Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
aaef169d TTN |
2 | Copyright (C) 2001, 2002, 2003, 2004, 2005, |
3 | 2006 Free Software Foundation, Inc. | |
ce03bf76 KH |
4 | Copyright (C) 1995, 1997, 1998, 2002, 2003, 2004, 2005 |
5 | National Institute of Advanced Industrial Science and Technology (AIST) | |
6 | Registration Number H14PRO021 | |
8f924df7 | 7 | Copyright (C) 2003 |
df7492f9 KH |
8 | National Institute of Advanced Industrial Science and Technology (AIST) |
9 | Registration Number H13PRO009 | |
4ed46869 | 10 | |
369314dc KH |
11 | This file is part of GNU Emacs. |
12 | ||
13 | GNU Emacs is free software; you can redistribute it and/or modify | |
14 | it under the terms of the GNU General Public License as published by | |
15 | the Free Software Foundation; either version 2, or (at your option) | |
16 | any later version. | |
4ed46869 | 17 | |
369314dc KH |
18 | GNU Emacs is distributed in the hope that it will be useful, |
19 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
20 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
21 | GNU General Public License for more details. | |
4ed46869 | 22 | |
369314dc KH |
23 | You should have received a copy of the GNU General Public License |
24 | along with GNU Emacs; see the file COPYING. If not, write to | |
4fc5845f LK |
25 | the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, |
26 | Boston, MA 02110-1301, USA. */ | |
4ed46869 KH |
27 | |
28 | /*** TABLE OF CONTENTS *** | |
29 | ||
b73bfc1c | 30 | 0. General comments |
4ed46869 | 31 | 1. Preamble |
df7492f9 KH |
32 | 2. Emacs' internal format (emacs-utf-8) handlers |
33 | 3. UTF-8 handlers | |
34 | 4. UTF-16 handlers | |
35 | 5. Charset-base coding systems handlers | |
36 | 6. emacs-mule (old Emacs' internal format) handlers | |
37 | 7. ISO2022 handlers | |
38 | 8. Shift-JIS and BIG5 handlers | |
39 | 9. CCL handlers | |
40 | 10. C library functions | |
41 | 11. Emacs Lisp library functions | |
42 | 12. Postamble | |
4ed46869 KH |
43 | |
44 | */ | |
45 | ||
df7492f9 | 46 | /*** 0. General comments *** |
b73bfc1c KH |
47 | |
48 | ||
df7492f9 | 49 | CODING SYSTEM |
4ed46869 | 50 | |
5bad0796 DL |
51 | A coding system is an object for an encoding mechanism that contains |
52 | information about how to convert byte sequences to character | |
e19c3639 KH |
53 | sequences and vice versa. When we say "decode", it means converting |
54 | a byte sequence of a specific coding system into a character | |
55 | sequence that is represented by Emacs' internal coding system | |
56 | `emacs-utf-8', and when we say "encode", it means converting a | |
57 | character sequence of emacs-utf-8 to a byte sequence of a specific | |
0ef69138 | 58 | coding system. |
4ed46869 | 59 | |
e19c3639 KH |
60 | In Emacs Lisp, a coding system is represented by a Lisp symbol. In |
61 | C level, a coding system is represented by a vector of attributes | |
5bad0796 | 62 | stored in the hash table Vcharset_hash_table. The conversion from |
e19c3639 KH |
63 | coding system symbol to attributes vector is done by looking up |
64 | Vcharset_hash_table by the symbol. | |
4ed46869 | 65 | |
e19c3639 | 66 | Coding systems are classified into the following types depending on |
5bad0796 | 67 | the encoding mechanism. Here's a brief description of the types. |
4ed46869 | 68 | |
df7492f9 KH |
69 | o UTF-8 |
70 | ||
71 | o UTF-16 | |
72 | ||
73 | o Charset-base coding system | |
74 | ||
75 | A coding system defined by one or more (coded) character sets. | |
5bad0796 | 76 | Decoding and encoding are done by a code converter defined for each |
df7492f9 KH |
77 | character set. |
78 | ||
5bad0796 | 79 | o Old Emacs internal format (emacs-mule) |
df7492f9 | 80 | |
5bad0796 | 81 | The coding system adopted by old versions of Emacs (20 and 21). |
4ed46869 | 82 | |
df7492f9 | 83 | o ISO2022-base coding system |
4ed46869 KH |
84 | |
85 | The most famous coding system for multiple character sets. X's | |
df7492f9 KH |
86 | Compound Text, various EUCs (Extended Unix Code), and coding systems |
87 | used in the Internet communication such as ISO-2022-JP are all | |
88 | variants of ISO2022. | |
4ed46869 | 89 | |
df7492f9 | 90 | o SJIS (or Shift-JIS or MS-Kanji-Code) |
93dec019 | 91 | |
4ed46869 KH |
92 | A coding system to encode character sets: ASCII, JISX0201, and |
93 | JISX0208. Widely used for PC's in Japan. Details are described in | |
df7492f9 | 94 | section 8. |
4ed46869 | 95 | |
df7492f9 | 96 | o BIG5 |
4ed46869 | 97 | |
df7492f9 | 98 | A coding system to encode character sets: ASCII and Big5. Widely |
cfb43547 | 99 | used for Chinese (mainly in Taiwan and Hong Kong). Details are |
df7492f9 KH |
100 | described in section 8. In this file, when we write "big5" (all |
101 | lowercase), we mean the coding system, and when we write "Big5" | |
102 | (capitalized), we mean the character set. | |
4ed46869 | 103 | |
df7492f9 | 104 | o CCL |
27901516 | 105 | |
5bad0796 | 106 | If a user wants to decode/encode text encoded in a coding system |
df7492f9 KH |
107 | not listed above, he can supply a decoder and an encoder for it in |
108 | CCL (Code Conversion Language) programs. Emacs executes the CCL | |
109 | program while decoding/encoding. | |
27901516 | 110 | |
df7492f9 | 111 | o Raw-text |
4ed46869 | 112 | |
5a936b46 | 113 | A coding system for text containing raw eight-bit data. Emacs |
5bad0796 | 114 | treats each byte of source text as a character (except for |
df7492f9 | 115 | end-of-line conversion). |
4ed46869 | 116 | |
df7492f9 KH |
117 | o No-conversion |
118 | ||
119 | Like raw text, but don't do end-of-line conversion. | |
4ed46869 | 120 | |
4ed46869 | 121 | |
df7492f9 | 122 | END-OF-LINE FORMAT |
4ed46869 | 123 | |
5bad0796 | 124 | How text end-of-line is encoded depends on operating system. For |
df7492f9 | 125 | instance, Unix's format is just one byte of LF (line-feed) code, |
f4dee582 | 126 | whereas DOS's format is two-byte sequence of `carriage-return' and |
d46c5b12 KH |
127 | `line-feed' codes. MacOS's format is usually one byte of |
128 | `carriage-return'. | |
4ed46869 | 129 | |
cfb43547 | 130 | Since text character encoding and end-of-line encoding are |
df7492f9 KH |
131 | independent, any coding system described above can take any format |
132 | of end-of-line (except for no-conversion). | |
4ed46869 | 133 | |
e19c3639 KH |
134 | STRUCT CODING_SYSTEM |
135 | ||
136 | Before using a coding system for code conversion (i.e. decoding and | |
137 | encoding), we setup a structure of type `struct coding_system'. | |
138 | This structure keeps various information about a specific code | |
5bad0796 | 139 | conversion (e.g. the location of source and destination data). |
4ed46869 KH |
140 | |
141 | */ | |
142 | ||
df7492f9 KH |
143 | /* COMMON MACROS */ |
144 | ||
145 | ||
4ed46869 KH |
146 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
147 | ||
df7492f9 | 148 | These functions check if a byte sequence specified as a source in |
ff0dacd7 KH |
149 | CODING conforms to the format of XXX, and update the members of |
150 | DETECT_INFO. | |
df7492f9 | 151 | |
ff0dacd7 | 152 | Return 1 if the byte sequence conforms to XXX, otherwise return 0. |
df7492f9 KH |
153 | |
154 | Below is the template of these functions. */ | |
155 | ||
4ed46869 | 156 | #if 0 |
df7492f9 | 157 | static int |
ff0dacd7 | 158 | detect_coding_XXX (coding, detect_info) |
df7492f9 | 159 | struct coding_system *coding; |
ff0dacd7 | 160 | struct coding_detection_info *detect_info; |
4ed46869 | 161 | { |
f1d34bca MB |
162 | const unsigned char *src = coding->source; |
163 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 164 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 165 | int consumed_chars = 0; |
df7492f9 KH |
166 | int found = 0; |
167 | ...; | |
168 | ||
169 | while (1) | |
170 | { | |
171 | /* Get one byte from the source. If the souce is exausted, jump | |
172 | to no_more_source:. */ | |
173 | ONE_MORE_BYTE (c); | |
ff0dacd7 KH |
174 | |
175 | if (! __C_conforms_to_XXX___ (c)) | |
176 | break; | |
177 | if (! __C_strongly_suggests_XXX__ (c)) | |
178 | found = CATEGORY_MASK_XXX; | |
df7492f9 | 179 | } |
ff0dacd7 KH |
180 | /* The byte sequence is invalid for XXX. */ |
181 | detect_info->rejected |= CATEGORY_MASK_XXX; | |
df7492f9 | 182 | return 0; |
ff0dacd7 | 183 | |
df7492f9 | 184 | no_more_source: |
ff0dacd7 KH |
185 | /* The source exausted successfully. */ |
186 | detect_info->found |= found; | |
df7492f9 | 187 | return 1; |
4ed46869 KH |
188 | } |
189 | #endif | |
190 | ||
191 | /*** GENERAL NOTES on `decode_coding_XXX ()' functions *** | |
192 | ||
df7492f9 KH |
193 | These functions decode a byte sequence specified as a source by |
194 | CODING. The resulting multibyte text goes to a place pointed to by | |
195 | CODING->charbuf, the length of which should not exceed | |
196 | CODING->charbuf_size; | |
d46c5b12 | 197 | |
df7492f9 KH |
198 | These functions set the information of original and decoded texts in |
199 | CODING->consumed, CODING->consumed_char, and CODING->charbuf_used. | |
200 | They also set CODING->result to one of CODING_RESULT_XXX indicating | |
201 | how the decoding is finished. | |
d46c5b12 | 202 | |
df7492f9 | 203 | Below is the template of these functions. */ |
d46c5b12 | 204 | |
4ed46869 | 205 | #if 0 |
b73bfc1c | 206 | static void |
df7492f9 | 207 | decode_coding_XXXX (coding) |
4ed46869 | 208 | struct coding_system *coding; |
4ed46869 | 209 | { |
f1d34bca MB |
210 | const unsigned char *src = coding->source + coding->consumed; |
211 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
212 | /* SRC_BASE remembers the start position in source in each loop. |
213 | The loop will be exited when there's not enough source code, or | |
214 | when there's no room in CHARBUF for a decoded character. */ | |
f1d34bca | 215 | const unsigned char *src_base; |
df7492f9 | 216 | /* A buffer to produce decoded characters. */ |
69a80ea3 KH |
217 | int *charbuf = coding->charbuf + coding->charbuf_used; |
218 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
219 | int multibytep = coding->src_multibyte; |
220 | ||
221 | while (1) | |
222 | { | |
223 | src_base = src; | |
224 | if (charbuf < charbuf_end) | |
225 | /* No more room to produce a decoded character. */ | |
226 | break; | |
227 | ONE_MORE_BYTE (c); | |
228 | /* Decode it. */ | |
229 | } | |
230 | ||
231 | no_more_source: | |
232 | if (src_base < src_end | |
233 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
234 | /* If the source ends by partial bytes to construct a character, | |
235 | treat them as eight-bit raw data. */ | |
236 | while (src_base < src_end && charbuf < charbuf_end) | |
237 | *charbuf++ = *src_base++; | |
238 | /* Remember how many bytes and characters we consumed. If the | |
239 | source is multibyte, the bytes and chars are not identical. */ | |
240 | coding->consumed = coding->consumed_char = src_base - coding->source; | |
241 | /* Remember how many characters we produced. */ | |
242 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
243 | } |
244 | #endif | |
245 | ||
246 | /*** GENERAL NOTES on `encode_coding_XXX ()' functions *** | |
247 | ||
df7492f9 KH |
248 | These functions encode SRC_BYTES length text at SOURCE of Emacs' |
249 | internal multibyte format by CODING. The resulting byte sequence | |
b73bfc1c KH |
250 | goes to a place pointed to by DESTINATION, the length of which |
251 | should not exceed DST_BYTES. | |
d46c5b12 | 252 | |
df7492f9 KH |
253 | These functions set the information of original and encoded texts in |
254 | the members produced, produced_char, consumed, and consumed_char of | |
255 | the structure *CODING. They also set the member result to one of | |
256 | CODING_RESULT_XXX indicating how the encoding finished. | |
d46c5b12 | 257 | |
df7492f9 KH |
258 | DST_BYTES zero means that source area and destination area are |
259 | overlapped, which means that we can produce a encoded text until it | |
260 | reaches at the head of not-yet-encoded source text. | |
d46c5b12 | 261 | |
df7492f9 | 262 | Below is a template of these functions. */ |
4ed46869 | 263 | #if 0 |
b73bfc1c | 264 | static void |
df7492f9 | 265 | encode_coding_XXX (coding) |
4ed46869 | 266 | struct coding_system *coding; |
4ed46869 | 267 | { |
df7492f9 KH |
268 | int multibytep = coding->dst_multibyte; |
269 | int *charbuf = coding->charbuf; | |
270 | int *charbuf_end = charbuf->charbuf + coding->charbuf_used; | |
271 | unsigned char *dst = coding->destination + coding->produced; | |
272 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
273 | unsigned char *adjusted_dst_end = dst_end - _MAX_BYTES_PRODUCED_IN_LOOP_; | |
274 | int produced_chars = 0; | |
275 | ||
276 | for (; charbuf < charbuf_end && dst < adjusted_dst_end; charbuf++) | |
277 | { | |
278 | int c = *charbuf; | |
279 | /* Encode C into DST, and increment DST. */ | |
280 | } | |
281 | label_no_more_destination: | |
282 | /* How many chars and bytes we produced. */ | |
283 | coding->produced_char += produced_chars; | |
284 | coding->produced = dst - coding->destination; | |
4ed46869 KH |
285 | } |
286 | #endif | |
287 | ||
4ed46869 KH |
288 | \f |
289 | /*** 1. Preamble ***/ | |
290 | ||
68c45bf0 | 291 | #include <config.h> |
4ed46869 KH |
292 | #include <stdio.h> |
293 | ||
4ed46869 KH |
294 | #include "lisp.h" |
295 | #include "buffer.h" | |
df7492f9 | 296 | #include "character.h" |
4ed46869 KH |
297 | #include "charset.h" |
298 | #include "ccl.h" | |
df7492f9 | 299 | #include "composite.h" |
4ed46869 KH |
300 | #include "coding.h" |
301 | #include "window.h" | |
4ed46869 | 302 | |
df7492f9 | 303 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 304 | |
df7492f9 | 305 | Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type; |
1965cb73 DL |
306 | Lisp_Object Qunix, Qdos; |
307 | extern Lisp_Object Qmac; /* frame.c */ | |
4ed46869 KH |
308 | Lisp_Object Qbuffer_file_coding_system; |
309 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
df7492f9 | 310 | Lisp_Object Qdefault_char; |
27901516 | 311 | Lisp_Object Qno_conversion, Qundecided; |
df7492f9 | 312 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
b49a1807 | 313 | Lisp_Object Qbig, Qlittle; |
bb0115a2 | 314 | Lisp_Object Qcoding_system_history; |
1397dc18 | 315 | Lisp_Object Qvalid_codes; |
a6f87d34 KH |
316 | Lisp_Object QCcategory, QCmnemonic, QCdefalut_char; |
317 | Lisp_Object QCdecode_translation_table, QCencode_translation_table; | |
318 | Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
35befdaa | 319 | Lisp_Object QCascii_compatible_p; |
4ed46869 KH |
320 | |
321 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; | |
387f6ba5 | 322 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 KH |
323 | Lisp_Object Qstart_process, Qopen_network_stream; |
324 | Lisp_Object Qtarget_idx; | |
325 | ||
065e3595 KH |
326 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
327 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
328 | ||
44e8490d KH |
329 | /* If a symbol has this property, evaluate the value to define the |
330 | symbol as a coding system. */ | |
331 | static Lisp_Object Qcoding_system_define_form; | |
332 | ||
5d5bf4d8 KH |
333 | int coding_system_require_warning; |
334 | ||
d46c5b12 KH |
335 | Lisp_Object Vselect_safe_coding_system_function; |
336 | ||
7722baf9 EZ |
337 | /* Mnemonic string for each format of end-of-line. */ |
338 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
339 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 340 | decided. */ |
7722baf9 | 341 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 KH |
342 | |
343 | #ifdef emacs | |
344 | ||
4608c386 KH |
345 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
346 | ||
347 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 348 | |
d46c5b12 KH |
349 | /* Coding system emacs-mule and raw-text are for converting only |
350 | end-of-line format. */ | |
351 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 352 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 353 | |
4ed46869 KH |
354 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
355 | routines by the following three variables. */ | |
356 | /* Coding-system for reading files and receiving data from process. */ | |
357 | Lisp_Object Vcoding_system_for_read; | |
358 | /* Coding-system for writing files and sending data to process. */ | |
359 | Lisp_Object Vcoding_system_for_write; | |
360 | /* Coding-system actually used in the latest I/O. */ | |
361 | Lisp_Object Vlast_coding_system_used; | |
065e3595 KH |
362 | /* Set to non-nil when an error is detected while code conversion. */ |
363 | Lisp_Object Vlast_code_conversion_error; | |
c4825358 | 364 | /* A vector of length 256 which contains information about special |
94487c4e | 365 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 366 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 367 | |
9ce27fde KH |
368 | /* Flag to inhibit code conversion of end-of-line format. */ |
369 | int inhibit_eol_conversion; | |
370 | ||
74383408 KH |
371 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
372 | int inhibit_iso_escape_detection; | |
373 | ||
ed29121d EZ |
374 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
375 | int inherit_process_coding_system; | |
376 | ||
c4825358 | 377 | /* Coding system to be used to encode text for terminal display. */ |
4ed46869 KH |
378 | struct coding_system terminal_coding; |
379 | ||
c4825358 KH |
380 | /* Coding system to be used to encode text for terminal display when |
381 | terminal coding system is nil. */ | |
382 | struct coding_system safe_terminal_coding; | |
383 | ||
384 | /* Coding system of what is sent from terminal keyboard. */ | |
4ed46869 KH |
385 | struct coding_system keyboard_coding; |
386 | ||
02ba4723 KH |
387 | Lisp_Object Vfile_coding_system_alist; |
388 | Lisp_Object Vprocess_coding_system_alist; | |
389 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 390 | |
68c45bf0 PE |
391 | Lisp_Object Vlocale_coding_system; |
392 | ||
4ed46869 KH |
393 | #endif /* emacs */ |
394 | ||
f967223b KH |
395 | /* Flag to tell if we look up translation table on character code |
396 | conversion. */ | |
84fbb8a0 | 397 | Lisp_Object Venable_character_translation; |
f967223b KH |
398 | /* Standard translation table to look up on decoding (reading). */ |
399 | Lisp_Object Vstandard_translation_table_for_decode; | |
400 | /* Standard translation table to look up on encoding (writing). */ | |
401 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 402 | |
f967223b KH |
403 | Lisp_Object Qtranslation_table; |
404 | Lisp_Object Qtranslation_table_id; | |
405 | Lisp_Object Qtranslation_table_for_decode; | |
406 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
407 | |
408 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 409 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 410 | |
02ba4723 KH |
411 | /* Default coding systems used for process I/O. */ |
412 | Lisp_Object Vdefault_process_coding_system; | |
413 | ||
002fdb44 DL |
414 | /* Char table for translating Quail and self-inserting input. */ |
415 | Lisp_Object Vtranslation_table_for_input; | |
416 | ||
df7492f9 KH |
417 | /* Two special coding systems. */ |
418 | Lisp_Object Vsjis_coding_system; | |
419 | Lisp_Object Vbig5_coding_system; | |
420 | ||
df7492f9 KH |
421 | /* ISO2022 section */ |
422 | ||
423 | #define CODING_ISO_INITIAL(coding, reg) \ | |
424 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
425 | coding_attr_iso_initial), \ | |
426 | reg))) | |
427 | ||
428 | ||
429 | #define CODING_ISO_REQUEST(coding, charset_id) \ | |
430 | ((charset_id <= (coding)->max_charset_id \ | |
431 | ? (coding)->safe_charsets[charset_id] \ | |
432 | : -1)) | |
433 | ||
434 | ||
435 | #define CODING_ISO_FLAGS(coding) \ | |
436 | ((coding)->spec.iso_2022.flags) | |
437 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
438 | ((coding)->spec.iso_2022.current_designation[reg]) | |
439 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
440 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
441 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
442 | ((coding)->spec.iso_2022.single_shifting) | |
443 | #define CODING_ISO_BOL(coding) \ | |
444 | ((coding)->spec.iso_2022.bol) | |
445 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
446 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
447 | ||
448 | /* Control characters of ISO2022. */ | |
449 | /* code */ /* function */ | |
450 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
451 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
452 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
453 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
454 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
455 | #define ISO_CODE_ESC 0x1B /* escape */ | |
456 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
457 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
458 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
459 | ||
460 | /* All code (1-byte) of ISO2022 is classified into one of the | |
461 | followings. */ | |
462 | enum iso_code_class_type | |
463 | { | |
464 | ISO_control_0, /* Control codes in the range | |
465 | 0x00..0x1F and 0x7F, except for the | |
466 | following 5 codes. */ | |
df7492f9 KH |
467 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
468 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
469 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
470 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
471 | ISO_control_1, /* Control codes in the range | |
472 | 0x80..0x9F, except for the | |
473 | following 3 codes. */ | |
474 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
475 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
476 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
477 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
478 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
479 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
480 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
481 | }; | |
05e6f5dc | 482 | |
df7492f9 KH |
483 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
484 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 485 | |
df7492f9 KH |
486 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
487 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
488 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 489 | |
df7492f9 KH |
490 | /* If set, reset graphic planes and registers at end-of-line to the |
491 | initial state. */ | |
492 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 493 | |
df7492f9 KH |
494 | /* If set, reset graphic planes and registers before any control |
495 | characters to the initial state. */ | |
496 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 497 | |
df7492f9 KH |
498 | /* If set, encode by 7-bit environment. */ |
499 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 500 | |
df7492f9 KH |
501 | /* If set, use locking-shift function. */ |
502 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 503 | |
df7492f9 KH |
504 | /* If set, use single-shift function. Overwrite |
505 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
506 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 507 | |
df7492f9 KH |
508 | /* If set, use designation escape sequence. */ |
509 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 510 | |
df7492f9 KH |
511 | /* If set, produce revision number sequence. */ |
512 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 513 | |
df7492f9 KH |
514 | /* If set, produce ISO6429's direction specifying sequence. */ |
515 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 516 | |
df7492f9 KH |
517 | /* If set, assume designation states are reset at beginning of line on |
518 | output. */ | |
519 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 520 | |
df7492f9 KH |
521 | /* If set, designation sequence should be placed at beginning of line |
522 | on output. */ | |
523 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 524 | |
df7492f9 KH |
525 | /* If set, do not encode unsafe charactes on output. */ |
526 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 527 | |
df7492f9 KH |
528 | /* If set, extra latin codes (128..159) are accepted as a valid code |
529 | on input. */ | |
530 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 531 | |
df7492f9 | 532 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 533 | |
df7492f9 | 534 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 535 | |
bf16eb23 | 536 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 537 | |
bf16eb23 | 538 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 539 | |
bf16eb23 | 540 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 541 | |
df7492f9 KH |
542 | /* A character to be produced on output if encoding of the original |
543 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
544 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 545 | |
4ed46869 | 546 | |
df7492f9 KH |
547 | /* UTF-16 section */ |
548 | #define CODING_UTF_16_BOM(coding) \ | |
549 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 550 | |
df7492f9 KH |
551 | #define CODING_UTF_16_ENDIAN(coding) \ |
552 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 553 | |
df7492f9 KH |
554 | #define CODING_UTF_16_SURROGATE(coding) \ |
555 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 556 | |
4ed46869 | 557 | |
df7492f9 KH |
558 | /* CCL section */ |
559 | #define CODING_CCL_DECODER(coding) \ | |
560 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
561 | #define CODING_CCL_ENCODER(coding) \ | |
562 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
563 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 564 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 565 | |
5a936b46 | 566 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 567 | |
df7492f9 KH |
568 | enum coding_category |
569 | { | |
570 | coding_category_iso_7, | |
571 | coding_category_iso_7_tight, | |
572 | coding_category_iso_8_1, | |
573 | coding_category_iso_8_2, | |
574 | coding_category_iso_7_else, | |
575 | coding_category_iso_8_else, | |
576 | coding_category_utf_8, | |
577 | coding_category_utf_16_auto, | |
578 | coding_category_utf_16_be, | |
579 | coding_category_utf_16_le, | |
580 | coding_category_utf_16_be_nosig, | |
581 | coding_category_utf_16_le_nosig, | |
582 | coding_category_charset, | |
583 | coding_category_sjis, | |
584 | coding_category_big5, | |
585 | coding_category_ccl, | |
586 | coding_category_emacs_mule, | |
587 | /* All above are targets of code detection. */ | |
588 | coding_category_raw_text, | |
589 | coding_category_undecided, | |
590 | coding_category_max | |
591 | }; | |
592 | ||
593 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
594 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
595 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
596 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
597 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
598 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
599 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
600 | #define CATEGORY_MASK_UTF_8 (1 << coding_category_utf_8) | |
b49a1807 | 601 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
602 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
603 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
604 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
605 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
606 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
607 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
608 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
609 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
610 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 611 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
612 | |
613 | /* This value is returned if detect_coding_mask () find nothing other | |
614 | than ASCII characters. */ | |
615 | #define CATEGORY_MASK_ANY \ | |
616 | (CATEGORY_MASK_ISO_7 \ | |
617 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
618 | | CATEGORY_MASK_ISO_8_1 \ | |
619 | | CATEGORY_MASK_ISO_8_2 \ | |
620 | | CATEGORY_MASK_ISO_7_ELSE \ | |
621 | | CATEGORY_MASK_ISO_8_ELSE \ | |
622 | | CATEGORY_MASK_UTF_8 \ | |
623 | | CATEGORY_MASK_UTF_16_BE \ | |
624 | | CATEGORY_MASK_UTF_16_LE \ | |
625 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
626 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
627 | | CATEGORY_MASK_CHARSET \ | |
628 | | CATEGORY_MASK_SJIS \ | |
629 | | CATEGORY_MASK_BIG5 \ | |
630 | | CATEGORY_MASK_CCL \ | |
631 | | CATEGORY_MASK_EMACS_MULE) | |
632 | ||
633 | ||
634 | #define CATEGORY_MASK_ISO_7BIT \ | |
635 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
636 | ||
637 | #define CATEGORY_MASK_ISO_8BIT \ | |
638 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
639 | ||
640 | #define CATEGORY_MASK_ISO_ELSE \ | |
641 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
642 | ||
643 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
644 | (CATEGORY_MASK_ISO_7 \ | |
645 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
646 | | CATEGORY_MASK_ISO_7_ELSE \ | |
647 | | CATEGORY_MASK_ISO_8_ELSE) | |
648 | ||
649 | #define CATEGORY_MASK_ISO \ | |
650 | ( CATEGORY_MASK_ISO_7BIT \ | |
651 | | CATEGORY_MASK_ISO_8BIT \ | |
652 | | CATEGORY_MASK_ISO_ELSE) | |
653 | ||
654 | #define CATEGORY_MASK_UTF_16 \ | |
655 | (CATEGORY_MASK_UTF_16_BE \ | |
656 | | CATEGORY_MASK_UTF_16_LE \ | |
657 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
658 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
659 | ||
660 | ||
661 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
662 | variable is exposed to Emacs Lisp. */ | |
663 | static Lisp_Object Vcoding_category_list; | |
664 | ||
665 | /* Table of coding categories (Lisp symbols). This variable is for | |
666 | internal use oly. */ | |
667 | static Lisp_Object Vcoding_category_table; | |
668 | ||
669 | /* Table of coding-categories ordered by priority. */ | |
670 | static enum coding_category coding_priorities[coding_category_max]; | |
671 | ||
672 | /* Nth element is a coding context for the coding system bound to the | |
673 | Nth coding category. */ | |
674 | static struct coding_system coding_categories[coding_category_max]; | |
675 | ||
df7492f9 KH |
676 | /*** Commonly used macros and functions ***/ |
677 | ||
678 | #ifndef min | |
679 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
680 | #endif | |
681 | #ifndef max | |
682 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
683 | #endif | |
4ed46869 | 684 | |
24a73b0a KH |
685 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
686 | do { \ | |
687 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
688 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 689 | } while (0) |
4ed46869 | 690 | |
4ed46869 | 691 | |
df7492f9 KH |
692 | /* Safely get one byte from the source text pointed by SRC which ends |
693 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
694 | in the source, it jumps to `no_more_source'. If multibytep is |
695 | nonzero, and a multibyte character is found at SRC, set C to the | |
696 | negative value of the character code. The caller should declare | |
697 | and set these variables appropriately in advance: | |
698 | src, src_end, multibytep */ | |
aa72b389 | 699 | |
065e3595 KH |
700 | #define ONE_MORE_BYTE(c) \ |
701 | do { \ | |
702 | if (src == src_end) \ | |
703 | { \ | |
704 | if (src_base < src) \ | |
705 | record_conversion_result \ | |
706 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
707 | goto no_more_source; \ | |
708 | } \ | |
709 | c = *src++; \ | |
710 | if (multibytep && (c & 0x80)) \ | |
711 | { \ | |
712 | if ((c & 0xFE) == 0xC0) \ | |
713 | c = ((c & 1) << 6) | *src++; \ | |
714 | else \ | |
715 | { \ | |
35befdaa KH |
716 | src--; \ |
717 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
718 | record_conversion_result \ |
719 | (coding, CODING_RESULT_INVALID_SRC); \ | |
720 | } \ | |
721 | } \ | |
722 | consumed_chars++; \ | |
aa72b389 KH |
723 | } while (0) |
724 | ||
aa72b389 | 725 | |
065e3595 KH |
726 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
727 | do { \ | |
728 | c = *src++; \ | |
729 | if (multibytep && (c & 0x80)) \ | |
730 | { \ | |
731 | if ((c & 0xFE) == 0xC0) \ | |
732 | c = ((c & 1) << 6) | *src++; \ | |
733 | else \ | |
734 | { \ | |
35befdaa KH |
735 | src--; \ |
736 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
737 | record_conversion_result \ |
738 | (coding, CODING_RESULT_INVALID_SRC); \ | |
739 | } \ | |
740 | } \ | |
741 | consumed_chars++; \ | |
aa72b389 KH |
742 | } while (0) |
743 | ||
aa72b389 | 744 | |
df7492f9 KH |
745 | /* Store a byte C in the place pointed by DST and increment DST to the |
746 | next free point, and increment PRODUCED_CHARS. The caller should | |
747 | assure that C is 0..127, and declare and set the variable `dst' | |
748 | appropriately in advance. | |
749 | */ | |
aa72b389 KH |
750 | |
751 | ||
df7492f9 KH |
752 | #define EMIT_ONE_ASCII_BYTE(c) \ |
753 | do { \ | |
754 | produced_chars++; \ | |
755 | *dst++ = (c); \ | |
b6871cc7 | 756 | } while (0) |
aa72b389 KH |
757 | |
758 | ||
df7492f9 | 759 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 760 | |
df7492f9 KH |
761 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
762 | do { \ | |
763 | produced_chars += 2; \ | |
764 | *dst++ = (c1), *dst++ = (c2); \ | |
765 | } while (0) | |
aa72b389 KH |
766 | |
767 | ||
df7492f9 KH |
768 | /* Store a byte C in the place pointed by DST and increment DST to the |
769 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
770 | nonzero, store in an appropriate multibyte from. The caller should | |
771 | declare and set the variables `dst' and `multibytep' appropriately | |
772 | in advance. */ | |
773 | ||
774 | #define EMIT_ONE_BYTE(c) \ | |
775 | do { \ | |
776 | produced_chars++; \ | |
777 | if (multibytep) \ | |
778 | { \ | |
779 | int ch = (c); \ | |
780 | if (ch >= 0x80) \ | |
781 | ch = BYTE8_TO_CHAR (ch); \ | |
782 | CHAR_STRING_ADVANCE (ch, dst); \ | |
783 | } \ | |
784 | else \ | |
785 | *dst++ = (c); \ | |
aa72b389 | 786 | } while (0) |
aa72b389 | 787 | |
aa72b389 | 788 | |
df7492f9 | 789 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 790 | |
e19c3639 KH |
791 | #define EMIT_TWO_BYTES(c1, c2) \ |
792 | do { \ | |
793 | produced_chars += 2; \ | |
794 | if (multibytep) \ | |
795 | { \ | |
796 | int ch; \ | |
797 | \ | |
798 | ch = (c1); \ | |
799 | if (ch >= 0x80) \ | |
800 | ch = BYTE8_TO_CHAR (ch); \ | |
801 | CHAR_STRING_ADVANCE (ch, dst); \ | |
802 | ch = (c2); \ | |
803 | if (ch >= 0x80) \ | |
804 | ch = BYTE8_TO_CHAR (ch); \ | |
805 | CHAR_STRING_ADVANCE (ch, dst); \ | |
806 | } \ | |
807 | else \ | |
808 | { \ | |
809 | *dst++ = (c1); \ | |
810 | *dst++ = (c2); \ | |
811 | } \ | |
aa72b389 KH |
812 | } while (0) |
813 | ||
814 | ||
df7492f9 KH |
815 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
816 | do { \ | |
817 | EMIT_ONE_BYTE (c1); \ | |
818 | EMIT_TWO_BYTES (c2, c3); \ | |
819 | } while (0) | |
aa72b389 | 820 | |
aa72b389 | 821 | |
df7492f9 KH |
822 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
823 | do { \ | |
824 | EMIT_TWO_BYTES (c1, c2); \ | |
825 | EMIT_TWO_BYTES (c3, c4); \ | |
826 | } while (0) | |
aa72b389 | 827 | |
aa72b389 | 828 | |
f6cbaf43 KH |
829 | /* Prototypes for static functions. */ |
830 | static void record_conversion_result P_ ((struct coding_system *coding, | |
831 | enum coding_result_code result)); | |
832 | static int detect_coding_utf_8 P_ ((struct coding_system *, | |
833 | struct coding_detection_info *info)); | |
834 | static void decode_coding_utf_8 P_ ((struct coding_system *)); | |
835 | static int encode_coding_utf_8 P_ ((struct coding_system *)); | |
836 | ||
837 | static int detect_coding_utf_16 P_ ((struct coding_system *, | |
838 | struct coding_detection_info *info)); | |
839 | static void decode_coding_utf_16 P_ ((struct coding_system *)); | |
840 | static int encode_coding_utf_16 P_ ((struct coding_system *)); | |
841 | ||
842 | static int detect_coding_iso_2022 P_ ((struct coding_system *, | |
843 | struct coding_detection_info *info)); | |
844 | static void decode_coding_iso_2022 P_ ((struct coding_system *)); | |
845 | static int encode_coding_iso_2022 P_ ((struct coding_system *)); | |
846 | ||
847 | static int detect_coding_emacs_mule P_ ((struct coding_system *, | |
848 | struct coding_detection_info *info)); | |
849 | static void decode_coding_emacs_mule P_ ((struct coding_system *)); | |
850 | static int encode_coding_emacs_mule P_ ((struct coding_system *)); | |
851 | ||
852 | static int detect_coding_sjis P_ ((struct coding_system *, | |
853 | struct coding_detection_info *info)); | |
854 | static void decode_coding_sjis P_ ((struct coding_system *)); | |
855 | static int encode_coding_sjis P_ ((struct coding_system *)); | |
856 | ||
857 | static int detect_coding_big5 P_ ((struct coding_system *, | |
858 | struct coding_detection_info *info)); | |
859 | static void decode_coding_big5 P_ ((struct coding_system *)); | |
860 | static int encode_coding_big5 P_ ((struct coding_system *)); | |
861 | ||
862 | static int detect_coding_ccl P_ ((struct coding_system *, | |
863 | struct coding_detection_info *info)); | |
864 | static void decode_coding_ccl P_ ((struct coding_system *)); | |
865 | static int encode_coding_ccl P_ ((struct coding_system *)); | |
866 | ||
867 | static void decode_coding_raw_text P_ ((struct coding_system *)); | |
868 | static int encode_coding_raw_text P_ ((struct coding_system *)); | |
869 | ||
870 | static void coding_set_source P_ ((struct coding_system *)); | |
871 | static void coding_set_destination P_ ((struct coding_system *)); | |
872 | static void coding_alloc_by_realloc P_ ((struct coding_system *, EMACS_INT)); | |
873 | static void coding_alloc_by_making_gap P_ ((struct coding_system *, | |
874 | EMACS_INT)); | |
875 | static unsigned char *alloc_destination P_ ((struct coding_system *, | |
876 | EMACS_INT, unsigned char *)); | |
877 | static void setup_iso_safe_charsets P_ ((Lisp_Object)); | |
878 | static unsigned char *encode_designation_at_bol P_ ((struct coding_system *, | |
879 | int *, int *, | |
880 | unsigned char *)); | |
881 | static int detect_eol P_ ((const unsigned char *, | |
882 | EMACS_INT, enum coding_category)); | |
883 | static Lisp_Object adjust_coding_eol_type P_ ((struct coding_system *, int)); | |
884 | static void decode_eol P_ ((struct coding_system *)); | |
885 | static Lisp_Object get_translation_table P_ ((Lisp_Object, int, int *)); | |
886 | static Lisp_Object get_translation P_ ((Lisp_Object, int *, int *, | |
887 | int, int *, int *)); | |
888 | static int produce_chars P_ ((struct coding_system *, Lisp_Object, int)); | |
889 | static INLINE void produce_composition P_ ((struct coding_system *, int *, | |
890 | EMACS_INT)); | |
891 | static INLINE void produce_charset P_ ((struct coding_system *, int *, | |
892 | EMACS_INT)); | |
893 | static void produce_annotation P_ ((struct coding_system *, EMACS_INT)); | |
894 | static int decode_coding P_ ((struct coding_system *)); | |
895 | static INLINE int *handle_composition_annotation P_ ((EMACS_INT, EMACS_INT, | |
896 | struct coding_system *, | |
897 | int *, EMACS_INT *)); | |
898 | static INLINE int *handle_charset_annotation P_ ((EMACS_INT, EMACS_INT, | |
899 | struct coding_system *, | |
900 | int *, EMACS_INT *)); | |
901 | static void consume_chars P_ ((struct coding_system *, Lisp_Object, int)); | |
902 | static int encode_coding P_ ((struct coding_system *)); | |
903 | static Lisp_Object make_conversion_work_buffer P_ ((int)); | |
904 | static Lisp_Object code_conversion_restore P_ ((Lisp_Object)); | |
905 | static INLINE int char_encodable_p P_ ((int, Lisp_Object)); | |
906 | static Lisp_Object make_subsidiaries P_ ((Lisp_Object)); | |
907 | ||
065e3595 KH |
908 | static void |
909 | record_conversion_result (struct coding_system *coding, | |
910 | enum coding_result_code result) | |
911 | { | |
912 | coding->result = result; | |
913 | switch (result) | |
914 | { | |
915 | case CODING_RESULT_INSUFFICIENT_SRC: | |
916 | Vlast_code_conversion_error = Qinsufficient_source; | |
917 | break; | |
918 | case CODING_RESULT_INCONSISTENT_EOL: | |
919 | Vlast_code_conversion_error = Qinconsistent_eol; | |
920 | break; | |
921 | case CODING_RESULT_INVALID_SRC: | |
922 | Vlast_code_conversion_error = Qinvalid_source; | |
923 | break; | |
924 | case CODING_RESULT_INTERRUPT: | |
925 | Vlast_code_conversion_error = Qinterrupted; | |
926 | break; | |
927 | case CODING_RESULT_INSUFFICIENT_MEM: | |
928 | Vlast_code_conversion_error = Qinsufficient_memory; | |
929 | break; | |
35befdaa KH |
930 | default: |
931 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
932 | } |
933 | } | |
934 | ||
df7492f9 KH |
935 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
936 | do { \ | |
937 | charset_map_loaded = 0; \ | |
938 | c = DECODE_CHAR (charset, code); \ | |
939 | if (charset_map_loaded) \ | |
940 | { \ | |
8f924df7 | 941 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
942 | EMACS_INT offset; \ |
943 | \ | |
944 | coding_set_source (coding); \ | |
945 | offset = coding->source - orig; \ | |
946 | src += offset; \ | |
947 | src_base += offset; \ | |
948 | src_end += offset; \ | |
949 | } \ | |
aa72b389 KH |
950 | } while (0) |
951 | ||
952 | ||
df7492f9 KH |
953 | #define ASSURE_DESTINATION(bytes) \ |
954 | do { \ | |
955 | if (dst + (bytes) >= dst_end) \ | |
956 | { \ | |
957 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
958 | \ | |
959 | dst = alloc_destination (coding, more_bytes, dst); \ | |
960 | dst_end = coding->destination + coding->dst_bytes; \ | |
961 | } \ | |
962 | } while (0) | |
aa72b389 | 963 | |
aa72b389 | 964 | |
aa72b389 | 965 | |
df7492f9 KH |
966 | static void |
967 | coding_set_source (coding) | |
aa72b389 | 968 | struct coding_system *coding; |
aa72b389 | 969 | { |
df7492f9 KH |
970 | if (BUFFERP (coding->src_object)) |
971 | { | |
2cb26057 | 972 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 973 | |
df7492f9 | 974 | if (coding->src_pos < 0) |
2cb26057 | 975 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 976 | else |
2cb26057 | 977 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 978 | } |
df7492f9 | 979 | else if (STRINGP (coding->src_object)) |
aa72b389 | 980 | { |
8f924df7 | 981 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 982 | } |
df7492f9 KH |
983 | else |
984 | /* Otherwise, the source is C string and is never relocated | |
985 | automatically. Thus we don't have to update anything. */ | |
986 | ; | |
987 | } | |
aa72b389 | 988 | |
df7492f9 KH |
989 | static void |
990 | coding_set_destination (coding) | |
991 | struct coding_system *coding; | |
992 | { | |
993 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 994 | { |
df7492f9 | 995 | if (coding->src_pos < 0) |
aa72b389 | 996 | { |
28f67a95 KH |
997 | coding->destination = BEG_ADDR + coding->dst_pos_byte - 1; |
998 | coding->dst_bytes = (GAP_END_ADDR | |
999 | - (coding->src_bytes - coding->consumed) | |
1000 | - coding->destination); | |
aa72b389 | 1001 | } |
df7492f9 | 1002 | else |
28f67a95 KH |
1003 | { |
1004 | /* We are sure that coding->dst_pos_byte is before the gap | |
1005 | of the buffer. */ | |
1006 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
1007 | + coding->dst_pos_byte - 1); | |
1008 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) | |
1009 | - coding->destination); | |
1010 | } | |
df7492f9 KH |
1011 | } |
1012 | else | |
1013 | /* Otherwise, the destination is C string and is never relocated | |
1014 | automatically. Thus we don't have to update anything. */ | |
1015 | ; | |
1016 | } | |
1017 | ||
1018 | ||
1019 | static void | |
1020 | coding_alloc_by_realloc (coding, bytes) | |
1021 | struct coding_system *coding; | |
1022 | EMACS_INT bytes; | |
1023 | { | |
1024 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
1025 | coding->dst_bytes + bytes); | |
1026 | coding->dst_bytes += bytes; | |
1027 | } | |
1028 | ||
1029 | static void | |
1030 | coding_alloc_by_making_gap (coding, bytes) | |
1031 | struct coding_system *coding; | |
1032 | EMACS_INT bytes; | |
1033 | { | |
2c78b7e1 KH |
1034 | if (BUFFERP (coding->dst_object) |
1035 | && EQ (coding->src_object, coding->dst_object)) | |
df7492f9 KH |
1036 | { |
1037 | EMACS_INT add = coding->src_bytes - coding->consumed; | |
1038 | ||
1039 | GAP_SIZE -= add; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
1040 | make_gap (bytes); | |
1041 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
1042 | } | |
730fff51 | 1043 | else |
df7492f9 | 1044 | { |
2c78b7e1 KH |
1045 | Lisp_Object this_buffer; |
1046 | ||
1047 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1048 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1049 | make_gap (bytes); | |
1050 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1051 | } |
df7492f9 | 1052 | } |
8f924df7 | 1053 | |
df7492f9 KH |
1054 | |
1055 | static unsigned char * | |
1056 | alloc_destination (coding, nbytes, dst) | |
1057 | struct coding_system *coding; | |
3e139625 | 1058 | EMACS_INT nbytes; |
df7492f9 KH |
1059 | unsigned char *dst; |
1060 | { | |
1061 | EMACS_INT offset = dst - coding->destination; | |
1062 | ||
1063 | if (BUFFERP (coding->dst_object)) | |
1064 | coding_alloc_by_making_gap (coding, nbytes); | |
aa72b389 | 1065 | else |
df7492f9 | 1066 | coding_alloc_by_realloc (coding, nbytes); |
065e3595 | 1067 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1068 | coding_set_destination (coding); |
1069 | dst = coding->destination + offset; | |
1070 | return dst; | |
1071 | } | |
aa72b389 | 1072 | |
ff0dacd7 KH |
1073 | /** Macros for annotations. */ |
1074 | ||
1075 | /* Maximum length of annotation data (sum of annotations for | |
1076 | composition and charset). */ | |
69a80ea3 | 1077 | #define MAX_ANNOTATION_LENGTH (4 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 + 4) |
ff0dacd7 KH |
1078 | |
1079 | /* An annotation data is stored in the array coding->charbuf in this | |
1080 | format: | |
69a80ea3 | 1081 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1082 | LENGTH is the number of elements in the annotation. |
1083 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1084 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1085 | |
1086 | The format of the following elements depend on ANNOTATION_MASK. | |
1087 | ||
1088 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1089 | follows: | |
1090 | ... METHOD [ COMPOSITION-COMPONENTS ... ] | |
1091 | METHOD is one of enum composition_method. | |
1092 | Optionnal COMPOSITION-COMPONENTS are characters and composition | |
1093 | rules. | |
1094 | ||
1095 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
1096 | follows. */ | |
1097 | ||
69a80ea3 | 1098 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1099 | do { \ |
1100 | *(buf)++ = -(len); \ | |
1101 | *(buf)++ = (mask); \ | |
69a80ea3 | 1102 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1103 | coding->annotated = 1; \ |
1104 | } while (0); | |
1105 | ||
69a80ea3 KH |
1106 | #define ADD_COMPOSITION_DATA(buf, nchars, method) \ |
1107 | do { \ | |
1108 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ | |
1109 | *buf++ = method; \ | |
ff0dacd7 KH |
1110 | } while (0) |
1111 | ||
1112 | ||
69a80ea3 KH |
1113 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1114 | do { \ | |
1115 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1116 | *buf++ = id; \ | |
ff0dacd7 KH |
1117 | } while (0) |
1118 | ||
df7492f9 KH |
1119 | \f |
1120 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1121 | ||
1122 | ||
1123 | ||
1124 | \f | |
1125 | /*** 3. UTF-8 ***/ | |
1126 | ||
1127 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1128 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1129 | return 0. */ | |
df7492f9 KH |
1130 | |
1131 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1132 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1133 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1134 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1135 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1136 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1137 | ||
1138 | static int | |
ff0dacd7 | 1139 | detect_coding_utf_8 (coding, detect_info) |
df7492f9 | 1140 | struct coding_system *coding; |
ff0dacd7 | 1141 | struct coding_detection_info *detect_info; |
df7492f9 | 1142 | { |
065e3595 | 1143 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1144 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1145 | int multibytep = coding->src_multibyte; |
1146 | int consumed_chars = 0; | |
1147 | int found = 0; | |
1148 | ||
ff0dacd7 | 1149 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1150 | /* A coding system of this category is always ASCII compatible. */ |
1151 | src += coding->head_ascii; | |
1152 | ||
1153 | while (1) | |
aa72b389 | 1154 | { |
df7492f9 | 1155 | int c, c1, c2, c3, c4; |
aa72b389 | 1156 | |
065e3595 | 1157 | src_base = src; |
df7492f9 | 1158 | ONE_MORE_BYTE (c); |
065e3595 | 1159 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1160 | continue; |
1161 | ONE_MORE_BYTE (c1); | |
065e3595 | 1162 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1163 | break; |
1164 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1165 | { |
ff0dacd7 | 1166 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1167 | continue; |
aa72b389 | 1168 | } |
df7492f9 | 1169 | ONE_MORE_BYTE (c2); |
065e3595 | 1170 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1171 | break; |
1172 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1173 | { |
ff0dacd7 | 1174 | found = CATEGORY_MASK_UTF_8; |
df7492f9 | 1175 | continue; |
aa72b389 | 1176 | } |
df7492f9 | 1177 | ONE_MORE_BYTE (c3); |
065e3595 | 1178 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1179 | break; |
1180 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1181 | { |
ff0dacd7 | 1182 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1183 | continue; |
1184 | } | |
1185 | ONE_MORE_BYTE (c4); | |
065e3595 | 1186 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1187 | break; |
1188 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1189 | { | |
ff0dacd7 | 1190 | found = CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1191 | continue; |
1192 | } | |
1193 | break; | |
aa72b389 | 1194 | } |
ff0dacd7 | 1195 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1196 | return 0; |
aa72b389 | 1197 | |
df7492f9 | 1198 | no_more_source: |
065e3595 | 1199 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1200 | { |
ff0dacd7 | 1201 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1202 | return 0; |
aa72b389 | 1203 | } |
ff0dacd7 KH |
1204 | detect_info->found |= found; |
1205 | return 1; | |
aa72b389 KH |
1206 | } |
1207 | ||
4ed46869 | 1208 | |
b73bfc1c | 1209 | static void |
df7492f9 | 1210 | decode_coding_utf_8 (coding) |
b73bfc1c | 1211 | struct coding_system *coding; |
b73bfc1c | 1212 | { |
8f924df7 KH |
1213 | const unsigned char *src = coding->source + coding->consumed; |
1214 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1215 | const unsigned char *src_base; | |
69a80ea3 KH |
1216 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1217 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
1218 | int consumed_chars = 0, consumed_chars_base; |
1219 | int multibytep = coding->src_multibyte; | |
24a73b0a | 1220 | Lisp_Object attr, charset_list; |
4ed46869 | 1221 | |
24a73b0a | 1222 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 KH |
1223 | |
1224 | while (1) | |
b73bfc1c | 1225 | { |
df7492f9 | 1226 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1227 | |
df7492f9 KH |
1228 | src_base = src; |
1229 | consumed_chars_base = consumed_chars; | |
4af310db | 1230 | |
df7492f9 KH |
1231 | if (charbuf >= charbuf_end) |
1232 | break; | |
1233 | ||
1234 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1235 | if (c1 < 0) |
1236 | { | |
1237 | c = - c1; | |
1238 | } | |
1239 | else if (UTF_8_1_OCTET_P(c1)) | |
df7492f9 KH |
1240 | { |
1241 | c = c1; | |
4af310db | 1242 | } |
df7492f9 | 1243 | else |
4af310db | 1244 | { |
df7492f9 | 1245 | ONE_MORE_BYTE (c2); |
065e3595 | 1246 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1247 | goto invalid_code; |
1248 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1249 | { |
b0edb2c5 DL |
1250 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1251 | /* Reject overlong sequences here and below. Encoders | |
1252 | producing them are incorrect, they can be misleading, | |
1253 | and they mess up read/write invariance. */ | |
1254 | if (c < 128) | |
1255 | goto invalid_code; | |
4af310db | 1256 | } |
df7492f9 | 1257 | else |
aa72b389 | 1258 | { |
df7492f9 | 1259 | ONE_MORE_BYTE (c3); |
065e3595 | 1260 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1261 | goto invalid_code; |
1262 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1263 | { |
1264 | c = (((c1 & 0xF) << 12) | |
1265 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1266 | if (c < 0x800 |
1267 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1268 | goto invalid_code; |
1269 | } | |
df7492f9 KH |
1270 | else |
1271 | { | |
1272 | ONE_MORE_BYTE (c4); | |
065e3595 | 1273 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1274 | goto invalid_code; |
1275 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1276 | { |
df7492f9 KH |
1277 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1278 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1279 | if (c < 0x10000) |
1280 | goto invalid_code; | |
1281 | } | |
df7492f9 KH |
1282 | else |
1283 | { | |
1284 | ONE_MORE_BYTE (c5); | |
065e3595 | 1285 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1286 | goto invalid_code; |
1287 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1288 | { | |
1289 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1290 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1291 | | (c5 & 0x3F)); | |
b0edb2c5 | 1292 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1293 | goto invalid_code; |
1294 | } | |
1295 | else | |
1296 | goto invalid_code; | |
1297 | } | |
1298 | } | |
aa72b389 | 1299 | } |
b73bfc1c | 1300 | } |
df7492f9 KH |
1301 | |
1302 | *charbuf++ = c; | |
1303 | continue; | |
1304 | ||
1305 | invalid_code: | |
1306 | src = src_base; | |
1307 | consumed_chars = consumed_chars_base; | |
1308 | ONE_MORE_BYTE (c); | |
1309 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1310 | coding->errors++; | |
aa72b389 KH |
1311 | } |
1312 | ||
df7492f9 KH |
1313 | no_more_source: |
1314 | coding->consumed_char += consumed_chars_base; | |
1315 | coding->consumed = src_base - coding->source; | |
1316 | coding->charbuf_used = charbuf - coding->charbuf; | |
1317 | } | |
1318 | ||
1319 | ||
1320 | static int | |
1321 | encode_coding_utf_8 (coding) | |
1322 | struct coding_system *coding; | |
1323 | { | |
1324 | int multibytep = coding->dst_multibyte; | |
1325 | int *charbuf = coding->charbuf; | |
1326 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1327 | unsigned char *dst = coding->destination + coding->produced; | |
1328 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1329 | int produced_chars = 0; |
df7492f9 KH |
1330 | int c; |
1331 | ||
1332 | if (multibytep) | |
aa72b389 | 1333 | { |
df7492f9 KH |
1334 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1335 | ||
1336 | while (charbuf < charbuf_end) | |
b73bfc1c | 1337 | { |
df7492f9 | 1338 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1339 | |
df7492f9 KH |
1340 | ASSURE_DESTINATION (safe_room); |
1341 | c = *charbuf++; | |
28f67a95 KH |
1342 | if (CHAR_BYTE8_P (c)) |
1343 | { | |
1344 | c = CHAR_TO_BYTE8 (c); | |
1345 | EMIT_ONE_BYTE (c); | |
1346 | } | |
1347 | else | |
1348 | { | |
1349 | CHAR_STRING_ADVANCE (c, pend); | |
1350 | for (p = str; p < pend; p++) | |
1351 | EMIT_ONE_BYTE (*p); | |
1352 | } | |
b73bfc1c | 1353 | } |
aa72b389 | 1354 | } |
df7492f9 KH |
1355 | else |
1356 | { | |
1357 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1358 | ||
1359 | while (charbuf < charbuf_end) | |
b73bfc1c | 1360 | { |
df7492f9 KH |
1361 | ASSURE_DESTINATION (safe_room); |
1362 | c = *charbuf++; | |
f03caae0 KH |
1363 | if (CHAR_BYTE8_P (c)) |
1364 | *dst++ = CHAR_TO_BYTE8 (c); | |
1365 | else | |
1366 | dst += CHAR_STRING (c, dst); | |
df7492f9 | 1367 | produced_chars++; |
4ed46869 KH |
1368 | } |
1369 | } | |
065e3595 | 1370 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1371 | coding->produced_char += produced_chars; |
1372 | coding->produced = dst - coding->destination; | |
1373 | return 0; | |
4ed46869 KH |
1374 | } |
1375 | ||
b73bfc1c | 1376 | |
df7492f9 | 1377 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1378 | Check if a text is encoded in one of UTF-16 based coding systems. |
1379 | If it is, return 1, else return 0. */ | |
aa72b389 | 1380 | |
df7492f9 KH |
1381 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1382 | (((val) & 0xFC00) == 0xD800) | |
1383 | ||
1384 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1385 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1386 | |
df7492f9 KH |
1387 | #define UTF_16_INVALID_P(val) \ |
1388 | (((val) == 0xFFFE) \ | |
1389 | || ((val) == 0xFFFF) \ | |
1390 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1391 | |
aa72b389 | 1392 | |
df7492f9 | 1393 | static int |
ff0dacd7 | 1394 | detect_coding_utf_16 (coding, detect_info) |
aa72b389 | 1395 | struct coding_system *coding; |
ff0dacd7 | 1396 | struct coding_detection_info *detect_info; |
aa72b389 | 1397 | { |
8f924df7 KH |
1398 | const unsigned char *src = coding->source, *src_base = src; |
1399 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
1400 | int multibytep = coding->src_multibyte; |
1401 | int consumed_chars = 0; | |
1402 | int c1, c2; | |
aa72b389 | 1403 | |
ff0dacd7 | 1404 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1405 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1406 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1407 | { |
1408 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1409 | return 0; | |
1410 | } | |
24a73b0a | 1411 | |
df7492f9 KH |
1412 | ONE_MORE_BYTE (c1); |
1413 | ONE_MORE_BYTE (c2); | |
df7492f9 | 1414 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1415 | { |
b49a1807 KH |
1416 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1417 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1418 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1419 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1420 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1421 | } |
df7492f9 | 1422 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1423 | { |
b49a1807 KH |
1424 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1425 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1426 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1427 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1428 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1429 | } | |
065e3595 | 1430 | else if (c1 >= 0 && c2 >= 0) |
24a73b0a | 1431 | { |
24a73b0a KH |
1432 | detect_info->rejected |
1433 | |= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE); | |
ff0dacd7 | 1434 | } |
df7492f9 | 1435 | no_more_source: |
ff0dacd7 | 1436 | return 1; |
df7492f9 | 1437 | } |
aa72b389 | 1438 | |
df7492f9 KH |
1439 | static void |
1440 | decode_coding_utf_16 (coding) | |
1441 | struct coding_system *coding; | |
1442 | { | |
8f924df7 KH |
1443 | const unsigned char *src = coding->source + coding->consumed; |
1444 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1445 | const unsigned char *src_base; | |
69a80ea3 KH |
1446 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1447 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
1448 | int consumed_chars = 0, consumed_chars_base; |
1449 | int multibytep = coding->src_multibyte; | |
1450 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1451 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); | |
1452 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1453 | Lisp_Object attr, charset_list; |
df7492f9 | 1454 | |
24a73b0a | 1455 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1456 | |
b49a1807 | 1457 | if (bom == utf_16_with_bom) |
aa72b389 | 1458 | { |
df7492f9 | 1459 | int c, c1, c2; |
4af310db | 1460 | |
aa72b389 | 1461 | src_base = src; |
df7492f9 KH |
1462 | ONE_MORE_BYTE (c1); |
1463 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1464 | c = (c1 << 8) | c2; |
aa72b389 | 1465 | |
b49a1807 KH |
1466 | if (endian == utf_16_big_endian |
1467 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1468 | { |
b49a1807 KH |
1469 | /* The first two bytes are not BOM. Treat them as bytes |
1470 | for a normal character. */ | |
1471 | src = src_base; | |
1472 | coding->errors++; | |
aa72b389 | 1473 | } |
b49a1807 KH |
1474 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1475 | } | |
1476 | else if (bom == utf_16_detect_bom) | |
1477 | { | |
1478 | /* We have already tried to detect BOM and failed in | |
1479 | detect_coding. */ | |
1480 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; | |
df7492f9 | 1481 | } |
aa72b389 | 1482 | |
df7492f9 KH |
1483 | while (1) |
1484 | { | |
1485 | int c, c1, c2; | |
1486 | ||
1487 | src_base = src; | |
1488 | consumed_chars_base = consumed_chars; | |
1489 | ||
1490 | if (charbuf + 2 >= charbuf_end) | |
1491 | break; | |
1492 | ||
1493 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1494 | if (c1 < 0) |
1495 | { | |
1496 | *charbuf++ = -c1; | |
1497 | continue; | |
1498 | } | |
df7492f9 | 1499 | ONE_MORE_BYTE (c2); |
065e3595 KH |
1500 | if (c2 < 0) |
1501 | { | |
1502 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1503 | *charbuf++ = -c2; | |
1504 | continue; | |
1505 | } | |
df7492f9 | 1506 | c = (endian == utf_16_big_endian |
e19c3639 | 1507 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
df7492f9 | 1508 | if (surrogate) |
fd3ae0b9 | 1509 | { |
df7492f9 | 1510 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1511 | { |
df7492f9 KH |
1512 | if (endian == utf_16_big_endian) |
1513 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1514 | else | |
1515 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1516 | *charbuf++ = c1; | |
1517 | *charbuf++ = c2; | |
1518 | coding->errors++; | |
1519 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1520 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1521 | else |
df7492f9 | 1522 | *charbuf++ = c; |
fd3ae0b9 KH |
1523 | } |
1524 | else | |
df7492f9 KH |
1525 | { |
1526 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1527 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1528 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1529 | } |
fd3ae0b9 | 1530 | } |
aa72b389 | 1531 | else |
df7492f9 KH |
1532 | { |
1533 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1534 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1535 | else | |
1536 | *charbuf++ = c; | |
8f924df7 | 1537 | } |
aa72b389 | 1538 | } |
df7492f9 KH |
1539 | |
1540 | no_more_source: | |
1541 | coding->consumed_char += consumed_chars_base; | |
1542 | coding->consumed = src_base - coding->source; | |
1543 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1544 | } |
b73bfc1c | 1545 | |
df7492f9 KH |
1546 | static int |
1547 | encode_coding_utf_16 (coding) | |
1548 | struct coding_system *coding; | |
1549 | { | |
1550 | int multibytep = coding->dst_multibyte; | |
1551 | int *charbuf = coding->charbuf; | |
1552 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1553 | unsigned char *dst = coding->destination + coding->produced; | |
1554 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1555 | int safe_room = 8; | |
1556 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1557 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; | |
1558 | int produced_chars = 0; | |
24a73b0a | 1559 | Lisp_Object attrs, charset_list; |
df7492f9 | 1560 | int c; |
4ed46869 | 1561 | |
24a73b0a | 1562 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1563 | |
b49a1807 | 1564 | if (bom != utf_16_without_bom) |
df7492f9 KH |
1565 | { |
1566 | ASSURE_DESTINATION (safe_room); | |
1567 | if (big_endian) | |
df7492f9 | 1568 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1569 | else |
1570 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
df7492f9 KH |
1571 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; |
1572 | } | |
1573 | ||
1574 | while (charbuf < charbuf_end) | |
1575 | { | |
1576 | ASSURE_DESTINATION (safe_room); | |
1577 | c = *charbuf++; | |
e19c3639 KH |
1578 | if (c >= MAX_UNICODE_CHAR) |
1579 | c = coding->default_char; | |
df7492f9 KH |
1580 | |
1581 | if (c < 0x10000) | |
1582 | { | |
1583 | if (big_endian) | |
1584 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1585 | else | |
1586 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1587 | } | |
1588 | else | |
1589 | { | |
1590 | int c1, c2; | |
1591 | ||
1592 | c -= 0x10000; | |
1593 | c1 = (c >> 10) + 0xD800; | |
1594 | c2 = (c & 0x3FF) + 0xDC00; | |
1595 | if (big_endian) | |
1596 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1597 | else | |
1598 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1599 | } | |
1600 | } | |
065e3595 | 1601 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1602 | coding->produced = dst - coding->destination; |
1603 | coding->produced_char += produced_chars; | |
1604 | return 0; | |
1605 | } | |
1606 | ||
1607 | \f | |
1608 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1609 | ||
1610 | /* Emacs' internal format for representation of multiple character | |
1611 | sets is a kind of multi-byte encoding, i.e. characters are | |
1612 | represented by variable-length sequences of one-byte codes. | |
1613 | ||
1614 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1615 | represented by one-byte sequences which are their ASCII codes, in | |
1616 | the range 0x00 through 0x7F. | |
1617 | ||
1618 | 8-bit characters of the range 0x80..0x9F are represented by | |
1619 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1620 | code + 0x20). | |
1621 | ||
1622 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1623 | one-byte sequences which are their 8-bit code. | |
1624 | ||
1625 | The other characters are represented by a sequence of `base | |
1626 | leading-code', optional `extended leading-code', and one or two | |
1627 | `position-code's. The length of the sequence is determined by the | |
1628 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1629 | whereas extended leading-code and position-code take the range 0xA0 | |
1630 | through 0xFF. See `charset.h' for more details about leading-code | |
1631 | and position-code. | |
1632 | ||
1633 | --- CODE RANGE of Emacs' internal format --- | |
1634 | character set range | |
1635 | ------------- ----- | |
1636 | ascii 0x00..0x7F | |
1637 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1638 | eight-bit-graphic 0xA0..0xBF | |
1639 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1640 | --------------------------------------------- | |
1641 | ||
1642 | As this is the internal character representation, the format is | |
1643 | usually not used externally (i.e. in a file or in a data sent to a | |
1644 | process). But, it is possible to have a text externally in this | |
1645 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1646 | ||
1647 | In that case, a sequence of one-byte codes has a slightly different | |
1648 | form. | |
1649 | ||
1650 | At first, all characters in eight-bit-control are represented by | |
1651 | one-byte sequences which are their 8-bit code. | |
1652 | ||
1653 | Next, character composition data are represented by the byte | |
1654 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1655 | where, | |
1656 | METHOD is 0xF0 plus one of composition method (enum | |
1657 | composition_method), | |
1658 | ||
1659 | BYTES is 0xA0 plus a byte length of this composition data, | |
1660 | ||
1661 | CHARS is 0x20 plus a number of characters composed by this | |
1662 | data, | |
1663 | ||
1664 | COMPONENTs are characters of multibye form or composition | |
1665 | rules encoded by two-byte of ASCII codes. | |
1666 | ||
1667 | In addition, for backward compatibility, the following formats are | |
1668 | also recognized as composition data on decoding. | |
1669 | ||
1670 | 0x80 MSEQ ... | |
1671 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1672 | ||
1673 | Here, | |
1674 | MSEQ is a multibyte form but in these special format: | |
1675 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1676 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1677 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1678 | represents a composition rule. | |
1679 | */ | |
1680 | ||
1681 | char emacs_mule_bytes[256]; | |
1682 | ||
df7492f9 | 1683 | int |
ff0dacd7 | 1684 | emacs_mule_char (coding, src, nbytes, nchars, id) |
df7492f9 | 1685 | struct coding_system *coding; |
065e3595 | 1686 | const unsigned char *src; |
ff0dacd7 | 1687 | int *nbytes, *nchars, *id; |
df7492f9 | 1688 | { |
8f924df7 KH |
1689 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1690 | const unsigned char *src_base = src; | |
df7492f9 | 1691 | int multibytep = coding->src_multibyte; |
df7492f9 KH |
1692 | struct charset *charset; |
1693 | unsigned code; | |
1694 | int c; | |
1695 | int consumed_chars = 0; | |
1696 | ||
1697 | ONE_MORE_BYTE (c); | |
065e3595 | 1698 | if (c < 0) |
df7492f9 | 1699 | { |
065e3595 KH |
1700 | c = -c; |
1701 | charset = emacs_mule_charset[0]; | |
1702 | } | |
1703 | else | |
1704 | { | |
1705 | switch (emacs_mule_bytes[c]) | |
b73bfc1c | 1706 | { |
065e3595 | 1707 | case 2: |
df7492f9 KH |
1708 | if (! (charset = emacs_mule_charset[c])) |
1709 | goto invalid_code; | |
1710 | ONE_MORE_BYTE (c); | |
9ffd559c | 1711 | if (c < 0xA0) |
065e3595 | 1712 | goto invalid_code; |
df7492f9 | 1713 | code = c & 0x7F; |
065e3595 KH |
1714 | break; |
1715 | ||
1716 | case 3: | |
1717 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
1718 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
1719 | { | |
1720 | ONE_MORE_BYTE (c); | |
9ffd559c | 1721 | if (c < 0xA0 || ! (charset = emacs_mule_charset[c])) |
065e3595 KH |
1722 | goto invalid_code; |
1723 | ONE_MORE_BYTE (c); | |
9ffd559c | 1724 | if (c < 0xA0) |
065e3595 KH |
1725 | goto invalid_code; |
1726 | code = c & 0x7F; | |
1727 | } | |
1728 | else | |
1729 | { | |
1730 | if (! (charset = emacs_mule_charset[c])) | |
1731 | goto invalid_code; | |
1732 | ONE_MORE_BYTE (c); | |
9ffd559c | 1733 | if (c < 0xA0) |
065e3595 KH |
1734 | goto invalid_code; |
1735 | code = (c & 0x7F) << 8; | |
1736 | ONE_MORE_BYTE (c); | |
9ffd559c | 1737 | if (c < 0xA0) |
065e3595 KH |
1738 | goto invalid_code; |
1739 | code |= c & 0x7F; | |
1740 | } | |
1741 | break; | |
1742 | ||
1743 | case 4: | |
1744 | ONE_MORE_BYTE (c); | |
1745 | if (c < 0 || ! (charset = emacs_mule_charset[c])) | |
df7492f9 KH |
1746 | goto invalid_code; |
1747 | ONE_MORE_BYTE (c); | |
9ffd559c | 1748 | if (c < 0xA0) |
065e3595 | 1749 | goto invalid_code; |
781d7a48 | 1750 | code = (c & 0x7F) << 8; |
df7492f9 | 1751 | ONE_MORE_BYTE (c); |
9ffd559c | 1752 | if (c < 0xA0) |
065e3595 | 1753 | goto invalid_code; |
df7492f9 | 1754 | code |= c & 0x7F; |
065e3595 | 1755 | break; |
df7492f9 | 1756 | |
065e3595 KH |
1757 | case 1: |
1758 | code = c; | |
1759 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) | |
1760 | ? charset_ascii : charset_eight_bit); | |
1761 | break; | |
df7492f9 | 1762 | |
065e3595 KH |
1763 | default: |
1764 | abort (); | |
1765 | } | |
1766 | c = DECODE_CHAR (charset, code); | |
1767 | if (c < 0) | |
1768 | goto invalid_code; | |
df7492f9 | 1769 | } |
df7492f9 KH |
1770 | *nbytes = src - src_base; |
1771 | *nchars = consumed_chars; | |
ff0dacd7 KH |
1772 | if (id) |
1773 | *id = charset->id; | |
df7492f9 KH |
1774 | return c; |
1775 | ||
1776 | no_more_source: | |
1777 | return -2; | |
1778 | ||
1779 | invalid_code: | |
1780 | return -1; | |
1781 | } | |
1782 | ||
1783 | ||
1784 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1785 | Check if a text is encoded in `emacs-mule'. If it is, return 1, |
1786 | else return 0. */ | |
df7492f9 KH |
1787 | |
1788 | static int | |
ff0dacd7 | 1789 | detect_coding_emacs_mule (coding, detect_info) |
df7492f9 | 1790 | struct coding_system *coding; |
ff0dacd7 | 1791 | struct coding_detection_info *detect_info; |
df7492f9 | 1792 | { |
065e3595 | 1793 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1794 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1795 | int multibytep = coding->src_multibyte; |
1796 | int consumed_chars = 0; | |
1797 | int c; | |
1798 | int found = 0; | |
1799 | ||
ff0dacd7 | 1800 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1801 | /* A coding system of this category is always ASCII compatible. */ |
1802 | src += coding->head_ascii; | |
1803 | ||
1804 | while (1) | |
1805 | { | |
065e3595 | 1806 | src_base = src; |
df7492f9 | 1807 | ONE_MORE_BYTE (c); |
065e3595 KH |
1808 | if (c < 0) |
1809 | continue; | |
df7492f9 KH |
1810 | if (c == 0x80) |
1811 | { | |
1812 | /* Perhaps the start of composite character. We simple skip | |
1813 | it because analyzing it is too heavy for detecting. But, | |
1814 | at least, we check that the composite character | |
1815 | constitues of more than 4 bytes. */ | |
8f924df7 | 1816 | const unsigned char *src_base; |
df7492f9 KH |
1817 | |
1818 | repeat: | |
1819 | src_base = src; | |
1820 | do | |
1821 | { | |
1822 | ONE_MORE_BYTE (c); | |
1823 | } | |
1824 | while (c >= 0xA0); | |
1825 | ||
1826 | if (src - src_base <= 4) | |
1827 | break; | |
ff0dacd7 | 1828 | found = CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1829 | if (c == 0x80) |
1830 | goto repeat; | |
b73bfc1c | 1831 | } |
df7492f9 KH |
1832 | |
1833 | if (c < 0x80) | |
b73bfc1c | 1834 | { |
df7492f9 KH |
1835 | if (c < 0x20 |
1836 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1837 | break; | |
1838 | } | |
1839 | else | |
1840 | { | |
0e219d54 | 1841 | int more_bytes = emacs_mule_bytes[*src_base] - 1; |
df7492f9 | 1842 | |
0e219d54 | 1843 | while (more_bytes > 0) |
df7492f9 KH |
1844 | { |
1845 | ONE_MORE_BYTE (c); | |
0e219d54 KH |
1846 | if (c < 0xA0) |
1847 | { | |
1848 | src--; /* Unread the last byte. */ | |
1849 | break; | |
1850 | } | |
1851 | more_bytes--; | |
df7492f9 | 1852 | } |
0e219d54 | 1853 | if (more_bytes != 0) |
df7492f9 | 1854 | break; |
ff0dacd7 | 1855 | found = CATEGORY_MASK_EMACS_MULE; |
4ed46869 KH |
1856 | } |
1857 | } | |
ff0dacd7 | 1858 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
df7492f9 KH |
1859 | return 0; |
1860 | ||
1861 | no_more_source: | |
065e3595 | 1862 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 1863 | { |
ff0dacd7 | 1864 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; |
89528eb3 KH |
1865 | return 0; |
1866 | } | |
ff0dacd7 KH |
1867 | detect_info->found |= found; |
1868 | return 1; | |
4ed46869 KH |
1869 | } |
1870 | ||
b73bfc1c | 1871 | |
df7492f9 KH |
1872 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1873 | ||
1874 | /* Decode a character represented as a component of composition | |
1875 | sequence of Emacs 20/21 style at SRC. Set C to that character and | |
1876 | update SRC to the head of next character (or an encoded composition | |
1877 | rule). If SRC doesn't points a composition component, set C to -1. | |
1878 | If SRC points an invalid byte sequence, global exit by a return | |
1879 | value 0. */ | |
1880 | ||
1881 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | |
1882 | if (1) \ | |
1883 | { \ | |
1884 | int c; \ | |
1885 | int nbytes, nchars; \ | |
1886 | \ | |
1887 | if (src == src_end) \ | |
1888 | break; \ | |
ff0dacd7 | 1889 | c = emacs_mule_char (coding, src, &nbytes, &nchars, NULL);\ |
df7492f9 KH |
1890 | if (c < 0) \ |
1891 | { \ | |
1892 | if (c == -2) \ | |
1893 | break; \ | |
1894 | goto invalid_code; \ | |
1895 | } \ | |
1896 | *buf++ = c; \ | |
1897 | src += nbytes; \ | |
1898 | consumed_chars += nchars; \ | |
1899 | } \ | |
1900 | else | |
1901 | ||
1902 | ||
1903 | /* Decode a composition rule represented as a component of composition | |
781d7a48 KH |
1904 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, |
1905 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1906 | to -1. */ | |
df7492f9 | 1907 | |
781d7a48 | 1908 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ |
df7492f9 KH |
1909 | do { \ |
1910 | int c, gref, nref; \ | |
1911 | \ | |
781d7a48 | 1912 | if (src >= src_end) \ |
df7492f9 KH |
1913 | goto invalid_code; \ |
1914 | ONE_MORE_BYTE_NO_CHECK (c); \ | |
781d7a48 | 1915 | c -= 0x20; \ |
df7492f9 KH |
1916 | if (c < 0 || c >= 81) \ |
1917 | goto invalid_code; \ | |
1918 | \ | |
1919 | gref = c / 9, nref = c % 9; \ | |
1920 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1921 | } while (0) | |
1922 | ||
1923 | ||
781d7a48 KH |
1924 | /* Decode a composition rule represented as a component of composition |
1925 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | |
1926 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1927 | to -1. */ | |
1928 | ||
1929 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | |
1930 | do { \ | |
1931 | int gref, nref; \ | |
1932 | \ | |
1933 | if (src + 1>= src_end) \ | |
1934 | goto invalid_code; \ | |
1935 | ONE_MORE_BYTE_NO_CHECK (gref); \ | |
1936 | gref -= 0x20; \ | |
1937 | ONE_MORE_BYTE_NO_CHECK (nref); \ | |
1938 | nref -= 0x20; \ | |
1939 | if (gref < 0 || gref >= 81 \ | |
1940 | || nref < 0 || nref >= 81) \ | |
1941 | goto invalid_code; \ | |
1942 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1943 | } while (0) | |
1944 | ||
1945 | ||
df7492f9 | 1946 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ |
aa72b389 | 1947 | do { \ |
df7492f9 | 1948 | /* Emacs 21 style format. The first three bytes at SRC are \ |
781d7a48 | 1949 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ |
df7492f9 KH |
1950 | the byte length of this composition information, CHARS is the \ |
1951 | number of characters composed by this composition. */ \ | |
781d7a48 KH |
1952 | enum composition_method method = c - 0xF2; \ |
1953 | int *charbuf_base = charbuf; \ | |
df7492f9 KH |
1954 | int consumed_chars_limit; \ |
1955 | int nbytes, nchars; \ | |
1956 | \ | |
1957 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1958 | if (c < 0) \ |
1959 | goto invalid_code; \ | |
df7492f9 KH |
1960 | nbytes = c - 0xA0; \ |
1961 | if (nbytes < 3) \ | |
1962 | goto invalid_code; \ | |
1963 | ONE_MORE_BYTE (c); \ | |
065e3595 KH |
1964 | if (c < 0) \ |
1965 | goto invalid_code; \ | |
df7492f9 | 1966 | nchars = c - 0xA0; \ |
69a80ea3 | 1967 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 KH |
1968 | consumed_chars_limit = consumed_chars_base + nbytes; \ |
1969 | if (method != COMPOSITION_RELATIVE) \ | |
aa72b389 | 1970 | { \ |
df7492f9 KH |
1971 | int i = 0; \ |
1972 | while (consumed_chars < consumed_chars_limit) \ | |
aa72b389 | 1973 | { \ |
df7492f9 | 1974 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ |
781d7a48 | 1975 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ |
df7492f9 KH |
1976 | else \ |
1977 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | |
781d7a48 | 1978 | i++; \ |
aa72b389 | 1979 | } \ |
df7492f9 KH |
1980 | if (consumed_chars < consumed_chars_limit) \ |
1981 | goto invalid_code; \ | |
781d7a48 | 1982 | charbuf_base[0] -= i; \ |
aa72b389 KH |
1983 | } \ |
1984 | } while (0) | |
93dec019 | 1985 | |
aa72b389 | 1986 | |
df7492f9 KH |
1987 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ |
1988 | do { \ | |
1989 | /* Emacs 20 style format for relative composition. */ \ | |
1990 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 1991 | enum composition_method method = COMPOSITION_RELATIVE; \ |
df7492f9 KH |
1992 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
1993 | int *buf = components; \ | |
1994 | int i, j; \ | |
1995 | \ | |
1996 | src = src_base; \ | |
1997 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | |
1998 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
1999 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
2000 | if (i < 2) \ | |
2001 | goto invalid_code; \ | |
69a80ea3 | 2002 | ADD_COMPOSITION_DATA (charbuf, i, method); \ |
df7492f9 KH |
2003 | for (j = 0; j < i; j++) \ |
2004 | *charbuf++ = components[j]; \ | |
2005 | } while (0) | |
2006 | ||
2007 | ||
2008 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | |
2009 | do { \ | |
2010 | /* Emacs 20 style format for rule-base composition. */ \ | |
2011 | /* Store multibyte form of characters to be composed. */ \ | |
ff0dacd7 | 2012 | enum composition_method method = COMPOSITION_WITH_RULE; \ |
df7492f9 KH |
2013 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ |
2014 | int *buf = components; \ | |
2015 | int i, j; \ | |
2016 | \ | |
2017 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
2018 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
2019 | { \ | |
781d7a48 | 2020 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ |
df7492f9 KH |
2021 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
2022 | } \ | |
2023 | if (i < 1 || (buf - components) % 2 == 0) \ | |
2024 | goto invalid_code; \ | |
2025 | if (charbuf + i + (i / 2) + 1 < charbuf_end) \ | |
2026 | goto no_more_source; \ | |
69a80ea3 | 2027 | ADD_COMPOSITION_DATA (buf, i, method); \ |
df7492f9 KH |
2028 | for (j = 0; j < i; j++) \ |
2029 | *charbuf++ = components[j]; \ | |
2030 | for (j = 0; j < i; j += 2) \ | |
2031 | *charbuf++ = components[j]; \ | |
2032 | } while (0) | |
2033 | ||
aa72b389 KH |
2034 | |
2035 | static void | |
df7492f9 | 2036 | decode_coding_emacs_mule (coding) |
aa72b389 | 2037 | struct coding_system *coding; |
aa72b389 | 2038 | { |
8f924df7 KH |
2039 | const unsigned char *src = coding->source + coding->consumed; |
2040 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2041 | const unsigned char *src_base; | |
69a80ea3 KH |
2042 | int *charbuf = coding->charbuf + coding->charbuf_used; |
2043 | int *charbuf_end | |
2044 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 | 2045 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2046 | int multibytep = coding->src_multibyte; |
24a73b0a | 2047 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2048 | int char_offset = coding->produced_char; |
2049 | int last_offset = char_offset; | |
2050 | int last_id = charset_ascii; | |
aa72b389 | 2051 | |
24a73b0a | 2052 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2053 | |
aa72b389 KH |
2054 | while (1) |
2055 | { | |
df7492f9 KH |
2056 | int c; |
2057 | ||
aa72b389 | 2058 | src_base = src; |
df7492f9 KH |
2059 | consumed_chars_base = consumed_chars; |
2060 | ||
2061 | if (charbuf >= charbuf_end) | |
2062 | break; | |
aa72b389 | 2063 | |
df7492f9 | 2064 | ONE_MORE_BYTE (c); |
065e3595 KH |
2065 | if (c < 0) |
2066 | { | |
2067 | *charbuf++ = -c; | |
2068 | char_offset++; | |
2069 | } | |
2070 | else if (c < 0x80) | |
aa72b389 | 2071 | { |
df7492f9 KH |
2072 | *charbuf++ = c; |
2073 | char_offset++; | |
aa72b389 | 2074 | } |
df7492f9 KH |
2075 | else if (c == 0x80) |
2076 | { | |
df7492f9 | 2077 | ONE_MORE_BYTE (c); |
065e3595 KH |
2078 | if (c < 0) |
2079 | goto invalid_code; | |
781d7a48 KH |
2080 | if (c - 0xF2 >= COMPOSITION_RELATIVE |
2081 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | |
df7492f9 KH |
2082 | DECODE_EMACS_MULE_21_COMPOSITION (c); |
2083 | else if (c < 0xC0) | |
2084 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | |
2085 | else if (c == 0xFF) | |
2086 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | |
2087 | else | |
2088 | goto invalid_code; | |
2089 | } | |
2090 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | |
2091 | { | |
2092 | int nbytes, nchars; | |
ff0dacd7 KH |
2093 | int id; |
2094 | ||
781d7a48 KH |
2095 | src = src_base; |
2096 | consumed_chars = consumed_chars_base; | |
ff0dacd7 | 2097 | c = emacs_mule_char (coding, src, &nbytes, &nchars, &id); |
df7492f9 KH |
2098 | if (c < 0) |
2099 | { | |
2100 | if (c == -2) | |
2101 | break; | |
2102 | goto invalid_code; | |
2103 | } | |
ff0dacd7 KH |
2104 | if (last_id != id) |
2105 | { | |
2106 | if (last_id != charset_ascii) | |
69a80ea3 | 2107 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
2108 | last_id = id; |
2109 | last_offset = char_offset; | |
2110 | } | |
df7492f9 | 2111 | *charbuf++ = c; |
781d7a48 KH |
2112 | src += nbytes; |
2113 | consumed_chars += nchars; | |
df7492f9 KH |
2114 | char_offset++; |
2115 | } | |
2116 | continue; | |
2117 | ||
2118 | invalid_code: | |
2119 | src = src_base; | |
2120 | consumed_chars = consumed_chars_base; | |
2121 | ONE_MORE_BYTE (c); | |
2122 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2123 | char_offset++; |
df7492f9 KH |
2124 | coding->errors++; |
2125 | } | |
2126 | ||
2127 | no_more_source: | |
ff0dacd7 | 2128 | if (last_id != charset_ascii) |
69a80ea3 | 2129 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2130 | coding->consumed_char += consumed_chars_base; |
2131 | coding->consumed = src_base - coding->source; | |
2132 | coding->charbuf_used = charbuf - coding->charbuf; | |
2133 | } | |
2134 | ||
2135 | ||
2136 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2137 | do { \ | |
2138 | if (id < 0xA0) \ | |
2139 | codes[0] = id, codes[1] = 0; \ | |
2140 | else if (id < 0xE0) \ | |
2141 | codes[0] = 0x9A, codes[1] = id; \ | |
2142 | else if (id < 0xF0) \ | |
2143 | codes[0] = 0x9B, codes[1] = id; \ | |
2144 | else if (id < 0xF5) \ | |
2145 | codes[0] = 0x9C, codes[1] = id; \ | |
2146 | else \ | |
2147 | codes[0] = 0x9D, codes[1] = id; \ | |
2148 | } while (0); | |
2149 | ||
aa72b389 | 2150 | |
df7492f9 KH |
2151 | static int |
2152 | encode_coding_emacs_mule (coding) | |
2153 | struct coding_system *coding; | |
2154 | { | |
2155 | int multibytep = coding->dst_multibyte; | |
2156 | int *charbuf = coding->charbuf; | |
2157 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2158 | unsigned char *dst = coding->destination + coding->produced; | |
2159 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2160 | int safe_room = 8; | |
df7492f9 | 2161 | int produced_chars = 0; |
24a73b0a | 2162 | Lisp_Object attrs, charset_list; |
df7492f9 | 2163 | int c; |
ff0dacd7 | 2164 | int preferred_charset_id = -1; |
df7492f9 | 2165 | |
24a73b0a | 2166 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2167 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2168 | { | |
2169 | CODING_ATTR_CHARSET_LIST (attrs) | |
2170 | = charset_list = Vemacs_mule_charset_list; | |
2171 | } | |
df7492f9 KH |
2172 | |
2173 | while (charbuf < charbuf_end) | |
2174 | { | |
2175 | ASSURE_DESTINATION (safe_room); | |
2176 | c = *charbuf++; | |
ff0dacd7 KH |
2177 | |
2178 | if (c < 0) | |
2179 | { | |
2180 | /* Handle an annotation. */ | |
2181 | switch (*charbuf) | |
2182 | { | |
2183 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2184 | /* Not yet implemented. */ | |
2185 | break; | |
2186 | case CODING_ANNOTATE_CHARSET_MASK: | |
2187 | preferred_charset_id = charbuf[3]; | |
2188 | if (preferred_charset_id >= 0 | |
2189 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2190 | charset_list))) | |
2191 | preferred_charset_id = -1; | |
2192 | break; | |
2193 | default: | |
2194 | abort (); | |
2195 | } | |
2196 | charbuf += -c - 1; | |
2197 | continue; | |
2198 | } | |
2199 | ||
df7492f9 KH |
2200 | if (ASCII_CHAR_P (c)) |
2201 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2202 | else if (CHAR_BYTE8_P (c)) |
2203 | { | |
2204 | c = CHAR_TO_BYTE8 (c); | |
2205 | EMIT_ONE_BYTE (c); | |
2206 | } | |
df7492f9 | 2207 | else |
aa72b389 | 2208 | { |
df7492f9 KH |
2209 | struct charset *charset; |
2210 | unsigned code; | |
2211 | int dimension; | |
2212 | int emacs_mule_id; | |
2213 | unsigned char leading_codes[2]; | |
2214 | ||
ff0dacd7 KH |
2215 | if (preferred_charset_id >= 0) |
2216 | { | |
2217 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
2218 | if (! CHAR_CHARSET_P (c, charset)) | |
2219 | charset = char_charset (c, charset_list, NULL); | |
2220 | } | |
2221 | else | |
2222 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2223 | if (! charset) |
2224 | { | |
2225 | c = coding->default_char; | |
2226 | if (ASCII_CHAR_P (c)) | |
2227 | { | |
2228 | EMIT_ONE_ASCII_BYTE (c); | |
2229 | continue; | |
2230 | } | |
2231 | charset = char_charset (c, charset_list, &code); | |
2232 | } | |
2233 | dimension = CHARSET_DIMENSION (charset); | |
2234 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2235 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2236 | EMIT_ONE_BYTE (leading_codes[0]); | |
2237 | if (leading_codes[1]) | |
2238 | EMIT_ONE_BYTE (leading_codes[1]); | |
2239 | if (dimension == 1) | |
1fa663f9 | 2240 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2241 | else |
df7492f9 | 2242 | { |
1fa663f9 | 2243 | code |= 0x8080; |
df7492f9 KH |
2244 | EMIT_ONE_BYTE (code >> 8); |
2245 | EMIT_ONE_BYTE (code & 0xFF); | |
2246 | } | |
aa72b389 | 2247 | } |
aa72b389 | 2248 | } |
065e3595 | 2249 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2250 | coding->produced_char += produced_chars; |
2251 | coding->produced = dst - coding->destination; | |
2252 | return 0; | |
aa72b389 | 2253 | } |
b73bfc1c | 2254 | |
4ed46869 | 2255 | \f |
df7492f9 | 2256 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2257 | |
2258 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2259 | Since the intention of this note is to help understand the |
5a936b46 | 2260 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2261 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2262 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2263 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2264 | |
2265 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2266 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2267 | is encoded using bytes less than 128. This may make the encoded |
2268 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2269 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2270 | Significant Bit). |
b73bfc1c | 2271 | |
cfb43547 DL |
2272 | There are two kinds of character sets: control character sets and |
2273 | graphic character sets. The former contain control characters such | |
4ed46869 | 2274 | as `newline' and `escape' to provide control functions (control |
39787efd | 2275 | functions are also provided by escape sequences). The latter |
cfb43547 | 2276 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2277 | two control character sets and many graphic character sets. |
2278 | ||
2279 | Graphic character sets are classified into one of the following | |
39787efd KH |
2280 | four classes, according to the number of bytes (DIMENSION) and |
2281 | number of characters in one dimension (CHARS) of the set: | |
2282 | - DIMENSION1_CHARS94 | |
2283 | - DIMENSION1_CHARS96 | |
2284 | - DIMENSION2_CHARS94 | |
2285 | - DIMENSION2_CHARS96 | |
2286 | ||
2287 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2288 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2289 | hereafter). The <F> of each character set is decided by ECMA(*) |
2290 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2291 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2292 | |
2293 | Note (*): ECMA = European Computer Manufacturers Association | |
2294 | ||
cfb43547 | 2295 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2296 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2297 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2298 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2299 | o DIMENSION2_CHARS96 -- none for the moment | |
2300 | ||
39787efd | 2301 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2302 | C0 [0x00..0x1F] -- control character plane 0 |
2303 | GL [0x20..0x7F] -- graphic character plane 0 | |
2304 | C1 [0x80..0x9F] -- control character plane 1 | |
2305 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2306 | ||
2307 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2308 | C1 by an escape sequence. The most common case is that: |
2309 | - ISO646's control character set is designated/invoked to C0, and | |
2310 | - ISO6429's control character set is designated/invoked to C1, | |
2311 | and usually these designations/invocations are omitted in encoded | |
2312 | text. In a 7-bit environment, only C0 can be used, and a control | |
2313 | character for C1 is encoded by an appropriate escape sequence to | |
2314 | fit into the environment. All control characters for C1 are | |
2315 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2316 | |
2317 | A graphic character set is at first designated to one of four | |
2318 | graphic registers (G0 through G3), then these graphic registers are | |
2319 | invoked to GL or GR. These designations and invocations can be | |
2320 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2321 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2322 | these invocations and designations are omitted in encoded text. | |
2323 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2324 | |
39787efd KH |
2325 | When a graphic character set of CHARS94 is invoked to GL, codes |
2326 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2327 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2328 | be used. | |
4ed46869 KH |
2329 | |
2330 | There are two ways of invocation: locking-shift and single-shift. | |
2331 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2332 | invocation, whereas with single-shift, the invocation affects the |
2333 | following character only and doesn't affect the locking-shift | |
2334 | state. Invocations are done by the following control characters or | |
2335 | escape sequences: | |
4ed46869 KH |
2336 | |
2337 | ---------------------------------------------------------------------- | |
39787efd | 2338 | abbrev function cntrl escape seq description |
4ed46869 | 2339 | ---------------------------------------------------------------------- |
39787efd KH |
2340 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2341 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2342 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2343 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2344 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2345 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2346 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2347 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2348 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2349 | ---------------------------------------------------------------------- |
39787efd KH |
2350 | (*) These are not used by any known coding system. |
2351 | ||
2352 | Control characters for these functions are defined by macros | |
2353 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2354 | |
39787efd | 2355 | Designations are done by the following escape sequences: |
4ed46869 KH |
2356 | ---------------------------------------------------------------------- |
2357 | escape sequence description | |
2358 | ---------------------------------------------------------------------- | |
2359 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2360 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2361 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2362 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2363 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2364 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2365 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2366 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2367 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2368 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2369 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2370 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2371 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2372 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2373 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2374 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2375 | ---------------------------------------------------------------------- | |
2376 | ||
2377 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2378 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2379 | |
2380 | Note (*): Although these designations are not allowed in ISO2022, | |
2381 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2382 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2383 | 7-bit environment, non-locking-shift, and non-single-shift. |
2384 | ||
2385 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2386 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2387 | |
cfb43547 | 2388 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2389 | same multilingual text in ISO2022. Actually, there exist many |
2390 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2391 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2392 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2393 | localized platforms), and all of these are variants of ISO2022. |
2394 | ||
2395 | In addition to the above, Emacs handles two more kinds of escape | |
2396 | sequences: ISO6429's direction specification and Emacs' private | |
2397 | sequence for specifying character composition. | |
2398 | ||
39787efd | 2399 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2400 | o CSI ']' -- end of the current direction |
2401 | o CSI '0' ']' -- end of the current direction | |
2402 | o CSI '1' ']' -- start of left-to-right text | |
2403 | o CSI '2' ']' -- start of right-to-left text | |
2404 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2405 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2406 | ||
2407 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2408 | o ESC '0' -- start relative composition |
2409 | o ESC '1' -- end composition | |
2410 | o ESC '2' -- start rule-base composition (*) | |
2411 | o ESC '3' -- start relative composition with alternate chars (**) | |
2412 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2413 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2414 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2415 | |
5a936b46 DL |
2416 | (*) This form is used only in Emacs 20.7 and older versions, |
2417 | but newer versions can safely decode it. | |
cfb43547 | 2418 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2419 | and older versions can't decode it. |
ec6d2bb8 | 2420 | |
cfb43547 | 2421 | Here's a list of example usages of these composition escape |
b73bfc1c | 2422 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2423 | |
b73bfc1c | 2424 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2425 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2426 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2427 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2428 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2429 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2430 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2431 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2432 | |
2433 | enum iso_code_class_type iso_code_class[256]; | |
2434 | ||
df7492f9 KH |
2435 | #define SAFE_CHARSET_P(coding, id) \ |
2436 | ((id) <= (coding)->max_charset_id \ | |
2437 | && (coding)->safe_charsets[id] >= 0) | |
2438 | ||
2439 | ||
2440 | #define SHIFT_OUT_OK(category) \ | |
2441 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2442 | ||
2443 | static void | |
f0064e1f DL |
2444 | setup_iso_safe_charsets (attrs) |
2445 | Lisp_Object attrs; | |
df7492f9 KH |
2446 | { |
2447 | Lisp_Object charset_list, safe_charsets; | |
2448 | Lisp_Object request; | |
2449 | Lisp_Object reg_usage; | |
2450 | Lisp_Object tail; | |
2451 | int reg94, reg96; | |
2452 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2453 | int max_charset_id; | |
2454 | ||
2455 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2456 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2457 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2458 | { | |
2459 | CODING_ATTR_CHARSET_LIST (attrs) | |
2460 | = charset_list = Viso_2022_charset_list; | |
2461 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2462 | } | |
2463 | ||
2464 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2465 | return; | |
2466 | ||
2467 | max_charset_id = 0; | |
2468 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2469 | { | |
2470 | int id = XINT (XCAR (tail)); | |
2471 | if (max_charset_id < id) | |
2472 | max_charset_id = id; | |
2473 | } | |
d46c5b12 | 2474 | |
df7492f9 KH |
2475 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
2476 | make_number (255)); | |
2477 | request = AREF (attrs, coding_attr_iso_request); | |
2478 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2479 | reg94 = XINT (XCAR (reg_usage)); | |
2480 | reg96 = XINT (XCDR (reg_usage)); | |
2481 | ||
2482 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2483 | { | |
2484 | Lisp_Object id; | |
2485 | Lisp_Object reg; | |
2486 | struct charset *charset; | |
2487 | ||
2488 | id = XCAR (tail); | |
2489 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2490 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2491 | if (! NILP (reg)) |
8f924df7 | 2492 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2493 | else if (charset->iso_chars_96) |
2494 | { | |
2495 | if (reg96 < 4) | |
8f924df7 | 2496 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2497 | } |
2498 | else | |
2499 | { | |
2500 | if (reg94 < 4) | |
8f924df7 | 2501 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2502 | } |
2503 | } | |
2504 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2505 | } | |
d46c5b12 | 2506 | |
b6871cc7 | 2507 | |
4ed46869 | 2508 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
2509 | Check if a text is encoded in one of ISO-2022 based codig systems. |
2510 | If it is, return 1, else return 0. */ | |
4ed46869 | 2511 | |
0a28aafb | 2512 | static int |
ff0dacd7 | 2513 | detect_coding_iso_2022 (coding, detect_info) |
df7492f9 | 2514 | struct coding_system *coding; |
ff0dacd7 | 2515 | struct coding_detection_info *detect_info; |
4ed46869 | 2516 | { |
8f924df7 KH |
2517 | const unsigned char *src = coding->source, *src_base = src; |
2518 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2519 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2520 | int single_shifting = 0; |
df7492f9 KH |
2521 | int id; |
2522 | int c, c1; | |
2523 | int consumed_chars = 0; | |
2524 | int i; | |
ff0dacd7 KH |
2525 | int rejected = 0; |
2526 | int found = 0; | |
2527 | ||
2528 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2529 | |
2530 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2531 | { | |
2532 | struct coding_system *this = &(coding_categories[i]); | |
2533 | Lisp_Object attrs, val; | |
2534 | ||
2535 | attrs = CODING_ID_ATTRS (this->id); | |
2536 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
2537 | && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list)) | |
2538 | setup_iso_safe_charsets (attrs); | |
2539 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
2540 | this->max_charset_id = SCHARS (val) - 1; |
2541 | this->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
2542 | } |
2543 | ||
2544 | /* A coding system of this category is always ASCII compatible. */ | |
2545 | src += coding->head_ascii; | |
3f003981 | 2546 | |
ff0dacd7 | 2547 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2548 | { |
065e3595 | 2549 | src_base = src; |
df7492f9 | 2550 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2551 | switch (c) |
2552 | { | |
2553 | case ISO_CODE_ESC: | |
74383408 KH |
2554 | if (inhibit_iso_escape_detection) |
2555 | break; | |
f46869e4 | 2556 | single_shifting = 0; |
df7492f9 | 2557 | ONE_MORE_BYTE (c); |
d46c5b12 | 2558 | if (c >= '(' && c <= '/') |
4ed46869 | 2559 | { |
bf9cdd4e | 2560 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 2561 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2562 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2563 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
2564 | /* Invalid designation sequence. Just ignore. */ |
2565 | break; | |
bf9cdd4e KH |
2566 | } |
2567 | else if (c == '$') | |
2568 | { | |
2569 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 2570 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
2571 | if (c >= '@' && c <= 'B') |
2572 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 2573 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 2574 | else if (c >= '(' && c <= '/') |
bcf26d6a | 2575 | { |
df7492f9 | 2576 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2577 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2578 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
2579 | /* Invalid designation sequence. Just ignore. */ |
2580 | break; | |
bcf26d6a | 2581 | } |
bf9cdd4e | 2582 | else |
ff0dacd7 | 2583 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
2584 | break; |
2585 | } | |
ae9ff118 | 2586 | else if (c == 'N' || c == 'O') |
d46c5b12 | 2587 | { |
ae9ff118 | 2588 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2589 | single_shifting = 1; |
2590 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 2591 | break; |
4ed46869 | 2592 | } |
ec6d2bb8 KH |
2593 | else if (c >= '0' && c <= '4') |
2594 | { | |
2595 | /* ESC <Fp> for start/end composition. */ | |
ff0dacd7 | 2596 | found |= CATEGORY_MASK_ISO; |
ec6d2bb8 KH |
2597 | break; |
2598 | } | |
bf9cdd4e | 2599 | else |
df7492f9 | 2600 | { |
ff0dacd7 | 2601 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
2602 | break; |
2603 | } | |
d46c5b12 KH |
2604 | |
2605 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 2606 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
2607 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
2608 | id)) | |
ff0dacd7 | 2609 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 2610 | else |
ff0dacd7 | 2611 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
2612 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
2613 | id)) | |
ff0dacd7 | 2614 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 2615 | else |
ff0dacd7 | 2616 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
2617 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
2618 | id)) | |
ff0dacd7 | 2619 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 2620 | else |
ff0dacd7 | 2621 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
2622 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
2623 | id)) | |
ff0dacd7 | 2624 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 2625 | else |
ff0dacd7 | 2626 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
2627 | break; |
2628 | ||
4ed46869 | 2629 | case ISO_CODE_SO: |
d46c5b12 | 2630 | case ISO_CODE_SI: |
ff0dacd7 | 2631 | /* Locking shift out/in. */ |
74383408 KH |
2632 | if (inhibit_iso_escape_detection) |
2633 | break; | |
f46869e4 | 2634 | single_shifting = 0; |
ff0dacd7 KH |
2635 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
2636 | found |= CATEGORY_MASK_ISO_ELSE; | |
d46c5b12 KH |
2637 | break; |
2638 | ||
4ed46869 | 2639 | case ISO_CODE_CSI: |
ff0dacd7 | 2640 | /* Control sequence introducer. */ |
f46869e4 | 2641 | single_shifting = 0; |
ff0dacd7 KH |
2642 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2643 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
2644 | goto check_extra_latin; | |
2645 | ||
4ed46869 KH |
2646 | case ISO_CODE_SS2: |
2647 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
2648 | /* Single shift. */ |
2649 | if (inhibit_iso_escape_detection) | |
2650 | break; | |
75e2a253 | 2651 | single_shifting = 0; |
ff0dacd7 KH |
2652 | rejected |= CATEGORY_MASK_ISO_7BIT; |
2653 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2654 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 2655 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
2656 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
2657 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
2658 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
2659 | if (single_shifting) | |
2660 | break; | |
ff0dacd7 | 2661 | goto check_extra_latin; |
4ed46869 KH |
2662 | |
2663 | default: | |
065e3595 KH |
2664 | if (c < 0) |
2665 | continue; | |
4ed46869 | 2666 | if (c < 0x80) |
f46869e4 KH |
2667 | { |
2668 | single_shifting = 0; | |
2669 | break; | |
2670 | } | |
ff0dacd7 | 2671 | if (c >= 0xA0) |
c4825358 | 2672 | { |
ff0dacd7 KH |
2673 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
2674 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 2675 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
2676 | 0xA0..0FF. If the byte length is even, we include |
2677 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
2678 | only when we are not single shifting. */ | |
2679 | if (! single_shifting | |
2680 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 2681 | { |
e17de821 | 2682 | int i = 1; |
b73bfc1c KH |
2683 | while (src < src_end) |
2684 | { | |
df7492f9 | 2685 | ONE_MORE_BYTE (c); |
b73bfc1c KH |
2686 | if (c < 0xA0) |
2687 | break; | |
2688 | i++; | |
2689 | } | |
2690 | ||
2691 | if (i & 1 && src < src_end) | |
ff0dacd7 | 2692 | rejected |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2693 | else |
ff0dacd7 | 2694 | found |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2695 | } |
ff0dacd7 | 2696 | break; |
4ed46869 | 2697 | } |
ff0dacd7 KH |
2698 | check_extra_latin: |
2699 | single_shifting = 0; | |
2700 | if (! VECTORP (Vlatin_extra_code_table) | |
2701 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
2702 | { | |
2703 | rejected = CATEGORY_MASK_ISO; | |
2704 | break; | |
2705 | } | |
2706 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
2707 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2708 | found |= CATEGORY_MASK_ISO_8_1; | |
2709 | else | |
2710 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 2711 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
2712 | } |
2713 | } | |
ff0dacd7 KH |
2714 | detect_info->rejected |= CATEGORY_MASK_ISO; |
2715 | return 0; | |
4ed46869 | 2716 | |
df7492f9 | 2717 | no_more_source: |
ff0dacd7 KH |
2718 | detect_info->rejected |= rejected; |
2719 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 2720 | return 1; |
4ed46869 | 2721 | } |
ec6d2bb8 | 2722 | |
4ed46869 | 2723 | |
134b9549 KH |
2724 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
2725 | escape sequence should be kept. */ | |
df7492f9 KH |
2726 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
2727 | do { \ | |
2728 | int id, prev; \ | |
2729 | \ | |
2730 | if (final < '0' || final >= 128 \ | |
2731 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
2732 | || !SAFE_CHARSET_P (coding, id)) \ | |
2733 | { \ | |
2734 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
2735 | chars_96 = -1; \ |
2736 | break; \ | |
df7492f9 KH |
2737 | } \ |
2738 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
2739 | if (id == charset_jisx0201_roman) \ |
2740 | { \ | |
2741 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
2742 | id = charset_ascii; \ | |
2743 | } \ | |
2744 | else if (id == charset_jisx0208_1978) \ | |
2745 | { \ | |
2746 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
2747 | id = charset_jisx0208; \ | |
2748 | } \ | |
df7492f9 KH |
2749 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
2750 | /* If there was an invalid designation to REG previously, and this \ | |
2751 | designation is ASCII to REG, we should keep this designation \ | |
2752 | sequence. */ \ | |
2753 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 2754 | chars_96 = -1; \ |
4ed46869 KH |
2755 | } while (0) |
2756 | ||
d46c5b12 | 2757 | |
df7492f9 KH |
2758 | #define MAYBE_FINISH_COMPOSITION() \ |
2759 | do { \ | |
2760 | int i; \ | |
2761 | if (composition_state == COMPOSING_NO) \ | |
2762 | break; \ | |
2763 | /* It is assured that we have enough room for producing \ | |
2764 | characters stored in the table `components'. */ \ | |
2765 | if (charbuf + component_idx > charbuf_end) \ | |
2766 | goto no_more_source; \ | |
2767 | composition_state = COMPOSING_NO; \ | |
2768 | if (method == COMPOSITION_RELATIVE \ | |
2769 | || method == COMPOSITION_WITH_ALTCHARS) \ | |
2770 | { \ | |
2771 | for (i = 0; i < component_idx; i++) \ | |
2772 | *charbuf++ = components[i]; \ | |
2773 | char_offset += component_idx; \ | |
2774 | } \ | |
2775 | else \ | |
2776 | { \ | |
2777 | for (i = 0; i < component_idx; i += 2) \ | |
2778 | *charbuf++ = components[i]; \ | |
2779 | char_offset += (component_idx / 2) + 1; \ | |
2780 | } \ | |
2781 | } while (0) | |
2782 | ||
d46c5b12 | 2783 | |
aa72b389 KH |
2784 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
2785 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | |
2786 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
2787 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
2788 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
aa72b389 | 2789 | */ |
ec6d2bb8 | 2790 | |
df7492f9 KH |
2791 | #define DECODE_COMPOSITION_START(c1) \ |
2792 | do { \ | |
2793 | if (c1 == '0' \ | |
781d7a48 | 2794 | && composition_state == COMPOSING_COMPONENT_RULE) \ |
df7492f9 KH |
2795 | { \ |
2796 | component_len = component_idx; \ | |
2797 | composition_state = COMPOSING_CHAR; \ | |
2798 | } \ | |
2799 | else \ | |
2800 | { \ | |
8f924df7 | 2801 | const unsigned char *p; \ |
df7492f9 KH |
2802 | \ |
2803 | MAYBE_FINISH_COMPOSITION (); \ | |
2804 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | |
2805 | goto no_more_source; \ | |
2806 | for (p = src; p < src_end - 1; p++) \ | |
2807 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | |
2808 | break; \ | |
2809 | if (p == src_end - 1) \ | |
2810 | { \ | |
2811 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ | |
2812 | goto invalid_code; \ | |
2813 | goto no_more_source; \ | |
2814 | } \ | |
2815 | \ | |
2816 | /* This is surely the start of a composition. */ \ | |
2817 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
2818 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
2819 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
2820 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
2821 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | |
2822 | : COMPOSING_COMPONENT_CHAR); \ | |
2823 | component_idx = component_len = 0; \ | |
2824 | } \ | |
ec6d2bb8 KH |
2825 | } while (0) |
2826 | ||
ec6d2bb8 | 2827 | |
df7492f9 KH |
2828 | /* Handle compositoin end sequence ESC 1. */ |
2829 | ||
2830 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 2831 | do { \ |
df7492f9 KH |
2832 | int nchars = (component_len > 0 ? component_idx - component_len \ |
2833 | : method == COMPOSITION_RELATIVE ? component_idx \ | |
2834 | : (component_idx + 1) / 2); \ | |
2835 | int i; \ | |
2836 | int *saved_charbuf = charbuf; \ | |
2837 | \ | |
69a80ea3 | 2838 | ADD_COMPOSITION_DATA (charbuf, nchars, method); \ |
df7492f9 | 2839 | if (method != COMPOSITION_RELATIVE) \ |
ec6d2bb8 | 2840 | { \ |
df7492f9 KH |
2841 | if (component_len == 0) \ |
2842 | for (i = 0; i < component_idx; i++) \ | |
2843 | *charbuf++ = components[i]; \ | |
2844 | else \ | |
2845 | for (i = 0; i < component_len; i++) \ | |
2846 | *charbuf++ = components[i]; \ | |
2847 | *saved_charbuf = saved_charbuf - charbuf; \ | |
ec6d2bb8 | 2848 | } \ |
df7492f9 KH |
2849 | if (method == COMPOSITION_WITH_RULE) \ |
2850 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | |
2851 | *charbuf++ = components[i]; \ | |
ec6d2bb8 | 2852 | else \ |
df7492f9 KH |
2853 | for (i = component_len; i < component_idx; i++, char_offset++) \ |
2854 | *charbuf++ = components[i]; \ | |
2855 | coding->annotated = 1; \ | |
2856 | composition_state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
2857 | } while (0) |
2858 | ||
df7492f9 | 2859 | |
ec6d2bb8 KH |
2860 | /* Decode a composition rule from the byte C1 (and maybe one more byte |
2861 | from SRC) and store one encoded composition rule in | |
2862 | coding->cmp_data. */ | |
2863 | ||
2864 | #define DECODE_COMPOSITION_RULE(c1) \ | |
2865 | do { \ | |
ec6d2bb8 KH |
2866 | (c1) -= 32; \ |
2867 | if (c1 < 81) /* old format (before ver.21) */ \ | |
2868 | { \ | |
2869 | int gref = (c1) / 9; \ | |
2870 | int nref = (c1) % 9; \ | |
2871 | if (gref == 4) gref = 10; \ | |
2872 | if (nref == 4) nref = 10; \ | |
df7492f9 | 2873 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ |
ec6d2bb8 | 2874 | } \ |
b73bfc1c | 2875 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
2876 | { \ |
2877 | ONE_MORE_BYTE (c2); \ | |
df7492f9 | 2878 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
ec6d2bb8 | 2879 | } \ |
df7492f9 KH |
2880 | else \ |
2881 | c1 = 0; \ | |
ec6d2bb8 | 2882 | } while (0) |
88993dfd | 2883 | |
d46c5b12 | 2884 | |
4ed46869 KH |
2885 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
2886 | ||
b73bfc1c | 2887 | static void |
df7492f9 | 2888 | decode_coding_iso_2022 (coding) |
4ed46869 | 2889 | struct coding_system *coding; |
4ed46869 | 2890 | { |
8f924df7 KH |
2891 | const unsigned char *src = coding->source + coding->consumed; |
2892 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2893 | const unsigned char *src_base; | |
69a80ea3 | 2894 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ff0dacd7 | 2895 | int *charbuf_end |
69a80ea3 | 2896 | = coding->charbuf + coding->charbuf_size - 4 - MAX_ANNOTATION_LENGTH; |
df7492f9 | 2897 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2898 | int multibytep = coding->src_multibyte; |
4ed46869 | 2899 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
2900 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
2901 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 2902 | int charset_id_2, charset_id_3; |
df7492f9 KH |
2903 | struct charset *charset; |
2904 | int c; | |
2905 | /* For handling composition sequence. */ | |
2906 | #define COMPOSING_NO 0 | |
2907 | #define COMPOSING_CHAR 1 | |
2908 | #define COMPOSING_RULE 2 | |
2909 | #define COMPOSING_COMPONENT_CHAR 3 | |
2910 | #define COMPOSING_COMPONENT_RULE 4 | |
2911 | ||
2912 | int composition_state = COMPOSING_NO; | |
2913 | enum composition_method method; | |
2914 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | |
2915 | int component_idx; | |
2916 | int component_len; | |
24a73b0a | 2917 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2918 | int char_offset = coding->produced_char; |
2919 | int last_offset = char_offset; | |
2920 | int last_id = charset_ascii; | |
df7492f9 | 2921 | |
24a73b0a | 2922 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 2923 | setup_iso_safe_charsets (attrs); |
b73bfc1c KH |
2924 | |
2925 | while (1) | |
4ed46869 | 2926 | { |
463f5630 | 2927 | int c1, c2; |
b73bfc1c KH |
2928 | |
2929 | src_base = src; | |
df7492f9 KH |
2930 | consumed_chars_base = consumed_chars; |
2931 | ||
2932 | if (charbuf >= charbuf_end) | |
2933 | break; | |
2934 | ||
b73bfc1c | 2935 | ONE_MORE_BYTE (c1); |
065e3595 KH |
2936 | if (c1 < 0) |
2937 | goto invalid_code; | |
4ed46869 | 2938 | |
98725083 | 2939 | /* We produce at most one character. */ |
4ed46869 KH |
2940 | switch (iso_code_class [c1]) |
2941 | { | |
2942 | case ISO_0x20_or_0x7F: | |
df7492f9 | 2943 | if (composition_state != COMPOSING_NO) |
ec6d2bb8 | 2944 | { |
df7492f9 KH |
2945 | if (composition_state == COMPOSING_RULE |
2946 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2947 | { | |
2948 | DECODE_COMPOSITION_RULE (c1); | |
2949 | components[component_idx++] = c1; | |
2950 | composition_state--; | |
2951 | continue; | |
2952 | } | |
4ed46869 | 2953 | } |
df7492f9 KH |
2954 | if (charset_id_0 < 0 |
2955 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
2956 | /* This is SPACE or DEL. */ |
2957 | charset = CHARSET_FROM_ID (charset_ascii); | |
2958 | else | |
2959 | charset = CHARSET_FROM_ID (charset_id_0); | |
2960 | break; | |
4ed46869 KH |
2961 | |
2962 | case ISO_graphic_plane_0: | |
781d7a48 | 2963 | if (composition_state != COMPOSING_NO) |
b73bfc1c | 2964 | { |
781d7a48 KH |
2965 | if (composition_state == COMPOSING_RULE |
2966 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2967 | { | |
2968 | DECODE_COMPOSITION_RULE (c1); | |
2969 | components[component_idx++] = c1; | |
2970 | composition_state--; | |
2971 | continue; | |
2972 | } | |
b73bfc1c | 2973 | } |
134b9549 KH |
2974 | if (charset_id_0 < 0) |
2975 | charset = CHARSET_FROM_ID (charset_ascii); | |
2976 | else | |
2977 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
2978 | break; |
2979 | ||
2980 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
2981 | if (charset_id_1 < 0 |
2982 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
2983 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
2984 | goto invalid_code; | |
4ed46869 KH |
2985 | /* This is a graphic character, we fall down ... */ |
2986 | ||
2987 | case ISO_graphic_plane_1: | |
df7492f9 KH |
2988 | if (charset_id_1 < 0) |
2989 | goto invalid_code; | |
2990 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
2991 | break; |
2992 | ||
df7492f9 KH |
2993 | case ISO_control_0: |
2994 | MAYBE_FINISH_COMPOSITION (); | |
2995 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
2996 | break; |
2997 | ||
df7492f9 KH |
2998 | case ISO_control_1: |
2999 | MAYBE_FINISH_COMPOSITION (); | |
3000 | goto invalid_code; | |
3001 | ||
4ed46869 | 3002 | case ISO_shift_out: |
df7492f9 KH |
3003 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3004 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3005 | goto invalid_code; | |
3006 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3007 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3008 | continue; |
4ed46869 KH |
3009 | |
3010 | case ISO_shift_in: | |
df7492f9 KH |
3011 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3012 | goto invalid_code; | |
3013 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3014 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3015 | continue; |
4ed46869 KH |
3016 | |
3017 | case ISO_single_shift_2_7: | |
3018 | case ISO_single_shift_2: | |
df7492f9 KH |
3019 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3020 | goto invalid_code; | |
4ed46869 KH |
3021 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3022 | c1 = 'N'; | |
3023 | goto label_escape_sequence; | |
3024 | ||
3025 | case ISO_single_shift_3: | |
df7492f9 KH |
3026 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3027 | goto invalid_code; | |
4ed46869 KH |
3028 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3029 | c1 = 'O'; | |
3030 | goto label_escape_sequence; | |
3031 | ||
3032 | case ISO_control_sequence_introducer: | |
3033 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3034 | c1 = '['; | |
3035 | goto label_escape_sequence; | |
3036 | ||
3037 | case ISO_escape: | |
3038 | ONE_MORE_BYTE (c1); | |
3039 | label_escape_sequence: | |
df7492f9 | 3040 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3041 | designation, direction specification, and character |
3042 | composition specification. */ | |
3043 | switch (c1) | |
3044 | { | |
3045 | case '&': /* revision of following character set */ | |
3046 | ONE_MORE_BYTE (c1); | |
3047 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3048 | goto invalid_code; |
4ed46869 KH |
3049 | ONE_MORE_BYTE (c1); |
3050 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3051 | goto invalid_code; |
4ed46869 KH |
3052 | ONE_MORE_BYTE (c1); |
3053 | goto label_escape_sequence; | |
3054 | ||
3055 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3056 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3057 | goto invalid_code; | |
134b9549 KH |
3058 | { |
3059 | int reg, chars96; | |
3060 | ||
3061 | ONE_MORE_BYTE (c1); | |
3062 | if (c1 >= '@' && c1 <= 'B') | |
3063 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3064 | or JISX0208.1980 */ |
134b9549 KH |
3065 | reg = 0, chars96 = 0; |
3066 | } | |
3067 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3068 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3069 | reg = c1 - 0x28, chars96 = 0; | |
3070 | ONE_MORE_BYTE (c1); | |
3071 | } | |
3072 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3073 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3074 | reg = c1 - 0x2C, chars96 = 1; | |
3075 | ONE_MORE_BYTE (c1); | |
3076 | } | |
3077 | else | |
3078 | goto invalid_code; | |
3079 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3080 | /* We must update these variables now. */ | |
3081 | if (reg == 0) | |
3082 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3083 | else if (reg == 1) | |
3084 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3085 | if (chars96 < 0) | |
3086 | goto invalid_code; | |
3087 | } | |
b73bfc1c | 3088 | continue; |
4ed46869 KH |
3089 | |
3090 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3091 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3092 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3093 | goto invalid_code; | |
3094 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3095 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3096 | continue; |
4ed46869 KH |
3097 | |
3098 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3099 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3100 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3101 | goto invalid_code; | |
3102 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3103 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3104 | continue; |
4ed46869 KH |
3105 | |
3106 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3107 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3108 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3109 | goto invalid_code; | |
134b9549 KH |
3110 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3111 | if (charset_id_2 < 0) | |
3112 | charset = CHARSET_FROM_ID (charset_ascii); | |
3113 | else | |
3114 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3115 | ONE_MORE_BYTE (c1); |
e7046a18 | 3116 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3117 | goto invalid_code; |
4ed46869 KH |
3118 | break; |
3119 | ||
3120 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3121 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3122 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3123 | goto invalid_code; | |
134b9549 KH |
3124 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3125 | if (charset_id_3 < 0) | |
3126 | charset = CHARSET_FROM_ID (charset_ascii); | |
3127 | else | |
3128 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3129 | ONE_MORE_BYTE (c1); |
e7046a18 | 3130 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3131 | goto invalid_code; |
4ed46869 KH |
3132 | break; |
3133 | ||
ec6d2bb8 | 3134 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3135 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3136 | goto invalid_code; | |
ec6d2bb8 | 3137 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3138 | continue; |
4ed46869 | 3139 | |
ec6d2bb8 | 3140 | case '1': /* end composition */ |
df7492f9 KH |
3141 | if (composition_state == COMPOSING_NO) |
3142 | goto invalid_code; | |
3143 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3144 | continue; |
4ed46869 KH |
3145 | |
3146 | case '[': /* specification of direction */ | |
df7492f9 KH |
3147 | if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION) |
3148 | goto invalid_code; | |
4ed46869 | 3149 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3150 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 3151 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
3152 | ONE_MORE_BYTE (c1); |
3153 | switch (c1) | |
3154 | { | |
3155 | case ']': /* end of the current direction */ | |
d46c5b12 | 3156 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3157 | |
3158 | case '0': /* end of the current direction */ | |
3159 | case '1': /* start of left-to-right direction */ | |
3160 | ONE_MORE_BYTE (c1); | |
3161 | if (c1 == ']') | |
d46c5b12 | 3162 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3163 | else |
df7492f9 | 3164 | goto invalid_code; |
4ed46869 KH |
3165 | break; |
3166 | ||
3167 | case '2': /* start of right-to-left direction */ | |
3168 | ONE_MORE_BYTE (c1); | |
3169 | if (c1 == ']') | |
d46c5b12 | 3170 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3171 | else |
df7492f9 | 3172 | goto invalid_code; |
4ed46869 KH |
3173 | break; |
3174 | ||
3175 | default: | |
df7492f9 | 3176 | goto invalid_code; |
4ed46869 | 3177 | } |
b73bfc1c | 3178 | continue; |
4ed46869 | 3179 | |
103e0180 | 3180 | case '%': |
103e0180 KH |
3181 | ONE_MORE_BYTE (c1); |
3182 | if (c1 == '/') | |
3183 | { | |
3184 | /* CTEXT extended segment: | |
3185 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3186 | We keep these bytes as is for the moment. | |
3187 | They may be decoded by post-read-conversion. */ | |
3188 | int dim, M, L; | |
4776e638 | 3189 | int size; |
8f924df7 | 3190 | |
103e0180 KH |
3191 | ONE_MORE_BYTE (dim); |
3192 | ONE_MORE_BYTE (M); | |
3193 | ONE_MORE_BYTE (L); | |
3194 | size = ((M - 128) * 128) + (L - 128); | |
4776e638 KH |
3195 | if (charbuf + 8 + size > charbuf_end) |
3196 | goto break_loop; | |
3197 | *charbuf++ = ISO_CODE_ESC; | |
3198 | *charbuf++ = '%'; | |
3199 | *charbuf++ = '/'; | |
3200 | *charbuf++ = dim; | |
3201 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3202 | *charbuf++ = BYTE8_TO_CHAR (L); | |
103e0180 KH |
3203 | while (size-- > 0) |
3204 | { | |
3205 | ONE_MORE_BYTE (c1); | |
4776e638 | 3206 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3207 | } |
103e0180 KH |
3208 | } |
3209 | else if (c1 == 'G') | |
3210 | { | |
103e0180 KH |
3211 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3212 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3213 | We keep these bytes as is for the moment. | |
3214 | They may be decoded by post-read-conversion. */ | |
4776e638 KH |
3215 | int *p = charbuf; |
3216 | ||
3217 | if (p + 6 > charbuf_end) | |
3218 | goto break_loop; | |
3219 | *p++ = ISO_CODE_ESC; | |
3220 | *p++ = '%'; | |
3221 | *p++ = 'G'; | |
3222 | while (p < charbuf_end) | |
103e0180 KH |
3223 | { |
3224 | ONE_MORE_BYTE (c1); | |
3225 | if (c1 == ISO_CODE_ESC | |
3226 | && src + 1 < src_end | |
3227 | && src[0] == '%' | |
3228 | && src[1] == '@') | |
9ffd559c KH |
3229 | { |
3230 | src += 2; | |
3231 | break; | |
3232 | } | |
4776e638 | 3233 | *p++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
103e0180 | 3234 | } |
4776e638 KH |
3235 | if (p + 3 > charbuf_end) |
3236 | goto break_loop; | |
3237 | *p++ = ISO_CODE_ESC; | |
3238 | *p++ = '%'; | |
3239 | *p++ = '@'; | |
3240 | charbuf = p; | |
103e0180 KH |
3241 | } |
3242 | else | |
4776e638 | 3243 | goto invalid_code; |
103e0180 | 3244 | continue; |
4776e638 | 3245 | break; |
103e0180 | 3246 | |
4ed46869 | 3247 | default: |
df7492f9 KH |
3248 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3249 | goto invalid_code; | |
134b9549 KH |
3250 | { |
3251 | int reg, chars96; | |
3252 | ||
3253 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3254 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3255 | reg = c1 - 0x28, chars96 = 0; | |
3256 | ONE_MORE_BYTE (c1); | |
3257 | } | |
3258 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3259 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3260 | reg = c1 - 0x2C, chars96 = 1; | |
3261 | ONE_MORE_BYTE (c1); | |
3262 | } | |
3263 | else | |
3264 | goto invalid_code; | |
3265 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3266 | /* We must update these variables now. */ | |
3267 | if (reg == 0) | |
3268 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3269 | else if (reg == 1) | |
3270 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3271 | if (chars96 < 0) | |
3272 | goto invalid_code; | |
3273 | } | |
b73bfc1c | 3274 | continue; |
4ed46869 | 3275 | } |
b73bfc1c | 3276 | } |
4ed46869 | 3277 | |
ff0dacd7 KH |
3278 | if (charset->id != charset_ascii |
3279 | && last_id != charset->id) | |
3280 | { | |
3281 | if (last_id != charset_ascii) | |
69a80ea3 | 3282 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3283 | last_id = charset->id; |
3284 | last_offset = char_offset; | |
3285 | } | |
3286 | ||
b73bfc1c | 3287 | /* Now we know CHARSET and 1st position code C1 of a character. |
df7492f9 KH |
3288 | Produce a decoded character while getting 2nd position code |
3289 | C2 if necessary. */ | |
3290 | c1 &= 0x7F; | |
3291 | if (CHARSET_DIMENSION (charset) > 1) | |
b73bfc1c KH |
3292 | { |
3293 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3294 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) |
b73bfc1c | 3295 | /* C2 is not in a valid range. */ |
df7492f9 KH |
3296 | goto invalid_code; |
3297 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3298 | if (CHARSET_DIMENSION (charset) > 2) | |
3299 | { | |
3300 | ONE_MORE_BYTE (c2); | |
3301 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) | |
3302 | /* C2 is not in a valid range. */ | |
3303 | goto invalid_code; | |
3304 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3305 | } | |
3306 | } | |
3307 | ||
3308 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); | |
3309 | if (c < 0) | |
3310 | { | |
3311 | MAYBE_FINISH_COMPOSITION (); | |
3312 | for (; src_base < src; src_base++, char_offset++) | |
3313 | { | |
3314 | if (ASCII_BYTE_P (*src_base)) | |
3315 | *charbuf++ = *src_base; | |
3316 | else | |
3317 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3318 | } | |
3319 | } | |
3320 | else if (composition_state == COMPOSING_NO) | |
3321 | { | |
3322 | *charbuf++ = c; | |
3323 | char_offset++; | |
4ed46869 | 3324 | } |
df7492f9 | 3325 | else |
781d7a48 KH |
3326 | { |
3327 | components[component_idx++] = c; | |
3328 | if (method == COMPOSITION_WITH_RULE | |
3329 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | |
3330 | && composition_state == COMPOSING_COMPONENT_CHAR)) | |
3331 | composition_state++; | |
4ed46869 KH |
3332 | } |
3333 | continue; | |
3334 | ||
df7492f9 KH |
3335 | invalid_code: |
3336 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3337 | src = src_base; |
df7492f9 KH |
3338 | consumed_chars = consumed_chars_base; |
3339 | ONE_MORE_BYTE (c); | |
065e3595 | 3340 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3341 | char_offset++; |
df7492f9 | 3342 | coding->errors++; |
4776e638 KH |
3343 | continue; |
3344 | ||
3345 | break_loop: | |
3346 | break; | |
4ed46869 | 3347 | } |
fb88bf2d | 3348 | |
df7492f9 | 3349 | no_more_source: |
ff0dacd7 | 3350 | if (last_id != charset_ascii) |
69a80ea3 | 3351 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3352 | coding->consumed_char += consumed_chars_base; |
3353 | coding->consumed = src_base - coding->source; | |
3354 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3355 | } |
3356 | ||
b73bfc1c | 3357 | |
f4dee582 | 3358 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3359 | |
3360 | /* | |
f4dee582 | 3361 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3362 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3363 | variant has the following specifications: |
df7492f9 | 3364 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3365 | 2. Allows short-form designation? |
3366 | 3. ASCII should be designated to G0 before control characters? | |
3367 | 4. ASCII should be designated to G0 at end of line? | |
3368 | 5. 7-bit environment or 8-bit environment? | |
3369 | 6. Use locking-shift? | |
3370 | 7. Use Single-shift? | |
3371 | And the following two are only for Japanese: | |
3372 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3373 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3374 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3375 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3376 | details. |
4ed46869 KH |
3377 | */ |
3378 | ||
3379 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3380 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3381 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3382 | designation sequence of short-form. */ | |
4ed46869 KH |
3383 | |
3384 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3385 | do { \ | |
df7492f9 | 3386 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
3387 | char *intermediate_char_94 = "()*+"; \ |
3388 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
3389 | int revision = -1; \ |
3390 | int c; \ | |
3391 | \ | |
3392 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3393 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3394 | \ |
3395 | if (revision >= 0) \ | |
70c22245 | 3396 | { \ |
df7492f9 KH |
3397 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3398 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3399 | } \ |
df7492f9 | 3400 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3401 | if (CHARSET_DIMENSION (charset) == 1) \ |
3402 | { \ | |
df7492f9 KH |
3403 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
3404 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 3405 | else \ |
df7492f9 KH |
3406 | c = intermediate_char_96[reg]; \ |
3407 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
3408 | } \ |
3409 | else \ | |
3410 | { \ | |
df7492f9 KH |
3411 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3412 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3413 | { \ |
df7492f9 | 3414 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3415 | || reg != 0 \ |
3416 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3417 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3418 | } \ |
3419 | else \ | |
df7492f9 | 3420 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3421 | } \ |
df7492f9 KH |
3422 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3423 | \ | |
3424 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3425 | } while (0) |
3426 | ||
df7492f9 | 3427 | |
4ed46869 KH |
3428 | /* The following two macros produce codes (control character or escape |
3429 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3430 | single-shift-3). */ | |
3431 | ||
df7492f9 KH |
3432 | #define ENCODE_SINGLE_SHIFT_2 \ |
3433 | do { \ | |
3434 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3435 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3436 | else \ | |
3437 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3438 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3439 | } while (0) |
3440 | ||
df7492f9 KH |
3441 | |
3442 | #define ENCODE_SINGLE_SHIFT_3 \ | |
3443 | do { \ | |
3444 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3445 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
3446 | else \ | |
3447 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
3448 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3449 | } while (0) |
3450 | ||
df7492f9 | 3451 | |
4ed46869 KH |
3452 | /* The following four macros produce codes (control character or |
3453 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
3454 | shift-out, locking-shift-2, and locking-shift-3). */ | |
3455 | ||
df7492f9 KH |
3456 | #define ENCODE_SHIFT_IN \ |
3457 | do { \ | |
3458 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
3459 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
3460 | } while (0) |
3461 | ||
df7492f9 KH |
3462 | |
3463 | #define ENCODE_SHIFT_OUT \ | |
3464 | do { \ | |
3465 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
3466 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
3467 | } while (0) |
3468 | ||
df7492f9 KH |
3469 | |
3470 | #define ENCODE_LOCKING_SHIFT_2 \ | |
3471 | do { \ | |
3472 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3473 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
3474 | } while (0) |
3475 | ||
df7492f9 KH |
3476 | |
3477 | #define ENCODE_LOCKING_SHIFT_3 \ | |
3478 | do { \ | |
3479 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3480 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
3481 | } while (0) |
3482 | ||
df7492f9 | 3483 | |
f4dee582 RS |
3484 | /* Produce codes for a DIMENSION1 character whose character set is |
3485 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
3486 | sequences are also produced in advance if necessary. */ |
3487 | ||
6e85d753 KH |
3488 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
3489 | do { \ | |
df7492f9 | 3490 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3491 | \ |
3492 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3493 | && id == charset_ascii) \ | |
3494 | { \ | |
3495 | id = charset_jisx0201_roman; \ | |
3496 | charset = CHARSET_FROM_ID (id); \ | |
3497 | } \ | |
3498 | \ | |
df7492f9 | 3499 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3500 | { \ |
df7492f9 KH |
3501 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3502 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 3503 | else \ |
df7492f9 KH |
3504 | EMIT_ONE_BYTE (c1 | 0x80); \ |
3505 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3506 | break; \ |
3507 | } \ | |
df7492f9 | 3508 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3509 | { \ |
df7492f9 | 3510 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
3511 | break; \ |
3512 | } \ | |
df7492f9 | 3513 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3514 | { \ |
df7492f9 | 3515 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
3516 | break; \ |
3517 | } \ | |
6e85d753 KH |
3518 | else \ |
3519 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3520 | must invoke it, or, at first, designate it to some graphic \ | |
3521 | register. Then repeat the loop to actually produce the \ | |
3522 | character. */ \ | |
df7492f9 KH |
3523 | dst = encode_invocation_designation (charset, coding, dst, \ |
3524 | &produced_chars); \ | |
4ed46869 KH |
3525 | } while (1) |
3526 | ||
df7492f9 | 3527 | |
f4dee582 RS |
3528 | /* Produce codes for a DIMENSION2 character whose character set is |
3529 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
3530 | invocation codes are also produced in advance if necessary. */ |
3531 | ||
6e85d753 KH |
3532 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
3533 | do { \ | |
df7492f9 | 3534 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
3535 | \ |
3536 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3537 | && id == charset_jisx0208) \ | |
3538 | { \ | |
3539 | id = charset_jisx0208_1978; \ | |
3540 | charset = CHARSET_FROM_ID (id); \ | |
3541 | } \ | |
3542 | \ | |
df7492f9 | 3543 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 3544 | { \ |
df7492f9 KH |
3545 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3546 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 3547 | else \ |
df7492f9 KH |
3548 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
3549 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3550 | break; \ |
3551 | } \ | |
df7492f9 | 3552 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3553 | { \ |
df7492f9 | 3554 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
3555 | break; \ |
3556 | } \ | |
df7492f9 | 3557 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3558 | { \ |
df7492f9 | 3559 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
3560 | break; \ |
3561 | } \ | |
6e85d753 KH |
3562 | else \ |
3563 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3564 | must invoke it, or, at first, designate it to some graphic \ | |
3565 | register. Then repeat the loop to actually produce the \ | |
3566 | character. */ \ | |
df7492f9 KH |
3567 | dst = encode_invocation_designation (charset, coding, dst, \ |
3568 | &produced_chars); \ | |
4ed46869 KH |
3569 | } while (1) |
3570 | ||
05e6f5dc | 3571 | |
df7492f9 KH |
3572 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
3573 | do { \ | |
3574 | int code = ENCODE_CHAR ((charset),(c)); \ | |
3575 | \ | |
3576 | if (CHARSET_DIMENSION (charset) == 1) \ | |
3577 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
3578 | else \ | |
3579 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 3580 | } while (0) |
bdd9fb48 | 3581 | |
05e6f5dc | 3582 | |
4ed46869 | 3583 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 3584 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
3585 | Return new DST. */ |
3586 | ||
3587 | unsigned char * | |
df7492f9 KH |
3588 | encode_invocation_designation (charset, coding, dst, p_nchars) |
3589 | struct charset *charset; | |
4ed46869 KH |
3590 | struct coding_system *coding; |
3591 | unsigned char *dst; | |
df7492f9 | 3592 | int *p_nchars; |
4ed46869 | 3593 | { |
df7492f9 KH |
3594 | int multibytep = coding->dst_multibyte; |
3595 | int produced_chars = *p_nchars; | |
4ed46869 | 3596 | int reg; /* graphic register number */ |
df7492f9 | 3597 | int id = CHARSET_ID (charset); |
4ed46869 KH |
3598 | |
3599 | /* At first, check designations. */ | |
3600 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 3601 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
3602 | break; |
3603 | ||
3604 | if (reg >= 4) | |
3605 | { | |
3606 | /* CHARSET is not yet designated to any graphic registers. */ | |
3607 | /* At first check the requested designation. */ | |
df7492f9 KH |
3608 | reg = CODING_ISO_REQUEST (coding, id); |
3609 | if (reg < 0) | |
1ba9e4ab KH |
3610 | /* Since CHARSET requests no special designation, designate it |
3611 | to graphic register 0. */ | |
4ed46869 KH |
3612 | reg = 0; |
3613 | ||
3614 | ENCODE_DESIGNATION (charset, reg, coding); | |
3615 | } | |
3616 | ||
df7492f9 KH |
3617 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
3618 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
3619 | { |
3620 | /* Since the graphic register REG is not invoked to any graphic | |
3621 | planes, invoke it to graphic plane 0. */ | |
3622 | switch (reg) | |
3623 | { | |
3624 | case 0: /* graphic register 0 */ | |
3625 | ENCODE_SHIFT_IN; | |
3626 | break; | |
3627 | ||
3628 | case 1: /* graphic register 1 */ | |
3629 | ENCODE_SHIFT_OUT; | |
3630 | break; | |
3631 | ||
3632 | case 2: /* graphic register 2 */ | |
df7492f9 | 3633 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3634 | ENCODE_SINGLE_SHIFT_2; |
3635 | else | |
3636 | ENCODE_LOCKING_SHIFT_2; | |
3637 | break; | |
3638 | ||
3639 | case 3: /* graphic register 3 */ | |
df7492f9 | 3640 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3641 | ENCODE_SINGLE_SHIFT_3; |
3642 | else | |
3643 | ENCODE_LOCKING_SHIFT_3; | |
3644 | break; | |
3645 | } | |
3646 | } | |
b73bfc1c | 3647 | |
df7492f9 | 3648 | *p_nchars = produced_chars; |
4ed46869 KH |
3649 | return dst; |
3650 | } | |
3651 | ||
df7492f9 KH |
3652 | /* The following three macros produce codes for indicating direction |
3653 | of text. */ | |
3654 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 3655 | do { \ |
df7492f9 KH |
3656 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
3657 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 3658 | else \ |
df7492f9 | 3659 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
3660 | } while (0) |
3661 | ||
ec6d2bb8 | 3662 | |
df7492f9 KH |
3663 | #define ENCODE_DIRECTION_R2L() \ |
3664 | do { \ | |
3665 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
3666 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
3667 | } while (0) |
3668 | ||
ec6d2bb8 | 3669 | |
df7492f9 | 3670 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 3671 | do { \ |
df7492f9 KH |
3672 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
3673 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 3674 | } while (0) |
4ed46869 | 3675 | |
4ed46869 KH |
3676 | |
3677 | /* Produce codes for designation and invocation to reset the graphic | |
3678 | planes and registers to initial state. */ | |
df7492f9 KH |
3679 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
3680 | do { \ | |
3681 | int reg; \ | |
3682 | struct charset *charset; \ | |
3683 | \ | |
3684 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
3685 | ENCODE_SHIFT_IN; \ | |
3686 | for (reg = 0; reg < 4; reg++) \ | |
3687 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
3688 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
3689 | != CODING_ISO_INITIAL (coding, reg))) \ | |
3690 | { \ | |
3691 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
3692 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
3693 | } \ | |
4ed46869 KH |
3694 | } while (0) |
3695 | ||
df7492f9 | 3696 | |
bdd9fb48 | 3697 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 3698 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
3699 | |
3700 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
3701 | find all the necessary designations. */ |
3702 | ||
b73bfc1c | 3703 | static unsigned char * |
df7492f9 | 3704 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 3705 | struct coding_system *coding; |
df7492f9 KH |
3706 | int *charbuf, *charbuf_end; |
3707 | unsigned char *dst; | |
e0e989f6 | 3708 | { |
df7492f9 | 3709 | struct charset *charset; |
bdd9fb48 KH |
3710 | /* Table of charsets to be designated to each graphic register. */ |
3711 | int r[4]; | |
df7492f9 KH |
3712 | int c, found = 0, reg; |
3713 | int produced_chars = 0; | |
3714 | int multibytep = coding->dst_multibyte; | |
3715 | Lisp_Object attrs; | |
3716 | Lisp_Object charset_list; | |
3717 | ||
3718 | attrs = CODING_ID_ATTRS (coding->id); | |
3719 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3720 | if (EQ (charset_list, Qiso_2022)) | |
3721 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
3722 | |
3723 | for (reg = 0; reg < 4; reg++) | |
3724 | r[reg] = -1; | |
3725 | ||
b73bfc1c | 3726 | while (found < 4) |
e0e989f6 | 3727 | { |
df7492f9 KH |
3728 | int id; |
3729 | ||
3730 | c = *charbuf++; | |
b73bfc1c KH |
3731 | if (c == '\n') |
3732 | break; | |
df7492f9 KH |
3733 | charset = char_charset (c, charset_list, NULL); |
3734 | id = CHARSET_ID (charset); | |
3735 | reg = CODING_ISO_REQUEST (coding, id); | |
3736 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
3737 | { |
3738 | found++; | |
df7492f9 | 3739 | r[reg] = id; |
bdd9fb48 | 3740 | } |
bdd9fb48 KH |
3741 | } |
3742 | ||
3743 | if (found) | |
3744 | { | |
3745 | for (reg = 0; reg < 4; reg++) | |
3746 | if (r[reg] >= 0 | |
df7492f9 KH |
3747 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
3748 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 3749 | } |
b73bfc1c KH |
3750 | |
3751 | return dst; | |
e0e989f6 KH |
3752 | } |
3753 | ||
4ed46869 KH |
3754 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
3755 | ||
df7492f9 KH |
3756 | static int |
3757 | encode_coding_iso_2022 (coding) | |
4ed46869 | 3758 | struct coding_system *coding; |
4ed46869 | 3759 | { |
df7492f9 KH |
3760 | int multibytep = coding->dst_multibyte; |
3761 | int *charbuf = coding->charbuf; | |
3762 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3763 | unsigned char *dst = coding->destination + coding->produced; | |
3764 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3765 | int safe_room = 16; | |
3766 | int bol_designation | |
3767 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
3768 | && CODING_ISO_BOL (coding)); | |
3769 | int produced_chars = 0; | |
3770 | Lisp_Object attrs, eol_type, charset_list; | |
3771 | int ascii_compatible; | |
b73bfc1c | 3772 | int c; |
ff0dacd7 | 3773 | int preferred_charset_id = -1; |
05e6f5dc | 3774 | |
24a73b0a KH |
3775 | CODING_GET_INFO (coding, attrs, charset_list); |
3776 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
3777 | if (VECTORP (eol_type)) | |
3778 | eol_type = Qunix; | |
3779 | ||
004068e4 | 3780 | setup_iso_safe_charsets (attrs); |
ff0dacd7 KH |
3781 | /* Charset list may have been changed. */ |
3782 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); \ | |
8f924df7 | 3783 | coding->safe_charsets = (char *) SDATA (CODING_ATTR_SAFE_CHARSETS(attrs)); |
0eecad43 | 3784 | |
df7492f9 | 3785 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
bdd9fb48 | 3786 | |
df7492f9 | 3787 | while (charbuf < charbuf_end) |
4ed46869 | 3788 | { |
df7492f9 | 3789 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 3790 | |
df7492f9 | 3791 | if (bol_designation) |
b73bfc1c | 3792 | { |
df7492f9 | 3793 | unsigned char *dst_prev = dst; |
4ed46869 | 3794 | |
bdd9fb48 | 3795 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
3796 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
3797 | bol_designation = 0; | |
3798 | /* We are sure that designation sequences are all ASCII bytes. */ | |
3799 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
3800 | } |
3801 | ||
df7492f9 | 3802 | c = *charbuf++; |
ec6d2bb8 | 3803 | |
ff0dacd7 KH |
3804 | if (c < 0) |
3805 | { | |
3806 | /* Handle an annotation. */ | |
3807 | switch (*charbuf) | |
ec6d2bb8 | 3808 | { |
ff0dacd7 KH |
3809 | case CODING_ANNOTATE_COMPOSITION_MASK: |
3810 | /* Not yet implemented. */ | |
3811 | break; | |
3812 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 3813 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
3814 | if (preferred_charset_id >= 0 |
3815 | && NILP (Fmemq (make_number (preferred_charset_id), | |
3816 | charset_list))) | |
3817 | preferred_charset_id = -1; | |
3818 | break; | |
3819 | default: | |
3820 | abort (); | |
4ed46869 | 3821 | } |
ff0dacd7 KH |
3822 | charbuf += -c - 1; |
3823 | continue; | |
4ed46869 | 3824 | } |
ec6d2bb8 | 3825 | |
b73bfc1c KH |
3826 | /* Now encode the character C. */ |
3827 | if (c < 0x20 || c == 0x7F) | |
3828 | { | |
df7492f9 KH |
3829 | if (c == '\n' |
3830 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 3831 | { |
df7492f9 KH |
3832 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
3833 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3834 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 3835 | { |
df7492f9 KH |
3836 | int i; |
3837 | ||
3838 | for (i = 0; i < 4; i++) | |
3839 | CODING_ISO_DESIGNATION (coding, i) | |
3840 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 3841 | } |
df7492f9 KH |
3842 | bol_designation |
3843 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 3844 | } |
df7492f9 KH |
3845 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
3846 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3847 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 3848 | } |
df7492f9 | 3849 | else if (ASCII_CHAR_P (c)) |
88993dfd | 3850 | { |
df7492f9 KH |
3851 | if (ascii_compatible) |
3852 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 3853 | else |
19a8d9e0 | 3854 | { |
bf16eb23 KH |
3855 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
3856 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 3857 | } |
4ed46869 | 3858 | } |
16eafb5d | 3859 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 3860 | { |
16eafb5d KH |
3861 | c = CHAR_TO_BYTE8 (c); |
3862 | EMIT_ONE_BYTE (c); | |
88993dfd | 3863 | } |
b73bfc1c | 3864 | else |
df7492f9 | 3865 | { |
ff0dacd7 | 3866 | struct charset *charset; |
b73bfc1c | 3867 | |
ff0dacd7 KH |
3868 | if (preferred_charset_id >= 0) |
3869 | { | |
3870 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
3871 | if (! CHAR_CHARSET_P (c, charset)) | |
3872 | charset = char_charset (c, charset_list, NULL); | |
3873 | } | |
3874 | else | |
3875 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
3876 | if (!charset) |
3877 | { | |
41cbe562 KH |
3878 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3879 | { | |
3880 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3881 | charset = CHARSET_FROM_ID (charset_ascii); | |
3882 | } | |
3883 | else | |
3884 | { | |
3885 | c = coding->default_char; | |
3886 | charset = char_charset (c, charset_list, NULL); | |
3887 | } | |
df7492f9 KH |
3888 | } |
3889 | ENCODE_ISO_CHARACTER (charset, c); | |
3890 | } | |
84fbb8a0 | 3891 | } |
b73bfc1c | 3892 | |
df7492f9 KH |
3893 | if (coding->mode & CODING_MODE_LAST_BLOCK |
3894 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
3895 | { | |
3896 | ASSURE_DESTINATION (safe_room); | |
3897 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3898 | } | |
065e3595 | 3899 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
3900 | CODING_ISO_BOL (coding) = bol_designation; |
3901 | coding->produced_char += produced_chars; | |
3902 | coding->produced = dst - coding->destination; | |
3903 | return 0; | |
4ed46869 KH |
3904 | } |
3905 | ||
3906 | \f | |
df7492f9 | 3907 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 3908 | |
df7492f9 | 3909 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
3910 | quite widely. So, for the moment, Emacs supports them in the bare |
3911 | C code. But, in the future, they may be supported only by CCL. */ | |
3912 | ||
3913 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
3914 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
3915 | as is. A character of charset katakana-jisx0201 is encoded by | |
3916 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
3917 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 3918 | so that it fit in the range below. |
4ed46869 KH |
3919 | |
3920 | --- CODE RANGE of SJIS --- | |
3921 | (character set) (range) | |
3922 | ASCII 0x00 .. 0x7F | |
df7492f9 | 3923 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 3924 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 3925 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
3926 | ------------------------------- |
3927 | ||
3928 | */ | |
3929 | ||
3930 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
3931 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 3932 | character set and is encoded in two-byte. |
4ed46869 KH |
3933 | |
3934 | --- CODE RANGE of BIG5 --- | |
3935 | (character set) (range) | |
3936 | ASCII 0x00 .. 0x7F | |
3937 | Big5 (1st byte) 0xA1 .. 0xFE | |
3938 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
3939 | -------------------------- | |
3940 | ||
df7492f9 | 3941 | */ |
4ed46869 KH |
3942 | |
3943 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3944 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 3945 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 3946 | |
0a28aafb | 3947 | static int |
ff0dacd7 | 3948 | detect_coding_sjis (coding, detect_info) |
df7492f9 | 3949 | struct coding_system *coding; |
ff0dacd7 | 3950 | struct coding_detection_info *detect_info; |
4ed46869 | 3951 | { |
065e3595 | 3952 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 3953 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
3954 | int multibytep = coding->src_multibyte; |
3955 | int consumed_chars = 0; | |
3956 | int found = 0; | |
b73bfc1c | 3957 | int c; |
df7492f9 | 3958 | |
ff0dacd7 | 3959 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3960 | /* A coding system of this category is always ASCII compatible. */ |
3961 | src += coding->head_ascii; | |
4ed46869 | 3962 | |
b73bfc1c | 3963 | while (1) |
4ed46869 | 3964 | { |
065e3595 | 3965 | src_base = src; |
df7492f9 | 3966 | ONE_MORE_BYTE (c); |
682169fe KH |
3967 | if (c < 0x80) |
3968 | continue; | |
df7492f9 | 3969 | if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF)) |
4ed46869 | 3970 | { |
df7492f9 | 3971 | ONE_MORE_BYTE (c); |
682169fe | 3972 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 3973 | break; |
ff0dacd7 | 3974 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 3975 | } |
df7492f9 | 3976 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 3977 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
3978 | else |
3979 | break; | |
4ed46869 | 3980 | } |
ff0dacd7 | 3981 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
3982 | return 0; |
3983 | ||
3984 | no_more_source: | |
065e3595 | 3985 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 3986 | { |
ff0dacd7 | 3987 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 3988 | return 0; |
4ed46869 | 3989 | } |
ff0dacd7 KH |
3990 | detect_info->found |= found; |
3991 | return 1; | |
4ed46869 KH |
3992 | } |
3993 | ||
3994 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3995 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 3996 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 3997 | |
0a28aafb | 3998 | static int |
ff0dacd7 | 3999 | detect_coding_big5 (coding, detect_info) |
df7492f9 | 4000 | struct coding_system *coding; |
ff0dacd7 | 4001 | struct coding_detection_info *detect_info; |
4ed46869 | 4002 | { |
065e3595 | 4003 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4004 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4005 | int multibytep = coding->src_multibyte; |
4006 | int consumed_chars = 0; | |
4007 | int found = 0; | |
b73bfc1c | 4008 | int c; |
fa42c37f | 4009 | |
ff0dacd7 | 4010 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4011 | /* A coding system of this category is always ASCII compatible. */ |
4012 | src += coding->head_ascii; | |
fa42c37f | 4013 | |
b73bfc1c | 4014 | while (1) |
fa42c37f | 4015 | { |
065e3595 | 4016 | src_base = src; |
df7492f9 KH |
4017 | ONE_MORE_BYTE (c); |
4018 | if (c < 0x80) | |
fa42c37f | 4019 | continue; |
df7492f9 | 4020 | if (c >= 0xA1) |
fa42c37f | 4021 | { |
df7492f9 KH |
4022 | ONE_MORE_BYTE (c); |
4023 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4024 | return 0; |
ff0dacd7 | 4025 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4026 | } |
df7492f9 KH |
4027 | else |
4028 | break; | |
fa42c37f | 4029 | } |
ff0dacd7 | 4030 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4031 | return 0; |
fa42c37f | 4032 | |
df7492f9 | 4033 | no_more_source: |
065e3595 | 4034 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4035 | { |
ff0dacd7 | 4036 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4037 | return 0; |
4038 | } | |
ff0dacd7 KH |
4039 | detect_info->found |= found; |
4040 | return 1; | |
fa42c37f KH |
4041 | } |
4042 | ||
4ed46869 KH |
4043 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4044 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4045 | |
b73bfc1c | 4046 | static void |
df7492f9 | 4047 | decode_coding_sjis (coding) |
4ed46869 | 4048 | struct coding_system *coding; |
4ed46869 | 4049 | { |
8f924df7 KH |
4050 | const unsigned char *src = coding->source + coding->consumed; |
4051 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4052 | const unsigned char *src_base; | |
69a80ea3 KH |
4053 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4054 | int *charbuf_end | |
4055 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4056 | int consumed_chars = 0, consumed_chars_base; |
4057 | int multibytep = coding->src_multibyte; | |
4058 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4059 | struct charset *charset_kanji2; |
24a73b0a | 4060 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4061 | int char_offset = coding->produced_char; |
4062 | int last_offset = char_offset; | |
4063 | int last_id = charset_ascii; | |
a5d301df | 4064 | |
24a73b0a | 4065 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4066 | |
4067 | val = charset_list; | |
4068 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4069 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4070 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4071 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4072 | |
b73bfc1c | 4073 | while (1) |
4ed46869 | 4074 | { |
df7492f9 | 4075 | int c, c1; |
24a73b0a | 4076 | struct charset *charset; |
fa42c37f | 4077 | |
b73bfc1c | 4078 | src_base = src; |
df7492f9 | 4079 | consumed_chars_base = consumed_chars; |
fa42c37f | 4080 | |
df7492f9 KH |
4081 | if (charbuf >= charbuf_end) |
4082 | break; | |
4083 | ||
4084 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4085 | if (c < 0) |
4086 | goto invalid_code; | |
24a73b0a KH |
4087 | if (c < 0x80) |
4088 | charset = charset_roman; | |
57a47f8a | 4089 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4090 | goto invalid_code; |
57a47f8a KH |
4091 | else if (c >= 0xA1 && c <= 0xDF) |
4092 | { | |
4093 | /* SJIS -> JISX0201-Kana */ | |
4094 | c &= 0x7F; | |
4095 | charset = charset_kana; | |
4096 | } | |
4097 | else if (c <= 0xEF) | |
df7492f9 | 4098 | { |
57a47f8a KH |
4099 | /* SJIS -> JISX0208 */ |
4100 | ONE_MORE_BYTE (c1); | |
4101 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4102 | goto invalid_code; |
57a47f8a KH |
4103 | c = (c << 8) | c1; |
4104 | SJIS_TO_JIS (c); | |
4105 | charset = charset_kanji; | |
4106 | } | |
4107 | else if (c <= 0xFC && charset_kanji2) | |
4108 | { | |
c6876370 | 4109 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4110 | ONE_MORE_BYTE (c1); |
4111 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4112 | goto invalid_code; |
57a47f8a KH |
4113 | c = (c << 8) | c1; |
4114 | SJIS_TO_JIS2 (c); | |
4115 | charset = charset_kanji2; | |
df7492f9 | 4116 | } |
57a47f8a KH |
4117 | else |
4118 | goto invalid_code; | |
24a73b0a KH |
4119 | if (charset->id != charset_ascii |
4120 | && last_id != charset->id) | |
4121 | { | |
4122 | if (last_id != charset_ascii) | |
69a80ea3 | 4123 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4124 | last_id = charset->id; |
4125 | last_offset = char_offset; | |
4126 | } | |
4127 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4128 | *charbuf++ = c; |
ff0dacd7 | 4129 | char_offset++; |
df7492f9 | 4130 | continue; |
b73bfc1c | 4131 | |
df7492f9 KH |
4132 | invalid_code: |
4133 | src = src_base; | |
4134 | consumed_chars = consumed_chars_base; | |
4135 | ONE_MORE_BYTE (c); | |
065e3595 | 4136 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4137 | char_offset++; |
df7492f9 KH |
4138 | coding->errors++; |
4139 | } | |
fa42c37f | 4140 | |
df7492f9 | 4141 | no_more_source: |
ff0dacd7 | 4142 | if (last_id != charset_ascii) |
69a80ea3 | 4143 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4144 | coding->consumed_char += consumed_chars_base; |
4145 | coding->consumed = src_base - coding->source; | |
4146 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4147 | } |
4148 | ||
b73bfc1c | 4149 | static void |
df7492f9 | 4150 | decode_coding_big5 (coding) |
4ed46869 | 4151 | struct coding_system *coding; |
4ed46869 | 4152 | { |
8f924df7 KH |
4153 | const unsigned char *src = coding->source + coding->consumed; |
4154 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4155 | const unsigned char *src_base; | |
69a80ea3 KH |
4156 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4157 | int *charbuf_end | |
4158 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4159 | int consumed_chars = 0, consumed_chars_base; |
4160 | int multibytep = coding->src_multibyte; | |
4161 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4162 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4163 | int char_offset = coding->produced_char; |
4164 | int last_offset = char_offset; | |
4165 | int last_id = charset_ascii; | |
df7492f9 | 4166 | |
24a73b0a | 4167 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4168 | val = charset_list; |
4169 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4170 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4171 | |
b73bfc1c | 4172 | while (1) |
4ed46869 | 4173 | { |
df7492f9 | 4174 | int c, c1; |
24a73b0a | 4175 | struct charset *charset; |
b73bfc1c KH |
4176 | |
4177 | src_base = src; | |
df7492f9 KH |
4178 | consumed_chars_base = consumed_chars; |
4179 | ||
4180 | if (charbuf >= charbuf_end) | |
4181 | break; | |
4182 | ||
4183 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4184 | |
065e3595 KH |
4185 | if (c < 0) |
4186 | goto invalid_code; | |
24a73b0a KH |
4187 | if (c < 0x80) |
4188 | charset = charset_roman; | |
4189 | else | |
4ed46869 | 4190 | { |
24a73b0a KH |
4191 | /* BIG5 -> Big5 */ |
4192 | if (c < 0xA1 || c > 0xFE) | |
4193 | goto invalid_code; | |
4194 | ONE_MORE_BYTE (c1); | |
4195 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4196 | goto invalid_code; | |
4197 | c = c << 8 | c1; | |
4198 | charset = charset_big5; | |
4ed46869 | 4199 | } |
24a73b0a KH |
4200 | if (charset->id != charset_ascii |
4201 | && last_id != charset->id) | |
df7492f9 | 4202 | { |
24a73b0a | 4203 | if (last_id != charset_ascii) |
69a80ea3 | 4204 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4205 | last_id = charset->id; |
4206 | last_offset = char_offset; | |
4ed46869 | 4207 | } |
24a73b0a | 4208 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4209 | *charbuf++ = c; |
ff0dacd7 | 4210 | char_offset++; |
fb88bf2d KH |
4211 | continue; |
4212 | ||
df7492f9 | 4213 | invalid_code: |
4ed46869 | 4214 | src = src_base; |
df7492f9 KH |
4215 | consumed_chars = consumed_chars_base; |
4216 | ONE_MORE_BYTE (c); | |
065e3595 | 4217 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4218 | char_offset++; |
df7492f9 | 4219 | coding->errors++; |
fb88bf2d | 4220 | } |
d46c5b12 | 4221 | |
df7492f9 | 4222 | no_more_source: |
ff0dacd7 | 4223 | if (last_id != charset_ascii) |
69a80ea3 | 4224 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4225 | coding->consumed_char += consumed_chars_base; |
4226 | coding->consumed = src_base - coding->source; | |
4227 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4228 | } |
4229 | ||
4230 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4231 | This function can encode charsets `ascii', `katakana-jisx0201', |
4232 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4233 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4234 | (i.e. do not have extended leading-codes). Characters of other |
4235 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4236 | SJIS text, else encode BIG5 text. */ | |
4237 | ||
df7492f9 KH |
4238 | static int |
4239 | encode_coding_sjis (coding) | |
4ed46869 | 4240 | struct coding_system *coding; |
4ed46869 | 4241 | { |
df7492f9 KH |
4242 | int multibytep = coding->dst_multibyte; |
4243 | int *charbuf = coding->charbuf; | |
4244 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4245 | unsigned char *dst = coding->destination + coding->produced; | |
4246 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4247 | int safe_room = 4; | |
4248 | int produced_chars = 0; | |
24a73b0a | 4249 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4250 | int ascii_compatible; |
4251 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4252 | struct charset *charset_kanji2; |
df7492f9 | 4253 | int c; |
a5d301df | 4254 | |
24a73b0a | 4255 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4256 | val = charset_list; |
4257 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4258 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
4259 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4260 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4261 | |
df7492f9 | 4262 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4263 | |
df7492f9 KH |
4264 | while (charbuf < charbuf_end) |
4265 | { | |
4266 | ASSURE_DESTINATION (safe_room); | |
4267 | c = *charbuf++; | |
b73bfc1c | 4268 | /* Now encode the character C. */ |
df7492f9 KH |
4269 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4270 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4271 | else if (CHAR_BYTE8_P (c)) |
4272 | { | |
4273 | c = CHAR_TO_BYTE8 (c); | |
4274 | EMIT_ONE_BYTE (c); | |
4275 | } | |
df7492f9 | 4276 | else |
b73bfc1c | 4277 | { |
df7492f9 KH |
4278 | unsigned code; |
4279 | struct charset *charset = char_charset (c, charset_list, &code); | |
4280 | ||
4281 | if (!charset) | |
4ed46869 | 4282 | { |
41cbe562 | 4283 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4284 | { |
41cbe562 KH |
4285 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4286 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4287 | } |
41cbe562 | 4288 | else |
b73bfc1c | 4289 | { |
41cbe562 KH |
4290 | c = coding->default_char; |
4291 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4292 | } |
b73bfc1c | 4293 | } |
df7492f9 KH |
4294 | if (code == CHARSET_INVALID_CODE (charset)) |
4295 | abort (); | |
4296 | if (charset == charset_kanji) | |
4297 | { | |
4298 | int c1, c2; | |
4299 | JIS_TO_SJIS (code); | |
4300 | c1 = code >> 8, c2 = code & 0xFF; | |
4301 | EMIT_TWO_BYTES (c1, c2); | |
4302 | } | |
4303 | else if (charset == charset_kana) | |
4304 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4305 | else if (charset_kanji2 && charset == charset_kanji2) |
4306 | { | |
4307 | int c1, c2; | |
4308 | ||
4309 | c1 = code >> 8; | |
4310 | if (c1 == 0x21 || (c1 >= 0x23 && c1 < 0x25) | |
4311 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) | |
4312 | { | |
4313 | JIS_TO_SJIS2 (code); | |
4314 | c1 = code >> 8, c2 = code & 0xFF; | |
4315 | EMIT_TWO_BYTES (c1, c2); | |
4316 | } | |
4317 | else | |
4318 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4319 | } | |
df7492f9 KH |
4320 | else |
4321 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4322 | } | |
4323 | } | |
065e3595 | 4324 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4325 | coding->produced_char += produced_chars; |
4326 | coding->produced = dst - coding->destination; | |
4327 | return 0; | |
4328 | } | |
4329 | ||
4330 | static int | |
4331 | encode_coding_big5 (coding) | |
4332 | struct coding_system *coding; | |
4333 | { | |
4334 | int multibytep = coding->dst_multibyte; | |
4335 | int *charbuf = coding->charbuf; | |
4336 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4337 | unsigned char *dst = coding->destination + coding->produced; | |
4338 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4339 | int safe_room = 4; | |
4340 | int produced_chars = 0; | |
24a73b0a | 4341 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4342 | int ascii_compatible; |
4343 | struct charset *charset_roman, *charset_big5; | |
4344 | int c; | |
4345 | ||
24a73b0a | 4346 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4347 | val = charset_list; |
4348 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4349 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4350 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4351 | ||
4352 | while (charbuf < charbuf_end) | |
4353 | { | |
4354 | ASSURE_DESTINATION (safe_room); | |
4355 | c = *charbuf++; | |
4356 | /* Now encode the character C. */ | |
4357 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4358 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4359 | else if (CHAR_BYTE8_P (c)) |
4360 | { | |
4361 | c = CHAR_TO_BYTE8 (c); | |
4362 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4363 | } |
4364 | else | |
4365 | { | |
df7492f9 KH |
4366 | unsigned code; |
4367 | struct charset *charset = char_charset (c, charset_list, &code); | |
4368 | ||
4369 | if (! charset) | |
b73bfc1c | 4370 | { |
41cbe562 | 4371 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4372 | { |
41cbe562 KH |
4373 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4374 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4375 | } |
41cbe562 | 4376 | else |
0eecad43 | 4377 | { |
41cbe562 KH |
4378 | c = coding->default_char; |
4379 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 4380 | } |
4ed46869 | 4381 | } |
df7492f9 KH |
4382 | if (code == CHARSET_INVALID_CODE (charset)) |
4383 | abort (); | |
4384 | if (charset == charset_big5) | |
b73bfc1c | 4385 | { |
df7492f9 KH |
4386 | int c1, c2; |
4387 | ||
4388 | c1 = code >> 8, c2 = code & 0xFF; | |
4389 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4390 | } |
df7492f9 KH |
4391 | else |
4392 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4393 | } |
4ed46869 | 4394 | } |
065e3595 | 4395 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4396 | coding->produced_char += produced_chars; |
4397 | coding->produced = dst - coding->destination; | |
4398 | return 0; | |
4ed46869 KH |
4399 | } |
4400 | ||
4401 | \f | |
df7492f9 | 4402 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4403 | |
4404 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4405 | Check if a text is encoded in a coding system of which | |
4406 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 4407 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 4408 | |
0a28aafb | 4409 | static int |
ff0dacd7 | 4410 | detect_coding_ccl (coding, detect_info) |
df7492f9 | 4411 | struct coding_system *coding; |
ff0dacd7 | 4412 | struct coding_detection_info *detect_info; |
1397dc18 | 4413 | { |
065e3595 | 4414 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4415 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4416 | int multibytep = coding->src_multibyte; |
4417 | int consumed_chars = 0; | |
4418 | int found = 0; | |
0e219d54 | 4419 | unsigned char *valids; |
df7492f9 KH |
4420 | int head_ascii = coding->head_ascii; |
4421 | Lisp_Object attrs; | |
4422 | ||
ff0dacd7 KH |
4423 | detect_info->checked |= CATEGORY_MASK_CCL; |
4424 | ||
df7492f9 | 4425 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 4426 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
4427 | attrs = CODING_ID_ATTRS (coding->id); |
4428 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4429 | src += head_ascii; | |
1397dc18 | 4430 | |
b73bfc1c | 4431 | while (1) |
1397dc18 | 4432 | { |
df7492f9 | 4433 | int c; |
065e3595 KH |
4434 | |
4435 | src_base = src; | |
df7492f9 | 4436 | ONE_MORE_BYTE (c); |
065e3595 | 4437 | if (c < 0 || ! valids[c]) |
df7492f9 | 4438 | break; |
ff0dacd7 KH |
4439 | if ((valids[c] > 1)) |
4440 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 4441 | } |
ff0dacd7 | 4442 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
4443 | return 0; |
4444 | ||
4445 | no_more_source: | |
ff0dacd7 KH |
4446 | detect_info->found |= found; |
4447 | return 1; | |
df7492f9 KH |
4448 | } |
4449 | ||
4450 | static void | |
4451 | decode_coding_ccl (coding) | |
4452 | struct coding_system *coding; | |
4453 | { | |
7c78e542 | 4454 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 4455 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
4456 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4457 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
4458 | int consumed_chars = 0; |
4459 | int multibytep = coding->src_multibyte; | |
4460 | struct ccl_program ccl; | |
4461 | int source_charbuf[1024]; | |
4462 | int source_byteidx[1024]; | |
24a73b0a | 4463 | Lisp_Object attrs, charset_list; |
df7492f9 | 4464 | |
24a73b0a | 4465 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4466 | setup_ccl_program (&ccl, CODING_CCL_DECODER (coding)); |
4467 | ||
4468 | while (src < src_end) | |
4469 | { | |
7c78e542 | 4470 | const unsigned char *p = src; |
df7492f9 KH |
4471 | int *source, *source_end; |
4472 | int i = 0; | |
4473 | ||
4474 | if (multibytep) | |
4475 | while (i < 1024 && p < src_end) | |
4476 | { | |
4477 | source_byteidx[i] = p - src; | |
4478 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
4479 | } | |
4480 | else | |
4481 | while (i < 1024 && p < src_end) | |
4482 | source_charbuf[i++] = *p++; | |
8f924df7 | 4483 | |
df7492f9 KH |
4484 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
4485 | ccl.last_block = 1; | |
4486 | ||
4487 | source = source_charbuf; | |
4488 | source_end = source + i; | |
4489 | while (source < source_end) | |
4490 | { | |
4491 | ccl_driver (&ccl, source, charbuf, | |
8dcbea82 KH |
4492 | source_end - source, charbuf_end - charbuf, |
4493 | charset_list); | |
df7492f9 KH |
4494 | source += ccl.consumed; |
4495 | charbuf += ccl.produced; | |
4496 | if (ccl.status != CCL_STAT_SUSPEND_BY_DST) | |
4497 | break; | |
4498 | } | |
4499 | if (source < source_end) | |
4500 | src += source_byteidx[source - source_charbuf]; | |
4501 | else | |
4502 | src = p; | |
4503 | consumed_chars += source - source_charbuf; | |
4504 | ||
4505 | if (ccl.status != CCL_STAT_SUSPEND_BY_SRC | |
4506 | && ccl.status != CODING_RESULT_INSUFFICIENT_SRC) | |
4507 | break; | |
4508 | } | |
4509 | ||
4510 | switch (ccl.status) | |
4511 | { | |
4512 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4513 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4514 | break; |
4515 | case CCL_STAT_SUSPEND_BY_DST: | |
4516 | break; | |
4517 | case CCL_STAT_QUIT: | |
4518 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4519 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4520 | break; |
4521 | default: | |
065e3595 | 4522 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4523 | break; |
4524 | } | |
4525 | coding->consumed_char += consumed_chars; | |
4526 | coding->consumed = src - coding->source; | |
4527 | coding->charbuf_used = charbuf - coding->charbuf; | |
4528 | } | |
4529 | ||
4530 | static int | |
4531 | encode_coding_ccl (coding) | |
4532 | struct coding_system *coding; | |
4533 | { | |
4534 | struct ccl_program ccl; | |
4535 | int multibytep = coding->dst_multibyte; | |
4536 | int *charbuf = coding->charbuf; | |
4537 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4538 | unsigned char *dst = coding->destination + coding->produced; | |
4539 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4540 | unsigned char *adjusted_dst_end = dst_end - 1; | |
4541 | int destination_charbuf[1024]; | |
4542 | int i, produced_chars = 0; | |
24a73b0a | 4543 | Lisp_Object attrs, charset_list; |
df7492f9 | 4544 | |
24a73b0a | 4545 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4546 | setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding)); |
4547 | ||
4548 | ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK; | |
4549 | ccl.dst_multibyte = coding->dst_multibyte; | |
4550 | ||
4551 | while (charbuf < charbuf_end && dst < adjusted_dst_end) | |
4552 | { | |
4553 | int dst_bytes = dst_end - dst; | |
4554 | if (dst_bytes > 1024) | |
4555 | dst_bytes = 1024; | |
4556 | ||
4557 | ccl_driver (&ccl, charbuf, destination_charbuf, | |
8dcbea82 | 4558 | charbuf_end - charbuf, dst_bytes, charset_list); |
df7492f9 KH |
4559 | charbuf += ccl.consumed; |
4560 | if (multibytep) | |
4561 | for (i = 0; i < ccl.produced; i++) | |
4562 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); | |
4563 | else | |
4564 | { | |
4565 | for (i = 0; i < ccl.produced; i++) | |
4566 | *dst++ = destination_charbuf[i] & 0xFF; | |
4567 | produced_chars += ccl.produced; | |
4568 | } | |
4569 | } | |
4570 | ||
4571 | switch (ccl.status) | |
4572 | { | |
4573 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 4574 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
4575 | break; |
4576 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 4577 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
4578 | break; |
4579 | case CCL_STAT_QUIT: | |
4580 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 4581 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
4582 | break; |
4583 | default: | |
065e3595 | 4584 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4585 | break; |
1397dc18 | 4586 | } |
df7492f9 KH |
4587 | |
4588 | coding->produced_char += produced_chars; | |
4589 | coding->produced = dst - coding->destination; | |
4590 | return 0; | |
1397dc18 KH |
4591 | } |
4592 | ||
df7492f9 | 4593 | |
1397dc18 | 4594 | \f |
df7492f9 | 4595 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 4596 | |
b73bfc1c | 4597 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 4598 | |
b73bfc1c | 4599 | static void |
df7492f9 | 4600 | decode_coding_raw_text (coding) |
4ed46869 | 4601 | struct coding_system *coding; |
4ed46869 | 4602 | { |
df7492f9 | 4603 | coding->chars_at_source = 1; |
2c78b7e1 KH |
4604 | coding->consumed_char = 0; |
4605 | coding->consumed = 0; | |
065e3595 | 4606 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 4607 | } |
4ed46869 | 4608 | |
df7492f9 KH |
4609 | static int |
4610 | encode_coding_raw_text (coding) | |
4611 | struct coding_system *coding; | |
4612 | { | |
4613 | int multibytep = coding->dst_multibyte; | |
4614 | int *charbuf = coding->charbuf; | |
4615 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
4616 | unsigned char *dst = coding->destination + coding->produced; | |
4617 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4618 | int produced_chars = 0; | |
b73bfc1c KH |
4619 | int c; |
4620 | ||
df7492f9 | 4621 | if (multibytep) |
b73bfc1c | 4622 | { |
df7492f9 | 4623 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 4624 | |
df7492f9 KH |
4625 | if (coding->src_multibyte) |
4626 | while (charbuf < charbuf_end) | |
4627 | { | |
4628 | ASSURE_DESTINATION (safe_room); | |
4629 | c = *charbuf++; | |
4630 | if (ASCII_CHAR_P (c)) | |
4631 | EMIT_ONE_ASCII_BYTE (c); | |
4632 | else if (CHAR_BYTE8_P (c)) | |
4633 | { | |
4634 | c = CHAR_TO_BYTE8 (c); | |
4635 | EMIT_ONE_BYTE (c); | |
4636 | } | |
4637 | else | |
4638 | { | |
4639 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 4640 | |
df7492f9 KH |
4641 | CHAR_STRING_ADVANCE (c, p1); |
4642 | while (p0 < p1) | |
9d123124 KH |
4643 | { |
4644 | EMIT_ONE_BYTE (*p0); | |
4645 | p0++; | |
4646 | } | |
df7492f9 KH |
4647 | } |
4648 | } | |
b73bfc1c | 4649 | else |
df7492f9 KH |
4650 | while (charbuf < charbuf_end) |
4651 | { | |
4652 | ASSURE_DESTINATION (safe_room); | |
4653 | c = *charbuf++; | |
4654 | EMIT_ONE_BYTE (c); | |
4655 | } | |
4656 | } | |
4657 | else | |
4ed46869 | 4658 | { |
df7492f9 | 4659 | if (coding->src_multibyte) |
d46c5b12 | 4660 | { |
df7492f9 KH |
4661 | int safe_room = MAX_MULTIBYTE_LENGTH; |
4662 | ||
4663 | while (charbuf < charbuf_end) | |
d46c5b12 | 4664 | { |
df7492f9 KH |
4665 | ASSURE_DESTINATION (safe_room); |
4666 | c = *charbuf++; | |
4667 | if (ASCII_CHAR_P (c)) | |
4668 | *dst++ = c; | |
4669 | else if (CHAR_BYTE8_P (c)) | |
4670 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 4671 | else |
df7492f9 KH |
4672 | CHAR_STRING_ADVANCE (c, dst); |
4673 | produced_chars++; | |
d46c5b12 KH |
4674 | } |
4675 | } | |
df7492f9 KH |
4676 | else |
4677 | { | |
4678 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
4679 | while (charbuf < charbuf_end && dst < dst_end) | |
4680 | *dst++ = *charbuf++; | |
4681 | produced_chars = dst - (coding->destination + coding->dst_bytes); | |
8f924df7 | 4682 | } |
4ed46869 | 4683 | } |
065e3595 | 4684 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4685 | coding->produced_char += produced_chars; |
4686 | coding->produced = dst - coding->destination; | |
4687 | return 0; | |
4ed46869 KH |
4688 | } |
4689 | ||
ff0dacd7 KH |
4690 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
4691 | Check if a text is encoded in a charset-based coding system. If it | |
4692 | is, return 1, else return 0. */ | |
4693 | ||
0a28aafb | 4694 | static int |
ff0dacd7 | 4695 | detect_coding_charset (coding, detect_info) |
df7492f9 | 4696 | struct coding_system *coding; |
ff0dacd7 | 4697 | struct coding_detection_info *detect_info; |
1397dc18 | 4698 | { |
065e3595 | 4699 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4700 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4701 | int multibytep = coding->src_multibyte; |
4702 | int consumed_chars = 0; | |
4703 | Lisp_Object attrs, valids; | |
584948ac | 4704 | int found = 0; |
1397dc18 | 4705 | |
ff0dacd7 KH |
4706 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
4707 | ||
df7492f9 KH |
4708 | coding = &coding_categories[coding_category_charset]; |
4709 | attrs = CODING_ID_ATTRS (coding->id); | |
4710 | valids = AREF (attrs, coding_attr_charset_valids); | |
4711 | ||
4712 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4713 | src += coding->head_ascii; | |
1397dc18 | 4714 | |
b73bfc1c | 4715 | while (1) |
1397dc18 | 4716 | { |
df7492f9 | 4717 | int c; |
1397dc18 | 4718 | |
065e3595 | 4719 | src_base = src; |
df7492f9 | 4720 | ONE_MORE_BYTE (c); |
065e3595 KH |
4721 | if (c < 0) |
4722 | continue; | |
df7492f9 KH |
4723 | if (NILP (AREF (valids, c))) |
4724 | break; | |
584948ac | 4725 | if (c >= 0x80) |
ff0dacd7 | 4726 | found = CATEGORY_MASK_CHARSET; |
df7492f9 | 4727 | } |
ff0dacd7 | 4728 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 4729 | return 0; |
4ed46869 | 4730 | |
df7492f9 | 4731 | no_more_source: |
ff0dacd7 KH |
4732 | detect_info->found |= found; |
4733 | return 1; | |
df7492f9 | 4734 | } |
b73bfc1c | 4735 | |
b73bfc1c | 4736 | static void |
df7492f9 | 4737 | decode_coding_charset (coding) |
4ed46869 | 4738 | struct coding_system *coding; |
4ed46869 | 4739 | { |
8f924df7 KH |
4740 | const unsigned char *src = coding->source + coding->consumed; |
4741 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4742 | const unsigned char *src_base; | |
69a80ea3 KH |
4743 | int *charbuf = coding->charbuf + coding->charbuf_used; |
4744 | int *charbuf_end | |
4745 | = coding->charbuf + coding->charbuf_size - MAX_ANNOTATION_LENGTH; | |
df7492f9 KH |
4746 | int consumed_chars = 0, consumed_chars_base; |
4747 | int multibytep = coding->src_multibyte; | |
24a73b0a | 4748 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
4749 | int char_offset = coding->produced_char; |
4750 | int last_offset = char_offset; | |
4751 | int last_id = charset_ascii; | |
df7492f9 | 4752 | |
24a73b0a | 4753 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 4754 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 4755 | |
df7492f9 | 4756 | while (1) |
4ed46869 | 4757 | { |
4eb6d3f1 | 4758 | int c; |
24a73b0a KH |
4759 | Lisp_Object val; |
4760 | struct charset *charset; | |
4761 | int dim; | |
4762 | int len = 1; | |
4763 | unsigned code; | |
df7492f9 KH |
4764 | |
4765 | src_base = src; | |
4766 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 4767 | |
df7492f9 KH |
4768 | if (charbuf >= charbuf_end) |
4769 | break; | |
4770 | ||
4eb6d3f1 | 4771 | ONE_MORE_BYTE (c); |
065e3595 KH |
4772 | if (c < 0) |
4773 | goto invalid_code; | |
24a73b0a KH |
4774 | code = c; |
4775 | ||
4776 | val = AREF (valids, c); | |
4777 | if (NILP (val)) | |
4778 | goto invalid_code; | |
4779 | if (INTEGERP (val)) | |
d46c5b12 | 4780 | { |
24a73b0a KH |
4781 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
4782 | dim = CHARSET_DIMENSION (charset); | |
4783 | while (len < dim) | |
b73bfc1c | 4784 | { |
24a73b0a KH |
4785 | ONE_MORE_BYTE (c); |
4786 | code = (code << 8) | c; | |
4787 | len++; | |
b73bfc1c | 4788 | } |
24a73b0a KH |
4789 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
4790 | charset, code, c); | |
d46c5b12 | 4791 | } |
df7492f9 | 4792 | else |
d46c5b12 | 4793 | { |
24a73b0a KH |
4794 | /* VAL is a list of charset IDs. It is assured that the |
4795 | list is sorted by charset dimensions (smaller one | |
4796 | comes first). */ | |
4797 | while (CONSP (val)) | |
4eb6d3f1 | 4798 | { |
24a73b0a | 4799 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 4800 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 4801 | while (len < dim) |
4eb6d3f1 | 4802 | { |
acb2a965 KH |
4803 | ONE_MORE_BYTE (c); |
4804 | code = (code << 8) | c; | |
f9d71dcd | 4805 | len++; |
4eb6d3f1 | 4806 | } |
24a73b0a KH |
4807 | CODING_DECODE_CHAR (coding, src, src_base, |
4808 | src_end, charset, code, c); | |
4809 | if (c >= 0) | |
4810 | break; | |
4811 | val = XCDR (val); | |
ff0dacd7 | 4812 | } |
d46c5b12 | 4813 | } |
24a73b0a KH |
4814 | if (c < 0) |
4815 | goto invalid_code; | |
4816 | if (charset->id != charset_ascii | |
4817 | && last_id != charset->id) | |
4818 | { | |
4819 | if (last_id != charset_ascii) | |
69a80ea3 | 4820 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4821 | last_id = charset->id; |
4822 | last_offset = char_offset; | |
4823 | } | |
4824 | ||
df7492f9 | 4825 | *charbuf++ = c; |
ff0dacd7 | 4826 | char_offset++; |
df7492f9 KH |
4827 | continue; |
4828 | ||
4829 | invalid_code: | |
4830 | src = src_base; | |
4831 | consumed_chars = consumed_chars_base; | |
4832 | ONE_MORE_BYTE (c); | |
065e3595 | 4833 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4834 | char_offset++; |
df7492f9 | 4835 | coding->errors++; |
4ed46869 KH |
4836 | } |
4837 | ||
df7492f9 | 4838 | no_more_source: |
ff0dacd7 | 4839 | if (last_id != charset_ascii) |
69a80ea3 | 4840 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4841 | coding->consumed_char += consumed_chars_base; |
4842 | coding->consumed = src_base - coding->source; | |
4843 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4844 | } |
4845 | ||
df7492f9 KH |
4846 | static int |
4847 | encode_coding_charset (coding) | |
4ed46869 | 4848 | struct coding_system *coding; |
4ed46869 | 4849 | { |
df7492f9 KH |
4850 | int multibytep = coding->dst_multibyte; |
4851 | int *charbuf = coding->charbuf; | |
4852 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4853 | unsigned char *dst = coding->destination + coding->produced; | |
4854 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4855 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
4856 | int produced_chars = 0; | |
24a73b0a | 4857 | Lisp_Object attrs, charset_list; |
df7492f9 | 4858 | int ascii_compatible; |
b73bfc1c | 4859 | int c; |
b73bfc1c | 4860 | |
24a73b0a | 4861 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 4862 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 4863 | |
df7492f9 | 4864 | while (charbuf < charbuf_end) |
4ed46869 | 4865 | { |
4eb6d3f1 | 4866 | struct charset *charset; |
df7492f9 | 4867 | unsigned code; |
8f924df7 | 4868 | |
df7492f9 KH |
4869 | ASSURE_DESTINATION (safe_room); |
4870 | c = *charbuf++; | |
4871 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
4872 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 4873 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 4874 | { |
16eafb5d KH |
4875 | c = CHAR_TO_BYTE8 (c); |
4876 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 4877 | } |
d46c5b12 | 4878 | else |
b73bfc1c | 4879 | { |
4eb6d3f1 KH |
4880 | charset = char_charset (c, charset_list, &code); |
4881 | if (charset) | |
4882 | { | |
4883 | if (CHARSET_DIMENSION (charset) == 1) | |
4884 | EMIT_ONE_BYTE (code); | |
4885 | else if (CHARSET_DIMENSION (charset) == 2) | |
4886 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
4887 | else if (CHARSET_DIMENSION (charset) == 3) | |
4888 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
4889 | else | |
4890 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
4891 | (code >> 8) & 0xFF, code & 0xFF); | |
4892 | } | |
4893 | else | |
41cbe562 KH |
4894 | { |
4895 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
4896 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4897 | else | |
4898 | c = coding->default_char; | |
4899 | EMIT_ONE_BYTE (c); | |
4900 | } | |
4ed46869 | 4901 | } |
4ed46869 KH |
4902 | } |
4903 | ||
065e3595 | 4904 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4905 | coding->produced_char += produced_chars; |
4906 | coding->produced = dst - coding->destination; | |
4907 | return 0; | |
4ed46869 KH |
4908 | } |
4909 | ||
4910 | \f | |
1397dc18 | 4911 | /*** 7. C library functions ***/ |
4ed46869 | 4912 | |
df7492f9 KH |
4913 | /* Setup coding context CODING from information about CODING_SYSTEM. |
4914 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
4915 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 4916 | |
ec6d2bb8 | 4917 | void |
e0e989f6 KH |
4918 | setup_coding_system (coding_system, coding) |
4919 | Lisp_Object coding_system; | |
4ed46869 KH |
4920 | struct coding_system *coding; |
4921 | { | |
df7492f9 KH |
4922 | Lisp_Object attrs; |
4923 | Lisp_Object eol_type; | |
4924 | Lisp_Object coding_type; | |
4608c386 | 4925 | Lisp_Object val; |
4ed46869 | 4926 | |
df7492f9 | 4927 | if (NILP (coding_system)) |
ae6f73fa | 4928 | coding_system = Qundecided; |
c07c8e12 | 4929 | |
df7492f9 | 4930 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 4931 | |
df7492f9 KH |
4932 | attrs = CODING_ID_ATTRS (coding->id); |
4933 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
1f5dbf34 | 4934 | |
df7492f9 KH |
4935 | coding->mode = 0; |
4936 | coding->head_ascii = -1; | |
4937 | coding->common_flags | |
4938 | = (VECTORP (eol_type) ? CODING_REQUIRE_DETECTION_MASK : 0); | |
5e5c78be KH |
4939 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
4940 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
4941 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
4942 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
4943 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
4944 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 4945 | |
df7492f9 | 4946 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 KH |
4947 | coding->max_charset_id = SCHARS (val) - 1; |
4948 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 | 4949 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
4608c386 | 4950 | |
df7492f9 KH |
4951 | coding_type = CODING_ATTR_TYPE (attrs); |
4952 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 4953 | { |
df7492f9 KH |
4954 | coding->detector = NULL; |
4955 | coding->decoder = decode_coding_raw_text; | |
4956 | coding->encoder = encode_coding_raw_text; | |
4957 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 4958 | } |
df7492f9 | 4959 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 4960 | { |
df7492f9 KH |
4961 | int i; |
4962 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
4963 | ||
4964 | /* Invoke graphic register 0 to plane 0. */ | |
4965 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
4966 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
4967 | CODING_ISO_INVOCATION (coding, 1) | |
4968 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
4969 | /* Setup the initial status of designation. */ | |
4970 | for (i = 0; i < 4; i++) | |
4971 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
4972 | /* Not single shifting initially. */ | |
4973 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
4974 | /* Beginning of buffer should also be regarded as bol. */ | |
4975 | CODING_ISO_BOL (coding) = 1; | |
4976 | coding->detector = detect_coding_iso_2022; | |
4977 | coding->decoder = decode_coding_iso_2022; | |
4978 | coding->encoder = encode_coding_iso_2022; | |
4979 | if (flags & CODING_ISO_FLAG_SAFE) | |
4980 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 4981 | coding->common_flags |
df7492f9 KH |
4982 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
4983 | | CODING_REQUIRE_FLUSHING_MASK); | |
4984 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
4985 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
4986 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
4987 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
4988 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
4989 | { | |
4990 | setup_iso_safe_charsets (attrs); | |
4991 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 KH |
4992 | coding->max_charset_id = SCHARS (val) - 1; |
4993 | coding->safe_charsets = (char *) SDATA (val); | |
df7492f9 KH |
4994 | } |
4995 | CODING_ISO_FLAGS (coding) = flags; | |
d46c5b12 | 4996 | } |
df7492f9 | 4997 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 4998 | { |
df7492f9 KH |
4999 | coding->detector = detect_coding_charset; |
5000 | coding->decoder = decode_coding_charset; | |
5001 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5002 | coding->common_flags |
df7492f9 | 5003 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5004 | } |
df7492f9 | 5005 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5006 | { |
df7492f9 KH |
5007 | coding->detector = detect_coding_utf_8; |
5008 | coding->decoder = decode_coding_utf_8; | |
5009 | coding->encoder = encode_coding_utf_8; | |
5010 | coding->common_flags | |
5011 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
5012 | } | |
5013 | else if (EQ (coding_type, Qutf_16)) | |
5014 | { | |
5015 | val = AREF (attrs, coding_attr_utf_16_bom); | |
5016 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom | |
5017 | : EQ (val, Qt) ? utf_16_with_bom | |
5018 | : utf_16_without_bom); | |
5019 | val = AREF (attrs, coding_attr_utf_16_endian); | |
b49a1807 | 5020 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5021 | : utf_16_little_endian); |
e19c3639 | 5022 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5023 | coding->detector = detect_coding_utf_16; |
5024 | coding->decoder = decode_coding_utf_16; | |
5025 | coding->encoder = encode_coding_utf_16; | |
5026 | coding->common_flags | |
5027 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
b49a1807 KH |
5028 | if (CODING_UTF_16_BOM (coding) == utf_16_detect_bom) |
5029 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5030 | } |
df7492f9 | 5031 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5032 | { |
df7492f9 KH |
5033 | coding->detector = detect_coding_ccl; |
5034 | coding->decoder = decode_coding_ccl; | |
5035 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5036 | coding->common_flags |
df7492f9 KH |
5037 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5038 | | CODING_REQUIRE_FLUSHING_MASK); | |
5039 | } | |
5040 | else if (EQ (coding_type, Qemacs_mule)) | |
5041 | { | |
5042 | coding->detector = detect_coding_emacs_mule; | |
5043 | coding->decoder = decode_coding_emacs_mule; | |
5044 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5045 | coding->common_flags |
df7492f9 KH |
5046 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5047 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5048 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5049 | { | |
5050 | Lisp_Object tail, safe_charsets; | |
5051 | int max_charset_id = 0; | |
5052 | ||
5053 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5054 | tail = XCDR (tail)) | |
5055 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5056 | max_charset_id = XFASTINT (XCAR (tail)); | |
5057 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
5058 | make_number (255)); | |
5059 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5060 | tail = XCDR (tail)) | |
8f924df7 | 5061 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5062 | coding->max_charset_id = max_charset_id; |
8f924df7 | 5063 | coding->safe_charsets = (char *) SDATA (safe_charsets); |
df7492f9 KH |
5064 | } |
5065 | } | |
5066 | else if (EQ (coding_type, Qshift_jis)) | |
5067 | { | |
5068 | coding->detector = detect_coding_sjis; | |
5069 | coding->decoder = decode_coding_sjis; | |
5070 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5071 | coding->common_flags |
df7492f9 KH |
5072 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5073 | } | |
5074 | else if (EQ (coding_type, Qbig5)) | |
5075 | { | |
5076 | coding->detector = detect_coding_big5; | |
5077 | coding->decoder = decode_coding_big5; | |
5078 | coding->encoder = encode_coding_big5; | |
c952af22 | 5079 | coding->common_flags |
df7492f9 KH |
5080 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5081 | } | |
5082 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5083 | { |
df7492f9 KH |
5084 | coding->detector = NULL; |
5085 | coding->decoder = decode_coding_raw_text; | |
5086 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5087 | if (! EQ (eol_type, Qunix)) |
5088 | { | |
5089 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5090 | if (! VECTORP (eol_type)) | |
5091 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5092 | } | |
5093 | ||
4ed46869 | 5094 | } |
4ed46869 | 5095 | |
df7492f9 | 5096 | return; |
4ed46869 KH |
5097 | } |
5098 | ||
0ff61e78 KH |
5099 | /* Return a list of charsets supported by CODING. */ |
5100 | ||
5101 | Lisp_Object | |
5102 | coding_charset_list (coding) | |
5103 | struct coding_system *coding; | |
5104 | { | |
35befdaa | 5105 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5106 | |
5107 | CODING_GET_INFO (coding, attrs, charset_list); | |
5108 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5109 | { | |
5110 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5111 | ||
5112 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5113 | charset_list = Viso_2022_charset_list; | |
5114 | } | |
5115 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5116 | { | |
5117 | charset_list = Vemacs_mule_charset_list; | |
5118 | } | |
5119 | return charset_list; | |
5120 | } | |
5121 | ||
5122 | ||
df7492f9 KH |
5123 | /* Return raw-text or one of its subsidiaries that has the same |
5124 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5125 | |
df7492f9 KH |
5126 | Lisp_Object |
5127 | raw_text_coding_system (coding_system) | |
5128 | Lisp_Object coding_system; | |
ec6d2bb8 | 5129 | { |
0be8721c | 5130 | Lisp_Object spec, attrs; |
df7492f9 | 5131 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5132 | |
d3e4cb56 KH |
5133 | if (NILP (coding_system)) |
5134 | return Qraw_text; | |
df7492f9 KH |
5135 | spec = CODING_SYSTEM_SPEC (coding_system); |
5136 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5137 | |
df7492f9 KH |
5138 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5139 | return coding_system; | |
ec6d2bb8 | 5140 | |
df7492f9 KH |
5141 | eol_type = AREF (spec, 2); |
5142 | if (VECTORP (eol_type)) | |
5143 | return Qraw_text; | |
5144 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5145 | raw_text_eol_type = AREF (spec, 2); | |
5146 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5147 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5148 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5149 | } |
5150 | ||
54f78171 | 5151 | |
df7492f9 KH |
5152 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
5153 | does, return one of the subsidiary that has the same eol-spec as | |
5154 | PARENT. Otherwise, return CODING_SYSTEM. */ | |
5155 | ||
5156 | Lisp_Object | |
5157 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 5158 | Lisp_Object coding_system, parent; |
54f78171 | 5159 | { |
3e139625 | 5160 | Lisp_Object spec, eol_type; |
54f78171 | 5161 | |
d3e4cb56 KH |
5162 | if (NILP (coding_system)) |
5163 | coding_system = Qraw_text; | |
df7492f9 | 5164 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5165 | eol_type = AREF (spec, 2); |
d3e4cb56 KH |
5166 | if (VECTORP (eol_type) |
5167 | && ! NILP (parent)) | |
df7492f9 KH |
5168 | { |
5169 | Lisp_Object parent_spec; | |
df7492f9 KH |
5170 | Lisp_Object parent_eol_type; |
5171 | ||
5172 | parent_spec | |
5173 | = CODING_SYSTEM_SPEC (buffer_defaults.buffer_file_coding_system); | |
5174 | parent_eol_type = AREF (parent_spec, 2); | |
5175 | if (EQ (parent_eol_type, Qunix)) | |
5176 | coding_system = AREF (eol_type, 0); | |
5177 | else if (EQ (parent_eol_type, Qdos)) | |
5178 | coding_system = AREF (eol_type, 1); | |
5179 | else if (EQ (parent_eol_type, Qmac)) | |
5180 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5181 | } |
df7492f9 | 5182 | return coding_system; |
54f78171 KH |
5183 | } |
5184 | ||
4ed46869 KH |
5185 | /* Emacs has a mechanism to automatically detect a coding system if it |
5186 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5187 | it's impossible to distinguish some coding systems accurately | |
5188 | because they use the same range of codes. So, at first, coding | |
5189 | systems are categorized into 7, those are: | |
5190 | ||
0ef69138 | 5191 | o coding-category-emacs-mule |
4ed46869 KH |
5192 | |
5193 | The category for a coding system which has the same code range | |
5194 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5195 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5196 | |
5197 | o coding-category-sjis | |
5198 | ||
5199 | The category for a coding system which has the same code range | |
5200 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5201 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5202 | |
5203 | o coding-category-iso-7 | |
5204 | ||
5205 | The category for a coding system which has the same code range | |
7717c392 | 5206 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5207 | shift and single shift functions. This can encode/decode all |
5208 | charsets. Assigned the coding-system (Lisp symbol) | |
5209 | `iso-2022-7bit' by default. | |
5210 | ||
5211 | o coding-category-iso-7-tight | |
5212 | ||
5213 | Same as coding-category-iso-7 except that this can | |
5214 | encode/decode only the specified charsets. | |
4ed46869 KH |
5215 | |
5216 | o coding-category-iso-8-1 | |
5217 | ||
5218 | The category for a coding system which has the same code range | |
5219 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5220 | for DIMENSION1 charset. This doesn't use any locking shift |
5221 | and single shift functions. Assigned the coding-system (Lisp | |
5222 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
5223 | |
5224 | o coding-category-iso-8-2 | |
5225 | ||
5226 | The category for a coding system which has the same code range | |
5227 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5228 | for DIMENSION2 charset. This doesn't use any locking shift |
5229 | and single shift functions. Assigned the coding-system (Lisp | |
5230 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 5231 | |
7717c392 | 5232 | o coding-category-iso-7-else |
4ed46869 KH |
5233 | |
5234 | The category for a coding system which has the same code range | |
df7492f9 | 5235 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
5236 | single shift functions. Assigned the coding-system (Lisp |
5237 | symbol) `iso-2022-7bit-lock' by default. | |
5238 | ||
5239 | o coding-category-iso-8-else | |
5240 | ||
5241 | The category for a coding system which has the same code range | |
df7492f9 | 5242 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
5243 | single shift functions. Assigned the coding-system (Lisp |
5244 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
5245 | |
5246 | o coding-category-big5 | |
5247 | ||
5248 | The category for a coding system which has the same code range | |
5249 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5250 | `cn-big5' by default. |
4ed46869 | 5251 | |
fa42c37f KH |
5252 | o coding-category-utf-8 |
5253 | ||
5254 | The category for a coding system which has the same code range | |
6e76ae91 | 5255 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
5256 | symbol) `utf-8' by default. |
5257 | ||
5258 | o coding-category-utf-16-be | |
5259 | ||
5260 | The category for a coding system in which a text has an | |
5261 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
5262 | endian at the head. Assigned the coding-system (Lisp symbol) | |
5263 | `utf-16-be' by default. | |
5264 | ||
5265 | o coding-category-utf-16-le | |
5266 | ||
5267 | The category for a coding system in which a text has an | |
5268 | Unicode signature (cf. Unicode Standard) in the order of | |
5269 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
5270 | symbol) `utf-16-le' by default. | |
5271 | ||
1397dc18 KH |
5272 | o coding-category-ccl |
5273 | ||
5274 | The category for a coding system of which encoder/decoder is | |
5275 | written in CCL programs. The default value is nil, i.e., no | |
5276 | coding system is assigned. | |
5277 | ||
4ed46869 KH |
5278 | o coding-category-binary |
5279 | ||
5280 | The category for a coding system not categorized in any of the | |
5281 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 5282 | `no-conversion' by default. |
4ed46869 KH |
5283 | |
5284 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 5285 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
5286 | What Emacs does actually is to detect a category of coding system. |
5287 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 5288 | decide only one possible category, it selects a category of the |
4ed46869 KH |
5289 | highest priority. Priorities of categories are also specified by a |
5290 | user in a Lisp variable `coding-category-list'. | |
5291 | ||
5292 | */ | |
5293 | ||
df7492f9 KH |
5294 | #define EOL_SEEN_NONE 0 |
5295 | #define EOL_SEEN_LF 1 | |
5296 | #define EOL_SEEN_CR 2 | |
5297 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 5298 | |
ff0dacd7 KH |
5299 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
5300 | SOURCE is encoded. If CATEGORY is one of | |
5301 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
5302 | two-byte, else they are encoded by one-byte. | |
5303 | ||
5304 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 5305 | |
bc4bc72a | 5306 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
5307 | |
5308 | static int | |
89528eb3 | 5309 | detect_eol (source, src_bytes, category) |
f6cbaf43 | 5310 | const unsigned char *source; |
df7492f9 | 5311 | EMACS_INT src_bytes; |
89528eb3 | 5312 | enum coding_category category; |
4ed46869 | 5313 | { |
f6cbaf43 | 5314 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 5315 | unsigned char c; |
df7492f9 KH |
5316 | int total = 0; |
5317 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 5318 | |
89528eb3 | 5319 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 5320 | { |
df7492f9 | 5321 | int msb, lsb; |
fa42c37f | 5322 | |
89528eb3 KH |
5323 | msb = category == (coding_category_utf_16_le |
5324 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 5325 | lsb = 1 - msb; |
fa42c37f | 5326 | |
df7492f9 | 5327 | while (src + 1 < src_end) |
fa42c37f | 5328 | { |
df7492f9 KH |
5329 | c = src[lsb]; |
5330 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 5331 | { |
df7492f9 KH |
5332 | int this_eol; |
5333 | ||
5334 | if (c == '\n') | |
5335 | this_eol = EOL_SEEN_LF; | |
5336 | else if (src + 3 >= src_end | |
5337 | || src[msb + 2] != 0 | |
5338 | || src[lsb + 2] != '\n') | |
5339 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 5340 | else |
8f924df7 | 5341 | this_eol = EOL_SEEN_CRLF; |
df7492f9 KH |
5342 | |
5343 | if (eol_seen == EOL_SEEN_NONE) | |
5344 | /* This is the first end-of-line. */ | |
5345 | eol_seen = this_eol; | |
5346 | else if (eol_seen != this_eol) | |
fa42c37f | 5347 | { |
df7492f9 KH |
5348 | /* The found type is different from what found before. */ |
5349 | eol_seen = EOL_SEEN_LF; | |
5350 | break; | |
fa42c37f | 5351 | } |
df7492f9 KH |
5352 | if (++total == MAX_EOL_CHECK_COUNT) |
5353 | break; | |
fa42c37f | 5354 | } |
df7492f9 | 5355 | src += 2; |
fa42c37f | 5356 | } |
bcf26d6a | 5357 | } |
d46c5b12 | 5358 | else |
c4825358 | 5359 | { |
df7492f9 | 5360 | while (src < src_end) |
27901516 | 5361 | { |
df7492f9 KH |
5362 | c = *src++; |
5363 | if (c == '\n' || c == '\r') | |
5364 | { | |
5365 | int this_eol; | |
d46c5b12 | 5366 | |
df7492f9 KH |
5367 | if (c == '\n') |
5368 | this_eol = EOL_SEEN_LF; | |
5369 | else if (src >= src_end || *src != '\n') | |
5370 | this_eol = EOL_SEEN_CR; | |
5371 | else | |
5372 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 5373 | |
df7492f9 KH |
5374 | if (eol_seen == EOL_SEEN_NONE) |
5375 | /* This is the first end-of-line. */ | |
5376 | eol_seen = this_eol; | |
5377 | else if (eol_seen != this_eol) | |
5378 | { | |
5379 | /* The found type is different from what found before. */ | |
5380 | eol_seen = EOL_SEEN_LF; | |
5381 | break; | |
5382 | } | |
5383 | if (++total == MAX_EOL_CHECK_COUNT) | |
5384 | break; | |
5385 | } | |
5386 | } | |
73be902c | 5387 | } |
df7492f9 | 5388 | return eol_seen; |
73be902c KH |
5389 | } |
5390 | ||
df7492f9 | 5391 | |
24a73b0a | 5392 | static Lisp_Object |
df7492f9 KH |
5393 | adjust_coding_eol_type (coding, eol_seen) |
5394 | struct coding_system *coding; | |
5395 | int eol_seen; | |
73be902c | 5396 | { |
0be8721c | 5397 | Lisp_Object eol_type; |
8f924df7 | 5398 | |
df7492f9 KH |
5399 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
5400 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
5401 | { |
5402 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
5403 | eol_type = Qunix; | |
5404 | } | |
6f197c07 | 5405 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
5406 | { |
5407 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
5408 | eol_type = Qdos; | |
5409 | } | |
6f197c07 | 5410 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
5411 | { |
5412 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
5413 | eol_type = Qmac; | |
5414 | } | |
5415 | return eol_type; | |
d46c5b12 | 5416 | } |
4ed46869 | 5417 | |
df7492f9 KH |
5418 | /* Detect how a text specified in CODING is encoded. If a coding |
5419 | system is detected, update fields of CODING by the detected coding | |
5420 | system. */ | |
0a28aafb | 5421 | |
df7492f9 KH |
5422 | void |
5423 | detect_coding (coding) | |
d46c5b12 | 5424 | struct coding_system *coding; |
d46c5b12 | 5425 | { |
8f924df7 | 5426 | const unsigned char *src, *src_end; |
d46c5b12 | 5427 | |
df7492f9 KH |
5428 | coding->consumed = coding->consumed_char = 0; |
5429 | coding->produced = coding->produced_char = 0; | |
5430 | coding_set_source (coding); | |
1c3478b0 | 5431 | |
df7492f9 | 5432 | src_end = coding->source + coding->src_bytes; |
1c3478b0 | 5433 | |
df7492f9 KH |
5434 | /* If we have not yet decided the text encoding type, detect it |
5435 | now. */ | |
5436 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 5437 | { |
df7492f9 | 5438 | int c, i; |
6cb21a4f | 5439 | struct coding_detection_info detect_info; |
df7492f9 | 5440 | |
6cb21a4f | 5441 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
24a73b0a | 5442 | for (i = 0, src = coding->source; src < src_end; i++, src++) |
d46c5b12 | 5443 | { |
df7492f9 | 5444 | c = *src; |
6cb21a4f | 5445 | if (c & 0x80) |
df7492f9 | 5446 | break; |
6cb21a4f KH |
5447 | if (c < 0x20 |
5448 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
5449 | && ! inhibit_iso_escape_detection | |
5450 | && ! detect_info.checked) | |
5451 | { | |
5452 | coding->head_ascii = src - (coding->source + coding->consumed); | |
5453 | if (detect_coding_iso_2022 (coding, &detect_info)) | |
5454 | { | |
5455 | /* We have scanned the whole data. */ | |
5456 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
5457 | /* We didn't find an 8-bit code. */ | |
5458 | src = src_end; | |
5459 | break; | |
5460 | } | |
5461 | } | |
d46c5b12 | 5462 | } |
df7492f9 KH |
5463 | coding->head_ascii = src - (coding->source + coding->consumed); |
5464 | ||
3aef54f3 | 5465 | if (coding->head_ascii < coding->src_bytes |
6cb21a4f | 5466 | || detect_info.found) |
d46c5b12 | 5467 | { |
ff0dacd7 KH |
5468 | enum coding_category category; |
5469 | struct coding_system *this; | |
df7492f9 | 5470 | |
6cb21a4f KH |
5471 | if (coding->head_ascii == coding->src_bytes) |
5472 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
5473 | for (i = 0; i < coding_category_raw_text; i++) | |
5474 | { | |
5475 | category = coding_priorities[i]; | |
5476 | this = coding_categories + category; | |
5477 | if (detect_info.found & (1 << category)) | |
24a73b0a | 5478 | break; |
6cb21a4f KH |
5479 | } |
5480 | else | |
5481 | for (i = 0; i < coding_category_raw_text; i++) | |
5482 | { | |
5483 | category = coding_priorities[i]; | |
5484 | this = coding_categories + category; | |
5485 | if (this->id < 0) | |
5486 | { | |
5487 | /* No coding system of this category is defined. */ | |
5488 | detect_info.rejected |= (1 << category); | |
5489 | } | |
5490 | else if (category >= coding_category_raw_text) | |
5491 | continue; | |
5492 | else if (detect_info.checked & (1 << category)) | |
5493 | { | |
5494 | if (detect_info.found & (1 << category)) | |
5495 | break; | |
5496 | } | |
5497 | else if ((*(this->detector)) (coding, &detect_info) | |
5498 | && detect_info.found & (1 << category)) | |
5499 | { | |
5500 | if (category == coding_category_utf_16_auto) | |
5501 | { | |
5502 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5503 | category = coding_category_utf_16_le; | |
5504 | else | |
5505 | category = coding_category_utf_16_be; | |
5506 | } | |
5507 | break; | |
5508 | } | |
5509 | } | |
5510 | ||
ff0dacd7 KH |
5511 | if (i < coding_category_raw_text) |
5512 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5513 | else if (detect_info.rejected == CATEGORY_MASK_ANY) | |
df7492f9 | 5514 | setup_coding_system (Qraw_text, coding); |
ff0dacd7 | 5515 | else if (detect_info.rejected) |
df7492f9 | 5516 | for (i = 0; i < coding_category_raw_text; i++) |
ff0dacd7 KH |
5517 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) |
5518 | { | |
5519 | this = coding_categories + coding_priorities[i]; | |
5520 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5521 | break; | |
5522 | } | |
d46c5b12 | 5523 | } |
b73bfc1c | 5524 | } |
24a73b0a KH |
5525 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
5526 | == coding_category_utf_16_auto) | |
b49a1807 KH |
5527 | { |
5528 | Lisp_Object coding_systems; | |
5529 | struct coding_detection_info detect_info; | |
5530 | ||
5531 | coding_systems | |
5532 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_16_bom); | |
5533 | detect_info.found = detect_info.rejected = 0; | |
5534 | if (CONSP (coding_systems) | |
24a73b0a | 5535 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
5536 | { |
5537 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
5538 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 5539 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
5540 | setup_coding_system (XCDR (coding_systems), coding); |
5541 | } | |
5542 | } | |
4ed46869 | 5543 | } |
4ed46869 | 5544 | |
d46c5b12 | 5545 | |
aaaf0b1e | 5546 | static void |
df7492f9 | 5547 | decode_eol (coding) |
aaaf0b1e | 5548 | struct coding_system *coding; |
aaaf0b1e | 5549 | { |
24a73b0a KH |
5550 | Lisp_Object eol_type; |
5551 | unsigned char *p, *pbeg, *pend; | |
5552 | ||
5553 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
5554 | if (EQ (eol_type, Qunix)) | |
5555 | return; | |
5556 | ||
5557 | if (NILP (coding->dst_object)) | |
5558 | pbeg = coding->destination; | |
5559 | else | |
5560 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
5561 | pend = pbeg + coding->produced; | |
5562 | ||
5563 | if (VECTORP (eol_type)) | |
aaaf0b1e | 5564 | { |
df7492f9 | 5565 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 5566 | |
24a73b0a | 5567 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 5568 | { |
df7492f9 KH |
5569 | if (*p == '\n') |
5570 | eol_seen |= EOL_SEEN_LF; | |
5571 | else if (*p == '\r') | |
aaaf0b1e | 5572 | { |
df7492f9 | 5573 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 5574 | { |
df7492f9 KH |
5575 | eol_seen |= EOL_SEEN_CRLF; |
5576 | p++; | |
aaaf0b1e | 5577 | } |
aaaf0b1e | 5578 | else |
df7492f9 | 5579 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 5580 | } |
aaaf0b1e | 5581 | } |
24a73b0a KH |
5582 | if (eol_seen != EOL_SEEN_NONE |
5583 | && eol_seen != EOL_SEEN_LF | |
5584 | && eol_seen != EOL_SEEN_CRLF | |
5585 | && eol_seen != EOL_SEEN_CR) | |
5586 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 5587 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 5588 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 5589 | } |
d46c5b12 | 5590 | |
24a73b0a | 5591 | if (EQ (eol_type, Qmac)) |
27901516 | 5592 | { |
24a73b0a | 5593 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
5594 | if (*p == '\r') |
5595 | *p = '\n'; | |
4ed46869 | 5596 | } |
24a73b0a | 5597 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 5598 | { |
24a73b0a | 5599 | int n = 0; |
b73bfc1c | 5600 | |
24a73b0a KH |
5601 | if (NILP (coding->dst_object)) |
5602 | { | |
5603 | for (p = pend - 2; p >= pbeg; p--) | |
5604 | if (*p == '\r') | |
5605 | { | |
5606 | safe_bcopy ((char *) (p + 1), (char *) p, pend-- - p - 1); | |
5607 | n++; | |
5608 | } | |
5609 | } | |
5610 | else | |
5611 | { | |
5612 | for (p = pend - 2; p >= pbeg; p--) | |
5613 | if (*p == '\r') | |
5614 | { | |
5615 | int pos_byte = coding->dst_pos_byte + (p - pbeg); | |
5616 | int pos = BYTE_TO_CHAR (pos_byte); | |
5617 | ||
5618 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
5619 | n++; | |
5620 | } | |
5621 | } | |
5622 | coding->produced -= n; | |
5623 | coding->produced_char -= n; | |
aaaf0b1e | 5624 | } |
4ed46869 KH |
5625 | } |
5626 | ||
7d64c6ad | 5627 | |
a6f87d34 KH |
5628 | /* Return a translation table (or list of them) from coding system |
5629 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
5630 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 5631 | |
e6a54062 | 5632 | static Lisp_Object |
09ee6fdd KH |
5633 | get_translation_table (attrs, encodep, max_lookup) |
5634 | Lisp_Object attrs; | |
5635 | int encodep, *max_lookup; | |
7d64c6ad KH |
5636 | { |
5637 | Lisp_Object standard, translation_table; | |
09ee6fdd | 5638 | Lisp_Object val; |
7d64c6ad KH |
5639 | |
5640 | if (encodep) | |
5641 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
5642 | standard = Vstandard_translation_table_for_encode; | |
5643 | else | |
5644 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
5645 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 5646 | if (NILP (translation_table)) |
09ee6fdd KH |
5647 | translation_table = standard; |
5648 | else | |
a6f87d34 | 5649 | { |
09ee6fdd KH |
5650 | if (SYMBOLP (translation_table)) |
5651 | translation_table = Fget (translation_table, Qtranslation_table); | |
5652 | else if (CONSP (translation_table)) | |
5653 | { | |
5654 | translation_table = Fcopy_sequence (translation_table); | |
5655 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
5656 | if (SYMBOLP (XCAR (val))) | |
5657 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
5658 | } | |
5659 | if (CHAR_TABLE_P (standard)) | |
5660 | { | |
5661 | if (CONSP (translation_table)) | |
5662 | translation_table = nconc2 (translation_table, | |
5663 | Fcons (standard, Qnil)); | |
5664 | else | |
5665 | translation_table = Fcons (translation_table, | |
5666 | Fcons (standard, Qnil)); | |
5667 | } | |
a6f87d34 | 5668 | } |
2170c8f0 KH |
5669 | |
5670 | if (max_lookup) | |
09ee6fdd | 5671 | { |
2170c8f0 KH |
5672 | *max_lookup = 1; |
5673 | if (CHAR_TABLE_P (translation_table) | |
5674 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
5675 | { | |
5676 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
5677 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
5678 | *max_lookup = XFASTINT (val); | |
5679 | } | |
5680 | else if (CONSP (translation_table)) | |
5681 | { | |
5682 | Lisp_Object tail, val; | |
09ee6fdd | 5683 | |
2170c8f0 KH |
5684 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
5685 | if (CHAR_TABLE_P (XCAR (tail)) | |
5686 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
5687 | { | |
5688 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
5689 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
5690 | *max_lookup = XFASTINT (val); | |
5691 | } | |
5692 | } | |
a6f87d34 | 5693 | } |
7d64c6ad KH |
5694 | return translation_table; |
5695 | } | |
5696 | ||
09ee6fdd KH |
5697 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
5698 | do { \ | |
5699 | trans = Qnil; \ | |
5700 | if (CHAR_TABLE_P (table)) \ | |
5701 | { \ | |
5702 | trans = CHAR_TABLE_REF (table, c); \ | |
5703 | if (CHARACTERP (trans)) \ | |
5704 | c = XFASTINT (trans), trans = Qnil; \ | |
5705 | } \ | |
5706 | else if (CONSP (table)) \ | |
5707 | { \ | |
5708 | Lisp_Object tail; \ | |
5709 | \ | |
5710 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
5711 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
5712 | { \ | |
5713 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
5714 | if (CHARACTERP (trans)) \ | |
5715 | c = XFASTINT (trans), trans = Qnil; \ | |
5716 | else if (! NILP (trans)) \ | |
5717 | break; \ | |
5718 | } \ | |
5719 | } \ | |
e6a54062 KH |
5720 | } while (0) |
5721 | ||
7d64c6ad | 5722 | |
69a80ea3 KH |
5723 | static Lisp_Object |
5724 | get_translation (val, buf, buf_end, last_block, from_nchars, to_nchars) | |
5725 | Lisp_Object val; | |
5726 | int *buf, *buf_end; | |
5727 | int last_block; | |
5728 | int *from_nchars, *to_nchars; | |
5729 | { | |
433f7f87 KH |
5730 | /* VAL is TO or (([FROM-CHAR ...] . TO) ...) where TO is TO-CHAR or |
5731 | [TO-CHAR ...]. */ | |
69a80ea3 KH |
5732 | if (CONSP (val)) |
5733 | { | |
433f7f87 | 5734 | Lisp_Object from, tail; |
69a80ea3 KH |
5735 | int i, len; |
5736 | ||
433f7f87 | 5737 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
69a80ea3 | 5738 | { |
433f7f87 KH |
5739 | val = XCAR (tail); |
5740 | from = XCAR (val); | |
5741 | len = ASIZE (from); | |
5742 | for (i = 0; i < len; i++) | |
5743 | { | |
5744 | if (buf + i == buf_end) | |
5745 | { | |
5746 | if (! last_block) | |
5747 | return Qt; | |
5748 | break; | |
5749 | } | |
5750 | if (XINT (AREF (from, i)) != buf[i]) | |
5751 | break; | |
5752 | } | |
5753 | if (i == len) | |
5754 | { | |
5755 | val = XCDR (val); | |
5756 | *from_nchars = len; | |
5757 | break; | |
5758 | } | |
69a80ea3 | 5759 | } |
433f7f87 KH |
5760 | if (! CONSP (tail)) |
5761 | return Qnil; | |
69a80ea3 KH |
5762 | } |
5763 | if (VECTORP (val)) | |
5764 | *buf = XINT (AREF (val, 0)), *to_nchars = ASIZE (val); | |
5765 | else | |
5766 | *buf = XINT (val); | |
5767 | return val; | |
5768 | } | |
5769 | ||
5770 | ||
d46c5b12 | 5771 | static int |
69a80ea3 | 5772 | produce_chars (coding, translation_table, last_block) |
df7492f9 | 5773 | struct coding_system *coding; |
69a80ea3 KH |
5774 | Lisp_Object translation_table; |
5775 | int last_block; | |
4ed46869 | 5776 | { |
df7492f9 KH |
5777 | unsigned char *dst = coding->destination + coding->produced; |
5778 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5779 | int produced; | |
5780 | int produced_chars = 0; | |
69a80ea3 | 5781 | int carryover = 0; |
4ed46869 | 5782 | |
df7492f9 | 5783 | if (! coding->chars_at_source) |
4ed46869 | 5784 | { |
df7492f9 | 5785 | /* Characters are in coding->charbuf. */ |
fba4576f AS |
5786 | int *buf = coding->charbuf; |
5787 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 5788 | |
df7492f9 KH |
5789 | if (BUFFERP (coding->src_object) |
5790 | && EQ (coding->src_object, coding->dst_object)) | |
8f924df7 | 5791 | dst_end = ((unsigned char *) coding->source) + coding->consumed; |
4ed46869 | 5792 | |
df7492f9 | 5793 | while (buf < buf_end) |
4ed46869 | 5794 | { |
69a80ea3 | 5795 | int c = *buf, i; |
bc4bc72a | 5796 | |
df7492f9 KH |
5797 | if (c >= 0) |
5798 | { | |
69a80ea3 KH |
5799 | int from_nchars = 1, to_nchars = 1; |
5800 | Lisp_Object trans = Qnil; | |
5801 | ||
09ee6fdd | 5802 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 5803 | if (! NILP (trans)) |
69a80ea3 KH |
5804 | { |
5805 | trans = get_translation (trans, buf, buf_end, last_block, | |
5806 | &from_nchars, &to_nchars); | |
5807 | if (EQ (trans, Qt)) | |
5808 | break; | |
5809 | c = *buf; | |
5810 | } | |
5811 | ||
5812 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
5813 | { | |
5814 | dst = alloc_destination (coding, | |
5815 | buf_end - buf | |
5816 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
5817 | dst); | |
5818 | dst_end = coding->destination + coding->dst_bytes; | |
5819 | } | |
5820 | ||
433f7f87 | 5821 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 5822 | { |
433f7f87 KH |
5823 | if (i > 0) |
5824 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
5825 | if (coding->dst_multibyte |
5826 | || ! CHAR_BYTE8_P (c)) | |
5827 | CHAR_STRING_ADVANCE (c, dst); | |
5828 | else | |
5829 | *dst++ = CHAR_TO_BYTE8 (c); | |
5830 | } | |
5831 | produced_chars += to_nchars; | |
5832 | *buf++ = to_nchars; | |
5833 | while (--from_nchars > 0) | |
5834 | *buf++ = 0; | |
d46c5b12 | 5835 | } |
df7492f9 | 5836 | else |
69a80ea3 KH |
5837 | /* This is an annotation datum. (-C) is the length. */ |
5838 | buf += -c; | |
4ed46869 | 5839 | } |
69a80ea3 | 5840 | carryover = buf_end - buf; |
4ed46869 | 5841 | } |
fa42c37f | 5842 | else |
fa42c37f | 5843 | { |
8f924df7 KH |
5844 | const unsigned char *src = coding->source; |
5845 | const unsigned char *src_end = src + coding->src_bytes; | |
df7492f9 | 5846 | Lisp_Object eol_type; |
fa42c37f | 5847 | |
df7492f9 | 5848 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
4ed46869 | 5849 | |
df7492f9 | 5850 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 5851 | { |
df7492f9 | 5852 | if (coding->src_multibyte) |
fa42c37f | 5853 | { |
71c81426 | 5854 | int multibytep = 1; |
df7492f9 | 5855 | int consumed_chars; |
d46c5b12 | 5856 | |
df7492f9 KH |
5857 | while (1) |
5858 | { | |
8f924df7 | 5859 | const unsigned char *src_base = src; |
df7492f9 | 5860 | int c; |
b73bfc1c | 5861 | |
df7492f9 KH |
5862 | ONE_MORE_BYTE (c); |
5863 | if (c == '\r') | |
5864 | { | |
5865 | if (EQ (eol_type, Qdos)) | |
5866 | { | |
98725083 KH |
5867 | if (src == src_end) |
5868 | { | |
065e3595 KH |
5869 | record_conversion_result |
5870 | (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
98725083 KH |
5871 | goto no_more_source; |
5872 | } | |
5873 | if (*src == '\n') | |
df7492f9 KH |
5874 | c = *src++; |
5875 | } | |
5876 | else if (EQ (eol_type, Qmac)) | |
5877 | c = '\n'; | |
5878 | } | |
5879 | if (dst == dst_end) | |
5880 | { | |
2c78b7e1 | 5881 | coding->consumed = src - coding->source; |
b73bfc1c | 5882 | |
2c78b7e1 | 5883 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5884 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5885 | if (dst == dst_end) |
5886 | { | |
5887 | dst = alloc_destination (coding, src_end - src + 1, | |
5888 | dst); | |
5889 | dst_end = coding->destination + coding->dst_bytes; | |
5890 | coding_set_source (coding); | |
5891 | src = coding->source + coding->consumed; | |
5892 | src_end = coding->source + coding->src_bytes; | |
5893 | } | |
df7492f9 KH |
5894 | } |
5895 | *dst++ = c; | |
5896 | produced_chars++; | |
5897 | } | |
5898 | no_more_source: | |
5899 | ; | |
fa42c37f KH |
5900 | } |
5901 | else | |
df7492f9 KH |
5902 | while (src < src_end) |
5903 | { | |
71c81426 | 5904 | int multibytep = 1; |
df7492f9 | 5905 | int c = *src++; |
b73bfc1c | 5906 | |
df7492f9 KH |
5907 | if (c == '\r') |
5908 | { | |
5909 | if (EQ (eol_type, Qdos)) | |
5910 | { | |
5911 | if (src < src_end | |
5912 | && *src == '\n') | |
5913 | c = *src++; | |
5914 | } | |
5915 | else if (EQ (eol_type, Qmac)) | |
5916 | c = '\n'; | |
5917 | } | |
5918 | if (dst >= dst_end - 1) | |
5919 | { | |
2c78b7e1 | 5920 | coding->consumed = src - coding->source; |
df7492f9 | 5921 | |
2c78b7e1 | 5922 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 5923 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
5924 | if (dst >= dst_end - 1) |
5925 | { | |
5926 | dst = alloc_destination (coding, src_end - src + 2, | |
5927 | dst); | |
5928 | dst_end = coding->destination + coding->dst_bytes; | |
5929 | coding_set_source (coding); | |
5930 | src = coding->source + coding->consumed; | |
5931 | src_end = coding->source + coding->src_bytes; | |
5932 | } | |
df7492f9 KH |
5933 | } |
5934 | EMIT_ONE_BYTE (c); | |
5935 | } | |
d46c5b12 | 5936 | } |
df7492f9 KH |
5937 | else |
5938 | { | |
5939 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 5940 | { |
df7492f9 | 5941 | int require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 5942 | |
df7492f9 | 5943 | if (require > 0) |
fa42c37f | 5944 | { |
df7492f9 KH |
5945 | EMACS_INT offset = src - coding->source; |
5946 | ||
5947 | dst = alloc_destination (coding, require, dst); | |
5948 | coding_set_source (coding); | |
5949 | src = coding->source + offset; | |
5950 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
5951 | } |
5952 | } | |
df7492f9 KH |
5953 | produced_chars = coding->src_chars; |
5954 | while (src < src_end) | |
fa42c37f | 5955 | { |
df7492f9 KH |
5956 | int c = *src++; |
5957 | ||
5958 | if (c == '\r') | |
5959 | { | |
5960 | if (EQ (eol_type, Qdos)) | |
5961 | { | |
5962 | if (src < src_end | |
5963 | && *src == '\n') | |
5964 | c = *src++; | |
5965 | produced_chars--; | |
5966 | } | |
5967 | else if (EQ (eol_type, Qmac)) | |
5968 | c = '\n'; | |
5969 | } | |
5970 | *dst++ = c; | |
fa42c37f KH |
5971 | } |
5972 | } | |
2c78b7e1 KH |
5973 | coding->consumed = coding->src_bytes; |
5974 | coding->consumed_char = coding->src_chars; | |
fa42c37f KH |
5975 | } |
5976 | ||
df7492f9 KH |
5977 | produced = dst - (coding->destination + coding->produced); |
5978 | if (BUFFERP (coding->dst_object)) | |
5979 | insert_from_gap (produced_chars, produced); | |
5980 | coding->produced += produced; | |
5981 | coding->produced_char += produced_chars; | |
69a80ea3 | 5982 | return carryover; |
fa42c37f KH |
5983 | } |
5984 | ||
ff0dacd7 KH |
5985 | /* Compose text in CODING->object according to the annotation data at |
5986 | CHARBUF. CHARBUF is an array: | |
5987 | [ -LENGTH ANNOTATION_MASK FROM TO METHOD COMP_LEN [ COMPONENTS... ] ] | |
df7492f9 | 5988 | */ |
4ed46869 | 5989 | |
df7492f9 | 5990 | static INLINE void |
69a80ea3 | 5991 | produce_composition (coding, charbuf, pos) |
4ed46869 | 5992 | struct coding_system *coding; |
df7492f9 | 5993 | int *charbuf; |
69a80ea3 | 5994 | EMACS_INT pos; |
4ed46869 | 5995 | { |
df7492f9 | 5996 | int len; |
69a80ea3 | 5997 | EMACS_INT to; |
df7492f9 | 5998 | enum composition_method method; |
df7492f9 | 5999 | Lisp_Object components; |
fa42c37f | 6000 | |
df7492f9 | 6001 | len = -charbuf[0]; |
69a80ea3 | 6002 | to = pos + charbuf[2]; |
9ffd559c KH |
6003 | if (to <= pos) |
6004 | return; | |
69a80ea3 | 6005 | method = (enum composition_method) (charbuf[3]); |
d46c5b12 | 6006 | |
df7492f9 KH |
6007 | if (method == COMPOSITION_RELATIVE) |
6008 | components = Qnil; | |
9ffd559c KH |
6009 | else if (method >= COMPOSITION_WITH_RULE |
6010 | && method <= COMPOSITION_WITH_RULE_ALTCHARS) | |
d46c5b12 | 6011 | { |
df7492f9 KH |
6012 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
6013 | int i; | |
b73bfc1c | 6014 | |
69a80ea3 KH |
6015 | len -= 4; |
6016 | charbuf += 4; | |
df7492f9 | 6017 | for (i = 0; i < len; i++) |
9ffd559c KH |
6018 | { |
6019 | args[i] = make_number (charbuf[i]); | |
6020 | if (args[i] < 0) | |
6021 | return; | |
6022 | } | |
df7492f9 KH |
6023 | components = (method == COMPOSITION_WITH_ALTCHARS |
6024 | ? Fstring (len, args) : Fvector (len, args)); | |
d46c5b12 | 6025 | } |
9ffd559c KH |
6026 | else |
6027 | return; | |
69a80ea3 | 6028 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6029 | } |
6030 | ||
d46c5b12 | 6031 | |
ff0dacd7 KH |
6032 | /* Put `charset' property on text in CODING->object according to |
6033 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6034 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6035 | */ |
d46c5b12 | 6036 | |
ff0dacd7 | 6037 | static INLINE void |
69a80ea3 | 6038 | produce_charset (coding, charbuf, pos) |
d46c5b12 | 6039 | struct coding_system *coding; |
ff0dacd7 | 6040 | int *charbuf; |
69a80ea3 | 6041 | EMACS_INT pos; |
d46c5b12 | 6042 | { |
69a80ea3 KH |
6043 | EMACS_INT from = pos - charbuf[2]; |
6044 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 6045 | |
69a80ea3 | 6046 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6047 | Qcharset, CHARSET_NAME (charset), |
6048 | coding->dst_object); | |
d46c5b12 KH |
6049 | } |
6050 | ||
d46c5b12 | 6051 | |
df7492f9 KH |
6052 | #define CHARBUF_SIZE 0x4000 |
6053 | ||
6054 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6055 | do { \ | |
6056 | int size = CHARBUF_SIZE;; \ | |
6057 | \ | |
6058 | coding->charbuf = NULL; \ | |
6059 | while (size > 1024) \ | |
6060 | { \ | |
6061 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
6062 | if (coding->charbuf) \ | |
6063 | break; \ | |
6064 | size >>= 1; \ | |
6065 | } \ | |
6066 | if (! coding->charbuf) \ | |
6067 | { \ | |
065e3595 | 6068 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
6069 | return coding->result; \ |
6070 | } \ | |
6071 | coding->charbuf_size = size; \ | |
6072 | } while (0) | |
4ed46869 | 6073 | |
d46c5b12 KH |
6074 | |
6075 | static void | |
69a80ea3 | 6076 | produce_annotation (coding, pos) |
d46c5b12 | 6077 | struct coding_system *coding; |
69a80ea3 | 6078 | EMACS_INT pos; |
d46c5b12 | 6079 | { |
df7492f9 KH |
6080 | int *charbuf = coding->charbuf; |
6081 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6082 | |
ff0dacd7 KH |
6083 | if (NILP (coding->dst_object)) |
6084 | return; | |
d46c5b12 | 6085 | |
df7492f9 | 6086 | while (charbuf < charbuf_end) |
a84f1519 | 6087 | { |
df7492f9 | 6088 | if (*charbuf >= 0) |
69a80ea3 | 6089 | pos += *charbuf++; |
d46c5b12 | 6090 | else |
d46c5b12 | 6091 | { |
df7492f9 | 6092 | int len = -*charbuf; |
ff0dacd7 | 6093 | switch (charbuf[1]) |
df7492f9 KH |
6094 | { |
6095 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
69a80ea3 | 6096 | produce_composition (coding, charbuf, pos); |
df7492f9 | 6097 | break; |
ff0dacd7 | 6098 | case CODING_ANNOTATE_CHARSET_MASK: |
69a80ea3 | 6099 | produce_charset (coding, charbuf, pos); |
ff0dacd7 | 6100 | break; |
df7492f9 KH |
6101 | default: |
6102 | abort (); | |
6103 | } | |
6104 | charbuf += len; | |
d46c5b12 | 6105 | } |
a84f1519 | 6106 | } |
d46c5b12 KH |
6107 | } |
6108 | ||
df7492f9 KH |
6109 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6110 | CODING->src_object is a buffer, a string, or nil. | |
6111 | CODING->dst_object is a buffer. | |
d46c5b12 | 6112 | |
df7492f9 KH |
6113 | If CODING->src_object is a buffer, it must be the current buffer. |
6114 | In this case, if CODING->src_pos is positive, it is a position of | |
6115 | the source text in the buffer, otherwise, the source text is in the | |
6116 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
6117 | the text from GPT (which must be the same as PT). If this is the | |
6118 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6119 | negative. | |
d46c5b12 | 6120 | |
df7492f9 KH |
6121 | If CODING->src_object is a string, CODING->src_pos in an index to |
6122 | that string. | |
d46c5b12 | 6123 | |
df7492f9 KH |
6124 | If CODING->src_object is nil, CODING->source must already point to |
6125 | the non-relocatable memory area. In this case, CODING->src_pos is | |
6126 | an offset from CODING->source. | |
73be902c | 6127 | |
df7492f9 KH |
6128 | The decoded data is inserted at the current point of the buffer |
6129 | CODING->dst_object. | |
6130 | */ | |
d46c5b12 | 6131 | |
df7492f9 KH |
6132 | static int |
6133 | decode_coding (coding) | |
d46c5b12 | 6134 | struct coding_system *coding; |
d46c5b12 | 6135 | { |
df7492f9 | 6136 | Lisp_Object attrs; |
24a73b0a | 6137 | Lisp_Object undo_list; |
7d64c6ad | 6138 | Lisp_Object translation_table; |
69a80ea3 KH |
6139 | int carryover; |
6140 | int i; | |
d46c5b12 | 6141 | |
df7492f9 KH |
6142 | if (BUFFERP (coding->src_object) |
6143 | && coding->src_pos > 0 | |
6144 | && coding->src_pos < GPT | |
6145 | && coding->src_pos + coding->src_chars > GPT) | |
6146 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 6147 | |
24a73b0a | 6148 | undo_list = Qt; |
df7492f9 | 6149 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 6150 | { |
df7492f9 KH |
6151 | if (current_buffer != XBUFFER (coding->dst_object)) |
6152 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6153 | if (GPT != PT) | |
6154 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
6155 | undo_list = current_buffer->undo_list; |
6156 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
6157 | } |
6158 | ||
df7492f9 KH |
6159 | coding->consumed = coding->consumed_char = 0; |
6160 | coding->produced = coding->produced_char = 0; | |
6161 | coding->chars_at_source = 0; | |
065e3595 | 6162 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 6163 | coding->errors = 0; |
1c3478b0 | 6164 | |
df7492f9 KH |
6165 | ALLOC_CONVERSION_WORK_AREA (coding); |
6166 | ||
6167 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 6168 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 6169 | |
69a80ea3 | 6170 | carryover = 0; |
df7492f9 | 6171 | do |
b73bfc1c | 6172 | { |
69a80ea3 KH |
6173 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
6174 | ||
df7492f9 KH |
6175 | coding_set_source (coding); |
6176 | coding->annotated = 0; | |
69a80ea3 | 6177 | coding->charbuf_used = carryover; |
df7492f9 | 6178 | (*(coding->decoder)) (coding); |
df7492f9 | 6179 | coding_set_destination (coding); |
69a80ea3 | 6180 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 6181 | if (coding->annotated) |
69a80ea3 KH |
6182 | produce_annotation (coding, pos); |
6183 | for (i = 0; i < carryover; i++) | |
6184 | coding->charbuf[i] | |
6185 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 6186 | } |
df7492f9 | 6187 | while (coding->consumed < coding->src_bytes |
0ca493ee | 6188 | && coding->result != CODING_RESULT_INSUFFICIENT_MEM); |
d46c5b12 | 6189 | |
69a80ea3 KH |
6190 | if (carryover > 0) |
6191 | { | |
6192 | coding_set_destination (coding); | |
6193 | coding->charbuf_used = carryover; | |
6194 | produce_chars (coding, translation_table, 1); | |
6195 | } | |
6196 | ||
df7492f9 KH |
6197 | coding->carryover_bytes = 0; |
6198 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 6199 | { |
df7492f9 | 6200 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 6201 | const unsigned char *src; |
df7492f9 KH |
6202 | |
6203 | coding_set_source (coding); | |
6204 | coding_set_destination (coding); | |
6205 | src = coding->source + coding->consumed; | |
6206 | ||
6207 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 6208 | { |
df7492f9 KH |
6209 | /* Flush out unprocessed data as binary chars. We are sure |
6210 | that the number of data is less than the size of | |
6211 | coding->charbuf. */ | |
065e3595 | 6212 | coding->charbuf_used = 0; |
df7492f9 | 6213 | while (nbytes-- > 0) |
1c3478b0 | 6214 | { |
df7492f9 | 6215 | int c = *src++; |
98725083 | 6216 | |
1c91457d KH |
6217 | if (c & 0x80) |
6218 | c = BYTE8_TO_CHAR (c); | |
6219 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 6220 | } |
f6cbaf43 | 6221 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 6222 | } |
d46c5b12 | 6223 | else |
df7492f9 KH |
6224 | { |
6225 | /* Record unprocessed bytes in coding->carryover. We are | |
6226 | sure that the number of data is less than the size of | |
6227 | coding->carryover. */ | |
6228 | unsigned char *p = coding->carryover; | |
6229 | ||
6230 | coding->carryover_bytes = nbytes; | |
6231 | while (nbytes-- > 0) | |
6232 | *p++ = *src++; | |
1c3478b0 | 6233 | } |
df7492f9 | 6234 | coding->consumed = coding->src_bytes; |
b73bfc1c | 6235 | } |
69f76525 | 6236 | |
24a73b0a KH |
6237 | if (BUFFERP (coding->dst_object)) |
6238 | { | |
6239 | current_buffer->undo_list = undo_list; | |
6240 | record_insert (coding->dst_pos, coding->produced_char); | |
6241 | } | |
6242 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)) | |
6243 | decode_eol (coding); | |
73be902c | 6244 | return coding->result; |
4ed46869 KH |
6245 | } |
6246 | ||
aaaf0b1e | 6247 | |
e1c23804 | 6248 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
6249 | ending before LIMIT of CODING->src_object (buffer or string), store |
6250 | the data in BUF, set *STOP to a starting position of the next | |
6251 | composition (if any) or to LIMIT, and return the address of the | |
6252 | next element of BUF. | |
6253 | ||
6254 | If such an annotation is not found, set *STOP to a starting | |
6255 | position of a composition after POS (if any) or to LIMIT, and | |
6256 | return BUF. */ | |
6257 | ||
6258 | static INLINE int * | |
6259 | handle_composition_annotation (pos, limit, coding, buf, stop) | |
6260 | EMACS_INT pos, limit; | |
aaaf0b1e | 6261 | struct coding_system *coding; |
ff0dacd7 KH |
6262 | int *buf; |
6263 | EMACS_INT *stop; | |
aaaf0b1e | 6264 | { |
ff0dacd7 KH |
6265 | EMACS_INT start, end; |
6266 | Lisp_Object prop; | |
aaaf0b1e | 6267 | |
ff0dacd7 KH |
6268 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
6269 | || end > limit) | |
6270 | *stop = limit; | |
6271 | else if (start > pos) | |
6272 | *stop = start; | |
6273 | else | |
aaaf0b1e | 6274 | { |
ff0dacd7 | 6275 | if (start == pos) |
aaaf0b1e | 6276 | { |
ff0dacd7 KH |
6277 | /* We found a composition. Store the corresponding |
6278 | annotation data in BUF. */ | |
6279 | int *head = buf; | |
6280 | enum composition_method method = COMPOSITION_METHOD (prop); | |
6281 | int nchars = COMPOSITION_LENGTH (prop); | |
6282 | ||
69a80ea3 | 6283 | ADD_COMPOSITION_DATA (buf, nchars, method); |
ff0dacd7 | 6284 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 6285 | { |
ff0dacd7 KH |
6286 | Lisp_Object components; |
6287 | int len, i, i_byte; | |
6288 | ||
6289 | components = COMPOSITION_COMPONENTS (prop); | |
6290 | if (VECTORP (components)) | |
aaaf0b1e | 6291 | { |
ff0dacd7 KH |
6292 | len = XVECTOR (components)->size; |
6293 | for (i = 0; i < len; i++) | |
6294 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 6295 | } |
ff0dacd7 | 6296 | else if (STRINGP (components)) |
aaaf0b1e | 6297 | { |
8f924df7 | 6298 | len = SCHARS (components); |
ff0dacd7 KH |
6299 | i = i_byte = 0; |
6300 | while (i < len) | |
6301 | { | |
6302 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
6303 | buf++; | |
6304 | } | |
6305 | } | |
6306 | else if (INTEGERP (components)) | |
6307 | { | |
6308 | len = 1; | |
6309 | *buf++ = XINT (components); | |
6310 | } | |
6311 | else if (CONSP (components)) | |
6312 | { | |
6313 | for (len = 0; CONSP (components); | |
6314 | len++, components = XCDR (components)) | |
6315 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 6316 | } |
aaaf0b1e | 6317 | else |
ff0dacd7 KH |
6318 | abort (); |
6319 | *head -= len; | |
aaaf0b1e | 6320 | } |
aaaf0b1e | 6321 | } |
ff0dacd7 KH |
6322 | |
6323 | if (find_composition (end, limit, &start, &end, &prop, | |
6324 | coding->src_object) | |
6325 | && end <= limit) | |
6326 | *stop = start; | |
6327 | else | |
6328 | *stop = limit; | |
aaaf0b1e | 6329 | } |
ff0dacd7 KH |
6330 | return buf; |
6331 | } | |
6332 | ||
6333 | ||
e1c23804 | 6334 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
6335 | CODING->src_object (buffer of string), store the data in BUF, set |
6336 | *STOP to the position where the value of `charset' property changes | |
6337 | (limiting by LIMIT), and return the address of the next element of | |
6338 | BUF. | |
6339 | ||
6340 | If the property value is nil, set *STOP to the position where the | |
6341 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
6342 | ||
6343 | static INLINE int * | |
6344 | handle_charset_annotation (pos, limit, coding, buf, stop) | |
6345 | EMACS_INT pos, limit; | |
6346 | struct coding_system *coding; | |
6347 | int *buf; | |
6348 | EMACS_INT *stop; | |
6349 | { | |
6350 | Lisp_Object val, next; | |
6351 | int id; | |
6352 | ||
6353 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
6354 | if (! NILP (val) && CHARSETP (val)) | |
6355 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
6356 | else | |
6357 | id = -1; | |
69a80ea3 | 6358 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
6359 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
6360 | coding->src_object, | |
6361 | make_number (limit)); | |
6362 | *stop = XINT (next); | |
6363 | return buf; | |
6364 | } | |
6365 | ||
6366 | ||
df7492f9 | 6367 | static void |
09ee6fdd | 6368 | consume_chars (coding, translation_table, max_lookup) |
df7492f9 | 6369 | struct coding_system *coding; |
433f7f87 | 6370 | Lisp_Object translation_table; |
09ee6fdd | 6371 | int max_lookup; |
df7492f9 KH |
6372 | { |
6373 | int *buf = coding->charbuf; | |
ff0dacd7 | 6374 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 6375 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 6376 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
6377 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
6378 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
6379 | int multibytep = coding->src_multibyte; |
6380 | Lisp_Object eol_type; | |
6381 | int c; | |
ff0dacd7 | 6382 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 6383 | int *lookup_buf = NULL; |
433f7f87 KH |
6384 | |
6385 | if (! NILP (translation_table)) | |
09ee6fdd | 6386 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 6387 | |
df7492f9 KH |
6388 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6389 | if (VECTORP (eol_type)) | |
6390 | eol_type = Qunix; | |
88993dfd | 6391 | |
df7492f9 KH |
6392 | /* Note: composition handling is not yet implemented. */ |
6393 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 6394 | |
0b5670c9 KH |
6395 | if (NILP (coding->src_object)) |
6396 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 6397 | else |
0b5670c9 KH |
6398 | { |
6399 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
6400 | stop = stop_composition = pos; | |
6401 | else | |
6402 | stop = stop_composition = end_pos; | |
6403 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
6404 | stop = stop_charset = pos; | |
6405 | else | |
6406 | stop_charset = end_pos; | |
6407 | } | |
ec6d2bb8 | 6408 | |
24a73b0a | 6409 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 6410 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 6411 | while (buf < buf_end) |
aaaf0b1e | 6412 | { |
433f7f87 KH |
6413 | Lisp_Object trans; |
6414 | ||
df7492f9 | 6415 | if (pos == stop) |
ec6d2bb8 | 6416 | { |
df7492f9 KH |
6417 | if (pos == end_pos) |
6418 | break; | |
ff0dacd7 KH |
6419 | if (pos == stop_composition) |
6420 | buf = handle_composition_annotation (pos, end_pos, coding, | |
6421 | buf, &stop_composition); | |
6422 | if (pos == stop_charset) | |
6423 | buf = handle_charset_annotation (pos, end_pos, coding, | |
6424 | buf, &stop_charset); | |
6425 | stop = (stop_composition < stop_charset | |
6426 | ? stop_composition : stop_charset); | |
df7492f9 KH |
6427 | } |
6428 | ||
6429 | if (! multibytep) | |
4776e638 | 6430 | { |
d3e4cb56 | 6431 | EMACS_INT bytes; |
aaaf0b1e | 6432 | |
ea29edf2 KH |
6433 | if (coding->encoder == encode_coding_raw_text) |
6434 | c = *src++, pos++; | |
6435 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
4776e638 KH |
6436 | c = STRING_CHAR_ADVANCE (src), pos += bytes; |
6437 | else | |
f03caae0 | 6438 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 6439 | } |
df7492f9 | 6440 | else |
4776e638 | 6441 | c = STRING_CHAR_ADVANCE (src), pos++; |
df7492f9 KH |
6442 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
6443 | c = '\n'; | |
6444 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 6445 | { |
df7492f9 | 6446 | if (c == '\n') |
aaaf0b1e | 6447 | { |
df7492f9 KH |
6448 | if (EQ (eol_type, Qdos)) |
6449 | *buf++ = '\r'; | |
6450 | else | |
6451 | c = '\r'; | |
aaaf0b1e KH |
6452 | } |
6453 | } | |
433f7f87 | 6454 | |
e6a54062 | 6455 | trans = Qnil; |
09ee6fdd | 6456 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6457 | if (NILP (trans)) |
433f7f87 KH |
6458 | *buf++ = c; |
6459 | else | |
6460 | { | |
6461 | int from_nchars = 1, to_nchars = 1; | |
6462 | int *lookup_buf_end; | |
6463 | const unsigned char *p = src; | |
6464 | int i; | |
6465 | ||
6466 | lookup_buf[0] = c; | |
6467 | for (i = 1; i < max_lookup && p < src_end; i++) | |
6468 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
6469 | lookup_buf_end = lookup_buf + i; | |
6470 | trans = get_translation (trans, lookup_buf, lookup_buf_end, 1, | |
6471 | &from_nchars, &to_nchars); | |
6472 | if (EQ (trans, Qt) | |
6473 | || buf + to_nchars > buf_end) | |
6474 | break; | |
6475 | *buf++ = *lookup_buf; | |
6476 | for (i = 1; i < to_nchars; i++) | |
6477 | *buf++ = XINT (AREF (trans, i)); | |
6478 | for (i = 1; i < from_nchars; i++, pos++) | |
6479 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
6480 | } | |
aaaf0b1e | 6481 | } |
ec6d2bb8 | 6482 | |
df7492f9 KH |
6483 | coding->consumed = src - coding->source; |
6484 | coding->consumed_char = pos - coding->src_pos; | |
6485 | coding->charbuf_used = buf - coding->charbuf; | |
6486 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
6487 | } |
6488 | ||
4ed46869 | 6489 | |
df7492f9 KH |
6490 | /* Encode the text at CODING->src_object into CODING->dst_object. |
6491 | CODING->src_object is a buffer or a string. | |
6492 | CODING->dst_object is a buffer or nil. | |
6493 | ||
6494 | If CODING->src_object is a buffer, it must be the current buffer. | |
6495 | In this case, if CODING->src_pos is positive, it is a position of | |
6496 | the source text in the buffer, otherwise. the source text is in the | |
6497 | gap area of the buffer, and coding->src_pos specifies the offset of | |
6498 | the text from GPT (which must be the same as PT). If this is the | |
6499 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6500 | negative and CODING should not have `pre-write-conversion'. | |
6501 | ||
6502 | If CODING->src_object is a string, CODING should not have | |
6503 | `pre-write-conversion'. | |
6504 | ||
6505 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
6506 | the current point of that buffer. | |
6507 | ||
6508 | If CODING->dst_object is nil, the encoded data is placed at the | |
6509 | memory area specified by CODING->destination. */ | |
6510 | ||
6511 | static int | |
6512 | encode_coding (coding) | |
4ed46869 | 6513 | struct coding_system *coding; |
4ed46869 | 6514 | { |
df7492f9 | 6515 | Lisp_Object attrs; |
7d64c6ad | 6516 | Lisp_Object translation_table; |
09ee6fdd | 6517 | int max_lookup; |
9861e777 | 6518 | |
df7492f9 | 6519 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
6520 | if (coding->encoder == encode_coding_raw_text) |
6521 | translation_table = Qnil, max_lookup = 0; | |
6522 | else | |
6523 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 6524 | |
df7492f9 | 6525 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 6526 | { |
df7492f9 KH |
6527 | set_buffer_internal (XBUFFER (coding->dst_object)); |
6528 | coding->dst_multibyte | |
6529 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 6530 | } |
4ed46869 | 6531 | |
b73bfc1c | 6532 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 6533 | coding->produced = coding->produced_char = 0; |
065e3595 | 6534 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 6535 | coding->errors = 0; |
b73bfc1c | 6536 | |
df7492f9 | 6537 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 6538 | |
df7492f9 KH |
6539 | do { |
6540 | coding_set_source (coding); | |
09ee6fdd | 6541 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
6542 | coding_set_destination (coding); |
6543 | (*(coding->encoder)) (coding); | |
6544 | } while (coding->consumed_char < coding->src_chars); | |
6545 | ||
6546 | if (BUFFERP (coding->dst_object)) | |
6547 | insert_from_gap (coding->produced_char, coding->produced); | |
6548 | ||
6549 | return (coding->result); | |
ec6d2bb8 KH |
6550 | } |
6551 | ||
fb88bf2d | 6552 | |
24a73b0a KH |
6553 | /* Name (or base name) of work buffer for code conversion. */ |
6554 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 6555 | |
24a73b0a KH |
6556 | /* A working buffer used by the top level conversion. Once it is |
6557 | created, it is never destroyed. It has the name | |
6558 | Vcode_conversion_workbuf_name. The other working buffers are | |
6559 | destroyed after the use is finished, and their names are modified | |
6560 | versions of Vcode_conversion_workbuf_name. */ | |
6561 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 6562 | |
24a73b0a KH |
6563 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
6564 | static int reused_workbuf_in_use; | |
4ed46869 | 6565 | |
24a73b0a KH |
6566 | |
6567 | /* Return a working buffer of code convesion. MULTIBYTE specifies the | |
6568 | multibyteness of returning buffer. */ | |
b73bfc1c | 6569 | |
f6cbaf43 | 6570 | static Lisp_Object |
24a73b0a | 6571 | make_conversion_work_buffer (multibyte) |
f6cbaf43 | 6572 | int multibyte; |
df7492f9 | 6573 | { |
24a73b0a KH |
6574 | Lisp_Object name, workbuf; |
6575 | struct buffer *current; | |
4ed46869 | 6576 | |
24a73b0a | 6577 | if (reused_workbuf_in_use++) |
065e3595 KH |
6578 | { |
6579 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
6580 | workbuf = Fget_buffer_create (name); | |
6581 | } | |
df7492f9 | 6582 | else |
065e3595 KH |
6583 | { |
6584 | name = Vcode_conversion_workbuf_name; | |
6585 | workbuf = Fget_buffer_create (name); | |
6586 | if (NILP (Vcode_conversion_reused_workbuf)) | |
6587 | Vcode_conversion_reused_workbuf = workbuf; | |
6588 | } | |
24a73b0a KH |
6589 | current = current_buffer; |
6590 | set_buffer_internal (XBUFFER (workbuf)); | |
6591 | Ferase_buffer (); | |
df7492f9 | 6592 | current_buffer->undo_list = Qt; |
24a73b0a | 6593 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 6594 | set_buffer_internal (current); |
24a73b0a | 6595 | return workbuf; |
df7492f9 | 6596 | } |
d46c5b12 | 6597 | |
24a73b0a | 6598 | |
4776e638 | 6599 | static Lisp_Object |
24a73b0a KH |
6600 | code_conversion_restore (arg) |
6601 | Lisp_Object arg; | |
4776e638 | 6602 | { |
24a73b0a | 6603 | Lisp_Object current, workbuf; |
948bdcf3 | 6604 | struct gcpro gcpro1; |
24a73b0a | 6605 | |
948bdcf3 | 6606 | GCPRO1 (arg); |
24a73b0a KH |
6607 | current = XCAR (arg); |
6608 | workbuf = XCDR (arg); | |
6609 | if (! NILP (workbuf)) | |
6610 | { | |
6611 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
6612 | reused_workbuf_in_use = 0; | |
6613 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
6614 | Fkill_buffer (workbuf); | |
6615 | } | |
6616 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 6617 | UNGCPRO; |
4776e638 KH |
6618 | return Qnil; |
6619 | } | |
b73bfc1c | 6620 | |
24a73b0a KH |
6621 | Lisp_Object |
6622 | code_conversion_save (with_work_buf, multibyte) | |
4776e638 | 6623 | int with_work_buf, multibyte; |
df7492f9 | 6624 | { |
24a73b0a | 6625 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 6626 | |
4776e638 | 6627 | if (with_work_buf) |
24a73b0a KH |
6628 | workbuf = make_conversion_work_buffer (multibyte); |
6629 | record_unwind_protect (code_conversion_restore, | |
6630 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 6631 | return workbuf; |
df7492f9 | 6632 | } |
d46c5b12 | 6633 | |
df7492f9 KH |
6634 | int |
6635 | decode_coding_gap (coding, chars, bytes) | |
6636 | struct coding_system *coding; | |
6637 | EMACS_INT chars, bytes; | |
6638 | { | |
6639 | int count = specpdl_ptr - specpdl; | |
5e5c78be | 6640 | Lisp_Object attrs; |
fb88bf2d | 6641 | |
24a73b0a | 6642 | code_conversion_save (0, 0); |
ec6d2bb8 | 6643 | |
24a73b0a | 6644 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6645 | coding->src_chars = chars; |
6646 | coding->src_bytes = bytes; | |
6647 | coding->src_pos = -chars; | |
6648 | coding->src_pos_byte = -bytes; | |
6649 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 6650 | coding->dst_object = coding->src_object; |
df7492f9 KH |
6651 | coding->dst_pos = PT; |
6652 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 6653 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
98725083 | 6654 | coding->mode |= CODING_MODE_LAST_BLOCK; |
4ed46869 | 6655 | |
df7492f9 KH |
6656 | if (CODING_REQUIRE_DETECTION (coding)) |
6657 | detect_coding (coding); | |
8f924df7 | 6658 | |
df7492f9 | 6659 | decode_coding (coding); |
d46c5b12 | 6660 | |
5e5c78be KH |
6661 | attrs = CODING_ID_ATTRS (coding->id); |
6662 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 6663 | { |
5e5c78be KH |
6664 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
6665 | Lisp_Object val; | |
6666 | ||
6667 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
6668 | val = call1 (CODING_ATTR_POST_READ (attrs), |
6669 | make_number (coding->produced_char)); | |
5e5c78be KH |
6670 | CHECK_NATNUM (val); |
6671 | coding->produced_char += Z - prev_Z; | |
6672 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 6673 | } |
4ed46869 | 6674 | |
df7492f9 | 6675 | unbind_to (count, Qnil); |
b73bfc1c KH |
6676 | return coding->result; |
6677 | } | |
52d41803 | 6678 | |
4ed46869 | 6679 | int |
df7492f9 | 6680 | encode_coding_gap (coding, chars, bytes) |
4ed46869 | 6681 | struct coding_system *coding; |
df7492f9 | 6682 | EMACS_INT chars, bytes; |
4ed46869 | 6683 | { |
df7492f9 | 6684 | int count = specpdl_ptr - specpdl; |
4ed46869 | 6685 | |
24a73b0a | 6686 | code_conversion_save (0, 0); |
4ed46869 | 6687 | |
24a73b0a | 6688 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6689 | coding->src_chars = chars; |
6690 | coding->src_bytes = bytes; | |
6691 | coding->src_pos = -chars; | |
6692 | coding->src_pos_byte = -bytes; | |
6693 | coding->src_multibyte = chars < bytes; | |
6694 | coding->dst_object = coding->src_object; | |
6695 | coding->dst_pos = PT; | |
6696 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 6697 | |
df7492f9 | 6698 | encode_coding (coding); |
b73bfc1c | 6699 | |
df7492f9 KH |
6700 | unbind_to (count, Qnil); |
6701 | return coding->result; | |
6702 | } | |
4ed46869 | 6703 | |
d46c5b12 | 6704 | |
df7492f9 KH |
6705 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
6706 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 6707 | |
df7492f9 | 6708 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 6709 | |
df7492f9 KH |
6710 | If it is a buffer, the text is at point of the buffer. FROM and TO |
6711 | are positions in the buffer. | |
b73bfc1c | 6712 | |
df7492f9 KH |
6713 | If it is a string, the text is at the beginning of the string. |
6714 | FROM and TO are indices to the string. | |
4ed46869 | 6715 | |
df7492f9 KH |
6716 | If it is nil, the text is at coding->source. FROM and TO are |
6717 | indices to coding->source. | |
bb10be8b | 6718 | |
df7492f9 | 6719 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 6720 | |
df7492f9 KH |
6721 | If it is a buffer, the decoded text is inserted at point of the |
6722 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
6723 | is deleted. | |
4ed46869 | 6724 | |
df7492f9 KH |
6725 | If it is Qt, a string is made from the decoded text, and |
6726 | set in CODING->dst_object. | |
d46c5b12 | 6727 | |
df7492f9 | 6728 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 6729 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
6730 | CODING->destination by xmalloc. If the decoded text is longer than |
6731 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
6732 | */ | |
d46c5b12 | 6733 | |
df7492f9 KH |
6734 | void |
6735 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6736 | dst_object) | |
d46c5b12 | 6737 | struct coding_system *coding; |
df7492f9 KH |
6738 | Lisp_Object src_object; |
6739 | EMACS_INT from, from_byte, to, to_byte; | |
6740 | Lisp_Object dst_object; | |
d46c5b12 | 6741 | { |
df7492f9 KH |
6742 | int count = specpdl_ptr - specpdl; |
6743 | unsigned char *destination; | |
6744 | EMACS_INT dst_bytes; | |
6745 | EMACS_INT chars = to - from; | |
6746 | EMACS_INT bytes = to_byte - from_byte; | |
6747 | Lisp_Object attrs; | |
4776e638 KH |
6748 | Lisp_Object buffer; |
6749 | int saved_pt = -1, saved_pt_byte; | |
d46c5b12 | 6750 | |
4776e638 | 6751 | buffer = Fcurrent_buffer (); |
93dec019 | 6752 | |
df7492f9 | 6753 | if (NILP (dst_object)) |
d46c5b12 | 6754 | { |
df7492f9 KH |
6755 | destination = coding->destination; |
6756 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 6757 | } |
93dec019 | 6758 | |
df7492f9 KH |
6759 | coding->src_object = src_object; |
6760 | coding->src_chars = chars; | |
6761 | coding->src_bytes = bytes; | |
6762 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 6763 | |
df7492f9 | 6764 | if (STRINGP (src_object)) |
d46c5b12 | 6765 | { |
df7492f9 KH |
6766 | coding->src_pos = from; |
6767 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6768 | } |
df7492f9 | 6769 | else if (BUFFERP (src_object)) |
88993dfd | 6770 | { |
df7492f9 KH |
6771 | set_buffer_internal (XBUFFER (src_object)); |
6772 | if (from != GPT) | |
6773 | move_gap_both (from, from_byte); | |
6774 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 6775 | { |
4776e638 | 6776 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6777 | TEMP_SET_PT_BOTH (from, from_byte); |
6778 | del_range_both (from, from_byte, to, to_byte, 1); | |
6779 | coding->src_pos = -chars; | |
6780 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 6781 | } |
df7492f9 | 6782 | else |
fb88bf2d | 6783 | { |
df7492f9 KH |
6784 | coding->src_pos = from; |
6785 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 6786 | } |
88993dfd KH |
6787 | } |
6788 | ||
df7492f9 KH |
6789 | if (CODING_REQUIRE_DETECTION (coding)) |
6790 | detect_coding (coding); | |
6791 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 6792 | |
2cb26057 KH |
6793 | if (EQ (dst_object, Qt) |
6794 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
6795 | && NILP (dst_object))) | |
b73bfc1c | 6796 | { |
24a73b0a | 6797 | coding->dst_object = code_conversion_save (1, 1); |
df7492f9 KH |
6798 | coding->dst_pos = BEG; |
6799 | coding->dst_pos_byte = BEG_BYTE; | |
6800 | coding->dst_multibyte = 1; | |
b73bfc1c | 6801 | } |
df7492f9 | 6802 | else if (BUFFERP (dst_object)) |
d46c5b12 | 6803 | { |
24a73b0a | 6804 | code_conversion_save (0, 0); |
df7492f9 KH |
6805 | coding->dst_object = dst_object; |
6806 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6807 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6808 | coding->dst_multibyte | |
6809 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
6810 | } |
6811 | else | |
6812 | { | |
24a73b0a | 6813 | code_conversion_save (0, 0); |
df7492f9 KH |
6814 | coding->dst_object = Qnil; |
6815 | coding->dst_multibyte = 1; | |
d46c5b12 KH |
6816 | } |
6817 | ||
df7492f9 | 6818 | decode_coding (coding); |
fa46990e | 6819 | |
df7492f9 KH |
6820 | if (BUFFERP (coding->dst_object)) |
6821 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 6822 | |
df7492f9 | 6823 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 6824 | { |
df7492f9 KH |
6825 | struct gcpro gcpro1, gcpro2; |
6826 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; | |
2b4f9037 | 6827 | Lisp_Object val; |
d46c5b12 | 6828 | |
c0cc7f7f | 6829 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
df7492f9 | 6830 | GCPRO2 (coding->src_object, coding->dst_object); |
d4850d67 KH |
6831 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
6832 | make_number (coding->produced_char)); | |
df7492f9 KH |
6833 | UNGCPRO; |
6834 | CHECK_NATNUM (val); | |
6835 | coding->produced_char += Z - prev_Z; | |
6836 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 6837 | } |
de79a6a5 | 6838 | |
df7492f9 | 6839 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 6840 | { |
df7492f9 KH |
6841 | coding->dst_object = Fbuffer_string (); |
6842 | } | |
6843 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
6844 | { | |
6845 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6846 | if (dst_bytes < coding->produced) | |
6847 | { | |
6848 | destination | |
6849 | = (unsigned char *) xrealloc (destination, coding->produced); | |
6850 | if (! destination) | |
6851 | { | |
065e3595 KH |
6852 | record_conversion_result (coding, |
6853 | CODING_RESULT_INSUFFICIENT_DST); | |
df7492f9 KH |
6854 | unbind_to (count, Qnil); |
6855 | return; | |
6856 | } | |
6857 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
6858 | move_gap_both (BEGV, BEGV_BYTE); | |
6859 | bcopy (BEGV_ADDR, destination, coding->produced); | |
6860 | coding->destination = destination; | |
d46c5b12 | 6861 | } |
ec6d2bb8 | 6862 | } |
b73bfc1c | 6863 | |
4776e638 KH |
6864 | if (saved_pt >= 0) |
6865 | { | |
6866 | /* This is the case of: | |
6867 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
6868 | As we have moved PT while replacing the original buffer | |
6869 | contents, we must recover it now. */ | |
6870 | set_buffer_internal (XBUFFER (src_object)); | |
6871 | if (saved_pt < from) | |
6872 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
6873 | else if (saved_pt < from + chars) | |
6874 | TEMP_SET_PT_BOTH (from, from_byte); | |
6875 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
6876 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
6877 | saved_pt_byte + (coding->produced - bytes)); | |
6878 | else | |
6879 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
6880 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 6881 | } |
4776e638 | 6882 | |
065e3595 | 6883 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
6884 | } |
6885 | ||
d46c5b12 | 6886 | |
df7492f9 KH |
6887 | void |
6888 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6889 | dst_object) | |
d46c5b12 | 6890 | struct coding_system *coding; |
df7492f9 KH |
6891 | Lisp_Object src_object; |
6892 | EMACS_INT from, from_byte, to, to_byte; | |
6893 | Lisp_Object dst_object; | |
d46c5b12 | 6894 | { |
b73bfc1c | 6895 | int count = specpdl_ptr - specpdl; |
df7492f9 KH |
6896 | EMACS_INT chars = to - from; |
6897 | EMACS_INT bytes = to_byte - from_byte; | |
6898 | Lisp_Object attrs; | |
4776e638 KH |
6899 | Lisp_Object buffer; |
6900 | int saved_pt = -1, saved_pt_byte; | |
c02d943b | 6901 | int kill_src_buffer = 0; |
df7492f9 | 6902 | |
4776e638 | 6903 | buffer = Fcurrent_buffer (); |
df7492f9 KH |
6904 | |
6905 | coding->src_object = src_object; | |
6906 | coding->src_chars = chars; | |
6907 | coding->src_bytes = bytes; | |
6908 | coding->src_multibyte = chars < bytes; | |
6909 | ||
6910 | attrs = CODING_ID_ATTRS (coding->id); | |
6911 | ||
6912 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
6bac5b12 | 6913 | { |
24a73b0a | 6914 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
6915 | set_buffer_internal (XBUFFER (coding->src_object)); |
6916 | if (STRINGP (src_object)) | |
6917 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
6918 | else if (BUFFERP (src_object)) | |
6919 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
6920 | else | |
6921 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 6922 | |
df7492f9 KH |
6923 | if (EQ (src_object, dst_object)) |
6924 | { | |
6925 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 6926 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
6927 | del_range_both (from, from_byte, to, to_byte, 1); |
6928 | set_buffer_internal (XBUFFER (coding->src_object)); | |
6929 | } | |
6930 | ||
d4850d67 KH |
6931 | { |
6932 | Lisp_Object args[3]; | |
6933 | ||
6934 | args[0] = CODING_ATTR_PRE_WRITE (attrs); | |
6935 | args[1] = make_number (BEG); | |
6936 | args[2] = make_number (Z); | |
6937 | safe_call (3, args); | |
6938 | } | |
c02d943b KH |
6939 | if (XBUFFER (coding->src_object) != current_buffer) |
6940 | kill_src_buffer = 1; | |
ac87bbef | 6941 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
6942 | if (BEG != GPT) |
6943 | move_gap_both (BEG, BEG_BYTE); | |
6944 | coding->src_chars = Z - BEG; | |
6945 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
6946 | coding->src_pos = BEG; | |
6947 | coding->src_pos_byte = BEG_BYTE; | |
6948 | coding->src_multibyte = Z < Z_BYTE; | |
6949 | } | |
6950 | else if (STRINGP (src_object)) | |
d46c5b12 | 6951 | { |
24a73b0a | 6952 | code_conversion_save (0, 0); |
df7492f9 KH |
6953 | coding->src_pos = from; |
6954 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 6955 | } |
df7492f9 | 6956 | else if (BUFFERP (src_object)) |
b73bfc1c | 6957 | { |
24a73b0a | 6958 | code_conversion_save (0, 0); |
df7492f9 | 6959 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 6960 | if (EQ (src_object, dst_object)) |
d46c5b12 | 6961 | { |
4776e638 | 6962 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
6963 | coding->src_object = del_range_1 (from, to, 1, 1); |
6964 | coding->src_pos = 0; | |
6965 | coding->src_pos_byte = 0; | |
d46c5b12 | 6966 | } |
df7492f9 | 6967 | else |
d46c5b12 | 6968 | { |
ff0dacd7 KH |
6969 | if (from < GPT && to >= GPT) |
6970 | move_gap_both (from, from_byte); | |
df7492f9 KH |
6971 | coding->src_pos = from; |
6972 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 6973 | } |
d46c5b12 | 6974 | } |
4776e638 | 6975 | else |
24a73b0a | 6976 | code_conversion_save (0, 0); |
d46c5b12 | 6977 | |
df7492f9 | 6978 | if (BUFFERP (dst_object)) |
88993dfd | 6979 | { |
df7492f9 | 6980 | coding->dst_object = dst_object; |
28f67a95 KH |
6981 | if (EQ (src_object, dst_object)) |
6982 | { | |
6983 | coding->dst_pos = from; | |
6984 | coding->dst_pos_byte = from_byte; | |
6985 | } | |
6986 | else | |
6987 | { | |
6988 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6989 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6990 | } | |
df7492f9 KH |
6991 | coding->dst_multibyte |
6992 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 6993 | } |
df7492f9 | 6994 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 6995 | { |
df7492f9 | 6996 | coding->dst_object = Qnil; |
df7492f9 | 6997 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
6998 | if (coding->dst_bytes == 0) |
6999 | coding->dst_bytes = 1; | |
7000 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 7001 | coding->dst_multibyte = 0; |
d46c5b12 KH |
7002 | } |
7003 | else | |
7004 | { | |
df7492f9 KH |
7005 | coding->dst_object = Qnil; |
7006 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
7007 | } |
7008 | ||
df7492f9 | 7009 | encode_coding (coding); |
d46c5b12 | 7010 | |
df7492f9 | 7011 | if (EQ (dst_object, Qt)) |
d46c5b12 | 7012 | { |
df7492f9 KH |
7013 | if (BUFFERP (coding->dst_object)) |
7014 | coding->dst_object = Fbuffer_string (); | |
7015 | else | |
d46c5b12 | 7016 | { |
df7492f9 KH |
7017 | coding->dst_object |
7018 | = make_unibyte_string ((char *) coding->destination, | |
7019 | coding->produced); | |
7020 | xfree (coding->destination); | |
d46c5b12 | 7021 | } |
4ed46869 | 7022 | } |
d46c5b12 | 7023 | |
4776e638 KH |
7024 | if (saved_pt >= 0) |
7025 | { | |
7026 | /* This is the case of: | |
7027 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7028 | As we have moved PT while replacing the original buffer | |
7029 | contents, we must recover it now. */ | |
7030 | set_buffer_internal (XBUFFER (src_object)); | |
7031 | if (saved_pt < from) | |
7032 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7033 | else if (saved_pt < from + chars) | |
7034 | TEMP_SET_PT_BOTH (from, from_byte); | |
7035 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
7036 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
7037 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 7038 | else |
4776e638 KH |
7039 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
7040 | saved_pt_byte + (coding->produced - bytes)); | |
7041 | } | |
7042 | ||
c02d943b KH |
7043 | if (kill_src_buffer) |
7044 | Fkill_buffer (coding->src_object); | |
df7492f9 | 7045 | unbind_to (count, Qnil); |
b73bfc1c KH |
7046 | } |
7047 | ||
df7492f9 | 7048 | |
b73bfc1c | 7049 | Lisp_Object |
df7492f9 | 7050 | preferred_coding_system () |
b73bfc1c | 7051 | { |
df7492f9 | 7052 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 7053 | |
df7492f9 | 7054 | return CODING_ID_NAME (id); |
4ed46869 KH |
7055 | } |
7056 | ||
7057 | \f | |
7058 | #ifdef emacs | |
1397dc18 | 7059 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 7060 | |
4ed46869 | 7061 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 7062 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 7063 | See the documentation of `define-coding-system' for information |
48b0f3ae PJ |
7064 | about coding-system objects. */) |
7065 | (obj) | |
4ed46869 KH |
7066 | Lisp_Object obj; |
7067 | { | |
44e8490d KH |
7068 | if (NILP (obj) |
7069 | || CODING_SYSTEM_ID (obj) >= 0) | |
7070 | return Qt; | |
7071 | if (! SYMBOLP (obj) | |
7072 | || NILP (Fget (obj, Qcoding_system_define_form))) | |
7073 | return Qnil; | |
7074 | return Qt; | |
4ed46869 KH |
7075 | } |
7076 | ||
9d991de8 RS |
7077 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
7078 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
7079 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
7080 | (prompt) | |
4ed46869 KH |
7081 | Lisp_Object prompt; |
7082 | { | |
e0e989f6 | 7083 | Lisp_Object val; |
9d991de8 RS |
7084 | do |
7085 | { | |
4608c386 KH |
7086 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
7087 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 7088 | } |
8f924df7 | 7089 | while (SCHARS (val) == 0); |
e0e989f6 | 7090 | return (Fintern (val, Qnil)); |
4ed46869 KH |
7091 | } |
7092 | ||
9b787f3e | 7093 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae PJ |
7094 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
7095 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */) | |
7096 | (prompt, default_coding_system) | |
9b787f3e | 7097 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 7098 | { |
f44d27ce | 7099 | Lisp_Object val; |
9b787f3e | 7100 | if (SYMBOLP (default_coding_system)) |
a3181084 | 7101 | XSETSTRING (default_coding_system, XPNTR (SYMBOL_NAME (default_coding_system))); |
4608c386 | 7102 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
7103 | Qt, Qnil, Qcoding_system_history, |
7104 | default_coding_system, Qnil); | |
8f924df7 | 7105 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
7106 | } |
7107 | ||
7108 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
7109 | 1, 1, 0, | |
48b0f3ae | 7110 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
7111 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
7112 | It is valid if it is nil or a symbol defined as a coding system by the | |
7113 | function `define-coding-system'. */) | |
df7492f9 | 7114 | (coding_system) |
4ed46869 KH |
7115 | Lisp_Object coding_system; |
7116 | { | |
44e8490d KH |
7117 | Lisp_Object define_form; |
7118 | ||
7119 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
7120 | if (! NILP (define_form)) | |
7121 | { | |
7122 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
7123 | safe_eval (define_form); | |
7124 | } | |
4ed46869 KH |
7125 | if (!NILP (Fcoding_system_p (coding_system))) |
7126 | return coding_system; | |
7127 | while (1) | |
02ba4723 | 7128 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
4ed46869 | 7129 | } |
df7492f9 | 7130 | |
3a73fa5d | 7131 | \f |
89528eb3 KH |
7132 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
7133 | HIGHEST is nonzero, return the coding system of the highest | |
7134 | priority among the detected coding systems. Otherwize return a | |
7135 | list of detected coding systems sorted by their priorities. If | |
7136 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
7137 | multibyte form but contains only ASCII and eight-bit chars. | |
7138 | Otherwise, the bytes are raw bytes. | |
7139 | ||
7140 | CODING-SYSTEM controls the detection as below: | |
7141 | ||
7142 | If it is nil, detect both text-format and eol-format. If the | |
7143 | text-format part of CODING-SYSTEM is already specified | |
7144 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
7145 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
7146 | detect only text-format. */ | |
7147 | ||
d46c5b12 | 7148 | Lisp_Object |
24a73b0a KH |
7149 | detect_coding_system (src, src_chars, src_bytes, highest, multibytep, |
7150 | coding_system) | |
8f924df7 | 7151 | const unsigned char *src; |
24a73b0a | 7152 | int src_chars, src_bytes, highest; |
0a28aafb | 7153 | int multibytep; |
df7492f9 | 7154 | Lisp_Object coding_system; |
4ed46869 | 7155 | { |
8f924df7 | 7156 | const unsigned char *src_end = src + src_bytes; |
df7492f9 KH |
7157 | Lisp_Object attrs, eol_type; |
7158 | Lisp_Object val; | |
7159 | struct coding_system coding; | |
89528eb3 | 7160 | int id; |
ff0dacd7 | 7161 | struct coding_detection_info detect_info; |
24a73b0a | 7162 | enum coding_category base_category; |
b73bfc1c | 7163 | |
df7492f9 KH |
7164 | if (NILP (coding_system)) |
7165 | coding_system = Qundecided; | |
7166 | setup_coding_system (coding_system, &coding); | |
7167 | attrs = CODING_ID_ATTRS (coding.id); | |
7168 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 7169 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 7170 | |
df7492f9 | 7171 | coding.source = src; |
24a73b0a | 7172 | coding.src_chars = src_chars; |
df7492f9 KH |
7173 | coding.src_bytes = src_bytes; |
7174 | coding.src_multibyte = multibytep; | |
7175 | coding.consumed = 0; | |
89528eb3 | 7176 | coding.mode |= CODING_MODE_LAST_BLOCK; |
d46c5b12 | 7177 | |
ff0dacd7 | 7178 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 7179 | |
89528eb3 | 7180 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
7181 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
7182 | if (base_category == coding_category_undecided) | |
4ed46869 | 7183 | { |
ff0dacd7 KH |
7184 | enum coding_category category; |
7185 | struct coding_system *this; | |
7186 | int c, i; | |
88993dfd | 7187 | |
24a73b0a KH |
7188 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
7189 | for (i = 0; src < src_end; i++, src++) | |
4ed46869 | 7190 | { |
df7492f9 | 7191 | c = *src; |
6cb21a4f | 7192 | if (c & 0x80) |
d46c5b12 | 7193 | break; |
6cb21a4f KH |
7194 | if (c < 0x20 |
7195 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
7196 | && inhibit_iso_escape_detection) | |
7197 | { | |
7198 | coding.head_ascii = src - coding.source; | |
7199 | if (detect_coding_iso_2022 (&coding, &detect_info)) | |
7200 | { | |
7201 | /* We have scanned the whole data. */ | |
7202 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
7203 | /* We didn't find an 8-bit code. */ | |
7204 | src = src_end; | |
7205 | break; | |
7206 | } | |
7207 | } | |
4ed46869 | 7208 | } |
df7492f9 | 7209 | coding.head_ascii = src - coding.source; |
88993dfd | 7210 | |
6cb21a4f KH |
7211 | if (src < src_end |
7212 | || detect_info.found) | |
7213 | { | |
7214 | if (src == src_end) | |
7215 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
7216 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 7217 | { |
6cb21a4f KH |
7218 | category = coding_priorities[i]; |
7219 | if (detect_info.found & (1 << category)) | |
ff0dacd7 KH |
7220 | break; |
7221 | } | |
6cb21a4f KH |
7222 | else |
7223 | for (i = 0; i < coding_category_raw_text; i++) | |
df7492f9 | 7224 | { |
6cb21a4f KH |
7225 | category = coding_priorities[i]; |
7226 | this = coding_categories + category; | |
7227 | ||
7228 | if (this->id < 0) | |
24a73b0a | 7229 | { |
6cb21a4f KH |
7230 | /* No coding system of this category is defined. */ |
7231 | detect_info.rejected |= (1 << category); | |
7232 | } | |
7233 | else if (category >= coding_category_raw_text) | |
7234 | continue; | |
7235 | else if (detect_info.checked & (1 << category)) | |
7236 | { | |
7237 | if (highest | |
7238 | && (detect_info.found & (1 << category))) | |
7239 | break; | |
7240 | } | |
7241 | else | |
7242 | { | |
7243 | if ((*(this->detector)) (&coding, &detect_info) | |
7244 | && highest | |
7245 | && (detect_info.found & (1 << category))) | |
24a73b0a | 7246 | { |
6cb21a4f KH |
7247 | if (category == coding_category_utf_16_auto) |
7248 | { | |
7249 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7250 | category = coding_category_utf_16_le; | |
7251 | else | |
7252 | category = coding_category_utf_16_be; | |
7253 | } | |
7254 | break; | |
24a73b0a | 7255 | } |
24a73b0a | 7256 | } |
df7492f9 | 7257 | } |
6cb21a4f | 7258 | } |
ec6d2bb8 | 7259 | |
ff0dacd7 | 7260 | if (detect_info.rejected == CATEGORY_MASK_ANY) |
ec6d2bb8 | 7261 | { |
ff0dacd7 | 7262 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
89528eb3 KH |
7263 | id = coding_categories[coding_category_raw_text].id; |
7264 | val = Fcons (make_number (id), Qnil); | |
7265 | } | |
ff0dacd7 | 7266 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 7267 | { |
ff0dacd7 | 7268 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
7269 | id = coding_categories[coding_category_undecided].id; |
7270 | val = Fcons (make_number (id), Qnil); | |
7271 | } | |
7272 | else if (highest) | |
7273 | { | |
ff0dacd7 | 7274 | if (detect_info.found) |
ec6d2bb8 | 7275 | { |
ff0dacd7 KH |
7276 | detect_info.found = 1 << category; |
7277 | val = Fcons (make_number (this->id), Qnil); | |
7278 | } | |
7279 | else | |
7280 | for (i = 0; i < coding_category_raw_text; i++) | |
7281 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
7282 | { | |
7283 | detect_info.found = 1 << coding_priorities[i]; | |
7284 | id = coding_categories[coding_priorities[i]].id; | |
7285 | val = Fcons (make_number (id), Qnil); | |
7286 | break; | |
7287 | } | |
7288 | } | |
89528eb3 KH |
7289 | else |
7290 | { | |
ff0dacd7 KH |
7291 | int mask = detect_info.rejected | detect_info.found; |
7292 | int found = 0; | |
89528eb3 | 7293 | val = Qnil; |
ec6d2bb8 | 7294 | |
89528eb3 | 7295 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
7296 | { |
7297 | category = coding_priorities[i]; | |
7298 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 7299 | { |
ff0dacd7 KH |
7300 | found |= 1 << category; |
7301 | id = coding_categories[category].id; | |
7302 | val = Fcons (make_number (id), val); | |
7303 | } | |
7304 | } | |
7305 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
7306 | { | |
7307 | category = coding_priorities[i]; | |
7308 | if (detect_info.found & (1 << category)) | |
7309 | { | |
7310 | id = coding_categories[category].id; | |
7311 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 7312 | } |
ec6d2bb8 | 7313 | } |
ff0dacd7 | 7314 | detect_info.found |= found; |
ec6d2bb8 | 7315 | } |
ec6d2bb8 | 7316 | } |
24a73b0a KH |
7317 | else if (base_category == coding_category_utf_16_auto) |
7318 | { | |
7319 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
7320 | { | |
24a73b0a KH |
7321 | struct coding_system *this; |
7322 | ||
7323 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
7324 | this = coding_categories + coding_category_utf_16_le; | |
7325 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
7326 | this = coding_categories + coding_category_utf_16_be; | |
7327 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
7328 | this = coding_categories + coding_category_utf_16_be_nosig; | |
7329 | else | |
7330 | this = coding_categories + coding_category_utf_16_le_nosig; | |
7331 | val = Fcons (make_number (this->id), Qnil); | |
7332 | } | |
7333 | } | |
df7492f9 KH |
7334 | else |
7335 | { | |
ff0dacd7 | 7336 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 7337 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 7338 | } |
df7492f9 | 7339 | |
89528eb3 | 7340 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 7341 | { |
89528eb3 | 7342 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol; |
df7492f9 KH |
7343 | Lisp_Object tail; |
7344 | ||
89528eb3 KH |
7345 | if (VECTORP (eol_type)) |
7346 | { | |
ff0dacd7 | 7347 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
89528eb3 KH |
7348 | normal_eol = detect_eol (coding.source, src_bytes, |
7349 | coding_category_raw_text); | |
ff0dacd7 KH |
7350 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
7351 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
7352 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
7353 | coding_category_utf_16_be); | |
ff0dacd7 KH |
7354 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
7355 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
7356 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
7357 | coding_category_utf_16_le); | |
7358 | } | |
7359 | else | |
7360 | { | |
7361 | if (EQ (eol_type, Qunix)) | |
7362 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
7363 | else if (EQ (eol_type, Qdos)) | |
7364 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
7365 | else | |
7366 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
7367 | } | |
7368 | ||
df7492f9 KH |
7369 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
7370 | { | |
89528eb3 | 7371 | enum coding_category category; |
df7492f9 | 7372 | int this_eol; |
89528eb3 KH |
7373 | |
7374 | id = XINT (XCAR (tail)); | |
7375 | attrs = CODING_ID_ATTRS (id); | |
7376 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
7377 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
7378 | if (VECTORP (eol_type)) |
7379 | { | |
89528eb3 KH |
7380 | if (category == coding_category_utf_16_be |
7381 | || category == coding_category_utf_16_be_nosig) | |
7382 | this_eol = utf_16_be_eol; | |
7383 | else if (category == coding_category_utf_16_le | |
7384 | || category == coding_category_utf_16_le_nosig) | |
7385 | this_eol = utf_16_le_eol; | |
df7492f9 | 7386 | else |
89528eb3 KH |
7387 | this_eol = normal_eol; |
7388 | ||
df7492f9 KH |
7389 | if (this_eol == EOL_SEEN_LF) |
7390 | XSETCAR (tail, AREF (eol_type, 0)); | |
7391 | else if (this_eol == EOL_SEEN_CRLF) | |
7392 | XSETCAR (tail, AREF (eol_type, 1)); | |
7393 | else if (this_eol == EOL_SEEN_CR) | |
7394 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
7395 | else |
7396 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 7397 | } |
89528eb3 KH |
7398 | else |
7399 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
7400 | } |
7401 | } | |
ec6d2bb8 | 7402 | |
03699b14 | 7403 | return (highest ? XCAR (val) : val); |
ec6d2bb8 KH |
7404 | } |
7405 | ||
ec6d2bb8 | 7406 | |
d46c5b12 KH |
7407 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
7408 | 2, 3, 0, | |
48b0f3ae PJ |
7409 | doc: /* Detect coding system of the text in the region between START and END. |
7410 | Return a list of possible coding systems ordered by priority. | |
ec6d2bb8 | 7411 | |
48b0f3ae PJ |
7412 | If only ASCII characters are found, it returns a list of single element |
7413 | `undecided' or its subsidiary coding system according to a detected | |
7414 | end-of-line format. | |
ec6d2bb8 | 7415 | |
48b0f3ae PJ |
7416 | If optional argument HIGHEST is non-nil, return the coding system of |
7417 | highest priority. */) | |
7418 | (start, end, highest) | |
d46c5b12 KH |
7419 | Lisp_Object start, end, highest; |
7420 | { | |
7421 | int from, to; | |
7422 | int from_byte, to_byte; | |
ec6d2bb8 | 7423 | |
b7826503 PJ |
7424 | CHECK_NUMBER_COERCE_MARKER (start); |
7425 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 7426 | |
d46c5b12 KH |
7427 | validate_region (&start, &end); |
7428 | from = XINT (start), to = XINT (end); | |
7429 | from_byte = CHAR_TO_BYTE (from); | |
7430 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 7431 | |
d46c5b12 KH |
7432 | if (from < GPT && to >= GPT) |
7433 | move_gap_both (to, to_byte); | |
c210f766 | 7434 | |
d46c5b12 | 7435 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 7436 | to - from, to_byte - from_byte, |
0a28aafb KH |
7437 | !NILP (highest), |
7438 | !NILP (current_buffer | |
df7492f9 KH |
7439 | ->enable_multibyte_characters), |
7440 | Qnil); | |
ec6d2bb8 KH |
7441 | } |
7442 | ||
d46c5b12 KH |
7443 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
7444 | 1, 2, 0, | |
48b0f3ae PJ |
7445 | doc: /* Detect coding system of the text in STRING. |
7446 | Return a list of possible coding systems ordered by priority. | |
fb88bf2d | 7447 | |
48b0f3ae PJ |
7448 | If only ASCII characters are found, it returns a list of single element |
7449 | `undecided' or its subsidiary coding system according to a detected | |
7450 | end-of-line format. | |
d46c5b12 | 7451 | |
48b0f3ae PJ |
7452 | If optional argument HIGHEST is non-nil, return the coding system of |
7453 | highest priority. */) | |
7454 | (string, highest) | |
d46c5b12 KH |
7455 | Lisp_Object string, highest; |
7456 | { | |
b7826503 | 7457 | CHECK_STRING (string); |
b73bfc1c | 7458 | |
24a73b0a KH |
7459 | return detect_coding_system (SDATA (string), |
7460 | SCHARS (string), SBYTES (string), | |
8f924df7 | 7461 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 7462 | Qnil); |
4ed46869 | 7463 | } |
4ed46869 | 7464 | |
b73bfc1c | 7465 | |
df7492f9 KH |
7466 | static INLINE int |
7467 | char_encodable_p (c, attrs) | |
7468 | int c; | |
7469 | Lisp_Object attrs; | |
05e6f5dc | 7470 | { |
df7492f9 | 7471 | Lisp_Object tail; |
df7492f9 | 7472 | struct charset *charset; |
7d64c6ad | 7473 | Lisp_Object translation_table; |
d46c5b12 | 7474 | |
7d64c6ad | 7475 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 7476 | if (! NILP (translation_table)) |
7d64c6ad | 7477 | c = translate_char (translation_table, c); |
df7492f9 KH |
7478 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
7479 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 7480 | { |
df7492f9 KH |
7481 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
7482 | if (CHAR_CHARSET_P (c, charset)) | |
7483 | break; | |
e133c8fa | 7484 | } |
df7492f9 | 7485 | return (! NILP (tail)); |
05e6f5dc | 7486 | } |
83fa074f | 7487 | |
fb88bf2d | 7488 | |
df7492f9 KH |
7489 | /* Return a list of coding systems that safely encode the text between |
7490 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
7491 | systems not to check. The returned list doesn't contain any such | |
48468dac | 7492 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 7493 | unibyte, return t. */ |
e077cc80 | 7494 | |
df7492f9 KH |
7495 | DEFUN ("find-coding-systems-region-internal", |
7496 | Ffind_coding_systems_region_internal, | |
7497 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
7498 | doc: /* Internal use only. */) | |
7499 | (start, end, exclude) | |
7500 | Lisp_Object start, end, exclude; | |
7501 | { | |
7502 | Lisp_Object coding_attrs_list, safe_codings; | |
7503 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 7504 | const unsigned char *p, *pbeg, *pend; |
df7492f9 KH |
7505 | int c; |
7506 | Lisp_Object tail, elt; | |
d46c5b12 | 7507 | |
df7492f9 KH |
7508 | if (STRINGP (start)) |
7509 | { | |
7510 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 7511 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
7512 | return Qt; |
7513 | start_byte = 0; | |
8f924df7 | 7514 | end_byte = SBYTES (start); |
df7492f9 KH |
7515 | } |
7516 | else | |
d46c5b12 | 7517 | { |
df7492f9 KH |
7518 | CHECK_NUMBER_COERCE_MARKER (start); |
7519 | CHECK_NUMBER_COERCE_MARKER (end); | |
7520 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
7521 | args_out_of_range (start, end); | |
7522 | if (NILP (current_buffer->enable_multibyte_characters)) | |
7523 | return Qt; | |
7524 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7525 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7526 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
7527 | return Qt; | |
d46c5b12 | 7528 | |
e1c23804 | 7529 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 7530 | { |
e1c23804 DL |
7531 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7532 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7533 | else |
e1c23804 | 7534 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
7535 | } |
7536 | } | |
7537 | ||
df7492f9 KH |
7538 | coding_attrs_list = Qnil; |
7539 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
7540 | if (NILP (exclude) | |
7541 | || NILP (Fmemq (XCAR (tail), exclude))) | |
7542 | { | |
7543 | Lisp_Object attrs; | |
d46c5b12 | 7544 | |
df7492f9 KH |
7545 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
7546 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
7547 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
7548 | { |
7549 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 7550 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
7551 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
7552 | } | |
df7492f9 | 7553 | } |
d46c5b12 | 7554 | |
df7492f9 | 7555 | if (STRINGP (start)) |
8f924df7 | 7556 | p = pbeg = SDATA (start); |
df7492f9 KH |
7557 | else |
7558 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
7559 | pend = p + (end_byte - start_byte); | |
b843d1ae | 7560 | |
df7492f9 KH |
7561 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
7562 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 7563 | |
05e6f5dc | 7564 | while (p < pend) |
72d1a715 | 7565 | { |
df7492f9 KH |
7566 | if (ASCII_BYTE_P (*p)) |
7567 | p++; | |
72d1a715 RS |
7568 | else |
7569 | { | |
df7492f9 | 7570 | c = STRING_CHAR_ADVANCE (p); |
12410ef1 | 7571 | |
df7492f9 KH |
7572 | charset_map_loaded = 0; |
7573 | for (tail = coding_attrs_list; CONSP (tail);) | |
7574 | { | |
7575 | elt = XCAR (tail); | |
7576 | if (NILP (elt)) | |
7577 | tail = XCDR (tail); | |
7578 | else if (char_encodable_p (c, elt)) | |
7579 | tail = XCDR (tail); | |
7580 | else if (CONSP (XCDR (tail))) | |
7581 | { | |
7582 | XSETCAR (tail, XCAR (XCDR (tail))); | |
7583 | XSETCDR (tail, XCDR (XCDR (tail))); | |
7584 | } | |
7585 | else | |
7586 | { | |
7587 | XSETCAR (tail, Qnil); | |
7588 | tail = XCDR (tail); | |
7589 | } | |
7590 | } | |
7591 | if (charset_map_loaded) | |
7592 | { | |
7593 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 7594 | |
df7492f9 | 7595 | if (STRINGP (start)) |
8f924df7 | 7596 | pbeg = SDATA (start); |
df7492f9 KH |
7597 | else |
7598 | pbeg = BYTE_POS_ADDR (start_byte); | |
7599 | p = pbeg + p_offset; | |
7600 | pend = pbeg + pend_offset; | |
7601 | } | |
7602 | } | |
ec6d2bb8 | 7603 | } |
fb88bf2d | 7604 | |
988b3759 | 7605 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
7606 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
7607 | if (! NILP (XCAR (tail))) | |
7608 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 7609 | |
05e6f5dc KH |
7610 | return safe_codings; |
7611 | } | |
4956c225 | 7612 | |
d46c5b12 | 7613 | |
8f924df7 KH |
7614 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
7615 | Sunencodable_char_position, 3, 5, 0, | |
7616 | doc: /* | |
7617 | Return position of first un-encodable character in a region. | |
7618 | START and END specfiy the region and CODING-SYSTEM specifies the | |
7619 | encoding to check. Return nil if CODING-SYSTEM does encode the region. | |
d46c5b12 | 7620 | |
8f924df7 KH |
7621 | If optional 4th argument COUNT is non-nil, it specifies at most how |
7622 | many un-encodable characters to search. In this case, the value is a | |
7623 | list of positions. | |
d46c5b12 | 7624 | |
8f924df7 KH |
7625 | If optional 5th argument STRING is non-nil, it is a string to search |
7626 | for un-encodable characters. In that case, START and END are indexes | |
7627 | to the string. */) | |
7628 | (start, end, coding_system, count, string) | |
7629 | Lisp_Object start, end, coding_system, count, string; | |
7630 | { | |
7631 | int n; | |
7632 | struct coding_system coding; | |
7d64c6ad | 7633 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
7634 | Lisp_Object positions; |
7635 | int from, to; | |
7636 | const unsigned char *p, *stop, *pend; | |
7637 | int ascii_compatible; | |
fb88bf2d | 7638 | |
8f924df7 KH |
7639 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
7640 | attrs = CODING_ID_ATTRS (coding.id); | |
7641 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
7642 | return Qnil; | |
7643 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
7644 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 7645 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 7646 | |
8f924df7 KH |
7647 | if (NILP (string)) |
7648 | { | |
7649 | validate_region (&start, &end); | |
7650 | from = XINT (start); | |
7651 | to = XINT (end); | |
7652 | if (NILP (current_buffer->enable_multibyte_characters) | |
7653 | || (ascii_compatible | |
7654 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
7655 | return Qnil; | |
7656 | p = CHAR_POS_ADDR (from); | |
7657 | pend = CHAR_POS_ADDR (to); | |
7658 | if (from < GPT && to >= GPT) | |
7659 | stop = GPT_ADDR; | |
7660 | else | |
7661 | stop = pend; | |
7662 | } | |
7663 | else | |
7664 | { | |
7665 | CHECK_STRING (string); | |
7666 | CHECK_NATNUM (start); | |
7667 | CHECK_NATNUM (end); | |
7668 | from = XINT (start); | |
7669 | to = XINT (end); | |
7670 | if (from > to | |
7671 | || to > SCHARS (string)) | |
7672 | args_out_of_range_3 (string, start, end); | |
7673 | if (! STRING_MULTIBYTE (string)) | |
7674 | return Qnil; | |
7675 | p = SDATA (string) + string_char_to_byte (string, from); | |
7676 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
7677 | if (ascii_compatible && (to - from) == (pend - p)) | |
7678 | return Qnil; | |
7679 | } | |
f2558efd | 7680 | |
8f924df7 KH |
7681 | if (NILP (count)) |
7682 | n = 1; | |
7683 | else | |
b73bfc1c | 7684 | { |
8f924df7 KH |
7685 | CHECK_NATNUM (count); |
7686 | n = XINT (count); | |
b73bfc1c KH |
7687 | } |
7688 | ||
8f924df7 KH |
7689 | positions = Qnil; |
7690 | while (1) | |
d46c5b12 | 7691 | { |
8f924df7 | 7692 | int c; |
ec6d2bb8 | 7693 | |
8f924df7 KH |
7694 | if (ascii_compatible) |
7695 | while (p < stop && ASCII_BYTE_P (*p)) | |
7696 | p++, from++; | |
7697 | if (p >= stop) | |
0e79d667 | 7698 | { |
8f924df7 KH |
7699 | if (p >= pend) |
7700 | break; | |
7701 | stop = pend; | |
7702 | p = GAP_END_ADDR; | |
0e79d667 | 7703 | } |
ec6d2bb8 | 7704 | |
8f924df7 KH |
7705 | c = STRING_CHAR_ADVANCE (p); |
7706 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
7707 | && ! char_charset (translate_char (translation_table, c), |
7708 | charset_list, NULL)) | |
ec6d2bb8 | 7709 | { |
8f924df7 KH |
7710 | positions = Fcons (make_number (from), positions); |
7711 | n--; | |
7712 | if (n == 0) | |
7713 | break; | |
ec6d2bb8 KH |
7714 | } |
7715 | ||
8f924df7 KH |
7716 | from++; |
7717 | } | |
d46c5b12 | 7718 | |
8f924df7 KH |
7719 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
7720 | } | |
d46c5b12 | 7721 | |
d46c5b12 | 7722 | |
df7492f9 KH |
7723 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
7724 | Scheck_coding_systems_region, 3, 3, 0, | |
7725 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 7726 | |
df7492f9 KH |
7727 | START and END are buffer positions specifying the region. |
7728 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 7729 | |
df7492f9 KH |
7730 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
7731 | CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the | |
7732 | whole region, POS0, POS1, ... are buffer positions where non-encodable | |
7733 | characters are found. | |
93dec019 | 7734 | |
df7492f9 KH |
7735 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
7736 | value is nil. | |
93dec019 | 7737 | |
df7492f9 KH |
7738 | START may be a string. In that case, check if the string is |
7739 | encodable, and the value contains indices to the string instead of | |
7740 | buffer positions. END is ignored. */) | |
7741 | (start, end, coding_system_list) | |
7742 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 7743 | { |
df7492f9 KH |
7744 | Lisp_Object list; |
7745 | EMACS_INT start_byte, end_byte; | |
7746 | int pos; | |
7c78e542 | 7747 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 7748 | int c; |
7d64c6ad | 7749 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 7750 | |
05e6f5dc KH |
7751 | if (STRINGP (start)) |
7752 | { | |
df7492f9 | 7753 | if (!STRING_MULTIBYTE (start) |
8f924df7 | 7754 | && SCHARS (start) != SBYTES (start)) |
df7492f9 KH |
7755 | return Qnil; |
7756 | start_byte = 0; | |
8f924df7 | 7757 | end_byte = SBYTES (start); |
df7492f9 | 7758 | pos = 0; |
d46c5b12 | 7759 | } |
05e6f5dc | 7760 | else |
b73bfc1c | 7761 | { |
b7826503 PJ |
7762 | CHECK_NUMBER_COERCE_MARKER (start); |
7763 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
7764 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
7765 | args_out_of_range (start, end); | |
7766 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
7767 | return Qnil; |
7768 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
7769 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
7770 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
05e6f5dc | 7771 | return Qt; |
df7492f9 | 7772 | |
e1c23804 | 7773 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 7774 | { |
e1c23804 DL |
7775 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
7776 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 7777 | else |
e1c23804 | 7778 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 7779 | } |
e1c23804 | 7780 | pos = XINT (start); |
b73bfc1c | 7781 | } |
7553d0e1 | 7782 | |
df7492f9 KH |
7783 | list = Qnil; |
7784 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 7785 | { |
df7492f9 | 7786 | elt = XCAR (tail); |
7d64c6ad | 7787 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
7788 | ASET (attrs, coding_attr_trans_tbl, |
7789 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 7790 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
7791 | } |
7792 | ||
df7492f9 | 7793 | if (STRINGP (start)) |
8f924df7 | 7794 | p = pbeg = SDATA (start); |
72d1a715 | 7795 | else |
df7492f9 KH |
7796 | p = pbeg = BYTE_POS_ADDR (start_byte); |
7797 | pend = p + (end_byte - start_byte); | |
4ed46869 | 7798 | |
df7492f9 KH |
7799 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
7800 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 7801 | |
df7492f9 | 7802 | while (p < pend) |
d46c5b12 | 7803 | { |
df7492f9 KH |
7804 | if (ASCII_BYTE_P (*p)) |
7805 | p++; | |
e133c8fa | 7806 | else |
05e6f5dc | 7807 | { |
df7492f9 KH |
7808 | c = STRING_CHAR_ADVANCE (p); |
7809 | ||
7810 | charset_map_loaded = 0; | |
7811 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
7812 | { | |
7813 | elt = XCDR (XCAR (tail)); | |
7814 | if (! char_encodable_p (c, XCAR (elt))) | |
7815 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
7816 | } | |
7817 | if (charset_map_loaded) | |
7818 | { | |
7819 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
7820 | ||
7821 | if (STRINGP (start)) | |
8f924df7 | 7822 | pbeg = SDATA (start); |
df7492f9 KH |
7823 | else |
7824 | pbeg = BYTE_POS_ADDR (start_byte); | |
7825 | p = pbeg + p_offset; | |
7826 | pend = pbeg + pend_offset; | |
7827 | } | |
05e6f5dc | 7828 | } |
df7492f9 | 7829 | pos++; |
d46c5b12 | 7830 | } |
4ed46869 | 7831 | |
df7492f9 KH |
7832 | tail = list; |
7833 | list = Qnil; | |
7834 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 7835 | { |
df7492f9 KH |
7836 | elt = XCAR (tail); |
7837 | if (CONSP (XCDR (XCDR (elt)))) | |
7838 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
7839 | list); | |
ec6d2bb8 | 7840 | } |
2b4f9037 | 7841 | |
df7492f9 | 7842 | return list; |
d46c5b12 KH |
7843 | } |
7844 | ||
3fd9494b | 7845 | |
b73bfc1c | 7846 | Lisp_Object |
df7492f9 KH |
7847 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
7848 | Lisp_Object start, end, coding_system, dst_object; | |
7849 | int encodep, norecord; | |
4ed46869 | 7850 | { |
3a73fa5d | 7851 | struct coding_system coding; |
df7492f9 KH |
7852 | EMACS_INT from, from_byte, to, to_byte; |
7853 | Lisp_Object src_object; | |
4ed46869 | 7854 | |
b7826503 PJ |
7855 | CHECK_NUMBER_COERCE_MARKER (start); |
7856 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
7857 | if (NILP (coding_system)) |
7858 | coding_system = Qno_conversion; | |
7859 | else | |
7860 | CHECK_CODING_SYSTEM (coding_system); | |
7861 | src_object = Fcurrent_buffer (); | |
7862 | if (NILP (dst_object)) | |
7863 | dst_object = src_object; | |
7864 | else if (! EQ (dst_object, Qt)) | |
7865 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 7866 | |
d46c5b12 KH |
7867 | validate_region (&start, &end); |
7868 | from = XFASTINT (start); | |
df7492f9 | 7869 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 7870 | to = XFASTINT (end); |
df7492f9 | 7871 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 7872 | |
df7492f9 KH |
7873 | setup_coding_system (coding_system, &coding); |
7874 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 7875 | |
df7492f9 KH |
7876 | if (encodep) |
7877 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7878 | dst_object); | |
7879 | else | |
7880 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
7881 | dst_object); | |
7882 | if (! norecord) | |
7883 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 7884 | |
df7492f9 KH |
7885 | return (BUFFERP (dst_object) |
7886 | ? make_number (coding.produced_char) | |
7887 | : coding.dst_object); | |
4031e2bf | 7888 | } |
78108bcd | 7889 | |
4ed46869 | 7890 | |
4031e2bf | 7891 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 7892 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 7893 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
7894 | When called from a program, takes four arguments: |
7895 | START, END, CODING-SYSTEM, and DESTINATION. | |
7896 | START and END are buffer positions. | |
8844fa83 | 7897 | |
df7492f9 KH |
7898 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
7899 | If nil, the region between START and END is replace by the decoded text. | |
7900 | If buffer, the decoded text is inserted in the buffer. | |
7901 | If t, the decoded text is returned. | |
8844fa83 | 7902 | |
48b0f3ae PJ |
7903 | This function sets `last-coding-system-used' to the precise coding system |
7904 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7905 | not fully specified.) | |
7906 | It returns the length of the decoded text. */) | |
df7492f9 KH |
7907 | (start, end, coding_system, destination) |
7908 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 7909 | { |
df7492f9 | 7910 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 7911 | } |
8844fa83 | 7912 | |
3a73fa5d | 7913 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
7914 | 3, 4, "r\nzCoding system: ", |
7915 | doc: /* Encode the current region by specified coding system. | |
48b0f3ae PJ |
7916 | When called from a program, takes three arguments: |
7917 | START, END, and CODING-SYSTEM. START and END are buffer positions. | |
d46c5b12 | 7918 | |
df7492f9 KH |
7919 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
7920 | If nil, the region between START and END is replace by the encoded text. | |
7921 | If buffer, the encoded text is inserted in the buffer. | |
7922 | If t, the encoded text is returned. | |
2391eaa4 | 7923 | |
48b0f3ae PJ |
7924 | This function sets `last-coding-system-used' to the precise coding system |
7925 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
7926 | not fully specified.) | |
7927 | It returns the length of the encoded text. */) | |
df7492f9 KH |
7928 | (start, end, coding_system, destination) |
7929 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 7930 | { |
df7492f9 | 7931 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
7932 | } |
7933 | ||
7934 | Lisp_Object | |
df7492f9 KH |
7935 | code_convert_string (string, coding_system, dst_object, |
7936 | encodep, nocopy, norecord) | |
7937 | Lisp_Object string, coding_system, dst_object; | |
7938 | int encodep, nocopy, norecord; | |
b73bfc1c | 7939 | { |
4031e2bf | 7940 | struct coding_system coding; |
df7492f9 | 7941 | EMACS_INT chars, bytes; |
ec6d2bb8 | 7942 | |
b7826503 | 7943 | CHECK_STRING (string); |
d46c5b12 | 7944 | if (NILP (coding_system)) |
4956c225 | 7945 | { |
df7492f9 KH |
7946 | if (! norecord) |
7947 | Vlast_coding_system_used = Qno_conversion; | |
7948 | if (NILP (dst_object)) | |
7949 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 7950 | } |
b73bfc1c | 7951 | |
df7492f9 KH |
7952 | if (NILP (coding_system)) |
7953 | coding_system = Qno_conversion; | |
7954 | else | |
7955 | CHECK_CODING_SYSTEM (coding_system); | |
7956 | if (NILP (dst_object)) | |
7957 | dst_object = Qt; | |
7958 | else if (! EQ (dst_object, Qt)) | |
7959 | CHECK_BUFFER (dst_object); | |
73be902c | 7960 | |
df7492f9 | 7961 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 7962 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
7963 | chars = SCHARS (string); |
7964 | bytes = SBYTES (string); | |
df7492f9 KH |
7965 | if (encodep) |
7966 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7967 | else | |
7968 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
7969 | if (! norecord) | |
7970 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 7971 | |
df7492f9 KH |
7972 | return (BUFFERP (dst_object) |
7973 | ? make_number (coding.produced_char) | |
7974 | : coding.dst_object); | |
4ed46869 | 7975 | } |
73be902c | 7976 | |
b73bfc1c | 7977 | |
ecec61c1 | 7978 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 7979 | Do not set Vlast_coding_system_used. |
4ed46869 | 7980 | |
ec6d2bb8 KH |
7981 | This function is called only from macros DECODE_FILE and |
7982 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 7983 | |
ecec61c1 KH |
7984 | Lisp_Object |
7985 | code_convert_string_norecord (string, coding_system, encodep) | |
7986 | Lisp_Object string, coding_system; | |
7987 | int encodep; | |
4ed46869 | 7988 | { |
0be8721c | 7989 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
7990 | } |
7991 | ||
4ed46869 | 7992 | |
df7492f9 KH |
7993 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
7994 | 2, 4, 0, | |
7995 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
7996 | ||
7997 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
7998 | if the decoding operation is trivial. | |
ecec61c1 | 7999 | |
df7492f9 | 8000 | Optional fourth arg BUFFER non-nil meant that the decoded text is |
a3f6ee6d | 8001 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 | 8002 | the return value is BUFFER. |
ecec61c1 | 8003 | |
df7492f9 KH |
8004 | This function sets `last-coding-system-used' to the precise coding system |
8005 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
8006 | not fully specified. */) | |
8007 | (string, coding_system, nocopy, buffer) | |
8008 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 8009 | { |
df7492f9 KH |
8010 | return code_convert_string (string, coding_system, buffer, |
8011 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
8012 | } |
8013 | ||
df7492f9 KH |
8014 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
8015 | 2, 4, 0, | |
8016 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
8017 | ||
8018 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
8019 | itself if the encoding operation is trivial. | |
8020 | ||
8021 | Optional fourth arg BUFFER non-nil meant that the encoded text is | |
a3f6ee6d | 8022 | inserted in BUFFER instead of returned as a string. In this case, |
df7492f9 KH |
8023 | the return value is BUFFER. |
8024 | ||
8025 | This function sets `last-coding-system-used' to the precise coding system | |
8026 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
8027 | not fully specified.) */) | |
8028 | (string, coding_system, nocopy, buffer) | |
8029 | Lisp_Object string, coding_system, nocopy, buffer; | |
4ed46869 | 8030 | { |
df7492f9 | 8031 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 8032 | 1, ! NILP (nocopy), 1); |
4ed46869 | 8033 | } |
df7492f9 | 8034 | |
3a73fa5d | 8035 | \f |
4ed46869 | 8036 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
8037 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
8038 | Return the corresponding character. */) | |
8039 | (code) | |
4ed46869 | 8040 | Lisp_Object code; |
4ed46869 | 8041 | { |
df7492f9 KH |
8042 | Lisp_Object spec, attrs, val; |
8043 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
8044 | int c; | |
4ed46869 | 8045 | |
df7492f9 KH |
8046 | CHECK_NATNUM (code); |
8047 | c = XFASTINT (code); | |
8048 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
8049 | attrs = AREF (spec, 0); | |
4ed46869 | 8050 | |
df7492f9 KH |
8051 | if (ASCII_BYTE_P (c) |
8052 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8053 | return code; | |
4ed46869 | 8054 | |
df7492f9 KH |
8055 | val = CODING_ATTR_CHARSET_LIST (attrs); |
8056 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
8057 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
8058 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 8059 | |
df7492f9 KH |
8060 | if (c <= 0x7F) |
8061 | charset = charset_roman; | |
8062 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 8063 | { |
df7492f9 KH |
8064 | charset = charset_kana; |
8065 | c -= 0x80; | |
4ed46869 | 8066 | } |
55ab7be3 | 8067 | else |
4ed46869 | 8068 | { |
004068e4 | 8069 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
8070 | |
8071 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
8072 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
8073 | error ("Invalid code: %d", code); | |
8074 | SJIS_TO_JIS (c); | |
8075 | charset = charset_kanji; | |
4ed46869 | 8076 | } |
df7492f9 KH |
8077 | c = DECODE_CHAR (charset, c); |
8078 | if (c < 0) | |
8079 | error ("Invalid code: %d", code); | |
8080 | return make_number (c); | |
93dec019 | 8081 | } |
4ed46869 | 8082 | |
48b0f3ae | 8083 | |
4ed46869 | 8084 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
8085 | doc: /* Encode a Japanese character CHAR to shift_jis encoding. |
8086 | Return the corresponding code in SJIS. */) | |
8087 | (ch) | |
df7492f9 | 8088 | Lisp_Object ch; |
4ed46869 | 8089 | { |
df7492f9 KH |
8090 | Lisp_Object spec, attrs, charset_list; |
8091 | int c; | |
8092 | struct charset *charset; | |
8093 | unsigned code; | |
48b0f3ae | 8094 | |
df7492f9 KH |
8095 | CHECK_CHARACTER (ch); |
8096 | c = XFASTINT (ch); | |
8097 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
8098 | attrs = AREF (spec, 0); | |
8099 | ||
8100 | if (ASCII_CHAR_P (c) | |
8101 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8102 | return ch; | |
8103 | ||
8104 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8105 | charset = char_charset (c, charset_list, &code); | |
8106 | if (code == CHARSET_INVALID_CODE (charset)) | |
8107 | error ("Can't encode by shift_jis encoding: %d", c); | |
8108 | JIS_TO_SJIS (code); | |
8109 | ||
8110 | return make_number (code); | |
4ed46869 KH |
8111 | } |
8112 | ||
8113 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
8114 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
8115 | Return the corresponding character. */) | |
8116 | (code) | |
4ed46869 | 8117 | Lisp_Object code; |
d46c5b12 | 8118 | { |
df7492f9 KH |
8119 | Lisp_Object spec, attrs, val; |
8120 | struct charset *charset_roman, *charset_big5, *charset; | |
8121 | int c; | |
6289dd10 | 8122 | |
df7492f9 KH |
8123 | CHECK_NATNUM (code); |
8124 | c = XFASTINT (code); | |
8125 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8126 | attrs = AREF (spec, 0); | |
4ed46869 | 8127 | |
df7492f9 KH |
8128 | if (ASCII_BYTE_P (c) |
8129 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8130 | return code; | |
6289dd10 | 8131 | |
df7492f9 KH |
8132 | val = CODING_ATTR_CHARSET_LIST (attrs); |
8133 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
8134 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 8135 | |
df7492f9 KH |
8136 | if (c <= 0x7F) |
8137 | charset = charset_roman; | |
c28a9453 KH |
8138 | else |
8139 | { | |
df7492f9 KH |
8140 | int b1 = c >> 8, b2 = c & 0x7F; |
8141 | if (b1 < 0xA1 || b1 > 0xFE | |
8142 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
8143 | error ("Invalid code: %d", code); | |
8144 | charset = charset_big5; | |
c28a9453 | 8145 | } |
df7492f9 KH |
8146 | c = DECODE_CHAR (charset, (unsigned )c); |
8147 | if (c < 0) | |
8148 | error ("Invalid code: %d", code); | |
8149 | return make_number (c); | |
d46c5b12 | 8150 | } |
6289dd10 | 8151 | |
4ed46869 | 8152 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
48b0f3ae PJ |
8153 | doc: /* Encode the Big5 character CHAR to BIG5 coding system. |
8154 | Return the corresponding character code in Big5. */) | |
8155 | (ch) | |
4ed46869 KH |
8156 | Lisp_Object ch; |
8157 | { | |
df7492f9 KH |
8158 | Lisp_Object spec, attrs, charset_list; |
8159 | struct charset *charset; | |
8160 | int c; | |
8161 | unsigned code; | |
8162 | ||
8163 | CHECK_CHARACTER (ch); | |
8164 | c = XFASTINT (ch); | |
8165 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
8166 | attrs = AREF (spec, 0); | |
8167 | if (ASCII_CHAR_P (c) | |
8168 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
8169 | return ch; | |
8170 | ||
8171 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
8172 | charset = char_charset (c, charset_list, &code); | |
8173 | if (code == CHARSET_INVALID_CODE (charset)) | |
8174 | error ("Can't encode by Big5 encoding: %d", c); | |
8175 | ||
8176 | return make_number (code); | |
4ed46869 | 8177 | } |
48b0f3ae | 8178 | |
3a73fa5d | 8179 | \f |
1ba9e4ab KH |
8180 | DEFUN ("set-terminal-coding-system-internal", |
8181 | Fset_terminal_coding_system_internal, | |
48b0f3ae PJ |
8182 | Sset_terminal_coding_system_internal, 1, 1, 0, |
8183 | doc: /* Internal use only. */) | |
8184 | (coding_system) | |
b74e4686 | 8185 | Lisp_Object coding_system; |
4ed46869 | 8186 | { |
b7826503 | 8187 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
8188 | setup_coding_system (Fcheck_coding_system (coding_system), |
8189 | &terminal_coding); | |
48b0f3ae | 8190 | |
70c22245 | 8191 | /* We had better not send unsafe characters to terminal. */ |
df7492f9 KH |
8192 | terminal_coding.mode |= CODING_MODE_SAFE_ENCODING; |
8193 | /* Characer composition should be disabled. */ | |
8194 | terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8195 | terminal_coding.src_multibyte = 1; |
8196 | terminal_coding.dst_multibyte = 0; | |
4ed46869 KH |
8197 | return Qnil; |
8198 | } | |
8199 | ||
c4825358 KH |
8200 | DEFUN ("set-safe-terminal-coding-system-internal", |
8201 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 8202 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 8203 | doc: /* Internal use only. */) |
48b0f3ae | 8204 | (coding_system) |
b74e4686 | 8205 | Lisp_Object coding_system; |
d46c5b12 | 8206 | { |
b7826503 | 8207 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
8208 | setup_coding_system (Fcheck_coding_system (coding_system), |
8209 | &safe_terminal_coding); | |
df7492f9 KH |
8210 | /* Characer composition should be disabled. */ |
8211 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
8212 | safe_terminal_coding.src_multibyte = 1; |
8213 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
8214 | return Qnil; |
8215 | } | |
4ed46869 | 8216 | |
4ed46869 KH |
8217 | DEFUN ("terminal-coding-system", |
8218 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
8219 | doc: /* Return coding system specified for terminal output. */) |
8220 | () | |
4ed46869 | 8221 | { |
ae6f73fa KH |
8222 | Lisp_Object coding_system; |
8223 | ||
8224 | coding_system = CODING_ID_NAME (terminal_coding.id); | |
8225 | /* For backward compatibility, return nil if it is `undecided'. */ | |
8226 | return (coding_system != Qundecided ? coding_system : Qnil); | |
4ed46869 KH |
8227 | } |
8228 | ||
1ba9e4ab KH |
8229 | DEFUN ("set-keyboard-coding-system-internal", |
8230 | Fset_keyboard_coding_system_internal, | |
48b0f3ae PJ |
8231 | Sset_keyboard_coding_system_internal, 1, 1, 0, |
8232 | doc: /* Internal use only. */) | |
8233 | (coding_system) | |
4ed46869 KH |
8234 | Lisp_Object coding_system; |
8235 | { | |
b7826503 | 8236 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
8237 | setup_coding_system (Fcheck_coding_system (coding_system), |
8238 | &keyboard_coding); | |
8239 | /* Characer composition should be disabled. */ | |
8240 | keyboard_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
8241 | return Qnil; |
8242 | } | |
8243 | ||
8244 | DEFUN ("keyboard-coding-system", | |
8245 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
8246 | doc: /* Return coding system specified for decoding keyboard input. */) |
8247 | () | |
4ed46869 | 8248 | { |
df7492f9 | 8249 | return CODING_ID_NAME (keyboard_coding.id); |
4ed46869 KH |
8250 | } |
8251 | ||
4ed46869 | 8252 | \f |
a5d301df KH |
8253 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
8254 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
8255 | doc: /* Choose a coding system for an operation based on the target name. |
8256 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
8257 | DECODING-SYSTEM is the coding system to use for decoding | |
8258 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
8259 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 8260 | |
48b0f3ae PJ |
8261 | The first argument OPERATION specifies an I/O primitive: |
8262 | For file I/O, `insert-file-contents' or `write-region'. | |
8263 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
8264 | For network I/O, `open-network-stream'. | |
05e6f5dc | 8265 | |
48b0f3ae PJ |
8266 | The remaining arguments should be the same arguments that were passed |
8267 | to the primitive. Depending on which primitive, one of those arguments | |
8268 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
8269 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 8270 | |
48b0f3ae PJ |
8271 | TARGET has a meaning which depends on OPERATION: |
8272 | For file I/O, TARGET is a file name. | |
8273 | For process I/O, TARGET is a process name. | |
8274 | For network I/O, TARGET is a service name or a port number | |
05e6f5dc | 8275 | |
48b0f3ae PJ |
8276 | This function looks up what specified for TARGET in, |
8277 | `file-coding-system-alist', `process-coding-system-alist', | |
8278 | or `network-coding-system-alist' depending on OPERATION. | |
8279 | They may specify a coding system, a cons of coding systems, | |
8280 | or a function symbol to call. | |
8281 | In the last case, we call the function with one argument, | |
8282 | which is a list of all the arguments given to this function. | |
8283 | ||
8284 | usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */) | |
8285 | (nargs, args) | |
4ed46869 KH |
8286 | int nargs; |
8287 | Lisp_Object *args; | |
6b89e3aa | 8288 | { |
4ed46869 KH |
8289 | Lisp_Object operation, target_idx, target, val; |
8290 | register Lisp_Object chain; | |
177c0ea7 | 8291 | |
4ed46869 KH |
8292 | if (nargs < 2) |
8293 | error ("Too few arguments"); | |
8294 | operation = args[0]; | |
8295 | if (!SYMBOLP (operation) | |
8296 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
df7492f9 | 8297 | error ("Invalid first arguement"); |
4ed46869 KH |
8298 | if (nargs < 1 + XINT (target_idx)) |
8299 | error ("Too few arguments for operation: %s", | |
8f924df7 | 8300 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
8301 | target = args[XINT (target_idx) + 1]; |
8302 | if (!(STRINGP (target) | |
8303 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) | |
df7492f9 | 8304 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
4ed46869 | 8305 | |
2e34157c RS |
8306 | chain = ((EQ (operation, Qinsert_file_contents) |
8307 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 8308 | ? Vfile_coding_system_alist |
2e34157c | 8309 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
8310 | ? Vnetwork_coding_system_alist |
8311 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
8312 | if (NILP (chain)) |
8313 | return Qnil; | |
8314 | ||
03699b14 | 8315 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 8316 | { |
f44d27ce | 8317 | Lisp_Object elt; |
6b89e3aa | 8318 | |
df7492f9 | 8319 | elt = XCAR (chain); |
4ed46869 KH |
8320 | if (CONSP (elt) |
8321 | && ((STRINGP (target) | |
03699b14 KR |
8322 | && STRINGP (XCAR (elt)) |
8323 | && fast_string_match (XCAR (elt), target) >= 0) | |
8324 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 8325 | { |
03699b14 | 8326 | val = XCDR (elt); |
b19fd4c5 KH |
8327 | /* Here, if VAL is both a valid coding system and a valid |
8328 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
8329 | if (CONSP (val)) |
8330 | return val; | |
8331 | if (! SYMBOLP (val)) | |
8332 | return Qnil; | |
8333 | if (! NILP (Fcoding_system_p (val))) | |
8334 | return Fcons (val, val); | |
b19fd4c5 | 8335 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 8336 | { |
b19fd4c5 KH |
8337 | val = call1 (val, Flist (nargs, args)); |
8338 | if (CONSP (val)) | |
8339 | return val; | |
8340 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
8341 | return Fcons (val, val); | |
6b89e3aa | 8342 | } |
02ba4723 | 8343 | return Qnil; |
6b89e3aa KH |
8344 | } |
8345 | } | |
4ed46869 | 8346 | return Qnil; |
6b89e3aa KH |
8347 | } |
8348 | ||
df7492f9 | 8349 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 8350 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 8351 | doc: /* Assign higher priority to the coding systems given as arguments. |
ff563fce | 8352 | If multiple coding systems belongs to the same category, |
a3181084 DL |
8353 | all but the first one are ignored. |
8354 | ||
8355 | usage: (set-coding-system-priority ...) */) | |
df7492f9 KH |
8356 | (nargs, args) |
8357 | int nargs; | |
8358 | Lisp_Object *args; | |
8359 | { | |
8360 | int i, j; | |
8361 | int changed[coding_category_max]; | |
8362 | enum coding_category priorities[coding_category_max]; | |
8363 | ||
8364 | bzero (changed, sizeof changed); | |
6b89e3aa | 8365 | |
df7492f9 | 8366 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 8367 | { |
df7492f9 KH |
8368 | enum coding_category category; |
8369 | Lisp_Object spec, attrs; | |
6b89e3aa | 8370 | |
df7492f9 KH |
8371 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
8372 | attrs = AREF (spec, 0); | |
8373 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8374 | if (changed[category]) | |
8375 | /* Ignore this coding system because a coding system of the | |
8376 | same category already had a higher priority. */ | |
8377 | continue; | |
8378 | changed[category] = 1; | |
8379 | priorities[j++] = category; | |
8380 | if (coding_categories[category].id >= 0 | |
8381 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
8382 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 8383 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 8384 | } |
6b89e3aa | 8385 | |
df7492f9 KH |
8386 | /* Now we have decided top J priorities. Reflect the order of the |
8387 | original priorities to the remaining priorities. */ | |
6b89e3aa | 8388 | |
df7492f9 | 8389 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 8390 | { |
df7492f9 KH |
8391 | while (j < coding_category_max |
8392 | && changed[coding_priorities[j]]) | |
8393 | j++; | |
8394 | if (j == coding_category_max) | |
8395 | abort (); | |
8396 | priorities[i] = coding_priorities[j]; | |
8397 | } | |
6b89e3aa | 8398 | |
df7492f9 | 8399 | bcopy (priorities, coding_priorities, sizeof priorities); |
177c0ea7 | 8400 | |
ff563fce KH |
8401 | /* Update `coding-category-list'. */ |
8402 | Vcoding_category_list = Qnil; | |
8403 | for (i = coding_category_max - 1; i >= 0; i--) | |
8404 | Vcoding_category_list | |
8405 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
8406 | Vcoding_category_list); | |
6b89e3aa | 8407 | |
df7492f9 | 8408 | return Qnil; |
6b89e3aa KH |
8409 | } |
8410 | ||
df7492f9 KH |
8411 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
8412 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 DL |
8413 | doc: /* Return a list of coding systems ordered by their priorities. |
8414 | HIGHESTP non-nil means just return the highest priority one. */) | |
df7492f9 KH |
8415 | (highestp) |
8416 | Lisp_Object highestp; | |
d46c5b12 KH |
8417 | { |
8418 | int i; | |
df7492f9 | 8419 | Lisp_Object val; |
6b89e3aa | 8420 | |
df7492f9 | 8421 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 8422 | { |
df7492f9 KH |
8423 | enum coding_category category = coding_priorities[i]; |
8424 | int id = coding_categories[category].id; | |
8425 | Lisp_Object attrs; | |
068a9dbd | 8426 | |
df7492f9 KH |
8427 | if (id < 0) |
8428 | continue; | |
8429 | attrs = CODING_ID_ATTRS (id); | |
8430 | if (! NILP (highestp)) | |
8431 | return CODING_ATTR_BASE_NAME (attrs); | |
8432 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
8433 | } | |
8434 | return Fnreverse (val); | |
8435 | } | |
068a9dbd | 8436 | |
f0064e1f | 8437 | static char *suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
8438 | |
8439 | static Lisp_Object | |
df7492f9 KH |
8440 | make_subsidiaries (base) |
8441 | Lisp_Object base; | |
068a9dbd | 8442 | { |
df7492f9 | 8443 | Lisp_Object subsidiaries; |
8f924df7 | 8444 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
8445 | char *buf = (char *) alloca (base_name_len + 6); |
8446 | int i; | |
068a9dbd | 8447 | |
8f924df7 | 8448 | bcopy (SDATA (SYMBOL_NAME (base)), buf, base_name_len); |
df7492f9 KH |
8449 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
8450 | for (i = 0; i < 3; i++) | |
068a9dbd | 8451 | { |
df7492f9 KH |
8452 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); |
8453 | ASET (subsidiaries, i, intern (buf)); | |
068a9dbd | 8454 | } |
df7492f9 | 8455 | return subsidiaries; |
068a9dbd KH |
8456 | } |
8457 | ||
8458 | ||
df7492f9 KH |
8459 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
8460 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
8461 | doc: /* For internal use only. |
8462 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
8463 | (nargs, args) |
8464 | int nargs; | |
8465 | Lisp_Object *args; | |
068a9dbd | 8466 | { |
df7492f9 KH |
8467 | Lisp_Object name; |
8468 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
8469 | Lisp_Object attrs; /* Vector of attributes. */ | |
8470 | Lisp_Object eol_type; | |
8471 | Lisp_Object aliases; | |
8472 | Lisp_Object coding_type, charset_list, safe_charsets; | |
8473 | enum coding_category category; | |
8474 | Lisp_Object tail, val; | |
8475 | int max_charset_id = 0; | |
8476 | int i; | |
068a9dbd | 8477 | |
df7492f9 KH |
8478 | if (nargs < coding_arg_max) |
8479 | goto short_args; | |
068a9dbd | 8480 | |
df7492f9 | 8481 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 8482 | |
df7492f9 KH |
8483 | name = args[coding_arg_name]; |
8484 | CHECK_SYMBOL (name); | |
8485 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 8486 | |
df7492f9 KH |
8487 | val = args[coding_arg_mnemonic]; |
8488 | if (! STRINGP (val)) | |
8489 | CHECK_CHARACTER (val); | |
8490 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 8491 | |
df7492f9 KH |
8492 | coding_type = args[coding_arg_coding_type]; |
8493 | CHECK_SYMBOL (coding_type); | |
8494 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 8495 | |
df7492f9 KH |
8496 | charset_list = args[coding_arg_charset_list]; |
8497 | if (SYMBOLP (charset_list)) | |
8498 | { | |
8499 | if (EQ (charset_list, Qiso_2022)) | |
8500 | { | |
8501 | if (! EQ (coding_type, Qiso_2022)) | |
8502 | error ("Invalid charset-list"); | |
8503 | charset_list = Viso_2022_charset_list; | |
8504 | } | |
8505 | else if (EQ (charset_list, Qemacs_mule)) | |
8506 | { | |
8507 | if (! EQ (coding_type, Qemacs_mule)) | |
8508 | error ("Invalid charset-list"); | |
8509 | charset_list = Vemacs_mule_charset_list; | |
8510 | } | |
8511 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8512 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
8513 | max_charset_id = XFASTINT (XCAR (tail)); | |
8514 | } | |
068a9dbd KH |
8515 | else |
8516 | { | |
df7492f9 KH |
8517 | charset_list = Fcopy_sequence (charset_list); |
8518 | for (tail = charset_list; !NILP (tail); tail = Fcdr (tail)) | |
068a9dbd | 8519 | { |
df7492f9 KH |
8520 | struct charset *charset; |
8521 | ||
8522 | val = Fcar (tail); | |
8523 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8524 | if (EQ (coding_type, Qiso_2022) | |
8525 | ? CHARSET_ISO_FINAL (charset) < 0 | |
8526 | : EQ (coding_type, Qemacs_mule) | |
8527 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
8528 | : 0) | |
8529 | error ("Can't handle charset `%s'", | |
8f924df7 | 8530 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 8531 | |
8f924df7 | 8532 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
8533 | if (max_charset_id < charset->id) |
8534 | max_charset_id = charset->id; | |
068a9dbd KH |
8535 | } |
8536 | } | |
df7492f9 | 8537 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 8538 | |
df7492f9 KH |
8539 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), |
8540 | make_number (255)); | |
8541 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
8f924df7 | 8542 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 8543 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 8544 | |
584948ac | 8545 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 8546 | |
df7492f9 | 8547 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 8548 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 8549 | CHECK_SYMBOL (val); |
df7492f9 | 8550 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 8551 | |
df7492f9 | 8552 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 8553 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 8554 | CHECK_SYMBOL (val); |
df7492f9 | 8555 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 8556 | |
df7492f9 KH |
8557 | val = args[coding_arg_post_read_conversion]; |
8558 | CHECK_SYMBOL (val); | |
8559 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 8560 | |
df7492f9 KH |
8561 | val = args[coding_arg_pre_write_conversion]; |
8562 | CHECK_SYMBOL (val); | |
8563 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 8564 | |
df7492f9 KH |
8565 | val = args[coding_arg_default_char]; |
8566 | if (NILP (val)) | |
8567 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
8568 | else | |
8569 | { | |
8f924df7 | 8570 | CHECK_CHARACTER (val); |
df7492f9 KH |
8571 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
8572 | } | |
4031e2bf | 8573 | |
8f924df7 KH |
8574 | val = args[coding_arg_for_unibyte]; |
8575 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 8576 | |
df7492f9 KH |
8577 | val = args[coding_arg_plist]; |
8578 | CHECK_LIST (val); | |
8579 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 8580 | |
df7492f9 KH |
8581 | if (EQ (coding_type, Qcharset)) |
8582 | { | |
c7c66a95 KH |
8583 | /* Generate a lisp vector of 256 elements. Each element is nil, |
8584 | integer, or a list of charset IDs. | |
3a73fa5d | 8585 | |
c7c66a95 KH |
8586 | If Nth element is nil, the byte code N is invalid in this |
8587 | coding system. | |
4ed46869 | 8588 | |
c7c66a95 KH |
8589 | If Nth element is a number NUM, N is the first byte of a |
8590 | charset whose ID is NUM. | |
4ed46869 | 8591 | |
c7c66a95 KH |
8592 | If Nth element is a list of charset IDs, N is the first byte |
8593 | of one of them. The list is sorted by dimensions of the | |
2bc515e4 | 8594 | charsets. A charset of smaller dimension comes firtst. */ |
df7492f9 | 8595 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 8596 | |
5c99c2e6 | 8597 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 8598 | { |
c7c66a95 KH |
8599 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
8600 | int dim = CHARSET_DIMENSION (charset); | |
8601 | int idx = (dim - 1) * 4; | |
4ed46869 | 8602 | |
5c99c2e6 | 8603 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 8604 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 8605 | |
15d143f7 KH |
8606 | for (i = charset->code_space[idx]; |
8607 | i <= charset->code_space[idx + 1]; i++) | |
8608 | { | |
c7c66a95 KH |
8609 | Lisp_Object tmp, tmp2; |
8610 | int dim2; | |
ec6d2bb8 | 8611 | |
c7c66a95 KH |
8612 | tmp = AREF (val, i); |
8613 | if (NILP (tmp)) | |
8614 | tmp = XCAR (tail); | |
8615 | else if (NUMBERP (tmp)) | |
8616 | { | |
8617 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
8618 | if (dim < dim2) | |
c7c66a95 | 8619 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
8620 | else |
8621 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 8622 | } |
15d143f7 | 8623 | else |
c7c66a95 KH |
8624 | { |
8625 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
8626 | { | |
8627 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
8628 | if (dim < dim2) | |
8629 | break; | |
8630 | } | |
8631 | if (NILP (tmp2)) | |
8632 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
8633 | else | |
8634 | { | |
8635 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
8636 | XSETCAR (tmp2, XCAR (tail)); | |
8637 | } | |
8638 | } | |
8639 | ASET (val, i, tmp); | |
15d143f7 | 8640 | } |
df7492f9 KH |
8641 | } |
8642 | ASET (attrs, coding_attr_charset_valids, val); | |
8643 | category = coding_category_charset; | |
8644 | } | |
8645 | else if (EQ (coding_type, Qccl)) | |
8646 | { | |
8647 | Lisp_Object valids; | |
ecec61c1 | 8648 | |
df7492f9 KH |
8649 | if (nargs < coding_arg_ccl_max) |
8650 | goto short_args; | |
ecec61c1 | 8651 | |
df7492f9 KH |
8652 | val = args[coding_arg_ccl_decoder]; |
8653 | CHECK_CCL_PROGRAM (val); | |
8654 | if (VECTORP (val)) | |
8655 | val = Fcopy_sequence (val); | |
8656 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 8657 | |
df7492f9 KH |
8658 | val = args[coding_arg_ccl_encoder]; |
8659 | CHECK_CCL_PROGRAM (val); | |
8660 | if (VECTORP (val)) | |
8661 | val = Fcopy_sequence (val); | |
8662 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 8663 | |
df7492f9 KH |
8664 | val = args[coding_arg_ccl_valids]; |
8665 | valids = Fmake_string (make_number (256), make_number (0)); | |
8666 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
8667 | { | |
8dcbea82 | 8668 | int from, to; |
ecec61c1 | 8669 | |
df7492f9 KH |
8670 | val = Fcar (tail); |
8671 | if (INTEGERP (val)) | |
8dcbea82 KH |
8672 | { |
8673 | from = to = XINT (val); | |
8674 | if (from < 0 || from > 255) | |
8675 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
8676 | } | |
df7492f9 KH |
8677 | else |
8678 | { | |
df7492f9 | 8679 | CHECK_CONS (val); |
8f924df7 KH |
8680 | CHECK_NATNUM_CAR (val); |
8681 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 8682 | from = XINT (XCAR (val)); |
8f924df7 | 8683 | if (from > 255) |
8dcbea82 KH |
8684 | args_out_of_range_3 (XCAR (val), |
8685 | make_number (0), make_number (255)); | |
df7492f9 | 8686 | to = XINT (XCDR (val)); |
8dcbea82 KH |
8687 | if (to < from || to > 255) |
8688 | args_out_of_range_3 (XCDR (val), | |
8689 | XCAR (val), make_number (255)); | |
df7492f9 | 8690 | } |
8dcbea82 | 8691 | for (i = from; i <= to; i++) |
8f924df7 | 8692 | SSET (valids, i, 1); |
df7492f9 KH |
8693 | } |
8694 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 8695 | |
df7492f9 | 8696 | category = coding_category_ccl; |
55ab7be3 | 8697 | } |
df7492f9 | 8698 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 8699 | { |
df7492f9 | 8700 | Lisp_Object bom, endian; |
4ed46869 | 8701 | |
584948ac | 8702 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 8703 | |
df7492f9 KH |
8704 | if (nargs < coding_arg_utf16_max) |
8705 | goto short_args; | |
4ed46869 | 8706 | |
df7492f9 KH |
8707 | bom = args[coding_arg_utf16_bom]; |
8708 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
8709 | { | |
8710 | CHECK_CONS (bom); | |
8f924df7 KH |
8711 | val = XCAR (bom); |
8712 | CHECK_CODING_SYSTEM (val); | |
8713 | val = XCDR (bom); | |
8714 | CHECK_CODING_SYSTEM (val); | |
df7492f9 KH |
8715 | } |
8716 | ASET (attrs, coding_attr_utf_16_bom, bom); | |
8717 | ||
8718 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
8719 | CHECK_SYMBOL (endian); |
8720 | if (NILP (endian)) | |
8721 | endian = Qbig; | |
8722 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 8723 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
8724 | ASET (attrs, coding_attr_utf_16_endian, endian); |
8725 | ||
8726 | category = (CONSP (bom) | |
8727 | ? coding_category_utf_16_auto | |
8728 | : NILP (bom) | |
b49a1807 | 8729 | ? (EQ (endian, Qbig) |
df7492f9 KH |
8730 | ? coding_category_utf_16_be_nosig |
8731 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 8732 | : (EQ (endian, Qbig) |
df7492f9 KH |
8733 | ? coding_category_utf_16_be |
8734 | : coding_category_utf_16_le)); | |
8735 | } | |
8736 | else if (EQ (coding_type, Qiso_2022)) | |
8737 | { | |
8738 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 8739 | int i; |
1397dc18 | 8740 | |
df7492f9 KH |
8741 | if (nargs < coding_arg_iso2022_max) |
8742 | goto short_args; | |
8743 | ||
8744 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
8745 | CHECK_VECTOR (initial); | |
8746 | for (i = 0; i < 4; i++) | |
8747 | { | |
8748 | val = Faref (initial, make_number (i)); | |
8749 | if (! NILP (val)) | |
8750 | { | |
584948ac KH |
8751 | struct charset *charset; |
8752 | ||
8753 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
8754 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
8755 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
8756 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8757 | } |
8758 | else | |
8759 | ASET (initial, i, make_number (-1)); | |
8760 | } | |
8761 | ||
8762 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
8763 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
8764 | CHECK_NUMBER_CAR (reg_usage); |
8765 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
8766 | |
8767 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
8768 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 8769 | { |
df7492f9 | 8770 | int id; |
8f924df7 | 8771 | Lisp_Object tmp; |
df7492f9 KH |
8772 | |
8773 | val = Fcar (tail); | |
8774 | CHECK_CONS (val); | |
8f924df7 KH |
8775 | tmp = XCAR (val); |
8776 | CHECK_CHARSET_GET_ID (tmp, id); | |
8777 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
8778 | if (XINT (XCDR (val)) >= 4) |
8779 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 8780 | XSETCAR (val, make_number (id)); |
1397dc18 | 8781 | } |
4ed46869 | 8782 | |
df7492f9 KH |
8783 | flags = args[coding_arg_iso2022_flags]; |
8784 | CHECK_NATNUM (flags); | |
8785 | i = XINT (flags); | |
8786 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
8787 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
8788 | ||
8789 | ASET (attrs, coding_attr_iso_initial, initial); | |
8790 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
8791 | ASET (attrs, coding_attr_iso_request, request); | |
8792 | ASET (attrs, coding_attr_iso_flags, flags); | |
8793 | setup_iso_safe_charsets (attrs); | |
8794 | ||
8795 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
8796 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
8797 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
8798 | ? coding_category_iso_7_else | |
8799 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
8800 | ? coding_category_iso_7 | |
8801 | : coding_category_iso_7_tight); | |
8802 | else | |
8803 | { | |
8804 | int id = XINT (AREF (initial, 1)); | |
8805 | ||
c6fb6e98 | 8806 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
8807 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
8808 | || id < 0) | |
8809 | ? coding_category_iso_8_else | |
8810 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
8811 | ? coding_category_iso_8_1 | |
8812 | : coding_category_iso_8_2); | |
8813 | } | |
0ce7886f KH |
8814 | if (category != coding_category_iso_8_1 |
8815 | && category != coding_category_iso_8_2) | |
8816 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
8817 | } |
8818 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 8819 | { |
df7492f9 KH |
8820 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
8821 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 8822 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 8823 | category = coding_category_emacs_mule; |
c28a9453 | 8824 | } |
df7492f9 | 8825 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 8826 | { |
df7492f9 KH |
8827 | |
8828 | struct charset *charset; | |
8829 | ||
7d64c6ad | 8830 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 8831 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 8832 | error ("There should be three or four charsets"); |
df7492f9 KH |
8833 | |
8834 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8835 | if (CHARSET_DIMENSION (charset) != 1) | |
8836 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8837 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8838 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8839 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8840 | |
8841 | charset_list = XCDR (charset_list); | |
8842 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8843 | if (CHARSET_DIMENSION (charset) != 1) | |
8844 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8845 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
8846 | |
8847 | charset_list = XCDR (charset_list); | |
8848 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8849 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
8850 | error ("Dimension of charset %s is not two", |
8851 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8852 | ||
8853 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
8854 | if (! NILP (charset_list)) |
8855 | { | |
8856 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8857 | if (CHARSET_DIMENSION (charset) != 2) | |
8858 | error ("Dimension of charset %s is not two", | |
8859 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
8860 | } | |
df7492f9 KH |
8861 | |
8862 | category = coding_category_sjis; | |
8863 | Vsjis_coding_system = name; | |
c28a9453 | 8864 | } |
df7492f9 KH |
8865 | else if (EQ (coding_type, Qbig5)) |
8866 | { | |
8867 | struct charset *charset; | |
4ed46869 | 8868 | |
df7492f9 KH |
8869 | if (XINT (Flength (charset_list)) != 2) |
8870 | error ("There should be just two charsets"); | |
8871 | ||
8872 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8873 | if (CHARSET_DIMENSION (charset) != 1) | |
8874 | error ("Dimension of charset %s is not one", | |
8f924df7 | 8875 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
8876 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
8877 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
8878 | |
8879 | charset_list = XCDR (charset_list); | |
8880 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
8881 | if (CHARSET_DIMENSION (charset) != 2) | |
8882 | error ("Dimension of charset %s is not two", | |
8f924df7 | 8883 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 8884 | |
df7492f9 KH |
8885 | category = coding_category_big5; |
8886 | Vbig5_coding_system = name; | |
8887 | } | |
8888 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 8889 | { |
584948ac KH |
8890 | category = coding_category_raw_text; |
8891 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 8892 | } |
df7492f9 | 8893 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 8894 | { |
584948ac KH |
8895 | category = coding_category_utf_8; |
8896 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
4ed46869 | 8897 | } |
df7492f9 KH |
8898 | else if (EQ (coding_type, Qundecided)) |
8899 | category = coding_category_undecided; | |
4ed46869 | 8900 | else |
df7492f9 | 8901 | error ("Invalid coding system type: %s", |
8f924df7 | 8902 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 8903 | |
df7492f9 | 8904 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
8905 | CODING_ATTR_PLIST (attrs) |
8906 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
8907 | CODING_ATTR_PLIST (attrs))); | |
35befdaa KH |
8908 | CODING_ATTR_PLIST (attrs) |
8909 | = Fcons (QCascii_compatible_p, | |
8910 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), | |
8911 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 8912 | |
df7492f9 KH |
8913 | eol_type = args[coding_arg_eol_type]; |
8914 | if (! NILP (eol_type) | |
8915 | && ! EQ (eol_type, Qunix) | |
8916 | && ! EQ (eol_type, Qdos) | |
8917 | && ! EQ (eol_type, Qmac)) | |
8918 | error ("Invalid eol-type"); | |
4ed46869 | 8919 | |
df7492f9 | 8920 | aliases = Fcons (name, Qnil); |
4ed46869 | 8921 | |
df7492f9 KH |
8922 | if (NILP (eol_type)) |
8923 | { | |
8924 | eol_type = make_subsidiaries (name); | |
8925 | for (i = 0; i < 3; i++) | |
1397dc18 | 8926 | { |
df7492f9 KH |
8927 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
8928 | ||
8929 | this_name = AREF (eol_type, i); | |
8930 | this_aliases = Fcons (this_name, Qnil); | |
8931 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
8932 | this_spec = Fmake_vector (make_number (3), attrs); | |
8933 | ASET (this_spec, 1, this_aliases); | |
8934 | ASET (this_spec, 2, this_eol_type); | |
8935 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
8936 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
8937 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
8938 | if (NILP (val)) | |
8939 | Vcoding_system_alist | |
8940 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
8941 | Vcoding_system_alist); | |
1397dc18 | 8942 | } |
d46c5b12 | 8943 | } |
4ed46869 | 8944 | |
df7492f9 KH |
8945 | spec_vec = Fmake_vector (make_number (3), attrs); |
8946 | ASET (spec_vec, 1, aliases); | |
8947 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 8948 | |
df7492f9 KH |
8949 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
8950 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
8951 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
8952 | if (NILP (val)) | |
8953 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
8954 | Vcoding_system_alist); | |
48b0f3ae | 8955 | |
df7492f9 KH |
8956 | { |
8957 | int id = coding_categories[category].id; | |
48b0f3ae | 8958 | |
df7492f9 KH |
8959 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
8960 | setup_coding_system (name, &coding_categories[category]); | |
8961 | } | |
48b0f3ae | 8962 | |
d46c5b12 | 8963 | return Qnil; |
48b0f3ae | 8964 | |
df7492f9 KH |
8965 | short_args: |
8966 | return Fsignal (Qwrong_number_of_arguments, | |
8967 | Fcons (intern ("define-coding-system-internal"), | |
8968 | make_number (nargs))); | |
d46c5b12 | 8969 | } |
4ed46869 | 8970 | |
d6925f38 | 8971 | |
a6f87d34 KH |
8972 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
8973 | 3, 3, 0, | |
8974 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
8975 | (coding_system, prop, val) | |
8976 | Lisp_Object coding_system, prop, val; | |
8977 | { | |
3dbe7859 | 8978 | Lisp_Object spec, attrs; |
a6f87d34 KH |
8979 | |
8980 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
8981 | attrs = AREF (spec, 0); | |
8982 | if (EQ (prop, QCmnemonic)) | |
8983 | { | |
8984 | if (! STRINGP (val)) | |
8985 | CHECK_CHARACTER (val); | |
8986 | CODING_ATTR_MNEMONIC (attrs) = val; | |
8987 | } | |
8988 | else if (EQ (prop, QCdefalut_char)) | |
8989 | { | |
8990 | if (NILP (val)) | |
8991 | val = make_number (' '); | |
8992 | else | |
8993 | CHECK_CHARACTER (val); | |
8994 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
8995 | } | |
8996 | else if (EQ (prop, QCdecode_translation_table)) | |
8997 | { | |
8998 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
8999 | CHECK_SYMBOL (val); | |
9000 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
9001 | } | |
9002 | else if (EQ (prop, QCencode_translation_table)) | |
9003 | { | |
9004 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
9005 | CHECK_SYMBOL (val); | |
9006 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
9007 | } | |
9008 | else if (EQ (prop, QCpost_read_conversion)) | |
9009 | { | |
9010 | CHECK_SYMBOL (val); | |
9011 | CODING_ATTR_POST_READ (attrs) = val; | |
9012 | } | |
9013 | else if (EQ (prop, QCpre_write_conversion)) | |
9014 | { | |
9015 | CHECK_SYMBOL (val); | |
9016 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
9017 | } | |
35befdaa KH |
9018 | else if (EQ (prop, QCascii_compatible_p)) |
9019 | { | |
9020 | CODING_ATTR_ASCII_COMPAT (attrs) = val; | |
9021 | } | |
a6f87d34 KH |
9022 | |
9023 | CODING_ATTR_PLIST (attrs) | |
9024 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
9025 | return val; | |
9026 | } | |
9027 | ||
9028 | ||
df7492f9 KH |
9029 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
9030 | Sdefine_coding_system_alias, 2, 2, 0, | |
9031 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
9032 | (alias, coding_system) | |
9033 | Lisp_Object alias, coding_system; | |
66cfb530 | 9034 | { |
583f71ca | 9035 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 9036 | |
df7492f9 KH |
9037 | CHECK_SYMBOL (alias); |
9038 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9039 | aliases = AREF (spec, 1); | |
d6925f38 KH |
9040 | /* ALISES should be a list of length more than zero, and the first |
9041 | element is a base coding system. Append ALIAS at the tail of the | |
9042 | list. */ | |
df7492f9 KH |
9043 | while (!NILP (XCDR (aliases))) |
9044 | aliases = XCDR (aliases); | |
8f924df7 | 9045 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 9046 | |
df7492f9 KH |
9047 | eol_type = AREF (spec, 2); |
9048 | if (VECTORP (eol_type)) | |
4ed46869 | 9049 | { |
df7492f9 KH |
9050 | Lisp_Object subsidiaries; |
9051 | int i; | |
4ed46869 | 9052 | |
df7492f9 KH |
9053 | subsidiaries = make_subsidiaries (alias); |
9054 | for (i = 0; i < 3; i++) | |
9055 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
9056 | AREF (eol_type, i)); | |
4ed46869 | 9057 | } |
df7492f9 KH |
9058 | |
9059 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 9060 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
9061 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
9062 | if (NILP (val)) | |
9063 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
9064 | Vcoding_system_alist); | |
66cfb530 | 9065 | |
4ed46869 KH |
9066 | return Qnil; |
9067 | } | |
9068 | ||
df7492f9 KH |
9069 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
9070 | 1, 1, 0, | |
9071 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 9072 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
9073 | (coding_system) |
9074 | Lisp_Object coding_system; | |
d46c5b12 | 9075 | { |
df7492f9 | 9076 | Lisp_Object spec, attrs; |
d46c5b12 | 9077 | |
df7492f9 KH |
9078 | if (NILP (coding_system)) |
9079 | return (Qno_conversion); | |
9080 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9081 | attrs = AREF (spec, 0); | |
9082 | return CODING_ATTR_BASE_NAME (attrs); | |
9083 | } | |
1397dc18 | 9084 | |
df7492f9 KH |
9085 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
9086 | 1, 1, 0, | |
9087 | doc: "Return the property list of CODING-SYSTEM.") | |
9088 | (coding_system) | |
9089 | Lisp_Object coding_system; | |
9090 | { | |
9091 | Lisp_Object spec, attrs; | |
1397dc18 | 9092 | |
df7492f9 KH |
9093 | if (NILP (coding_system)) |
9094 | coding_system = Qno_conversion; | |
9095 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9096 | attrs = AREF (spec, 0); | |
9097 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
9098 | } |
9099 | ||
df7492f9 KH |
9100 | |
9101 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
9102 | 1, 1, 0, | |
da7db224 | 9103 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
9104 | (coding_system) |
9105 | Lisp_Object coding_system; | |
66cfb530 | 9106 | { |
df7492f9 | 9107 | Lisp_Object spec; |
84d60297 | 9108 | |
df7492f9 KH |
9109 | if (NILP (coding_system)) |
9110 | coding_system = Qno_conversion; | |
9111 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 9112 | return AREF (spec, 1); |
df7492f9 | 9113 | } |
66cfb530 | 9114 | |
df7492f9 KH |
9115 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
9116 | Scoding_system_eol_type, 1, 1, 0, | |
9117 | doc: /* Return eol-type of CODING-SYSTEM. | |
9118 | An eol-type is integer 0, 1, 2, or a vector of coding systems. | |
66cfb530 | 9119 | |
df7492f9 KH |
9120 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
9121 | and CR respectively. | |
66cfb530 | 9122 | |
df7492f9 KH |
9123 | A vector value indicates that a format of end-of-line should be |
9124 | detected automatically. Nth element of the vector is the subsidiary | |
9125 | coding system whose eol-type is N. */) | |
6b89e3aa KH |
9126 | (coding_system) |
9127 | Lisp_Object coding_system; | |
9128 | { | |
df7492f9 KH |
9129 | Lisp_Object spec, eol_type; |
9130 | int n; | |
6b89e3aa | 9131 | |
df7492f9 KH |
9132 | if (NILP (coding_system)) |
9133 | coding_system = Qno_conversion; | |
9134 | if (! CODING_SYSTEM_P (coding_system)) | |
9135 | return Qnil; | |
9136 | spec = CODING_SYSTEM_SPEC (coding_system); | |
9137 | eol_type = AREF (spec, 2); | |
9138 | if (VECTORP (eol_type)) | |
9139 | return Fcopy_sequence (eol_type); | |
9140 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
9141 | return make_number (n); | |
6b89e3aa KH |
9142 | } |
9143 | ||
4ed46869 KH |
9144 | #endif /* emacs */ |
9145 | ||
9146 | \f | |
1397dc18 | 9147 | /*** 9. Post-amble ***/ |
4ed46869 | 9148 | |
dfcf069d | 9149 | void |
4ed46869 KH |
9150 | init_coding_once () |
9151 | { | |
9152 | int i; | |
9153 | ||
df7492f9 KH |
9154 | for (i = 0; i < coding_category_max; i++) |
9155 | { | |
9156 | coding_categories[i].id = -1; | |
9157 | coding_priorities[i] = i; | |
9158 | } | |
4ed46869 KH |
9159 | |
9160 | /* ISO2022 specific initialize routine. */ | |
9161 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 9162 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
9163 | for (i = 0x21; i < 0x7F; i++) |
9164 | iso_code_class[i] = ISO_graphic_plane_0; | |
9165 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 9166 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
9167 | for (i = 0xA1; i < 0xFF; i++) |
9168 | iso_code_class[i] = ISO_graphic_plane_1; | |
9169 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
9170 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
9171 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
9172 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
9173 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
9174 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
9175 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
9176 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
9177 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
9178 | ||
df7492f9 KH |
9179 | for (i = 0; i < 256; i++) |
9180 | { | |
9181 | emacs_mule_bytes[i] = 1; | |
9182 | } | |
7c78e542 KH |
9183 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
9184 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
9185 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
9186 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
9187 | } |
9188 | ||
9189 | #ifdef emacs | |
9190 | ||
dfcf069d | 9191 | void |
e0e989f6 KH |
9192 | syms_of_coding () |
9193 | { | |
df7492f9 | 9194 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
9195 | { |
9196 | Lisp_Object args[2]; | |
9197 | args[0] = QCtest; | |
9198 | args[1] = Qeq; | |
9199 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
9200 | } | |
df7492f9 KH |
9201 | |
9202 | staticpro (&Vsjis_coding_system); | |
9203 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 9204 | |
df7492f9 KH |
9205 | staticpro (&Vbig5_coding_system); |
9206 | Vbig5_coding_system = Qnil; | |
9207 | ||
24a73b0a KH |
9208 | staticpro (&Vcode_conversion_reused_workbuf); |
9209 | Vcode_conversion_reused_workbuf = Qnil; | |
9210 | ||
9211 | staticpro (&Vcode_conversion_workbuf_name); | |
9212 | Vcode_conversion_workbuf_name = build_string (" *code-conversion-work*"); | |
e0e989f6 | 9213 | |
24a73b0a | 9214 | reused_workbuf_in_use = 0; |
df7492f9 KH |
9215 | |
9216 | DEFSYM (Qcharset, "charset"); | |
9217 | DEFSYM (Qtarget_idx, "target-idx"); | |
9218 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
9219 | Fset (Qcoding_system_history, Qnil); |
9220 | ||
9ce27fde | 9221 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 9222 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 9223 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
9224 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
9225 | ||
df7492f9 | 9226 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 9227 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
9228 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
9229 | ||
df7492f9 | 9230 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 9231 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9232 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
9233 | ||
df7492f9 | 9234 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 9235 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
9236 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
9237 | ||
df7492f9 | 9238 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 9239 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
9240 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
9241 | ||
df7492f9 KH |
9242 | DEFSYM (Qcoding_system, "coding-system"); |
9243 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 9244 | |
df7492f9 KH |
9245 | DEFSYM (Qeol_type, "eol-type"); |
9246 | DEFSYM (Qunix, "unix"); | |
9247 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 9248 | |
df7492f9 KH |
9249 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
9250 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
9251 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
9252 | DEFSYM (Qdefault_char, "default-char"); | |
9253 | DEFSYM (Qundecided, "undecided"); | |
9254 | DEFSYM (Qno_conversion, "no-conversion"); | |
9255 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 9256 | |
df7492f9 | 9257 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 9258 | |
df7492f9 | 9259 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 9260 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 9261 | |
df7492f9 | 9262 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
9263 | DEFSYM (Qbig, "big"); |
9264 | DEFSYM (Qlittle, "little"); | |
27901516 | 9265 | |
df7492f9 KH |
9266 | DEFSYM (Qshift_jis, "shift-jis"); |
9267 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 9268 | |
df7492f9 | 9269 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 9270 | |
df7492f9 | 9271 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 KH |
9272 | Fput (Qcoding_system_error, Qerror_conditions, |
9273 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
9274 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 9275 | build_string ("Invalid coding system")); |
4ed46869 | 9276 | |
05e6f5dc KH |
9277 | /* Intern this now in case it isn't already done. |
9278 | Setting this variable twice is harmless. | |
9279 | But don't staticpro it here--that is done in alloc.c. */ | |
9280 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
70c22245 | 9281 | |
df7492f9 | 9282 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 9283 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
9284 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
9285 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
9286 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 9287 | |
df7492f9 | 9288 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 9289 | |
df7492f9 | 9290 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 9291 | |
01378f49 | 9292 | DEFSYM (QCcategory, ":category"); |
a6f87d34 KH |
9293 | DEFSYM (QCmnemonic, ":mnemonic"); |
9294 | DEFSYM (QCdefalut_char, ":default-char"); | |
9295 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); | |
9296 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
9297 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
9298 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 9299 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 9300 | |
df7492f9 KH |
9301 | Vcoding_category_table |
9302 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
9303 | staticpro (&Vcoding_category_table); | |
9304 | /* Followings are target of code detection. */ | |
9305 | ASET (Vcoding_category_table, coding_category_iso_7, | |
9306 | intern ("coding-category-iso-7")); | |
9307 | ASET (Vcoding_category_table, coding_category_iso_7_tight, | |
9308 | intern ("coding-category-iso-7-tight")); | |
9309 | ASET (Vcoding_category_table, coding_category_iso_8_1, | |
9310 | intern ("coding-category-iso-8-1")); | |
9311 | ASET (Vcoding_category_table, coding_category_iso_8_2, | |
9312 | intern ("coding-category-iso-8-2")); | |
9313 | ASET (Vcoding_category_table, coding_category_iso_7_else, | |
9314 | intern ("coding-category-iso-7-else")); | |
9315 | ASET (Vcoding_category_table, coding_category_iso_8_else, | |
9316 | intern ("coding-category-iso-8-else")); | |
9317 | ASET (Vcoding_category_table, coding_category_utf_8, | |
9318 | intern ("coding-category-utf-8")); | |
9319 | ASET (Vcoding_category_table, coding_category_utf_16_be, | |
9320 | intern ("coding-category-utf-16-be")); | |
ff563fce KH |
9321 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
9322 | intern ("coding-category-utf-16-auto")); | |
df7492f9 KH |
9323 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
9324 | intern ("coding-category-utf-16-le")); | |
9325 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, | |
9326 | intern ("coding-category-utf-16-be-nosig")); | |
9327 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, | |
9328 | intern ("coding-category-utf-16-le-nosig")); | |
9329 | ASET (Vcoding_category_table, coding_category_charset, | |
9330 | intern ("coding-category-charset")); | |
9331 | ASET (Vcoding_category_table, coding_category_sjis, | |
9332 | intern ("coding-category-sjis")); | |
9333 | ASET (Vcoding_category_table, coding_category_big5, | |
9334 | intern ("coding-category-big5")); | |
9335 | ASET (Vcoding_category_table, coding_category_ccl, | |
9336 | intern ("coding-category-ccl")); | |
9337 | ASET (Vcoding_category_table, coding_category_emacs_mule, | |
9338 | intern ("coding-category-emacs-mule")); | |
9339 | /* Followings are NOT target of code detection. */ | |
9340 | ASET (Vcoding_category_table, coding_category_raw_text, | |
9341 | intern ("coding-category-raw-text")); | |
9342 | ASET (Vcoding_category_table, coding_category_undecided, | |
9343 | intern ("coding-category-undecided")); | |
ecf488bc | 9344 | |
065e3595 KH |
9345 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
9346 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
9347 | DEFSYM (Qinvalid_source, "invalid-source"); | |
9348 | DEFSYM (Qinterrupted, "interrupted"); | |
9349 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 9350 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 9351 | |
4ed46869 KH |
9352 | defsubr (&Scoding_system_p); |
9353 | defsubr (&Sread_coding_system); | |
9354 | defsubr (&Sread_non_nil_coding_system); | |
9355 | defsubr (&Scheck_coding_system); | |
9356 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 9357 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 9358 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 9359 | defsubr (&Sunencodable_char_position); |
df7492f9 | 9360 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
9361 | defsubr (&Sdecode_coding_region); |
9362 | defsubr (&Sencode_coding_region); | |
9363 | defsubr (&Sdecode_coding_string); | |
9364 | defsubr (&Sencode_coding_string); | |
9365 | defsubr (&Sdecode_sjis_char); | |
9366 | defsubr (&Sencode_sjis_char); | |
9367 | defsubr (&Sdecode_big5_char); | |
9368 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 9369 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 9370 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 9371 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 9372 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 9373 | defsubr (&Skeyboard_coding_system); |
a5d301df | 9374 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 9375 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 9376 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 9377 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 9378 | defsubr (&Scoding_system_put); |
df7492f9 KH |
9379 | defsubr (&Scoding_system_base); |
9380 | defsubr (&Scoding_system_plist); | |
9381 | defsubr (&Scoding_system_aliases); | |
9382 | defsubr (&Scoding_system_eol_type); | |
9383 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 9384 | |
4608c386 | 9385 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
9386 | doc: /* List of coding systems. |
9387 | ||
9388 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 9389 | updated by the functions `define-coding-system' and |
48b0f3ae | 9390 | `define-coding-system-alias'. */); |
4608c386 KH |
9391 | Vcoding_system_list = Qnil; |
9392 | ||
9393 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
9394 | doc: /* Alist of coding system names. |
9395 | Each element is one element list of coding system name. | |
9396 | This variable is given to `completing-read' as TABLE argument. | |
9397 | ||
9398 | Do not alter the value of this variable manually. This variable should be | |
9399 | updated by the functions `make-coding-system' and | |
9400 | `define-coding-system-alias'. */); | |
4608c386 KH |
9401 | Vcoding_system_alist = Qnil; |
9402 | ||
4ed46869 | 9403 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
9404 | doc: /* List of coding-categories (symbols) ordered by priority. |
9405 | ||
9406 | On detecting a coding system, Emacs tries code detection algorithms | |
9407 | associated with each coding-category one by one in this order. When | |
9408 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
9409 | system bound to the corresponding coding-category is selected. |
9410 | ||
42205607 | 9411 | Don't modify this variable directly, but use `set-coding-priority'. */); |
4ed46869 KH |
9412 | { |
9413 | int i; | |
9414 | ||
9415 | Vcoding_category_list = Qnil; | |
df7492f9 | 9416 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 9417 | Vcoding_category_list |
d46c5b12 KH |
9418 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
9419 | Vcoding_category_list); | |
4ed46869 KH |
9420 | } |
9421 | ||
9422 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
9423 | doc: /* Specify the coding system for read operations. |
9424 | It is useful to bind this variable with `let', but do not set it globally. | |
9425 | If the value is a coding system, it is used for decoding on read operation. | |
9426 | If not, an appropriate element is used from one of the coding system alists: | |
9427 | There are three such tables, `file-coding-system-alist', | |
9428 | `process-coding-system-alist', and `network-coding-system-alist'. */); | |
4ed46869 KH |
9429 | Vcoding_system_for_read = Qnil; |
9430 | ||
9431 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
9432 | doc: /* Specify the coding system for write operations. |
9433 | Programs bind this variable with `let', but you should not set it globally. | |
9434 | If the value is a coding system, it is used for encoding of output, | |
9435 | when writing it to a file and when sending it to a file or subprocess. | |
9436 | ||
9437 | If this does not specify a coding system, an appropriate element | |
9438 | is used from one of the coding system alists: | |
9439 | There are three such tables, `file-coding-system-alist', | |
9440 | `process-coding-system-alist', and `network-coding-system-alist'. | |
9441 | For output to files, if the above procedure does not specify a coding system, | |
9442 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
9443 | Vcoding_system_for_write = Qnil; |
9444 | ||
9445 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
9446 | doc: /* |
9447 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
9448 | Vlast_coding_system_used = Qnil; |
9449 | ||
065e3595 KH |
9450 | DEFVAR_LISP ("last-code-conversion-error", &Vlast_code_conversion_error, |
9451 | doc: /* | |
9452 | Error status of the last code conversion. | |
9453 | ||
9454 | When an error was detected in the last code conversion, this variable | |
9455 | is set to one of the following symbols. | |
9456 | `insufficient-source' | |
9457 | `inconsistent-eol' | |
9458 | `invalid-source' | |
9459 | `interrupted' | |
9460 | `insufficient-memory' | |
9461 | When no error was detected, the value doesn't change. So, to check | |
9462 | the error status of a code conversion by this variable, you must | |
9463 | explicitly set this variable to nil before performing code | |
9464 | conversion. */); | |
9465 | Vlast_code_conversion_error = Qnil; | |
9466 | ||
9ce27fde | 9467 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
9468 | doc: /* |
9469 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
9470 | See info node `Coding Systems' and info node `Text and Binary' concerning |
9471 | such conversion. */); | |
9ce27fde KH |
9472 | inhibit_eol_conversion = 0; |
9473 | ||
ed29121d | 9474 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
9475 | doc: /* |
9476 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
9477 | Bind it to t if the process output is to be treated as if it were a file |
9478 | read from some filesystem. */); | |
ed29121d EZ |
9479 | inherit_process_coding_system = 0; |
9480 | ||
02ba4723 | 9481 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
9482 | doc: /* |
9483 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
9484 | The format is ((PATTERN . VAL) ...), |
9485 | where PATTERN is a regular expression matching a file name, | |
9486 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9487 | If VAL is a coding system, it is used for both decoding and encoding | |
9488 | the file contents. | |
9489 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9490 | and the cdr part is used for encoding. | |
9491 | If VAL is a function symbol, the function must return a coding system | |
0192762c DL |
9492 | or a cons of coding systems which are used as above. The function gets |
9493 | the arguments with which `find-operation-coding-systems' was called. | |
48b0f3ae PJ |
9494 | |
9495 | See also the function `find-operation-coding-system' | |
9496 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
9497 | Vfile_coding_system_alist = Qnil; |
9498 | ||
9499 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
9500 | doc: /* |
9501 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
9502 | The format is ((PATTERN . VAL) ...), |
9503 | where PATTERN is a regular expression matching a program name, | |
9504 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9505 | If VAL is a coding system, it is used for both decoding what received | |
9506 | from the program and encoding what sent to the program. | |
9507 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9508 | and the cdr part is used for encoding. | |
9509 | If VAL is a function symbol, the function must return a coding system | |
9510 | or a cons of coding systems which are used as above. | |
9511 | ||
9512 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
9513 | Vprocess_coding_system_alist = Qnil; |
9514 | ||
9515 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
9516 | doc: /* |
9517 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
9518 | The format is ((PATTERN . VAL) ...), |
9519 | where PATTERN is a regular expression matching a network service name | |
9520 | or is a port number to connect to, | |
9521 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
9522 | If VAL is a coding system, it is used for both decoding what received | |
9523 | from the network stream and encoding what sent to the network stream. | |
9524 | If VAL is a cons of coding systems, the car part is used for decoding, | |
9525 | and the cdr part is used for encoding. | |
9526 | If VAL is a function symbol, the function must return a coding system | |
9527 | or a cons of coding systems which are used as above. | |
9528 | ||
9529 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 9530 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 9531 | |
68c45bf0 | 9532 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
9533 | doc: /* Coding system to use with system messages. |
9534 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
9535 | Vlocale_coding_system = Qnil; |
9536 | ||
005f0d35 | 9537 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 9538 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
9539 | doc: /* |
9540 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
7722baf9 | 9541 | eol_mnemonic_unix = build_string (":"); |
4ed46869 | 9542 | |
7722baf9 | 9543 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
9544 | doc: /* |
9545 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
7722baf9 | 9546 | eol_mnemonic_dos = build_string ("\\"); |
4ed46869 | 9547 | |
7722baf9 | 9548 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
9549 | doc: /* |
9550 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
7722baf9 | 9551 | eol_mnemonic_mac = build_string ("/"); |
4ed46869 | 9552 | |
7722baf9 | 9553 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
9554 | doc: /* |
9555 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
7722baf9 | 9556 | eol_mnemonic_undecided = build_string (":"); |
4ed46869 | 9557 | |
84fbb8a0 | 9558 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
9559 | doc: /* |
9560 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 9561 | Venable_character_translation = Qt; |
bdd9fb48 | 9562 | |
f967223b | 9563 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
9564 | &Vstandard_translation_table_for_decode, |
9565 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 9566 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 9567 | |
f967223b | 9568 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
9569 | &Vstandard_translation_table_for_encode, |
9570 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 9571 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 9572 | |
df7492f9 | 9573 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
9574 | doc: /* Alist of charsets vs revision numbers. |
9575 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
9576 | designate it with the escape sequence identifying revision (cdr part |
9577 | of the element). */); | |
9578 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
9579 | |
9580 | DEFVAR_LISP ("default-process-coding-system", | |
9581 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
9582 | doc: /* Cons of coding systems used for process I/O by default. |
9583 | The car part is used for decoding a process output, | |
9584 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 9585 | Vdefault_process_coding_system = Qnil; |
c4825358 | 9586 | |
3f003981 | 9587 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
9588 | doc: /* |
9589 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
9590 | This is a vector of length 256. |
9591 | If Nth element is non-nil, the existence of code N in a file | |
9592 | \(or output of subprocess) doesn't prevent it to be detected as | |
9593 | a coding system of ISO 2022 variant which has a flag | |
9594 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
9595 | or reading output of a subprocess. | |
9596 | Only 128th through 159th elements has a meaning. */); | |
3f003981 | 9597 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
9598 | |
9599 | DEFVAR_LISP ("select-safe-coding-system-function", | |
9600 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
9601 | doc: /* |
9602 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
9603 | |
9604 | If set, this function is called to force a user to select a proper | |
9605 | coding system which can encode the text in the case that a default | |
9606 | coding system used in each operation can't encode the text. | |
9607 | ||
9608 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
9609 | Vselect_safe_coding_system_function = Qnil; |
9610 | ||
5d5bf4d8 KH |
9611 | DEFVAR_BOOL ("coding-system-require-warning", |
9612 | &coding_system_require_warning, | |
9613 | doc: /* Internal use only. | |
6b89e3aa KH |
9614 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
9615 | called even if `coding-system-for-write' is non-nil. The command | |
9616 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
9617 | coding_system_require_warning = 0; |
9618 | ||
9619 | ||
22ab2303 | 9620 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 9621 | &inhibit_iso_escape_detection, |
df7492f9 KH |
9622 | doc: /* |
9623 | If non-nil, Emacs ignores ISO2022's escape sequence on code detection. | |
48b0f3ae PJ |
9624 | |
9625 | By default, on reading a file, Emacs tries to detect how the text is | |
9626 | encoded. This code detection is sensitive to escape sequences. If | |
9627 | the sequence is valid as ISO2022, the code is determined as one of | |
9628 | the ISO2022 encodings, and the file is decoded by the corresponding | |
9629 | coding system (e.g. `iso-2022-7bit'). | |
9630 | ||
9631 | However, there may be a case that you want to read escape sequences in | |
9632 | a file as is. In such a case, you can set this variable to non-nil. | |
9633 | Then, as the code detection ignores any escape sequences, no file is | |
9634 | detected as encoded in some ISO2022 encoding. The result is that all | |
9635 | escape sequences become visible in a buffer. | |
9636 | ||
9637 | The default value is nil, and it is strongly recommended not to change | |
9638 | it. That is because many Emacs Lisp source files that contain | |
9639 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
9640 | in Emacs's distribution, and they won't be decoded correctly on | |
9641 | reading if you suppress escape sequence detection. | |
9642 | ||
9643 | The other way to read escape sequences in a file without decoding is | |
9644 | to explicitly specify some coding system that doesn't use ISO2022's | |
9645 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); | |
74383408 | 9646 | inhibit_iso_escape_detection = 0; |
002fdb44 DL |
9647 | |
9648 | DEFVAR_LISP ("translation-table-for-input", &Vtranslation_table_for_input, | |
15c8f9d1 DL |
9649 | doc: /* Char table for translating self-inserting characters. |
9650 | This is applied to the result of input methods, not their input. See also | |
9651 | `keyboard-translate-table'. */); | |
002fdb44 | 9652 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 9653 | |
2c78b7e1 KH |
9654 | { |
9655 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 9656 | Lisp_Object plist[16]; |
2c78b7e1 KH |
9657 | int i; |
9658 | ||
9659 | for (i = 0; i < coding_arg_max; i++) | |
9660 | args[i] = Qnil; | |
9661 | ||
9662 | plist[0] = intern (":name"); | |
9663 | plist[1] = args[coding_arg_name] = Qno_conversion; | |
9664 | plist[2] = intern (":mnemonic"); | |
9665 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); | |
9666 | plist[4] = intern (":coding-type"); | |
9667 | plist[5] = args[coding_arg_coding_type] = Qraw_text; | |
9668 | plist[6] = intern (":ascii-compatible-p"); | |
9669 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; | |
9670 | plist[8] = intern (":default-char"); | |
9671 | plist[9] = args[coding_arg_default_char] = make_number (0); | |
8f924df7 KH |
9672 | plist[10] = intern (":for-unibyte"); |
9673 | plist[11] = args[coding_arg_for_unibyte] = Qt; | |
9674 | plist[12] = intern (":docstring"); | |
9675 | plist[13] = build_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
9676 | \n\ |
9677 | When you visit a file with this coding, the file is read into a\n\ | |
9678 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
9679 | character."); | |
8f924df7 KH |
9680 | plist[14] = intern (":eol-type"); |
9681 | plist[15] = args[coding_arg_eol_type] = Qunix; | |
9682 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 9683 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
9684 | |
9685 | plist[1] = args[coding_arg_name] = Qundecided; | |
9686 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
9687 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
9688 | /* This is already set. | |
35befdaa | 9689 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
ae6f73fa KH |
9690 | plist[8] = intern (":charset-list"); |
9691 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); | |
9692 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
9693 | plist[13] = build_string ("No conversion on encoding, automatic conversion on decoding."); | |
9694 | plist[15] = args[coding_arg_eol_type] = Qnil; | |
9695 | args[coding_arg_plist] = Flist (16, plist); | |
9696 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
9697 | } |
9698 | ||
9699 | setup_coding_system (Qno_conversion, &keyboard_coding); | |
ae6f73fa | 9700 | setup_coding_system (Qundecided, &terminal_coding); |
2c78b7e1 | 9701 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
9702 | |
9703 | { | |
9704 | int i; | |
9705 | ||
9706 | for (i = 0; i < coding_category_max; i++) | |
9707 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
9708 | } | |
4ed46869 KH |
9709 | } |
9710 | ||
68c45bf0 PE |
9711 | char * |
9712 | emacs_strerror (error_number) | |
9713 | int error_number; | |
9714 | { | |
9715 | char *str; | |
9716 | ||
ca9c0567 | 9717 | synchronize_system_messages_locale (); |
68c45bf0 PE |
9718 | str = strerror (error_number); |
9719 | ||
9720 | if (! NILP (Vlocale_coding_system)) | |
9721 | { | |
9722 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
9723 | Vlocale_coding_system, | |
9724 | 0); | |
d5db4077 | 9725 | str = (char *) SDATA (dec); |
68c45bf0 PE |
9726 | } |
9727 | ||
9728 | return str; | |
9729 | } | |
9730 | ||
4ed46869 | 9731 | #endif /* emacs */ |
9ffd559c KH |
9732 | |
9733 | /* arch-tag: 3a3a2b01-5ff6-4071-9afe-f5b808d9229d | |
9734 | (do not change this comment) */ |