEVEN_BITS) | |
3024 | | (NILP (flags[8]) ? 0 : CODING_FLAG_ISO_LOCKING_SHIFT) | |
3025 | | (NILP (flags[9]) ? 0 : CODING_FLAG_ISO_SINGLE_SHIFT) | |
3026 | | (NILP (flags[10]) ? 0 : CODING_FLAG_ISO_USE_ROMAN) | |
3027 | | (NILP (flags[11]) ? 0 : CODING_FLAG_ISO_USE_OLDJIS) | |
e0e989f6 KH |
3028 | | (NILP (flags[12]) ? 0 : CODING_FLAG_ISO_NO_DIRECTION) |
3029 | | (NILP (flags[13]) ? 0 : CODING_FLAG_ISO_INIT_AT_BOL) | |
c4825358 KH |
3030 | | (NILP (flags[14]) ? 0 : CODING_FLAG_ISO_DESIGNATE_AT_BOL) |
3031 | | (NILP (flags[15]) ? 0 : CODING_FLAG_ISO_SAFE) | |
3f003981 | 3032 | | (NILP (flags[16]) ? 0 : CODING_FLAG_ISO_LATIN_EXTRA) |
c4825358 | 3033 | ); |
4ed46869 KH |
3034 | |
3035 | /* Invoke graphic register 0 to plane 0. */ | |
3036 | CODING_SPEC_ISO_INVOCATION (coding, 0) = 0; | |
3037 | /* Invoke graphic register 1 to plane 1 if we can use full 8-bit. */ | |
3038 | CODING_SPEC_ISO_INVOCATION (coding, 1) | |
3039 | = (coding->flags & CODING_FLAG_ISO_SEVEN_BITS ? -1 : 1); | |
3040 | /* Not single shifting at first. */ | |
6e85d753 | 3041 | CODING_SPEC_ISO_SINGLE_SHIFTING (coding) = 0; |
e0e989f6 | 3042 | /* Beginning of buffer should also be regarded as bol. */ |
6e85d753 | 3043 | CODING_SPEC_ISO_BOL (coding) = 1; |
4ed46869 | 3044 | |
70c22245 KH |
3045 | for (charset = 0; charset <= MAX_CHARSET; charset++) |
3046 | CODING_SPEC_ISO_REVISION_NUMBER (coding, charset) = 255; | |
3047 | val = Vcharset_revision_alist; | |
3048 | while (CONSP (val)) | |
3049 | { | |
03699b14 | 3050 | charset = get_charset_id (Fcar_safe (XCAR (val))); |
70c22245 | 3051 | if (charset >= 0 |
03699b14 | 3052 | && (temp = Fcdr_safe (XCAR (val)), INTEGERP (temp)) |
70c22245 KH |
3053 | && (i = XINT (temp), (i >= 0 && (i + '@') < 128))) |
3054 | CODING_SPEC_ISO_REVISION_NUMBER (coding, charset) = i; | |
03699b14 | 3055 | val = XCDR (val); |
70c22245 KH |
3056 | } |
3057 | ||
4ed46869 KH |
3058 | /* Checks FLAGS[REG] (REG = 0, 1, 2 3) and decide designations. |
3059 | FLAGS[REG] can be one of below: | |
3060 | integer CHARSET: CHARSET occupies register I, | |
3061 | t: designate nothing to REG initially, but can be used | |
3062 | by any charsets, | |
3063 | list of integer, nil, or t: designate the first | |
3064 | element (if integer) to REG initially, the remaining | |
3065 | elements (if integer) is designated to REG on request, | |
d46c5b12 | 3066 | if an element is t, REG can be used by any charsets, |
4ed46869 | 3067 | nil: REG is never used. */ |
467e7675 | 3068 | for (charset = 0; charset <= MAX_CHARSET; charset++) |
1ba9e4ab KH |
3069 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
3070 | = CODING_SPEC_ISO_NO_REQUESTED_DESIGNATION; | |
4ed46869 KH |
3071 | for (i = 0; i < 4; i++) |
3072 | { | |
3073 | if (INTEGERP (flags[i]) | |
e0e989f6 KH |
3074 | && (charset = XINT (flags[i]), CHARSET_VALID_P (charset)) |
3075 | || (charset = get_charset_id (flags[i])) >= 0) | |
4ed46869 KH |
3076 | { |
3077 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = charset; | |
3078 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) = i; | |
3079 | } | |
3080 | else if (EQ (flags[i], Qt)) | |
3081 | { | |
3082 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; | |
d46c5b12 KH |
3083 | reg_bits |= 1 << i; |
3084 | coding->flags |= CODING_FLAG_ISO_DESIGNATION; | |
4ed46869 KH |
3085 | } |
3086 | else if (CONSP (flags[i])) | |
3087 | { | |
84d60297 RS |
3088 | Lisp_Object tail; |
3089 | tail = flags[i]; | |
4ed46869 | 3090 | |
d46c5b12 | 3091 | coding->flags |= CODING_FLAG_ISO_DESIGNATION; |
03699b14 KR |
3092 | if (INTEGERP (XCAR (tail)) |
3093 | && (charset = XINT (XCAR (tail)), | |
e0e989f6 | 3094 | CHARSET_VALID_P (charset)) |
03699b14 | 3095 | || (charset = get_charset_id (XCAR (tail))) >= 0) |
4ed46869 KH |
3096 | { |
3097 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = charset; | |
3098 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) =i; | |
3099 | } | |
3100 | else | |
3101 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; | |
03699b14 | 3102 | tail = XCDR (tail); |
4ed46869 KH |
3103 | while (CONSP (tail)) |
3104 | { | |
03699b14 KR |
3105 | if (INTEGERP (XCAR (tail)) |
3106 | && (charset = XINT (XCAR (tail)), | |
e0e989f6 | 3107 | CHARSET_VALID_P (charset)) |
03699b14 | 3108 | || (charset = get_charset_id (XCAR (tail))) >= 0) |
70c22245 KH |
3109 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) |
3110 | = i; | |
03699b14 | 3111 | else if (EQ (XCAR (tail), Qt)) |
d46c5b12 | 3112 | reg_bits |= 1 << i; |
03699b14 | 3113 | tail = XCDR (tail); |
4ed46869 KH |
3114 | } |
3115 | } | |
3116 | else | |
3117 | CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i) = -1; | |
3118 | ||
3119 | CODING_SPEC_ISO_DESIGNATION (coding, i) | |
3120 | = CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, i); | |
3121 | } | |
3122 | ||
d46c5b12 | 3123 | if (reg_bits && ! (coding->flags & CODING_FLAG_ISO_LOCKING_SHIFT)) |
4ed46869 KH |
3124 | { |
3125 | /* REG 1 can be used only by locking shift in 7-bit env. */ | |
3126 | if (coding->flags & CODING_FLAG_ISO_SEVEN_BITS) | |
d46c5b12 | 3127 | reg_bits &= ~2; |
4ed46869 KH |
3128 | if (! (coding->flags & CODING_FLAG_ISO_SINGLE_SHIFT)) |
3129 | /* Without any shifting, only REG 0 and 1 can be used. */ | |
d46c5b12 | 3130 | reg_bits &= 3; |
4ed46869 KH |
3131 | } |
3132 | ||
d46c5b12 KH |
3133 | if (reg_bits) |
3134 | for (charset = 0; charset <= MAX_CHARSET; charset++) | |
6e85d753 | 3135 | { |
d46c5b12 KH |
3136 | if (CHARSET_VALID_P (charset)) |
3137 | { | |
3138 | /* There exist some default graphic registers to be | |
3139 | used CHARSET. */ | |
3140 | ||
3141 | /* We had better avoid designating a charset of | |
3142 | CHARS96 to REG 0 as far as possible. */ | |
3143 | if (CHARSET_CHARS (charset) == 96) | |
3144 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) | |
3145 | = (reg_bits & 2 | |
3146 | ? 1 : (reg_bits & 4 ? 2 : (reg_bits & 8 ? 3 : 0))); | |
3147 | else | |
3148 | CODING_SPEC_ISO_REQUESTED_DESIGNATION (coding, charset) | |
3149 | = (reg_bits & 1 | |
3150 | ? 0 : (reg_bits & 2 ? 1 : (reg_bits & 4 ? 2 : 3))); | |
3151 | } | |
6e85d753 | 3152 | } |
4ed46869 | 3153 | } |
c952af22 | 3154 | coding->common_flags |= CODING_REQUIRE_FLUSHING_MASK; |
d46c5b12 | 3155 | coding->spec.iso2022.last_invalid_designation_register = -1; |
4ed46869 KH |
3156 | break; |
3157 | ||
3158 | case 3: | |
3159 | coding->type = coding_type_big5; | |
c952af22 KH |
3160 | coding->common_flags |
3161 | |= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; | |
4ed46869 | 3162 | coding->flags |
4608c386 | 3163 | = (NILP (XVECTOR (coding_spec)->contents[4]) |
4ed46869 KH |
3164 | ? CODING_FLAG_BIG5_HKU |
3165 | : CODING_FLAG_BIG5_ETEN); | |
3166 | break; | |
3167 | ||
3168 | case 4: | |
3169 | coding->type = coding_type_ccl; | |
c952af22 KH |
3170 | coding->common_flags |
3171 | |= CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK; | |
4ed46869 | 3172 | { |
84d60297 | 3173 | val = XVECTOR (coding_spec)->contents[4]; |
ef4ced28 KH |
3174 | if (! CONSP (val) |
3175 | || setup_ccl_program (&(coding->spec.ccl.decoder), | |
03699b14 | 3176 | XCAR (val)) < 0 |
ef4ced28 | 3177 | || setup_ccl_program (&(coding->spec.ccl.encoder), |
03699b14 | 3178 | XCDR (val)) < 0) |
4ed46869 | 3179 | goto label_invalid_coding_system; |
1397dc18 KH |
3180 | |
3181 | bzero (coding->spec.ccl.valid_codes, 256); | |
3182 | val = Fplist_get (plist, Qvalid_codes); | |
3183 | if (CONSP (val)) | |
3184 | { | |
3185 | Lisp_Object this; | |
3186 | ||
03699b14 | 3187 | for (; CONSP (val); val = XCDR (val)) |
1397dc18 | 3188 | { |
03699b14 | 3189 | this = XCAR (val); |
1397dc18 KH |
3190 | if (INTEGERP (this) |
3191 | && XINT (this) >= 0 && XINT (this) < 256) | |
3192 | coding->spec.ccl.valid_codes[XINT (this)] = 1; | |
3193 | else if (CONSP (this) | |
03699b14 KR |
3194 | && INTEGERP (XCAR (this)) |
3195 | && INTEGERP (XCDR (this))) | |
1397dc18 | 3196 | { |
03699b14 KR |
3197 | int start = XINT (XCAR (this)); |
3198 | int end = XINT (XCDR (this)); | |
1397dc18 KH |
3199 | |
3200 | if (start >= 0 && start <= end && end < 256) | |
e133c8fa | 3201 | while (start <= end) |
1397dc18 KH |
3202 | coding->spec.ccl.valid_codes[start++] = 1; |
3203 | } | |
3204 | } | |
3205 | } | |
4ed46869 | 3206 | } |
c952af22 | 3207 | coding->common_flags |= CODING_REQUIRE_FLUSHING_MASK; |
4ed46869 KH |
3208 | break; |
3209 | ||
27901516 KH |
3210 | case 5: |
3211 | coding->type = coding_type_raw_text; | |
3212 | break; | |
3213 | ||
4ed46869 | 3214 | default: |
d46c5b12 | 3215 | goto label_invalid_coding_system; |
4ed46869 KH |
3216 | } |
3217 | return 0; | |
3218 | ||
3219 | label_invalid_coding_system: | |
3220 | coding->type = coding_type_no_conversion; | |
d46c5b12 | 3221 | coding->category_idx = CODING_CATEGORY_IDX_BINARY; |
c952af22 | 3222 | coding->common_flags = 0; |
dec137e5 | 3223 | coding->eol_type = CODING_EOL_LF; |
d46c5b12 | 3224 | coding->pre_write_conversion = coding->post_read_conversion = Qnil; |
4ed46869 KH |
3225 | return -1; |
3226 | } | |
3227 | ||
ec6d2bb8 KH |
3228 | /* Free memory blocks allocated for storing composition information. */ |
3229 | ||
3230 | void | |
3231 | coding_free_composition_data (coding) | |
3232 | struct coding_system *coding; | |
3233 | { | |
3234 | struct composition_data *cmp_data = coding->cmp_data, *next; | |
3235 | ||
3236 | if (!cmp_data) | |
3237 | return; | |
3238 | /* Memory blocks are chained. At first, rewind to the first, then, | |
3239 | free blocks one by one. */ | |
3240 | while (cmp_data->prev) | |
3241 | cmp_data = cmp_data->prev; | |
3242 | while (cmp_data) | |
3243 | { | |
3244 | next = cmp_data->next; | |
3245 | xfree (cmp_data); | |
3246 | cmp_data = next; | |
3247 | } | |
3248 | coding->cmp_data = NULL; | |
3249 | } | |
3250 | ||
3251 | /* Set `char_offset' member of all memory blocks pointed by | |
3252 | coding->cmp_data to POS. */ | |
3253 | ||
3254 | void | |
3255 | coding_adjust_composition_offset (coding, pos) | |
3256 | struct coding_system *coding; | |
3257 | int pos; | |
3258 | { | |
3259 | struct composition_data *cmp_data; | |
3260 | ||
3261 | for (cmp_data = coding->cmp_data; cmp_data; cmp_data = cmp_data->next) | |
3262 | cmp_data->char_offset = pos; | |
3263 | } | |
3264 | ||
54f78171 KH |
3265 | /* Setup raw-text or one of its subsidiaries in the structure |
3266 | coding_system CODING according to the already setup value eol_type | |
3267 | in CODING. CODING should be setup for some coding system in | |
3268 | advance. */ | |
3269 | ||
3270 | void | |
3271 | setup_raw_text_coding_system (coding) | |
3272 | struct coding_system *coding; | |
3273 | { | |
3274 | if (coding->type != coding_type_raw_text) | |
3275 | { | |
3276 | coding->symbol = Qraw_text; | |
3277 | coding->type = coding_type_raw_text; | |
3278 | if (coding->eol_type != CODING_EOL_UNDECIDED) | |
3279 | { | |
84d60297 RS |
3280 | Lisp_Object subsidiaries; |
3281 | subsidiaries = Fget (Qraw_text, Qeol_type); | |
54f78171 KH |
3282 | |
3283 | if (VECTORP (subsidiaries) | |
3284 | && XVECTOR (subsidiaries)->size == 3) | |
3285 | coding->symbol | |
3286 | = XVECTOR (subsidiaries)->contents[coding->eol_type]; | |
3287 | } | |
716e0b0a | 3288 | setup_coding_system (coding->symbol, coding); |
54f78171 KH |
3289 | } |
3290 | return; | |
3291 | } | |
3292 | ||
4ed46869 KH |
3293 | /* Emacs has a mechanism to automatically detect a coding system if it |
3294 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
3295 | it's impossible to distinguish some coding systems accurately | |
3296 | because they use the same range of codes. So, at first, coding | |
3297 | systems are categorized into 7, those are: | |
3298 | ||
0ef69138 | 3299 | o coding-category-emacs-mule |
4ed46869 KH |
3300 | |
3301 | The category for a coding system which has the same code range | |
3302 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 3303 | symbol) `emacs-mule' by default. |
4ed46869 KH |
3304 | |
3305 | o coding-category-sjis | |
3306 | ||
3307 | The category for a coding system which has the same code range | |
3308 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 3309 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
3310 | |
3311 | o coding-category-iso-7 | |
3312 | ||
3313 | The category for a coding system which has the same code range | |
7717c392 | 3314 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
3315 | shift and single shift functions. This can encode/decode all |
3316 | charsets. Assigned the coding-system (Lisp symbol) | |
3317 | `iso-2022-7bit' by default. | |
3318 | ||
3319 | o coding-category-iso-7-tight | |
3320 | ||
3321 | Same as coding-category-iso-7 except that this can | |
3322 | encode/decode only the specified charsets. | |
4ed46869 KH |
3323 | |
3324 | o coding-category-iso-8-1 | |
3325 | ||
3326 | The category for a coding system which has the same code range | |
3327 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
3328 | for DIMENSION1 charset. This doesn't use any locking shift |
3329 | and single shift functions. Assigned the coding-system (Lisp | |
3330 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
3331 | |
3332 | o coding-category-iso-8-2 | |
3333 | ||
3334 | The category for a coding system which has the same code range | |
3335 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
3336 | for DIMENSION2 charset. This doesn't use any locking shift |
3337 | and single shift functions. Assigned the coding-system (Lisp | |
3338 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 3339 | |
7717c392 | 3340 | o coding-category-iso-7-else |
4ed46869 KH |
3341 | |
3342 | The category for a coding system which has the same code range | |
7717c392 KH |
3343 | as ISO2022 of 7-bit environemnt but uses locking shift or |
3344 | single shift functions. Assigned the coding-system (Lisp | |
3345 | symbol) `iso-2022-7bit-lock' by default. | |
3346 | ||
3347 | o coding-category-iso-8-else | |
3348 | ||
3349 | The category for a coding system which has the same code range | |
3350 | as ISO2022 of 8-bit environemnt but uses locking shift or | |
3351 | single shift functions. Assigned the coding-system (Lisp | |
3352 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
3353 | |
3354 | o coding-category-big5 | |
3355 | ||
3356 | The category for a coding system which has the same code range | |
3357 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 3358 | `cn-big5' by default. |
4ed46869 | 3359 | |
fa42c37f KH |
3360 | o coding-category-utf-8 |
3361 | ||
3362 | The category for a coding system which has the same code range | |
3363 | as UTF-8 (cf. RFC2279). Assigned the coding-system (Lisp | |
3364 | symbol) `utf-8' by default. | |
3365 | ||
3366 | o coding-category-utf-16-be | |
3367 | ||
3368 | The category for a coding system in which a text has an | |
3369 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
3370 | endian at the head. Assigned the coding-system (Lisp symbol) | |
3371 | `utf-16-be' by default. | |
3372 | ||
3373 | o coding-category-utf-16-le | |
3374 | ||
3375 | The category for a coding system in which a text has an | |
3376 | Unicode signature (cf. Unicode Standard) in the order of | |
3377 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
3378 | symbol) `utf-16-le' by default. | |
3379 | ||
1397dc18 KH |
3380 | o coding-category-ccl |
3381 | ||
3382 | The category for a coding system of which encoder/decoder is | |
3383 | written in CCL programs. The default value is nil, i.e., no | |
3384 | coding system is assigned. | |
3385 | ||
4ed46869 KH |
3386 | o coding-category-binary |
3387 | ||
3388 | The category for a coding system not categorized in any of the | |
3389 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 3390 | `no-conversion' by default. |
4ed46869 KH |
3391 | |
3392 | Each of them is a Lisp symbol and the value is an actual | |
3393 | `coding-system's (this is also a Lisp symbol) assigned by a user. | |
3394 | What Emacs does actually is to detect a category of coding system. | |
3395 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
3396 | decide only one possible category, it selects a category of the | |
3397 | highest priority. Priorities of categories are also specified by a | |
3398 | user in a Lisp variable `coding-category-list'. | |
3399 | ||
3400 | */ | |
3401 | ||
66cfb530 KH |
3402 | static |
3403 | int ascii_skip_code[256]; | |
3404 | ||
d46c5b12 | 3405 | /* Detect how a text of length SRC_BYTES pointed by SOURCE is encoded. |
4ed46869 KH |
3406 | If it detects possible coding systems, return an integer in which |
3407 | appropriate flag bits are set. Flag bits are defined by macros | |
fa42c37f KH |
3408 | CODING_CATEGORY_MASK_XXX in `coding.h'. If PRIORITIES is non-NULL, |
3409 | it should point the table `coding_priorities'. In that case, only | |
3410 | the flag bit for a coding system of the highest priority is set in | |
3411 | the returned value. | |
4ed46869 | 3412 | |
d46c5b12 KH |
3413 | How many ASCII characters are at the head is returned as *SKIP. */ |
3414 | ||
3415 | static int | |
3416 | detect_coding_mask (source, src_bytes, priorities, skip) | |
3417 | unsigned char *source; | |
3418 | int src_bytes, *priorities, *skip; | |
4ed46869 KH |
3419 | { |
3420 | register unsigned char c; | |
d46c5b12 | 3421 | unsigned char *src = source, *src_end = source + src_bytes; |
fa42c37f KH |
3422 | unsigned int mask, utf16_examined_p, iso2022_examined_p; |
3423 | int i, idx; | |
4ed46869 KH |
3424 | |
3425 | /* At first, skip all ASCII characters and control characters except | |
3426 | for three ISO2022 specific control characters. */ | |
66cfb530 KH |
3427 | ascii_skip_code[ISO_CODE_SO] = 0; |
3428 | ascii_skip_code[ISO_CODE_SI] = 0; | |
3429 | ascii_skip_code[ISO_CODE_ESC] = 0; | |
3430 | ||
bcf26d6a | 3431 | label_loop_detect_coding: |
66cfb530 | 3432 | while (src < src_end && ascii_skip_code[*src]) src++; |
d46c5b12 | 3433 | *skip = src - source; |
4ed46869 KH |
3434 | |
3435 | if (src >= src_end) | |
3436 | /* We found nothing other than ASCII. There's nothing to do. */ | |
d46c5b12 | 3437 | return 0; |
4ed46869 | 3438 | |
8a8147d6 | 3439 | c = *src; |
4ed46869 KH |
3440 | /* The text seems to be encoded in some multilingual coding system. |
3441 | Now, try to find in which coding system the text is encoded. */ | |
3442 | if (c < 0x80) | |
bcf26d6a KH |
3443 | { |
3444 | /* i.e. (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) */ | |
3445 | /* C is an ISO2022 specific control code of C0. */ | |
3446 | mask = detect_coding_iso2022 (src, src_end); | |
1b2af4b0 | 3447 | if (mask == 0) |
d46c5b12 KH |
3448 | { |
3449 | /* No valid ISO2022 code follows C. Try again. */ | |
3450 | src++; | |
66cfb530 KH |
3451 | if (c == ISO_CODE_ESC) |
3452 | ascii_skip_code[ISO_CODE_ESC] = 1; | |
3453 | else | |
3454 | ascii_skip_code[ISO_CODE_SO] = ascii_skip_code[ISO_CODE_SI] = 1; | |
d46c5b12 KH |
3455 | goto label_loop_detect_coding; |
3456 | } | |
3457 | if (priorities) | |
fa42c37f KH |
3458 | { |
3459 | for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++) | |
3460 | { | |
3461 | if (mask & priorities[i]) | |
3462 | return priorities[i]; | |
3463 | } | |
3464 | return CODING_CATEGORY_MASK_RAW_TEXT; | |
3465 | } | |
bcf26d6a | 3466 | } |
d46c5b12 | 3467 | else |
c4825358 | 3468 | { |
d46c5b12 | 3469 | int try; |
4ed46869 | 3470 | |
d46c5b12 KH |
3471 | if (c < 0xA0) |
3472 | { | |
3473 | /* C is the first byte of SJIS character code, | |
fa42c37f KH |
3474 | or a leading-code of Emacs' internal format (emacs-mule), |
3475 | or the first byte of UTF-16. */ | |
3476 | try = (CODING_CATEGORY_MASK_SJIS | |
3477 | | CODING_CATEGORY_MASK_EMACS_MULE | |
3478 | | CODING_CATEGORY_MASK_UTF_16_BE | |
3479 | | CODING_CATEGORY_MASK_UTF_16_LE); | |
d46c5b12 KH |
3480 | |
3481 | /* Or, if C is a special latin extra code, | |
3482 | or is an ISO2022 specific control code of C1 (SS2 or SS3), | |
3483 | or is an ISO2022 control-sequence-introducer (CSI), | |
3484 | we should also consider the possibility of ISO2022 codings. */ | |
3485 | if ((VECTORP (Vlatin_extra_code_table) | |
3486 | && !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
3487 | || (c == ISO_CODE_SS2 || c == ISO_CODE_SS3) | |
3488 | || (c == ISO_CODE_CSI | |
3489 | && (src < src_end | |
3490 | && (*src == ']' | |
3491 | || ((*src == '0' || *src == '1' || *src == '2') | |
3492 | && src + 1 < src_end | |
3493 | && src[1] == ']'))))) | |
3494 | try |= (CODING_CATEGORY_MASK_ISO_8_ELSE | |
3495 | | CODING_CATEGORY_MASK_ISO_8BIT); | |
3496 | } | |
c4825358 | 3497 | else |
d46c5b12 KH |
3498 | /* C is a character of ISO2022 in graphic plane right, |
3499 | or a SJIS's 1-byte character code (i.e. JISX0201), | |
fa42c37f KH |
3500 | or the first byte of BIG5's 2-byte code, |
3501 | or the first byte of UTF-8/16. */ | |
d46c5b12 KH |
3502 | try = (CODING_CATEGORY_MASK_ISO_8_ELSE |
3503 | | CODING_CATEGORY_MASK_ISO_8BIT | |
3504 | | CODING_CATEGORY_MASK_SJIS | |
fa42c37f KH |
3505 | | CODING_CATEGORY_MASK_BIG5 |
3506 | | CODING_CATEGORY_MASK_UTF_8 | |
3507 | | CODING_CATEGORY_MASK_UTF_16_BE | |
3508 | | CODING_CATEGORY_MASK_UTF_16_LE); | |
d46c5b12 | 3509 | |
1397dc18 KH |
3510 | /* Or, we may have to consider the possibility of CCL. */ |
3511 | if (coding_system_table[CODING_CATEGORY_IDX_CCL] | |
3512 | && (coding_system_table[CODING_CATEGORY_IDX_CCL] | |
3513 | ->spec.ccl.valid_codes)[c]) | |
3514 | try |= CODING_CATEGORY_MASK_CCL; | |
3515 | ||
d46c5b12 | 3516 | mask = 0; |
fa42c37f | 3517 | utf16_examined_p = iso2022_examined_p = 0; |
d46c5b12 KH |
3518 | if (priorities) |
3519 | { | |
3520 | for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++) | |
3521 | { | |
fa42c37f KH |
3522 | if (!iso2022_examined_p |
3523 | && (priorities[i] & try & CODING_CATEGORY_MASK_ISO)) | |
3524 | { | |
3525 | mask |= detect_coding_iso2022 (src, src_end); | |
3526 | iso2022_examined_p = 1; | |
3527 | } | |
5ab13dd0 | 3528 | else if (priorities[i] & try & CODING_CATEGORY_MASK_SJIS) |
fa42c37f KH |
3529 | mask |= detect_coding_sjis (src, src_end); |
3530 | else if (priorities[i] & try & CODING_CATEGORY_MASK_UTF_8) | |
3531 | mask |= detect_coding_utf_8 (src, src_end); | |
3532 | else if (!utf16_examined_p | |
3533 | && (priorities[i] & try & | |
3534 | CODING_CATEGORY_MASK_UTF_16_BE_LE)) | |
3535 | { | |
3536 | mask |= detect_coding_utf_16 (src, src_end); | |
3537 | utf16_examined_p = 1; | |
3538 | } | |
5ab13dd0 | 3539 | else if (priorities[i] & try & CODING_CATEGORY_MASK_BIG5) |
fa42c37f | 3540 | mask |= detect_coding_big5 (src, src_end); |
5ab13dd0 | 3541 | else if (priorities[i] & try & CODING_CATEGORY_MASK_EMACS_MULE) |
fa42c37f | 3542 | mask |= detect_coding_emacs_mule (src, src_end); |
89fa8b36 | 3543 | else if (priorities[i] & try & CODING_CATEGORY_MASK_CCL) |
fa42c37f | 3544 | mask |= detect_coding_ccl (src, src_end); |
5ab13dd0 | 3545 | else if (priorities[i] & CODING_CATEGORY_MASK_RAW_TEXT) |
fa42c37f | 3546 | mask |= CODING_CATEGORY_MASK_RAW_TEXT; |
5ab13dd0 | 3547 | else if (priorities[i] & CODING_CATEGORY_MASK_BINARY) |
fa42c37f KH |
3548 | mask |= CODING_CATEGORY_MASK_BINARY; |
3549 | if (mask & priorities[i]) | |
3550 | return priorities[i]; | |
d46c5b12 KH |
3551 | } |
3552 | return CODING_CATEGORY_MASK_RAW_TEXT; | |
3553 | } | |
3554 | if (try & CODING_CATEGORY_MASK_ISO) | |
3555 | mask |= detect_coding_iso2022 (src, src_end); | |
3556 | if (try & CODING_CATEGORY_MASK_SJIS) | |
3557 | mask |= detect_coding_sjis (src, src_end); | |
3558 | if (try & CODING_CATEGORY_MASK_BIG5) | |
3559 | mask |= detect_coding_big5 (src, src_end); | |
fa42c37f KH |
3560 | if (try & CODING_CATEGORY_MASK_UTF_8) |
3561 | mask |= detect_coding_utf_8 (src, src_end); | |
3562 | if (try & CODING_CATEGORY_MASK_UTF_16_BE_LE) | |
3563 | mask |= detect_coding_utf_16 (src, src_end); | |
d46c5b12 | 3564 | if (try & CODING_CATEGORY_MASK_EMACS_MULE) |
1397dc18 KH |
3565 | mask |= detect_coding_emacs_mule (src, src_end); |
3566 | if (try & CODING_CATEGORY_MASK_CCL) | |
3567 | mask |= detect_coding_ccl (src, src_end); | |
c4825358 | 3568 | } |
5ab13dd0 | 3569 | return (mask | CODING_CATEGORY_MASK_RAW_TEXT | CODING_CATEGORY_MASK_BINARY); |
4ed46869 KH |
3570 | } |
3571 | ||
3572 | /* Detect how a text of length SRC_BYTES pointed by SRC is encoded. | |
3573 | The information of the detected coding system is set in CODING. */ | |
3574 | ||
3575 | void | |
3576 | detect_coding (coding, src, src_bytes) | |
3577 | struct coding_system *coding; | |
3578 | unsigned char *src; | |
3579 | int src_bytes; | |
3580 | { | |
d46c5b12 KH |
3581 | unsigned int idx; |
3582 | int skip, mask, i; | |
84d60297 | 3583 | Lisp_Object val; |
4ed46869 | 3584 | |
84d60297 | 3585 | val = Vcoding_category_list; |
66cfb530 | 3586 | mask = detect_coding_mask (src, src_bytes, coding_priorities, &skip); |
d46c5b12 | 3587 | coding->heading_ascii = skip; |
4ed46869 | 3588 | |
d46c5b12 KH |
3589 | if (!mask) return; |
3590 | ||
3591 | /* We found a single coding system of the highest priority in MASK. */ | |
3592 | idx = 0; | |
3593 | while (mask && ! (mask & 1)) mask >>= 1, idx++; | |
3594 | if (! mask) | |
3595 | idx = CODING_CATEGORY_IDX_RAW_TEXT; | |
4ed46869 | 3596 | |
d46c5b12 KH |
3597 | val = XSYMBOL (XVECTOR (Vcoding_category_table)->contents[idx])->value; |
3598 | ||
3599 | if (coding->eol_type != CODING_EOL_UNDECIDED) | |
27901516 | 3600 | { |
84d60297 | 3601 | Lisp_Object tmp; |
d46c5b12 | 3602 | |
84d60297 | 3603 | tmp = Fget (val, Qeol_type); |
d46c5b12 KH |
3604 | if (VECTORP (tmp)) |
3605 | val = XVECTOR (tmp)->contents[coding->eol_type]; | |
4ed46869 | 3606 | } |
b73bfc1c KH |
3607 | |
3608 | /* Setup this new coding system while preserving some slots. */ | |
3609 | { | |
3610 | int src_multibyte = coding->src_multibyte; | |
3611 | int dst_multibyte = coding->dst_multibyte; | |
3612 | ||
3613 | setup_coding_system (val, coding); | |
3614 | coding->src_multibyte = src_multibyte; | |
3615 | coding->dst_multibyte = dst_multibyte; | |
3616 | coding->heading_ascii = skip; | |
3617 | } | |
4ed46869 KH |
3618 | } |
3619 | ||
d46c5b12 KH |
3620 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
3621 | SOURCE is encoded. Return one of CODING_EOL_LF, CODING_EOL_CRLF, | |
3622 | CODING_EOL_CR, and CODING_EOL_UNDECIDED. | |
3623 | ||
3624 | How many non-eol characters are at the head is returned as *SKIP. */ | |
4ed46869 | 3625 | |
bc4bc72a RS |
3626 | #define MAX_EOL_CHECK_COUNT 3 |
3627 | ||
d46c5b12 KH |
3628 | static int |
3629 | detect_eol_type (source, src_bytes, skip) | |
3630 | unsigned char *source; | |
3631 | int src_bytes, *skip; | |
4ed46869 | 3632 | { |
d46c5b12 | 3633 | unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 3634 | unsigned char c; |
bc4bc72a RS |
3635 | int total = 0; /* How many end-of-lines are found so far. */ |
3636 | int eol_type = CODING_EOL_UNDECIDED; | |
3637 | int this_eol_type; | |
4ed46869 | 3638 | |
d46c5b12 KH |
3639 | *skip = 0; |
3640 | ||
bc4bc72a | 3641 | while (src < src_end && total < MAX_EOL_CHECK_COUNT) |
4ed46869 KH |
3642 | { |
3643 | c = *src++; | |
bc4bc72a | 3644 | if (c == '\n' || c == '\r') |
4ed46869 | 3645 | { |
d46c5b12 KH |
3646 | if (*skip == 0) |
3647 | *skip = src - 1 - source; | |
bc4bc72a RS |
3648 | total++; |
3649 | if (c == '\n') | |
3650 | this_eol_type = CODING_EOL_LF; | |
3651 | else if (src >= src_end || *src != '\n') | |
3652 | this_eol_type = CODING_EOL_CR; | |
4ed46869 | 3653 | else |
bc4bc72a RS |
3654 | this_eol_type = CODING_EOL_CRLF, src++; |
3655 | ||
3656 | if (eol_type == CODING_EOL_UNDECIDED) | |
3657 | /* This is the first end-of-line. */ | |
3658 | eol_type = this_eol_type; | |
3659 | else if (eol_type != this_eol_type) | |
d46c5b12 KH |
3660 | { |
3661 | /* The found type is different from what found before. */ | |
3662 | eol_type = CODING_EOL_INCONSISTENT; | |
3663 | break; | |
3664 | } | |
4ed46869 KH |
3665 | } |
3666 | } | |
bc4bc72a | 3667 | |
d46c5b12 KH |
3668 | if (*skip == 0) |
3669 | *skip = src_end - source; | |
85a02ca4 | 3670 | return eol_type; |
4ed46869 KH |
3671 | } |
3672 | ||
fa42c37f KH |
3673 | /* Like detect_eol_type, but detect EOL type in 2-octet |
3674 | big-endian/little-endian format for coding systems utf-16-be and | |
3675 | utf-16-le. */ | |
3676 | ||
3677 | static int | |
3678 | detect_eol_type_in_2_octet_form (source, src_bytes, skip, big_endian_p) | |
3679 | unsigned char *source; | |
3680 | int src_bytes, *skip; | |
3681 | { | |
3682 | unsigned char *src = source, *src_end = src + src_bytes; | |
3683 | unsigned int c1, c2; | |
3684 | int total = 0; /* How many end-of-lines are found so far. */ | |
3685 | int eol_type = CODING_EOL_UNDECIDED; | |
3686 | int this_eol_type; | |
3687 | int msb, lsb; | |
3688 | ||
3689 | if (big_endian_p) | |
3690 | msb = 0, lsb = 1; | |
3691 | else | |
3692 | msb = 1, lsb = 0; | |
3693 | ||
3694 | *skip = 0; | |
3695 | ||
3696 | while ((src + 1) < src_end && total < MAX_EOL_CHECK_COUNT) | |
3697 | { | |
3698 | c1 = (src[msb] << 8) | (src[lsb]); | |
3699 | src += 2; | |
3700 | ||
3701 | if (c1 == '\n' || c1 == '\r') | |
3702 | { | |
3703 | if (*skip == 0) | |
3704 | *skip = src - 2 - source; | |
3705 | total++; | |
3706 | if (c1 == '\n') | |
3707 | { | |
3708 | this_eol_type = CODING_EOL_LF; | |
3709 | } | |
3710 | else | |
3711 | { | |
3712 | if ((src + 1) >= src_end) | |
3713 | { | |
3714 | this_eol_type = CODING_EOL_CR; | |
3715 | } | |
3716 | else | |
3717 | { | |
3718 | c2 = (src[msb] << 8) | (src[lsb]); | |
3719 | if (c2 == '\n') | |
3720 | this_eol_type = CODING_EOL_CRLF, src += 2; | |
3721 | else | |
3722 | this_eol_type = CODING_EOL_CR; | |
3723 | } | |
3724 | } | |
3725 | ||
3726 | if (eol_type == CODING_EOL_UNDECIDED) | |
3727 | /* This is the first end-of-line. */ | |
3728 | eol_type = this_eol_type; | |
3729 | else if (eol_type != this_eol_type) | |
3730 | { | |
3731 | /* The found type is different from what found before. */ | |
3732 | eol_type = CODING_EOL_INCONSISTENT; | |
3733 | break; | |
3734 | } | |
3735 | } | |
3736 | } | |
3737 | ||
3738 | if (*skip == 0) | |
3739 | *skip = src_end - source; | |
3740 | return eol_type; | |
3741 | } | |
3742 | ||
4ed46869 KH |
3743 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by SRC |
3744 | is encoded. If it detects an appropriate format of end-of-line, it | |
3745 | sets the information in *CODING. */ | |
3746 | ||
3747 | void | |
3748 | detect_eol (coding, src, src_bytes) | |
3749 | struct coding_system *coding; | |
3750 | unsigned char *src; | |
3751 | int src_bytes; | |
3752 | { | |
4608c386 | 3753 | Lisp_Object val; |
d46c5b12 | 3754 | int skip; |
fa42c37f KH |
3755 | int eol_type; |
3756 | ||
3757 | switch (coding->category_idx) | |
3758 | { | |
3759 | case CODING_CATEGORY_IDX_UTF_16_BE: | |
3760 | eol_type = detect_eol_type_in_2_octet_form (src, src_bytes, &skip, 1); | |
3761 | break; | |
3762 | case CODING_CATEGORY_IDX_UTF_16_LE: | |
3763 | eol_type = detect_eol_type_in_2_octet_form (src, src_bytes, &skip, 0); | |
3764 | break; | |
3765 | default: | |
3766 | eol_type = detect_eol_type (src, src_bytes, &skip); | |
3767 | break; | |
3768 | } | |
d46c5b12 KH |
3769 | |
3770 | if (coding->heading_ascii > skip) | |
3771 | coding->heading_ascii = skip; | |
3772 | else | |
3773 | skip = coding->heading_ascii; | |
4ed46869 | 3774 | |
0ef69138 | 3775 | if (eol_type == CODING_EOL_UNDECIDED) |
4ed46869 | 3776 | return; |
27901516 KH |
3777 | if (eol_type == CODING_EOL_INCONSISTENT) |
3778 | { | |
3779 | #if 0 | |
3780 | /* This code is suppressed until we find a better way to | |
992f23f2 | 3781 | distinguish raw text file and binary file. */ |
27901516 KH |
3782 | |
3783 | /* If we have already detected that the coding is raw-text, the | |
3784 | coding should actually be no-conversion. */ | |
3785 | if (coding->type == coding_type_raw_text) | |
3786 | { | |
3787 | setup_coding_system (Qno_conversion, coding); | |
3788 | return; | |
3789 | } | |
3790 | /* Else, let's decode only text code anyway. */ | |
3791 | #endif /* 0 */ | |
1b2af4b0 | 3792 | eol_type = CODING_EOL_LF; |
27901516 KH |
3793 | } |
3794 | ||
4608c386 | 3795 | val = Fget (coding->symbol, Qeol_type); |
4ed46869 | 3796 | if (VECTORP (val) && XVECTOR (val)->size == 3) |
d46c5b12 | 3797 | { |
b73bfc1c KH |
3798 | int src_multibyte = coding->src_multibyte; |
3799 | int dst_multibyte = coding->dst_multibyte; | |
3800 | ||
d46c5b12 | 3801 | setup_coding_system (XVECTOR (val)->contents[eol_type], coding); |
b73bfc1c KH |
3802 | coding->src_multibyte = src_multibyte; |
3803 | coding->dst_multibyte = dst_multibyte; | |
d46c5b12 KH |
3804 | coding->heading_ascii = skip; |
3805 | } | |
3806 | } | |
3807 | ||
3808 | #define CONVERSION_BUFFER_EXTRA_ROOM 256 | |
3809 | ||
b73bfc1c KH |
3810 | #define DECODING_BUFFER_MAG(coding) \ |
3811 | (coding->type == coding_type_iso2022 \ | |
3812 | ? 3 \ | |
3813 | : (coding->type == coding_type_ccl \ | |
3814 | ? coding->spec.ccl.decoder.buf_magnification \ | |
3815 | : 2)) | |
d46c5b12 KH |
3816 | |
3817 | /* Return maximum size (bytes) of a buffer enough for decoding | |
3818 | SRC_BYTES of text encoded in CODING. */ | |
3819 | ||
3820 | int | |
3821 | decoding_buffer_size (coding, src_bytes) | |
3822 | struct coding_system *coding; | |
3823 | int src_bytes; | |
3824 | { | |
3825 | return (src_bytes * DECODING_BUFFER_MAG (coding) | |
3826 | + CONVERSION_BUFFER_EXTRA_ROOM); | |
3827 | } | |
3828 | ||
3829 | /* Return maximum size (bytes) of a buffer enough for encoding | |
3830 | SRC_BYTES of text to CODING. */ | |
3831 | ||
3832 | int | |
3833 | encoding_buffer_size (coding, src_bytes) | |
3834 | struct coding_system *coding; | |
3835 | int src_bytes; | |
3836 | { | |
3837 | int magnification; | |
3838 | ||
3839 | if (coding->type == coding_type_ccl) | |
3840 | magnification = coding->spec.ccl.encoder.buf_magnification; | |
b73bfc1c | 3841 | else if (CODING_REQUIRE_ENCODING (coding)) |
d46c5b12 | 3842 | magnification = 3; |
b73bfc1c KH |
3843 | else |
3844 | magnification = 1; | |
d46c5b12 KH |
3845 | |
3846 | return (src_bytes * magnification + CONVERSION_BUFFER_EXTRA_ROOM); | |
3847 | } | |
3848 | ||
3849 | #ifndef MINIMUM_CONVERSION_BUFFER_SIZE | |
3850 | #define MINIMUM_CONVERSION_BUFFER_SIZE 1024 | |
3851 | #endif | |
3852 | ||
3853 | char *conversion_buffer; | |
3854 | int conversion_buffer_size; | |
3855 | ||
3856 | /* Return a pointer to a SIZE bytes of buffer to be used for encoding | |
3857 | or decoding. Sufficient memory is allocated automatically. If we | |
3858 | run out of memory, return NULL. */ | |
3859 | ||
3860 | char * | |
3861 | get_conversion_buffer (size) | |
3862 | int size; | |
3863 | { | |
3864 | if (size > conversion_buffer_size) | |
3865 | { | |
3866 | char *buf; | |
3867 | int real_size = conversion_buffer_size * 2; | |
3868 | ||
3869 | while (real_size < size) real_size *= 2; | |
3870 | buf = (char *) xmalloc (real_size); | |
3871 | xfree (conversion_buffer); | |
3872 | conversion_buffer = buf; | |
3873 | conversion_buffer_size = real_size; | |
3874 | } | |
3875 | return conversion_buffer; | |
3876 | } | |
3877 | ||
3878 | int | |
3879 | ccl_coding_driver (coding, source, destination, src_bytes, dst_bytes, encodep) | |
3880 | struct coding_system *coding; | |
3881 | unsigned char *source, *destination; | |
3882 | int src_bytes, dst_bytes, encodep; | |
3883 | { | |
3884 | struct ccl_program *ccl | |
3885 | = encodep ? &coding->spec.ccl.encoder : &coding->spec.ccl.decoder; | |
3886 | int result; | |
3887 | ||
ae9ff118 | 3888 | ccl->last_block = coding->mode & CODING_MODE_LAST_BLOCK; |
7b179c2d | 3889 | |
d46c5b12 KH |
3890 | coding->produced = ccl_driver (ccl, source, destination, |
3891 | src_bytes, dst_bytes, &(coding->consumed)); | |
b73bfc1c KH |
3892 | if (encodep) |
3893 | coding->produced_char = coding->produced; | |
3894 | else | |
3895 | { | |
3896 | int bytes | |
3897 | = dst_bytes ? dst_bytes : source + coding->consumed - destination; | |
3898 | coding->produced = str_as_multibyte (destination, bytes, | |
3899 | coding->produced, | |
3900 | &(coding->produced_char)); | |
3901 | } | |
69f76525 | 3902 | |
d46c5b12 KH |
3903 | switch (ccl->status) |
3904 | { | |
3905 | case CCL_STAT_SUSPEND_BY_SRC: | |
3906 | result = CODING_FINISH_INSUFFICIENT_SRC; | |
3907 | break; | |
3908 | case CCL_STAT_SUSPEND_BY_DST: | |
3909 | result = CODING_FINISH_INSUFFICIENT_DST; | |
3910 | break; | |
9864ebce KH |
3911 | case CCL_STAT_QUIT: |
3912 | case CCL_STAT_INVALID_CMD: | |
3913 | result = CODING_FINISH_INTERRUPT; | |
3914 | break; | |
d46c5b12 KH |
3915 | default: |
3916 | result = CODING_FINISH_NORMAL; | |
3917 | break; | |
3918 | } | |
3919 | return result; | |
4ed46869 KH |
3920 | } |
3921 | ||
3922 | /* See "GENERAL NOTES about `decode_coding_XXX ()' functions". Before | |
3923 | decoding, it may detect coding system and format of end-of-line if | |
b73bfc1c KH |
3924 | those are not yet decided. The source should be unibyte, the |
3925 | result is multibyte if CODING->dst_multibyte is nonzero, else | |
3926 | unibyte. */ | |
4ed46869 KH |
3927 | |
3928 | int | |
d46c5b12 | 3929 | decode_coding (coding, source, destination, src_bytes, dst_bytes) |
4ed46869 KH |
3930 | struct coding_system *coding; |
3931 | unsigned char *source, *destination; | |
3932 | int src_bytes, dst_bytes; | |
4ed46869 | 3933 | { |
0ef69138 | 3934 | if (coding->type == coding_type_undecided) |
4ed46869 KH |
3935 | detect_coding (coding, source, src_bytes); |
3936 | ||
0ef69138 | 3937 | if (coding->eol_type == CODING_EOL_UNDECIDED) |
4ed46869 KH |
3938 | detect_eol (coding, source, src_bytes); |
3939 | ||
b73bfc1c KH |
3940 | coding->produced = coding->produced_char = 0; |
3941 | coding->consumed = coding->consumed_char = 0; | |
3942 | coding->errors = 0; | |
3943 | coding->result = CODING_FINISH_NORMAL; | |
3944 | ||
4ed46869 KH |
3945 | switch (coding->type) |
3946 | { | |
4ed46869 | 3947 | case coding_type_sjis: |
b73bfc1c KH |
3948 | decode_coding_sjis_big5 (coding, source, destination, |
3949 | src_bytes, dst_bytes, 1); | |
4ed46869 KH |
3950 | break; |
3951 | ||
3952 | case coding_type_iso2022: | |
b73bfc1c KH |
3953 | decode_coding_iso2022 (coding, source, destination, |
3954 | src_bytes, dst_bytes); | |
4ed46869 KH |
3955 | break; |
3956 | ||
3957 | case coding_type_big5: | |
b73bfc1c KH |
3958 | decode_coding_sjis_big5 (coding, source, destination, |
3959 | src_bytes, dst_bytes, 0); | |
3960 | break; | |
3961 | ||
3962 | case coding_type_emacs_mule: | |
3963 | decode_coding_emacs_mule (coding, source, destination, | |
3964 | src_bytes, dst_bytes); | |
4ed46869 KH |
3965 | break; |
3966 | ||
3967 | case coding_type_ccl: | |
b73bfc1c KH |
3968 | ccl_coding_driver (coding, source, destination, |
3969 | src_bytes, dst_bytes, 0); | |
d46c5b12 KH |
3970 | break; |
3971 | ||
b73bfc1c KH |
3972 | default: |
3973 | decode_eol (coding, source, destination, src_bytes, dst_bytes); | |
3974 | } | |
3975 | ||
3976 | if (coding->result == CODING_FINISH_INSUFFICIENT_SRC | |
3977 | && coding->consumed == src_bytes) | |
3978 | coding->result = CODING_FINISH_NORMAL; | |
3979 | ||
3980 | if (coding->mode & CODING_MODE_LAST_BLOCK | |
3981 | && coding->result == CODING_FINISH_INSUFFICIENT_SRC) | |
3982 | { | |
3983 | unsigned char *src = source + coding->consumed; | |
3984 | unsigned char *dst = destination + coding->produced; | |
3985 | ||
3986 | src_bytes -= coding->consumed; | |
3987 | coding->errors++; | |
3988 | if (COMPOSING_P (coding)) | |
3989 | DECODE_COMPOSITION_END ('1'); | |
3990 | while (src_bytes--) | |
d46c5b12 | 3991 | { |
b73bfc1c KH |
3992 | int c = *src++; |
3993 | dst += CHAR_STRING (c, dst); | |
3994 | coding->produced_char++; | |
d46c5b12 | 3995 | } |
b73bfc1c KH |
3996 | coding->consumed = coding->consumed_char = src - source; |
3997 | coding->produced = dst - destination; | |
4ed46869 KH |
3998 | } |
3999 | ||
b73bfc1c KH |
4000 | if (!coding->dst_multibyte) |
4001 | { | |
4002 | coding->produced = str_as_unibyte (destination, coding->produced); | |
4003 | coding->produced_char = coding->produced; | |
4004 | } | |
4ed46869 | 4005 | |
b73bfc1c KH |
4006 | return coding->result; |
4007 | } | |
52d41803 | 4008 | |
b73bfc1c KH |
4009 | /* See "GENERAL NOTES about `encode_coding_XXX ()' functions". The |
4010 | multibyteness of the source is CODING->src_multibyte, the | |
4011 | multibyteness of the result is always unibyte. */ | |
4ed46869 KH |
4012 | |
4013 | int | |
d46c5b12 | 4014 | encode_coding (coding, source, destination, src_bytes, dst_bytes) |
4ed46869 KH |
4015 | struct coding_system *coding; |
4016 | unsigned char *source, *destination; | |
4017 | int src_bytes, dst_bytes; | |
4ed46869 | 4018 | { |
b73bfc1c KH |
4019 | coding->produced = coding->produced_char = 0; |
4020 | coding->consumed = coding->consumed_char = 0; | |
4021 | coding->errors = 0; | |
4022 | coding->result = CODING_FINISH_NORMAL; | |
4ed46869 | 4023 | |
d46c5b12 KH |
4024 | switch (coding->type) |
4025 | { | |
4ed46869 | 4026 | case coding_type_sjis: |
b73bfc1c KH |
4027 | encode_coding_sjis_big5 (coding, source, destination, |
4028 | src_bytes, dst_bytes, 1); | |
4ed46869 KH |
4029 | break; |
4030 | ||
4031 | case coding_type_iso2022: | |
b73bfc1c KH |
4032 | encode_coding_iso2022 (coding, source, destination, |
4033 | src_bytes, dst_bytes); | |
4ed46869 KH |
4034 | break; |
4035 | ||
4036 | case coding_type_big5: | |
b73bfc1c KH |
4037 | encode_coding_sjis_big5 (coding, source, destination, |
4038 | src_bytes, dst_bytes, 0); | |
4039 | break; | |
4040 | ||
4041 | case coding_type_emacs_mule: | |
4042 | encode_coding_emacs_mule (coding, source, destination, | |
4043 | src_bytes, dst_bytes); | |
4ed46869 KH |
4044 | break; |
4045 | ||
4046 | case coding_type_ccl: | |
b73bfc1c KH |
4047 | ccl_coding_driver (coding, source, destination, |
4048 | src_bytes, dst_bytes, 1); | |
d46c5b12 KH |
4049 | break; |
4050 | ||
b73bfc1c KH |
4051 | default: |
4052 | encode_eol (coding, source, destination, src_bytes, dst_bytes); | |
4053 | } | |
4054 | ||
4055 | if (coding->result == CODING_FINISH_INSUFFICIENT_SRC | |
4056 | && coding->consumed == src_bytes) | |
4057 | coding->result = CODING_FINISH_NORMAL; | |
4058 | ||
4059 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
4060 | { | |
4061 | unsigned char *src = source + coding->consumed; | |
4062 | unsigned char *src_end = src + src_bytes; | |
4063 | unsigned char *dst = destination + coding->produced; | |
4064 | ||
4065 | if (coding->type == coding_type_iso2022) | |
4066 | ENCODE_RESET_PLANE_AND_REGISTER; | |
4067 | if (COMPOSING_P (coding)) | |
4068 | *dst++ = ISO_CODE_ESC, *dst++ = '1'; | |
4069 | if (coding->consumed < src_bytes) | |
d46c5b12 | 4070 | { |
b73bfc1c KH |
4071 | int len = src_bytes - coding->consumed; |
4072 | ||
4073 | BCOPY_SHORT (source + coding->consumed, dst, len); | |
4074 | if (coding->src_multibyte) | |
4075 | len = str_as_unibyte (dst, len); | |
4076 | dst += len; | |
4077 | coding->consumed = src_bytes; | |
d46c5b12 | 4078 | } |
b73bfc1c | 4079 | coding->produced = coding->produced_char = dst - destination; |
4ed46869 KH |
4080 | } |
4081 | ||
b73bfc1c | 4082 | return coding->result; |
4ed46869 KH |
4083 | } |
4084 | ||
fb88bf2d KH |
4085 | /* Scan text in the region between *BEG and *END (byte positions), |
4086 | skip characters which we don't have to decode by coding system | |
4087 | CODING at the head and tail, then set *BEG and *END to the region | |
4088 | of the text we actually have to convert. The caller should move | |
b73bfc1c KH |
4089 | the gap out of the region in advance if the region is from a |
4090 | buffer. | |
4ed46869 | 4091 | |
d46c5b12 KH |
4092 | If STR is not NULL, *BEG and *END are indices into STR. */ |
4093 | ||
4094 | static void | |
4095 | shrink_decoding_region (beg, end, coding, str) | |
4096 | int *beg, *end; | |
4097 | struct coding_system *coding; | |
4098 | unsigned char *str; | |
4099 | { | |
fb88bf2d | 4100 | unsigned char *begp_orig, *begp, *endp_orig, *endp, c; |
d46c5b12 | 4101 | int eol_conversion; |
88993dfd | 4102 | Lisp_Object translation_table; |
d46c5b12 KH |
4103 | |
4104 | if (coding->type == coding_type_ccl | |
4105 | || coding->type == coding_type_undecided | |
b73bfc1c KH |
4106 | || coding->eol_type != CODING_EOL_LF |
4107 | || !NILP (coding->post_read_conversion) | |
4108 | || coding->composing != COMPOSITION_DISABLED) | |
d46c5b12 KH |
4109 | { |
4110 | /* We can't skip any data. */ | |
4111 | return; | |
4112 | } | |
b73bfc1c KH |
4113 | if (coding->type == coding_type_no_conversion |
4114 | || coding->type == coding_type_raw_text | |
4115 | || coding->type == coding_type_emacs_mule) | |
d46c5b12 | 4116 | { |
fb88bf2d KH |
4117 | /* We need no conversion, but don't have to skip any data here. |
4118 | Decoding routine handles them effectively anyway. */ | |
d46c5b12 KH |
4119 | return; |
4120 | } | |
4121 | ||
88993dfd KH |
4122 | translation_table = coding->translation_table_for_decode; |
4123 | if (NILP (translation_table) && !NILP (Venable_character_translation)) | |
4124 | translation_table = Vstandard_translation_table_for_decode; | |
4125 | if (CHAR_TABLE_P (translation_table)) | |
4126 | { | |
4127 | int i; | |
4128 | for (i = 0; i < 128; i++) | |
4129 | if (!NILP (CHAR_TABLE_REF (translation_table, i))) | |
4130 | break; | |
4131 | if (i < 128) | |
fa46990e | 4132 | /* Some ASCII character should be translated. We give up |
88993dfd KH |
4133 | shrinking. */ |
4134 | return; | |
4135 | } | |
4136 | ||
b73bfc1c | 4137 | if (coding->heading_ascii >= 0) |
d46c5b12 KH |
4138 | /* Detection routine has already found how much we can skip at the |
4139 | head. */ | |
4140 | *beg += coding->heading_ascii; | |
4141 | ||
4142 | if (str) | |
4143 | { | |
4144 | begp_orig = begp = str + *beg; | |
4145 | endp_orig = endp = str + *end; | |
4146 | } | |
4147 | else | |
4148 | { | |
fb88bf2d | 4149 | begp_orig = begp = BYTE_POS_ADDR (*beg); |
d46c5b12 KH |
4150 | endp_orig = endp = begp + *end - *beg; |
4151 | } | |
4152 | ||
fa46990e DL |
4153 | eol_conversion = (coding->eol_type == CODING_EOL_CR |
4154 | || coding->eol_type == CODING_EOL_CRLF); | |
4155 | ||
d46c5b12 KH |
4156 | switch (coding->type) |
4157 | { | |
d46c5b12 KH |
4158 | case coding_type_sjis: |
4159 | case coding_type_big5: | |
4160 | /* We can skip all ASCII characters at the head. */ | |
4161 | if (coding->heading_ascii < 0) | |
4162 | { | |
4163 | if (eol_conversion) | |
de9d083c | 4164 | while (begp < endp && *begp < 0x80 && *begp != '\r') begp++; |
d46c5b12 KH |
4165 | else |
4166 | while (begp < endp && *begp < 0x80) begp++; | |
4167 | } | |
4168 | /* We can skip all ASCII characters at the tail except for the | |
4169 | second byte of SJIS or BIG5 code. */ | |
4170 | if (eol_conversion) | |
de9d083c | 4171 | while (begp < endp && endp[-1] < 0x80 && endp[-1] != '\r') endp--; |
d46c5b12 KH |
4172 | else |
4173 | while (begp < endp && endp[-1] < 0x80) endp--; | |
ee59c65f RS |
4174 | /* Do not consider LF as ascii if preceded by CR, since that |
4175 | confuses eol decoding. */ | |
4176 | if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n') | |
4177 | endp++; | |
d46c5b12 KH |
4178 | if (begp < endp && endp < endp_orig && endp[-1] >= 0x80) |
4179 | endp++; | |
4180 | break; | |
4181 | ||
b73bfc1c | 4182 | case coding_type_iso2022: |
622fece5 KH |
4183 | if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, 0) != CHARSET_ASCII) |
4184 | /* We can't skip any data. */ | |
4185 | break; | |
d46c5b12 KH |
4186 | if (coding->heading_ascii < 0) |
4187 | { | |
d46c5b12 KH |
4188 | /* We can skip all ASCII characters at the head except for a |
4189 | few control codes. */ | |
4190 | while (begp < endp && (c = *begp) < 0x80 | |
4191 | && c != ISO_CODE_CR && c != ISO_CODE_SO | |
4192 | && c != ISO_CODE_SI && c != ISO_CODE_ESC | |
4193 | && (!eol_conversion || c != ISO_CODE_LF)) | |
4194 | begp++; | |
4195 | } | |
4196 | switch (coding->category_idx) | |
4197 | { | |
4198 | case CODING_CATEGORY_IDX_ISO_8_1: | |
4199 | case CODING_CATEGORY_IDX_ISO_8_2: | |
4200 | /* We can skip all ASCII characters at the tail. */ | |
4201 | if (eol_conversion) | |
de9d083c | 4202 | while (begp < endp && (c = endp[-1]) < 0x80 && c != '\r') endp--; |
d46c5b12 KH |
4203 | else |
4204 | while (begp < endp && endp[-1] < 0x80) endp--; | |
ee59c65f RS |
4205 | /* Do not consider LF as ascii if preceded by CR, since that |
4206 | confuses eol decoding. */ | |
4207 | if (begp < endp && endp < endp_orig && endp[-1] == '\r' && endp[0] == '\n') | |
4208 | endp++; | |
d46c5b12 KH |
4209 | break; |
4210 | ||
4211 | case CODING_CATEGORY_IDX_ISO_7: | |
4212 | case CODING_CATEGORY_IDX_ISO_7_TIGHT: | |
de79a6a5 KH |
4213 | { |
4214 | /* We can skip all charactes at the tail except for 8-bit | |
4215 | codes and ESC and the following 2-byte at the tail. */ | |
4216 | unsigned char *eight_bit = NULL; | |
4217 | ||
4218 | if (eol_conversion) | |
4219 | while (begp < endp | |
4220 | && (c = endp[-1]) != ISO_CODE_ESC && c != '\r') | |
4221 | { | |
4222 | if (!eight_bit && c & 0x80) eight_bit = endp; | |
4223 | endp--; | |
4224 | } | |
4225 | else | |
4226 | while (begp < endp | |
4227 | && (c = endp[-1]) != ISO_CODE_ESC) | |
4228 | { | |
4229 | if (!eight_bit && c & 0x80) eight_bit = endp; | |
4230 | endp--; | |
4231 | } | |
4232 | /* Do not consider LF as ascii if preceded by CR, since that | |
4233 | confuses eol decoding. */ | |
4234 | if (begp < endp && endp < endp_orig | |
4235 | && endp[-1] == '\r' && endp[0] == '\n') | |
4236 | endp++; | |
4237 | if (begp < endp && endp[-1] == ISO_CODE_ESC) | |
4238 | { | |
4239 | if (endp + 1 < endp_orig && end[0] == '(' && end[1] == 'B') | |
4240 | /* This is an ASCII designation sequence. We can | |
4241 | surely skip the tail. But, if we have | |
4242 | encountered an 8-bit code, skip only the codes | |
4243 | after that. */ | |
4244 | endp = eight_bit ? eight_bit : endp + 2; | |
4245 | else | |
4246 | /* Hmmm, we can't skip the tail. */ | |
4247 | endp = endp_orig; | |
4248 | } | |
4249 | else if (eight_bit) | |
4250 | endp = eight_bit; | |
4251 | } | |
d46c5b12 | 4252 | } |
b73bfc1c KH |
4253 | break; |
4254 | ||
4255 | default: | |
4256 | abort (); | |
d46c5b12 KH |
4257 | } |
4258 | *beg += begp - begp_orig; | |
4259 | *end += endp - endp_orig; | |
4260 | return; | |
4261 | } | |
4262 | ||
4263 | /* Like shrink_decoding_region but for encoding. */ | |
4264 | ||
4265 | static void | |
4266 | shrink_encoding_region (beg, end, coding, str) | |
4267 | int *beg, *end; | |
4268 | struct coding_system *coding; | |
4269 | unsigned char *str; | |
4270 | { | |
4271 | unsigned char *begp_orig, *begp, *endp_orig, *endp; | |
4272 | int eol_conversion; | |
88993dfd | 4273 | Lisp_Object translation_table; |
d46c5b12 | 4274 | |
b73bfc1c KH |
4275 | if (coding->type == coding_type_ccl |
4276 | || coding->eol_type == CODING_EOL_CRLF | |
4277 | || coding->eol_type == CODING_EOL_CR | |
4278 | || coding->cmp_data && coding->cmp_data->used > 0) | |
d46c5b12 | 4279 | { |
b73bfc1c KH |
4280 | /* We can't skip any data. */ |
4281 | return; | |
4282 | } | |
4283 | if (coding->type == coding_type_no_conversion | |
4284 | || coding->type == coding_type_raw_text | |
4285 | || coding->type == coding_type_emacs_mule | |
4286 | || coding->type == coding_type_undecided) | |
4287 | { | |
4288 | /* We need no conversion, but don't have to skip any data here. | |
4289 | Encoding routine handles them effectively anyway. */ | |
d46c5b12 KH |
4290 | return; |
4291 | } | |
4292 | ||
88993dfd KH |
4293 | translation_table = coding->translation_table_for_encode; |
4294 | if (NILP (translation_table) && !NILP (Venable_character_translation)) | |
4295 | translation_table = Vstandard_translation_table_for_encode; | |
4296 | if (CHAR_TABLE_P (translation_table)) | |
4297 | { | |
4298 | int i; | |
4299 | for (i = 0; i < 128; i++) | |
4300 | if (!NILP (CHAR_TABLE_REF (translation_table, i))) | |
4301 | break; | |
4302 | if (i < 128) | |
4303 | /* Some ASCII character should be tranlsated. We give up | |
4304 | shrinking. */ | |
4305 | return; | |
4306 | } | |
4307 | ||
d46c5b12 KH |
4308 | if (str) |
4309 | { | |
4310 | begp_orig = begp = str + *beg; | |
4311 | endp_orig = endp = str + *end; | |
4312 | } | |
4313 | else | |
4314 | { | |
fb88bf2d | 4315 | begp_orig = begp = BYTE_POS_ADDR (*beg); |
d46c5b12 KH |
4316 | endp_orig = endp = begp + *end - *beg; |
4317 | } | |
4318 | ||
4319 | eol_conversion = (coding->eol_type == CODING_EOL_CR | |
4320 | || coding->eol_type == CODING_EOL_CRLF); | |
4321 | ||
4322 | /* Here, we don't have to check coding->pre_write_conversion because | |
4323 | the caller is expected to have handled it already. */ | |
4324 | switch (coding->type) | |
4325 | { | |
d46c5b12 | 4326 | case coding_type_iso2022: |
622fece5 KH |
4327 | if (CODING_SPEC_ISO_INITIAL_DESIGNATION (coding, 0) != CHARSET_ASCII) |
4328 | /* We can't skip any data. */ | |
4329 | break; | |
d46c5b12 KH |
4330 | if (coding->flags & CODING_FLAG_ISO_DESIGNATE_AT_BOL) |
4331 | { | |
4332 | unsigned char *bol = begp; | |
4333 | while (begp < endp && *begp < 0x80) | |
4334 | { | |
4335 | begp++; | |
4336 | if (begp[-1] == '\n') | |
4337 | bol = begp; | |
4338 | } | |
4339 | begp = bol; | |
4340 | goto label_skip_tail; | |
4341 | } | |
4342 | /* fall down ... */ | |
4343 | ||
b73bfc1c KH |
4344 | case coding_type_sjis: |
4345 | case coding_type_big5: | |
d46c5b12 KH |
4346 | /* We can skip all ASCII characters at the head and tail. */ |
4347 | if (eol_conversion) | |
4348 | while (begp < endp && *begp < 0x80 && *begp != '\n') begp++; | |
4349 | else | |
4350 | while (begp < endp && *begp < 0x80) begp++; | |
4351 | label_skip_tail: | |
4352 | if (eol_conversion) | |
4353 | while (begp < endp && endp[-1] < 0x80 && endp[-1] != '\n') endp--; | |
4354 | else | |
4355 | while (begp < endp && *(endp - 1) < 0x80) endp--; | |
4356 | break; | |
b73bfc1c KH |
4357 | |
4358 | default: | |
4359 | abort (); | |
d46c5b12 KH |
4360 | } |
4361 | ||
4362 | *beg += begp - begp_orig; | |
4363 | *end += endp - endp_orig; | |
4364 | return; | |
4365 | } | |
4366 | ||
88993dfd KH |
4367 | /* As shrinking conversion region requires some overhead, we don't try |
4368 | shrinking if the length of conversion region is less than this | |
4369 | value. */ | |
4370 | static int shrink_conversion_region_threshhold = 1024; | |
4371 | ||
4372 | #define SHRINK_CONVERSION_REGION(beg, end, coding, str, encodep) \ | |
4373 | do { \ | |
4374 | if (*(end) - *(beg) > shrink_conversion_region_threshhold) \ | |
4375 | { \ | |
4376 | if (encodep) shrink_encoding_region (beg, end, coding, str); \ | |
4377 | else shrink_decoding_region (beg, end, coding, str); \ | |
4378 | } \ | |
4379 | } while (0) | |
4380 | ||
b843d1ae KH |
4381 | static Lisp_Object |
4382 | code_convert_region_unwind (dummy) | |
4383 | Lisp_Object dummy; | |
4384 | { | |
4385 | inhibit_pre_post_conversion = 0; | |
4386 | return Qnil; | |
4387 | } | |
4388 | ||
ec6d2bb8 KH |
4389 | /* Store information about all compositions in the range FROM and TO |
4390 | of OBJ in memory blocks pointed by CODING->cmp_data. OBJ is a | |
4391 | buffer or a string, defaults to the current buffer. */ | |
4392 | ||
4393 | void | |
4394 | coding_save_composition (coding, from, to, obj) | |
4395 | struct coding_system *coding; | |
4396 | int from, to; | |
4397 | Lisp_Object obj; | |
4398 | { | |
4399 | Lisp_Object prop; | |
4400 | int start, end; | |
4401 | ||
91bee881 KH |
4402 | if (coding->composing == COMPOSITION_DISABLED) |
4403 | return; | |
4404 | if (!coding->cmp_data) | |
4405 | coding_allocate_composition_data (coding, from); | |
ec6d2bb8 KH |
4406 | if (!find_composition (from, to, &start, &end, &prop, obj) |
4407 | || end > to) | |
4408 | return; | |
4409 | if (start < from | |
4410 | && (!find_composition (end, to, &start, &end, &prop, obj) | |
4411 | || end > to)) | |
4412 | return; | |
4413 | coding->composing = COMPOSITION_NO; | |
ec6d2bb8 KH |
4414 | do |
4415 | { | |
4416 | if (COMPOSITION_VALID_P (start, end, prop)) | |
4417 | { | |
4418 | enum composition_method method = COMPOSITION_METHOD (prop); | |
4419 | if (coding->cmp_data->used + COMPOSITION_DATA_MAX_BUNCH_LENGTH | |
4420 | >= COMPOSITION_DATA_SIZE) | |
4421 | coding_allocate_composition_data (coding, from); | |
4422 | /* For relative composition, we remember start and end | |
4423 | positions, for the other compositions, we also remember | |
4424 | components. */ | |
4425 | CODING_ADD_COMPOSITION_START (coding, start - from, method); | |
4426 | if (method != COMPOSITION_RELATIVE) | |
4427 | { | |
4428 | /* We must store a*/ | |
4429 | Lisp_Object val, ch; | |
4430 | ||
4431 | val = COMPOSITION_COMPONENTS (prop); | |
4432 | if (CONSP (val)) | |
4433 | while (CONSP (val)) | |
4434 | { | |
4435 | ch = XCAR (val), val = XCDR (val); | |
4436 | CODING_ADD_COMPOSITION_COMPONENT (coding, XINT (ch)); | |
4437 | } | |
4438 | else if (VECTORP (val) || STRINGP (val)) | |
4439 | { | |
4440 | int len = (VECTORP (val) | |
4441 | ? XVECTOR (val)->size : XSTRING (val)->size); | |
4442 | int i; | |
4443 | for (i = 0; i < len; i++) | |
4444 | { | |
4445 | ch = (STRINGP (val) | |
4446 | ? Faref (val, make_number (i)) | |
4447 | : XVECTOR (val)->contents[i]); | |
4448 | CODING_ADD_COMPOSITION_COMPONENT (coding, XINT (ch)); | |
4449 | } | |
4450 | } | |
4451 | else /* INTEGERP (val) */ | |
4452 | CODING_ADD_COMPOSITION_COMPONENT (coding, XINT (val)); | |
4453 | } | |
4454 | CODING_ADD_COMPOSITION_END (coding, end - from); | |
4455 | } | |
4456 | start = end; | |
4457 | } | |
4458 | while (start < to | |
4459 | && find_composition (start, to, &start, &end, &prop, obj) | |
4460 | && end <= to); | |
4461 | ||
4462 | /* Make coding->cmp_data point to the first memory block. */ | |
4463 | while (coding->cmp_data->prev) | |
4464 | coding->cmp_data = coding->cmp_data->prev; | |
4465 | coding->cmp_data_start = 0; | |
4466 | } | |
4467 | ||
4468 | /* Reflect the saved information about compositions to OBJ. | |
4469 | CODING->cmp_data points to a memory block for the informaiton. OBJ | |
4470 | is a buffer or a string, defaults to the current buffer. */ | |
4471 | ||
33fb63eb | 4472 | void |
ec6d2bb8 KH |
4473 | coding_restore_composition (coding, obj) |
4474 | struct coding_system *coding; | |
4475 | Lisp_Object obj; | |
4476 | { | |
4477 | struct composition_data *cmp_data = coding->cmp_data; | |
4478 | ||
4479 | if (!cmp_data) | |
4480 | return; | |
4481 | ||
4482 | while (cmp_data->prev) | |
4483 | cmp_data = cmp_data->prev; | |
4484 | ||
4485 | while (cmp_data) | |
4486 | { | |
4487 | int i; | |
4488 | ||
4489 | for (i = 0; i < cmp_data->used; i += cmp_data->data[i]) | |
4490 | { | |
4491 | int *data = cmp_data->data + i; | |
4492 | enum composition_method method = (enum composition_method) data[3]; | |
4493 | Lisp_Object components; | |
4494 | ||
4495 | if (method == COMPOSITION_RELATIVE) | |
4496 | components = Qnil; | |
4497 | else | |
4498 | { | |
4499 | int len = data[0] - 4, j; | |
4500 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; | |
4501 | ||
4502 | for (j = 0; j < len; j++) | |
4503 | args[j] = make_number (data[4 + j]); | |
4504 | components = (method == COMPOSITION_WITH_ALTCHARS | |
4505 | ? Fstring (len, args) : Fvector (len, args)); | |
4506 | } | |
4507 | compose_text (data[1], data[2], components, Qnil, obj); | |
4508 | } | |
4509 | cmp_data = cmp_data->next; | |
4510 | } | |
4511 | } | |
4512 | ||
d46c5b12 | 4513 | /* Decode (if ENCODEP is zero) or encode (if ENCODEP is nonzero) the |
fb88bf2d KH |
4514 | text from FROM to TO (byte positions are FROM_BYTE and TO_BYTE) by |
4515 | coding system CODING, and return the status code of code conversion | |
4516 | (currently, this value has no meaning). | |
4517 | ||
4518 | How many characters (and bytes) are converted to how many | |
4519 | characters (and bytes) are recorded in members of the structure | |
4520 | CODING. | |
d46c5b12 | 4521 | |
6e44253b | 4522 | If REPLACE is nonzero, we do various things as if the original text |
d46c5b12 | 4523 | is deleted and a new text is inserted. See the comments in |
b73bfc1c KH |
4524 | replace_range (insdel.c) to know what we are doing. |
4525 | ||
4526 | If REPLACE is zero, it is assumed that the source text is unibyte. | |
4527 | Otherwize, it is assumed that the source text is multibyte. */ | |
4ed46869 KH |
4528 | |
4529 | int | |
6e44253b KH |
4530 | code_convert_region (from, from_byte, to, to_byte, coding, encodep, replace) |
4531 | int from, from_byte, to, to_byte, encodep, replace; | |
4ed46869 | 4532 | struct coding_system *coding; |
4ed46869 | 4533 | { |
fb88bf2d KH |
4534 | int len = to - from, len_byte = to_byte - from_byte; |
4535 | int require, inserted, inserted_byte; | |
4b39528c | 4536 | int head_skip, tail_skip, total_skip = 0; |
84d60297 | 4537 | Lisp_Object saved_coding_symbol; |
fb88bf2d | 4538 | int first = 1; |
fb88bf2d | 4539 | unsigned char *src, *dst; |
84d60297 | 4540 | Lisp_Object deletion; |
e133c8fa | 4541 | int orig_point = PT, orig_len = len; |
6abb9bd9 | 4542 | int prev_Z; |
b73bfc1c KH |
4543 | int multibyte_p = !NILP (current_buffer->enable_multibyte_characters); |
4544 | ||
4545 | coding->src_multibyte = replace && multibyte_p; | |
4546 | coding->dst_multibyte = multibyte_p; | |
84d60297 RS |
4547 | |
4548 | deletion = Qnil; | |
4549 | saved_coding_symbol = Qnil; | |
d46c5b12 | 4550 | |
83fa074f | 4551 | if (from < PT && PT < to) |
e133c8fa KH |
4552 | { |
4553 | TEMP_SET_PT_BOTH (from, from_byte); | |
4554 | orig_point = from; | |
4555 | } | |
83fa074f | 4556 | |
6e44253b | 4557 | if (replace) |
d46c5b12 | 4558 | { |
fb88bf2d KH |
4559 | int saved_from = from; |
4560 | ||
d46c5b12 | 4561 | prepare_to_modify_buffer (from, to, &from); |
fb88bf2d KH |
4562 | if (saved_from != from) |
4563 | { | |
4564 | to = from + len; | |
b73bfc1c | 4565 | from_byte = CHAR_TO_BYTE (from), to_byte = CHAR_TO_BYTE (to); |
fb88bf2d KH |
4566 | len_byte = to_byte - from_byte; |
4567 | } | |
d46c5b12 | 4568 | } |
d46c5b12 KH |
4569 | |
4570 | if (! encodep && CODING_REQUIRE_DETECTION (coding)) | |
4571 | { | |
12410ef1 | 4572 | /* We must detect encoding of text and eol format. */ |
d46c5b12 KH |
4573 | |
4574 | if (from < GPT && to > GPT) | |
4575 | move_gap_both (from, from_byte); | |
4576 | if (coding->type == coding_type_undecided) | |
4577 | { | |
fb88bf2d | 4578 | detect_coding (coding, BYTE_POS_ADDR (from_byte), len_byte); |
d46c5b12 | 4579 | if (coding->type == coding_type_undecided) |
12410ef1 KH |
4580 | /* It seems that the text contains only ASCII, but we |
4581 | should not left it undecided because the deeper | |
4582 | decoding routine (decode_coding) tries to detect the | |
4583 | encodings again in vain. */ | |
d46c5b12 KH |
4584 | coding->type = coding_type_emacs_mule; |
4585 | } | |
4586 | if (coding->eol_type == CODING_EOL_UNDECIDED) | |
4587 | { | |
4588 | saved_coding_symbol = coding->symbol; | |
4589 | detect_eol (coding, BYTE_POS_ADDR (from_byte), len_byte); | |
4590 | if (coding->eol_type == CODING_EOL_UNDECIDED) | |
4591 | coding->eol_type = CODING_EOL_LF; | |
4592 | /* We had better recover the original eol format if we | |
4593 | encounter an inconsitent eol format while decoding. */ | |
4594 | coding->mode |= CODING_MODE_INHIBIT_INCONSISTENT_EOL; | |
4595 | } | |
4596 | } | |
4597 | ||
d46c5b12 KH |
4598 | /* Now we convert the text. */ |
4599 | ||
4600 | /* For encoding, we must process pre-write-conversion in advance. */ | |
b73bfc1c KH |
4601 | if (! inhibit_pre_post_conversion |
4602 | && encodep | |
d46c5b12 KH |
4603 | && SYMBOLP (coding->pre_write_conversion) |
4604 | && ! NILP (Ffboundp (coding->pre_write_conversion))) | |
4605 | { | |
2b4f9037 KH |
4606 | /* The function in pre-write-conversion may put a new text in a |
4607 | new buffer. */ | |
0007bdd0 KH |
4608 | struct buffer *prev = current_buffer; |
4609 | Lisp_Object new; | |
b843d1ae | 4610 | int count = specpdl_ptr - specpdl; |
d46c5b12 | 4611 | |
b843d1ae KH |
4612 | record_unwind_protect (code_convert_region_unwind, Qnil); |
4613 | /* We should not call any more pre-write/post-read-conversion | |
4614 | functions while this pre-write-conversion is running. */ | |
4615 | inhibit_pre_post_conversion = 1; | |
b39f748c AS |
4616 | call2 (coding->pre_write_conversion, |
4617 | make_number (from), make_number (to)); | |
b843d1ae KH |
4618 | inhibit_pre_post_conversion = 0; |
4619 | /* Discard the unwind protect. */ | |
4620 | specpdl_ptr--; | |
4621 | ||
d46c5b12 KH |
4622 | if (current_buffer != prev) |
4623 | { | |
4624 | len = ZV - BEGV; | |
0007bdd0 | 4625 | new = Fcurrent_buffer (); |
d46c5b12 | 4626 | set_buffer_internal_1 (prev); |
7dae4502 | 4627 | del_range_2 (from, from_byte, to, to_byte, 0); |
e133c8fa | 4628 | TEMP_SET_PT_BOTH (from, from_byte); |
0007bdd0 KH |
4629 | insert_from_buffer (XBUFFER (new), 1, len, 0); |
4630 | Fkill_buffer (new); | |
e133c8fa KH |
4631 | if (orig_point >= to) |
4632 | orig_point += len - orig_len; | |
4633 | else if (orig_point > from) | |
4634 | orig_point = from; | |
4635 | orig_len = len; | |
d46c5b12 | 4636 | to = from + len; |
b73bfc1c KH |
4637 | from_byte = CHAR_TO_BYTE (from); |
4638 | to_byte = CHAR_TO_BYTE (to); | |
d46c5b12 | 4639 | len_byte = to_byte - from_byte; |
e133c8fa | 4640 | TEMP_SET_PT_BOTH (from, from_byte); |
d46c5b12 KH |
4641 | } |
4642 | } | |
4643 | ||
12410ef1 KH |
4644 | if (replace) |
4645 | deletion = make_buffer_string_both (from, from_byte, to, to_byte, 1); | |
4646 | ||
ec6d2bb8 KH |
4647 | if (coding->composing != COMPOSITION_DISABLED) |
4648 | { | |
4649 | if (encodep) | |
4650 | coding_save_composition (coding, from, to, Fcurrent_buffer ()); | |
4651 | else | |
4652 | coding_allocate_composition_data (coding, from); | |
4653 | } | |
fb88bf2d | 4654 | |
b73bfc1c KH |
4655 | /* Try to skip the heading and tailing ASCIIs. */ |
4656 | { | |
4657 | int from_byte_orig = from_byte, to_byte_orig = to_byte; | |
4658 | ||
4659 | if (from < GPT && GPT < to) | |
4660 | move_gap_both (from, from_byte); | |
4661 | SHRINK_CONVERSION_REGION (&from_byte, &to_byte, coding, NULL, encodep); | |
4662 | if (from_byte == to_byte | |
4663 | && (encodep || NILP (coding->post_read_conversion)) | |
4664 | && ! CODING_REQUIRE_FLUSHING (coding)) | |
4665 | { | |
4666 | coding->produced = len_byte; | |
4667 | coding->produced_char = len; | |
4668 | if (!replace) | |
4669 | /* We must record and adjust for this new text now. */ | |
4670 | adjust_after_insert (from, from_byte_orig, to, to_byte_orig, len); | |
4671 | return 0; | |
4672 | } | |
ec6d2bb8 | 4673 | |
b73bfc1c KH |
4674 | head_skip = from_byte - from_byte_orig; |
4675 | tail_skip = to_byte_orig - to_byte; | |
4676 | total_skip = head_skip + tail_skip; | |
4677 | from += head_skip; | |
4678 | to -= tail_skip; | |
4679 | len -= total_skip; len_byte -= total_skip; | |
4680 | } | |
d46c5b12 | 4681 | |
88993dfd | 4682 | /* The code conversion routine can not preserve text properties for |
55d8d769 KH |
4683 | now. So, we must remove all text properties in the region. |
4684 | Here, we must suppress all modification hooks. */ | |
88993dfd | 4685 | if (replace) |
55d8d769 KH |
4686 | { |
4687 | int saved_inhibit_modification_hooks = inhibit_modification_hooks; | |
4688 | inhibit_modification_hooks = 1; | |
4689 | Fset_text_properties (make_number (from), make_number (to), Qnil, Qnil); | |
4690 | inhibit_modification_hooks = saved_inhibit_modification_hooks; | |
4691 | } | |
88993dfd | 4692 | |
fb88bf2d KH |
4693 | /* For converion, we must put the gap before the text in addition to |
4694 | making the gap larger for efficient decoding. The required gap | |
4695 | size starts from 2000 which is the magic number used in make_gap. | |
4696 | But, after one batch of conversion, it will be incremented if we | |
4697 | find that it is not enough . */ | |
d46c5b12 KH |
4698 | require = 2000; |
4699 | ||
4700 | if (GAP_SIZE < require) | |
4701 | make_gap (require - GAP_SIZE); | |
4702 | move_gap_both (from, from_byte); | |
4703 | ||
d46c5b12 | 4704 | inserted = inserted_byte = 0; |
fb88bf2d KH |
4705 | |
4706 | GAP_SIZE += len_byte; | |
4707 | ZV -= len; | |
4708 | Z -= len; | |
4709 | ZV_BYTE -= len_byte; | |
4710 | Z_BYTE -= len_byte; | |
4711 | ||
d9f9a1bc GM |
4712 | if (GPT - BEG < BEG_UNCHANGED) |
4713 | BEG_UNCHANGED = GPT - BEG; | |
4714 | if (Z - GPT < END_UNCHANGED) | |
4715 | END_UNCHANGED = Z - GPT; | |
f2558efd | 4716 | |
b73bfc1c KH |
4717 | if (!encodep && coding->src_multibyte) |
4718 | { | |
4719 | /* Decoding routines expects that the source text is unibyte. | |
4720 | We must convert 8-bit characters of multibyte form to | |
4721 | unibyte. */ | |
4722 | int len_byte_orig = len_byte; | |
4723 | len_byte = str_as_unibyte (GAP_END_ADDR - len_byte, len_byte); | |
4724 | if (len_byte < len_byte_orig) | |
4725 | safe_bcopy (GAP_END_ADDR - len_byte_orig, GAP_END_ADDR - len_byte, | |
4726 | len_byte); | |
4727 | coding->src_multibyte = 0; | |
4728 | } | |
4729 | ||
d46c5b12 KH |
4730 | for (;;) |
4731 | { | |
fb88bf2d | 4732 | int result; |
d46c5b12 | 4733 | |
ec6d2bb8 | 4734 | /* The buffer memory is now: |
b73bfc1c KH |
4735 | +--------+converted-text+---------+-------original-text-------+---+ |
4736 | |<-from->|<--inserted-->|---------|<--------len_byte--------->|---| | |
4737 | |<---------------------- GAP ----------------------->| */ | |
ec6d2bb8 KH |
4738 | src = GAP_END_ADDR - len_byte; |
4739 | dst = GPT_ADDR + inserted_byte; | |
4740 | ||
d46c5b12 | 4741 | if (encodep) |
fb88bf2d | 4742 | result = encode_coding (coding, src, dst, len_byte, 0); |
d46c5b12 | 4743 | else |
fb88bf2d | 4744 | result = decode_coding (coding, src, dst, len_byte, 0); |
ec6d2bb8 KH |
4745 | |
4746 | /* The buffer memory is now: | |
b73bfc1c KH |
4747 | +--------+-------converted-text----+--+------original-text----+---+ |
4748 | |<-from->|<-inserted->|<-produced->|--|<-(len_byte-consumed)->|---| | |
4749 | |<---------------------- GAP ----------------------->| */ | |
ec6d2bb8 | 4750 | |
d46c5b12 KH |
4751 | inserted += coding->produced_char; |
4752 | inserted_byte += coding->produced; | |
d46c5b12 | 4753 | len_byte -= coding->consumed; |
ec6d2bb8 KH |
4754 | |
4755 | if (result == CODING_FINISH_INSUFFICIENT_CMP) | |
4756 | { | |
4757 | coding_allocate_composition_data (coding, from + inserted); | |
4758 | continue; | |
4759 | } | |
4760 | ||
fb88bf2d | 4761 | src += coding->consumed; |
3636f7a3 | 4762 | dst += coding->produced; |
d46c5b12 | 4763 | |
9864ebce KH |
4764 | if (result == CODING_FINISH_NORMAL) |
4765 | { | |
4766 | src += len_byte; | |
4767 | break; | |
4768 | } | |
d46c5b12 KH |
4769 | if (! encodep && result == CODING_FINISH_INCONSISTENT_EOL) |
4770 | { | |
fb88bf2d | 4771 | unsigned char *pend = dst, *p = pend - inserted_byte; |
38edf7d4 | 4772 | Lisp_Object eol_type; |
d46c5b12 KH |
4773 | |
4774 | /* Encode LFs back to the original eol format (CR or CRLF). */ | |
4775 | if (coding->eol_type == CODING_EOL_CR) | |
4776 | { | |
4777 | while (p < pend) if (*p++ == '\n') p[-1] = '\r'; | |
4778 | } | |
4779 | else | |
4780 | { | |
d46c5b12 KH |
4781 | int count = 0; |
4782 | ||
fb88bf2d KH |
4783 | while (p < pend) if (*p++ == '\n') count++; |
4784 | if (src - dst < count) | |
d46c5b12 | 4785 | { |
38edf7d4 | 4786 | /* We don't have sufficient room for encoding LFs |
fb88bf2d KH |
4787 | back to CRLF. We must record converted and |
4788 | not-yet-converted text back to the buffer | |
4789 | content, enlarge the gap, then record them out of | |
4790 | the buffer contents again. */ | |
4791 | int add = len_byte + inserted_byte; | |
4792 | ||
4793 | GAP_SIZE -= add; | |
4794 | ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
4795 | GPT += inserted_byte; GPT_BYTE += inserted_byte; | |
4796 | make_gap (count - GAP_SIZE); | |
4797 | GAP_SIZE += add; | |
4798 | ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
4799 | GPT -= inserted_byte; GPT_BYTE -= inserted_byte; | |
4800 | /* Don't forget to update SRC, DST, and PEND. */ | |
4801 | src = GAP_END_ADDR - len_byte; | |
4802 | dst = GPT_ADDR + inserted_byte; | |
4803 | pend = dst; | |
d46c5b12 | 4804 | } |
d46c5b12 KH |
4805 | inserted += count; |
4806 | inserted_byte += count; | |
fb88bf2d KH |
4807 | coding->produced += count; |
4808 | p = dst = pend + count; | |
4809 | while (count) | |
4810 | { | |
4811 | *--p = *--pend; | |
4812 | if (*p == '\n') count--, *--p = '\r'; | |
4813 | } | |
d46c5b12 KH |
4814 | } |
4815 | ||
4816 | /* Suppress eol-format conversion in the further conversion. */ | |
4817 | coding->eol_type = CODING_EOL_LF; | |
4818 | ||
38edf7d4 KH |
4819 | /* Set the coding system symbol to that for Unix-like EOL. */ |
4820 | eol_type = Fget (saved_coding_symbol, Qeol_type); | |
4821 | if (VECTORP (eol_type) | |
4822 | && XVECTOR (eol_type)->size == 3 | |
4823 | && SYMBOLP (XVECTOR (eol_type)->contents[CODING_EOL_LF])) | |
4824 | coding->symbol = XVECTOR (eol_type)->contents[CODING_EOL_LF]; | |
4825 | else | |
4826 | coding->symbol = saved_coding_symbol; | |
fb88bf2d KH |
4827 | |
4828 | continue; | |
d46c5b12 KH |
4829 | } |
4830 | if (len_byte <= 0) | |
944bd420 KH |
4831 | { |
4832 | if (coding->type != coding_type_ccl | |
4833 | || coding->mode & CODING_MODE_LAST_BLOCK) | |
4834 | break; | |
4835 | coding->mode |= CODING_MODE_LAST_BLOCK; | |
4836 | continue; | |
4837 | } | |
d46c5b12 KH |
4838 | if (result == CODING_FINISH_INSUFFICIENT_SRC) |
4839 | { | |
4840 | /* The source text ends in invalid codes. Let's just | |
4841 | make them valid buffer contents, and finish conversion. */ | |
fb88bf2d | 4842 | inserted += len_byte; |
d46c5b12 | 4843 | inserted_byte += len_byte; |
fb88bf2d | 4844 | while (len_byte--) |
ee59c65f | 4845 | *dst++ = *src++; |
d46c5b12 KH |
4846 | break; |
4847 | } | |
9864ebce KH |
4848 | if (result == CODING_FINISH_INTERRUPT) |
4849 | { | |
4850 | /* The conversion procedure was interrupted by a user. */ | |
9864ebce KH |
4851 | break; |
4852 | } | |
4853 | /* Now RESULT == CODING_FINISH_INSUFFICIENT_DST */ | |
4854 | if (coding->consumed < 1) | |
4855 | { | |
4856 | /* It's quite strange to require more memory without | |
4857 | consuming any bytes. Perhaps CCL program bug. */ | |
9864ebce KH |
4858 | break; |
4859 | } | |
fb88bf2d KH |
4860 | if (first) |
4861 | { | |
4862 | /* We have just done the first batch of conversion which was | |
4863 | stoped because of insufficient gap. Let's reconsider the | |
4864 | required gap size (i.e. SRT - DST) now. | |
4865 | ||
4866 | We have converted ORIG bytes (== coding->consumed) into | |
4867 | NEW bytes (coding->produced). To convert the remaining | |
4868 | LEN bytes, we may need REQUIRE bytes of gap, where: | |
4869 | REQUIRE + LEN_BYTE = LEN_BYTE * (NEW / ORIG) | |
4870 | REQUIRE = LEN_BYTE * (NEW - ORIG) / ORIG | |
4871 | Here, we are sure that NEW >= ORIG. */ | |
6e44253b KH |
4872 | float ratio = coding->produced - coding->consumed; |
4873 | ratio /= coding->consumed; | |
4874 | require = len_byte * ratio; | |
fb88bf2d KH |
4875 | first = 0; |
4876 | } | |
4877 | if ((src - dst) < (require + 2000)) | |
4878 | { | |
4879 | /* See the comment above the previous call of make_gap. */ | |
4880 | int add = len_byte + inserted_byte; | |
4881 | ||
4882 | GAP_SIZE -= add; | |
4883 | ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
4884 | GPT += inserted_byte; GPT_BYTE += inserted_byte; | |
4885 | make_gap (require + 2000); | |
4886 | GAP_SIZE += add; | |
4887 | ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
4888 | GPT -= inserted_byte; GPT_BYTE -= inserted_byte; | |
fb88bf2d | 4889 | } |
d46c5b12 | 4890 | } |
fb88bf2d KH |
4891 | if (src - dst > 0) *dst = 0; /* Put an anchor. */ |
4892 | ||
b73bfc1c KH |
4893 | if (encodep && coding->dst_multibyte) |
4894 | { | |
4895 | /* The output is unibyte. We must convert 8-bit characters to | |
4896 | multibyte form. */ | |
4897 | if (inserted_byte * 2 > GAP_SIZE) | |
4898 | { | |
4899 | GAP_SIZE -= inserted_byte; | |
4900 | ZV += inserted_byte; Z += inserted_byte; | |
4901 | ZV_BYTE += inserted_byte; Z_BYTE += inserted_byte; | |
4902 | GPT += inserted_byte; GPT_BYTE += inserted_byte; | |
4903 | make_gap (inserted_byte - GAP_SIZE); | |
4904 | GAP_SIZE += inserted_byte; | |
4905 | ZV -= inserted_byte; Z -= inserted_byte; | |
4906 | ZV_BYTE -= inserted_byte; Z_BYTE -= inserted_byte; | |
4907 | GPT -= inserted_byte; GPT_BYTE -= inserted_byte; | |
4908 | } | |
4909 | inserted_byte = str_to_multibyte (GPT_ADDR, GAP_SIZE, inserted_byte); | |
4910 | } | |
7553d0e1 | 4911 | |
12410ef1 KH |
4912 | /* If we have shrinked the conversion area, adjust it now. */ |
4913 | if (total_skip > 0) | |
4914 | { | |
4915 | if (tail_skip > 0) | |
4916 | safe_bcopy (GAP_END_ADDR, GPT_ADDR + inserted_byte, tail_skip); | |
4917 | inserted += total_skip; inserted_byte += total_skip; | |
4918 | GAP_SIZE += total_skip; | |
4919 | GPT -= head_skip; GPT_BYTE -= head_skip; | |
4920 | ZV -= total_skip; ZV_BYTE -= total_skip; | |
4921 | Z -= total_skip; Z_BYTE -= total_skip; | |
4922 | from -= head_skip; from_byte -= head_skip; | |
4923 | to += tail_skip; to_byte += tail_skip; | |
4924 | } | |
4925 | ||
6abb9bd9 | 4926 | prev_Z = Z; |
12410ef1 | 4927 | adjust_after_replace (from, from_byte, deletion, inserted, inserted_byte); |
6abb9bd9 | 4928 | inserted = Z - prev_Z; |
4ed46869 | 4929 | |
ec6d2bb8 KH |
4930 | if (!encodep && coding->cmp_data && coding->cmp_data->used) |
4931 | coding_restore_composition (coding, Fcurrent_buffer ()); | |
4932 | coding_free_composition_data (coding); | |
4933 | ||
b73bfc1c KH |
4934 | if (! inhibit_pre_post_conversion |
4935 | && ! encodep && ! NILP (coding->post_read_conversion)) | |
d46c5b12 | 4936 | { |
2b4f9037 | 4937 | Lisp_Object val; |
b843d1ae | 4938 | int count = specpdl_ptr - specpdl; |
4ed46869 | 4939 | |
e133c8fa KH |
4940 | if (from != PT) |
4941 | TEMP_SET_PT_BOTH (from, from_byte); | |
6abb9bd9 | 4942 | prev_Z = Z; |
b843d1ae KH |
4943 | record_unwind_protect (code_convert_region_unwind, Qnil); |
4944 | /* We should not call any more pre-write/post-read-conversion | |
4945 | functions while this post-read-conversion is running. */ | |
4946 | inhibit_pre_post_conversion = 1; | |
2b4f9037 | 4947 | val = call1 (coding->post_read_conversion, make_number (inserted)); |
b843d1ae KH |
4948 | inhibit_pre_post_conversion = 0; |
4949 | /* Discard the unwind protect. */ | |
4950 | specpdl_ptr--; | |
6abb9bd9 | 4951 | CHECK_NUMBER (val, 0); |
944bd420 | 4952 | inserted += Z - prev_Z; |
e133c8fa KH |
4953 | } |
4954 | ||
4955 | if (orig_point >= from) | |
4956 | { | |
4957 | if (orig_point >= from + orig_len) | |
4958 | orig_point += inserted - orig_len; | |
4959 | else | |
4960 | orig_point = from; | |
4961 | TEMP_SET_PT (orig_point); | |
d46c5b12 | 4962 | } |
4ed46869 | 4963 | |
ec6d2bb8 KH |
4964 | if (replace) |
4965 | { | |
4966 | signal_after_change (from, to - from, inserted); | |
e19539f1 | 4967 | update_compositions (from, from + inserted, CHECK_BORDER); |
ec6d2bb8 | 4968 | } |
2b4f9037 | 4969 | |
fb88bf2d | 4970 | { |
12410ef1 KH |
4971 | coding->consumed = to_byte - from_byte; |
4972 | coding->consumed_char = to - from; | |
4973 | coding->produced = inserted_byte; | |
4974 | coding->produced_char = inserted; | |
fb88bf2d | 4975 | } |
7553d0e1 | 4976 | |
fb88bf2d | 4977 | return 0; |
d46c5b12 KH |
4978 | } |
4979 | ||
4980 | Lisp_Object | |
b73bfc1c KH |
4981 | run_pre_post_conversion_on_str (str, coding, encodep) |
4982 | Lisp_Object str; | |
4983 | struct coding_system *coding; | |
4984 | int encodep; | |
4985 | { | |
4986 | int count = specpdl_ptr - specpdl; | |
4987 | struct gcpro gcpro1; | |
4988 | struct buffer *prev = current_buffer; | |
4989 | int multibyte = STRING_MULTIBYTE (str); | |
4990 | ||
4991 | record_unwind_protect (Fset_buffer, Fcurrent_buffer ()); | |
4992 | record_unwind_protect (code_convert_region_unwind, Qnil); | |
4993 | GCPRO1 (str); | |
4994 | temp_output_buffer_setup (" *code-converting-work*"); | |
4995 | set_buffer_internal (XBUFFER (Vstandard_output)); | |
4996 | /* We must insert the contents of STR as is without | |
4997 | unibyte<->multibyte conversion. For that, we adjust the | |
4998 | multibyteness of the working buffer to that of STR. */ | |
4999 | Ferase_buffer (); | |
5000 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; | |
5001 | insert_from_string (str, 0, 0, | |
5002 | XSTRING (str)->size, STRING_BYTES (XSTRING (str)), 0); | |
5003 | UNGCPRO; | |
5004 | inhibit_pre_post_conversion = 1; | |
5005 | if (encodep) | |
5006 | call2 (coding->pre_write_conversion, make_number (BEG), make_number (Z)); | |
5007 | else | |
6bac5b12 KH |
5008 | { |
5009 | TEMP_SET_PT_BOTH (BEG, BEG_BYTE); | |
5010 | call1 (coding->post_read_conversion, make_number (Z - BEG)); | |
5011 | } | |
b73bfc1c KH |
5012 | inhibit_pre_post_conversion = 0; |
5013 | str = make_buffer_string (BEG, Z, 0); | |
5014 | return unbind_to (count, str); | |
5015 | } | |
5016 | ||
5017 | Lisp_Object | |
5018 | decode_coding_string (str, coding, nocopy) | |
d46c5b12 | 5019 | Lisp_Object str; |
4ed46869 | 5020 | struct coding_system *coding; |
b73bfc1c | 5021 | int nocopy; |
4ed46869 | 5022 | { |
d46c5b12 KH |
5023 | int len; |
5024 | char *buf; | |
b73bfc1c | 5025 | int from, to, to_byte; |
d46c5b12 | 5026 | struct gcpro gcpro1; |
84d60297 | 5027 | Lisp_Object saved_coding_symbol; |
d46c5b12 | 5028 | int result; |
4ed46869 | 5029 | |
b73bfc1c KH |
5030 | from = 0; |
5031 | to = XSTRING (str)->size; | |
5032 | to_byte = STRING_BYTES (XSTRING (str)); | |
4ed46869 | 5033 | |
b73bfc1c KH |
5034 | saved_coding_symbol = Qnil; |
5035 | if (CODING_REQUIRE_DETECTION (coding)) | |
d46c5b12 KH |
5036 | { |
5037 | /* See the comments in code_convert_region. */ | |
5038 | if (coding->type == coding_type_undecided) | |
5039 | { | |
5040 | detect_coding (coding, XSTRING (str)->data, to_byte); | |
5041 | if (coding->type == coding_type_undecided) | |
5042 | coding->type = coding_type_emacs_mule; | |
5043 | } | |
5044 | if (coding->eol_type == CODING_EOL_UNDECIDED) | |
5045 | { | |
5046 | saved_coding_symbol = coding->symbol; | |
5047 | detect_eol (coding, XSTRING (str)->data, to_byte); | |
5048 | if (coding->eol_type == CODING_EOL_UNDECIDED) | |
5049 | coding->eol_type = CODING_EOL_LF; | |
5050 | /* We had better recover the original eol format if we | |
5051 | encounter an inconsitent eol format while decoding. */ | |
5052 | coding->mode |= CODING_MODE_INHIBIT_INCONSISTENT_EOL; | |
5053 | } | |
5054 | } | |
4ed46869 | 5055 | |
b73bfc1c | 5056 | if (! CODING_REQUIRE_DECODING (coding)) |
ec6d2bb8 | 5057 | { |
b73bfc1c KH |
5058 | if (!STRING_MULTIBYTE (str)) |
5059 | { | |
5060 | str = Fstring_as_multibyte (str); | |
5061 | nocopy = 1; | |
5062 | } | |
5063 | return (nocopy ? str : Fcopy_sequence (str)); | |
ec6d2bb8 KH |
5064 | } |
5065 | ||
b73bfc1c | 5066 | if (STRING_MULTIBYTE (str)) |
d46c5b12 | 5067 | { |
b73bfc1c KH |
5068 | /* Decoding routines expect the source text to be unibyte. */ |
5069 | str = Fstring_as_unibyte (str); | |
5070 | nocopy = 1; | |
5071 | coding->src_multibyte = 0; | |
5072 | } | |
5073 | coding->dst_multibyte = 1; | |
ec6d2bb8 | 5074 | |
b73bfc1c KH |
5075 | if (coding->composing != COMPOSITION_DISABLED) |
5076 | coding_allocate_composition_data (coding, from); | |
ec6d2bb8 | 5077 | |
b73bfc1c KH |
5078 | /* Try to skip the heading and tailing ASCIIs. */ |
5079 | { | |
5080 | int from_orig = from; | |
4ed46869 | 5081 | |
b73bfc1c KH |
5082 | SHRINK_CONVERSION_REGION (&from, &to_byte, coding, XSTRING (str)->data, |
5083 | 0); | |
5084 | if (from == to_byte) | |
5085 | return (nocopy ? str : Fcopy_sequence (str)); | |
5086 | } | |
5087 | ||
5088 | len = decoding_buffer_size (coding, to_byte - from); | |
fc932ac6 | 5089 | len += from + STRING_BYTES (XSTRING (str)) - to_byte; |
d46c5b12 KH |
5090 | GCPRO1 (str); |
5091 | buf = get_conversion_buffer (len); | |
5092 | UNGCPRO; | |
4ed46869 | 5093 | |
d46c5b12 KH |
5094 | if (from > 0) |
5095 | bcopy (XSTRING (str)->data, buf, from); | |
b73bfc1c KH |
5096 | result = decode_coding (coding, XSTRING (str)->data + from, |
5097 | buf + from, to_byte - from, len); | |
5098 | if (result == CODING_FINISH_INCONSISTENT_EOL) | |
4ed46869 | 5099 | { |
ec6d2bb8 | 5100 | /* We simply try to decode the whole string again but without |
d46c5b12 KH |
5101 | eol-conversion this time. */ |
5102 | coding->eol_type = CODING_EOL_LF; | |
5103 | coding->symbol = saved_coding_symbol; | |
ec6d2bb8 | 5104 | coding_free_composition_data (coding); |
b73bfc1c | 5105 | return decode_coding_string (str, coding, nocopy); |
4ed46869 | 5106 | } |
d46c5b12 KH |
5107 | |
5108 | bcopy (XSTRING (str)->data + to_byte, buf + from + coding->produced, | |
fc932ac6 | 5109 | STRING_BYTES (XSTRING (str)) - to_byte); |
d46c5b12 | 5110 | |
fc932ac6 | 5111 | len = from + STRING_BYTES (XSTRING (str)) - to_byte; |
b73bfc1c KH |
5112 | str = make_multibyte_string (buf, len + coding->produced_char, |
5113 | len + coding->produced); | |
5114 | ||
5115 | if (coding->cmp_data && coding->cmp_data->used) | |
5116 | coding_restore_composition (coding, str); | |
5117 | coding_free_composition_data (coding); | |
5118 | ||
5119 | if (SYMBOLP (coding->post_read_conversion) | |
5120 | && !NILP (Ffboundp (coding->post_read_conversion))) | |
6bac5b12 | 5121 | str = run_pre_post_conversion_on_str (str, coding, 0); |
b73bfc1c KH |
5122 | |
5123 | return str; | |
5124 | } | |
5125 | ||
5126 | Lisp_Object | |
5127 | encode_coding_string (str, coding, nocopy) | |
5128 | Lisp_Object str; | |
5129 | struct coding_system *coding; | |
5130 | int nocopy; | |
5131 | { | |
5132 | int len; | |
5133 | char *buf; | |
5134 | int from, to, to_byte; | |
5135 | struct gcpro gcpro1; | |
5136 | Lisp_Object saved_coding_symbol; | |
5137 | int result; | |
5138 | ||
5139 | if (SYMBOLP (coding->pre_write_conversion) | |
5140 | && !NILP (Ffboundp (coding->pre_write_conversion))) | |
6bac5b12 | 5141 | str = run_pre_post_conversion_on_str (str, coding, 1); |
b73bfc1c KH |
5142 | |
5143 | from = 0; | |
5144 | to = XSTRING (str)->size; | |
5145 | to_byte = STRING_BYTES (XSTRING (str)); | |
5146 | ||
5147 | saved_coding_symbol = Qnil; | |
5148 | if (! CODING_REQUIRE_ENCODING (coding)) | |
826bfb8b | 5149 | { |
b73bfc1c KH |
5150 | if (STRING_MULTIBYTE (str)) |
5151 | { | |
5152 | str = Fstring_as_unibyte (str); | |
5153 | nocopy = 1; | |
5154 | } | |
5155 | return (nocopy ? str : Fcopy_sequence (str)); | |
826bfb8b KH |
5156 | } |
5157 | ||
b73bfc1c KH |
5158 | /* Encoding routines determine the multibyteness of the source text |
5159 | by coding->src_multibyte. */ | |
5160 | coding->src_multibyte = STRING_MULTIBYTE (str); | |
5161 | coding->dst_multibyte = 0; | |
5162 | ||
5163 | if (coding->composing != COMPOSITION_DISABLED) | |
5164 | coding_save_composition (coding, from, to, str); | |
ec6d2bb8 | 5165 | |
b73bfc1c KH |
5166 | /* Try to skip the heading and tailing ASCIIs. */ |
5167 | { | |
5168 | int from_orig = from; | |
5169 | ||
5170 | SHRINK_CONVERSION_REGION (&from, &to_byte, coding, XSTRING (str)->data, | |
5171 | 1); | |
5172 | if (from == to_byte) | |
5173 | return (nocopy ? str : Fcopy_sequence (str)); | |
5174 | } | |
5175 | ||
5176 | len = encoding_buffer_size (coding, to_byte - from); | |
5177 | len += from + STRING_BYTES (XSTRING (str)) - to_byte; | |
5178 | GCPRO1 (str); | |
5179 | buf = get_conversion_buffer (len); | |
5180 | UNGCPRO; | |
5181 | ||
5182 | if (from > 0) | |
5183 | bcopy (XSTRING (str)->data, buf, from); | |
5184 | result = encode_coding (coding, XSTRING (str)->data + from, | |
5185 | buf + from, to_byte - from, len); | |
5186 | bcopy (XSTRING (str)->data + to_byte, buf + from + coding->produced, | |
5187 | STRING_BYTES (XSTRING (str)) - to_byte); | |
5188 | ||
5189 | len = from + STRING_BYTES (XSTRING (str)) - to_byte; | |
5190 | str = make_unibyte_string (buf, len + coding->produced); | |
ec6d2bb8 | 5191 | coding_free_composition_data (coding); |
b73bfc1c | 5192 | |
d46c5b12 | 5193 | return str; |
4ed46869 KH |
5194 | } |
5195 | ||
5196 | \f | |
5197 | #ifdef emacs | |
1397dc18 | 5198 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 5199 | |
4ed46869 KH |
5200 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
5201 | "Return t if OBJECT is nil or a coding-system.\n\ | |
3a73fa5d RS |
5202 | See the documentation of `make-coding-system' for information\n\ |
5203 | about coding-system objects.") | |
4ed46869 KH |
5204 | (obj) |
5205 | Lisp_Object obj; | |
5206 | { | |
4608c386 KH |
5207 | if (NILP (obj)) |
5208 | return Qt; | |
5209 | if (!SYMBOLP (obj)) | |
5210 | return Qnil; | |
5211 | /* Get coding-spec vector for OBJ. */ | |
5212 | obj = Fget (obj, Qcoding_system); | |
5213 | return ((VECTORP (obj) && XVECTOR (obj)->size == 5) | |
5214 | ? Qt : Qnil); | |
4ed46869 KH |
5215 | } |
5216 | ||
9d991de8 RS |
5217 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
5218 | Sread_non_nil_coding_system, 1, 1, 0, | |
e0e989f6 | 5219 | "Read a coding system from the minibuffer, prompting with string PROMPT.") |
4ed46869 KH |
5220 | (prompt) |
5221 | Lisp_Object prompt; | |
5222 | { | |
e0e989f6 | 5223 | Lisp_Object val; |
9d991de8 RS |
5224 | do |
5225 | { | |
4608c386 KH |
5226 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
5227 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 RS |
5228 | } |
5229 | while (XSTRING (val)->size == 0); | |
e0e989f6 | 5230 | return (Fintern (val, Qnil)); |
4ed46869 KH |
5231 | } |
5232 | ||
9b787f3e RS |
5233 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
5234 | "Read a coding system from the minibuffer, prompting with string PROMPT.\n\ | |
5235 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM.") | |
5236 | (prompt, default_coding_system) | |
5237 | Lisp_Object prompt, default_coding_system; | |
4ed46869 | 5238 | { |
f44d27ce | 5239 | Lisp_Object val; |
9b787f3e RS |
5240 | if (SYMBOLP (default_coding_system)) |
5241 | XSETSTRING (default_coding_system, XSYMBOL (default_coding_system)->name); | |
4608c386 | 5242 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
5243 | Qt, Qnil, Qcoding_system_history, |
5244 | default_coding_system, Qnil); | |
e0e989f6 | 5245 | return (XSTRING (val)->size == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
5246 | } |
5247 | ||
5248 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
5249 | 1, 1, 0, | |
5250 | "Check validity of CODING-SYSTEM.\n\ | |
3a73fa5d RS |
5251 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error.\n\ |
5252 | It is valid if it is a symbol with a non-nil `coding-system' property.\n\ | |
4ed46869 KH |
5253 | The value of property should be a vector of length 5.") |
5254 | (coding_system) | |
5255 | Lisp_Object coding_system; | |
5256 | { | |
5257 | CHECK_SYMBOL (coding_system, 0); | |
5258 | if (!NILP (Fcoding_system_p (coding_system))) | |
5259 | return coding_system; | |
5260 | while (1) | |
02ba4723 | 5261 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
4ed46869 | 5262 | } |
3a73fa5d | 5263 | \f |
d46c5b12 KH |
5264 | Lisp_Object |
5265 | detect_coding_system (src, src_bytes, highest) | |
5266 | unsigned char *src; | |
5267 | int src_bytes, highest; | |
4ed46869 KH |
5268 | { |
5269 | int coding_mask, eol_type; | |
d46c5b12 KH |
5270 | Lisp_Object val, tmp; |
5271 | int dummy; | |
4ed46869 | 5272 | |
d46c5b12 KH |
5273 | coding_mask = detect_coding_mask (src, src_bytes, NULL, &dummy); |
5274 | eol_type = detect_eol_type (src, src_bytes, &dummy); | |
5275 | if (eol_type == CODING_EOL_INCONSISTENT) | |
25b02698 | 5276 | eol_type = CODING_EOL_UNDECIDED; |
4ed46869 | 5277 | |
d46c5b12 | 5278 | if (!coding_mask) |
4ed46869 | 5279 | { |
27901516 | 5280 | val = Qundecided; |
d46c5b12 | 5281 | if (eol_type != CODING_EOL_UNDECIDED) |
4ed46869 | 5282 | { |
f44d27ce RS |
5283 | Lisp_Object val2; |
5284 | val2 = Fget (Qundecided, Qeol_type); | |
4ed46869 KH |
5285 | if (VECTORP (val2)) |
5286 | val = XVECTOR (val2)->contents[eol_type]; | |
5287 | } | |
80e803b4 | 5288 | return (highest ? val : Fcons (val, Qnil)); |
4ed46869 | 5289 | } |
4ed46869 | 5290 | |
d46c5b12 KH |
5291 | /* At first, gather possible coding systems in VAL. */ |
5292 | val = Qnil; | |
fa42c37f | 5293 | for (tmp = Vcoding_category_list; CONSP (tmp); tmp = XCDR (tmp)) |
4ed46869 | 5294 | { |
fa42c37f KH |
5295 | Lisp_Object category_val, category_index; |
5296 | ||
5297 | category_index = Fget (XCAR (tmp), Qcoding_category_index); | |
5298 | category_val = Fsymbol_value (XCAR (tmp)); | |
5299 | if (!NILP (category_val) | |
5300 | && NATNUMP (category_index) | |
5301 | && (coding_mask & (1 << XFASTINT (category_index)))) | |
4ed46869 | 5302 | { |
fa42c37f | 5303 | val = Fcons (category_val, val); |
d46c5b12 KH |
5304 | if (highest) |
5305 | break; | |
4ed46869 KH |
5306 | } |
5307 | } | |
d46c5b12 KH |
5308 | if (!highest) |
5309 | val = Fnreverse (val); | |
4ed46869 | 5310 | |
65059037 | 5311 | /* Then, replace the elements with subsidiary coding systems. */ |
fa42c37f | 5312 | for (tmp = val; CONSP (tmp); tmp = XCDR (tmp)) |
4ed46869 | 5313 | { |
65059037 RS |
5314 | if (eol_type != CODING_EOL_UNDECIDED |
5315 | && eol_type != CODING_EOL_INCONSISTENT) | |
4ed46869 | 5316 | { |
d46c5b12 | 5317 | Lisp_Object eol; |
03699b14 | 5318 | eol = Fget (XCAR (tmp), Qeol_type); |
d46c5b12 | 5319 | if (VECTORP (eol)) |
03699b14 | 5320 | XCAR (tmp) = XVECTOR (eol)->contents[eol_type]; |
4ed46869 KH |
5321 | } |
5322 | } | |
03699b14 | 5323 | return (highest ? XCAR (val) : val); |
d46c5b12 | 5324 | } |
4ed46869 | 5325 | |
d46c5b12 KH |
5326 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
5327 | 2, 3, 0, | |
5328 | "Detect coding system of the text in the region between START and END.\n\ | |
5329 | Return a list of possible coding systems ordered by priority.\n\ | |
5330 | \n\ | |
80e803b4 KH |
5331 | If only ASCII characters are found, it returns a list of single element\n\ |
5332 | `undecided' or its subsidiary coding system according to a detected\n\ | |
5333 | end-of-line format.\n\ | |
d46c5b12 KH |
5334 | \n\ |
5335 | If optional argument HIGHEST is non-nil, return the coding system of\n\ | |
5336 | highest priority.") | |
5337 | (start, end, highest) | |
5338 | Lisp_Object start, end, highest; | |
5339 | { | |
5340 | int from, to; | |
5341 | int from_byte, to_byte; | |
6289dd10 | 5342 | |
d46c5b12 KH |
5343 | CHECK_NUMBER_COERCE_MARKER (start, 0); |
5344 | CHECK_NUMBER_COERCE_MARKER (end, 1); | |
4ed46869 | 5345 | |
d46c5b12 KH |
5346 | validate_region (&start, &end); |
5347 | from = XINT (start), to = XINT (end); | |
5348 | from_byte = CHAR_TO_BYTE (from); | |
5349 | to_byte = CHAR_TO_BYTE (to); | |
6289dd10 | 5350 | |
d46c5b12 KH |
5351 | if (from < GPT && to >= GPT) |
5352 | move_gap_both (to, to_byte); | |
4ed46869 | 5353 | |
d46c5b12 KH |
5354 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
5355 | to_byte - from_byte, | |
5356 | !NILP (highest)); | |
5357 | } | |
6289dd10 | 5358 | |
d46c5b12 KH |
5359 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
5360 | 1, 2, 0, | |
5361 | "Detect coding system of the text in STRING.\n\ | |
5362 | Return a list of possible coding systems ordered by priority.\n\ | |
5363 | \n\ | |
80e803b4 KH |
5364 | If only ASCII characters are found, it returns a list of single element\n\ |
5365 | `undecided' or its subsidiary coding system according to a detected\n\ | |
5366 | end-of-line format.\n\ | |
d46c5b12 KH |
5367 | \n\ |
5368 | If optional argument HIGHEST is non-nil, return the coding system of\n\ | |
5369 | highest priority.") | |
5370 | (string, highest) | |
5371 | Lisp_Object string, highest; | |
5372 | { | |
5373 | CHECK_STRING (string, 0); | |
4ed46869 | 5374 | |
d46c5b12 | 5375 | return detect_coding_system (XSTRING (string)->data, |
fc932ac6 | 5376 | STRING_BYTES (XSTRING (string)), |
d46c5b12 | 5377 | !NILP (highest)); |
4ed46869 KH |
5378 | } |
5379 | ||
4031e2bf KH |
5380 | Lisp_Object |
5381 | code_convert_region1 (start, end, coding_system, encodep) | |
d46c5b12 | 5382 | Lisp_Object start, end, coding_system; |
4031e2bf | 5383 | int encodep; |
3a73fa5d RS |
5384 | { |
5385 | struct coding_system coding; | |
4031e2bf | 5386 | int from, to, len; |
3a73fa5d | 5387 | |
d46c5b12 KH |
5388 | CHECK_NUMBER_COERCE_MARKER (start, 0); |
5389 | CHECK_NUMBER_COERCE_MARKER (end, 1); | |
3a73fa5d RS |
5390 | CHECK_SYMBOL (coding_system, 2); |
5391 | ||
d46c5b12 KH |
5392 | validate_region (&start, &end); |
5393 | from = XFASTINT (start); | |
5394 | to = XFASTINT (end); | |
5395 | ||
3a73fa5d | 5396 | if (NILP (coding_system)) |
d46c5b12 KH |
5397 | return make_number (to - from); |
5398 | ||
3a73fa5d | 5399 | if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
d46c5b12 | 5400 | error ("Invalid coding system: %s", XSYMBOL (coding_system)->name->data); |
3a73fa5d | 5401 | |
d46c5b12 | 5402 | coding.mode |= CODING_MODE_LAST_BLOCK; |
b73bfc1c KH |
5403 | coding.src_multibyte = coding.dst_multibyte |
5404 | = !NILP (current_buffer->enable_multibyte_characters); | |
fb88bf2d KH |
5405 | code_convert_region (from, CHAR_TO_BYTE (from), to, CHAR_TO_BYTE (to), |
5406 | &coding, encodep, 1); | |
f072a3e8 | 5407 | Vlast_coding_system_used = coding.symbol; |
fb88bf2d | 5408 | return make_number (coding.produced_char); |
4031e2bf KH |
5409 | } |
5410 | ||
5411 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, | |
5412 | 3, 3, "r\nzCoding system: ", | |
5413 | "Decode the current region by specified coding system.\n\ | |
5414 | When called from a program, takes three arguments:\n\ | |
5415 | START, END, and CODING-SYSTEM. START and END are buffer positions.\n\ | |
f072a3e8 RS |
5416 | This function sets `last-coding-system-used' to the precise coding system\n\ |
5417 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is\n\ | |
5418 | not fully specified.)\n\ | |
5419 | It returns the length of the decoded text.") | |
4031e2bf KH |
5420 | (start, end, coding_system) |
5421 | Lisp_Object start, end, coding_system; | |
5422 | { | |
5423 | return code_convert_region1 (start, end, coding_system, 0); | |
3a73fa5d RS |
5424 | } |
5425 | ||
5426 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, | |
5427 | 3, 3, "r\nzCoding system: ", | |
d46c5b12 | 5428 | "Encode the current region by specified coding system.\n\ |
3a73fa5d | 5429 | When called from a program, takes three arguments:\n\ |
d46c5b12 | 5430 | START, END, and CODING-SYSTEM. START and END are buffer positions.\n\ |
f072a3e8 RS |
5431 | This function sets `last-coding-system-used' to the precise coding system\n\ |
5432 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is\n\ | |
5433 | not fully specified.)\n\ | |
5434 | It returns the length of the encoded text.") | |
d46c5b12 KH |
5435 | (start, end, coding_system) |
5436 | Lisp_Object start, end, coding_system; | |
3a73fa5d | 5437 | { |
4031e2bf KH |
5438 | return code_convert_region1 (start, end, coding_system, 1); |
5439 | } | |
3a73fa5d | 5440 | |
4031e2bf KH |
5441 | Lisp_Object |
5442 | code_convert_string1 (string, coding_system, nocopy, encodep) | |
5443 | Lisp_Object string, coding_system, nocopy; | |
5444 | int encodep; | |
5445 | { | |
5446 | struct coding_system coding; | |
3a73fa5d | 5447 | |
4031e2bf KH |
5448 | CHECK_STRING (string, 0); |
5449 | CHECK_SYMBOL (coding_system, 1); | |
4ed46869 | 5450 | |
d46c5b12 | 5451 | if (NILP (coding_system)) |
4031e2bf | 5452 | return (NILP (nocopy) ? Fcopy_sequence (string) : string); |
4ed46869 | 5453 | |
d46c5b12 KH |
5454 | if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) |
5455 | error ("Invalid coding system: %s", XSYMBOL (coding_system)->name->data); | |
5f1cd180 | 5456 | |
d46c5b12 | 5457 | coding.mode |= CODING_MODE_LAST_BLOCK; |
b73bfc1c KH |
5458 | string = (encodep |
5459 | ? encode_coding_string (string, &coding, !NILP (nocopy)) | |
5460 | : decode_coding_string (string, &coding, !NILP (nocopy))); | |
f072a3e8 | 5461 | Vlast_coding_system_used = coding.symbol; |
ec6d2bb8 KH |
5462 | |
5463 | return string; | |
4ed46869 KH |
5464 | } |
5465 | ||
4ed46869 | 5466 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
e0e989f6 KH |
5467 | 2, 3, 0, |
5468 | "Decode STRING which is encoded in CODING-SYSTEM, and return the result.\n\ | |
fe487a71 | 5469 | Optional arg NOCOPY non-nil means it is ok to return STRING itself\n\ |
f072a3e8 RS |
5470 | if the decoding operation is trivial.\n\ |
5471 | This function sets `last-coding-system-used' to the precise coding system\n\ | |
5472 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is\n\ | |
5473 | not fully specified.)") | |
e0e989f6 KH |
5474 | (string, coding_system, nocopy) |
5475 | Lisp_Object string, coding_system, nocopy; | |
4ed46869 | 5476 | { |
f072a3e8 | 5477 | return code_convert_string1 (string, coding_system, nocopy, 0); |
4ed46869 KH |
5478 | } |
5479 | ||
5480 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, | |
e0e989f6 KH |
5481 | 2, 3, 0, |
5482 | "Encode STRING to CODING-SYSTEM, and return the result.\n\ | |
fe487a71 | 5483 | Optional arg NOCOPY non-nil means it is ok to return STRING itself\n\ |
f072a3e8 RS |
5484 | if the encoding operation is trivial.\n\ |
5485 | This function sets `last-coding-system-used' to the precise coding system\n\ | |
5486 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is\n\ | |
5487 | not fully specified.)") | |
e0e989f6 KH |
5488 | (string, coding_system, nocopy) |
5489 | Lisp_Object string, coding_system, nocopy; | |
4ed46869 | 5490 | { |
f072a3e8 | 5491 | return code_convert_string1 (string, coding_system, nocopy, 1); |
4ed46869 | 5492 | } |
4031e2bf | 5493 | |
ecec61c1 | 5494 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 KH |
5495 | Do not set Vlast_coding_system_used. |
5496 | ||
5497 | This function is called only from macros DECODE_FILE and | |
5498 | ENCODE_FILE, thus we ignore character composition. */ | |
ecec61c1 KH |
5499 | |
5500 | Lisp_Object | |
5501 | code_convert_string_norecord (string, coding_system, encodep) | |
5502 | Lisp_Object string, coding_system; | |
5503 | int encodep; | |
5504 | { | |
5505 | struct coding_system coding; | |
5506 | ||
5507 | CHECK_STRING (string, 0); | |
5508 | CHECK_SYMBOL (coding_system, 1); | |
5509 | ||
5510 | if (NILP (coding_system)) | |
5511 | return string; | |
5512 | ||
5513 | if (setup_coding_system (Fcheck_coding_system (coding_system), &coding) < 0) | |
5514 | error ("Invalid coding system: %s", XSYMBOL (coding_system)->name->data); | |
5515 | ||
ec6d2bb8 | 5516 | coding.composing = COMPOSITION_DISABLED; |
ecec61c1 | 5517 | coding.mode |= CODING_MODE_LAST_BLOCK; |
b73bfc1c KH |
5518 | return (encodep |
5519 | ? encode_coding_string (string, &coding, 1) | |
5520 | : decode_coding_string (string, &coding, 1)); | |
ecec61c1 | 5521 | } |
3a73fa5d | 5522 | \f |
4ed46869 | 5523 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
55ab7be3 | 5524 | "Decode a Japanese character which has CODE in shift_jis encoding.\n\ |
4ed46869 KH |
5525 | Return the corresponding character.") |
5526 | (code) | |
5527 | Lisp_Object code; | |
5528 | { | |
5529 | unsigned char c1, c2, s1, s2; | |
5530 | Lisp_Object val; | |
5531 | ||
5532 | CHECK_NUMBER (code, 0); | |
5533 | s1 = (XFASTINT (code)) >> 8, s2 = (XFASTINT (code)) & 0xFF; | |
55ab7be3 KH |
5534 | if (s1 == 0) |
5535 | { | |
c28a9453 KH |
5536 | if (s2 < 0x80) |
5537 | XSETFASTINT (val, s2); | |
5538 | else if (s2 >= 0xA0 || s2 <= 0xDF) | |
b73bfc1c | 5539 | XSETFASTINT (val, MAKE_CHAR (charset_katakana_jisx0201, s2, 0)); |
c28a9453 | 5540 | else |
9da8350f | 5541 | error ("Invalid Shift JIS code: %x", XFASTINT (code)); |
55ab7be3 KH |
5542 | } |
5543 | else | |
5544 | { | |
5545 | if ((s1 < 0x80 || s1 > 0x9F && s1 < 0xE0 || s1 > 0xEF) | |
5546 | || (s2 < 0x40 || s2 == 0x7F || s2 > 0xFC)) | |
9da8350f | 5547 | error ("Invalid Shift JIS code: %x", XFASTINT (code)); |
55ab7be3 | 5548 | DECODE_SJIS (s1, s2, c1, c2); |
b73bfc1c | 5549 | XSETFASTINT (val, MAKE_CHAR (charset_jisx0208, c1, c2)); |
55ab7be3 | 5550 | } |
4ed46869 KH |
5551 | return val; |
5552 | } | |
5553 | ||
5554 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, | |
55ab7be3 KH |
5555 | "Encode a Japanese character CHAR to shift_jis encoding.\n\ |
5556 | Return the corresponding code in SJIS.") | |
4ed46869 KH |
5557 | (ch) |
5558 | Lisp_Object ch; | |
5559 | { | |
bcf26d6a | 5560 | int charset, c1, c2, s1, s2; |
4ed46869 KH |
5561 | Lisp_Object val; |
5562 | ||
5563 | CHECK_NUMBER (ch, 0); | |
5564 | SPLIT_CHAR (XFASTINT (ch), charset, c1, c2); | |
c28a9453 KH |
5565 | if (charset == CHARSET_ASCII) |
5566 | { | |
5567 | val = ch; | |
5568 | } | |
5569 | else if (charset == charset_jisx0208 | |
5570 | && c1 > 0x20 && c1 < 0x7F && c2 > 0x20 && c2 < 0x7F) | |
4ed46869 KH |
5571 | { |
5572 | ENCODE_SJIS (c1, c2, s1, s2); | |
bcf26d6a | 5573 | XSETFASTINT (val, (s1 << 8) | s2); |
4ed46869 | 5574 | } |
55ab7be3 KH |
5575 | else if (charset == charset_katakana_jisx0201 |
5576 | && c1 > 0x20 && c2 < 0xE0) | |
5577 | { | |
5578 | XSETFASTINT (val, c1 | 0x80); | |
5579 | } | |
4ed46869 | 5580 | else |
55ab7be3 | 5581 | error ("Can't encode to shift_jis: %d", XFASTINT (ch)); |
4ed46869 KH |
5582 | return val; |
5583 | } | |
5584 | ||
5585 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
c28a9453 | 5586 | "Decode a Big5 character which has CODE in BIG5 coding system.\n\ |
4ed46869 KH |
5587 | Return the corresponding character.") |
5588 | (code) | |
5589 | Lisp_Object code; | |
5590 | { | |
5591 | int charset; | |
5592 | unsigned char b1, b2, c1, c2; | |
5593 | Lisp_Object val; | |
5594 | ||
5595 | CHECK_NUMBER (code, 0); | |
5596 | b1 = (XFASTINT (code)) >> 8, b2 = (XFASTINT (code)) & 0xFF; | |
c28a9453 KH |
5597 | if (b1 == 0) |
5598 | { | |
5599 | if (b2 >= 0x80) | |
9da8350f | 5600 | error ("Invalid BIG5 code: %x", XFASTINT (code)); |
c28a9453 KH |
5601 | val = code; |
5602 | } | |
5603 | else | |
5604 | { | |
5605 | if ((b1 < 0xA1 || b1 > 0xFE) | |
5606 | || (b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE)) | |
9da8350f | 5607 | error ("Invalid BIG5 code: %x", XFASTINT (code)); |
c28a9453 | 5608 | DECODE_BIG5 (b1, b2, charset, c1, c2); |
b73bfc1c | 5609 | XSETFASTINT (val, MAKE_CHAR (charset, c1, c2)); |
c28a9453 | 5610 | } |
4ed46869 KH |
5611 | return val; |
5612 | } | |
5613 | ||
5614 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, | |
d46c5b12 | 5615 | "Encode the Big5 character CHAR to BIG5 coding system.\n\ |
4ed46869 KH |
5616 | Return the corresponding character code in Big5.") |
5617 | (ch) | |
5618 | Lisp_Object ch; | |
5619 | { | |
bcf26d6a | 5620 | int charset, c1, c2, b1, b2; |
4ed46869 KH |
5621 | Lisp_Object val; |
5622 | ||
5623 | CHECK_NUMBER (ch, 0); | |
5624 | SPLIT_CHAR (XFASTINT (ch), charset, c1, c2); | |
c28a9453 KH |
5625 | if (charset == CHARSET_ASCII) |
5626 | { | |
5627 | val = ch; | |
5628 | } | |
5629 | else if ((charset == charset_big5_1 | |
5630 | && (XFASTINT (ch) >= 0x250a1 && XFASTINT (ch) <= 0x271ec)) | |
5631 | || (charset == charset_big5_2 | |
5632 | && XFASTINT (ch) >= 0x290a1 && XFASTINT (ch) <= 0x2bdb2)) | |
4ed46869 KH |
5633 | { |
5634 | ENCODE_BIG5 (charset, c1, c2, b1, b2); | |
bcf26d6a | 5635 | XSETFASTINT (val, (b1 << 8) | b2); |
4ed46869 KH |
5636 | } |
5637 | else | |
c28a9453 | 5638 | error ("Can't encode to Big5: %d", XFASTINT (ch)); |
4ed46869 KH |
5639 | return val; |
5640 | } | |
3a73fa5d | 5641 | \f |
1ba9e4ab KH |
5642 | DEFUN ("set-terminal-coding-system-internal", |
5643 | Fset_terminal_coding_system_internal, | |
5644 | Sset_terminal_coding_system_internal, 1, 1, 0, "") | |
4ed46869 KH |
5645 | (coding_system) |
5646 | Lisp_Object coding_system; | |
5647 | { | |
5648 | CHECK_SYMBOL (coding_system, 0); | |
5649 | setup_coding_system (Fcheck_coding_system (coding_system), &terminal_coding); | |
70c22245 | 5650 | /* We had better not send unsafe characters to terminal. */ |
6e85d753 | 5651 | terminal_coding.flags |= CODING_FLAG_ISO_SAFE; |
ec6d2bb8 KH |
5652 | /* Characer composition should be disabled. */ |
5653 | terminal_coding.composing = COMPOSITION_DISABLED; | |
b73bfc1c KH |
5654 | terminal_coding.src_multibyte = 1; |
5655 | terminal_coding.dst_multibyte = 0; | |
4ed46869 KH |
5656 | return Qnil; |
5657 | } | |
5658 | ||
c4825358 KH |
5659 | DEFUN ("set-safe-terminal-coding-system-internal", |
5660 | Fset_safe_terminal_coding_system_internal, | |
5661 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, "") | |
5662 | (coding_system) | |
5663 | Lisp_Object coding_system; | |
5664 | { | |
5665 | CHECK_SYMBOL (coding_system, 0); | |
5666 | setup_coding_system (Fcheck_coding_system (coding_system), | |
5667 | &safe_terminal_coding); | |
ec6d2bb8 KH |
5668 | /* Characer composition should be disabled. */ |
5669 | safe_terminal_coding.composing = COMPOSITION_DISABLED; | |
b73bfc1c KH |
5670 | safe_terminal_coding.src_multibyte = 1; |
5671 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
5672 | return Qnil; |
5673 | } | |
5674 | ||
4ed46869 KH |
5675 | DEFUN ("terminal-coding-system", |
5676 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, | |
3a73fa5d | 5677 | "Return coding system specified for terminal output.") |
4ed46869 KH |
5678 | () |
5679 | { | |
5680 | return terminal_coding.symbol; | |
5681 | } | |
5682 | ||
1ba9e4ab KH |
5683 | DEFUN ("set-keyboard-coding-system-internal", |
5684 | Fset_keyboard_coding_system_internal, | |
5685 | Sset_keyboard_coding_system_internal, 1, 1, 0, "") | |
4ed46869 KH |
5686 | (coding_system) |
5687 | Lisp_Object coding_system; | |
5688 | { | |
5689 | CHECK_SYMBOL (coding_system, 0); | |
5690 | setup_coding_system (Fcheck_coding_system (coding_system), &keyboard_coding); | |
ec6d2bb8 KH |
5691 | /* Characer composition should be disabled. */ |
5692 | keyboard_coding.composing = COMPOSITION_DISABLED; | |
4ed46869 KH |
5693 | return Qnil; |
5694 | } | |
5695 | ||
5696 | DEFUN ("keyboard-coding-system", | |
5697 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, | |
3a73fa5d | 5698 | "Return coding system specified for decoding keyboard input.") |
4ed46869 KH |
5699 | () |
5700 | { | |
5701 | return keyboard_coding.symbol; | |
5702 | } | |
5703 | ||
5704 | \f | |
a5d301df KH |
5705 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
5706 | Sfind_operation_coding_system, 1, MANY, 0, | |
5707 | "Choose a coding system for an operation based on the target name.\n\ | |
69f76525 | 5708 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM).\n\ |
9ce27fde KH |
5709 | DECODING-SYSTEM is the coding system to use for decoding\n\ |
5710 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system\n\ | |
5711 | for encoding (in case OPERATION does encoding).\n\ | |
ccdb79f5 RS |
5712 | \n\ |
5713 | The first argument OPERATION specifies an I/O primitive:\n\ | |
5714 | For file I/O, `insert-file-contents' or `write-region'.\n\ | |
5715 | For process I/O, `call-process', `call-process-region', or `start-process'.\n\ | |
5716 | For network I/O, `open-network-stream'.\n\ | |
5717 | \n\ | |
5718 | The remaining arguments should be the same arguments that were passed\n\ | |
5719 | to the primitive. Depending on which primitive, one of those arguments\n\ | |
5720 | is selected as the TARGET. For example, if OPERATION does file I/O,\n\ | |
5721 | whichever argument specifies the file name is TARGET.\n\ | |
5722 | \n\ | |
5723 | TARGET has a meaning which depends on OPERATION:\n\ | |
4ed46869 KH |
5724 | For file I/O, TARGET is a file name.\n\ |
5725 | For process I/O, TARGET is a process name.\n\ | |
5726 | For network I/O, TARGET is a service name or a port number\n\ | |
5727 | \n\ | |
02ba4723 KH |
5728 | This function looks up what specified for TARGET in,\n\ |
5729 | `file-coding-system-alist', `process-coding-system-alist',\n\ | |
5730 | or `network-coding-system-alist' depending on OPERATION.\n\ | |
5731 | They may specify a coding system, a cons of coding systems,\n\ | |
5732 | or a function symbol to call.\n\ | |
5733 | In the last case, we call the function with one argument,\n\ | |
9ce27fde | 5734 | which is a list of all the arguments given to this function.") |
4ed46869 KH |
5735 | (nargs, args) |
5736 | int nargs; | |
5737 | Lisp_Object *args; | |
5738 | { | |
5739 | Lisp_Object operation, target_idx, target, val; | |
5740 | register Lisp_Object chain; | |
5741 | ||
5742 | if (nargs < 2) | |
5743 | error ("Too few arguments"); | |
5744 | operation = args[0]; | |
5745 | if (!SYMBOLP (operation) | |
5746 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
5747 | error ("Invalid first arguement"); | |
5748 | if (nargs < 1 + XINT (target_idx)) | |
5749 | error ("Too few arguments for operation: %s", | |
5750 | XSYMBOL (operation)->name->data); | |
5751 | target = args[XINT (target_idx) + 1]; | |
5752 | if (!(STRINGP (target) | |
5753 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) | |
5754 | error ("Invalid %dth argument", XINT (target_idx) + 1); | |
5755 | ||
2e34157c RS |
5756 | chain = ((EQ (operation, Qinsert_file_contents) |
5757 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 5758 | ? Vfile_coding_system_alist |
2e34157c | 5759 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
5760 | ? Vnetwork_coding_system_alist |
5761 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
5762 | if (NILP (chain)) |
5763 | return Qnil; | |
5764 | ||
03699b14 | 5765 | for (; CONSP (chain); chain = XCDR (chain)) |
4ed46869 | 5766 | { |
f44d27ce | 5767 | Lisp_Object elt; |
03699b14 | 5768 | elt = XCAR (chain); |
4ed46869 KH |
5769 | |
5770 | if (CONSP (elt) | |
5771 | && ((STRINGP (target) | |
03699b14 KR |
5772 | && STRINGP (XCAR (elt)) |
5773 | && fast_string_match (XCAR (elt), target) >= 0) | |
5774 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
02ba4723 | 5775 | { |
03699b14 | 5776 | val = XCDR (elt); |
b19fd4c5 KH |
5777 | /* Here, if VAL is both a valid coding system and a valid |
5778 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
5779 | if (CONSP (val)) |
5780 | return val; | |
5781 | if (! SYMBOLP (val)) | |
5782 | return Qnil; | |
5783 | if (! NILP (Fcoding_system_p (val))) | |
5784 | return Fcons (val, val); | |
b19fd4c5 KH |
5785 | if (! NILP (Ffboundp (val))) |
5786 | { | |
5787 | val = call1 (val, Flist (nargs, args)); | |
5788 | if (CONSP (val)) | |
5789 | return val; | |
5790 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
5791 | return Fcons (val, val); | |
5792 | } | |
02ba4723 KH |
5793 | return Qnil; |
5794 | } | |
4ed46869 KH |
5795 | } |
5796 | return Qnil; | |
5797 | } | |
5798 | ||
1397dc18 KH |
5799 | DEFUN ("update-coding-systems-internal", Fupdate_coding_systems_internal, |
5800 | Supdate_coding_systems_internal, 0, 0, 0, | |
5801 | "Update internal database for ISO2022 and CCL based coding systems.\n\ | |
fa42c37f KH |
5802 | When values of any coding categories are changed, you must\n\ |
5803 | call this function") | |
d46c5b12 KH |
5804 | () |
5805 | { | |
5806 | int i; | |
5807 | ||
fa42c37f | 5808 | for (i = CODING_CATEGORY_IDX_EMACS_MULE; i < CODING_CATEGORY_IDX_MAX; i++) |
d46c5b12 | 5809 | { |
1397dc18 KH |
5810 | Lisp_Object val; |
5811 | ||
5812 | val = XSYMBOL (XVECTOR (Vcoding_category_table)->contents[i])->value; | |
5813 | if (!NILP (val)) | |
5814 | { | |
5815 | if (! coding_system_table[i]) | |
5816 | coding_system_table[i] = ((struct coding_system *) | |
5817 | xmalloc (sizeof (struct coding_system))); | |
5818 | setup_coding_system (val, coding_system_table[i]); | |
5819 | } | |
5820 | else if (coding_system_table[i]) | |
5821 | { | |
5822 | xfree (coding_system_table[i]); | |
5823 | coding_system_table[i] = NULL; | |
5824 | } | |
d46c5b12 | 5825 | } |
1397dc18 | 5826 | |
d46c5b12 KH |
5827 | return Qnil; |
5828 | } | |
5829 | ||
66cfb530 KH |
5830 | DEFUN ("set-coding-priority-internal", Fset_coding_priority_internal, |
5831 | Sset_coding_priority_internal, 0, 0, 0, | |
5832 | "Update internal database for the current value of `coding-category-list'.\n\ | |
5833 | This function is internal use only.") | |
5834 | () | |
5835 | { | |
5836 | int i = 0, idx; | |
84d60297 RS |
5837 | Lisp_Object val; |
5838 | ||
5839 | val = Vcoding_category_list; | |
66cfb530 KH |
5840 | |
5841 | while (CONSP (val) && i < CODING_CATEGORY_IDX_MAX) | |
5842 | { | |
03699b14 | 5843 | if (! SYMBOLP (XCAR (val))) |
66cfb530 | 5844 | break; |
03699b14 | 5845 | idx = XFASTINT (Fget (XCAR (val), Qcoding_category_index)); |
66cfb530 KH |
5846 | if (idx >= CODING_CATEGORY_IDX_MAX) |
5847 | break; | |
5848 | coding_priorities[i++] = (1 << idx); | |
03699b14 | 5849 | val = XCDR (val); |
66cfb530 KH |
5850 | } |
5851 | /* If coding-category-list is valid and contains all coding | |
5852 | categories, `i' should be CODING_CATEGORY_IDX_MAX now. If not, | |
fa42c37f | 5853 | the following code saves Emacs from crashing. */ |
66cfb530 KH |
5854 | while (i < CODING_CATEGORY_IDX_MAX) |
5855 | coding_priorities[i++] = CODING_CATEGORY_MASK_RAW_TEXT; | |
5856 | ||
5857 | return Qnil; | |
5858 | } | |
5859 | ||
4ed46869 KH |
5860 | #endif /* emacs */ |
5861 | ||
5862 | \f | |
1397dc18 | 5863 | /*** 9. Post-amble ***/ |
4ed46869 | 5864 | |
6d74c3aa KH |
5865 | void |
5866 | init_coding () | |
5867 | { | |
5868 | conversion_buffer = (char *) xmalloc (MINIMUM_CONVERSION_BUFFER_SIZE); | |
5869 | } | |
5870 | ||
dfcf069d | 5871 | void |
4ed46869 KH |
5872 | init_coding_once () |
5873 | { | |
5874 | int i; | |
5875 | ||
0ef69138 | 5876 | /* Emacs' internal format specific initialize routine. */ |
4ed46869 KH |
5877 | for (i = 0; i <= 0x20; i++) |
5878 | emacs_code_class[i] = EMACS_control_code; | |
5879 | emacs_code_class[0x0A] = EMACS_linefeed_code; | |
5880 | emacs_code_class[0x0D] = EMACS_carriage_return_code; | |
5881 | for (i = 0x21 ; i < 0x7F; i++) | |
5882 | emacs_code_class[i] = EMACS_ascii_code; | |
5883 | emacs_code_class[0x7F] = EMACS_control_code; | |
ec6d2bb8 | 5884 | for (i = 0x80; i < 0xFF; i++) |
4ed46869 KH |
5885 | emacs_code_class[i] = EMACS_invalid_code; |
5886 | emacs_code_class[LEADING_CODE_PRIVATE_11] = EMACS_leading_code_3; | |
5887 | emacs_code_class[LEADING_CODE_PRIVATE_12] = EMACS_leading_code_3; | |
5888 | emacs_code_class[LEADING_CODE_PRIVATE_21] = EMACS_leading_code_4; | |
5889 | emacs_code_class[LEADING_CODE_PRIVATE_22] = EMACS_leading_code_4; | |
5890 | ||
5891 | /* ISO2022 specific initialize routine. */ | |
5892 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 5893 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
5894 | for (i = 0x21; i < 0x7F; i++) |
5895 | iso_code_class[i] = ISO_graphic_plane_0; | |
5896 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 5897 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
5898 | for (i = 0xA1; i < 0xFF; i++) |
5899 | iso_code_class[i] = ISO_graphic_plane_1; | |
5900 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
5901 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
5902 | iso_code_class[ISO_CODE_CR] = ISO_carriage_return; | |
5903 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; | |
5904 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
5905 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
5906 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
5907 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
5908 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
5909 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
5910 | ||
e0e989f6 | 5911 | conversion_buffer_size = MINIMUM_CONVERSION_BUFFER_SIZE; |
e0e989f6 KH |
5912 | |
5913 | setup_coding_system (Qnil, &keyboard_coding); | |
5914 | setup_coding_system (Qnil, &terminal_coding); | |
c4825358 | 5915 | setup_coding_system (Qnil, &safe_terminal_coding); |
6bc51348 | 5916 | setup_coding_system (Qnil, &default_buffer_file_coding); |
9ce27fde | 5917 | |
d46c5b12 KH |
5918 | bzero (coding_system_table, sizeof coding_system_table); |
5919 | ||
66cfb530 KH |
5920 | bzero (ascii_skip_code, sizeof ascii_skip_code); |
5921 | for (i = 0; i < 128; i++) | |
5922 | ascii_skip_code[i] = 1; | |
5923 | ||
9ce27fde KH |
5924 | #if defined (MSDOS) || defined (WINDOWSNT) |
5925 | system_eol_type = CODING_EOL_CRLF; | |
5926 | #else | |
5927 | system_eol_type = CODING_EOL_LF; | |
5928 | #endif | |
b843d1ae KH |
5929 | |
5930 | inhibit_pre_post_conversion = 0; | |
e0e989f6 KH |
5931 | } |
5932 | ||
5933 | #ifdef emacs | |
5934 | ||
dfcf069d | 5935 | void |
e0e989f6 KH |
5936 | syms_of_coding () |
5937 | { | |
5938 | Qtarget_idx = intern ("target-idx"); | |
5939 | staticpro (&Qtarget_idx); | |
5940 | ||
bb0115a2 RS |
5941 | Qcoding_system_history = intern ("coding-system-history"); |
5942 | staticpro (&Qcoding_system_history); | |
5943 | Fset (Qcoding_system_history, Qnil); | |
5944 | ||
9ce27fde | 5945 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 5946 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 5947 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
5948 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
5949 | ||
5950 | Qcall_process = intern ("call-process"); | |
5951 | staticpro (&Qcall_process); | |
9ce27fde | 5952 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
5953 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
5954 | ||
5955 | Qcall_process_region = intern ("call-process-region"); | |
5956 | staticpro (&Qcall_process_region); | |
9ce27fde | 5957 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
5958 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
5959 | ||
5960 | Qstart_process = intern ("start-process"); | |
5961 | staticpro (&Qstart_process); | |
9ce27fde | 5962 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
5963 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
5964 | ||
5965 | Qopen_network_stream = intern ("open-network-stream"); | |
5966 | staticpro (&Qopen_network_stream); | |
9ce27fde | 5967 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
5968 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
5969 | ||
4ed46869 KH |
5970 | Qcoding_system = intern ("coding-system"); |
5971 | staticpro (&Qcoding_system); | |
5972 | ||
5973 | Qeol_type = intern ("eol-type"); | |
5974 | staticpro (&Qeol_type); | |
5975 | ||
5976 | Qbuffer_file_coding_system = intern ("buffer-file-coding-system"); | |
5977 | staticpro (&Qbuffer_file_coding_system); | |
5978 | ||
5979 | Qpost_read_conversion = intern ("post-read-conversion"); | |
5980 | staticpro (&Qpost_read_conversion); | |
5981 | ||
5982 | Qpre_write_conversion = intern ("pre-write-conversion"); | |
5983 | staticpro (&Qpre_write_conversion); | |
5984 | ||
27901516 KH |
5985 | Qno_conversion = intern ("no-conversion"); |
5986 | staticpro (&Qno_conversion); | |
5987 | ||
5988 | Qundecided = intern ("undecided"); | |
5989 | staticpro (&Qundecided); | |
5990 | ||
4ed46869 KH |
5991 | Qcoding_system_p = intern ("coding-system-p"); |
5992 | staticpro (&Qcoding_system_p); | |
5993 | ||
5994 | Qcoding_system_error = intern ("coding-system-error"); | |
5995 | staticpro (&Qcoding_system_error); | |
5996 | ||
5997 | Fput (Qcoding_system_error, Qerror_conditions, | |
5998 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
5999 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 6000 | build_string ("Invalid coding system")); |
4ed46869 | 6001 | |
d46c5b12 KH |
6002 | Qcoding_category = intern ("coding-category"); |
6003 | staticpro (&Qcoding_category); | |
4ed46869 KH |
6004 | Qcoding_category_index = intern ("coding-category-index"); |
6005 | staticpro (&Qcoding_category_index); | |
6006 | ||
d46c5b12 KH |
6007 | Vcoding_category_table |
6008 | = Fmake_vector (make_number (CODING_CATEGORY_IDX_MAX), Qnil); | |
6009 | staticpro (&Vcoding_category_table); | |
4ed46869 KH |
6010 | { |
6011 | int i; | |
6012 | for (i = 0; i < CODING_CATEGORY_IDX_MAX; i++) | |
6013 | { | |
d46c5b12 KH |
6014 | XVECTOR (Vcoding_category_table)->contents[i] |
6015 | = intern (coding_category_name[i]); | |
6016 | Fput (XVECTOR (Vcoding_category_table)->contents[i], | |
6017 | Qcoding_category_index, make_number (i)); | |
4ed46869 KH |
6018 | } |
6019 | } | |
6020 | ||
f967223b KH |
6021 | Qtranslation_table = intern ("translation-table"); |
6022 | staticpro (&Qtranslation_table); | |
1397dc18 | 6023 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (1)); |
bdd9fb48 | 6024 | |
f967223b KH |
6025 | Qtranslation_table_id = intern ("translation-table-id"); |
6026 | staticpro (&Qtranslation_table_id); | |
84fbb8a0 | 6027 | |
f967223b KH |
6028 | Qtranslation_table_for_decode = intern ("translation-table-for-decode"); |
6029 | staticpro (&Qtranslation_table_for_decode); | |
a5d301df | 6030 | |
f967223b KH |
6031 | Qtranslation_table_for_encode = intern ("translation-table-for-encode"); |
6032 | staticpro (&Qtranslation_table_for_encode); | |
a5d301df | 6033 | |
70c22245 KH |
6034 | Qsafe_charsets = intern ("safe-charsets"); |
6035 | staticpro (&Qsafe_charsets); | |
6036 | ||
1397dc18 KH |
6037 | Qvalid_codes = intern ("valid-codes"); |
6038 | staticpro (&Qvalid_codes); | |
6039 | ||
9ce27fde KH |
6040 | Qemacs_mule = intern ("emacs-mule"); |
6041 | staticpro (&Qemacs_mule); | |
6042 | ||
d46c5b12 KH |
6043 | Qraw_text = intern ("raw-text"); |
6044 | staticpro (&Qraw_text); | |
6045 | ||
4ed46869 KH |
6046 | defsubr (&Scoding_system_p); |
6047 | defsubr (&Sread_coding_system); | |
6048 | defsubr (&Sread_non_nil_coding_system); | |
6049 | defsubr (&Scheck_coding_system); | |
6050 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 6051 | defsubr (&Sdetect_coding_string); |
4ed46869 KH |
6052 | defsubr (&Sdecode_coding_region); |
6053 | defsubr (&Sencode_coding_region); | |
6054 | defsubr (&Sdecode_coding_string); | |
6055 | defsubr (&Sencode_coding_string); | |
6056 | defsubr (&Sdecode_sjis_char); | |
6057 | defsubr (&Sencode_sjis_char); | |
6058 | defsubr (&Sdecode_big5_char); | |
6059 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 6060 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 6061 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 6062 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 6063 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 6064 | defsubr (&Skeyboard_coding_system); |
a5d301df | 6065 | defsubr (&Sfind_operation_coding_system); |
1397dc18 | 6066 | defsubr (&Supdate_coding_systems_internal); |
66cfb530 | 6067 | defsubr (&Sset_coding_priority_internal); |
4ed46869 | 6068 | |
4608c386 KH |
6069 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
6070 | "List of coding systems.\n\ | |
6071 | \n\ | |
6072 | Do not alter the value of this variable manually. This variable should be\n\ | |
6073 | updated by the functions `make-coding-system' and\n\ | |
6074 | `define-coding-system-alias'."); | |
6075 | Vcoding_system_list = Qnil; | |
6076 | ||
6077 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
6078 | "Alist of coding system names.\n\ | |
6079 | Each element is one element list of coding system name.\n\ | |
6080 | This variable is given to `completing-read' as TABLE argument.\n\ | |
6081 | \n\ | |
6082 | Do not alter the value of this variable manually. This variable should be\n\ | |
6083 | updated by the functions `make-coding-system' and\n\ | |
6084 | `define-coding-system-alias'."); | |
6085 | Vcoding_system_alist = Qnil; | |
6086 | ||
4ed46869 KH |
6087 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
6088 | "List of coding-categories (symbols) ordered by priority."); | |
6089 | { | |
6090 | int i; | |
6091 | ||
6092 | Vcoding_category_list = Qnil; | |
6093 | for (i = CODING_CATEGORY_IDX_MAX - 1; i >= 0; i--) | |
6094 | Vcoding_category_list | |
d46c5b12 KH |
6095 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
6096 | Vcoding_category_list); | |
4ed46869 KH |
6097 | } |
6098 | ||
6099 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
10bff6f1 | 6100 | "Specify the coding system for read operations.\n\ |
2ebb362d | 6101 | It is useful to bind this variable with `let', but do not set it globally.\n\ |
4ed46869 | 6102 | If the value is a coding system, it is used for decoding on read operation.\n\ |
a67a9c66 | 6103 | If not, an appropriate element is used from one of the coding system alists:\n\ |
10bff6f1 | 6104 | There are three such tables, `file-coding-system-alist',\n\ |
a67a9c66 | 6105 | `process-coding-system-alist', and `network-coding-system-alist'."); |
4ed46869 KH |
6106 | Vcoding_system_for_read = Qnil; |
6107 | ||
6108 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
10bff6f1 | 6109 | "Specify the coding system for write operations.\n\ |
928aedd8 RS |
6110 | Programs bind this variable with `let', but you should not set it globally.\n\ |
6111 | If the value is a coding system, it is used for encoding of output,\n\ | |
6112 | when writing it to a file and when sending it to a file or subprocess.\n\ | |
6113 | \n\ | |
6114 | If this does not specify a coding system, an appropriate element\n\ | |
6115 | is used from one of the coding system alists:\n\ | |
10bff6f1 | 6116 | There are three such tables, `file-coding-system-alist',\n\ |
928aedd8 RS |
6117 | `process-coding-system-alist', and `network-coding-system-alist'.\n\ |
6118 | For output to files, if the above procedure does not specify a coding system,\n\ | |
6119 | the value of `buffer-file-coding-system' is used."); | |
4ed46869 KH |
6120 | Vcoding_system_for_write = Qnil; |
6121 | ||
6122 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
a67a9c66 | 6123 | "Coding system used in the latest file or process I/O."); |
4ed46869 KH |
6124 | Vlast_coding_system_used = Qnil; |
6125 | ||
9ce27fde | 6126 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
f07f4a24 | 6127 | "*Non-nil means always inhibit code conversion of end-of-line format.\n\ |
94c7a214 DL |
6128 | See info node `Coding Systems' and info node `Text and Binary' concerning\n\ |
6129 | such conversion."); | |
9ce27fde KH |
6130 | inhibit_eol_conversion = 0; |
6131 | ||
ed29121d EZ |
6132 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
6133 | "Non-nil means process buffer inherits coding system of process output.\n\ | |
6134 | Bind it to t if the process output is to be treated as if it were a file\n\ | |
6135 | read from some filesystem."); | |
6136 | inherit_process_coding_system = 0; | |
6137 | ||
02ba4723 KH |
6138 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
6139 | "Alist to decide a coding system to use for a file I/O operation.\n\ | |
6140 | The format is ((PATTERN . VAL) ...),\n\ | |
6141 | where PATTERN is a regular expression matching a file name,\n\ | |
6142 | VAL is a coding system, a cons of coding systems, or a function symbol.\n\ | |
6143 | If VAL is a coding system, it is used for both decoding and encoding\n\ | |
6144 | the file contents.\n\ | |
6145 | If VAL is a cons of coding systems, the car part is used for decoding,\n\ | |
6146 | and the cdr part is used for encoding.\n\ | |
6147 | If VAL is a function symbol, the function must return a coding system\n\ | |
6148 | or a cons of coding systems which are used as above.\n\ | |
e0e989f6 | 6149 | \n\ |
a85a871a | 6150 | See also the function `find-operation-coding-system'\n\ |
eda284ac | 6151 | and the variable `auto-coding-alist'."); |
02ba4723 KH |
6152 | Vfile_coding_system_alist = Qnil; |
6153 | ||
6154 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
6155 | "Alist to decide a coding system to use for a process I/O operation.\n\ | |
6156 | The format is ((PATTERN . VAL) ...),\n\ | |
6157 | where PATTERN is a regular expression matching a program name,\n\ | |
6158 | VAL is a coding system, a cons of coding systems, or a function symbol.\n\ | |
6159 | If VAL is a coding system, it is used for both decoding what received\n\ | |
6160 | from the program and encoding what sent to the program.\n\ | |
6161 | If VAL is a cons of coding systems, the car part is used for decoding,\n\ | |
6162 | and the cdr part is used for encoding.\n\ | |
6163 | If VAL is a function symbol, the function must return a coding system\n\ | |
6164 | or a cons of coding systems which are used as above.\n\ | |
4ed46869 | 6165 | \n\ |
9ce27fde | 6166 | See also the function `find-operation-coding-system'."); |
02ba4723 KH |
6167 | Vprocess_coding_system_alist = Qnil; |
6168 | ||
6169 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
6170 | "Alist to decide a coding system to use for a network I/O operation.\n\ | |
6171 | The format is ((PATTERN . VAL) ...),\n\ | |
6172 | where PATTERN is a regular expression matching a network service name\n\ | |
6173 | or is a port number to connect to,\n\ | |
6174 | VAL is a coding system, a cons of coding systems, or a function symbol.\n\ | |
6175 | If VAL is a coding system, it is used for both decoding what received\n\ | |
6176 | from the network stream and encoding what sent to the network stream.\n\ | |
6177 | If VAL is a cons of coding systems, the car part is used for decoding,\n\ | |
6178 | and the cdr part is used for encoding.\n\ | |
6179 | If VAL is a function symbol, the function must return a coding system\n\ | |
6180 | or a cons of coding systems which are used as above.\n\ | |
4ed46869 | 6181 | \n\ |
9ce27fde | 6182 | See also the function `find-operation-coding-system'."); |
02ba4723 | 6183 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 6184 | |
68c45bf0 PE |
6185 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
6186 | "Coding system to use with system messages."); | |
6187 | Vlocale_coding_system = Qnil; | |
6188 | ||
005f0d35 | 6189 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 EZ |
6190 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
6191 | "*String displayed in mode line for UNIX-like (LF) end-of-line format."); | |
6192 | eol_mnemonic_unix = build_string (":"); | |
4ed46869 | 6193 | |
7722baf9 EZ |
6194 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
6195 | "*String displayed in mode line for DOS-like (CRLF) end-of-line format."); | |
6196 | eol_mnemonic_dos = build_string ("\\"); | |
4ed46869 | 6197 | |
7722baf9 EZ |
6198 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
6199 | "*String displayed in mode line for MAC-like (CR) end-of-line format."); | |
6200 | eol_mnemonic_mac = build_string ("/"); | |
4ed46869 | 6201 | |
7722baf9 EZ |
6202 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
6203 | "*String displayed in mode line when end-of-line format is not yet determined."); | |
6204 | eol_mnemonic_undecided = build_string (":"); | |
4ed46869 | 6205 | |
84fbb8a0 | 6206 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
f967223b | 6207 | "*Non-nil enables character translation while encoding and decoding."); |
84fbb8a0 | 6208 | Venable_character_translation = Qt; |
bdd9fb48 | 6209 | |
f967223b KH |
6210 | DEFVAR_LISP ("standard-translation-table-for-decode", |
6211 | &Vstandard_translation_table_for_decode, | |
84fbb8a0 | 6212 | "Table for translating characters while decoding."); |
f967223b | 6213 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 6214 | |
f967223b KH |
6215 | DEFVAR_LISP ("standard-translation-table-for-encode", |
6216 | &Vstandard_translation_table_for_encode, | |
84fbb8a0 | 6217 | "Table for translationg characters while encoding."); |
f967223b | 6218 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 KH |
6219 | |
6220 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_alist, | |
6221 | "Alist of charsets vs revision numbers.\n\ | |
6222 | While encoding, if a charset (car part of an element) is found,\n\ | |
6223 | designate it with the escape sequence identifing revision (cdr part of the element)."); | |
6224 | Vcharset_revision_alist = Qnil; | |
02ba4723 KH |
6225 | |
6226 | DEFVAR_LISP ("default-process-coding-system", | |
6227 | &Vdefault_process_coding_system, | |
6228 | "Cons of coding systems used for process I/O by default.\n\ | |
6229 | The car part is used for decoding a process output,\n\ | |
6230 | the cdr part is used for encoding a text to be sent to a process."); | |
6231 | Vdefault_process_coding_system = Qnil; | |
c4825358 | 6232 | |
3f003981 KH |
6233 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
6234 | "Table of extra Latin codes in the range 128..159 (inclusive).\n\ | |
c4825358 KH |
6235 | This is a vector of length 256.\n\ |
6236 | If Nth element is non-nil, the existence of code N in a file\n\ | |
bb0115a2 | 6237 | \(or output of subprocess) doesn't prevent it to be detected as\n\ |
3f003981 KH |
6238 | a coding system of ISO 2022 variant which has a flag\n\ |
6239 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file\n\ | |
c4825358 KH |
6240 | or reading output of a subprocess.\n\ |
6241 | Only 128th through 159th elements has a meaning."); | |
3f003981 | 6242 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
6243 | |
6244 | DEFVAR_LISP ("select-safe-coding-system-function", | |
6245 | &Vselect_safe_coding_system_function, | |
6246 | "Function to call to select safe coding system for encoding a text.\n\ | |
6247 | \n\ | |
6248 | If set, this function is called to force a user to select a proper\n\ | |
6249 | coding system which can encode the text in the case that a default\n\ | |
6250 | coding system used in each operation can't encode the text.\n\ | |
6251 | \n\ | |
a85a871a | 6252 | The default value is `select-safe-coding-system' (which see)."); |
d46c5b12 KH |
6253 | Vselect_safe_coding_system_function = Qnil; |
6254 | ||
4ed46869 KH |
6255 | } |
6256 | ||
68c45bf0 PE |
6257 | char * |
6258 | emacs_strerror (error_number) | |
6259 | int error_number; | |
6260 | { | |
6261 | char *str; | |
6262 | ||
ca9c0567 | 6263 | synchronize_system_messages_locale (); |
68c45bf0 PE |
6264 | str = strerror (error_number); |
6265 | ||
6266 | if (! NILP (Vlocale_coding_system)) | |
6267 | { | |
6268 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
6269 | Vlocale_coding_system, | |
6270 | 0); | |
6271 | str = (char *) XSTRING (dec)->data; | |
6272 | } | |
6273 | ||
6274 | return str; | |
6275 | } | |
6276 | ||
4ed46869 | 6277 | #endif /* emacs */ |
c2f94ebc | 6278 |