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