Commit | Line | Data |
---|---|---|
4ed46869 | 1 | /* Coding system handler (conversion, detection, and etc). |
4a2f9c6a | 2 | Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. |
203cb916 | 3 | Licensed to the Free Software Foundation. |
70ad9fc4 | 4 | Copyright (C) 2001 Free Software Foundation, Inc. |
df7492f9 KH |
5 | Copyright (C) 2001, 2002 |
6 | National Institute of Advanced Industrial Science and Technology (AIST) | |
7 | Registration Number H13PRO009 | |
4ed46869 | 8 | |
369314dc KH |
9 | This file is part of GNU Emacs. |
10 | ||
11 | GNU Emacs is free software; you can redistribute it and/or modify | |
12 | it under the terms of the GNU General Public License as published by | |
13 | the Free Software Foundation; either version 2, or (at your option) | |
14 | any later version. | |
4ed46869 | 15 | |
369314dc KH |
16 | GNU Emacs is distributed in the hope that it will be useful, |
17 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
18 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
19 | GNU General Public License for more details. | |
4ed46869 | 20 | |
369314dc KH |
21 | You should have received a copy of the GNU General Public License |
22 | along with GNU Emacs; see the file COPYING. If not, write to | |
23 | the Free Software Foundation, Inc., 59 Temple Place - Suite 330, | |
24 | Boston, MA 02111-1307, USA. */ | |
4ed46869 KH |
25 | |
26 | /*** TABLE OF CONTENTS *** | |
27 | ||
b73bfc1c | 28 | 0. General comments |
4ed46869 | 29 | 1. Preamble |
df7492f9 KH |
30 | 2. Emacs' internal format (emacs-utf-8) handlers |
31 | 3. UTF-8 handlers | |
32 | 4. UTF-16 handlers | |
33 | 5. Charset-base coding systems handlers | |
34 | 6. emacs-mule (old Emacs' internal format) handlers | |
35 | 7. ISO2022 handlers | |
36 | 8. Shift-JIS and BIG5 handlers | |
37 | 9. CCL handlers | |
38 | 10. C library functions | |
39 | 11. Emacs Lisp library functions | |
40 | 12. Postamble | |
4ed46869 KH |
41 | |
42 | */ | |
43 | ||
df7492f9 | 44 | /*** 0. General comments *** |
b73bfc1c KH |
45 | |
46 | ||
df7492f9 | 47 | CODING SYSTEM |
4ed46869 | 48 | |
5bad0796 DL |
49 | A coding system is an object for an encoding mechanism that contains |
50 | information about how to convert byte sequences to character | |
e19c3639 KH |
51 | sequences and vice versa. When we say "decode", it means converting |
52 | a byte sequence of a specific coding system into a character | |
53 | sequence that is represented by Emacs' internal coding system | |
54 | `emacs-utf-8', and when we say "encode", it means converting a | |
55 | character sequence of emacs-utf-8 to a byte sequence of a specific | |
56 | coding system. | |
57 | ||
58 | In Emacs Lisp, a coding system is represented by a Lisp symbol. In | |
59 | C level, a coding system is represented by a vector of attributes | |
5bad0796 | 60 | stored in the hash table Vcharset_hash_table. The conversion from |
e19c3639 KH |
61 | coding system symbol to attributes vector is done by looking up |
62 | Vcharset_hash_table by the symbol. | |
63 | ||
64 | Coding systems are classified into the following types depending on | |
5bad0796 | 65 | the encoding mechanism. Here's a brief description of the types. |
df7492f9 KH |
66 | |
67 | o UTF-8 | |
68 | ||
69 | o UTF-16 | |
70 | ||
71 | o Charset-base coding system | |
72 | ||
73 | A coding system defined by one or more (coded) character sets. | |
5bad0796 | 74 | Decoding and encoding are done by a code converter defined for each |
df7492f9 KH |
75 | character set. |
76 | ||
5bad0796 | 77 | o Old Emacs internal format (emacs-mule) |
df7492f9 | 78 | |
5bad0796 | 79 | The coding system adopted by old versions of Emacs (20 and 21). |
4ed46869 | 80 | |
df7492f9 | 81 | o ISO2022-base coding system |
93dec019 | 82 | |
df7492f9 KH |
83 | The most famous coding system for multiple character sets. X's |
84 | Compound Text, various EUCs (Extended Unix Code), and coding systems | |
85 | used in the Internet communication such as ISO-2022-JP are all | |
86 | variants of ISO2022. | |
87 | ||
88 | o SJIS (or Shift-JIS or MS-Kanji-Code) | |
89 | ||
4ed46869 KH |
90 | A coding system to encode character sets: ASCII, JISX0201, and |
91 | JISX0208. Widely used for PC's in Japan. Details are described in | |
df7492f9 | 92 | section 8. |
4ed46869 | 93 | |
df7492f9 | 94 | o BIG5 |
4ed46869 | 95 | |
df7492f9 KH |
96 | A coding system to encode character sets: ASCII and Big5. Widely |
97 | used by Chinese (mainly in Taiwan and Hong Kong). Details are | |
98 | described in section 8. In this file, when we write "big5" (all | |
99 | lowercase), we mean the coding system, and when we write "Big5" | |
100 | (capitalized), we mean the character set. | |
4ed46869 | 101 | |
df7492f9 | 102 | o CCL |
27901516 | 103 | |
5bad0796 | 104 | If a user wants to decode/encode text encoded in a coding system |
df7492f9 KH |
105 | not listed above, he can supply a decoder and an encoder for it in |
106 | CCL (Code Conversion Language) programs. Emacs executes the CCL | |
107 | program while decoding/encoding. | |
27901516 | 108 | |
df7492f9 | 109 | o Raw-text |
4ed46869 | 110 | |
df7492f9 | 111 | A coding system for a text containing raw eight-bit data. Emacs |
5bad0796 | 112 | treats each byte of source text as a character (except for |
df7492f9 | 113 | end-of-line conversion). |
4ed46869 | 114 | |
df7492f9 KH |
115 | o No-conversion |
116 | ||
117 | Like raw text, but don't do end-of-line conversion. | |
4ed46869 | 118 | |
4ed46869 | 119 | |
df7492f9 | 120 | END-OF-LINE FORMAT |
4ed46869 | 121 | |
5bad0796 | 122 | How text end-of-line is encoded depends on operating system. For |
df7492f9 | 123 | instance, Unix's format is just one byte of LF (line-feed) code, |
f4dee582 | 124 | whereas DOS's format is two-byte sequence of `carriage-return' and |
d46c5b12 KH |
125 | `line-feed' codes. MacOS's format is usually one byte of |
126 | `carriage-return'. | |
4ed46869 | 127 | |
5bad0796 | 128 | Since text character encoding and end-of-line encoding are |
df7492f9 KH |
129 | independent, any coding system described above can take any format |
130 | of end-of-line (except for no-conversion). | |
4ed46869 | 131 | |
e19c3639 KH |
132 | STRUCT CODING_SYSTEM |
133 | ||
134 | Before using a coding system for code conversion (i.e. decoding and | |
135 | encoding), we setup a structure of type `struct coding_system'. | |
136 | This structure keeps various information about a specific code | |
5bad0796 | 137 | conversion (e.g. the location of source and destination data). |
e19c3639 | 138 | |
4ed46869 KH |
139 | */ |
140 | ||
df7492f9 KH |
141 | /* COMMON MACROS */ |
142 | ||
143 | ||
4ed46869 KH |
144 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
145 | ||
df7492f9 KH |
146 | These functions check if a byte sequence specified as a source in |
147 | CODING conforms to the format of XXX. Return 1 if the data contains | |
148 | a byte sequence which can be decoded into non-ASCII characters by | |
149 | the coding system. Otherwize (i.e. the data contains only ASCII | |
150 | characters or invalid sequence) return 0. | |
151 | ||
152 | It also resets some bits of an integer pointed by MASK. The macros | |
153 | CATEGORY_MASK_XXX specifies each bit of this integer. | |
154 | ||
155 | Below is the template of these functions. */ | |
156 | ||
4ed46869 | 157 | #if 0 |
df7492f9 KH |
158 | static int |
159 | detect_coding_XXX (coding, mask) | |
160 | struct coding_system *coding; | |
161 | int *mask; | |
4ed46869 | 162 | { |
df7492f9 KH |
163 | unsigned char *src = coding->source; |
164 | unsigned char *src_end = coding->source + coding->src_bytes; | |
165 | int multibytep = coding->src_multibyte; | |
166 | int c; | |
167 | int found = 0; | |
168 | ...; | |
169 | ||
170 | while (1) | |
171 | { | |
172 | /* Get one byte from the source. If the souce is exausted, jump | |
173 | to no_more_source:. */ | |
174 | ONE_MORE_BYTE (c); | |
175 | /* Check if it conforms to XXX. If not, break the loop. */ | |
176 | } | |
177 | /* As the data is invalid for XXX, reset a proper bits. */ | |
178 | *mask &= ~CODING_CATEGORY_XXX; | |
179 | return 0; | |
180 | no_more_source: | |
181 | /* The source exausted. */ | |
182 | if (!found) | |
183 | /* ASCII characters only. */ | |
184 | return 0; | |
185 | /* Some data should be decoded into non-ASCII characters. */ | |
186 | *mask &= CODING_CATEGORY_XXX; | |
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 | { |
df7492f9 KH |
210 | unsigned char *src = coding->source + coding->consumed; |
211 | unsigned char *src_end = coding->source + coding->src_bytes; | |
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. */ | |
215 | unsigned char *src_base; | |
216 | /* A buffer to produce decoded characters. */ | |
217 | int *charbuf = coding->charbuf; | |
218 | int *charbuf_end = charbuf + coding->charbuf_size; | |
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" | |
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 KH |
312 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
313 | Lisp_Object Qutf_16_be_nosig, Qutf_16_be, Qutf_16_le_nosig, Qutf_16_le; | |
314 | Lisp_Object Qsignature, Qendian, Qbig, Qlittle; | |
bb0115a2 | 315 | Lisp_Object Qcoding_system_history; |
1397dc18 | 316 | Lisp_Object Qvalid_codes; |
4ed46869 KH |
317 | |
318 | extern Lisp_Object Qinsert_file_contents, Qwrite_region; | |
319 | Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument; | |
320 | Lisp_Object Qstart_process, Qopen_network_stream; | |
321 | Lisp_Object Qtarget_idx; | |
322 | ||
d46c5b12 KH |
323 | Lisp_Object Vselect_safe_coding_system_function; |
324 | ||
7722baf9 EZ |
325 | /* Mnemonic string for each format of end-of-line. */ |
326 | Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac; | |
327 | /* Mnemonic string to indicate format of end-of-line is not yet | |
4ed46869 | 328 | decided. */ |
7722baf9 | 329 | Lisp_Object eol_mnemonic_undecided; |
4ed46869 KH |
330 | |
331 | #ifdef emacs | |
332 | ||
4608c386 KH |
333 | Lisp_Object Vcoding_system_list, Vcoding_system_alist; |
334 | ||
335 | Lisp_Object Qcoding_system_p, Qcoding_system_error; | |
4ed46869 | 336 | |
d46c5b12 KH |
337 | /* Coding system emacs-mule and raw-text are for converting only |
338 | end-of-line format. */ | |
339 | Lisp_Object Qemacs_mule, Qraw_text; | |
9ce27fde | 340 | |
4ed46869 KH |
341 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
342 | routines by the following three variables. */ | |
343 | /* Coding-system for reading files and receiving data from process. */ | |
344 | Lisp_Object Vcoding_system_for_read; | |
345 | /* Coding-system for writing files and sending data to process. */ | |
346 | Lisp_Object Vcoding_system_for_write; | |
347 | /* Coding-system actually used in the latest I/O. */ | |
348 | Lisp_Object Vlast_coding_system_used; | |
349 | ||
c4825358 | 350 | /* A vector of length 256 which contains information about special |
94487c4e | 351 | Latin codes (especially for dealing with Microsoft codes). */ |
3f003981 | 352 | Lisp_Object Vlatin_extra_code_table; |
c4825358 | 353 | |
9ce27fde KH |
354 | /* Flag to inhibit code conversion of end-of-line format. */ |
355 | int inhibit_eol_conversion; | |
356 | ||
74383408 KH |
357 | /* Flag to inhibit ISO2022 escape sequence detection. */ |
358 | int inhibit_iso_escape_detection; | |
359 | ||
ed29121d EZ |
360 | /* Flag to make buffer-file-coding-system inherit from process-coding. */ |
361 | int inherit_process_coding_system; | |
362 | ||
c4825358 | 363 | /* Coding system to be used to encode text for terminal display. */ |
4ed46869 KH |
364 | struct coding_system terminal_coding; |
365 | ||
c4825358 KH |
366 | /* Coding system to be used to encode text for terminal display when |
367 | terminal coding system is nil. */ | |
368 | struct coding_system safe_terminal_coding; | |
369 | ||
370 | /* Coding system of what is sent from terminal keyboard. */ | |
4ed46869 KH |
371 | struct coding_system keyboard_coding; |
372 | ||
02ba4723 KH |
373 | Lisp_Object Vfile_coding_system_alist; |
374 | Lisp_Object Vprocess_coding_system_alist; | |
375 | Lisp_Object Vnetwork_coding_system_alist; | |
4ed46869 | 376 | |
68c45bf0 PE |
377 | Lisp_Object Vlocale_coding_system; |
378 | ||
4ed46869 KH |
379 | #endif /* emacs */ |
380 | ||
f967223b KH |
381 | /* Flag to tell if we look up translation table on character code |
382 | conversion. */ | |
84fbb8a0 | 383 | Lisp_Object Venable_character_translation; |
f967223b KH |
384 | /* Standard translation table to look up on decoding (reading). */ |
385 | Lisp_Object Vstandard_translation_table_for_decode; | |
386 | /* Standard translation table to look up on encoding (writing). */ | |
387 | Lisp_Object Vstandard_translation_table_for_encode; | |
84fbb8a0 | 388 | |
f967223b KH |
389 | Lisp_Object Qtranslation_table; |
390 | Lisp_Object Qtranslation_table_id; | |
391 | Lisp_Object Qtranslation_table_for_decode; | |
392 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 KH |
393 | |
394 | /* Alist of charsets vs revision number. */ | |
df7492f9 | 395 | static Lisp_Object Vcharset_revision_table; |
4ed46869 | 396 | |
02ba4723 KH |
397 | /* Default coding systems used for process I/O. */ |
398 | Lisp_Object Vdefault_process_coding_system; | |
399 | ||
b843d1ae KH |
400 | /* Global flag to tell that we can't call post-read-conversion and |
401 | pre-write-conversion functions. Usually the value is zero, but it | |
402 | is set to 1 temporarily while such functions are running. This is | |
403 | to avoid infinite recursive call. */ | |
404 | static int inhibit_pre_post_conversion; | |
405 | ||
df7492f9 KH |
406 | /* Two special coding systems. */ |
407 | Lisp_Object Vsjis_coding_system; | |
408 | Lisp_Object Vbig5_coding_system; | |
409 | ||
410 | ||
411 | static int detect_coding_utf_8 P_ ((struct coding_system *, int *)); | |
412 | static void decode_coding_utf_8 P_ ((struct coding_system *)); | |
413 | static int encode_coding_utf_8 P_ ((struct coding_system *)); | |
414 | ||
415 | static int detect_coding_utf_16 P_ ((struct coding_system *, int *)); | |
416 | static void decode_coding_utf_16 P_ ((struct coding_system *)); | |
417 | static int encode_coding_utf_16 P_ ((struct coding_system *)); | |
418 | ||
419 | static int detect_coding_iso_2022 P_ ((struct coding_system *, int *)); | |
420 | static void decode_coding_iso_2022 P_ ((struct coding_system *)); | |
421 | static int encode_coding_iso_2022 P_ ((struct coding_system *)); | |
422 | ||
423 | static int detect_coding_emacs_mule P_ ((struct coding_system *, int *)); | |
424 | static void decode_coding_emacs_mule P_ ((struct coding_system *)); | |
425 | static int encode_coding_emacs_mule P_ ((struct coding_system *)); | |
426 | ||
427 | static int detect_coding_sjis P_ ((struct coding_system *, int *)); | |
428 | static void decode_coding_sjis P_ ((struct coding_system *)); | |
429 | static int encode_coding_sjis P_ ((struct coding_system *)); | |
430 | ||
431 | static int detect_coding_big5 P_ ((struct coding_system *, int *)); | |
432 | static void decode_coding_big5 P_ ((struct coding_system *)); | |
433 | static int encode_coding_big5 P_ ((struct coding_system *)); | |
434 | ||
435 | static int detect_coding_ccl P_ ((struct coding_system *, int *)); | |
436 | static void decode_coding_ccl P_ ((struct coding_system *)); | |
437 | static int encode_coding_ccl P_ ((struct coding_system *)); | |
438 | ||
439 | static void decode_coding_raw_text P_ ((struct coding_system *)); | |
440 | static int encode_coding_raw_text P_ ((struct coding_system *)); | |
441 | ||
442 | ||
443 | /* ISO2022 section */ | |
444 | ||
445 | #define CODING_ISO_INITIAL(coding, reg) \ | |
446 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
447 | coding_attr_iso_initial), \ | |
448 | reg))) | |
449 | ||
450 | ||
451 | #define CODING_ISO_REQUEST(coding, charset_id) \ | |
452 | ((charset_id <= (coding)->max_charset_id \ | |
453 | ? (coding)->safe_charsets[charset_id] \ | |
454 | : -1)) | |
455 | ||
456 | ||
457 | #define CODING_ISO_FLAGS(coding) \ | |
458 | ((coding)->spec.iso_2022.flags) | |
459 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
460 | ((coding)->spec.iso_2022.current_designation[reg]) | |
461 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
462 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
463 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
464 | ((coding)->spec.iso_2022.single_shifting) | |
465 | #define CODING_ISO_BOL(coding) \ | |
466 | ((coding)->spec.iso_2022.bol) | |
467 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
468 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
469 | ||
470 | /* Control characters of ISO2022. */ | |
471 | /* code */ /* function */ | |
472 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
473 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
474 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
475 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
476 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
477 | #define ISO_CODE_ESC 0x1B /* escape */ | |
478 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
479 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
480 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
481 | ||
482 | /* All code (1-byte) of ISO2022 is classified into one of the | |
483 | followings. */ | |
484 | enum iso_code_class_type | |
485 | { | |
486 | ISO_control_0, /* Control codes in the range | |
487 | 0x00..0x1F and 0x7F, except for the | |
488 | following 5 codes. */ | |
489 | ISO_carriage_return, /* ISO_CODE_CR (0x0D) */ | |
490 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ | |
491 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
492 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
493 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
494 | ISO_control_1, /* Control codes in the range | |
495 | 0x80..0x9F, except for the | |
496 | following 3 codes. */ | |
497 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
498 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
499 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
500 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
501 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
502 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
503 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
504 | }; | |
05e6f5dc | 505 | |
df7492f9 KH |
506 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
507 | `iso-flags' attribute of an iso2022 coding system. */ | |
93dec019 | 508 | |
df7492f9 KH |
509 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
510 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
511 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
05e6f5dc | 512 | |
df7492f9 KH |
513 | /* If set, reset graphic planes and registers at end-of-line to the |
514 | initial state. */ | |
515 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 516 | |
df7492f9 KH |
517 | /* If set, reset graphic planes and registers before any control |
518 | characters to the initial state. */ | |
519 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
4ed46869 | 520 | |
df7492f9 KH |
521 | /* If set, encode by 7-bit environment. */ |
522 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
b73bfc1c | 523 | |
df7492f9 KH |
524 | /* If set, use locking-shift function. */ |
525 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 526 | |
df7492f9 KH |
527 | /* If set, use single-shift function. Overwrite |
528 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
529 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 530 | |
df7492f9 KH |
531 | /* If set, use designation escape sequence. */ |
532 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 533 | |
df7492f9 KH |
534 | /* If set, produce revision number sequence. */ |
535 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
f4dee582 | 536 | |
df7492f9 KH |
537 | /* If set, produce ISO6429's direction specifying sequence. */ |
538 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
4ed46869 | 539 | |
df7492f9 KH |
540 | /* If set, assume designation states are reset at beginning of line on |
541 | output. */ | |
542 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
aa72b389 | 543 | |
df7492f9 KH |
544 | /* If set, designation sequence should be placed at beginning of line |
545 | on output. */ | |
546 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 547 | |
df7492f9 KH |
548 | /* If set, do not encode unsafe charactes on output. */ |
549 | #define CODING_ISO_FLAG_SAFE 0x0800 | |
aa72b389 | 550 | |
df7492f9 KH |
551 | /* If set, extra latin codes (128..159) are accepted as a valid code |
552 | on input. */ | |
553 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 554 | |
df7492f9 | 555 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 556 | |
df7492f9 | 557 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 558 | |
df7492f9 | 559 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x8000 |
aa72b389 | 560 | |
df7492f9 KH |
561 | /* A character to be produced on output if encoding of the original |
562 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
563 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 564 | |
aa72b389 | 565 | |
df7492f9 KH |
566 | /* UTF-16 section */ |
567 | #define CODING_UTF_16_BOM(coding) \ | |
568 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 569 | |
df7492f9 KH |
570 | #define CODING_UTF_16_ENDIAN(coding) \ |
571 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 572 | |
df7492f9 KH |
573 | #define CODING_UTF_16_SURROGATE(coding) \ |
574 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 575 | |
4ed46869 | 576 | |
df7492f9 KH |
577 | /* CCL section */ |
578 | #define CODING_CCL_DECODER(coding) \ | |
579 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
580 | #define CODING_CCL_ENCODER(coding) \ | |
581 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
582 | #define CODING_CCL_VALIDS(coding) \ | |
583 | (XSTRING (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids)) \ | |
584 | ->data) | |
4ed46869 | 585 | |
df7492f9 | 586 | /* Index for each coding category in `coding_category_table' */ |
4ed46869 | 587 | |
df7492f9 KH |
588 | enum coding_category |
589 | { | |
590 | coding_category_iso_7, | |
591 | coding_category_iso_7_tight, | |
592 | coding_category_iso_8_1, | |
593 | coding_category_iso_8_2, | |
594 | coding_category_iso_7_else, | |
595 | coding_category_iso_8_else, | |
596 | coding_category_utf_8, | |
597 | coding_category_utf_16_auto, | |
598 | coding_category_utf_16_be, | |
599 | coding_category_utf_16_le, | |
600 | coding_category_utf_16_be_nosig, | |
601 | coding_category_utf_16_le_nosig, | |
602 | coding_category_charset, | |
603 | coding_category_sjis, | |
604 | coding_category_big5, | |
605 | coding_category_ccl, | |
606 | coding_category_emacs_mule, | |
607 | /* All above are targets of code detection. */ | |
608 | coding_category_raw_text, | |
609 | coding_category_undecided, | |
610 | coding_category_max | |
611 | }; | |
612 | ||
613 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
614 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
615 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
616 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
617 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
618 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
619 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
620 | #define CATEGORY_MASK_UTF_8 (1 << coding_category_utf_8) | |
621 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) | |
622 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
623 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
624 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
625 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
626 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
627 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
628 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
629 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
630 | ||
631 | /* This value is returned if detect_coding_mask () find nothing other | |
632 | than ASCII characters. */ | |
633 | #define CATEGORY_MASK_ANY \ | |
634 | (CATEGORY_MASK_ISO_7 \ | |
635 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
636 | | CATEGORY_MASK_ISO_8_1 \ | |
637 | | CATEGORY_MASK_ISO_8_2 \ | |
638 | | CATEGORY_MASK_ISO_7_ELSE \ | |
639 | | CATEGORY_MASK_ISO_8_ELSE \ | |
640 | | CATEGORY_MASK_UTF_8 \ | |
641 | | CATEGORY_MASK_UTF_16_BE \ | |
642 | | CATEGORY_MASK_UTF_16_LE \ | |
643 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
644 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
645 | | CATEGORY_MASK_CHARSET \ | |
646 | | CATEGORY_MASK_SJIS \ | |
647 | | CATEGORY_MASK_BIG5 \ | |
648 | | CATEGORY_MASK_CCL \ | |
649 | | CATEGORY_MASK_EMACS_MULE) | |
650 | ||
651 | ||
652 | #define CATEGORY_MASK_ISO_7BIT \ | |
653 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
654 | ||
655 | #define CATEGORY_MASK_ISO_8BIT \ | |
656 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
657 | ||
658 | #define CATEGORY_MASK_ISO_ELSE \ | |
659 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
660 | ||
661 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
662 | (CATEGORY_MASK_ISO_7 \ | |
663 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
664 | | CATEGORY_MASK_ISO_7_ELSE \ | |
665 | | CATEGORY_MASK_ISO_8_ELSE) | |
666 | ||
667 | #define CATEGORY_MASK_ISO \ | |
668 | ( CATEGORY_MASK_ISO_7BIT \ | |
669 | | CATEGORY_MASK_ISO_8BIT \ | |
670 | | CATEGORY_MASK_ISO_ELSE) | |
671 | ||
672 | #define CATEGORY_MASK_UTF_16 \ | |
673 | (CATEGORY_MASK_UTF_16_BE \ | |
674 | | CATEGORY_MASK_UTF_16_LE \ | |
675 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
676 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
677 | ||
678 | ||
679 | /* List of symbols `coding-category-xxx' ordered by priority. This | |
680 | variable is exposed to Emacs Lisp. */ | |
681 | static Lisp_Object Vcoding_category_list; | |
682 | ||
683 | /* Table of coding categories (Lisp symbols). This variable is for | |
684 | internal use oly. */ | |
685 | static Lisp_Object Vcoding_category_table; | |
686 | ||
687 | /* Table of coding-categories ordered by priority. */ | |
688 | static enum coding_category coding_priorities[coding_category_max]; | |
689 | ||
690 | /* Nth element is a coding context for the coding system bound to the | |
691 | Nth coding category. */ | |
692 | static struct coding_system coding_categories[coding_category_max]; | |
693 | ||
694 | static int detected_mask[coding_category_raw_text] = | |
695 | { CATEGORY_MASK_ISO, | |
696 | CATEGORY_MASK_ISO, | |
697 | CATEGORY_MASK_ISO, | |
698 | CATEGORY_MASK_ISO, | |
699 | CATEGORY_MASK_ISO, | |
700 | CATEGORY_MASK_ISO, | |
701 | CATEGORY_MASK_UTF_8, | |
702 | CATEGORY_MASK_UTF_16, | |
703 | CATEGORY_MASK_UTF_16, | |
704 | CATEGORY_MASK_UTF_16, | |
705 | CATEGORY_MASK_UTF_16, | |
706 | CATEGORY_MASK_UTF_16, | |
707 | CATEGORY_MASK_CHARSET, | |
708 | CATEGORY_MASK_SJIS, | |
709 | CATEGORY_MASK_BIG5, | |
710 | CATEGORY_MASK_CCL, | |
711 | CATEGORY_MASK_EMACS_MULE | |
712 | }; | |
713 | ||
714 | /*** Commonly used macros and functions ***/ | |
715 | ||
716 | #ifndef min | |
717 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
718 | #endif | |
719 | #ifndef max | |
720 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
721 | #endif | |
4ed46869 | 722 | |
df7492f9 KH |
723 | #define CODING_GET_INFO(coding, attrs, eol_type, charset_list) \ |
724 | do { \ | |
725 | attrs = CODING_ID_ATTRS (coding->id); \ | |
726 | eol_type = CODING_ID_EOL_TYPE (coding->id); \ | |
727 | if (VECTORP (eol_type)) \ | |
728 | eol_type = Qunix; \ | |
729 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); \ | |
730 | } while (0) | |
4ed46869 | 731 | |
4ed46869 | 732 | |
df7492f9 KH |
733 | /* Safely get one byte from the source text pointed by SRC which ends |
734 | at SRC_END, and set C to that byte. If there are not enough bytes | |
735 | in the source, it jumps to `no_more_source'. The caller | |
736 | should declare and set these variables appropriately in advance: | |
737 | src, src_end, multibytep | |
738 | */ | |
aa72b389 | 739 | |
df7492f9 | 740 | #define ONE_MORE_BYTE(c) \ |
aa72b389 | 741 | do { \ |
df7492f9 KH |
742 | if (src == src_end) \ |
743 | { \ | |
744 | if (src_base < src) \ | |
745 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; \ | |
746 | goto no_more_source; \ | |
747 | } \ | |
748 | c = *src++; \ | |
749 | if (multibytep && (c & 0x80)) \ | |
750 | { \ | |
751 | if ((c & 0xFE) != 0xC0) \ | |
752 | error ("Undecodable char found"); \ | |
753 | c = ((c & 1) << 6) | *src++; \ | |
754 | } \ | |
755 | consumed_chars++; \ | |
aa72b389 KH |
756 | } while (0) |
757 | ||
aa72b389 | 758 | |
df7492f9 KH |
759 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
760 | do { \ | |
761 | c = *src++; \ | |
762 | if (multibytep && (c & 0x80)) \ | |
763 | { \ | |
764 | if ((c & 0xFE) != 0xC0) \ | |
765 | error ("Undecodable char found"); \ | |
766 | c = ((c & 1) << 6) | *src++; \ | |
767 | } \ | |
781d7a48 | 768 | consumed_chars++; \ |
aa72b389 KH |
769 | } while (0) |
770 | ||
aa72b389 | 771 | |
df7492f9 KH |
772 | /* Store a byte C in the place pointed by DST and increment DST to the |
773 | next free point, and increment PRODUCED_CHARS. The caller should | |
774 | assure that C is 0..127, and declare and set the variable `dst' | |
775 | appropriately in advance. | |
776 | */ | |
aa72b389 KH |
777 | |
778 | ||
df7492f9 KH |
779 | #define EMIT_ONE_ASCII_BYTE(c) \ |
780 | do { \ | |
781 | produced_chars++; \ | |
782 | *dst++ = (c); \ | |
783 | } while (0) | |
aa72b389 | 784 | |
aa72b389 | 785 | |
df7492f9 | 786 | /* Like EMIT_ONE_ASCII_BYTE byt store two bytes; C1 and C2. */ |
aa72b389 | 787 | |
df7492f9 KH |
788 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
789 | do { \ | |
790 | produced_chars += 2; \ | |
791 | *dst++ = (c1), *dst++ = (c2); \ | |
792 | } while (0) | |
aa72b389 | 793 | |
df7492f9 KH |
794 | |
795 | /* Store a byte C in the place pointed by DST and increment DST to the | |
796 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
797 | nonzero, store in an appropriate multibyte from. The caller should | |
798 | declare and set the variables `dst' and `multibytep' appropriately | |
799 | in advance. */ | |
800 | ||
801 | #define EMIT_ONE_BYTE(c) \ | |
802 | do { \ | |
803 | produced_chars++; \ | |
804 | if (multibytep) \ | |
805 | { \ | |
806 | int ch = (c); \ | |
807 | if (ch >= 0x80) \ | |
808 | ch = BYTE8_TO_CHAR (ch); \ | |
809 | CHAR_STRING_ADVANCE (ch, dst); \ | |
810 | } \ | |
811 | else \ | |
812 | *dst++ = (c); \ | |
aa72b389 KH |
813 | } while (0) |
814 | ||
815 | ||
df7492f9 | 816 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 817 | |
e19c3639 KH |
818 | #define EMIT_TWO_BYTES(c1, c2) \ |
819 | do { \ | |
820 | produced_chars += 2; \ | |
821 | if (multibytep) \ | |
822 | { \ | |
823 | int ch; \ | |
824 | \ | |
825 | ch = (c1); \ | |
826 | if (ch >= 0x80) \ | |
827 | ch = BYTE8_TO_CHAR (ch); \ | |
828 | CHAR_STRING_ADVANCE (ch, dst); \ | |
829 | ch = (c2); \ | |
830 | if (ch >= 0x80) \ | |
831 | ch = BYTE8_TO_CHAR (ch); \ | |
832 | CHAR_STRING_ADVANCE (ch, dst); \ | |
833 | } \ | |
834 | else \ | |
835 | { \ | |
836 | *dst++ = (c1); \ | |
837 | *dst++ = (c2); \ | |
838 | } \ | |
aa72b389 KH |
839 | } while (0) |
840 | ||
841 | ||
df7492f9 KH |
842 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
843 | do { \ | |
844 | EMIT_ONE_BYTE (c1); \ | |
845 | EMIT_TWO_BYTES (c2, c3); \ | |
846 | } while (0) | |
aa72b389 | 847 | |
aa72b389 | 848 | |
df7492f9 KH |
849 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
850 | do { \ | |
851 | EMIT_TWO_BYTES (c1, c2); \ | |
852 | EMIT_TWO_BYTES (c3, c4); \ | |
853 | } while (0) | |
aa72b389 | 854 | |
aa72b389 | 855 | |
df7492f9 KH |
856 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
857 | do { \ | |
858 | charset_map_loaded = 0; \ | |
859 | c = DECODE_CHAR (charset, code); \ | |
860 | if (charset_map_loaded) \ | |
861 | { \ | |
862 | unsigned char *orig = coding->source; \ | |
863 | EMACS_INT offset; \ | |
864 | \ | |
865 | coding_set_source (coding); \ | |
866 | offset = coding->source - orig; \ | |
867 | src += offset; \ | |
868 | src_base += offset; \ | |
869 | src_end += offset; \ | |
870 | } \ | |
871 | } while (0) | |
aa72b389 | 872 | |
aa72b389 | 873 | |
df7492f9 KH |
874 | #define ASSURE_DESTINATION(bytes) \ |
875 | do { \ | |
876 | if (dst + (bytes) >= dst_end) \ | |
877 | { \ | |
878 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
879 | \ | |
880 | dst = alloc_destination (coding, more_bytes, dst); \ | |
881 | dst_end = coding->destination + coding->dst_bytes; \ | |
882 | } \ | |
883 | } while (0) | |
b1887814 | 884 | |
df7492f9 KH |
885 | |
886 | ||
887 | static void | |
888 | coding_set_source (coding) | |
889 | struct coding_system *coding; | |
890 | { | |
891 | if (BUFFERP (coding->src_object)) | |
892 | { | |
893 | if (coding->src_pos < 0) | |
894 | coding->source = GAP_END_ADDR + coding->src_pos_byte; | |
895 | else | |
896 | { | |
e19c3639 | 897 | struct buffer *buf = XBUFFER (coding->src_object); |
e19c3639 KH |
898 | EMACS_INT gpt_byte = BUF_GPT_BYTE (buf); |
899 | unsigned char *beg_addr = BUF_BEG_ADDR (buf); | |
900 | ||
901 | coding->source = beg_addr + coding->src_pos_byte - 1; | |
902 | if (coding->src_pos_byte >= gpt_byte) | |
903 | coding->source += BUF_GAP_SIZE (buf); | |
aa72b389 KH |
904 | } |
905 | } | |
df7492f9 | 906 | else if (STRINGP (coding->src_object)) |
aa72b389 | 907 | { |
df7492f9 KH |
908 | coding->source = (XSTRING (coding->src_object)->data |
909 | + coding->src_pos_byte); | |
910 | } | |
911 | else | |
912 | /* Otherwise, the source is C string and is never relocated | |
913 | automatically. Thus we don't have to update anything. */ | |
914 | ; | |
915 | } | |
916 | ||
917 | static void | |
918 | coding_set_destination (coding) | |
919 | struct coding_system *coding; | |
920 | { | |
921 | if (BUFFERP (coding->dst_object)) | |
922 | { | |
923 | /* We are sure that coding->dst_pos_byte is before the gap of the | |
924 | buffer. */ | |
925 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
926 | + coding->dst_pos_byte - 1); | |
927 | if (coding->src_pos < 0) | |
df7492f9 KH |
928 | coding->dst_bytes = (GAP_END_ADDR |
929 | - (coding->src_bytes - coding->consumed) | |
930 | - coding->destination); | |
931 | else | |
932 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) | |
933 | - coding->destination); | |
934 | } | |
935 | else | |
936 | /* Otherwise, the destination is C string and is never relocated | |
937 | automatically. Thus we don't have to update anything. */ | |
938 | ; | |
939 | } | |
940 | ||
941 | ||
942 | static void | |
943 | coding_alloc_by_realloc (coding, bytes) | |
944 | struct coding_system *coding; | |
945 | EMACS_INT bytes; | |
946 | { | |
947 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
948 | coding->dst_bytes + bytes); | |
949 | coding->dst_bytes += bytes; | |
950 | } | |
951 | ||
952 | static void | |
953 | coding_alloc_by_making_gap (coding, bytes) | |
954 | struct coding_system *coding; | |
955 | EMACS_INT bytes; | |
956 | { | |
2c78b7e1 KH |
957 | if (BUFFERP (coding->dst_object) |
958 | && EQ (coding->src_object, coding->dst_object)) | |
df7492f9 KH |
959 | { |
960 | EMACS_INT add = coding->src_bytes - coding->consumed; | |
961 | ||
962 | GAP_SIZE -= add; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
963 | make_gap (bytes); | |
964 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
965 | } | |
966 | else | |
967 | { | |
2c78b7e1 KH |
968 | Lisp_Object this_buffer; |
969 | ||
970 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
971 | set_buffer_internal (XBUFFER (coding->dst_object)); |
972 | make_gap (bytes); | |
973 | set_buffer_internal (XBUFFER (this_buffer)); | |
974 | } | |
975 | } | |
976 | ||
977 | ||
978 | static unsigned char * | |
979 | alloc_destination (coding, nbytes, dst) | |
980 | struct coding_system *coding; | |
981 | int nbytes; | |
982 | unsigned char *dst; | |
983 | { | |
984 | EMACS_INT offset = dst - coding->destination; | |
985 | ||
986 | if (BUFFERP (coding->dst_object)) | |
987 | coding_alloc_by_making_gap (coding, nbytes); | |
988 | else | |
989 | coding_alloc_by_realloc (coding, nbytes); | |
990 | coding->result = CODING_RESULT_SUCCESS; | |
991 | coding_set_destination (coding); | |
992 | dst = coding->destination + offset; | |
993 | return dst; | |
994 | } | |
aa72b389 | 995 | |
df7492f9 KH |
996 | \f |
997 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
998 | ||
999 | ||
1000 | ||
1001 | \f | |
1002 | /*** 3. UTF-8 ***/ | |
1003 | ||
1004 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
1005 | Check if a text is encoded in UTF-8. If it is, return | |
1006 | CATEGORY_MASK_UTF_8, else return 0. */ | |
1007 | ||
1008 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1009 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1010 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1011 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1012 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1013 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1014 | ||
1015 | static int | |
1016 | detect_coding_utf_8 (coding, mask) | |
1017 | struct coding_system *coding; | |
1018 | int *mask; | |
1019 | { | |
1020 | unsigned char *src = coding->source, *src_base = src; | |
1021 | unsigned char *src_end = coding->source + coding->src_bytes; | |
1022 | int multibytep = coding->src_multibyte; | |
1023 | int consumed_chars = 0; | |
1024 | int found = 0; | |
1025 | ||
1026 | /* A coding system of this category is always ASCII compatible. */ | |
1027 | src += coding->head_ascii; | |
1028 | ||
1029 | while (1) | |
1030 | { | |
1031 | int c, c1, c2, c3, c4; | |
1032 | ||
1033 | ONE_MORE_BYTE (c); | |
1034 | if (UTF_8_1_OCTET_P (c)) | |
1035 | continue; | |
1036 | ONE_MORE_BYTE (c1); | |
1037 | if (! UTF_8_EXTRA_OCTET_P (c1)) | |
1038 | break; | |
1039 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
1040 | { | |
1041 | found++; | |
1042 | continue; | |
1043 | } | |
1044 | ONE_MORE_BYTE (c2); | |
1045 | if (! UTF_8_EXTRA_OCTET_P (c2)) | |
1046 | break; | |
1047 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
1048 | { | |
1049 | found++; | |
1050 | continue; | |
1051 | } | |
1052 | ONE_MORE_BYTE (c3); | |
1053 | if (! UTF_8_EXTRA_OCTET_P (c3)) | |
1054 | break; | |
1055 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1056 | { |
df7492f9 KH |
1057 | found++; |
1058 | continue; | |
1059 | } | |
1060 | ONE_MORE_BYTE (c4); | |
1061 | if (! UTF_8_EXTRA_OCTET_P (c4)) | |
1062 | break; | |
1063 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1064 | { | |
1065 | found++; | |
1066 | continue; | |
1067 | } | |
1068 | break; | |
1069 | } | |
1070 | *mask &= ~CATEGORY_MASK_UTF_8; | |
1071 | return 0; | |
1072 | ||
1073 | no_more_source: | |
1074 | if (! found) | |
1075 | return 0; | |
1076 | *mask &= CATEGORY_MASK_UTF_8; | |
1077 | return 1; | |
1078 | } | |
1079 | ||
1080 | ||
b0edb2c5 | 1081 | /* Fixme: deal with surrogates? */ |
df7492f9 KH |
1082 | static void |
1083 | decode_coding_utf_8 (coding) | |
1084 | struct coding_system *coding; | |
1085 | { | |
1086 | unsigned char *src = coding->source + coding->consumed; | |
1087 | unsigned char *src_end = coding->source + coding->src_bytes; | |
1088 | unsigned char *src_base; | |
1089 | int *charbuf = coding->charbuf; | |
1090 | int *charbuf_end = charbuf + coding->charbuf_size; | |
1091 | int consumed_chars = 0, consumed_chars_base; | |
1092 | int multibytep = coding->src_multibyte; | |
1093 | Lisp_Object attr, eol_type, charset_list; | |
1094 | ||
1095 | CODING_GET_INFO (coding, attr, eol_type, charset_list); | |
1096 | ||
1097 | while (1) | |
1098 | { | |
1099 | int c, c1, c2, c3, c4, c5; | |
1100 | ||
1101 | src_base = src; | |
1102 | consumed_chars_base = consumed_chars; | |
1103 | ||
1104 | if (charbuf >= charbuf_end) | |
1105 | break; | |
1106 | ||
1107 | ONE_MORE_BYTE (c1); | |
1108 | if (UTF_8_1_OCTET_P(c1)) | |
1109 | { | |
1110 | c = c1; | |
1111 | if (c == '\r') | |
aa72b389 | 1112 | { |
df7492f9 KH |
1113 | if (EQ (eol_type, Qdos)) |
1114 | { | |
1115 | if (src == src_end) | |
1116 | goto no_more_source; | |
1117 | if (*src == '\n') | |
1118 | ONE_MORE_BYTE (c); | |
1119 | } | |
1120 | else if (EQ (eol_type, Qmac)) | |
1121 | c = '\n'; | |
aa72b389 | 1122 | } |
aa72b389 | 1123 | } |
df7492f9 | 1124 | else |
aa72b389 | 1125 | { |
df7492f9 KH |
1126 | ONE_MORE_BYTE (c2); |
1127 | if (! UTF_8_EXTRA_OCTET_P (c2)) | |
1128 | goto invalid_code; | |
1129 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1130 | { |
1131 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); | |
1132 | /* Reject overlong sequences here and below. Encoders | |
1133 | producing them are incorrect, they can be misleading, | |
1134 | and they mess up read/write invariance. */ | |
1135 | if (c < 128) | |
1136 | goto invalid_code; | |
1137 | } | |
df7492f9 | 1138 | else |
aa72b389 | 1139 | { |
df7492f9 KH |
1140 | ONE_MORE_BYTE (c3); |
1141 | if (! UTF_8_EXTRA_OCTET_P (c3)) | |
1142 | goto invalid_code; | |
1143 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1144 | { |
1145 | c = (((c1 & 0xF) << 12) | |
1146 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
1147 | if (c < 0x800) | |
1148 | goto invalid_code; | |
1149 | } | |
df7492f9 KH |
1150 | else |
1151 | { | |
1152 | ONE_MORE_BYTE (c4); | |
1153 | if (! UTF_8_EXTRA_OCTET_P (c4)) | |
1154 | goto invalid_code; | |
1155 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1156 | { |
df7492f9 KH |
1157 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1158 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1159 | if (c < 0x10000) |
1160 | goto invalid_code; | |
1161 | } | |
df7492f9 KH |
1162 | else |
1163 | { | |
1164 | ONE_MORE_BYTE (c5); | |
1165 | if (! UTF_8_EXTRA_OCTET_P (c5)) | |
1166 | goto invalid_code; | |
1167 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1168 | { | |
1169 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1170 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1171 | | (c5 & 0x3F)); | |
b0edb2c5 | 1172 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1173 | goto invalid_code; |
1174 | } | |
1175 | else | |
1176 | goto invalid_code; | |
1177 | } | |
1178 | } | |
aa72b389 | 1179 | } |
aa72b389 | 1180 | } |
df7492f9 KH |
1181 | |
1182 | *charbuf++ = c; | |
1183 | continue; | |
1184 | ||
1185 | invalid_code: | |
1186 | src = src_base; | |
1187 | consumed_chars = consumed_chars_base; | |
1188 | ONE_MORE_BYTE (c); | |
1189 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1190 | coding->errors++; | |
aa72b389 KH |
1191 | } |
1192 | ||
df7492f9 KH |
1193 | no_more_source: |
1194 | coding->consumed_char += consumed_chars_base; | |
1195 | coding->consumed = src_base - coding->source; | |
1196 | coding->charbuf_used = charbuf - coding->charbuf; | |
1197 | } | |
1198 | ||
1199 | ||
1200 | static int | |
1201 | encode_coding_utf_8 (coding) | |
1202 | struct coding_system *coding; | |
1203 | { | |
1204 | int multibytep = coding->dst_multibyte; | |
1205 | int *charbuf = coding->charbuf; | |
1206 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1207 | unsigned char *dst = coding->destination + coding->produced; | |
1208 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1209 | int produced_chars = 0; |
df7492f9 KH |
1210 | int c; |
1211 | ||
1212 | if (multibytep) | |
aa72b389 | 1213 | { |
df7492f9 KH |
1214 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1215 | ||
1216 | while (charbuf < charbuf_end) | |
aa72b389 | 1217 | { |
df7492f9 KH |
1218 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
1219 | ||
1220 | ASSURE_DESTINATION (safe_room); | |
1221 | c = *charbuf++; | |
1222 | CHAR_STRING_ADVANCE (c, pend); | |
1223 | for (p = str; p < pend; p++) | |
1224 | EMIT_ONE_BYTE (*p); | |
aa72b389 | 1225 | } |
aa72b389 | 1226 | } |
df7492f9 KH |
1227 | else |
1228 | { | |
1229 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1230 | ||
1231 | while (charbuf < charbuf_end) | |
1232 | { | |
1233 | ASSURE_DESTINATION (safe_room); | |
1234 | c = *charbuf++; | |
1235 | dst += CHAR_STRING (c, dst); | |
1236 | produced_chars++; | |
1237 | } | |
1238 | } | |
1239 | coding->result = CODING_RESULT_SUCCESS; | |
1240 | coding->produced_char += produced_chars; | |
1241 | coding->produced = dst - coding->destination; | |
1242 | return 0; | |
aa72b389 KH |
1243 | } |
1244 | ||
4ed46869 | 1245 | |
df7492f9 KH |
1246 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
1247 | Check if a text is encoded in UTF-16 Big Endian (endian == 1) or | |
1248 | Little Endian (otherwise). If it is, return | |
1249 | CATEGORY_MASK_UTF_16_BE or CATEGORY_MASK_UTF_16_LE, | |
1250 | else return 0. */ | |
1251 | ||
1252 | #define UTF_16_HIGH_SURROGATE_P(val) \ | |
1253 | (((val) & 0xFC00) == 0xD800) | |
1254 | ||
1255 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1256 | (((val) & 0xFC00) == 0xDC00) | |
1257 | ||
1258 | #define UTF_16_INVALID_P(val) \ | |
1259 | (((val) == 0xFFFE) \ | |
1260 | || ((val) == 0xFFFF) \ | |
1261 | || UTF_16_LOW_SURROGATE_P (val)) | |
1262 | ||
1263 | ||
1264 | static int | |
1265 | detect_coding_utf_16 (coding, mask) | |
b73bfc1c | 1266 | struct coding_system *coding; |
df7492f9 | 1267 | int *mask; |
b73bfc1c | 1268 | { |
df7492f9 KH |
1269 | unsigned char *src = coding->source, *src_base = src; |
1270 | unsigned char *src_end = coding->source + coding->src_bytes; | |
1271 | int multibytep = coding->src_multibyte; | |
1272 | int consumed_chars = 0; | |
1273 | int c1, c2; | |
1274 | ||
1275 | ONE_MORE_BYTE (c1); | |
1276 | ONE_MORE_BYTE (c2); | |
4ed46869 | 1277 | |
df7492f9 | 1278 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
b73bfc1c | 1279 | { |
df7492f9 KH |
1280 | *mask &= CATEGORY_MASK_UTF_16_LE; |
1281 | return 1; | |
1282 | } | |
1283 | else if ((c1 == 0xFE) && (c2 == 0xFF)) | |
1284 | { | |
1285 | *mask &= CATEGORY_MASK_UTF_16_BE; | |
1286 | return 1; | |
1287 | } | |
1288 | no_more_source: | |
1289 | return 0; | |
1290 | } | |
ec6d2bb8 | 1291 | |
df7492f9 KH |
1292 | static void |
1293 | decode_coding_utf_16 (coding) | |
1294 | struct coding_system *coding; | |
1295 | { | |
1296 | unsigned char *src = coding->source + coding->consumed; | |
1297 | unsigned char *src_end = coding->source + coding->src_bytes; | |
0be8721c | 1298 | unsigned char *src_base; |
df7492f9 KH |
1299 | int *charbuf = coding->charbuf; |
1300 | int *charbuf_end = charbuf + coding->charbuf_size; | |
1301 | int consumed_chars = 0, consumed_chars_base; | |
1302 | int multibytep = coding->src_multibyte; | |
1303 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1304 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); | |
1305 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
1306 | Lisp_Object attr, eol_type, charset_list; | |
1307 | ||
1308 | CODING_GET_INFO (coding, attr, eol_type, charset_list); | |
1309 | ||
1310 | if (bom != utf_16_without_bom) | |
1311 | { | |
1312 | int c, c1, c2; | |
4af310db | 1313 | |
df7492f9 KH |
1314 | src_base = src; |
1315 | ONE_MORE_BYTE (c1); | |
1316 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1317 | c = (c1 << 8) | c2; |
df7492f9 KH |
1318 | if (bom == utf_16_with_bom) |
1319 | { | |
1320 | if (endian == utf_16_big_endian | |
1321 | ? c != 0xFFFE : c != 0xFEFF) | |
4af310db | 1322 | { |
df7492f9 KH |
1323 | /* We are sure that there's enouph room at CHARBUF. */ |
1324 | *charbuf++ = c1; | |
1325 | *charbuf++ = c2; | |
1326 | coding->errors++; | |
4af310db | 1327 | } |
4af310db | 1328 | } |
df7492f9 | 1329 | else |
4af310db | 1330 | { |
df7492f9 KH |
1331 | if (c == 0xFFFE) |
1332 | CODING_UTF_16_ENDIAN (coding) | |
1333 | = endian = utf_16_big_endian; | |
1334 | else if (c == 0xFEFF) | |
1335 | CODING_UTF_16_ENDIAN (coding) | |
1336 | = endian = utf_16_little_endian; | |
1337 | else | |
4af310db | 1338 | { |
df7492f9 KH |
1339 | CODING_UTF_16_ENDIAN (coding) |
1340 | = endian = utf_16_big_endian; | |
1341 | src = src_base; | |
4af310db | 1342 | } |
4af310db | 1343 | } |
df7492f9 KH |
1344 | CODING_UTF_16_BOM (coding) = utf_16_with_bom; |
1345 | } | |
1346 | ||
1347 | while (1) | |
1348 | { | |
1349 | int c, c1, c2; | |
1350 | ||
1351 | src_base = src; | |
1352 | consumed_chars_base = consumed_chars; | |
1353 | ||
1354 | if (charbuf + 2 >= charbuf_end) | |
1355 | break; | |
1356 | ||
1357 | ONE_MORE_BYTE (c1); | |
1358 | ONE_MORE_BYTE (c2); | |
1359 | c = (endian == utf_16_big_endian | |
e19c3639 | 1360 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
df7492f9 | 1361 | if (surrogate) |
aa72b389 | 1362 | { |
df7492f9 | 1363 | if (! UTF_16_LOW_SURROGATE_P (c)) |
aa72b389 | 1364 | { |
df7492f9 KH |
1365 | if (endian == utf_16_big_endian) |
1366 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1367 | else | |
1368 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1369 | *charbuf++ = c1; | |
1370 | *charbuf++ = c2; | |
1371 | coding->errors++; | |
1372 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1373 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1374 | else | |
1375 | *charbuf++ = c; | |
aa72b389 | 1376 | } |
df7492f9 KH |
1377 | else |
1378 | { | |
1379 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1380 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
1381 | *charbuf++ = c; | |
1382 | } | |
1383 | } | |
1384 | else | |
1385 | { | |
1386 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1387 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1388 | else | |
1389 | *charbuf++ = c; | |
1390 | } | |
1391 | } | |
1392 | ||
1393 | no_more_source: | |
1394 | coding->consumed_char += consumed_chars_base; | |
1395 | coding->consumed = src_base - coding->source; | |
1396 | coding->charbuf_used = charbuf - coding->charbuf; | |
1397 | } | |
1398 | ||
1399 | static int | |
1400 | encode_coding_utf_16 (coding) | |
1401 | struct coding_system *coding; | |
1402 | { | |
1403 | int multibytep = coding->dst_multibyte; | |
1404 | int *charbuf = coding->charbuf; | |
1405 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1406 | unsigned char *dst = coding->destination + coding->produced; | |
1407 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1408 | int safe_room = 8; | |
1409 | enum utf_16_bom_type bom = CODING_UTF_16_BOM (coding); | |
1410 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; | |
1411 | int produced_chars = 0; | |
1412 | Lisp_Object attrs, eol_type, charset_list; | |
1413 | int c; | |
1414 | ||
1415 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
1416 | ||
1417 | if (bom == utf_16_with_bom) | |
1418 | { | |
1419 | ASSURE_DESTINATION (safe_room); | |
1420 | if (big_endian) | |
1421 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
1422 | else | |
1423 | EMIT_TWO_BYTES (0xFE, 0xFF); | |
1424 | CODING_UTF_16_BOM (coding) = utf_16_without_bom; | |
1425 | } | |
1426 | ||
1427 | while (charbuf < charbuf_end) | |
1428 | { | |
1429 | ASSURE_DESTINATION (safe_room); | |
1430 | c = *charbuf++; | |
e19c3639 KH |
1431 | if (c >= MAX_UNICODE_CHAR) |
1432 | c = coding->default_char; | |
df7492f9 KH |
1433 | |
1434 | if (c < 0x10000) | |
1435 | { | |
1436 | if (big_endian) | |
1437 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1438 | else | |
1439 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1440 | } | |
1441 | else | |
1442 | { | |
1443 | int c1, c2; | |
1444 | ||
1445 | c -= 0x10000; | |
1446 | c1 = (c >> 10) + 0xD800; | |
1447 | c2 = (c & 0x3FF) + 0xDC00; | |
1448 | if (big_endian) | |
1449 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1450 | else | |
1451 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1452 | } | |
1453 | } | |
1454 | coding->result = CODING_RESULT_SUCCESS; | |
1455 | coding->produced = dst - coding->destination; | |
1456 | coding->produced_char += produced_chars; | |
1457 | return 0; | |
1458 | } | |
1459 | ||
1460 | \f | |
1461 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1462 | ||
1463 | /* Emacs' internal format for representation of multiple character | |
1464 | sets is a kind of multi-byte encoding, i.e. characters are | |
1465 | represented by variable-length sequences of one-byte codes. | |
1466 | ||
1467 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1468 | represented by one-byte sequences which are their ASCII codes, in | |
1469 | the range 0x00 through 0x7F. | |
1470 | ||
1471 | 8-bit characters of the range 0x80..0x9F are represented by | |
1472 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1473 | code + 0x20). | |
1474 | ||
1475 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1476 | one-byte sequences which are their 8-bit code. | |
1477 | ||
1478 | The other characters are represented by a sequence of `base | |
1479 | leading-code', optional `extended leading-code', and one or two | |
1480 | `position-code's. The length of the sequence is determined by the | |
1481 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1482 | whereas extended leading-code and position-code take the range 0xA0 | |
1483 | through 0xFF. See `charset.h' for more details about leading-code | |
1484 | and position-code. | |
1485 | ||
1486 | --- CODE RANGE of Emacs' internal format --- | |
1487 | character set range | |
1488 | ------------- ----- | |
1489 | ascii 0x00..0x7F | |
1490 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1491 | eight-bit-graphic 0xA0..0xBF | |
1492 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1493 | --------------------------------------------- | |
1494 | ||
1495 | As this is the internal character representation, the format is | |
1496 | usually not used externally (i.e. in a file or in a data sent to a | |
1497 | process). But, it is possible to have a text externally in this | |
1498 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1499 | ||
1500 | In that case, a sequence of one-byte codes has a slightly different | |
1501 | form. | |
1502 | ||
1503 | At first, all characters in eight-bit-control are represented by | |
1504 | one-byte sequences which are their 8-bit code. | |
1505 | ||
1506 | Next, character composition data are represented by the byte | |
1507 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1508 | where, | |
1509 | METHOD is 0xF0 plus one of composition method (enum | |
1510 | composition_method), | |
1511 | ||
1512 | BYTES is 0xA0 plus a byte length of this composition data, | |
1513 | ||
1514 | CHARS is 0x20 plus a number of characters composed by this | |
1515 | data, | |
1516 | ||
1517 | COMPONENTs are characters of multibye form or composition | |
1518 | rules encoded by two-byte of ASCII codes. | |
1519 | ||
1520 | In addition, for backward compatibility, the following formats are | |
1521 | also recognized as composition data on decoding. | |
1522 | ||
1523 | 0x80 MSEQ ... | |
1524 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1525 | ||
1526 | Here, | |
1527 | MSEQ is a multibyte form but in these special format: | |
1528 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1529 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1530 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1531 | represents a composition rule. | |
1532 | */ | |
1533 | ||
1534 | char emacs_mule_bytes[256]; | |
1535 | ||
1536 | /* Leading-code followed by extended leading-code. */ | |
1537 | #define LEADING_CODE_PRIVATE_11 0x9A /* for private DIMENSION1 of 1-column */ | |
1538 | #define LEADING_CODE_PRIVATE_12 0x9B /* for private DIMENSION1 of 2-column */ | |
1539 | #define LEADING_CODE_PRIVATE_21 0x9C /* for private DIMENSION2 of 1-column */ | |
1540 | #define LEADING_CODE_PRIVATE_22 0x9D /* for private DIMENSION2 of 2-column */ | |
1541 | ||
1542 | ||
1543 | int | |
781d7a48 | 1544 | emacs_mule_char (coding, src, nbytes, nchars) |
df7492f9 | 1545 | struct coding_system *coding; |
781d7a48 | 1546 | unsigned char *src; |
df7492f9 KH |
1547 | int *nbytes, *nchars; |
1548 | { | |
df7492f9 KH |
1549 | unsigned char *src_end = coding->source + coding->src_bytes; |
1550 | int multibytep = coding->src_multibyte; | |
1551 | unsigned char *src_base = src; | |
1552 | struct charset *charset; | |
1553 | unsigned code; | |
1554 | int c; | |
1555 | int consumed_chars = 0; | |
1556 | ||
1557 | ONE_MORE_BYTE (c); | |
df7492f9 KH |
1558 | switch (emacs_mule_bytes[c]) |
1559 | { | |
1560 | case 2: | |
1561 | if (! (charset = emacs_mule_charset[c])) | |
1562 | goto invalid_code; | |
1563 | ONE_MORE_BYTE (c); | |
1564 | code = c & 0x7F; | |
1565 | break; | |
1566 | ||
1567 | case 3: | |
1568 | if (c == LEADING_CODE_PRIVATE_11 | |
1569 | || c == LEADING_CODE_PRIVATE_12) | |
b73bfc1c | 1570 | { |
df7492f9 KH |
1571 | ONE_MORE_BYTE (c); |
1572 | if (! (charset = emacs_mule_charset[c])) | |
1573 | goto invalid_code; | |
1574 | ONE_MORE_BYTE (c); | |
1575 | code = c & 0x7F; | |
b73bfc1c KH |
1576 | } |
1577 | else | |
1578 | { | |
df7492f9 KH |
1579 | if (! (charset = emacs_mule_charset[c])) |
1580 | goto invalid_code; | |
1581 | ONE_MORE_BYTE (c); | |
781d7a48 | 1582 | code = (c & 0x7F) << 8; |
df7492f9 KH |
1583 | ONE_MORE_BYTE (c); |
1584 | code |= c & 0x7F; | |
1585 | } | |
1586 | break; | |
1587 | ||
1588 | case 4: | |
781d7a48 | 1589 | ONE_MORE_BYTE (c); |
df7492f9 KH |
1590 | if (! (charset = emacs_mule_charset[c])) |
1591 | goto invalid_code; | |
1592 | ONE_MORE_BYTE (c); | |
781d7a48 | 1593 | code = (c & 0x7F) << 8; |
df7492f9 KH |
1594 | ONE_MORE_BYTE (c); |
1595 | code |= c & 0x7F; | |
1596 | break; | |
1597 | ||
1598 | case 1: | |
1599 | code = c; | |
1600 | charset = CHARSET_FROM_ID (ASCII_BYTE_P (code) ? charset_ascii | |
1601 | : code < 0xA0 ? charset_8_bit_control | |
1602 | : charset_8_bit_graphic); | |
1603 | break; | |
1604 | ||
1605 | default: | |
1606 | abort (); | |
1607 | } | |
1608 | c = DECODE_CHAR (charset, code); | |
1609 | if (c < 0) | |
1610 | goto invalid_code; | |
1611 | *nbytes = src - src_base; | |
1612 | *nchars = consumed_chars; | |
1613 | return c; | |
1614 | ||
1615 | no_more_source: | |
1616 | return -2; | |
1617 | ||
1618 | invalid_code: | |
1619 | return -1; | |
1620 | } | |
1621 | ||
1622 | ||
1623 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
1624 | Check if a text is encoded in `emacs-mule'. */ | |
1625 | ||
1626 | static int | |
1627 | detect_coding_emacs_mule (coding, mask) | |
1628 | struct coding_system *coding; | |
1629 | int *mask; | |
1630 | { | |
1631 | unsigned char *src = coding->source, *src_base = src; | |
1632 | unsigned char *src_end = coding->source + coding->src_bytes; | |
1633 | int multibytep = coding->src_multibyte; | |
1634 | int consumed_chars = 0; | |
1635 | int c; | |
1636 | int found = 0; | |
1637 | ||
1638 | /* A coding system of this category is always ASCII compatible. */ | |
1639 | src += coding->head_ascii; | |
1640 | ||
1641 | while (1) | |
1642 | { | |
1643 | ONE_MORE_BYTE (c); | |
1644 | ||
1645 | if (c == 0x80) | |
1646 | { | |
1647 | /* Perhaps the start of composite character. We simple skip | |
1648 | it because analyzing it is too heavy for detecting. But, | |
1649 | at least, we check that the composite character | |
1650 | constitues of more than 4 bytes. */ | |
1651 | unsigned char *src_base; | |
1652 | ||
1653 | repeat: | |
1654 | src_base = src; | |
1655 | do | |
1656 | { | |
1657 | ONE_MORE_BYTE (c); | |
1658 | } | |
1659 | while (c >= 0xA0); | |
1660 | ||
1661 | if (src - src_base <= 4) | |
1662 | break; | |
1663 | found = 1; | |
1664 | if (c == 0x80) | |
1665 | goto repeat; | |
b73bfc1c | 1666 | } |
df7492f9 KH |
1667 | |
1668 | if (c < 0x80) | |
b73bfc1c | 1669 | { |
df7492f9 KH |
1670 | if (c < 0x20 |
1671 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1672 | break; | |
1673 | } | |
1674 | else | |
1675 | { | |
1676 | unsigned char *src_base = src - 1; | |
1677 | ||
1678 | do | |
1679 | { | |
1680 | ONE_MORE_BYTE (c); | |
1681 | } | |
1682 | while (c >= 0xA0); | |
1683 | if (src - src_base != emacs_mule_bytes[*src_base]) | |
1684 | break; | |
1685 | found = 1; | |
4ed46869 KH |
1686 | } |
1687 | } | |
df7492f9 KH |
1688 | *mask &= ~CATEGORY_MASK_EMACS_MULE; |
1689 | return 0; | |
1690 | ||
1691 | no_more_source: | |
1692 | if (!found) | |
1693 | return 0; | |
1694 | *mask &= CATEGORY_MASK_EMACS_MULE; | |
1695 | return 1; | |
4ed46869 KH |
1696 | } |
1697 | ||
b73bfc1c | 1698 | |
df7492f9 KH |
1699 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
1700 | ||
1701 | /* Decode a character represented as a component of composition | |
1702 | sequence of Emacs 20/21 style at SRC. Set C to that character and | |
1703 | update SRC to the head of next character (or an encoded composition | |
1704 | rule). If SRC doesn't points a composition component, set C to -1. | |
1705 | If SRC points an invalid byte sequence, global exit by a return | |
1706 | value 0. */ | |
1707 | ||
1708 | #define DECODE_EMACS_MULE_COMPOSITION_CHAR(buf) \ | |
1709 | if (1) \ | |
1710 | { \ | |
1711 | int c; \ | |
1712 | int nbytes, nchars; \ | |
1713 | \ | |
1714 | if (src == src_end) \ | |
1715 | break; \ | |
781d7a48 | 1716 | c = emacs_mule_char (coding, src, &nbytes, &nchars); \ |
df7492f9 KH |
1717 | if (c < 0) \ |
1718 | { \ | |
1719 | if (c == -2) \ | |
1720 | break; \ | |
1721 | goto invalid_code; \ | |
1722 | } \ | |
1723 | *buf++ = c; \ | |
1724 | src += nbytes; \ | |
1725 | consumed_chars += nchars; \ | |
1726 | } \ | |
1727 | else | |
1728 | ||
1729 | ||
1730 | /* Decode a composition rule represented as a component of composition | |
781d7a48 KH |
1731 | sequence of Emacs 20 style at SRC. Store the decoded rule in *BUF, |
1732 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1733 | to -1. */ | |
df7492f9 | 1734 | |
781d7a48 | 1735 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(buf) \ |
df7492f9 KH |
1736 | do { \ |
1737 | int c, gref, nref; \ | |
1738 | \ | |
781d7a48 | 1739 | if (src >= src_end) \ |
df7492f9 KH |
1740 | goto invalid_code; \ |
1741 | ONE_MORE_BYTE_NO_CHECK (c); \ | |
781d7a48 | 1742 | c -= 0x20; \ |
df7492f9 KH |
1743 | if (c < 0 || c >= 81) \ |
1744 | goto invalid_code; \ | |
1745 | \ | |
1746 | gref = c / 9, nref = c % 9; \ | |
1747 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1748 | } while (0) | |
1749 | ||
1750 | ||
781d7a48 KH |
1751 | /* Decode a composition rule represented as a component of composition |
1752 | sequence of Emacs 21 style at SRC. Store the decoded rule in *BUF, | |
1753 | and increment BUF. If SRC points an invalid byte sequence, set C | |
1754 | to -1. */ | |
1755 | ||
1756 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(buf) \ | |
1757 | do { \ | |
1758 | int gref, nref; \ | |
1759 | \ | |
1760 | if (src + 1>= src_end) \ | |
1761 | goto invalid_code; \ | |
1762 | ONE_MORE_BYTE_NO_CHECK (gref); \ | |
1763 | gref -= 0x20; \ | |
1764 | ONE_MORE_BYTE_NO_CHECK (nref); \ | |
1765 | nref -= 0x20; \ | |
1766 | if (gref < 0 || gref >= 81 \ | |
1767 | || nref < 0 || nref >= 81) \ | |
1768 | goto invalid_code; \ | |
1769 | *buf++ = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
1770 | } while (0) | |
1771 | ||
1772 | ||
df7492f9 KH |
1773 | #define ADD_COMPOSITION_DATA(buf, method, nchars) \ |
1774 | do { \ | |
1775 | *buf++ = -5; \ | |
1776 | *buf++ = coding->produced_char + char_offset; \ | |
1777 | *buf++ = CODING_ANNOTATE_COMPOSITION_MASK; \ | |
1778 | *buf++ = method; \ | |
1779 | *buf++ = nchars; \ | |
1780 | } while (0) | |
aa72b389 | 1781 | |
df7492f9 KH |
1782 | |
1783 | #define DECODE_EMACS_MULE_21_COMPOSITION(c) \ | |
aa72b389 | 1784 | do { \ |
df7492f9 | 1785 | /* Emacs 21 style format. The first three bytes at SRC are \ |
781d7a48 | 1786 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is \ |
df7492f9 KH |
1787 | the byte length of this composition information, CHARS is the \ |
1788 | number of characters composed by this composition. */ \ | |
781d7a48 KH |
1789 | enum composition_method method = c - 0xF2; \ |
1790 | int *charbuf_base = charbuf; \ | |
df7492f9 KH |
1791 | int consumed_chars_limit; \ |
1792 | int nbytes, nchars; \ | |
1793 | \ | |
1794 | ONE_MORE_BYTE (c); \ | |
1795 | nbytes = c - 0xA0; \ | |
1796 | if (nbytes < 3) \ | |
1797 | goto invalid_code; \ | |
1798 | ONE_MORE_BYTE (c); \ | |
1799 | nchars = c - 0xA0; \ | |
1800 | ADD_COMPOSITION_DATA (charbuf, method, nchars); \ | |
1801 | consumed_chars_limit = consumed_chars_base + nbytes; \ | |
1802 | if (method != COMPOSITION_RELATIVE) \ | |
aa72b389 | 1803 | { \ |
df7492f9 KH |
1804 | int i = 0; \ |
1805 | while (consumed_chars < consumed_chars_limit) \ | |
aa72b389 | 1806 | { \ |
df7492f9 | 1807 | if (i % 2 && method != COMPOSITION_WITH_ALTCHARS) \ |
781d7a48 | 1808 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (charbuf); \ |
df7492f9 KH |
1809 | else \ |
1810 | DECODE_EMACS_MULE_COMPOSITION_CHAR (charbuf); \ | |
781d7a48 | 1811 | i++; \ |
aa72b389 | 1812 | } \ |
df7492f9 KH |
1813 | if (consumed_chars < consumed_chars_limit) \ |
1814 | goto invalid_code; \ | |
781d7a48 | 1815 | charbuf_base[0] -= i; \ |
aa72b389 KH |
1816 | } \ |
1817 | } while (0) | |
93dec019 | 1818 | |
aa72b389 | 1819 | |
df7492f9 KH |
1820 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION(c) \ |
1821 | do { \ | |
1822 | /* Emacs 20 style format for relative composition. */ \ | |
1823 | /* Store multibyte form of characters to be composed. */ \ | |
1824 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ | |
1825 | int *buf = components; \ | |
1826 | int i, j; \ | |
1827 | \ | |
1828 | src = src_base; \ | |
1829 | ONE_MORE_BYTE (c); /* skip 0x80 */ \ | |
1830 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
1831 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
1832 | if (i < 2) \ | |
1833 | goto invalid_code; \ | |
1834 | ADD_COMPOSITION_DATA (charbuf, COMPOSITION_RELATIVE, i); \ | |
1835 | for (j = 0; j < i; j++) \ | |
1836 | *charbuf++ = components[j]; \ | |
1837 | } while (0) | |
1838 | ||
1839 | ||
1840 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION(c) \ | |
1841 | do { \ | |
1842 | /* Emacs 20 style format for rule-base composition. */ \ | |
1843 | /* Store multibyte form of characters to be composed. */ \ | |
1844 | int components[MAX_COMPOSITION_COMPONENTS * 2 - 1]; \ | |
1845 | int *buf = components; \ | |
1846 | int i, j; \ | |
1847 | \ | |
1848 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ | |
1849 | for (i = 0; i < MAX_COMPOSITION_COMPONENTS; i++) \ | |
1850 | { \ | |
781d7a48 | 1851 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (buf); \ |
df7492f9 KH |
1852 | DECODE_EMACS_MULE_COMPOSITION_CHAR (buf); \ |
1853 | } \ | |
1854 | if (i < 1 || (buf - components) % 2 == 0) \ | |
1855 | goto invalid_code; \ | |
1856 | if (charbuf + i + (i / 2) + 1 < charbuf_end) \ | |
1857 | goto no_more_source; \ | |
1858 | ADD_COMPOSITION_DATA (buf, COMPOSITION_WITH_RULE, i); \ | |
1859 | for (j = 0; j < i; j++) \ | |
1860 | *charbuf++ = components[j]; \ | |
1861 | for (j = 0; j < i; j += 2) \ | |
1862 | *charbuf++ = components[j]; \ | |
1863 | } while (0) | |
1864 | ||
aa72b389 KH |
1865 | |
1866 | static void | |
df7492f9 | 1867 | decode_coding_emacs_mule (coding) |
aa72b389 | 1868 | struct coding_system *coding; |
aa72b389 | 1869 | { |
df7492f9 KH |
1870 | unsigned char *src = coding->source + coding->consumed; |
1871 | unsigned char *src_end = coding->source + coding->src_bytes; | |
aa72b389 | 1872 | unsigned char *src_base; |
df7492f9 KH |
1873 | int *charbuf = coding->charbuf; |
1874 | int *charbuf_end = charbuf + coding->charbuf_size; | |
1875 | int consumed_chars = 0, consumed_chars_base; | |
1876 | int char_offset = 0; | |
1877 | int multibytep = coding->src_multibyte; | |
1878 | Lisp_Object attrs, eol_type, charset_list; | |
aa72b389 | 1879 | |
df7492f9 | 1880 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
aa72b389 | 1881 | |
aa72b389 KH |
1882 | while (1) |
1883 | { | |
df7492f9 KH |
1884 | int c; |
1885 | ||
aa72b389 | 1886 | src_base = src; |
df7492f9 KH |
1887 | consumed_chars_base = consumed_chars; |
1888 | ||
1889 | if (charbuf >= charbuf_end) | |
1890 | break; | |
aa72b389 | 1891 | |
df7492f9 KH |
1892 | ONE_MORE_BYTE (c); |
1893 | ||
1894 | if (c < 0x80) | |
aa72b389 | 1895 | { |
df7492f9 KH |
1896 | if (c == '\r') |
1897 | { | |
1898 | if (EQ (eol_type, Qdos)) | |
1899 | { | |
1900 | if (src == src_end) | |
1901 | goto no_more_source; | |
1902 | if (*src == '\n') | |
1903 | ONE_MORE_BYTE (c); | |
1904 | } | |
1905 | else if (EQ (eol_type, Qmac)) | |
1906 | c = '\n'; | |
1907 | } | |
1908 | *charbuf++ = c; | |
1909 | char_offset++; | |
aa72b389 | 1910 | } |
df7492f9 KH |
1911 | else if (c == 0x80) |
1912 | { | |
1913 | if (charbuf + 5 + (MAX_COMPOSITION_COMPONENTS * 2) - 1 > charbuf_end) | |
1914 | break; | |
1915 | ONE_MORE_BYTE (c); | |
781d7a48 KH |
1916 | if (c - 0xF2 >= COMPOSITION_RELATIVE |
1917 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) | |
df7492f9 KH |
1918 | DECODE_EMACS_MULE_21_COMPOSITION (c); |
1919 | else if (c < 0xC0) | |
1920 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (c); | |
1921 | else if (c == 0xFF) | |
1922 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (c); | |
1923 | else | |
1924 | goto invalid_code; | |
781d7a48 | 1925 | coding->annotated = 1; |
df7492f9 KH |
1926 | } |
1927 | else if (c < 0xA0 && emacs_mule_bytes[c] > 1) | |
1928 | { | |
1929 | int nbytes, nchars; | |
781d7a48 KH |
1930 | src = src_base; |
1931 | consumed_chars = consumed_chars_base; | |
1932 | c = emacs_mule_char (coding, src, &nbytes, &nchars); | |
df7492f9 KH |
1933 | if (c < 0) |
1934 | { | |
1935 | if (c == -2) | |
1936 | break; | |
1937 | goto invalid_code; | |
1938 | } | |
1939 | *charbuf++ = c; | |
781d7a48 KH |
1940 | src += nbytes; |
1941 | consumed_chars += nchars; | |
df7492f9 KH |
1942 | char_offset++; |
1943 | } | |
1944 | continue; | |
1945 | ||
1946 | invalid_code: | |
1947 | src = src_base; | |
1948 | consumed_chars = consumed_chars_base; | |
1949 | ONE_MORE_BYTE (c); | |
1950 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1951 | coding->errors++; | |
1952 | } | |
1953 | ||
1954 | no_more_source: | |
1955 | coding->consumed_char += consumed_chars_base; | |
1956 | coding->consumed = src_base - coding->source; | |
1957 | coding->charbuf_used = charbuf - coding->charbuf; | |
1958 | } | |
1959 | ||
1960 | ||
1961 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
1962 | do { \ | |
1963 | if (id < 0xA0) \ | |
1964 | codes[0] = id, codes[1] = 0; \ | |
1965 | else if (id < 0xE0) \ | |
1966 | codes[0] = 0x9A, codes[1] = id; \ | |
1967 | else if (id < 0xF0) \ | |
1968 | codes[0] = 0x9B, codes[1] = id; \ | |
1969 | else if (id < 0xF5) \ | |
1970 | codes[0] = 0x9C, codes[1] = id; \ | |
1971 | else \ | |
1972 | codes[0] = 0x9D, codes[1] = id; \ | |
1973 | } while (0); | |
1974 | ||
aa72b389 | 1975 | |
df7492f9 KH |
1976 | static int |
1977 | encode_coding_emacs_mule (coding) | |
1978 | struct coding_system *coding; | |
1979 | { | |
1980 | int multibytep = coding->dst_multibyte; | |
1981 | int *charbuf = coding->charbuf; | |
1982 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1983 | unsigned char *dst = coding->destination + coding->produced; | |
1984 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1985 | int safe_room = 8; | |
df7492f9 KH |
1986 | int produced_chars = 0; |
1987 | Lisp_Object attrs, eol_type, charset_list; | |
1988 | int c; | |
1989 | ||
1990 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
1991 | ||
1992 | while (charbuf < charbuf_end) | |
1993 | { | |
1994 | ASSURE_DESTINATION (safe_room); | |
1995 | c = *charbuf++; | |
1996 | if (ASCII_CHAR_P (c)) | |
1997 | EMIT_ONE_ASCII_BYTE (c); | |
1998 | else | |
aa72b389 | 1999 | { |
df7492f9 KH |
2000 | struct charset *charset; |
2001 | unsigned code; | |
2002 | int dimension; | |
2003 | int emacs_mule_id; | |
2004 | unsigned char leading_codes[2]; | |
2005 | ||
2006 | charset = char_charset (c, charset_list, &code); | |
2007 | if (! charset) | |
2008 | { | |
2009 | c = coding->default_char; | |
2010 | if (ASCII_CHAR_P (c)) | |
2011 | { | |
2012 | EMIT_ONE_ASCII_BYTE (c); | |
2013 | continue; | |
2014 | } | |
2015 | charset = char_charset (c, charset_list, &code); | |
2016 | } | |
2017 | dimension = CHARSET_DIMENSION (charset); | |
2018 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2019 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2020 | EMIT_ONE_BYTE (leading_codes[0]); | |
2021 | if (leading_codes[1]) | |
2022 | EMIT_ONE_BYTE (leading_codes[1]); | |
2023 | if (dimension == 1) | |
2024 | EMIT_ONE_BYTE (code); | |
aa72b389 | 2025 | else |
df7492f9 KH |
2026 | { |
2027 | EMIT_ONE_BYTE (code >> 8); | |
2028 | EMIT_ONE_BYTE (code & 0xFF); | |
2029 | } | |
aa72b389 | 2030 | } |
aa72b389 | 2031 | } |
df7492f9 KH |
2032 | coding->result = CODING_RESULT_SUCCESS; |
2033 | coding->produced_char += produced_chars; | |
2034 | coding->produced = dst - coding->destination; | |
2035 | return 0; | |
aa72b389 | 2036 | } |
b73bfc1c | 2037 | |
4ed46869 | 2038 | \f |
df7492f9 | 2039 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2040 | |
2041 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2042 | Since the intention of this note is to help understand the |
df7492f9 | 2043 | functions in this file, some parts are NOT ACCURATE or OVERLY |
39787efd | 2044 | SIMPLIFIED. For thorough understanding, please refer to the |
df7492f9 | 2045 | original document of ISO2022. |
4ed46869 KH |
2046 | |
2047 | ISO2022 provides many mechanisms to encode several character sets | |
df7492f9 | 2048 | in 7-bit and 8-bit environments. For 7-bite environments, all text |
39787efd KH |
2049 | is encoded using bytes less than 128. This may make the encoded |
2050 | text a little bit longer, but the text passes more easily through | |
df7492f9 | 2051 | several gateways, some of which strip off MSB (Most Signigant Bit). |
b73bfc1c | 2052 | |
df7492f9 KH |
2053 | There are two kinds of character sets: control character set and |
2054 | graphic character set. The former contains control characters such | |
4ed46869 | 2055 | as `newline' and `escape' to provide control functions (control |
39787efd | 2056 | functions are also provided by escape sequences). The latter |
df7492f9 | 2057 | contains graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2058 | two control character sets and many graphic character sets. |
2059 | ||
2060 | Graphic character sets are classified into one of the following | |
39787efd KH |
2061 | four classes, according to the number of bytes (DIMENSION) and |
2062 | number of characters in one dimension (CHARS) of the set: | |
2063 | - DIMENSION1_CHARS94 | |
2064 | - DIMENSION1_CHARS96 | |
2065 | - DIMENSION2_CHARS94 | |
2066 | - DIMENSION2_CHARS96 | |
2067 | ||
2068 | In addition, each character set is assigned an identification tag, | |
df7492f9 | 2069 | unique for each set, called "final character" (denoted as <F> |
39787efd KH |
2070 | hereafter). The <F> of each character set is decided by ECMA(*) |
2071 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2072 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2073 | |
2074 | Note (*): ECMA = European Computer Manufacturers Association | |
2075 | ||
df7492f9 | 2076 | Here are examples of graphic character set [NAME(<F>)]: |
4ed46869 KH |
2077 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2078 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2079 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2080 | o DIMENSION2_CHARS96 -- none for the moment | |
2081 | ||
39787efd | 2082 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2083 | C0 [0x00..0x1F] -- control character plane 0 |
2084 | GL [0x20..0x7F] -- graphic character plane 0 | |
2085 | C1 [0x80..0x9F] -- control character plane 1 | |
2086 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2087 | ||
2088 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2089 | C1 by an escape sequence. The most common case is that: |
2090 | - ISO646's control character set is designated/invoked to C0, and | |
2091 | - ISO6429's control character set is designated/invoked to C1, | |
2092 | and usually these designations/invocations are omitted in encoded | |
2093 | text. In a 7-bit environment, only C0 can be used, and a control | |
2094 | character for C1 is encoded by an appropriate escape sequence to | |
2095 | fit into the environment. All control characters for C1 are | |
2096 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2097 | |
2098 | A graphic character set is at first designated to one of four | |
2099 | graphic registers (G0 through G3), then these graphic registers are | |
2100 | invoked to GL or GR. These designations and invocations can be | |
2101 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2102 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2103 | these invocations and designations are omitted in encoded text. | |
2104 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2105 | |
39787efd KH |
2106 | When a graphic character set of CHARS94 is invoked to GL, codes |
2107 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2108 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2109 | be used. | |
4ed46869 KH |
2110 | |
2111 | There are two ways of invocation: locking-shift and single-shift. | |
2112 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2113 | invocation, whereas with single-shift, the invocation affects the |
2114 | following character only and doesn't affect the locking-shift | |
2115 | state. Invocations are done by the following control characters or | |
2116 | escape sequences: | |
4ed46869 KH |
2117 | |
2118 | ---------------------------------------------------------------------- | |
39787efd | 2119 | abbrev function cntrl escape seq description |
4ed46869 | 2120 | ---------------------------------------------------------------------- |
39787efd KH |
2121 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2122 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2123 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2124 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2125 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2126 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2127 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2128 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2129 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2130 | ---------------------------------------------------------------------- |
39787efd KH |
2131 | (*) These are not used by any known coding system. |
2132 | ||
2133 | Control characters for these functions are defined by macros | |
2134 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2135 | |
39787efd | 2136 | Designations are done by the following escape sequences: |
4ed46869 KH |
2137 | ---------------------------------------------------------------------- |
2138 | escape sequence description | |
2139 | ---------------------------------------------------------------------- | |
2140 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2141 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2142 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2143 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2144 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2145 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2146 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2147 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2148 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2149 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2150 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2151 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2152 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2153 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2154 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2155 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2156 | ---------------------------------------------------------------------- | |
2157 | ||
2158 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2159 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2160 | |
2161 | Note (*): Although these designations are not allowed in ISO2022, | |
2162 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2163 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2164 | 7-bit environment, non-locking-shift, and non-single-shift. |
2165 | ||
2166 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2167 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2168 | |
df7492f9 | 2169 | Now you may notice that there are a lot of ways for encoding the |
39787efd KH |
2170 | same multilingual text in ISO2022. Actually, there exist many |
2171 | coding systems such as Compound Text (used in X11's inter client | |
df7492f9 KH |
2172 | communication, ISO-2022-JP (used in Japanese internet), ISO-2022-KR |
2173 | (used in Korean internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2174 | localized platforms), and all of these are variants of ISO2022. |
2175 | ||
2176 | In addition to the above, Emacs handles two more kinds of escape | |
2177 | sequences: ISO6429's direction specification and Emacs' private | |
2178 | sequence for specifying character composition. | |
2179 | ||
39787efd | 2180 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2181 | o CSI ']' -- end of the current direction |
2182 | o CSI '0' ']' -- end of the current direction | |
2183 | o CSI '1' ']' -- start of left-to-right text | |
2184 | o CSI '2' ']' -- start of right-to-left text | |
2185 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2186 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2187 | ||
2188 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2189 | o ESC '0' -- start relative composition |
2190 | o ESC '1' -- end composition | |
2191 | o ESC '2' -- start rule-base composition (*) | |
2192 | o ESC '3' -- start relative composition with alternate chars (**) | |
2193 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2194 | Since these are not standard escape sequences of any ISO standard, |
df7492f9 | 2195 | the use of them for these meaning is restricted to Emacs only. |
ec6d2bb8 | 2196 | |
df7492f9 | 2197 | (*) This form is used only in Emacs 20.5 and the older versions, |
b73bfc1c | 2198 | but the newer versions can safely decode it. |
df7492f9 | 2199 | (**) This form is used only in Emacs 21.1 and the newer versions, |
b73bfc1c | 2200 | and the older versions can't decode it. |
ec6d2bb8 | 2201 | |
df7492f9 | 2202 | Here's a list of examples usages of these composition escape |
b73bfc1c | 2203 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2204 | |
b73bfc1c | 2205 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2206 | ESC 0 CHAR [ CHAR ] ESC 1 |
df7492f9 | 2207 | COMPOSITOIN_WITH_RULE: |
ec6d2bb8 | 2208 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2209 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2210 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2211 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2212 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2213 | |
2214 | enum iso_code_class_type iso_code_class[256]; | |
2215 | ||
df7492f9 KH |
2216 | #define SAFE_CHARSET_P(coding, id) \ |
2217 | ((id) <= (coding)->max_charset_id \ | |
2218 | && (coding)->safe_charsets[id] >= 0) | |
2219 | ||
2220 | ||
2221 | #define SHIFT_OUT_OK(category) \ | |
2222 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2223 | ||
2224 | static void | |
f0064e1f DL |
2225 | setup_iso_safe_charsets (attrs) |
2226 | Lisp_Object attrs; | |
df7492f9 KH |
2227 | { |
2228 | Lisp_Object charset_list, safe_charsets; | |
2229 | Lisp_Object request; | |
2230 | Lisp_Object reg_usage; | |
2231 | Lisp_Object tail; | |
2232 | int reg94, reg96; | |
2233 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2234 | int max_charset_id; | |
2235 | ||
2236 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2237 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2238 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2239 | { | |
2240 | CODING_ATTR_CHARSET_LIST (attrs) | |
2241 | = charset_list = Viso_2022_charset_list; | |
2242 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2243 | } | |
2244 | ||
2245 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2246 | return; | |
2247 | ||
2248 | max_charset_id = 0; | |
2249 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2250 | { | |
2251 | int id = XINT (XCAR (tail)); | |
2252 | if (max_charset_id < id) | |
2253 | max_charset_id = id; | |
2254 | } | |
2255 | ||
2256 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
2257 | make_number (255)); | |
2258 | request = AREF (attrs, coding_attr_iso_request); | |
2259 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2260 | reg94 = XINT (XCAR (reg_usage)); | |
2261 | reg96 = XINT (XCDR (reg_usage)); | |
2262 | ||
2263 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2264 | { | |
2265 | Lisp_Object id; | |
2266 | Lisp_Object reg; | |
2267 | struct charset *charset; | |
2268 | ||
2269 | id = XCAR (tail); | |
2270 | charset = CHARSET_FROM_ID (XINT (id)); | |
2271 | reg = Fcdr (Fassq (request, id)); | |
2272 | if (! NILP (reg)) | |
2273 | XSTRING (safe_charsets)->data[XINT (id)] = XINT (reg); | |
2274 | else if (charset->iso_chars_96) | |
2275 | { | |
2276 | if (reg96 < 4) | |
2277 | XSTRING (safe_charsets)->data[XINT (id)] = reg96; | |
2278 | } | |
2279 | else | |
2280 | { | |
2281 | if (reg94 < 4) | |
2282 | XSTRING (safe_charsets)->data[XINT (id)] = reg94; | |
2283 | } | |
2284 | } | |
2285 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2286 | } | |
d46c5b12 | 2287 | |
d46c5b12 | 2288 | |
4ed46869 | 2289 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
df7492f9 | 2290 | Check if a text is encoded in ISO2022. If it is, returns an |
4ed46869 | 2291 | integer in which appropriate flag bits any of: |
df7492f9 KH |
2292 | CATEGORY_MASK_ISO_7 |
2293 | CATEGORY_MASK_ISO_7_TIGHT | |
2294 | CATEGORY_MASK_ISO_8_1 | |
2295 | CATEGORY_MASK_ISO_8_2 | |
2296 | CATEGORY_MASK_ISO_7_ELSE | |
2297 | CATEGORY_MASK_ISO_8_ELSE | |
4ed46869 KH |
2298 | are set. If a code which should never appear in ISO2022 is found, |
2299 | returns 0. */ | |
2300 | ||
0a28aafb | 2301 | static int |
df7492f9 KH |
2302 | detect_coding_iso_2022 (coding, mask) |
2303 | struct coding_system *coding; | |
2304 | int *mask; | |
4ed46869 | 2305 | { |
df7492f9 KH |
2306 | unsigned char *src = coding->source, *src_base = src; |
2307 | unsigned char *src_end = coding->source + coding->src_bytes; | |
2308 | int multibytep = coding->src_multibyte; | |
2309 | int mask_iso = CATEGORY_MASK_ISO; | |
2310 | int mask_found = 0, mask_8bit_found = 0; | |
f46869e4 | 2311 | int reg[4], shift_out = 0, single_shifting = 0; |
df7492f9 KH |
2312 | int id; |
2313 | int c, c1; | |
2314 | int consumed_chars = 0; | |
2315 | int i; | |
2316 | ||
2317 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2318 | { | |
2319 | struct coding_system *this = &(coding_categories[i]); | |
2320 | Lisp_Object attrs, val; | |
2321 | ||
2322 | attrs = CODING_ID_ATTRS (this->id); | |
2323 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
2324 | && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list)) | |
2325 | setup_iso_safe_charsets (attrs); | |
2326 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
2327 | this->max_charset_id = XSTRING (val)->size - 1; | |
2328 | this->safe_charsets = (char *) XSTRING (val)->data; | |
2329 | } | |
2330 | ||
2331 | /* A coding system of this category is always ASCII compatible. */ | |
2332 | src += coding->head_ascii; | |
3f003981 | 2333 | |
df7492f9 KH |
2334 | reg[0] = charset_ascii, reg[1] = reg[2] = reg[3] = -1; |
2335 | while (mask_iso && src < src_end) | |
4ed46869 | 2336 | { |
df7492f9 | 2337 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2338 | switch (c) |
2339 | { | |
2340 | case ISO_CODE_ESC: | |
74383408 KH |
2341 | if (inhibit_iso_escape_detection) |
2342 | break; | |
f46869e4 | 2343 | single_shifting = 0; |
df7492f9 | 2344 | ONE_MORE_BYTE (c); |
d46c5b12 | 2345 | if (c >= '(' && c <= '/') |
4ed46869 | 2346 | { |
bf9cdd4e | 2347 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 2348 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2349 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2350 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
2351 | /* Invalid designation sequence. Just ignore. */ |
2352 | break; | |
df7492f9 | 2353 | reg[(c - '(') % 4] = id; |
bf9cdd4e KH |
2354 | } |
2355 | else if (c == '$') | |
2356 | { | |
2357 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 2358 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
2359 | if (c >= '@' && c <= 'B') |
2360 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
df7492f9 | 2361 | reg[0] = id = iso_charset_table[1][0][c]; |
bf9cdd4e | 2362 | else if (c >= '(' && c <= '/') |
bcf26d6a | 2363 | { |
df7492f9 | 2364 | ONE_MORE_BYTE (c1); |
d46c5b12 | 2365 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 2366 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
2367 | /* Invalid designation sequence. Just ignore. */ |
2368 | break; | |
df7492f9 | 2369 | reg[(c - '(') % 4] = id; |
bcf26d6a | 2370 | } |
bf9cdd4e | 2371 | else |
d46c5b12 KH |
2372 | /* Invalid designation sequence. Just ignore. */ |
2373 | break; | |
2374 | } | |
ae9ff118 | 2375 | else if (c == 'N' || c == 'O') |
d46c5b12 | 2376 | { |
ae9ff118 | 2377 | /* ESC <Fe> for SS2 or SS3. */ |
df7492f9 | 2378 | mask_iso &= CATEGORY_MASK_ISO_7_ELSE; |
d46c5b12 | 2379 | break; |
4ed46869 | 2380 | } |
ec6d2bb8 KH |
2381 | else if (c >= '0' && c <= '4') |
2382 | { | |
2383 | /* ESC <Fp> for start/end composition. */ | |
df7492f9 | 2384 | mask_found |= CATEGORY_MASK_ISO; |
ec6d2bb8 KH |
2385 | break; |
2386 | } | |
bf9cdd4e | 2387 | else |
df7492f9 KH |
2388 | { |
2389 | /* Invalid escape sequence. */ | |
2390 | mask_iso &= ~CATEGORY_MASK_ISO_ESCAPE; | |
2391 | break; | |
2392 | } | |
d46c5b12 KH |
2393 | |
2394 | /* We found a valid designation sequence for CHARSET. */ | |
df7492f9 KH |
2395 | mask_iso &= ~CATEGORY_MASK_ISO_8BIT; |
2396 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], | |
2397 | id)) | |
2398 | mask_found |= CATEGORY_MASK_ISO_7; | |
d46c5b12 | 2399 | else |
df7492f9 KH |
2400 | mask_iso &= ~CATEGORY_MASK_ISO_7; |
2401 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], | |
2402 | id)) | |
2403 | mask_found |= CATEGORY_MASK_ISO_7_TIGHT; | |
d46c5b12 | 2404 | else |
df7492f9 KH |
2405 | mask_iso &= ~CATEGORY_MASK_ISO_7_TIGHT; |
2406 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], | |
2407 | id)) | |
2408 | mask_found |= CATEGORY_MASK_ISO_7_ELSE; | |
ae9ff118 | 2409 | else |
df7492f9 KH |
2410 | mask_iso &= ~CATEGORY_MASK_ISO_7_ELSE; |
2411 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], | |
2412 | id)) | |
2413 | mask_found |= CATEGORY_MASK_ISO_8_ELSE; | |
ae9ff118 | 2414 | else |
df7492f9 | 2415 | mask_iso &= ~CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
2416 | break; |
2417 | ||
4ed46869 | 2418 | case ISO_CODE_SO: |
74383408 KH |
2419 | if (inhibit_iso_escape_detection) |
2420 | break; | |
f46869e4 | 2421 | single_shifting = 0; |
d46c5b12 KH |
2422 | if (shift_out == 0 |
2423 | && (reg[1] >= 0 | |
df7492f9 KH |
2424 | || SHIFT_OUT_OK (coding_category_iso_7_else) |
2425 | || SHIFT_OUT_OK (coding_category_iso_8_else))) | |
d46c5b12 KH |
2426 | { |
2427 | /* Locking shift out. */ | |
df7492f9 KH |
2428 | mask_iso &= ~CATEGORY_MASK_ISO_7BIT; |
2429 | mask_found |= CATEGORY_MASK_ISO_ELSE; | |
d46c5b12 | 2430 | } |
e0e989f6 | 2431 | break; |
df7492f9 | 2432 | |
d46c5b12 | 2433 | case ISO_CODE_SI: |
74383408 KH |
2434 | if (inhibit_iso_escape_detection) |
2435 | break; | |
f46869e4 | 2436 | single_shifting = 0; |
d46c5b12 KH |
2437 | if (shift_out == 1) |
2438 | { | |
2439 | /* Locking shift in. */ | |
df7492f9 KH |
2440 | mask_iso &= ~CATEGORY_MASK_ISO_7BIT; |
2441 | mask_found |= CATEGORY_MASK_ISO_ELSE; | |
d46c5b12 KH |
2442 | } |
2443 | break; | |
2444 | ||
4ed46869 | 2445 | case ISO_CODE_CSI: |
f46869e4 | 2446 | single_shifting = 0; |
4ed46869 KH |
2447 | case ISO_CODE_SS2: |
2448 | case ISO_CODE_SS3: | |
3f003981 | 2449 | { |
df7492f9 | 2450 | int newmask = CATEGORY_MASK_ISO_8_ELSE; |
3f003981 | 2451 | |
74383408 KH |
2452 | if (inhibit_iso_escape_detection) |
2453 | break; | |
70c22245 KH |
2454 | if (c != ISO_CODE_CSI) |
2455 | { | |
df7492f9 KH |
2456 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) |
2457 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
2458 | newmask |= CATEGORY_MASK_ISO_8_1; | |
2459 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) | |
2460 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
2461 | newmask |= CATEGORY_MASK_ISO_8_2; | |
f46869e4 | 2462 | single_shifting = 1; |
70c22245 | 2463 | } |
3f003981 KH |
2464 | if (VECTORP (Vlatin_extra_code_table) |
2465 | && !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
2466 | { | |
df7492f9 KH |
2467 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) |
2468 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2469 | newmask |= CATEGORY_MASK_ISO_8_1; | |
2470 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) | |
2471 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2472 | newmask |= CATEGORY_MASK_ISO_8_2; | |
3f003981 | 2473 | } |
df7492f9 | 2474 | mask_iso &= newmask; |
d46c5b12 | 2475 | mask_found |= newmask; |
3f003981 KH |
2476 | } |
2477 | break; | |
4ed46869 KH |
2478 | |
2479 | default: | |
2480 | if (c < 0x80) | |
f46869e4 KH |
2481 | { |
2482 | single_shifting = 0; | |
2483 | break; | |
2484 | } | |
4ed46869 | 2485 | else if (c < 0xA0) |
c4825358 | 2486 | { |
f46869e4 | 2487 | single_shifting = 0; |
df7492f9 | 2488 | mask_8bit_found = 1; |
3f003981 KH |
2489 | if (VECTORP (Vlatin_extra_code_table) |
2490 | && !NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
c4825358 | 2491 | { |
3f003981 KH |
2492 | int newmask = 0; |
2493 | ||
df7492f9 KH |
2494 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) |
2495 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2496 | newmask |= CATEGORY_MASK_ISO_8_1; | |
2497 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) | |
2498 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
2499 | newmask |= CATEGORY_MASK_ISO_8_2; | |
2500 | mask_iso &= newmask; | |
d46c5b12 | 2501 | mask_found |= newmask; |
c4825358 | 2502 | } |
3f003981 KH |
2503 | else |
2504 | return 0; | |
c4825358 | 2505 | } |
4ed46869 KH |
2506 | else |
2507 | { | |
df7492f9 KH |
2508 | mask_iso &= ~(CATEGORY_MASK_ISO_7BIT |
2509 | | CATEGORY_MASK_ISO_7_ELSE); | |
2510 | mask_found |= CATEGORY_MASK_ISO_8_1; | |
2511 | mask_8bit_found = 1; | |
f46869e4 KH |
2512 | /* Check the length of succeeding codes of the range |
2513 | 0xA0..0FF. If the byte length is odd, we exclude | |
df7492f9 | 2514 | CATEGORY_MASK_ISO_8_2. We can check this only |
f46869e4 | 2515 | when we are not single shifting. */ |
b73bfc1c | 2516 | if (!single_shifting |
df7492f9 | 2517 | && mask_iso & CATEGORY_MASK_ISO_8_2) |
f46869e4 | 2518 | { |
e17de821 | 2519 | int i = 1; |
b73bfc1c KH |
2520 | while (src < src_end) |
2521 | { | |
df7492f9 | 2522 | ONE_MORE_BYTE (c); |
b73bfc1c KH |
2523 | if (c < 0xA0) |
2524 | break; | |
2525 | i++; | |
2526 | } | |
2527 | ||
2528 | if (i & 1 && src < src_end) | |
df7492f9 | 2529 | mask_iso &= ~CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2530 | else |
df7492f9 | 2531 | mask_found |= CATEGORY_MASK_ISO_8_2; |
f46869e4 | 2532 | } |
4ed46869 KH |
2533 | } |
2534 | break; | |
2535 | } | |
2536 | } | |
df7492f9 KH |
2537 | no_more_source: |
2538 | if (!mask_iso) | |
2539 | { | |
2540 | *mask &= ~CATEGORY_MASK_ISO; | |
2541 | return 0; | |
2542 | } | |
2543 | if (!mask_found) | |
2544 | return 0; | |
2545 | *mask &= mask_iso & mask_found; | |
2546 | if (! mask_8bit_found) | |
2547 | *mask &= ~(CATEGORY_MASK_ISO_8BIT | CATEGORY_MASK_ISO_8_ELSE); | |
2548 | return 1; | |
4ed46869 KH |
2549 | } |
2550 | ||
4ed46869 KH |
2551 | |
2552 | /* Set designation state into CODING. */ | |
df7492f9 KH |
2553 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
2554 | do { \ | |
2555 | int id, prev; \ | |
2556 | \ | |
2557 | if (final < '0' || final >= 128 \ | |
2558 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
2559 | || !SAFE_CHARSET_P (coding, id)) \ | |
2560 | { \ | |
2561 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
2562 | goto invalid_code; \ | |
2563 | } \ | |
2564 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
2565 | CODING_ISO_DESIGNATION (coding, reg) = id; \ | |
2566 | /* If there was an invalid designation to REG previously, and this \ | |
2567 | designation is ASCII to REG, we should keep this designation \ | |
2568 | sequence. */ \ | |
2569 | if (prev == -2 && id == charset_ascii) \ | |
2570 | goto invalid_code; \ | |
4ed46869 KH |
2571 | } while (0) |
2572 | ||
d46c5b12 | 2573 | |
df7492f9 KH |
2574 | #define MAYBE_FINISH_COMPOSITION() \ |
2575 | do { \ | |
2576 | int i; \ | |
2577 | if (composition_state == COMPOSING_NO) \ | |
2578 | break; \ | |
2579 | /* It is assured that we have enough room for producing \ | |
2580 | characters stored in the table `components'. */ \ | |
2581 | if (charbuf + component_idx > charbuf_end) \ | |
2582 | goto no_more_source; \ | |
2583 | composition_state = COMPOSING_NO; \ | |
2584 | if (method == COMPOSITION_RELATIVE \ | |
2585 | || method == COMPOSITION_WITH_ALTCHARS) \ | |
2586 | { \ | |
2587 | for (i = 0; i < component_idx; i++) \ | |
2588 | *charbuf++ = components[i]; \ | |
2589 | char_offset += component_idx; \ | |
2590 | } \ | |
2591 | else \ | |
2592 | { \ | |
2593 | for (i = 0; i < component_idx; i += 2) \ | |
2594 | *charbuf++ = components[i]; \ | |
2595 | char_offset += (component_idx / 2) + 1; \ | |
2596 | } \ | |
2597 | } while (0) | |
2598 | ||
d46c5b12 | 2599 | |
aa72b389 KH |
2600 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
2601 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 | |
2602 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
2603 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
2604 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
aa72b389 | 2605 | */ |
ec6d2bb8 | 2606 | |
df7492f9 KH |
2607 | #define DECODE_COMPOSITION_START(c1) \ |
2608 | do { \ | |
2609 | if (c1 == '0' \ | |
781d7a48 | 2610 | && composition_state == COMPOSING_COMPONENT_RULE) \ |
df7492f9 KH |
2611 | { \ |
2612 | component_len = component_idx; \ | |
2613 | composition_state = COMPOSING_CHAR; \ | |
2614 | } \ | |
2615 | else \ | |
2616 | { \ | |
2617 | unsigned char *p; \ | |
2618 | \ | |
2619 | MAYBE_FINISH_COMPOSITION (); \ | |
2620 | if (charbuf + MAX_COMPOSITION_COMPONENTS > charbuf_end) \ | |
2621 | goto no_more_source; \ | |
2622 | for (p = src; p < src_end - 1; p++) \ | |
2623 | if (*p == ISO_CODE_ESC && p[1] == '1') \ | |
2624 | break; \ | |
2625 | if (p == src_end - 1) \ | |
2626 | { \ | |
2627 | if (coding->mode & CODING_MODE_LAST_BLOCK) \ | |
2628 | goto invalid_code; \ | |
2629 | goto no_more_source; \ | |
2630 | } \ | |
2631 | \ | |
2632 | /* This is surely the start of a composition. */ \ | |
2633 | method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
2634 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
2635 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
2636 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
2637 | composition_state = (c1 <= '2' ? COMPOSING_CHAR \ | |
2638 | : COMPOSING_COMPONENT_CHAR); \ | |
2639 | component_idx = component_len = 0; \ | |
2640 | } \ | |
ec6d2bb8 KH |
2641 | } while (0) |
2642 | ||
ec6d2bb8 | 2643 | |
df7492f9 KH |
2644 | /* Handle compositoin end sequence ESC 1. */ |
2645 | ||
2646 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 2647 | do { \ |
df7492f9 KH |
2648 | int nchars = (component_len > 0 ? component_idx - component_len \ |
2649 | : method == COMPOSITION_RELATIVE ? component_idx \ | |
2650 | : (component_idx + 1) / 2); \ | |
2651 | int i; \ | |
2652 | int *saved_charbuf = charbuf; \ | |
2653 | \ | |
2654 | ADD_COMPOSITION_DATA (charbuf, method, nchars); \ | |
2655 | if (method != COMPOSITION_RELATIVE) \ | |
ec6d2bb8 | 2656 | { \ |
df7492f9 KH |
2657 | if (component_len == 0) \ |
2658 | for (i = 0; i < component_idx; i++) \ | |
2659 | *charbuf++ = components[i]; \ | |
2660 | else \ | |
2661 | for (i = 0; i < component_len; i++) \ | |
2662 | *charbuf++ = components[i]; \ | |
2663 | *saved_charbuf = saved_charbuf - charbuf; \ | |
ec6d2bb8 | 2664 | } \ |
df7492f9 KH |
2665 | if (method == COMPOSITION_WITH_RULE) \ |
2666 | for (i = 0; i < component_idx; i += 2, char_offset++) \ | |
2667 | *charbuf++ = components[i]; \ | |
ec6d2bb8 | 2668 | else \ |
df7492f9 KH |
2669 | for (i = component_len; i < component_idx; i++, char_offset++) \ |
2670 | *charbuf++ = components[i]; \ | |
2671 | coding->annotated = 1; \ | |
2672 | composition_state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
2673 | } while (0) |
2674 | ||
df7492f9 | 2675 | |
ec6d2bb8 KH |
2676 | /* Decode a composition rule from the byte C1 (and maybe one more byte |
2677 | from SRC) and store one encoded composition rule in | |
2678 | coding->cmp_data. */ | |
2679 | ||
2680 | #define DECODE_COMPOSITION_RULE(c1) \ | |
2681 | do { \ | |
ec6d2bb8 KH |
2682 | (c1) -= 32; \ |
2683 | if (c1 < 81) /* old format (before ver.21) */ \ | |
2684 | { \ | |
2685 | int gref = (c1) / 9; \ | |
2686 | int nref = (c1) % 9; \ | |
2687 | if (gref == 4) gref = 10; \ | |
2688 | if (nref == 4) nref = 10; \ | |
df7492f9 | 2689 | c1 = COMPOSITION_ENCODE_RULE (gref, nref); \ |
ec6d2bb8 | 2690 | } \ |
b73bfc1c | 2691 | else if (c1 < 93) /* new format (after ver.21) */ \ |
ec6d2bb8 KH |
2692 | { \ |
2693 | ONE_MORE_BYTE (c2); \ | |
df7492f9 | 2694 | c1 = COMPOSITION_ENCODE_RULE (c1 - 81, c2 - 32); \ |
ec6d2bb8 | 2695 | } \ |
df7492f9 KH |
2696 | else \ |
2697 | c1 = 0; \ | |
ec6d2bb8 | 2698 | } while (0) |
88993dfd | 2699 | |
d46c5b12 | 2700 | |
4ed46869 KH |
2701 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
2702 | ||
b73bfc1c | 2703 | static void |
df7492f9 | 2704 | decode_coding_iso_2022 (coding) |
4ed46869 | 2705 | struct coding_system *coding; |
4ed46869 | 2706 | { |
df7492f9 KH |
2707 | unsigned char *src = coding->source + coding->consumed; |
2708 | unsigned char *src_end = coding->source + coding->src_bytes; | |
b73bfc1c | 2709 | unsigned char *src_base; |
df7492f9 KH |
2710 | int *charbuf = coding->charbuf; |
2711 | int *charbuf_end = charbuf + coding->charbuf_size - 4; | |
2712 | int consumed_chars = 0, consumed_chars_base; | |
2713 | int char_offset = 0; | |
2714 | int multibytep = coding->src_multibyte; | |
2715 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ | |
2716 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
2717 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
2718 | struct charset *charset; | |
2719 | int c; | |
2720 | /* For handling composition sequence. */ | |
2721 | #define COMPOSING_NO 0 | |
2722 | #define COMPOSING_CHAR 1 | |
2723 | #define COMPOSING_RULE 2 | |
2724 | #define COMPOSING_COMPONENT_CHAR 3 | |
2725 | #define COMPOSING_COMPONENT_RULE 4 | |
2726 | ||
2727 | int composition_state = COMPOSING_NO; | |
2728 | enum composition_method method; | |
2729 | int components[MAX_COMPOSITION_COMPONENTS * 2 + 1]; | |
2730 | int component_idx; | |
2731 | int component_len; | |
2732 | Lisp_Object attrs, eol_type, charset_list; | |
2733 | ||
2734 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
2735 | setup_iso_safe_charsets (attrs); | |
b73bfc1c KH |
2736 | |
2737 | while (1) | |
4ed46869 | 2738 | { |
b73bfc1c KH |
2739 | int c1, c2; |
2740 | ||
2741 | src_base = src; | |
df7492f9 KH |
2742 | consumed_chars_base = consumed_chars; |
2743 | ||
2744 | if (charbuf >= charbuf_end) | |
2745 | break; | |
2746 | ||
b73bfc1c | 2747 | ONE_MORE_BYTE (c1); |
4ed46869 | 2748 | |
ec6d2bb8 | 2749 | /* We produce no character or one character. */ |
4ed46869 KH |
2750 | switch (iso_code_class [c1]) |
2751 | { | |
2752 | case ISO_0x20_or_0x7F: | |
df7492f9 | 2753 | if (composition_state != COMPOSING_NO) |
ec6d2bb8 | 2754 | { |
df7492f9 KH |
2755 | if (composition_state == COMPOSING_RULE |
2756 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2757 | { | |
2758 | DECODE_COMPOSITION_RULE (c1); | |
2759 | components[component_idx++] = c1; | |
2760 | composition_state--; | |
2761 | continue; | |
2762 | } | |
ec6d2bb8 | 2763 | } |
df7492f9 KH |
2764 | if (charset_id_0 < 0 |
2765 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
2766 | /* This is SPACE or DEL. */ |
2767 | charset = CHARSET_FROM_ID (charset_ascii); | |
2768 | else | |
2769 | charset = CHARSET_FROM_ID (charset_id_0); | |
2770 | break; | |
4ed46869 KH |
2771 | |
2772 | case ISO_graphic_plane_0: | |
781d7a48 | 2773 | if (composition_state != COMPOSING_NO) |
b73bfc1c | 2774 | { |
781d7a48 KH |
2775 | if (composition_state == COMPOSING_RULE |
2776 | || composition_state == COMPOSING_COMPONENT_RULE) | |
2777 | { | |
2778 | DECODE_COMPOSITION_RULE (c1); | |
2779 | components[component_idx++] = c1; | |
2780 | composition_state--; | |
2781 | continue; | |
2782 | } | |
b73bfc1c | 2783 | } |
df7492f9 | 2784 | charset = CHARSET_FROM_ID (charset_id_0); |
4ed46869 KH |
2785 | break; |
2786 | ||
2787 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
2788 | if (charset_id_1 < 0 |
2789 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
2790 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
2791 | goto invalid_code; | |
4ed46869 KH |
2792 | /* This is a graphic character, we fall down ... */ |
2793 | ||
2794 | case ISO_graphic_plane_1: | |
df7492f9 KH |
2795 | if (charset_id_1 < 0) |
2796 | goto invalid_code; | |
2797 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
2798 | break; |
2799 | ||
2800 | case ISO_carriage_return: | |
df7492f9 | 2801 | if (c1 == '\r') |
4ed46869 | 2802 | { |
df7492f9 | 2803 | if (EQ (eol_type, Qdos)) |
4ed46869 | 2804 | { |
df7492f9 KH |
2805 | if (src == src_end) |
2806 | goto no_more_source; | |
2807 | if (*src == '\n') | |
2808 | ONE_MORE_BYTE (c1); | |
4ed46869 | 2809 | } |
df7492f9 KH |
2810 | else if (EQ (eol_type, Qmac)) |
2811 | c1 = '\n'; | |
4ed46869 | 2812 | } |
df7492f9 KH |
2813 | /* fall through */ |
2814 | ||
2815 | case ISO_control_0: | |
2816 | MAYBE_FINISH_COMPOSITION (); | |
2817 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
2818 | break; |
2819 | ||
df7492f9 KH |
2820 | case ISO_control_1: |
2821 | MAYBE_FINISH_COMPOSITION (); | |
2822 | goto invalid_code; | |
2823 | ||
4ed46869 | 2824 | case ISO_shift_out: |
df7492f9 KH |
2825 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
2826 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
2827 | goto invalid_code; | |
2828 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
2829 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2830 | continue; |
4ed46869 KH |
2831 | |
2832 | case ISO_shift_in: | |
df7492f9 KH |
2833 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
2834 | goto invalid_code; | |
2835 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
2836 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2837 | continue; |
4ed46869 KH |
2838 | |
2839 | case ISO_single_shift_2_7: | |
2840 | case ISO_single_shift_2: | |
df7492f9 KH |
2841 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
2842 | goto invalid_code; | |
4ed46869 KH |
2843 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
2844 | c1 = 'N'; | |
2845 | goto label_escape_sequence; | |
2846 | ||
2847 | case ISO_single_shift_3: | |
df7492f9 KH |
2848 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
2849 | goto invalid_code; | |
4ed46869 KH |
2850 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
2851 | c1 = 'O'; | |
2852 | goto label_escape_sequence; | |
2853 | ||
2854 | case ISO_control_sequence_introducer: | |
2855 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
2856 | c1 = '['; | |
2857 | goto label_escape_sequence; | |
2858 | ||
2859 | case ISO_escape: | |
2860 | ONE_MORE_BYTE (c1); | |
2861 | label_escape_sequence: | |
df7492f9 | 2862 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
2863 | designation, direction specification, and character |
2864 | composition specification. */ | |
2865 | switch (c1) | |
2866 | { | |
2867 | case '&': /* revision of following character set */ | |
2868 | ONE_MORE_BYTE (c1); | |
2869 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 2870 | goto invalid_code; |
4ed46869 KH |
2871 | ONE_MORE_BYTE (c1); |
2872 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 2873 | goto invalid_code; |
4ed46869 KH |
2874 | ONE_MORE_BYTE (c1); |
2875 | goto label_escape_sequence; | |
2876 | ||
2877 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
2878 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
2879 | goto invalid_code; | |
4ed46869 KH |
2880 | ONE_MORE_BYTE (c1); |
2881 | if (c1 >= '@' && c1 <= 'B') | |
2882 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 2883 | or JISX0208.1980 */ |
df7492f9 | 2884 | DECODE_DESIGNATION (0, 2, 0, c1); |
4ed46869 KH |
2885 | } |
2886 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
2887 | { /* designation of DIMENSION2_CHARS94 character set */ | |
2888 | ONE_MORE_BYTE (c2); | |
df7492f9 | 2889 | DECODE_DESIGNATION (c1 - 0x28, 2, 0, c2); |
4ed46869 KH |
2890 | } |
2891 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
2892 | { /* designation of DIMENSION2_CHARS96 character set */ | |
2893 | ONE_MORE_BYTE (c2); | |
df7492f9 | 2894 | DECODE_DESIGNATION (c1 - 0x2C, 2, 1, c2); |
4ed46869 KH |
2895 | } |
2896 | else | |
df7492f9 | 2897 | goto invalid_code; |
b73bfc1c | 2898 | /* We must update these variables now. */ |
df7492f9 KH |
2899 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
2900 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
b73bfc1c | 2901 | continue; |
4ed46869 KH |
2902 | |
2903 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
2904 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
2905 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
2906 | goto invalid_code; | |
2907 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
2908 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2909 | continue; |
4ed46869 KH |
2910 | |
2911 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
2912 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
2913 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
2914 | goto invalid_code; | |
2915 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
2916 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 2917 | continue; |
4ed46869 KH |
2918 | |
2919 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
2920 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
2921 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
2922 | goto invalid_code; | |
2923 | charset = CHARSET_FROM_ID (CODING_ISO_DESIGNATION (coding, 2)); | |
b73bfc1c | 2924 | ONE_MORE_BYTE (c1); |
e7046a18 | 2925 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 2926 | goto invalid_code; |
4ed46869 KH |
2927 | break; |
2928 | ||
2929 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
2930 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
2931 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
2932 | goto invalid_code; | |
2933 | charset = CHARSET_FROM_ID (CODING_ISO_DESIGNATION (coding, 3)); | |
b73bfc1c | 2934 | ONE_MORE_BYTE (c1); |
e7046a18 | 2935 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 2936 | goto invalid_code; |
4ed46869 KH |
2937 | break; |
2938 | ||
ec6d2bb8 | 2939 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
2940 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
2941 | goto invalid_code; | |
ec6d2bb8 | 2942 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 2943 | continue; |
4ed46869 | 2944 | |
ec6d2bb8 | 2945 | case '1': /* end composition */ |
df7492f9 KH |
2946 | if (composition_state == COMPOSING_NO) |
2947 | goto invalid_code; | |
2948 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 2949 | continue; |
4ed46869 KH |
2950 | |
2951 | case '[': /* specification of direction */ | |
df7492f9 KH |
2952 | if (! CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION) |
2953 | goto invalid_code; | |
4ed46869 | 2954 | /* For the moment, nested direction is not supported. |
d46c5b12 | 2955 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
df7492f9 | 2956 | left-to-right, and nozero means right-to-left. */ |
4ed46869 KH |
2957 | ONE_MORE_BYTE (c1); |
2958 | switch (c1) | |
2959 | { | |
2960 | case ']': /* end of the current direction */ | |
d46c5b12 | 2961 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
2962 | |
2963 | case '0': /* end of the current direction */ | |
2964 | case '1': /* start of left-to-right direction */ | |
2965 | ONE_MORE_BYTE (c1); | |
2966 | if (c1 == ']') | |
d46c5b12 | 2967 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 2968 | else |
df7492f9 | 2969 | goto invalid_code; |
4ed46869 KH |
2970 | break; |
2971 | ||
2972 | case '2': /* start of right-to-left direction */ | |
2973 | ONE_MORE_BYTE (c1); | |
2974 | if (c1 == ']') | |
d46c5b12 | 2975 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 2976 | else |
df7492f9 | 2977 | goto invalid_code; |
4ed46869 KH |
2978 | break; |
2979 | ||
2980 | default: | |
df7492f9 | 2981 | goto invalid_code; |
4ed46869 | 2982 | } |
b73bfc1c | 2983 | continue; |
4ed46869 KH |
2984 | |
2985 | default: | |
df7492f9 KH |
2986 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
2987 | goto invalid_code; | |
4ed46869 KH |
2988 | if (c1 >= 0x28 && c1 <= 0x2B) |
2989 | { /* designation of DIMENSION1_CHARS94 character set */ | |
2990 | ONE_MORE_BYTE (c2); | |
df7492f9 | 2991 | DECODE_DESIGNATION (c1 - 0x28, 1, 0, c2); |
4ed46869 KH |
2992 | } |
2993 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
2994 | { /* designation of DIMENSION1_CHARS96 character set */ | |
2995 | ONE_MORE_BYTE (c2); | |
df7492f9 | 2996 | DECODE_DESIGNATION (c1 - 0x2C, 1, 1, c2); |
4ed46869 KH |
2997 | } |
2998 | else | |
df7492f9 | 2999 | goto invalid_code; |
b73bfc1c | 3000 | /* We must update these variables now. */ |
df7492f9 KH |
3001 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3002 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
b73bfc1c | 3003 | continue; |
4ed46869 | 3004 | } |
b73bfc1c | 3005 | } |
4ed46869 | 3006 | |
b73bfc1c | 3007 | /* Now we know CHARSET and 1st position code C1 of a character. |
df7492f9 KH |
3008 | Produce a decoded character while getting 2nd position code |
3009 | C2 if necessary. */ | |
3010 | c1 &= 0x7F; | |
3011 | if (CHARSET_DIMENSION (charset) > 1) | |
b73bfc1c KH |
3012 | { |
3013 | ONE_MORE_BYTE (c2); | |
df7492f9 | 3014 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) |
b73bfc1c | 3015 | /* C2 is not in a valid range. */ |
df7492f9 KH |
3016 | goto invalid_code; |
3017 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3018 | if (CHARSET_DIMENSION (charset) > 2) | |
3019 | { | |
3020 | ONE_MORE_BYTE (c2); | |
3021 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0)) | |
3022 | /* C2 is not in a valid range. */ | |
3023 | goto invalid_code; | |
3024 | c1 = (c1 << 8) | (c2 & 0x7F); | |
3025 | } | |
3026 | } | |
3027 | ||
3028 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); | |
3029 | if (c < 0) | |
3030 | { | |
3031 | MAYBE_FINISH_COMPOSITION (); | |
3032 | for (; src_base < src; src_base++, char_offset++) | |
3033 | { | |
3034 | if (ASCII_BYTE_P (*src_base)) | |
3035 | *charbuf++ = *src_base; | |
3036 | else | |
3037 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3038 | } | |
3039 | } | |
3040 | else if (composition_state == COMPOSING_NO) | |
3041 | { | |
3042 | *charbuf++ = c; | |
3043 | char_offset++; | |
4ed46869 | 3044 | } |
df7492f9 | 3045 | else |
781d7a48 KH |
3046 | { |
3047 | components[component_idx++] = c; | |
3048 | if (method == COMPOSITION_WITH_RULE | |
3049 | || (method == COMPOSITION_WITH_RULE_ALTCHARS | |
3050 | && composition_state == COMPOSING_COMPONENT_CHAR)) | |
3051 | composition_state++; | |
3052 | } | |
4ed46869 KH |
3053 | continue; |
3054 | ||
df7492f9 KH |
3055 | invalid_code: |
3056 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3057 | src = src_base; |
df7492f9 KH |
3058 | consumed_chars = consumed_chars_base; |
3059 | ONE_MORE_BYTE (c); | |
3060 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
3061 | coding->errors++; | |
4ed46869 | 3062 | } |
fb88bf2d | 3063 | |
df7492f9 KH |
3064 | no_more_source: |
3065 | coding->consumed_char += consumed_chars_base; | |
3066 | coding->consumed = src_base - coding->source; | |
3067 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3068 | } |
3069 | ||
b73bfc1c | 3070 | |
f4dee582 | 3071 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3072 | |
3073 | /* | |
f4dee582 | 3074 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3075 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3076 | variant has the following specifications: |
df7492f9 | 3077 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3078 | 2. Allows short-form designation? |
3079 | 3. ASCII should be designated to G0 before control characters? | |
3080 | 4. ASCII should be designated to G0 at end of line? | |
3081 | 5. 7-bit environment or 8-bit environment? | |
3082 | 6. Use locking-shift? | |
3083 | 7. Use Single-shift? | |
3084 | And the following two are only for Japanese: | |
3085 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3086 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3087 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3088 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3089 | details. |
4ed46869 KH |
3090 | */ |
3091 | ||
3092 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3093 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3094 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3095 | designation sequence of short-form. */ | |
4ed46869 KH |
3096 | |
3097 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3098 | do { \ | |
df7492f9 | 3099 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
4ed46869 KH |
3100 | char *intermediate_char_94 = "()*+"; \ |
3101 | char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
3102 | int revision = -1; \ |
3103 | int c; \ | |
3104 | \ | |
3105 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
3106 | revision = XINT (CHARSET_ISO_REVISION (charset)); \ | |
3107 | \ | |
3108 | if (revision >= 0) \ | |
70c22245 | 3109 | { \ |
df7492f9 KH |
3110 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3111 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3112 | } \ |
df7492f9 | 3113 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3114 | if (CHARSET_DIMENSION (charset) == 1) \ |
3115 | { \ | |
df7492f9 KH |
3116 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
3117 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 3118 | else \ |
df7492f9 KH |
3119 | c = intermediate_char_96[reg]; \ |
3120 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
3121 | } \ |
3122 | else \ | |
3123 | { \ | |
df7492f9 KH |
3124 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3125 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3126 | { \ |
df7492f9 | 3127 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3128 | || reg != 0 \ |
3129 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3130 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3131 | } \ |
3132 | else \ | |
df7492f9 | 3133 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3134 | } \ |
df7492f9 KH |
3135 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3136 | \ | |
3137 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3138 | } while (0) |
3139 | ||
df7492f9 | 3140 | |
4ed46869 KH |
3141 | /* The following two macros produce codes (control character or escape |
3142 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3143 | single-shift-3). */ | |
3144 | ||
df7492f9 KH |
3145 | #define ENCODE_SINGLE_SHIFT_2 \ |
3146 | do { \ | |
3147 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3148 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3149 | else \ | |
3150 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3151 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3152 | } while (0) |
3153 | ||
df7492f9 KH |
3154 | |
3155 | #define ENCODE_SINGLE_SHIFT_3 \ | |
3156 | do { \ | |
3157 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3158 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
3159 | else \ | |
3160 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
3161 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
3162 | } while (0) |
3163 | ||
df7492f9 | 3164 | |
4ed46869 KH |
3165 | /* The following four macros produce codes (control character or |
3166 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
3167 | shift-out, locking-shift-2, and locking-shift-3). */ | |
3168 | ||
df7492f9 KH |
3169 | #define ENCODE_SHIFT_IN \ |
3170 | do { \ | |
3171 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
3172 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
3173 | } while (0) |
3174 | ||
df7492f9 KH |
3175 | |
3176 | #define ENCODE_SHIFT_OUT \ | |
3177 | do { \ | |
3178 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
3179 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
3180 | } while (0) |
3181 | ||
df7492f9 KH |
3182 | |
3183 | #define ENCODE_LOCKING_SHIFT_2 \ | |
3184 | do { \ | |
3185 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3186 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
3187 | } while (0) |
3188 | ||
df7492f9 KH |
3189 | |
3190 | #define ENCODE_LOCKING_SHIFT_3 \ | |
3191 | do { \ | |
3192 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
3193 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
3194 | } while (0) |
3195 | ||
df7492f9 | 3196 | |
f4dee582 RS |
3197 | /* Produce codes for a DIMENSION1 character whose character set is |
3198 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
3199 | sequences are also produced in advance if necessary. */ |
3200 | ||
6e85d753 KH |
3201 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
3202 | do { \ | |
df7492f9 KH |
3203 | int id = CHARSET_ID (charset); \ |
3204 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ | |
6e85d753 | 3205 | { \ |
df7492f9 KH |
3206 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3207 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 3208 | else \ |
df7492f9 KH |
3209 | EMIT_ONE_BYTE (c1 | 0x80); \ |
3210 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3211 | break; \ |
3212 | } \ | |
df7492f9 | 3213 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3214 | { \ |
df7492f9 | 3215 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
3216 | break; \ |
3217 | } \ | |
df7492f9 | 3218 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3219 | { \ |
df7492f9 | 3220 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
3221 | break; \ |
3222 | } \ | |
6e85d753 KH |
3223 | else \ |
3224 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3225 | must invoke it, or, at first, designate it to some graphic \ | |
3226 | register. Then repeat the loop to actually produce the \ | |
3227 | character. */ \ | |
df7492f9 KH |
3228 | dst = encode_invocation_designation (charset, coding, dst, \ |
3229 | &produced_chars); \ | |
4ed46869 KH |
3230 | } while (1) |
3231 | ||
df7492f9 | 3232 | |
f4dee582 RS |
3233 | /* Produce codes for a DIMENSION2 character whose character set is |
3234 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
3235 | invocation codes are also produced in advance if necessary. */ |
3236 | ||
6e85d753 KH |
3237 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
3238 | do { \ | |
df7492f9 KH |
3239 | int id = CHARSET_ID (charset); \ |
3240 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ | |
6e85d753 | 3241 | { \ |
df7492f9 KH |
3242 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
3243 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 3244 | else \ |
df7492f9 KH |
3245 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
3246 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
3247 | break; \ |
3248 | } \ | |
df7492f9 | 3249 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 3250 | { \ |
df7492f9 | 3251 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
3252 | break; \ |
3253 | } \ | |
df7492f9 | 3254 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 3255 | { \ |
df7492f9 | 3256 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
3257 | break; \ |
3258 | } \ | |
6e85d753 KH |
3259 | else \ |
3260 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
3261 | must invoke it, or, at first, designate it to some graphic \ | |
3262 | register. Then repeat the loop to actually produce the \ | |
3263 | character. */ \ | |
df7492f9 KH |
3264 | dst = encode_invocation_designation (charset, coding, dst, \ |
3265 | &produced_chars); \ | |
4ed46869 KH |
3266 | } while (1) |
3267 | ||
05e6f5dc | 3268 | |
df7492f9 KH |
3269 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
3270 | do { \ | |
3271 | int code = ENCODE_CHAR ((charset),(c)); \ | |
3272 | \ | |
3273 | if (CHARSET_DIMENSION (charset) == 1) \ | |
3274 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
3275 | else \ | |
3276 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 3277 | } while (0) |
bdd9fb48 | 3278 | |
05e6f5dc | 3279 | |
4ed46869 | 3280 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 3281 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
3282 | Return new DST. */ |
3283 | ||
3284 | unsigned char * | |
df7492f9 KH |
3285 | encode_invocation_designation (charset, coding, dst, p_nchars) |
3286 | struct charset *charset; | |
4ed46869 KH |
3287 | struct coding_system *coding; |
3288 | unsigned char *dst; | |
df7492f9 | 3289 | int *p_nchars; |
4ed46869 | 3290 | { |
df7492f9 KH |
3291 | int multibytep = coding->dst_multibyte; |
3292 | int produced_chars = *p_nchars; | |
4ed46869 | 3293 | int reg; /* graphic register number */ |
df7492f9 | 3294 | int id = CHARSET_ID (charset); |
4ed46869 KH |
3295 | |
3296 | /* At first, check designations. */ | |
3297 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 3298 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
3299 | break; |
3300 | ||
3301 | if (reg >= 4) | |
3302 | { | |
3303 | /* CHARSET is not yet designated to any graphic registers. */ | |
3304 | /* At first check the requested designation. */ | |
df7492f9 KH |
3305 | reg = CODING_ISO_REQUEST (coding, id); |
3306 | if (reg < 0) | |
1ba9e4ab KH |
3307 | /* Since CHARSET requests no special designation, designate it |
3308 | to graphic register 0. */ | |
4ed46869 KH |
3309 | reg = 0; |
3310 | ||
3311 | ENCODE_DESIGNATION (charset, reg, coding); | |
3312 | } | |
3313 | ||
df7492f9 KH |
3314 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
3315 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
3316 | { |
3317 | /* Since the graphic register REG is not invoked to any graphic | |
3318 | planes, invoke it to graphic plane 0. */ | |
3319 | switch (reg) | |
3320 | { | |
3321 | case 0: /* graphic register 0 */ | |
3322 | ENCODE_SHIFT_IN; | |
3323 | break; | |
3324 | ||
3325 | case 1: /* graphic register 1 */ | |
3326 | ENCODE_SHIFT_OUT; | |
3327 | break; | |
3328 | ||
3329 | case 2: /* graphic register 2 */ | |
df7492f9 | 3330 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3331 | ENCODE_SINGLE_SHIFT_2; |
3332 | else | |
3333 | ENCODE_LOCKING_SHIFT_2; | |
3334 | break; | |
3335 | ||
3336 | case 3: /* graphic register 3 */ | |
df7492f9 | 3337 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
3338 | ENCODE_SINGLE_SHIFT_3; |
3339 | else | |
3340 | ENCODE_LOCKING_SHIFT_3; | |
3341 | break; | |
3342 | } | |
3343 | } | |
b73bfc1c | 3344 | |
df7492f9 | 3345 | *p_nchars = produced_chars; |
4ed46869 KH |
3346 | return dst; |
3347 | } | |
3348 | ||
df7492f9 KH |
3349 | /* The following three macros produce codes for indicating direction |
3350 | of text. */ | |
3351 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 3352 | do { \ |
df7492f9 KH |
3353 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
3354 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 3355 | else \ |
df7492f9 | 3356 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
3357 | } while (0) |
3358 | ||
ec6d2bb8 | 3359 | |
df7492f9 KH |
3360 | #define ENCODE_DIRECTION_R2L() \ |
3361 | do { \ | |
3362 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
3363 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
3364 | } while (0) |
3365 | ||
ec6d2bb8 | 3366 | |
df7492f9 | 3367 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 3368 | do { \ |
df7492f9 KH |
3369 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
3370 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
4ed46869 KH |
3371 | } while (0) |
3372 | ||
4ed46869 KH |
3373 | |
3374 | /* Produce codes for designation and invocation to reset the graphic | |
3375 | planes and registers to initial state. */ | |
df7492f9 KH |
3376 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
3377 | do { \ | |
3378 | int reg; \ | |
3379 | struct charset *charset; \ | |
3380 | \ | |
3381 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
3382 | ENCODE_SHIFT_IN; \ | |
3383 | for (reg = 0; reg < 4; reg++) \ | |
3384 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
3385 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
3386 | != CODING_ISO_INITIAL (coding, reg))) \ | |
3387 | { \ | |
3388 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
3389 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
3390 | } \ | |
4ed46869 KH |
3391 | } while (0) |
3392 | ||
df7492f9 | 3393 | |
bdd9fb48 | 3394 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 3395 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
3396 | |
3397 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
3398 | find all the necessary designations. */ |
3399 | ||
b73bfc1c | 3400 | static unsigned char * |
df7492f9 | 3401 | encode_designation_at_bol (coding, charbuf, charbuf_end, dst) |
e0e989f6 | 3402 | struct coding_system *coding; |
df7492f9 KH |
3403 | int *charbuf, *charbuf_end; |
3404 | unsigned char *dst; | |
e0e989f6 | 3405 | { |
df7492f9 | 3406 | struct charset *charset; |
bdd9fb48 KH |
3407 | /* Table of charsets to be designated to each graphic register. */ |
3408 | int r[4]; | |
df7492f9 KH |
3409 | int c, found = 0, reg; |
3410 | int produced_chars = 0; | |
3411 | int multibytep = coding->dst_multibyte; | |
3412 | Lisp_Object attrs; | |
3413 | Lisp_Object charset_list; | |
3414 | ||
3415 | attrs = CODING_ID_ATTRS (coding->id); | |
3416 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
3417 | if (EQ (charset_list, Qiso_2022)) | |
3418 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
3419 | |
3420 | for (reg = 0; reg < 4; reg++) | |
3421 | r[reg] = -1; | |
3422 | ||
b73bfc1c | 3423 | while (found < 4) |
e0e989f6 | 3424 | { |
df7492f9 KH |
3425 | int id; |
3426 | ||
3427 | c = *charbuf++; | |
b73bfc1c KH |
3428 | if (c == '\n') |
3429 | break; | |
df7492f9 KH |
3430 | charset = char_charset (c, charset_list, NULL); |
3431 | id = CHARSET_ID (charset); | |
3432 | reg = CODING_ISO_REQUEST (coding, id); | |
3433 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
3434 | { |
3435 | found++; | |
df7492f9 | 3436 | r[reg] = id; |
bdd9fb48 | 3437 | } |
bdd9fb48 KH |
3438 | } |
3439 | ||
3440 | if (found) | |
3441 | { | |
3442 | for (reg = 0; reg < 4; reg++) | |
3443 | if (r[reg] >= 0 | |
df7492f9 KH |
3444 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
3445 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 3446 | } |
b73bfc1c KH |
3447 | |
3448 | return dst; | |
e0e989f6 KH |
3449 | } |
3450 | ||
4ed46869 KH |
3451 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
3452 | ||
df7492f9 KH |
3453 | static int |
3454 | encode_coding_iso_2022 (coding) | |
4ed46869 | 3455 | struct coding_system *coding; |
4ed46869 | 3456 | { |
df7492f9 KH |
3457 | int multibytep = coding->dst_multibyte; |
3458 | int *charbuf = coding->charbuf; | |
3459 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3460 | unsigned char *dst = coding->destination + coding->produced; | |
3461 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3462 | int safe_room = 16; | |
3463 | int bol_designation | |
3464 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
3465 | && CODING_ISO_BOL (coding)); | |
3466 | int produced_chars = 0; | |
3467 | Lisp_Object attrs, eol_type, charset_list; | |
3468 | int ascii_compatible; | |
b73bfc1c | 3469 | int c; |
05e6f5dc | 3470 | |
df7492f9 | 3471 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
004068e4 KH |
3472 | setup_iso_safe_charsets (attrs); |
3473 | coding->safe_charsets | |
3474 | = (char *) XSTRING (CODING_ATTR_SAFE_CHARSETS(attrs))->data; | |
bdd9fb48 | 3475 | |
df7492f9 | 3476 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
4ed46869 | 3477 | |
df7492f9 | 3478 | while (charbuf < charbuf_end) |
4ed46869 | 3479 | { |
df7492f9 | 3480 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 3481 | |
df7492f9 | 3482 | if (bol_designation) |
b73bfc1c | 3483 | { |
df7492f9 | 3484 | unsigned char *dst_prev = dst; |
4ed46869 | 3485 | |
bdd9fb48 | 3486 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
3487 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
3488 | bol_designation = 0; | |
3489 | /* We are sure that designation sequences are all ASCII bytes. */ | |
3490 | produced_chars += dst - dst_prev; | |
4ed46869 | 3491 | } |
ec6d2bb8 | 3492 | |
df7492f9 | 3493 | c = *charbuf++; |
4ed46869 | 3494 | |
b73bfc1c KH |
3495 | /* Now encode the character C. */ |
3496 | if (c < 0x20 || c == 0x7F) | |
3497 | { | |
df7492f9 KH |
3498 | if (c == '\n' |
3499 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 3500 | { |
df7492f9 KH |
3501 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
3502 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3503 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 3504 | { |
df7492f9 KH |
3505 | int i; |
3506 | ||
3507 | for (i = 0; i < 4; i++) | |
3508 | CODING_ISO_DESIGNATION (coding, i) | |
3509 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 3510 | } |
df7492f9 KH |
3511 | bol_designation |
3512 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 3513 | } |
df7492f9 KH |
3514 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
3515 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3516 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 3517 | } |
df7492f9 | 3518 | else if (ASCII_CHAR_P (c)) |
88993dfd | 3519 | { |
df7492f9 KH |
3520 | if (ascii_compatible) |
3521 | EMIT_ONE_ASCII_BYTE (c); | |
3522 | else | |
3523 | ENCODE_ISO_CHARACTER (CHARSET_FROM_ID (charset_ascii), c); | |
88993dfd | 3524 | } |
b73bfc1c | 3525 | else |
df7492f9 KH |
3526 | { |
3527 | struct charset *charset = char_charset (c, charset_list, NULL); | |
b73bfc1c | 3528 | |
df7492f9 KH |
3529 | if (!charset) |
3530 | { | |
41cbe562 KH |
3531 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3532 | { | |
3533 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3534 | charset = CHARSET_FROM_ID (charset_ascii); | |
3535 | } | |
3536 | else | |
3537 | { | |
3538 | c = coding->default_char; | |
3539 | charset = char_charset (c, charset_list, NULL); | |
3540 | } | |
df7492f9 KH |
3541 | } |
3542 | ENCODE_ISO_CHARACTER (charset, c); | |
3543 | } | |
84fbb8a0 | 3544 | } |
b73bfc1c | 3545 | |
df7492f9 KH |
3546 | if (coding->mode & CODING_MODE_LAST_BLOCK |
3547 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
3548 | { | |
3549 | ASSURE_DESTINATION (safe_room); | |
3550 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
3551 | } | |
3552 | coding->result = CODING_RESULT_SUCCESS; | |
3553 | CODING_ISO_BOL (coding) = bol_designation; | |
3554 | coding->produced_char += produced_chars; | |
3555 | coding->produced = dst - coding->destination; | |
3556 | return 0; | |
4ed46869 KH |
3557 | } |
3558 | ||
3559 | \f | |
df7492f9 | 3560 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 3561 | |
df7492f9 | 3562 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
3563 | quite widely. So, for the moment, Emacs supports them in the bare |
3564 | C code. But, in the future, they may be supported only by CCL. */ | |
3565 | ||
3566 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
3567 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
3568 | as is. A character of charset katakana-jisx0201 is encoded by | |
3569 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
3570 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 3571 | so that it fit in the range below. |
4ed46869 KH |
3572 | |
3573 | --- CODE RANGE of SJIS --- | |
3574 | (character set) (range) | |
3575 | ASCII 0x00 .. 0x7F | |
df7492f9 | 3576 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 3577 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 3578 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
3579 | ------------------------------- |
3580 | ||
3581 | */ | |
3582 | ||
3583 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
3584 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 3585 | character set and is encoded in two-byte. |
4ed46869 KH |
3586 | |
3587 | --- CODE RANGE of BIG5 --- | |
3588 | (character set) (range) | |
3589 | ASCII 0x00 .. 0x7F | |
3590 | Big5 (1st byte) 0xA1 .. 0xFE | |
3591 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
3592 | -------------------------- | |
3593 | ||
df7492f9 | 3594 | */ |
4ed46869 KH |
3595 | |
3596 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3597 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 3598 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 3599 | |
0a28aafb | 3600 | static int |
df7492f9 KH |
3601 | detect_coding_sjis (coding, mask) |
3602 | struct coding_system *coding; | |
3603 | int *mask; | |
4ed46869 | 3604 | { |
df7492f9 KH |
3605 | unsigned char *src = coding->source, *src_base = src; |
3606 | unsigned char *src_end = coding->source + coding->src_bytes; | |
3607 | int multibytep = coding->src_multibyte; | |
3608 | int consumed_chars = 0; | |
3609 | int found = 0; | |
b73bfc1c | 3610 | int c; |
df7492f9 KH |
3611 | |
3612 | /* A coding system of this category is always ASCII compatible. */ | |
3613 | src += coding->head_ascii; | |
4ed46869 | 3614 | |
b73bfc1c | 3615 | while (1) |
4ed46869 | 3616 | { |
df7492f9 | 3617 | ONE_MORE_BYTE (c); |
682169fe KH |
3618 | if (c < 0x80) |
3619 | continue; | |
df7492f9 | 3620 | if ((c >= 0x81 && c <= 0x9F) || (c >= 0xE0 && c <= 0xEF)) |
4ed46869 | 3621 | { |
df7492f9 | 3622 | ONE_MORE_BYTE (c); |
682169fe | 3623 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 KH |
3624 | break; |
3625 | found = 1; | |
4ed46869 | 3626 | } |
df7492f9 KH |
3627 | else if (c >= 0xA0 && c < 0xE0) |
3628 | found = 1; | |
3629 | else | |
3630 | break; | |
4ed46869 | 3631 | } |
df7492f9 KH |
3632 | *mask &= ~CATEGORY_MASK_SJIS; |
3633 | return 0; | |
3634 | ||
3635 | no_more_source: | |
3636 | if (!found) | |
3637 | return 0; | |
3638 | *mask &= CATEGORY_MASK_SJIS; | |
3639 | return 1; | |
4ed46869 KH |
3640 | } |
3641 | ||
3642 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
3643 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 3644 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 3645 | |
0a28aafb | 3646 | static int |
df7492f9 KH |
3647 | detect_coding_big5 (coding, mask) |
3648 | struct coding_system *coding; | |
3649 | int *mask; | |
4ed46869 | 3650 | { |
df7492f9 KH |
3651 | unsigned char *src = coding->source, *src_base = src; |
3652 | unsigned char *src_end = coding->source + coding->src_bytes; | |
3653 | int multibytep = coding->src_multibyte; | |
3654 | int consumed_chars = 0; | |
3655 | int found = 0; | |
b73bfc1c | 3656 | int c; |
fa42c37f | 3657 | |
df7492f9 KH |
3658 | /* A coding system of this category is always ASCII compatible. */ |
3659 | src += coding->head_ascii; | |
fa42c37f | 3660 | |
b73bfc1c | 3661 | while (1) |
fa42c37f | 3662 | { |
df7492f9 KH |
3663 | ONE_MORE_BYTE (c); |
3664 | if (c < 0x80) | |
fa42c37f | 3665 | continue; |
df7492f9 | 3666 | if (c >= 0xA1) |
fa42c37f | 3667 | { |
df7492f9 KH |
3668 | ONE_MORE_BYTE (c); |
3669 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 3670 | return 0; |
df7492f9 | 3671 | found = 1; |
fa42c37f | 3672 | } |
df7492f9 KH |
3673 | else |
3674 | break; | |
fa42c37f | 3675 | } |
df7492f9 | 3676 | *mask &= ~CATEGORY_MASK_BIG5; |
fa42c37f | 3677 | return 0; |
df7492f9 KH |
3678 | |
3679 | no_more_source: | |
3680 | if (!found) | |
3681 | return 0; | |
3682 | *mask &= CATEGORY_MASK_BIG5; | |
3683 | return 1; | |
fa42c37f KH |
3684 | } |
3685 | ||
4ed46869 KH |
3686 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
3687 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
3688 | ||
b73bfc1c | 3689 | static void |
df7492f9 | 3690 | decode_coding_sjis (coding) |
4ed46869 | 3691 | struct coding_system *coding; |
4ed46869 | 3692 | { |
df7492f9 KH |
3693 | unsigned char *src = coding->source + coding->consumed; |
3694 | unsigned char *src_end = coding->source + coding->src_bytes; | |
b73bfc1c | 3695 | unsigned char *src_base; |
df7492f9 KH |
3696 | int *charbuf = coding->charbuf; |
3697 | int *charbuf_end = charbuf + coding->charbuf_size; | |
3698 | int consumed_chars = 0, consumed_chars_base; | |
3699 | int multibytep = coding->src_multibyte; | |
3700 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
3701 | Lisp_Object attrs, eol_type, charset_list, val; | |
a5d301df | 3702 | |
df7492f9 KH |
3703 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
3704 | ||
3705 | val = charset_list; | |
3706 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
3707 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
3708 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 3709 | |
b73bfc1c | 3710 | while (1) |
4ed46869 | 3711 | { |
df7492f9 | 3712 | int c, c1; |
b73bfc1c KH |
3713 | |
3714 | src_base = src; | |
df7492f9 KH |
3715 | consumed_chars_base = consumed_chars; |
3716 | ||
3717 | if (charbuf >= charbuf_end) | |
3718 | break; | |
3719 | ||
3720 | ONE_MORE_BYTE (c); | |
b73bfc1c | 3721 | |
df7492f9 | 3722 | if (c == '\r') |
4ed46869 | 3723 | { |
df7492f9 | 3724 | if (EQ (eol_type, Qdos)) |
4ed46869 | 3725 | { |
df7492f9 KH |
3726 | if (src == src_end) |
3727 | goto no_more_source; | |
3728 | if (*src == '\n') | |
3729 | ONE_MORE_BYTE (c); | |
4ed46869 | 3730 | } |
df7492f9 KH |
3731 | else if (EQ (eol_type, Qmac)) |
3732 | c = '\n'; | |
4ed46869 | 3733 | } |
54f78171 | 3734 | else |
df7492f9 KH |
3735 | { |
3736 | struct charset *charset; | |
3737 | ||
3738 | if (c < 0x80) | |
3739 | charset = charset_roman; | |
3740 | else | |
4ed46869 | 3741 | { |
df7492f9 KH |
3742 | if (c >= 0xF0) |
3743 | goto invalid_code; | |
3744 | if (c < 0xA0 || c >= 0xE0) | |
fb88bf2d | 3745 | { |
54f78171 | 3746 | /* SJIS -> JISX0208 */ |
df7492f9 KH |
3747 | ONE_MORE_BYTE (c1); |
3748 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
3749 | goto invalid_code; | |
3750 | c = (c << 8) | c1; | |
3751 | SJIS_TO_JIS (c); | |
3752 | charset = charset_kanji; | |
5e34de15 | 3753 | } |
fb88bf2d | 3754 | else |
b73bfc1c | 3755 | /* SJIS -> JISX0201-Kana */ |
df7492f9 KH |
3756 | charset = charset_kana; |
3757 | } | |
3758 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
3759 | } | |
3760 | *charbuf++ = c; | |
3761 | continue; | |
3762 | ||
3763 | invalid_code: | |
3764 | src = src_base; | |
3765 | consumed_chars = consumed_chars_base; | |
3766 | ONE_MORE_BYTE (c); | |
3767 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
3768 | coding->errors++; | |
3769 | } | |
3770 | ||
3771 | no_more_source: | |
3772 | coding->consumed_char += consumed_chars_base; | |
3773 | coding->consumed = src_base - coding->source; | |
3774 | coding->charbuf_used = charbuf - coding->charbuf; | |
3775 | } | |
3776 | ||
3777 | static void | |
3778 | decode_coding_big5 (coding) | |
3779 | struct coding_system *coding; | |
3780 | { | |
3781 | unsigned char *src = coding->source + coding->consumed; | |
3782 | unsigned char *src_end = coding->source + coding->src_bytes; | |
3783 | unsigned char *src_base; | |
3784 | int *charbuf = coding->charbuf; | |
3785 | int *charbuf_end = charbuf + coding->charbuf_size; | |
3786 | int consumed_chars = 0, consumed_chars_base; | |
3787 | int multibytep = coding->src_multibyte; | |
3788 | struct charset *charset_roman, *charset_big5; | |
3789 | Lisp_Object attrs, eol_type, charset_list, val; | |
3790 | ||
3791 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
3792 | val = charset_list; | |
3793 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
3794 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
3795 | ||
3796 | while (1) | |
3797 | { | |
3798 | int c, c1; | |
3799 | ||
3800 | src_base = src; | |
3801 | consumed_chars_base = consumed_chars; | |
3802 | ||
3803 | if (charbuf >= charbuf_end) | |
3804 | break; | |
3805 | ||
3806 | ONE_MORE_BYTE (c); | |
3807 | ||
3808 | if (c == '\r') | |
3809 | { | |
3810 | if (EQ (eol_type, Qdos)) | |
3811 | { | |
3812 | if (src == src_end) | |
3813 | goto no_more_source; | |
3814 | if (*src == '\n') | |
3815 | ONE_MORE_BYTE (c); | |
4ed46869 | 3816 | } |
df7492f9 KH |
3817 | else if (EQ (eol_type, Qmac)) |
3818 | c = '\n'; | |
3819 | } | |
3820 | else | |
3821 | { | |
3822 | struct charset *charset; | |
3823 | if (c < 0x80) | |
3824 | charset = charset_roman; | |
fb88bf2d | 3825 | else |
fb88bf2d | 3826 | { |
54f78171 | 3827 | /* BIG5 -> Big5 */ |
df7492f9 KH |
3828 | if (c < 0xA1 || c > 0xFE) |
3829 | goto invalid_code; | |
3830 | ONE_MORE_BYTE (c1); | |
3831 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
3832 | goto invalid_code; | |
3833 | c = c << 8 | c1; | |
3834 | charset = charset_big5; | |
4ed46869 | 3835 | } |
df7492f9 | 3836 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
4ed46869 | 3837 | } |
4ed46869 | 3838 | |
df7492f9 | 3839 | *charbuf++ = c; |
fb88bf2d KH |
3840 | continue; |
3841 | ||
df7492f9 | 3842 | invalid_code: |
4ed46869 | 3843 | src = src_base; |
df7492f9 KH |
3844 | consumed_chars = consumed_chars_base; |
3845 | ONE_MORE_BYTE (c); | |
3846 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
3847 | coding->errors++; | |
fb88bf2d | 3848 | } |
d46c5b12 | 3849 | |
df7492f9 KH |
3850 | no_more_source: |
3851 | coding->consumed_char += consumed_chars_base; | |
3852 | coding->consumed = src_base - coding->source; | |
3853 | coding->charbuf_used = charbuf - coding->charbuf; | |
3854 | } | |
3855 | ||
3856 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
3857 | This function can encode charsets `ascii', `katakana-jisx0201', | |
3858 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
3859 | are sure that all these charsets are registered as official charset | |
3860 | (i.e. do not have extended leading-codes). Characters of other | |
3861 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
3862 | SJIS text, else encode BIG5 text. */ | |
3863 | ||
3864 | static int | |
3865 | encode_coding_sjis (coding) | |
3866 | struct coding_system *coding; | |
3867 | { | |
3868 | int multibytep = coding->dst_multibyte; | |
3869 | int *charbuf = coding->charbuf; | |
3870 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3871 | unsigned char *dst = coding->destination + coding->produced; | |
3872 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3873 | int safe_room = 4; | |
3874 | int produced_chars = 0; | |
3875 | Lisp_Object attrs, eol_type, charset_list, val; | |
3876 | int ascii_compatible; | |
3877 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
3878 | int c; | |
3879 | ||
3880 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
3881 | val = charset_list; | |
3882 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
3883 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
3884 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
3885 | ||
3886 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
3887 | ||
3888 | while (charbuf < charbuf_end) | |
3889 | { | |
3890 | ASSURE_DESTINATION (safe_room); | |
3891 | c = *charbuf++; | |
3892 | /* Now encode the character C. */ | |
3893 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
3894 | EMIT_ONE_ASCII_BYTE (c); | |
3895 | else | |
3896 | { | |
3897 | unsigned code; | |
3898 | struct charset *charset = char_charset (c, charset_list, &code); | |
3899 | ||
3900 | if (!charset) | |
3901 | { | |
41cbe562 KH |
3902 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3903 | { | |
3904 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3905 | charset = CHARSET_FROM_ID (charset_ascii); | |
3906 | } | |
3907 | else | |
3908 | { | |
3909 | c = coding->default_char; | |
3910 | charset = char_charset (c, charset_list, &code); | |
3911 | } | |
df7492f9 KH |
3912 | } |
3913 | if (code == CHARSET_INVALID_CODE (charset)) | |
3914 | abort (); | |
3915 | if (charset == charset_kanji) | |
3916 | { | |
3917 | int c1, c2; | |
3918 | JIS_TO_SJIS (code); | |
3919 | c1 = code >> 8, c2 = code & 0xFF; | |
3920 | EMIT_TWO_BYTES (c1, c2); | |
3921 | } | |
3922 | else if (charset == charset_kana) | |
3923 | EMIT_ONE_BYTE (code | 0x80); | |
3924 | else | |
3925 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
3926 | } | |
3927 | } | |
3928 | coding->result = CODING_RESULT_SUCCESS; | |
3929 | coding->produced_char += produced_chars; | |
3930 | coding->produced = dst - coding->destination; | |
3931 | return 0; | |
3932 | } | |
3933 | ||
3934 | static int | |
3935 | encode_coding_big5 (coding) | |
3936 | struct coding_system *coding; | |
3937 | { | |
3938 | int multibytep = coding->dst_multibyte; | |
3939 | int *charbuf = coding->charbuf; | |
3940 | int *charbuf_end = charbuf + coding->charbuf_used; | |
3941 | unsigned char *dst = coding->destination + coding->produced; | |
3942 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
3943 | int safe_room = 4; | |
3944 | int produced_chars = 0; | |
3945 | Lisp_Object attrs, eol_type, charset_list, val; | |
3946 | int ascii_compatible; | |
3947 | struct charset *charset_roman, *charset_big5; | |
3948 | int c; | |
3949 | ||
3950 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
3951 | val = charset_list; | |
3952 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
3953 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
3954 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
3955 | ||
3956 | while (charbuf < charbuf_end) | |
3957 | { | |
3958 | ASSURE_DESTINATION (safe_room); | |
3959 | c = *charbuf++; | |
3960 | /* Now encode the character C. */ | |
3961 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
3962 | EMIT_ONE_ASCII_BYTE (c); | |
3963 | else | |
3964 | { | |
3965 | unsigned code; | |
3966 | struct charset *charset = char_charset (c, charset_list, &code); | |
3967 | ||
3968 | if (! charset) | |
3969 | { | |
41cbe562 KH |
3970 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
3971 | { | |
3972 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
3973 | charset = CHARSET_FROM_ID (charset_ascii); | |
3974 | } | |
3975 | else | |
3976 | { | |
3977 | c = coding->default_char; | |
3978 | charset = char_charset (c, charset_list, &code); | |
3979 | } | |
df7492f9 KH |
3980 | } |
3981 | if (code == CHARSET_INVALID_CODE (charset)) | |
3982 | abort (); | |
3983 | if (charset == charset_big5) | |
3984 | { | |
3985 | int c1, c2; | |
3986 | ||
3987 | c1 = code >> 8, c2 = code & 0xFF; | |
3988 | EMIT_TWO_BYTES (c1, c2); | |
3989 | } | |
3990 | else | |
3991 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
3992 | } | |
3993 | } | |
3994 | coding->result = CODING_RESULT_SUCCESS; | |
3995 | coding->produced_char += produced_chars; | |
3996 | coding->produced = dst - coding->destination; | |
3997 | return 0; | |
3998 | } | |
3999 | ||
4000 | \f | |
4001 | /*** 10. CCL handlers ***/ | |
4002 | ||
4003 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4004 | Check if a text is encoded in a coding system of which | |
4005 | encoder/decoder are written in CCL program. If it is, return | |
4006 | CATEGORY_MASK_CCL, else return 0. */ | |
4007 | ||
4008 | static int | |
4009 | detect_coding_ccl (coding, mask) | |
4010 | struct coding_system *coding; | |
4011 | int *mask; | |
4012 | { | |
4013 | unsigned char *src = coding->source, *src_base = src; | |
4014 | unsigned char *src_end = coding->source + coding->src_bytes; | |
4015 | int multibytep = coding->src_multibyte; | |
4016 | int consumed_chars = 0; | |
4017 | int found = 0; | |
4018 | unsigned char *valids = CODING_CCL_VALIDS (coding); | |
4019 | int head_ascii = coding->head_ascii; | |
4020 | Lisp_Object attrs; | |
4021 | ||
4022 | coding = &coding_categories[coding_category_ccl]; | |
4023 | attrs = CODING_ID_ATTRS (coding->id); | |
4024 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4025 | src += head_ascii; | |
4026 | ||
4027 | while (1) | |
4028 | { | |
4029 | int c; | |
4030 | ONE_MORE_BYTE (c); | |
4031 | if (! valids[c]) | |
4032 | break; | |
4033 | if (!found && valids[c] > 1) | |
4034 | found = 1; | |
4035 | } | |
4036 | *mask &= ~CATEGORY_MASK_CCL; | |
4037 | return 0; | |
4038 | ||
4039 | no_more_source: | |
4040 | if (!found) | |
4041 | return 0; | |
4042 | *mask &= CATEGORY_MASK_CCL; | |
4043 | return 1; | |
4044 | } | |
4045 | ||
4046 | static void | |
4047 | decode_coding_ccl (coding) | |
4048 | struct coding_system *coding; | |
4049 | { | |
4050 | unsigned char *src = coding->source + coding->consumed; | |
4051 | unsigned char *src_end = coding->source + coding->src_bytes; | |
4052 | int *charbuf = coding->charbuf; | |
4053 | int *charbuf_end = charbuf + coding->charbuf_size; | |
4054 | int consumed_chars = 0; | |
4055 | int multibytep = coding->src_multibyte; | |
4056 | struct ccl_program ccl; | |
4057 | int source_charbuf[1024]; | |
4058 | int source_byteidx[1024]; | |
4059 | ||
4060 | setup_ccl_program (&ccl, CODING_CCL_DECODER (coding)); | |
4061 | ||
4062 | while (src < src_end) | |
4063 | { | |
4064 | unsigned char *p = src; | |
4065 | int *source, *source_end; | |
4066 | int i = 0; | |
4067 | ||
4068 | if (multibytep) | |
4069 | while (i < 1024 && p < src_end) | |
4070 | { | |
4071 | source_byteidx[i] = p - src; | |
4072 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
4073 | } | |
4074 | else | |
4075 | while (i < 1024 && p < src_end) | |
4076 | source_charbuf[i++] = *p++; | |
4077 | ||
4078 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) | |
4079 | ccl.last_block = 1; | |
4080 | ||
4081 | source = source_charbuf; | |
4082 | source_end = source + i; | |
4083 | while (source < source_end) | |
4084 | { | |
4085 | ccl_driver (&ccl, source, charbuf, | |
4086 | source_end - source, charbuf_end - charbuf); | |
4087 | source += ccl.consumed; | |
4088 | charbuf += ccl.produced; | |
4089 | if (ccl.status != CCL_STAT_SUSPEND_BY_DST) | |
4090 | break; | |
4091 | } | |
4092 | if (source < source_end) | |
4093 | src += source_byteidx[source - source_charbuf]; | |
4094 | else | |
4095 | src = p; | |
4096 | consumed_chars += source - source_charbuf; | |
4097 | ||
4098 | if (ccl.status != CCL_STAT_SUSPEND_BY_SRC | |
4099 | && ccl.status != CODING_RESULT_INSUFFICIENT_SRC) | |
4100 | break; | |
4101 | } | |
4102 | ||
4103 | switch (ccl.status) | |
4104 | { | |
4105 | case CCL_STAT_SUSPEND_BY_SRC: | |
4106 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
4107 | break; | |
4108 | case CCL_STAT_SUSPEND_BY_DST: | |
4109 | break; | |
4110 | case CCL_STAT_QUIT: | |
4111 | case CCL_STAT_INVALID_CMD: | |
4112 | coding->result = CODING_RESULT_INTERRUPT; | |
4113 | break; | |
4114 | default: | |
4115 | coding->result = CODING_RESULT_SUCCESS; | |
4116 | break; | |
4117 | } | |
4118 | coding->consumed_char += consumed_chars; | |
4119 | coding->consumed = src - coding->source; | |
4120 | coding->charbuf_used = charbuf - coding->charbuf; | |
4121 | } | |
4122 | ||
4123 | static int | |
4124 | encode_coding_ccl (coding) | |
4125 | struct coding_system *coding; | |
4126 | { | |
4127 | struct ccl_program ccl; | |
4128 | int multibytep = coding->dst_multibyte; | |
4129 | int *charbuf = coding->charbuf; | |
4130 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4131 | unsigned char *dst = coding->destination + coding->produced; | |
4132 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4133 | unsigned char *adjusted_dst_end = dst_end - 1; | |
4134 | int destination_charbuf[1024]; | |
4135 | int i, produced_chars = 0; | |
4136 | ||
4137 | setup_ccl_program (&ccl, CODING_CCL_ENCODER (coding)); | |
4138 | ||
4139 | ccl.last_block = coding->mode & CODING_MODE_LAST_BLOCK; | |
4140 | ccl.dst_multibyte = coding->dst_multibyte; | |
4141 | ||
4142 | while (charbuf < charbuf_end && dst < adjusted_dst_end) | |
4143 | { | |
4144 | int dst_bytes = dst_end - dst; | |
4145 | if (dst_bytes > 1024) | |
4146 | dst_bytes = 1024; | |
4147 | ||
4148 | ccl_driver (&ccl, charbuf, destination_charbuf, | |
4149 | charbuf_end - charbuf, dst_bytes); | |
4150 | charbuf += ccl.consumed; | |
4151 | if (multibytep) | |
4152 | for (i = 0; i < ccl.produced; i++) | |
4153 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); | |
4154 | else | |
4155 | { | |
4156 | for (i = 0; i < ccl.produced; i++) | |
4157 | *dst++ = destination_charbuf[i] & 0xFF; | |
4158 | produced_chars += ccl.produced; | |
4159 | } | |
4160 | } | |
4161 | ||
4162 | switch (ccl.status) | |
4163 | { | |
4164 | case CCL_STAT_SUSPEND_BY_SRC: | |
4165 | coding->result = CODING_RESULT_INSUFFICIENT_SRC; | |
4166 | break; | |
4167 | case CCL_STAT_SUSPEND_BY_DST: | |
4168 | coding->result = CODING_RESULT_INSUFFICIENT_DST; | |
4169 | break; | |
4170 | case CCL_STAT_QUIT: | |
4171 | case CCL_STAT_INVALID_CMD: | |
4172 | coding->result = CODING_RESULT_INTERRUPT; | |
4173 | break; | |
4174 | default: | |
4175 | coding->result = CODING_RESULT_SUCCESS; | |
4176 | break; | |
4177 | } | |
4178 | ||
4179 | coding->produced_char += produced_chars; | |
4180 | coding->produced = dst - coding->destination; | |
4181 | return 0; | |
4ed46869 KH |
4182 | } |
4183 | ||
df7492f9 KH |
4184 | |
4185 | \f | |
4186 | /*** 10, 11. no-conversion handlers ***/ | |
4187 | ||
4188 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ | |
4ed46869 | 4189 | |
b73bfc1c | 4190 | static void |
df7492f9 | 4191 | decode_coding_raw_text (coding) |
4ed46869 | 4192 | struct coding_system *coding; |
4ed46869 | 4193 | { |
df7492f9 | 4194 | coding->chars_at_source = 1; |
2c78b7e1 KH |
4195 | coding->consumed_char = 0; |
4196 | coding->consumed = 0; | |
df7492f9 KH |
4197 | coding->result = CODING_RESULT_SUCCESS; |
4198 | } | |
4ed46869 | 4199 | |
df7492f9 KH |
4200 | static int |
4201 | encode_coding_raw_text (coding) | |
4202 | struct coding_system *coding; | |
4203 | { | |
4204 | int multibytep = coding->dst_multibyte; | |
4205 | int *charbuf = coding->charbuf; | |
4206 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
4207 | unsigned char *dst = coding->destination + coding->produced; | |
4208 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4209 | int produced_chars = 0; | |
4210 | int c; | |
a5d301df | 4211 | |
df7492f9 | 4212 | if (multibytep) |
b73bfc1c | 4213 | { |
df7492f9 | 4214 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 4215 | |
df7492f9 KH |
4216 | if (coding->src_multibyte) |
4217 | while (charbuf < charbuf_end) | |
4218 | { | |
4219 | ASSURE_DESTINATION (safe_room); | |
4220 | c = *charbuf++; | |
4221 | if (ASCII_CHAR_P (c)) | |
4222 | EMIT_ONE_ASCII_BYTE (c); | |
4223 | else if (CHAR_BYTE8_P (c)) | |
4224 | { | |
4225 | c = CHAR_TO_BYTE8 (c); | |
4226 | EMIT_ONE_BYTE (c); | |
4227 | } | |
4228 | else | |
4229 | { | |
4230 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 4231 | |
df7492f9 KH |
4232 | CHAR_STRING_ADVANCE (c, p1); |
4233 | while (p0 < p1) | |
4234 | EMIT_ONE_BYTE (*p0); | |
4235 | } | |
4236 | } | |
b73bfc1c | 4237 | else |
df7492f9 KH |
4238 | while (charbuf < charbuf_end) |
4239 | { | |
4240 | ASSURE_DESTINATION (safe_room); | |
4241 | c = *charbuf++; | |
4242 | EMIT_ONE_BYTE (c); | |
4243 | } | |
4244 | } | |
4245 | else | |
4246 | { | |
4247 | if (coding->src_multibyte) | |
b73bfc1c | 4248 | { |
df7492f9 KH |
4249 | int safe_room = MAX_MULTIBYTE_LENGTH; |
4250 | ||
4251 | while (charbuf < charbuf_end) | |
b73bfc1c | 4252 | { |
df7492f9 KH |
4253 | ASSURE_DESTINATION (safe_room); |
4254 | c = *charbuf++; | |
4255 | if (ASCII_CHAR_P (c)) | |
4256 | *dst++ = c; | |
4257 | else if (CHAR_BYTE8_P (c)) | |
4258 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 4259 | else |
df7492f9 KH |
4260 | CHAR_STRING_ADVANCE (c, dst); |
4261 | produced_chars++; | |
b73bfc1c | 4262 | } |
4ed46869 | 4263 | } |
df7492f9 KH |
4264 | else |
4265 | { | |
4266 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
4267 | while (charbuf < charbuf_end && dst < dst_end) | |
4268 | *dst++ = *charbuf++; | |
4269 | produced_chars = dst - (coding->destination + coding->dst_bytes); | |
4270 | } | |
4ed46869 | 4271 | } |
df7492f9 KH |
4272 | coding->result = CODING_RESULT_SUCCESS; |
4273 | coding->produced_char += produced_chars; | |
4274 | coding->produced = dst - coding->destination; | |
4275 | return 0; | |
4ed46869 KH |
4276 | } |
4277 | ||
0a28aafb | 4278 | static int |
df7492f9 KH |
4279 | detect_coding_charset (coding, mask) |
4280 | struct coding_system *coding; | |
4281 | int *mask; | |
1397dc18 | 4282 | { |
df7492f9 KH |
4283 | unsigned char *src = coding->source, *src_base = src; |
4284 | unsigned char *src_end = coding->source + coding->src_bytes; | |
4285 | int multibytep = coding->src_multibyte; | |
4286 | int consumed_chars = 0; | |
4287 | Lisp_Object attrs, valids; | |
1397dc18 | 4288 | |
df7492f9 KH |
4289 | coding = &coding_categories[coding_category_charset]; |
4290 | attrs = CODING_ID_ATTRS (coding->id); | |
4291 | valids = AREF (attrs, coding_attr_charset_valids); | |
4292 | ||
4293 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
4294 | src += coding->head_ascii; | |
1397dc18 | 4295 | |
b73bfc1c | 4296 | while (1) |
1397dc18 | 4297 | { |
df7492f9 | 4298 | int c; |
1397dc18 | 4299 | |
df7492f9 KH |
4300 | ONE_MORE_BYTE (c); |
4301 | if (NILP (AREF (valids, c))) | |
4302 | break; | |
4303 | } | |
4304 | *mask &= ~CATEGORY_MASK_CHARSET; | |
4305 | return 0; | |
4ed46869 | 4306 | |
df7492f9 KH |
4307 | no_more_source: |
4308 | *mask &= CATEGORY_MASK_CHARSET; | |
4309 | return 1; | |
4310 | } | |
4ed46869 | 4311 | |
b73bfc1c | 4312 | static void |
df7492f9 | 4313 | decode_coding_charset (coding) |
4ed46869 | 4314 | struct coding_system *coding; |
4ed46869 | 4315 | { |
df7492f9 KH |
4316 | unsigned char *src = coding->source + coding->consumed; |
4317 | unsigned char *src_end = coding->source + coding->src_bytes; | |
b73bfc1c | 4318 | unsigned char *src_base; |
df7492f9 KH |
4319 | int *charbuf = coding->charbuf; |
4320 | int *charbuf_end = charbuf + coding->charbuf_size; | |
4321 | int consumed_chars = 0, consumed_chars_base; | |
4322 | int multibytep = coding->src_multibyte; | |
4eb6d3f1 | 4323 | Lisp_Object attrs, eol_type, charset_list, valids; |
df7492f9 KH |
4324 | |
4325 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); | |
4eb6d3f1 | 4326 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 4327 | |
df7492f9 | 4328 | while (1) |
4ed46869 | 4329 | { |
4eb6d3f1 | 4330 | int c; |
df7492f9 KH |
4331 | |
4332 | src_base = src; | |
4333 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 4334 | |
df7492f9 KH |
4335 | if (charbuf >= charbuf_end) |
4336 | break; | |
4337 | ||
4eb6d3f1 | 4338 | ONE_MORE_BYTE (c); |
df7492f9 | 4339 | if (c == '\r') |
d46c5b12 | 4340 | { |
c7c66a95 KH |
4341 | /* Here we assume that no charset maps '\r' to something |
4342 | else. */ | |
df7492f9 | 4343 | if (EQ (eol_type, Qdos)) |
b73bfc1c | 4344 | { |
4eb6d3f1 KH |
4345 | if (src < src_end |
4346 | && *src == '\n') | |
df7492f9 | 4347 | ONE_MORE_BYTE (c); |
b73bfc1c | 4348 | } |
df7492f9 | 4349 | else if (EQ (eol_type, Qmac)) |
b73bfc1c | 4350 | c = '\n'; |
d46c5b12 | 4351 | } |
df7492f9 | 4352 | else |
d46c5b12 | 4353 | { |
4eb6d3f1 KH |
4354 | Lisp_Object val; |
4355 | struct charset *charset; | |
c7c66a95 | 4356 | int dim; |
acb2a965 KH |
4357 | int len = 1; |
4358 | unsigned code = c; | |
4eb6d3f1 KH |
4359 | |
4360 | val = AREF (valids, c); | |
4361 | if (NILP (val)) | |
4362 | goto invalid_code; | |
c7c66a95 | 4363 | if (INTEGERP (val)) |
4eb6d3f1 | 4364 | { |
c7c66a95 KH |
4365 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
4366 | dim = CHARSET_DIMENSION (charset); | |
f9d71dcd | 4367 | while (len < dim) |
4eb6d3f1 | 4368 | { |
acb2a965 KH |
4369 | ONE_MORE_BYTE (c); |
4370 | code = (code << 8) | c; | |
f9d71dcd | 4371 | len++; |
4eb6d3f1 | 4372 | } |
c7c66a95 KH |
4373 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
4374 | charset, code, c); | |
4375 | } | |
4376 | else | |
4377 | { | |
4378 | /* VAL is a list of charset IDs. It is assured that the | |
4379 | list is sorted by charset dimensions (smaller one | |
4380 | comes first). */ | |
c7c66a95 KH |
4381 | while (CONSP (val)) |
4382 | { | |
4383 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
4384 | dim = CHARSET_DIMENSION (charset); | |
f9d71dcd | 4385 | while (len < dim) |
c7c66a95 | 4386 | { |
acb2a965 KH |
4387 | ONE_MORE_BYTE (c); |
4388 | code = (code << 8) | c; | |
f9d71dcd | 4389 | len++; |
c7c66a95 | 4390 | } |
c7c66a95 KH |
4391 | CODING_DECODE_CHAR (coding, src, src_base, |
4392 | src_end, charset, code, c); | |
4393 | if (c >= 0) | |
4394 | break; | |
4395 | val = XCDR (val); | |
4396 | } | |
4eb6d3f1 | 4397 | } |
df7492f9 KH |
4398 | if (c < 0) |
4399 | goto invalid_code; | |
d46c5b12 | 4400 | } |
df7492f9 KH |
4401 | *charbuf++ = c; |
4402 | continue; | |
4403 | ||
4404 | invalid_code: | |
4405 | src = src_base; | |
4406 | consumed_chars = consumed_chars_base; | |
4407 | ONE_MORE_BYTE (c); | |
4408 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
4409 | coding->errors++; | |
4ed46869 KH |
4410 | } |
4411 | ||
df7492f9 KH |
4412 | no_more_source: |
4413 | coding->consumed_char += consumed_chars_base; | |
4414 | coding->consumed = src_base - coding->source; | |
4415 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4416 | } |
4417 | ||
df7492f9 KH |
4418 | static int |
4419 | encode_coding_charset (coding) | |
4ed46869 | 4420 | struct coding_system *coding; |
4ed46869 | 4421 | { |
df7492f9 KH |
4422 | int multibytep = coding->dst_multibyte; |
4423 | int *charbuf = coding->charbuf; | |
4424 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4425 | unsigned char *dst = coding->destination + coding->produced; | |
4426 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4427 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
4428 | int produced_chars = 0; | |
df7492f9 KH |
4429 | Lisp_Object attrs, eol_type, charset_list; |
4430 | int ascii_compatible; | |
b73bfc1c | 4431 | int c; |
b73bfc1c | 4432 | |
df7492f9 | 4433 | CODING_GET_INFO (coding, attrs, eol_type, charset_list); |
df7492f9 | 4434 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 4435 | |
df7492f9 | 4436 | while (charbuf < charbuf_end) |
4ed46869 | 4437 | { |
4eb6d3f1 | 4438 | struct charset *charset; |
df7492f9 KH |
4439 | unsigned code; |
4440 | ||
4441 | ASSURE_DESTINATION (safe_room); | |
4442 | c = *charbuf++; | |
4443 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
4444 | EMIT_ONE_ASCII_BYTE (c); | |
d46c5b12 | 4445 | else |
4eb6d3f1 KH |
4446 | { |
4447 | charset = char_charset (c, charset_list, &code); | |
4448 | if (charset) | |
4449 | { | |
4450 | if (CHARSET_DIMENSION (charset) == 1) | |
4451 | EMIT_ONE_BYTE (code); | |
4452 | else if (CHARSET_DIMENSION (charset) == 2) | |
4453 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
4454 | else if (CHARSET_DIMENSION (charset) == 3) | |
4455 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
4456 | else | |
4457 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
4458 | (code >> 8) & 0xFF, code & 0xFF); | |
4459 | } | |
4460 | else | |
41cbe562 KH |
4461 | { |
4462 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
4463 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4464 | else | |
4465 | c = coding->default_char; | |
4466 | EMIT_ONE_BYTE (c); | |
4467 | } | |
4eb6d3f1 | 4468 | } |
4ed46869 KH |
4469 | } |
4470 | ||
df7492f9 KH |
4471 | coding->result = CODING_RESULT_SUCCESS; |
4472 | coding->produced_char += produced_chars; | |
4473 | coding->produced = dst - coding->destination; | |
4474 | return 0; | |
4ed46869 KH |
4475 | } |
4476 | ||
4477 | \f | |
1397dc18 | 4478 | /*** 7. C library functions ***/ |
4ed46869 | 4479 | |
df7492f9 | 4480 | /* In Emacs Lisp, coding system is represented by a Lisp symbol which |
4ed46869 | 4481 | has a property `coding-system'. The value of this property is a |
df7492f9 | 4482 | vector of length 5 (called as coding-vector). Among elements of |
4ed46869 KH |
4483 | this vector, the first (element[0]) and the fifth (element[4]) |
4484 | carry important information for decoding/encoding. Before | |
4485 | decoding/encoding, this information should be set in fields of a | |
4486 | structure of type `coding_system'. | |
4487 | ||
df7492f9 | 4488 | A value of property `coding-system' can be a symbol of another |
4ed46869 KH |
4489 | subsidiary coding-system. In that case, Emacs gets coding-vector |
4490 | from that symbol. | |
4491 | ||
4492 | `element[0]' contains information to be set in `coding->type'. The | |
4493 | value and its meaning is as follows: | |
4494 | ||
0ef69138 KH |
4495 | 0 -- coding_type_emacs_mule |
4496 | 1 -- coding_type_sjis | |
df7492f9 | 4497 | 2 -- coding_type_iso_2022 |
0ef69138 KH |
4498 | 3 -- coding_type_big5 |
4499 | 4 -- coding_type_ccl encoder/decoder written in CCL | |
4500 | nil -- coding_type_no_conversion | |
4501 | t -- coding_type_undecided (automatic conversion on decoding, | |
4502 | no-conversion on encoding) | |
4ed46869 KH |
4503 | |
4504 | `element[4]' contains information to be set in `coding->flags' and | |
4505 | `coding->spec'. The meaning varies by `coding->type'. | |
4506 | ||
df7492f9 | 4507 | If `coding->type' is `coding_type_iso_2022', element[4] is a vector |
4ed46869 KH |
4508 | of length 32 (of which the first 13 sub-elements are used now). |
4509 | Meanings of these sub-elements are: | |
4510 | ||
df7492f9 KH |
4511 | sub-element[N] where N is 0 through 3: to be set in `coding->spec.iso_2022' |
4512 | If the value is an integer of valid charset, the charset is | |
4513 | assumed to be designated to graphic register N initially. | |
4ed46869 | 4514 | |
df7492f9 KH |
4515 | If the value is minus, it is a minus value of charset which |
4516 | reserves graphic register N, which means that the charset is | |
4517 | not designated initially but should be designated to graphic | |
4518 | register N just before encoding a character in that charset. | |
1397dc18 | 4519 | |
df7492f9 KH |
4520 | If the value is nil, graphic register N is never used on |
4521 | encoding. | |
4522 | ||
4523 | sub-element[N] where N is 4 through 11: to be set in `coding->flags' | |
4524 | Each value takes t or nil. See the section ISO2022 of | |
4525 | `coding.h' for more information. | |
1397dc18 | 4526 | |
df7492f9 KH |
4527 | If `coding->type' is `coding_type_big5', element[4] is t to denote |
4528 | BIG5-ETen or nil to denote BIG5-HKU. | |
4ed46869 | 4529 | |
df7492f9 | 4530 | If `coding->type' takes the other value, element[4] is ignored. |
27901516 | 4531 | |
df7492f9 KH |
4532 | Emacs Lisp's coding system also carries information about format of |
4533 | end-of-line in a value of property `eol-type'. If the value is | |
4534 | integer, 0 means eol_lf, 1 means eol_crlf, and 2 means eol_cr. If | |
4535 | it is not integer, it should be a vector of subsidiary coding | |
4536 | systems of which property `eol-type' has one of above values. | |
4ed46869 | 4537 | |
df7492f9 | 4538 | */ |
4ed46869 | 4539 | |
df7492f9 KH |
4540 | /* Setup coding context CODING from information about CODING_SYSTEM. |
4541 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
4542 | CODING_SYSTEM is invalid, signal an error. */ | |
ec6d2bb8 KH |
4543 | |
4544 | void | |
df7492f9 KH |
4545 | setup_coding_system (coding_system, coding) |
4546 | Lisp_Object coding_system; | |
ec6d2bb8 KH |
4547 | struct coding_system *coding; |
4548 | { | |
df7492f9 KH |
4549 | Lisp_Object attrs; |
4550 | Lisp_Object eol_type; | |
4551 | Lisp_Object coding_type; | |
4552 | Lisp_Object val; | |
ec6d2bb8 | 4553 | |
df7492f9 KH |
4554 | if (NILP (coding_system)) |
4555 | coding_system = Qno_conversion; | |
4556 | ||
4557 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); | |
4558 | ||
4559 | attrs = CODING_ID_ATTRS (coding->id); | |
4560 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
4561 | ||
4562 | coding->mode = 0; | |
4563 | coding->head_ascii = -1; | |
4564 | coding->common_flags | |
4565 | = (VECTORP (eol_type) ? CODING_REQUIRE_DETECTION_MASK : 0); | |
4566 | ||
4567 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
4568 | coding->max_charset_id = XSTRING (val)->size - 1; | |
4569 | coding->safe_charsets = (char *) XSTRING (val)->data; | |
4570 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); | |
4571 | ||
4572 | coding_type = CODING_ATTR_TYPE (attrs); | |
4573 | if (EQ (coding_type, Qundecided)) | |
4574 | { | |
4575 | coding->detector = NULL; | |
4576 | coding->decoder = decode_coding_raw_text; | |
4577 | coding->encoder = encode_coding_raw_text; | |
4578 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
4579 | } | |
4580 | else if (EQ (coding_type, Qiso_2022)) | |
4581 | { | |
4582 | int i; | |
4583 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
4584 | ||
4585 | /* Invoke graphic register 0 to plane 0. */ | |
4586 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
4587 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
4588 | CODING_ISO_INVOCATION (coding, 1) | |
4589 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
4590 | /* Setup the initial status of designation. */ | |
4591 | for (i = 0; i < 4; i++) | |
4592 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
4593 | /* Not single shifting initially. */ | |
4594 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
4595 | /* Beginning of buffer should also be regarded as bol. */ | |
4596 | CODING_ISO_BOL (coding) = 1; | |
4597 | coding->detector = detect_coding_iso_2022; | |
4598 | coding->decoder = decode_coding_iso_2022; | |
4599 | coding->encoder = encode_coding_iso_2022; | |
4600 | if (flags & CODING_ISO_FLAG_SAFE) | |
4601 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
4602 | coding->common_flags | |
4603 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK | |
4604 | | CODING_REQUIRE_FLUSHING_MASK); | |
4605 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
4606 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
4607 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
4608 | { | |
4609 | setup_iso_safe_charsets (attrs); | |
4610 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
4611 | coding->max_charset_id = XSTRING (val)->size - 1; | |
4612 | coding->safe_charsets = (char *) XSTRING (val)->data; | |
4613 | } | |
4614 | CODING_ISO_FLAGS (coding) = flags; | |
4615 | } | |
4616 | else if (EQ (coding_type, Qcharset)) | |
4617 | { | |
4618 | coding->detector = detect_coding_charset; | |
4619 | coding->decoder = decode_coding_charset; | |
4620 | coding->encoder = encode_coding_charset; | |
4621 | coding->common_flags | |
4622 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
4623 | } | |
4624 | else if (EQ (coding_type, Qutf_8)) | |
4625 | { | |
4626 | coding->detector = detect_coding_utf_8; | |
4627 | coding->decoder = decode_coding_utf_8; | |
4628 | coding->encoder = encode_coding_utf_8; | |
4629 | coding->common_flags | |
4630 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
4631 | } | |
4632 | else if (EQ (coding_type, Qutf_16)) | |
4633 | { | |
4634 | val = AREF (attrs, coding_attr_utf_16_bom); | |
4635 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom | |
4636 | : EQ (val, Qt) ? utf_16_with_bom | |
4637 | : utf_16_without_bom); | |
4638 | val = AREF (attrs, coding_attr_utf_16_endian); | |
4639 | CODING_UTF_16_ENDIAN (coding) = (NILP (val) ? utf_16_big_endian | |
4640 | : utf_16_little_endian); | |
e19c3639 | 4641 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
4642 | coding->detector = detect_coding_utf_16; |
4643 | coding->decoder = decode_coding_utf_16; | |
4644 | coding->encoder = encode_coding_utf_16; | |
4645 | coding->common_flags | |
4646 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
4647 | } | |
4648 | else if (EQ (coding_type, Qccl)) | |
4649 | { | |
4650 | coding->detector = detect_coding_ccl; | |
4651 | coding->decoder = decode_coding_ccl; | |
4652 | coding->encoder = encode_coding_ccl; | |
4653 | coding->common_flags | |
4654 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK | |
4655 | | CODING_REQUIRE_FLUSHING_MASK); | |
4656 | } | |
4657 | else if (EQ (coding_type, Qemacs_mule)) | |
4658 | { | |
4659 | coding->detector = detect_coding_emacs_mule; | |
4660 | coding->decoder = decode_coding_emacs_mule; | |
4661 | coding->encoder = encode_coding_emacs_mule; | |
4662 | coding->common_flags | |
4663 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
4664 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
4665 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
4666 | { | |
4667 | Lisp_Object tail, safe_charsets; | |
4668 | int max_charset_id = 0; | |
4669 | ||
4670 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
4671 | tail = XCDR (tail)) | |
4672 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
4673 | max_charset_id = XFASTINT (XCAR (tail)); | |
4674 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
4675 | make_number (255)); | |
4676 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
4677 | tail = XCDR (tail)) | |
4678 | XSTRING (safe_charsets)->data[XFASTINT (XCAR (tail))] = 0; | |
4679 | coding->max_charset_id = max_charset_id; | |
4680 | coding->safe_charsets = (char *) XSTRING (safe_charsets)->data; | |
4681 | } | |
4682 | } | |
4683 | else if (EQ (coding_type, Qshift_jis)) | |
4684 | { | |
4685 | coding->detector = detect_coding_sjis; | |
4686 | coding->decoder = decode_coding_sjis; | |
4687 | coding->encoder = encode_coding_sjis; | |
4688 | coding->common_flags | |
4689 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
4690 | } | |
4691 | else if (EQ (coding_type, Qbig5)) | |
4692 | { | |
4693 | coding->detector = detect_coding_big5; | |
4694 | coding->decoder = decode_coding_big5; | |
4695 | coding->encoder = encode_coding_big5; | |
4696 | coding->common_flags | |
4697 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
4698 | } | |
4699 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 4700 | { |
df7492f9 KH |
4701 | coding->detector = NULL; |
4702 | coding->decoder = decode_coding_raw_text; | |
4703 | coding->encoder = encode_coding_raw_text; | |
4704 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
ec6d2bb8 | 4705 | } |
df7492f9 KH |
4706 | |
4707 | return; | |
ec6d2bb8 KH |
4708 | } |
4709 | ||
df7492f9 KH |
4710 | /* Return raw-text or one of its subsidiaries that has the same |
4711 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 4712 | |
df7492f9 KH |
4713 | Lisp_Object |
4714 | raw_text_coding_system (coding_system) | |
4715 | Lisp_Object coding_system; | |
ec6d2bb8 | 4716 | { |
0be8721c | 4717 | Lisp_Object spec, attrs; |
df7492f9 KH |
4718 | Lisp_Object eol_type, raw_text_eol_type; |
4719 | ||
4720 | spec = CODING_SYSTEM_SPEC (coding_system); | |
4721 | attrs = AREF (spec, 0); | |
4722 | ||
4723 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
4724 | return coding_system; | |
ec6d2bb8 | 4725 | |
df7492f9 KH |
4726 | eol_type = AREF (spec, 2); |
4727 | if (VECTORP (eol_type)) | |
4728 | return Qraw_text; | |
4729 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
4730 | raw_text_eol_type = AREF (spec, 2); | |
4731 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
4732 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
4733 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
4734 | } |
4735 | ||
54f78171 | 4736 | |
df7492f9 KH |
4737 | /* If CODING_SYSTEM doesn't specify end-of-line format but PARENT |
4738 | does, return one of the subsidiary that has the same eol-spec as | |
4739 | PARENT. Otherwise, return CODING_SYSTEM. */ | |
4740 | ||
4741 | Lisp_Object | |
4742 | coding_inherit_eol_type (coding_system, parent) | |
b74e4686 | 4743 | Lisp_Object coding_system, parent; |
54f78171 | 4744 | { |
df7492f9 | 4745 | Lisp_Object spec, attrs, eol_type; |
54f78171 | 4746 | |
df7492f9 KH |
4747 | spec = CODING_SYSTEM_SPEC (coding_system); |
4748 | attrs = AREF (spec, 0); | |
4749 | eol_type = AREF (spec, 2); | |
4750 | if (VECTORP (eol_type)) | |
4751 | { | |
4752 | Lisp_Object parent_spec; | |
df7492f9 KH |
4753 | Lisp_Object parent_eol_type; |
4754 | ||
4755 | parent_spec | |
4756 | = CODING_SYSTEM_SPEC (buffer_defaults.buffer_file_coding_system); | |
4757 | parent_eol_type = AREF (parent_spec, 2); | |
4758 | if (EQ (parent_eol_type, Qunix)) | |
4759 | coding_system = AREF (eol_type, 0); | |
4760 | else if (EQ (parent_eol_type, Qdos)) | |
4761 | coding_system = AREF (eol_type, 1); | |
4762 | else if (EQ (parent_eol_type, Qmac)) | |
4763 | coding_system = AREF (eol_type, 2); | |
54f78171 | 4764 | } |
df7492f9 | 4765 | return coding_system; |
54f78171 KH |
4766 | } |
4767 | ||
4ed46869 KH |
4768 | /* Emacs has a mechanism to automatically detect a coding system if it |
4769 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
4770 | it's impossible to distinguish some coding systems accurately | |
4771 | because they use the same range of codes. So, at first, coding | |
4772 | systems are categorized into 7, those are: | |
4773 | ||
0ef69138 | 4774 | o coding-category-emacs-mule |
4ed46869 KH |
4775 | |
4776 | The category for a coding system which has the same code range | |
4777 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 4778 | symbol) `emacs-mule' by default. |
4ed46869 KH |
4779 | |
4780 | o coding-category-sjis | |
4781 | ||
4782 | The category for a coding system which has the same code range | |
4783 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 4784 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
4785 | |
4786 | o coding-category-iso-7 | |
4787 | ||
4788 | The category for a coding system which has the same code range | |
7717c392 | 4789 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
4790 | shift and single shift functions. This can encode/decode all |
4791 | charsets. Assigned the coding-system (Lisp symbol) | |
4792 | `iso-2022-7bit' by default. | |
4793 | ||
4794 | o coding-category-iso-7-tight | |
4795 | ||
4796 | Same as coding-category-iso-7 except that this can | |
4797 | encode/decode only the specified charsets. | |
4ed46869 KH |
4798 | |
4799 | o coding-category-iso-8-1 | |
4800 | ||
4801 | The category for a coding system which has the same code range | |
4802 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
4803 | for DIMENSION1 charset. This doesn't use any locking shift |
4804 | and single shift functions. Assigned the coding-system (Lisp | |
4805 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
4806 | |
4807 | o coding-category-iso-8-2 | |
4808 | ||
4809 | The category for a coding system which has the same code range | |
4810 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
4811 | for DIMENSION2 charset. This doesn't use any locking shift |
4812 | and single shift functions. Assigned the coding-system (Lisp | |
4813 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 4814 | |
7717c392 | 4815 | o coding-category-iso-7-else |
4ed46869 KH |
4816 | |
4817 | The category for a coding system which has the same code range | |
df7492f9 | 4818 | as ISO2022 of 7-bit environemnt but uses locking shift or |
7717c392 KH |
4819 | single shift functions. Assigned the coding-system (Lisp |
4820 | symbol) `iso-2022-7bit-lock' by default. | |
4821 | ||
4822 | o coding-category-iso-8-else | |
4823 | ||
4824 | The category for a coding system which has the same code range | |
df7492f9 | 4825 | as ISO2022 of 8-bit environemnt but uses locking shift or |
7717c392 KH |
4826 | single shift functions. Assigned the coding-system (Lisp |
4827 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
4828 | |
4829 | o coding-category-big5 | |
4830 | ||
4831 | The category for a coding system which has the same code range | |
4832 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 4833 | `cn-big5' by default. |
4ed46869 | 4834 | |
fa42c37f KH |
4835 | o coding-category-utf-8 |
4836 | ||
4837 | The category for a coding system which has the same code range | |
4838 | as UTF-8 (cf. RFC2279). Assigned the coding-system (Lisp | |
4839 | symbol) `utf-8' by default. | |
4840 | ||
4841 | o coding-category-utf-16-be | |
4842 | ||
4843 | The category for a coding system in which a text has an | |
4844 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
4845 | endian at the head. Assigned the coding-system (Lisp symbol) | |
4846 | `utf-16-be' by default. | |
4847 | ||
4848 | o coding-category-utf-16-le | |
4849 | ||
4850 | The category for a coding system in which a text has an | |
4851 | Unicode signature (cf. Unicode Standard) in the order of | |
4852 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
4853 | symbol) `utf-16-le' by default. | |
4854 | ||
1397dc18 KH |
4855 | o coding-category-ccl |
4856 | ||
4857 | The category for a coding system of which encoder/decoder is | |
4858 | written in CCL programs. The default value is nil, i.e., no | |
4859 | coding system is assigned. | |
4860 | ||
4ed46869 KH |
4861 | o coding-category-binary |
4862 | ||
4863 | The category for a coding system not categorized in any of the | |
4864 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 4865 | `no-conversion' by default. |
4ed46869 KH |
4866 | |
4867 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 4868 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
4869 | What Emacs does actually is to detect a category of coding system. |
4870 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 4871 | decide only one possible category, it selects a category of the |
4ed46869 KH |
4872 | highest priority. Priorities of categories are also specified by a |
4873 | user in a Lisp variable `coding-category-list'. | |
4874 | ||
4875 | */ | |
4876 | ||
df7492f9 KH |
4877 | #define EOL_SEEN_NONE 0 |
4878 | #define EOL_SEEN_LF 1 | |
4879 | #define EOL_SEEN_CR 2 | |
4880 | #define EOL_SEEN_CRLF 4 | |
4ed46869 | 4881 | |
df7492f9 KH |
4882 | /* Detect how end-of-line of a text of length CODING->src_bytes |
4883 | pointed by CODING->source is encoded. Return one of | |
4884 | EOL_SEEN_XXX. */ | |
4ed46869 | 4885 | |
bc4bc72a RS |
4886 | #define MAX_EOL_CHECK_COUNT 3 |
4887 | ||
d46c5b12 | 4888 | static int |
df7492f9 KH |
4889 | detect_eol (coding, source, src_bytes) |
4890 | struct coding_system *coding; | |
d46c5b12 | 4891 | unsigned char *source; |
df7492f9 | 4892 | EMACS_INT src_bytes; |
4ed46869 | 4893 | { |
df7492f9 | 4894 | Lisp_Object attrs, coding_type; |
d46c5b12 | 4895 | unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 4896 | unsigned char c; |
df7492f9 KH |
4897 | int total = 0; |
4898 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 4899 | |
df7492f9 KH |
4900 | attrs = CODING_ID_ATTRS (coding->id); |
4901 | coding_type = CODING_ATTR_TYPE (attrs); | |
d46c5b12 | 4902 | |
df7492f9 | 4903 | if (EQ (coding_type, Qccl)) |
4ed46869 | 4904 | { |
df7492f9 | 4905 | int msb, lsb; |
fa42c37f | 4906 | |
df7492f9 KH |
4907 | msb = coding->spec.utf_16.endian == utf_16_little_endian; |
4908 | lsb = 1 - msb; | |
fa42c37f | 4909 | |
df7492f9 | 4910 | while (src + 1 < src_end) |
fa42c37f | 4911 | { |
df7492f9 KH |
4912 | c = src[lsb]; |
4913 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 4914 | { |
df7492f9 KH |
4915 | int this_eol; |
4916 | ||
4917 | if (c == '\n') | |
4918 | this_eol = EOL_SEEN_LF; | |
4919 | else if (src + 3 >= src_end | |
4920 | || src[msb + 2] != 0 | |
4921 | || src[lsb + 2] != '\n') | |
4922 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 4923 | else |
df7492f9 KH |
4924 | this_eol = EOL_SEEN_CRLF; |
4925 | ||
4926 | if (eol_seen == EOL_SEEN_NONE) | |
4927 | /* This is the first end-of-line. */ | |
4928 | eol_seen = this_eol; | |
4929 | else if (eol_seen != this_eol) | |
fa42c37f | 4930 | { |
df7492f9 KH |
4931 | /* The found type is different from what found before. */ |
4932 | eol_seen = EOL_SEEN_LF; | |
4933 | break; | |
fa42c37f | 4934 | } |
df7492f9 KH |
4935 | if (++total == MAX_EOL_CHECK_COUNT) |
4936 | break; | |
fa42c37f | 4937 | } |
df7492f9 | 4938 | src += 2; |
fa42c37f | 4939 | } |
df7492f9 | 4940 | } |
d46c5b12 | 4941 | else |
27901516 | 4942 | { |
df7492f9 | 4943 | while (src < src_end) |
27901516 | 4944 | { |
df7492f9 KH |
4945 | c = *src++; |
4946 | if (c == '\n' || c == '\r') | |
4947 | { | |
4948 | int this_eol; | |
d46c5b12 | 4949 | |
df7492f9 KH |
4950 | if (c == '\n') |
4951 | this_eol = EOL_SEEN_LF; | |
4952 | else if (src >= src_end || *src != '\n') | |
4953 | this_eol = EOL_SEEN_CR; | |
4954 | else | |
4955 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 4956 | |
df7492f9 KH |
4957 | if (eol_seen == EOL_SEEN_NONE) |
4958 | /* This is the first end-of-line. */ | |
4959 | eol_seen = this_eol; | |
4960 | else if (eol_seen != this_eol) | |
4961 | { | |
4962 | /* The found type is different from what found before. */ | |
4963 | eol_seen = EOL_SEEN_LF; | |
4964 | break; | |
4965 | } | |
4966 | if (++total == MAX_EOL_CHECK_COUNT) | |
4967 | break; | |
4968 | } | |
4969 | } | |
73be902c | 4970 | } |
df7492f9 | 4971 | return eol_seen; |
73be902c KH |
4972 | } |
4973 | ||
df7492f9 | 4974 | |
73be902c | 4975 | static void |
df7492f9 KH |
4976 | adjust_coding_eol_type (coding, eol_seen) |
4977 | struct coding_system *coding; | |
4978 | int eol_seen; | |
73be902c | 4979 | { |
0be8721c | 4980 | Lisp_Object eol_type; |
df7492f9 KH |
4981 | |
4982 | eol_type = CODING_ID_EOL_TYPE (coding->id); | |
4983 | if (eol_seen & EOL_SEEN_LF) | |
4984 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
4985 | else if (eol_type & EOL_SEEN_CRLF) | |
4986 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
4987 | else if (eol_type & EOL_SEEN_CR) | |
4988 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
d46c5b12 KH |
4989 | } |
4990 | ||
df7492f9 KH |
4991 | /* Detect how a text specified in CODING is encoded. If a coding |
4992 | system is detected, update fields of CODING by the detected coding | |
4993 | system. */ | |
4994 | ||
4995 | void | |
4996 | detect_coding (coding) | |
d46c5b12 | 4997 | struct coding_system *coding; |
d46c5b12 | 4998 | { |
df7492f9 KH |
4999 | unsigned char *src, *src_end; |
5000 | Lisp_Object attrs, coding_type; | |
d46c5b12 | 5001 | |
df7492f9 KH |
5002 | coding->consumed = coding->consumed_char = 0; |
5003 | coding->produced = coding->produced_char = 0; | |
5004 | coding_set_source (coding); | |
1c3478b0 | 5005 | |
df7492f9 | 5006 | src_end = coding->source + coding->src_bytes; |
1c3478b0 | 5007 | |
df7492f9 KH |
5008 | /* If we have not yet decided the text encoding type, detect it |
5009 | now. */ | |
5010 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 5011 | { |
df7492f9 KH |
5012 | int mask = CATEGORY_MASK_ANY; |
5013 | int c, i; | |
5014 | ||
5015 | for (src = coding->source; src < src_end; src++) | |
5016 | { | |
5017 | c = *src; | |
5018 | if (c & 0x80 || (c < 0x20 && (c == ISO_CODE_ESC | |
5019 | || c == ISO_CODE_SI | |
5020 | || c == ISO_CODE_SO))) | |
5021 | break; | |
5022 | } | |
5023 | coding->head_ascii = src - (coding->source + coding->consumed); | |
5024 | ||
5025 | if (coding->head_ascii < coding->src_bytes) | |
1c3478b0 | 5026 | { |
df7492f9 KH |
5027 | int detected = 0; |
5028 | ||
5029 | for (i = 0; i < coding_category_raw_text; i++) | |
1c3478b0 | 5030 | { |
df7492f9 KH |
5031 | enum coding_category category = coding_priorities[i]; |
5032 | struct coding_system *this = coding_categories + category; | |
5033 | ||
5034 | if (category >= coding_category_raw_text | |
5035 | || detected & (1 << category)) | |
5036 | continue; | |
5037 | ||
5038 | if (this->id < 0) | |
1c3478b0 | 5039 | { |
df7492f9 KH |
5040 | /* No coding system of this category is defined. */ |
5041 | mask &= ~(1 << category); | |
5042 | } | |
5043 | else | |
5044 | { | |
5045 | detected |= detected_mask[category]; | |
5046 | if ((*(this->detector)) (coding, &mask)) | |
5047 | break; | |
1c3478b0 KH |
5048 | } |
5049 | } | |
df7492f9 KH |
5050 | if (! mask) |
5051 | setup_coding_system (Qraw_text, coding); | |
5052 | else if (mask != CATEGORY_MASK_ANY) | |
5053 | for (i = 0; i < coding_category_raw_text; i++) | |
5054 | { | |
5055 | enum coding_category category = coding_priorities[i]; | |
5056 | struct coding_system *this = coding_categories + category; | |
5057 | ||
5058 | if (mask & (1 << category)) | |
5059 | { | |
5060 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
5061 | break; | |
5062 | } | |
5063 | } | |
1c3478b0 | 5064 | } |
b73bfc1c | 5065 | } |
69f76525 | 5066 | |
df7492f9 KH |
5067 | attrs = CODING_ID_ATTRS (coding->id); |
5068 | coding_type = CODING_ATTR_TYPE (attrs); | |
5069 | ||
5070 | /* If we have not yet decided the EOL type, detect it now. But, the | |
5071 | detection is impossible for a CCL based coding system, in which | |
5072 | case, we detct the EOL type after decoding. */ | |
5073 | if (VECTORP (CODING_ID_EOL_TYPE (coding->id)) | |
5074 | && ! EQ (coding_type, Qccl)) | |
d46c5b12 | 5075 | { |
df7492f9 KH |
5076 | int eol_seen = detect_eol (coding, coding->source, coding->src_bytes); |
5077 | ||
5078 | if (eol_seen != EOL_SEEN_NONE) | |
5079 | adjust_coding_eol_type (coding, eol_seen); | |
d46c5b12 | 5080 | } |
4ed46869 KH |
5081 | } |
5082 | ||
aaaf0b1e KH |
5083 | |
5084 | static void | |
df7492f9 | 5085 | decode_eol (coding) |
aaaf0b1e | 5086 | struct coding_system *coding; |
aaaf0b1e | 5087 | { |
df7492f9 | 5088 | if (VECTORP (CODING_ID_EOL_TYPE (coding->id))) |
aaaf0b1e | 5089 | { |
df7492f9 KH |
5090 | unsigned char *p = CHAR_POS_ADDR (coding->dst_pos); |
5091 | unsigned char *pend = p + coding->produced; | |
5092 | int eol_seen = EOL_SEEN_NONE; | |
aaaf0b1e | 5093 | |
df7492f9 | 5094 | for (; p < pend; p++) |
aaaf0b1e | 5095 | { |
df7492f9 KH |
5096 | if (*p == '\n') |
5097 | eol_seen |= EOL_SEEN_LF; | |
5098 | else if (*p == '\r') | |
aaaf0b1e | 5099 | { |
df7492f9 | 5100 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 5101 | { |
df7492f9 KH |
5102 | eol_seen |= EOL_SEEN_CRLF; |
5103 | p++; | |
aaaf0b1e | 5104 | } |
aaaf0b1e | 5105 | else |
df7492f9 | 5106 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 5107 | } |
aaaf0b1e | 5108 | } |
df7492f9 KH |
5109 | if (eol_seen != EOL_SEEN_NONE) |
5110 | adjust_coding_eol_type (coding, eol_seen); | |
aaaf0b1e | 5111 | } |
aaaf0b1e | 5112 | |
df7492f9 KH |
5113 | if (EQ (CODING_ID_EOL_TYPE (coding->id), Qmac)) |
5114 | { | |
5115 | unsigned char *p = CHAR_POS_ADDR (coding->dst_pos); | |
5116 | unsigned char *pend = p + coding->produced; | |
5117 | ||
5118 | for (; p < pend; p++) | |
5119 | if (*p == '\r') | |
5120 | *p = '\n'; | |
5121 | } | |
5122 | else if (EQ (CODING_ID_EOL_TYPE (coding->id), Qdos)) | |
5123 | { | |
5124 | unsigned char *p, *pbeg, *pend; | |
5125 | Lisp_Object undo_list; | |
5126 | ||
5127 | move_gap_both (coding->dst_pos + coding->produced_char, | |
5128 | coding->dst_pos_byte + coding->produced); | |
5129 | undo_list = current_buffer->undo_list; | |
5130 | current_buffer->undo_list = Qt; | |
5131 | del_range_2 (coding->dst_pos, coding->dst_pos_byte, GPT, GPT_BYTE, Qnil); | |
5132 | current_buffer->undo_list = undo_list; | |
5133 | pbeg = GPT_ADDR; | |
5134 | pend = pbeg + coding->produced; | |
5135 | ||
5136 | for (p = pend - 1; p >= pbeg; p--) | |
5137 | if (*p == '\r') | |
5138 | { | |
5139 | safe_bcopy ((char *) (p + 1), (char *) p, pend - p - 1); | |
5140 | pend--; | |
5141 | } | |
5142 | coding->produced_char -= coding->produced - (pend - pbeg); | |
5143 | coding->produced = pend - pbeg; | |
5144 | insert_from_gap (coding->produced_char, coding->produced); | |
aaaf0b1e KH |
5145 | } |
5146 | } | |
5147 | ||
df7492f9 KH |
5148 | static void |
5149 | translate_chars (coding, table) | |
4ed46869 | 5150 | struct coding_system *coding; |
df7492f9 | 5151 | Lisp_Object table; |
4ed46869 | 5152 | { |
df7492f9 KH |
5153 | int *charbuf = coding->charbuf; |
5154 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5155 | int c; | |
5156 | ||
5157 | if (coding->chars_at_source) | |
5158 | return; | |
4ed46869 | 5159 | |
df7492f9 | 5160 | while (charbuf < charbuf_end) |
8844fa83 | 5161 | { |
df7492f9 KH |
5162 | c = *charbuf; |
5163 | if (c < 0) | |
5164 | charbuf += c; | |
5165 | else | |
5166 | *charbuf++ = translate_char (table, c); | |
8844fa83 | 5167 | } |
df7492f9 | 5168 | } |
4ed46869 | 5169 | |
df7492f9 KH |
5170 | static int |
5171 | produce_chars (coding) | |
5172 | struct coding_system *coding; | |
5173 | { | |
5174 | unsigned char *dst = coding->destination + coding->produced; | |
5175 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5176 | int produced; | |
5177 | int produced_chars = 0; | |
b73bfc1c | 5178 | |
df7492f9 | 5179 | if (! coding->chars_at_source) |
4ed46869 | 5180 | { |
df7492f9 KH |
5181 | /* Characters are in coding->charbuf. */ |
5182 | int *buf = coding->charbuf; | |
5183 | int *buf_end = buf + coding->charbuf_used; | |
5184 | unsigned char *adjusted_dst_end; | |
4ed46869 | 5185 | |
df7492f9 KH |
5186 | if (BUFFERP (coding->src_object) |
5187 | && EQ (coding->src_object, coding->dst_object)) | |
5188 | dst_end = coding->source + coding->consumed; | |
5189 | adjusted_dst_end = dst_end - MAX_MULTIBYTE_LENGTH; | |
4ed46869 | 5190 | |
df7492f9 KH |
5191 | while (buf < buf_end) |
5192 | { | |
5193 | int c = *buf++; | |
5194 | ||
5195 | if (dst >= adjusted_dst_end) | |
5196 | { | |
5197 | dst = alloc_destination (coding, | |
5198 | buf_end - buf + MAX_MULTIBYTE_LENGTH, | |
5199 | dst); | |
5200 | dst_end = coding->destination + coding->dst_bytes; | |
5201 | adjusted_dst_end = dst_end - MAX_MULTIBYTE_LENGTH; | |
5202 | } | |
5203 | if (c >= 0) | |
5204 | { | |
5205 | if (coding->dst_multibyte | |
5206 | || ! CHAR_BYTE8_P (c)) | |
5207 | CHAR_STRING_ADVANCE (c, dst); | |
5208 | else | |
5209 | *dst++ = CHAR_TO_BYTE8 (c); | |
5210 | produced_chars++; | |
5211 | } | |
5212 | else | |
5213 | /* This is an annotation data. */ | |
5214 | buf -= c + 1; | |
5215 | } | |
5216 | } | |
5217 | else | |
5218 | { | |
df7492f9 KH |
5219 | unsigned char *src = coding->source; |
5220 | unsigned char *src_end = src + coding->src_bytes; | |
5221 | Lisp_Object eol_type; | |
b73bfc1c | 5222 | |
df7492f9 | 5223 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
4ed46869 | 5224 | |
df7492f9 | 5225 | if (coding->src_multibyte != coding->dst_multibyte) |
aaaf0b1e | 5226 | { |
df7492f9 KH |
5227 | if (coding->src_multibyte) |
5228 | { | |
71c81426 | 5229 | int multibytep = 1; |
df7492f9 | 5230 | int consumed_chars; |
d46c5b12 | 5231 | |
df7492f9 KH |
5232 | while (1) |
5233 | { | |
5234 | unsigned char *src_base = src; | |
5235 | int c; | |
b73bfc1c | 5236 | |
df7492f9 KH |
5237 | ONE_MORE_BYTE (c); |
5238 | if (c == '\r') | |
5239 | { | |
5240 | if (EQ (eol_type, Qdos)) | |
5241 | { | |
5242 | if (src < src_end | |
5243 | && *src == '\n') | |
5244 | c = *src++; | |
5245 | } | |
5246 | else if (EQ (eol_type, Qmac)) | |
5247 | c = '\n'; | |
5248 | } | |
5249 | if (dst == dst_end) | |
5250 | { | |
2c78b7e1 | 5251 | coding->consumed = src - coding->source; |
b73bfc1c | 5252 | |
2c78b7e1 KH |
5253 | if (EQ (coding->src_object, coding->dst_object)) |
5254 | dst_end = src; | |
5255 | if (dst == dst_end) | |
5256 | { | |
5257 | dst = alloc_destination (coding, src_end - src + 1, | |
5258 | dst); | |
5259 | dst_end = coding->destination + coding->dst_bytes; | |
5260 | coding_set_source (coding); | |
5261 | src = coding->source + coding->consumed; | |
5262 | src_end = coding->source + coding->src_bytes; | |
5263 | } | |
df7492f9 KH |
5264 | } |
5265 | *dst++ = c; | |
5266 | produced_chars++; | |
5267 | } | |
5268 | no_more_source: | |
5269 | ; | |
5270 | } | |
5271 | else | |
5272 | while (src < src_end) | |
5273 | { | |
71c81426 | 5274 | int multibytep = 1; |
df7492f9 | 5275 | int c = *src++; |
b73bfc1c | 5276 | |
df7492f9 KH |
5277 | if (c == '\r') |
5278 | { | |
5279 | if (EQ (eol_type, Qdos)) | |
5280 | { | |
5281 | if (src < src_end | |
5282 | && *src == '\n') | |
5283 | c = *src++; | |
5284 | } | |
5285 | else if (EQ (eol_type, Qmac)) | |
5286 | c = '\n'; | |
5287 | } | |
5288 | if (dst >= dst_end - 1) | |
5289 | { | |
2c78b7e1 | 5290 | coding->consumed = src - coding->source; |
df7492f9 | 5291 | |
2c78b7e1 KH |
5292 | if (EQ (coding->src_object, coding->dst_object)) |
5293 | dst_end = src; | |
5294 | if (dst >= dst_end - 1) | |
5295 | { | |
5296 | dst = alloc_destination (coding, src_end - src + 2, | |
5297 | dst); | |
5298 | dst_end = coding->destination + coding->dst_bytes; | |
5299 | coding_set_source (coding); | |
5300 | src = coding->source + coding->consumed; | |
5301 | src_end = coding->source + coding->src_bytes; | |
5302 | } | |
df7492f9 KH |
5303 | } |
5304 | EMIT_ONE_BYTE (c); | |
5305 | } | |
d46c5b12 | 5306 | } |
df7492f9 KH |
5307 | else |
5308 | { | |
5309 | if (!EQ (coding->src_object, coding->dst_object)) | |
5310 | { | |
5311 | int require = coding->src_bytes - coding->dst_bytes; | |
4ed46869 | 5312 | |
df7492f9 KH |
5313 | if (require > 0) |
5314 | { | |
5315 | EMACS_INT offset = src - coding->source; | |
5316 | ||
5317 | dst = alloc_destination (coding, require, dst); | |
5318 | coding_set_source (coding); | |
5319 | src = coding->source + offset; | |
5320 | src_end = coding->source + coding->src_bytes; | |
5321 | } | |
5322 | } | |
5323 | produced_chars = coding->src_chars; | |
5324 | while (src < src_end) | |
5325 | { | |
5326 | int c = *src++; | |
5327 | ||
5328 | if (c == '\r') | |
5329 | { | |
5330 | if (EQ (eol_type, Qdos)) | |
5331 | { | |
5332 | if (src < src_end | |
5333 | && *src == '\n') | |
5334 | c = *src++; | |
5335 | produced_chars--; | |
5336 | } | |
5337 | else if (EQ (eol_type, Qmac)) | |
5338 | c = '\n'; | |
5339 | } | |
5340 | *dst++ = c; | |
5341 | } | |
5342 | } | |
2c78b7e1 KH |
5343 | coding->consumed = coding->src_bytes; |
5344 | coding->consumed_char = coding->src_chars; | |
b73bfc1c | 5345 | } |
4ed46869 | 5346 | |
df7492f9 KH |
5347 | produced = dst - (coding->destination + coding->produced); |
5348 | if (BUFFERP (coding->dst_object)) | |
5349 | insert_from_gap (produced_chars, produced); | |
5350 | coding->produced += produced; | |
5351 | coding->produced_char += produced_chars; | |
5352 | return produced_chars; | |
b73bfc1c | 5353 | } |
52d41803 | 5354 | |
df7492f9 KH |
5355 | /* [ -LENGTH CHAR_POS_OFFSET MASK METHOD COMP_LEN ] |
5356 | or | |
5357 | [ -LENGTH CHAR_POS_OFFSET MASK METHOD COMP_LEN COMPONENTS... ] | |
5358 | */ | |
4ed46869 | 5359 | |
df7492f9 KH |
5360 | static INLINE void |
5361 | produce_composition (coding, charbuf) | |
4ed46869 | 5362 | struct coding_system *coding; |
df7492f9 | 5363 | int *charbuf; |
4ed46869 | 5364 | { |
df7492f9 KH |
5365 | Lisp_Object buffer; |
5366 | int len; | |
5367 | EMACS_INT pos; | |
5368 | enum composition_method method; | |
5369 | int cmp_len; | |
5370 | Lisp_Object components; | |
5371 | ||
5372 | buffer = coding->dst_object; | |
5373 | len = -charbuf[0]; | |
5374 | pos = coding->dst_pos + charbuf[1]; | |
5375 | method = (enum composition_method) (charbuf[3]); | |
5376 | cmp_len = charbuf[4]; | |
5377 | ||
5378 | if (method == COMPOSITION_RELATIVE) | |
5379 | components = Qnil; | |
5380 | else | |
d46c5b12 | 5381 | { |
df7492f9 KH |
5382 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
5383 | int i; | |
4ed46869 | 5384 | |
df7492f9 KH |
5385 | len -= 5; |
5386 | charbuf += 5; | |
5387 | for (i = 0; i < len; i++) | |
5388 | args[i] = make_number (charbuf[i]); | |
5389 | components = (method == COMPOSITION_WITH_ALTCHARS | |
5390 | ? Fstring (len, args) : Fvector (len, args)); | |
5391 | } | |
5392 | compose_text (pos, pos + cmp_len, components, Qnil, Qnil); | |
5393 | } | |
b73bfc1c | 5394 | |
df7492f9 KH |
5395 | static int * |
5396 | save_composition_data (buf, buf_end, prop) | |
5397 | int *buf, *buf_end; | |
5398 | Lisp_Object prop; | |
5399 | { | |
5400 | enum composition_method method = COMPOSITION_METHOD (prop); | |
5401 | int cmp_len = COMPOSITION_LENGTH (prop); | |
4ed46869 | 5402 | |
df7492f9 KH |
5403 | if (buf + 4 + (MAX_COMPOSITION_COMPONENTS * 2 - 1) > buf_end) |
5404 | return NULL; | |
d46c5b12 | 5405 | |
df7492f9 KH |
5406 | buf[1] = CODING_ANNOTATE_COMPOSITION_MASK; |
5407 | buf[2] = method; | |
5408 | buf[3] = cmp_len; | |
b73bfc1c | 5409 | |
df7492f9 KH |
5410 | if (method == COMPOSITION_RELATIVE) |
5411 | buf[0] = 4; | |
5412 | else | |
b73bfc1c | 5413 | { |
df7492f9 KH |
5414 | Lisp_Object components; |
5415 | int len, i; | |
b73bfc1c | 5416 | |
df7492f9 KH |
5417 | components = COMPOSITION_COMPONENTS (prop); |
5418 | if (VECTORP (components)) | |
d46c5b12 | 5419 | { |
df7492f9 KH |
5420 | len = XVECTOR (components)->size; |
5421 | for (i = 0; i < len; i++) | |
5422 | buf[4 + i] = XINT (AREF (components, i)); | |
5423 | } | |
5424 | else if (STRINGP (components)) | |
5425 | { | |
5426 | int i_byte; | |
b73bfc1c | 5427 | |
df7492f9 KH |
5428 | len = XSTRING (components)->size; |
5429 | i = i_byte = 0; | |
5430 | while (i < len) | |
5431 | FETCH_STRING_CHAR_ADVANCE (buf[4 + i], components, i, i_byte); | |
5432 | } | |
5433 | else if (INTEGERP (components)) | |
5434 | { | |
5435 | len = 1; | |
5436 | buf[4] = XINT (components); | |
5437 | } | |
5438 | else if (CONSP (components)) | |
5439 | { | |
5440 | for (len = 0; CONSP (components); | |
5441 | len++, components = XCDR (components)) | |
5442 | buf[4 + len] = XINT (XCAR (components)); | |
d46c5b12 | 5443 | } |
df7492f9 KH |
5444 | else |
5445 | abort (); | |
5446 | buf[0] = 4 + len; | |
4ed46869 | 5447 | } |
df7492f9 | 5448 | return (buf + buf[0]); |
4ed46869 KH |
5449 | } |
5450 | ||
df7492f9 KH |
5451 | #define CHARBUF_SIZE 0x4000 |
5452 | ||
5453 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
5454 | do { \ | |
5455 | int size = CHARBUF_SIZE;; \ | |
5456 | \ | |
5457 | coding->charbuf = NULL; \ | |
5458 | while (size > 1024) \ | |
5459 | { \ | |
5460 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
5461 | if (coding->charbuf) \ | |
5462 | break; \ | |
5463 | size >>= 1; \ | |
5464 | } \ | |
5465 | if (! coding->charbuf) \ | |
5466 | { \ | |
5467 | coding->result = CODING_RESULT_INSUFFICIENT_MEM; \ | |
5468 | return coding->result; \ | |
5469 | } \ | |
5470 | coding->charbuf_size = size; \ | |
5471 | } while (0) | |
4ed46869 | 5472 | |
d46c5b12 KH |
5473 | |
5474 | static void | |
df7492f9 | 5475 | produce_annotation (coding) |
d46c5b12 | 5476 | struct coding_system *coding; |
d46c5b12 | 5477 | { |
df7492f9 KH |
5478 | int *charbuf = coding->charbuf; |
5479 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 5480 | |
df7492f9 | 5481 | while (charbuf < charbuf_end) |
d46c5b12 | 5482 | { |
df7492f9 KH |
5483 | if (*charbuf >= 0) |
5484 | charbuf++; | |
d46c5b12 | 5485 | else |
d46c5b12 | 5486 | { |
df7492f9 KH |
5487 | int len = -*charbuf; |
5488 | switch (charbuf[2]) | |
5489 | { | |
5490 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
5491 | produce_composition (coding, charbuf); | |
5492 | break; | |
5493 | default: | |
5494 | abort (); | |
5495 | } | |
5496 | charbuf += len; | |
d46c5b12 | 5497 | } |
df7492f9 KH |
5498 | } |
5499 | } | |
d46c5b12 | 5500 | |
df7492f9 KH |
5501 | /* Decode the data at CODING->src_object into CODING->dst_object. |
5502 | CODING->src_object is a buffer, a string, or nil. | |
5503 | CODING->dst_object is a buffer. | |
de79a6a5 | 5504 | |
df7492f9 KH |
5505 | If CODING->src_object is a buffer, it must be the current buffer. |
5506 | In this case, if CODING->src_pos is positive, it is a position of | |
5507 | the source text in the buffer, otherwise, the source text is in the | |
5508 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
5509 | the text from GPT (which must be the same as PT). If this is the | |
5510 | same buffer as CODING->dst_object, CODING->src_pos must be | |
5511 | negative. | |
b73bfc1c | 5512 | |
df7492f9 KH |
5513 | If CODING->src_object is a string, CODING->src_pos in an index to |
5514 | that string. | |
d46c5b12 | 5515 | |
df7492f9 KH |
5516 | If CODING->src_object is nil, CODING->source must already point to |
5517 | the non-relocatable memory area. In this case, CODING->src_pos is | |
5518 | an offset from CODING->source. | |
d46c5b12 | 5519 | |
df7492f9 KH |
5520 | The decoded data is inserted at the current point of the buffer |
5521 | CODING->dst_object. | |
5522 | */ | |
5523 | ||
5524 | static int | |
5525 | decode_coding (coding) | |
d46c5b12 | 5526 | struct coding_system *coding; |
d46c5b12 | 5527 | { |
df7492f9 | 5528 | Lisp_Object attrs; |
d46c5b12 | 5529 | |
df7492f9 KH |
5530 | if (BUFFERP (coding->src_object) |
5531 | && coding->src_pos > 0 | |
5532 | && coding->src_pos < GPT | |
5533 | && coding->src_pos + coding->src_chars > GPT) | |
5534 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 5535 | |
df7492f9 | 5536 | if (BUFFERP (coding->dst_object)) |
88993dfd | 5537 | { |
df7492f9 KH |
5538 | if (current_buffer != XBUFFER (coding->dst_object)) |
5539 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
5540 | if (GPT != PT) | |
5541 | move_gap_both (PT, PT_BYTE); | |
88993dfd KH |
5542 | } |
5543 | ||
df7492f9 KH |
5544 | coding->consumed = coding->consumed_char = 0; |
5545 | coding->produced = coding->produced_char = 0; | |
5546 | coding->chars_at_source = 0; | |
5547 | coding->result = CODING_RESULT_SUCCESS; | |
5548 | coding->errors = 0; | |
5549 | ||
5550 | ALLOC_CONVERSION_WORK_AREA (coding); | |
5551 | ||
5552 | attrs = CODING_ID_ATTRS (coding->id); | |
5553 | ||
5554 | do | |
d46c5b12 | 5555 | { |
df7492f9 KH |
5556 | coding_set_source (coding); |
5557 | coding->annotated = 0; | |
5558 | (*(coding->decoder)) (coding); | |
5559 | if (!NILP (CODING_ATTR_DECODE_TBL (attrs))) | |
5560 | translate_chars (CODING_ATTR_DECODE_TBL (attrs), coding); | |
5561 | coding_set_destination (coding); | |
5562 | produce_chars (coding); | |
5563 | if (coding->annotated) | |
5564 | produce_annotation (coding); | |
d46c5b12 | 5565 | } |
df7492f9 KH |
5566 | while (coding->consumed < coding->src_bytes |
5567 | && ! coding->result); | |
d46c5b12 | 5568 | |
df7492f9 KH |
5569 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qccl) |
5570 | && SYMBOLP (CODING_ID_EOL_TYPE (coding->id)) | |
5571 | && ! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix)) | |
5572 | decode_eol (coding); | |
d46c5b12 | 5573 | |
df7492f9 KH |
5574 | coding->carryover_bytes = 0; |
5575 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 5576 | { |
df7492f9 KH |
5577 | int nbytes = coding->src_bytes - coding->consumed; |
5578 | unsigned char *src; | |
5579 | ||
5580 | coding_set_source (coding); | |
5581 | coding_set_destination (coding); | |
5582 | src = coding->source + coding->consumed; | |
5583 | ||
5584 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
d46c5b12 | 5585 | { |
df7492f9 KH |
5586 | /* Flush out unprocessed data as binary chars. We are sure |
5587 | that the number of data is less than the size of | |
5588 | coding->charbuf. */ | |
5589 | int *charbuf = coding->charbuf; | |
5590 | ||
5591 | while (nbytes-- > 0) | |
d46c5b12 | 5592 | { |
df7492f9 KH |
5593 | int c = *src++; |
5594 | *charbuf++ = (c & 0x80 ? - c : c); | |
d46c5b12 | 5595 | } |
df7492f9 | 5596 | produce_chars (coding); |
d46c5b12 | 5597 | } |
d46c5b12 | 5598 | else |
df7492f9 KH |
5599 | { |
5600 | /* Record unprocessed bytes in coding->carryover. We are | |
5601 | sure that the number of data is less than the size of | |
5602 | coding->carryover. */ | |
5603 | unsigned char *p = coding->carryover; | |
5604 | ||
5605 | coding->carryover_bytes = nbytes; | |
5606 | while (nbytes-- > 0) | |
5607 | *p++ = *src++; | |
5608 | } | |
5609 | coding->consumed = coding->src_bytes; | |
5610 | } | |
b73bfc1c | 5611 | |
df7492f9 | 5612 | return coding->result; |
d46c5b12 KH |
5613 | } |
5614 | ||
df7492f9 KH |
5615 | static void |
5616 | consume_chars (coding) | |
5617 | struct coding_system *coding; | |
5618 | { | |
5619 | int *buf = coding->charbuf; | |
5620 | /* -1 is to compensate for CRLF. */ | |
5621 | int *buf_end = coding->charbuf + coding->charbuf_size - 1; | |
5622 | unsigned char *src = coding->source + coding->consumed; | |
5623 | int pos = coding->src_pos + coding->consumed_char; | |
5624 | int end_pos = coding->src_pos + coding->src_chars; | |
5625 | int multibytep = coding->src_multibyte; | |
5626 | Lisp_Object eol_type; | |
5627 | int c; | |
5628 | int start, end, stop; | |
5629 | Lisp_Object object, prop; | |
88993dfd | 5630 | |
df7492f9 KH |
5631 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
5632 | if (VECTORP (eol_type)) | |
5633 | eol_type = Qunix; | |
88993dfd | 5634 | |
df7492f9 | 5635 | object = coding->src_object; |
b843d1ae | 5636 | |
df7492f9 KH |
5637 | /* Note: composition handling is not yet implemented. */ |
5638 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 5639 | |
df7492f9 KH |
5640 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK |
5641 | && find_composition (pos, end_pos, &start, &end, &prop, object) | |
5642 | && end <= end_pos | |
5643 | && (start >= pos | |
5644 | || (find_composition (end, end_pos, &start, &end, &prop, object) | |
5645 | && end <= end_pos))) | |
5646 | stop = start; | |
5647 | else | |
5648 | stop = end_pos; | |
ec6d2bb8 | 5649 | |
df7492f9 | 5650 | while (buf < buf_end) |
ec6d2bb8 | 5651 | { |
df7492f9 | 5652 | if (pos == stop) |
ec6d2bb8 | 5653 | { |
df7492f9 | 5654 | int *p; |
ec6d2bb8 | 5655 | |
df7492f9 KH |
5656 | if (pos == end_pos) |
5657 | break; | |
5658 | p = save_composition_data (buf, buf_end, prop); | |
5659 | if (p == NULL) | |
5660 | break; | |
5661 | buf = p; | |
5662 | if (find_composition (end, end_pos, &start, &end, &prop, object) | |
5663 | && end <= end_pos) | |
5664 | stop = start; | |
5665 | else | |
5666 | stop = end_pos; | |
5667 | } | |
5668 | ||
5669 | if (! multibytep) | |
5670 | c = *src++; | |
5671 | else | |
5672 | c = STRING_CHAR_ADVANCE (src); | |
5673 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) | |
5674 | c = '\n'; | |
5675 | if (! EQ (eol_type, Qunix)) | |
5676 | { | |
5677 | if (c == '\n') | |
5678 | { | |
5679 | if (EQ (eol_type, Qdos)) | |
5680 | *buf++ = '\r'; | |
5681 | else | |
5682 | c = '\r'; | |
ec6d2bb8 | 5683 | } |
ec6d2bb8 | 5684 | } |
df7492f9 KH |
5685 | *buf++ = c; |
5686 | pos++; | |
ec6d2bb8 | 5687 | } |
ec6d2bb8 | 5688 | |
df7492f9 KH |
5689 | coding->consumed = src - coding->source; |
5690 | coding->consumed_char = pos - coding->src_pos; | |
5691 | coding->charbuf_used = buf - coding->charbuf; | |
5692 | coding->chars_at_source = 0; | |
ec6d2bb8 KH |
5693 | } |
5694 | ||
ec6d2bb8 | 5695 | |
df7492f9 KH |
5696 | /* Encode the text at CODING->src_object into CODING->dst_object. |
5697 | CODING->src_object is a buffer or a string. | |
5698 | CODING->dst_object is a buffer or nil. | |
5699 | ||
5700 | If CODING->src_object is a buffer, it must be the current buffer. | |
5701 | In this case, if CODING->src_pos is positive, it is a position of | |
5702 | the source text in the buffer, otherwise. the source text is in the | |
5703 | gap area of the buffer, and coding->src_pos specifies the offset of | |
5704 | the text from GPT (which must be the same as PT). If this is the | |
5705 | same buffer as CODING->dst_object, CODING->src_pos must be | |
5706 | negative and CODING should not have `pre-write-conversion'. | |
5707 | ||
5708 | If CODING->src_object is a string, CODING should not have | |
5709 | `pre-write-conversion'. | |
5710 | ||
5711 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
5712 | the current point of that buffer. | |
5713 | ||
5714 | If CODING->dst_object is nil, the encoded data is placed at the | |
5715 | memory area specified by CODING->destination. */ | |
5716 | ||
5717 | static int | |
5718 | encode_coding (coding) | |
ec6d2bb8 | 5719 | struct coding_system *coding; |
ec6d2bb8 | 5720 | { |
df7492f9 | 5721 | Lisp_Object attrs; |
ec6d2bb8 | 5722 | |
df7492f9 | 5723 | attrs = CODING_ID_ATTRS (coding->id); |
ec6d2bb8 | 5724 | |
df7492f9 | 5725 | if (BUFFERP (coding->dst_object)) |
ec6d2bb8 | 5726 | { |
df7492f9 KH |
5727 | set_buffer_internal (XBUFFER (coding->dst_object)); |
5728 | coding->dst_multibyte | |
5729 | = ! NILP (current_buffer->enable_multibyte_characters); | |
5730 | } | |
ec6d2bb8 | 5731 | |
df7492f9 KH |
5732 | coding->consumed = coding->consumed_char = 0; |
5733 | coding->produced = coding->produced_char = 0; | |
5734 | coding->result = CODING_RESULT_SUCCESS; | |
5735 | coding->errors = 0; | |
ec6d2bb8 | 5736 | |
df7492f9 | 5737 | ALLOC_CONVERSION_WORK_AREA (coding); |
ec6d2bb8 | 5738 | |
df7492f9 KH |
5739 | do { |
5740 | coding_set_source (coding); | |
5741 | consume_chars (coding); | |
5742 | ||
5743 | if (!NILP (CODING_ATTR_ENCODE_TBL (attrs))) | |
5744 | translate_chars (CODING_ATTR_ENCODE_TBL (attrs), coding); | |
5745 | ||
5746 | coding_set_destination (coding); | |
5747 | (*(coding->encoder)) (coding); | |
5748 | } while (coding->consumed_char < coding->src_chars); | |
5749 | ||
5750 | if (BUFFERP (coding->dst_object)) | |
5751 | insert_from_gap (coding->produced_char, coding->produced); | |
5752 | ||
5753 | return (coding->result); | |
ec6d2bb8 KH |
5754 | } |
5755 | ||
df7492f9 | 5756 | /* Work buffer */ |
fb88bf2d | 5757 | |
df7492f9 KH |
5758 | /* List of currently used working buffer. */ |
5759 | Lisp_Object Vcode_conversion_work_buf_list; | |
d46c5b12 | 5760 | |
df7492f9 KH |
5761 | /* A working buffer used by the top level conversion. */ |
5762 | Lisp_Object Vcode_conversion_reused_work_buf; | |
b73bfc1c | 5763 | |
4ed46869 | 5764 | |
df7492f9 KH |
5765 | /* Return a working buffer that can be freely used by the following |
5766 | code conversion. MULTIBYTEP specifies the multibyteness of the | |
5767 | buffer. */ | |
b73bfc1c | 5768 | |
df7492f9 KH |
5769 | Lisp_Object |
5770 | make_conversion_work_buffer (multibytep) | |
5771 | int multibytep; | |
5772 | { | |
5773 | struct buffer *current = current_buffer; | |
5774 | Lisp_Object buf; | |
d46c5b12 | 5775 | |
df7492f9 | 5776 | if (NILP (Vcode_conversion_work_buf_list)) |
e133c8fa | 5777 | { |
df7492f9 KH |
5778 | if (NILP (Vcode_conversion_reused_work_buf)) |
5779 | Vcode_conversion_reused_work_buf | |
5780 | = Fget_buffer_create (build_string (" *code-conversion-work*")); | |
5781 | Vcode_conversion_work_buf_list | |
5782 | = Fcons (Vcode_conversion_reused_work_buf, Qnil); | |
e133c8fa | 5783 | } |
df7492f9 | 5784 | else |
d46c5b12 | 5785 | { |
df7492f9 KH |
5786 | int depth = Flength (Vcode_conversion_work_buf_list); |
5787 | char str[128]; | |
e077cc80 | 5788 | |
df7492f9 KH |
5789 | sprintf (str, " *code-conversion-work*<%d>", depth); |
5790 | Vcode_conversion_work_buf_list | |
5791 | = Fcons (Fget_buffer_create (build_string (str)), | |
5792 | Vcode_conversion_work_buf_list); | |
d46c5b12 | 5793 | } |
d46c5b12 | 5794 | |
df7492f9 KH |
5795 | buf = XCAR (Vcode_conversion_work_buf_list); |
5796 | set_buffer_internal (XBUFFER (buf)); | |
5797 | current_buffer->undo_list = Qt; | |
5798 | Ferase_buffer (); | |
5799 | Fset_buffer_multibyte (multibytep ? Qt : Qnil); | |
5800 | set_buffer_internal (current); | |
5801 | return buf; | |
5802 | } | |
d46c5b12 | 5803 | |
df7492f9 | 5804 | static struct coding_system *saved_coding; |
d46c5b12 | 5805 | |
df7492f9 KH |
5806 | Lisp_Object |
5807 | code_conversion_restore (info) | |
5808 | Lisp_Object info; | |
5809 | { | |
5810 | int depth = Flength (Vcode_conversion_work_buf_list); | |
5811 | Lisp_Object buf; | |
d46c5b12 | 5812 | |
df7492f9 | 5813 | if (depth > 0) |
d46c5b12 | 5814 | { |
df7492f9 KH |
5815 | buf = XCAR (Vcode_conversion_work_buf_list); |
5816 | Vcode_conversion_work_buf_list = XCDR (Vcode_conversion_work_buf_list); | |
5817 | if (depth > 1 && !NILP (Fbuffer_live_p (buf))) | |
5818 | Fkill_buffer (buf); | |
5819 | } | |
d46c5b12 | 5820 | |
df7492f9 KH |
5821 | if (saved_coding->dst_object == Qt |
5822 | && saved_coding->destination) | |
5823 | xfree (saved_coding->destination); | |
b843d1ae | 5824 | |
df7492f9 KH |
5825 | return save_excursion_restore (info); |
5826 | } | |
d46c5b12 | 5827 | |
12410ef1 | 5828 | |
df7492f9 KH |
5829 | int |
5830 | decode_coding_gap (coding, chars, bytes) | |
5831 | struct coding_system *coding; | |
5832 | EMACS_INT chars, bytes; | |
5833 | { | |
5834 | int count = specpdl_ptr - specpdl; | |
fb88bf2d | 5835 | |
df7492f9 KH |
5836 | saved_coding = coding; |
5837 | record_unwind_protect (code_conversion_restore, save_excursion_save ()); | |
ec6d2bb8 | 5838 | |
df7492f9 KH |
5839 | coding->src_object = Fcurrent_buffer (); |
5840 | coding->src_chars = chars; | |
5841 | coding->src_bytes = bytes; | |
5842 | coding->src_pos = -chars; | |
5843 | coding->src_pos_byte = -bytes; | |
5844 | coding->src_multibyte = chars < bytes; | |
5845 | coding->dst_object = coding->src_object; | |
5846 | coding->dst_pos = PT; | |
5847 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 5848 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
4956c225 | 5849 | |
df7492f9 KH |
5850 | if (CODING_REQUIRE_DETECTION (coding)) |
5851 | detect_coding (coding); | |
5852 | ||
5853 | decode_coding (coding); | |
d46c5b12 | 5854 | |
df7492f9 KH |
5855 | unbind_to (count, Qnil); |
5856 | return coding->result; | |
5857 | } | |
d46c5b12 | 5858 | |
df7492f9 KH |
5859 | int |
5860 | encode_coding_gap (coding, chars, bytes) | |
5861 | struct coding_system *coding; | |
5862 | EMACS_INT chars, bytes; | |
5863 | { | |
5864 | int count = specpdl_ptr - specpdl; | |
5865 | Lisp_Object buffer; | |
d46c5b12 | 5866 | |
df7492f9 KH |
5867 | saved_coding = coding; |
5868 | record_unwind_protect (code_conversion_restore, save_excursion_save ()); | |
fb88bf2d | 5869 | |
df7492f9 KH |
5870 | buffer = Fcurrent_buffer (); |
5871 | coding->src_object = buffer; | |
5872 | coding->src_chars = chars; | |
5873 | coding->src_bytes = bytes; | |
5874 | coding->src_pos = -chars; | |
5875 | coding->src_pos_byte = -bytes; | |
5876 | coding->src_multibyte = chars < bytes; | |
5877 | coding->dst_object = coding->src_object; | |
5878 | coding->dst_pos = PT; | |
5879 | coding->dst_pos_byte = PT_BYTE; | |
fb88bf2d | 5880 | |
df7492f9 | 5881 | encode_coding (coding); |
f2558efd | 5882 | |
df7492f9 KH |
5883 | unbind_to (count, Qnil); |
5884 | return coding->result; | |
5885 | } | |
b73bfc1c | 5886 | |
d46c5b12 | 5887 | |
df7492f9 KH |
5888 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
5889 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
ec6d2bb8 | 5890 | |
df7492f9 | 5891 | SRC_OBJECT is a buffer, a string, or Qnil. |
ec6d2bb8 | 5892 | |
df7492f9 KH |
5893 | If it is a buffer, the text is at point of the buffer. FROM and TO |
5894 | are positions in the buffer. | |
ec6d2bb8 | 5895 | |
df7492f9 KH |
5896 | If it is a string, the text is at the beginning of the string. |
5897 | FROM and TO are indices to the string. | |
ec6d2bb8 | 5898 | |
df7492f9 KH |
5899 | If it is nil, the text is at coding->source. FROM and TO are |
5900 | indices to coding->source. | |
ec6d2bb8 | 5901 | |
df7492f9 | 5902 | DST_OBJECT is a buffer, Qt, or Qnil. |
d46c5b12 | 5903 | |
df7492f9 KH |
5904 | If it is a buffer, the decoded text is inserted at point of the |
5905 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
5906 | is deleted. | |
d46c5b12 | 5907 | |
df7492f9 KH |
5908 | If it is Qt, a string is made from the decoded text, and |
5909 | set in CODING->dst_object. | |
d46c5b12 | 5910 | |
df7492f9 KH |
5911 | If it is Qnil, the decoded text is stored at CODING->destination. |
5912 | The called must allocate CODING->dst_bytes bytes at | |
5913 | CODING->destination by xmalloc. If the decoded text is longer than | |
5914 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
5915 | */ | |
d46c5b12 | 5916 | |
df7492f9 KH |
5917 | void |
5918 | decode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
5919 | dst_object) | |
5920 | struct coding_system *coding; | |
5921 | Lisp_Object src_object; | |
5922 | EMACS_INT from, from_byte, to, to_byte; | |
5923 | Lisp_Object dst_object; | |
5924 | { | |
5925 | int count = specpdl_ptr - specpdl; | |
5926 | unsigned char *destination; | |
5927 | EMACS_INT dst_bytes; | |
5928 | EMACS_INT chars = to - from; | |
5929 | EMACS_INT bytes = to_byte - from_byte; | |
5930 | Lisp_Object attrs; | |
d46c5b12 | 5931 | |
df7492f9 KH |
5932 | saved_coding = coding; |
5933 | record_unwind_protect (code_conversion_restore, save_excursion_save ()); | |
93dec019 | 5934 | |
df7492f9 KH |
5935 | if (NILP (dst_object)) |
5936 | { | |
5937 | destination = coding->destination; | |
5938 | dst_bytes = coding->dst_bytes; | |
5939 | } | |
93dec019 | 5940 | |
df7492f9 KH |
5941 | coding->src_object = src_object; |
5942 | coding->src_chars = chars; | |
5943 | coding->src_bytes = bytes; | |
5944 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 5945 | |
df7492f9 KH |
5946 | if (STRINGP (src_object)) |
5947 | { | |
5948 | coding->src_pos = from; | |
5949 | coding->src_pos_byte = from_byte; | |
5950 | } | |
5951 | else if (BUFFERP (src_object)) | |
5952 | { | |
5953 | set_buffer_internal (XBUFFER (src_object)); | |
5954 | if (from != GPT) | |
5955 | move_gap_both (from, from_byte); | |
5956 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 5957 | { |
df7492f9 KH |
5958 | TEMP_SET_PT_BOTH (from, from_byte); |
5959 | del_range_both (from, from_byte, to, to_byte, 1); | |
5960 | coding->src_pos = -chars; | |
5961 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 5962 | } |
df7492f9 | 5963 | else |
fb88bf2d | 5964 | { |
df7492f9 KH |
5965 | coding->src_pos = from; |
5966 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 5967 | } |
d46c5b12 | 5968 | } |
fb88bf2d | 5969 | |
df7492f9 KH |
5970 | if (CODING_REQUIRE_DETECTION (coding)) |
5971 | detect_coding (coding); | |
5972 | attrs = CODING_ID_ATTRS (coding->id); | |
5973 | ||
5974 | if (! NILP (CODING_ATTR_POST_READ (attrs)) | |
5975 | || EQ (dst_object, Qt)) | |
b73bfc1c | 5976 | { |
df7492f9 KH |
5977 | coding->dst_object = make_conversion_work_buffer (1); |
5978 | coding->dst_pos = BEG; | |
5979 | coding->dst_pos_byte = BEG_BYTE; | |
5980 | coding->dst_multibyte = 1; | |
b73bfc1c | 5981 | } |
df7492f9 | 5982 | else if (BUFFERP (dst_object)) |
12410ef1 | 5983 | { |
df7492f9 KH |
5984 | coding->dst_object = dst_object; |
5985 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
5986 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
5987 | coding->dst_multibyte | |
5988 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
12410ef1 | 5989 | } |
72d1a715 | 5990 | else |
df7492f9 KH |
5991 | { |
5992 | coding->dst_object = Qnil; | |
5993 | coding->dst_multibyte = 1; | |
5994 | } | |
5995 | ||
5996 | decode_coding (coding); | |
4ed46869 | 5997 | |
df7492f9 KH |
5998 | if (BUFFERP (coding->dst_object)) |
5999 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
ec6d2bb8 | 6000 | |
df7492f9 | 6001 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 6002 | { |
df7492f9 KH |
6003 | struct gcpro gcpro1, gcpro2; |
6004 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; | |
2b4f9037 | 6005 | Lisp_Object val; |
4ed46869 | 6006 | |
c0cc7f7f | 6007 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
df7492f9 KH |
6008 | GCPRO2 (coding->src_object, coding->dst_object); |
6009 | val = call1 (CODING_ATTR_POST_READ (attrs), | |
6010 | make_number (coding->produced_char)); | |
6011 | UNGCPRO; | |
6012 | CHECK_NATNUM (val); | |
6013 | coding->produced_char += Z - prev_Z; | |
6014 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 6015 | } |
4ed46869 | 6016 | |
df7492f9 | 6017 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 6018 | { |
df7492f9 KH |
6019 | coding->dst_object = Fbuffer_string (); |
6020 | } | |
6021 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
6022 | { | |
6023 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
6024 | if (dst_bytes < coding->produced) | |
6025 | { | |
6026 | destination | |
6027 | = (unsigned char *) xrealloc (destination, coding->produced); | |
6028 | if (! destination) | |
6029 | { | |
6030 | coding->result = CODING_RESULT_INSUFFICIENT_DST; | |
6031 | unbind_to (count, Qnil); | |
6032 | return; | |
6033 | } | |
6034 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
6035 | move_gap_both (BEGV, BEGV_BYTE); | |
6036 | bcopy (BEGV_ADDR, destination, coding->produced); | |
6037 | coding->destination = destination; | |
6038 | } | |
ec6d2bb8 | 6039 | } |
2b4f9037 | 6040 | |
df7492f9 | 6041 | unbind_to (count, Qnil); |
d46c5b12 KH |
6042 | } |
6043 | ||
df7492f9 KH |
6044 | |
6045 | void | |
6046 | encode_coding_object (coding, src_object, from, from_byte, to, to_byte, | |
6047 | dst_object) | |
b73bfc1c | 6048 | struct coding_system *coding; |
df7492f9 KH |
6049 | Lisp_Object src_object; |
6050 | EMACS_INT from, from_byte, to, to_byte; | |
6051 | Lisp_Object dst_object; | |
b73bfc1c KH |
6052 | { |
6053 | int count = specpdl_ptr - specpdl; | |
df7492f9 KH |
6054 | EMACS_INT chars = to - from; |
6055 | EMACS_INT bytes = to_byte - from_byte; | |
6056 | Lisp_Object attrs; | |
6057 | ||
6058 | saved_coding = coding; | |
6059 | record_unwind_protect (code_conversion_restore, save_excursion_save ()); | |
6060 | ||
6061 | coding->src_object = src_object; | |
6062 | coding->src_chars = chars; | |
6063 | coding->src_bytes = bytes; | |
6064 | coding->src_multibyte = chars < bytes; | |
6065 | ||
6066 | attrs = CODING_ID_ATTRS (coding->id); | |
6067 | ||
6068 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
6bac5b12 | 6069 | { |
df7492f9 KH |
6070 | coding->src_object = make_conversion_work_buffer (coding->src_multibyte); |
6071 | set_buffer_internal (XBUFFER (coding->src_object)); | |
6072 | if (STRINGP (src_object)) | |
6073 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
6074 | else if (BUFFERP (src_object)) | |
6075 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
6076 | else | |
6077 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
6078 | ||
6079 | if (EQ (src_object, dst_object)) | |
6080 | { | |
6081 | set_buffer_internal (XBUFFER (src_object)); | |
6082 | del_range_both (from, from_byte, to, to_byte, 1); | |
6083 | set_buffer_internal (XBUFFER (coding->src_object)); | |
6084 | } | |
6085 | ||
ac87bbef KH |
6086 | call2 (CODING_ATTR_PRE_WRITE (attrs), |
6087 | make_number (BEG), make_number (Z)); | |
6088 | coding->src_object = Fcurrent_buffer (); | |
df7492f9 KH |
6089 | if (BEG != GPT) |
6090 | move_gap_both (BEG, BEG_BYTE); | |
6091 | coding->src_chars = Z - BEG; | |
6092 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
6093 | coding->src_pos = BEG; | |
6094 | coding->src_pos_byte = BEG_BYTE; | |
6095 | coding->src_multibyte = Z < Z_BYTE; | |
6096 | } | |
6097 | else if (STRINGP (src_object)) | |
6098 | { | |
6099 | coding->src_pos = from; | |
6100 | coding->src_pos_byte = from_byte; | |
6101 | } | |
6102 | else if (BUFFERP (src_object)) | |
d46c5b12 | 6103 | { |
df7492f9 KH |
6104 | set_buffer_internal (XBUFFER (src_object)); |
6105 | if (from != GPT) | |
6106 | move_gap_both (from, from_byte); | |
6107 | if (EQ (src_object, dst_object)) | |
d46c5b12 | 6108 | { |
df7492f9 KH |
6109 | del_range_both (from, from_byte, to, to_byte, 1); |
6110 | coding->src_pos = -chars; | |
6111 | coding->src_pos_byte = -bytes; | |
d46c5b12 | 6112 | } |
df7492f9 | 6113 | else |
d46c5b12 | 6114 | { |
df7492f9 KH |
6115 | coding->src_pos = from; |
6116 | coding->src_pos_byte = from_byte; | |
d46c5b12 KH |
6117 | } |
6118 | } | |
4ed46869 | 6119 | |
df7492f9 | 6120 | if (BUFFERP (dst_object)) |
d46c5b12 | 6121 | { |
df7492f9 KH |
6122 | coding->dst_object = dst_object; |
6123 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
6124 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
6125 | coding->dst_multibyte | |
6126 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
b73bfc1c | 6127 | } |
df7492f9 | 6128 | else if (EQ (dst_object, Qt)) |
4956c225 | 6129 | { |
df7492f9 | 6130 | coding->dst_object = Qnil; |
df7492f9 | 6131 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
6132 | if (coding->dst_bytes == 0) |
6133 | coding->dst_bytes = 1; | |
6134 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 6135 | coding->dst_multibyte = 0; |
4956c225 | 6136 | } |
df7492f9 | 6137 | else |
78108bcd | 6138 | { |
df7492f9 KH |
6139 | coding->dst_object = Qnil; |
6140 | coding->dst_multibyte = 0; | |
78108bcd KH |
6141 | } |
6142 | ||
df7492f9 | 6143 | encode_coding (coding); |
4ed46869 | 6144 | |
df7492f9 | 6145 | if (EQ (dst_object, Qt)) |
4ed46869 | 6146 | { |
df7492f9 KH |
6147 | if (BUFFERP (coding->dst_object)) |
6148 | coding->dst_object = Fbuffer_string (); | |
6149 | else | |
73be902c | 6150 | { |
df7492f9 KH |
6151 | coding->dst_object |
6152 | = make_unibyte_string ((char *) coding->destination, | |
6153 | coding->produced); | |
6154 | xfree (coding->destination); | |
73be902c | 6155 | } |
4ed46869 | 6156 | } |
d46c5b12 | 6157 | |
df7492f9 | 6158 | unbind_to (count, Qnil); |
b73bfc1c KH |
6159 | } |
6160 | ||
df7492f9 | 6161 | |
b73bfc1c | 6162 | Lisp_Object |
df7492f9 | 6163 | preferred_coding_system () |
b73bfc1c | 6164 | { |
df7492f9 | 6165 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 6166 | |
df7492f9 | 6167 | return CODING_ID_NAME (id); |
4ed46869 KH |
6168 | } |
6169 | ||
6170 | \f | |
6171 | #ifdef emacs | |
1397dc18 | 6172 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 6173 | |
4ed46869 | 6174 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 6175 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 6176 | See the documentation of `define-coding-system' for information |
48b0f3ae PJ |
6177 | about coding-system objects. */) |
6178 | (obj) | |
4ed46869 KH |
6179 | Lisp_Object obj; |
6180 | { | |
df7492f9 | 6181 | return ((NILP (obj) || CODING_SYSTEM_P (obj)) ? Qt : Qnil); |
4ed46869 KH |
6182 | } |
6183 | ||
9d991de8 RS |
6184 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
6185 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae PJ |
6186 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
6187 | (prompt) | |
4ed46869 KH |
6188 | Lisp_Object prompt; |
6189 | { | |
e0e989f6 | 6190 | Lisp_Object val; |
9d991de8 RS |
6191 | do |
6192 | { | |
4608c386 KH |
6193 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
6194 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 RS |
6195 | } |
6196 | while (XSTRING (val)->size == 0); | |
e0e989f6 | 6197 | return (Fintern (val, Qnil)); |
4ed46869 KH |
6198 | } |
6199 | ||
9b787f3e | 6200 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae PJ |
6201 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
6202 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. */) | |
6203 | (prompt, default_coding_system) | |
9b787f3e | 6204 | Lisp_Object prompt, default_coding_system; |
4ed46869 | 6205 | { |
f44d27ce | 6206 | Lisp_Object val; |
9b787f3e RS |
6207 | if (SYMBOLP (default_coding_system)) |
6208 | XSETSTRING (default_coding_system, XSYMBOL (default_coding_system)->name); | |
4608c386 | 6209 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
6210 | Qt, Qnil, Qcoding_system_history, |
6211 | default_coding_system, Qnil); | |
e0e989f6 | 6212 | return (XSTRING (val)->size == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
6213 | } |
6214 | ||
6215 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
6216 | 1, 1, 0, | |
48b0f3ae PJ |
6217 | doc: /* Check validity of CODING-SYSTEM. |
6218 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. | |
6219 | It is valid if it is a symbol with a non-nil `coding-system' property. | |
6220 | The value of property should be a vector of length 5. */) | |
df7492f9 | 6221 | (coding_system) |
4ed46869 KH |
6222 | Lisp_Object coding_system; |
6223 | { | |
b7826503 | 6224 | CHECK_SYMBOL (coding_system); |
4ed46869 KH |
6225 | if (!NILP (Fcoding_system_p (coding_system))) |
6226 | return coding_system; | |
6227 | while (1) | |
02ba4723 | 6228 | Fsignal (Qcoding_system_error, Fcons (coding_system, Qnil)); |
4ed46869 | 6229 | } |
df7492f9 | 6230 | |
3a73fa5d | 6231 | \f |
d46c5b12 | 6232 | Lisp_Object |
df7492f9 | 6233 | detect_coding_system (src, src_bytes, highest, multibytep, coding_system) |
d46c5b12 KH |
6234 | unsigned char *src; |
6235 | int src_bytes, highest; | |
0a28aafb | 6236 | int multibytep; |
df7492f9 | 6237 | Lisp_Object coding_system; |
4ed46869 | 6238 | { |
df7492f9 KH |
6239 | unsigned char *src_end = src + src_bytes; |
6240 | int mask = CATEGORY_MASK_ANY; | |
6241 | int detected = 0; | |
6242 | int c, i; | |
6243 | Lisp_Object attrs, eol_type; | |
6244 | Lisp_Object val; | |
6245 | struct coding_system coding; | |
6246 | ||
6247 | if (NILP (coding_system)) | |
6248 | coding_system = Qundecided; | |
6249 | setup_coding_system (coding_system, &coding); | |
6250 | attrs = CODING_ID_ATTRS (coding.id); | |
6251 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
4ed46869 | 6252 | |
df7492f9 KH |
6253 | coding.source = src; |
6254 | coding.src_bytes = src_bytes; | |
6255 | coding.src_multibyte = multibytep; | |
6256 | coding.consumed = 0; | |
4ed46869 | 6257 | |
df7492f9 | 6258 | if (XINT (CODING_ATTR_CATEGORY (attrs)) != coding_category_undecided) |
4ed46869 | 6259 | { |
df7492f9 | 6260 | mask = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
4ed46869 | 6261 | } |
df7492f9 | 6262 | else |
4ed46869 | 6263 | { |
df7492f9 KH |
6264 | coding_system = Qnil; |
6265 | for (; src < src_end; src++) | |
4ed46869 | 6266 | { |
df7492f9 KH |
6267 | c = *src; |
6268 | if (c & 0x80 || (c < 0x20 && (c == ISO_CODE_ESC | |
6269 | || c == ISO_CODE_SI | |
6270 | || c == ISO_CODE_SO))) | |
d46c5b12 | 6271 | break; |
4ed46869 | 6272 | } |
df7492f9 KH |
6273 | coding.head_ascii = src - coding.source; |
6274 | ||
6275 | if (src < src_end) | |
6276 | for (i = 0; i < coding_category_raw_text; i++) | |
6277 | { | |
6278 | enum coding_category category = coding_priorities[i]; | |
6279 | struct coding_system *this = coding_categories + category; | |
6280 | ||
6281 | if (category >= coding_category_raw_text | |
6282 | || detected & (1 << category)) | |
6283 | continue; | |
6284 | ||
6285 | if (this->id < 0) | |
6286 | { | |
6287 | /* No coding system of this category is defined. */ | |
6288 | mask &= ~(1 << category); | |
6289 | } | |
6290 | else | |
6291 | { | |
6292 | detected |= detected_mask[category]; | |
6293 | if ((*(coding_categories[category].detector)) (&coding, &mask) | |
6294 | && highest) | |
6295 | { | |
6296 | mask &= detected_mask[category]; | |
6297 | break; | |
6298 | } | |
6299 | } | |
6300 | } | |
4ed46869 | 6301 | } |
4ed46869 | 6302 | |
df7492f9 KH |
6303 | if (!mask) |
6304 | val = Fcons (make_number (coding_category_raw_text), Qnil); | |
6305 | else if (mask == CATEGORY_MASK_ANY) | |
6306 | val = Fcons (make_number (coding_category_undecided), Qnil); | |
6307 | else if (highest) | |
4ed46869 | 6308 | { |
df7492f9 KH |
6309 | for (i = 0; i < coding_category_raw_text; i++) |
6310 | if (mask & (1 << coding_priorities[i])) | |
6311 | { | |
6312 | val = Fcons (make_number (coding_priorities[i]), Qnil); | |
6313 | break; | |
6314 | } | |
6315 | } | |
6316 | else | |
6317 | { | |
6318 | val = Qnil; | |
6319 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
6320 | if (mask & (1 << coding_priorities[i])) | |
6321 | val = Fcons (make_number (coding_priorities[i]), val); | |
4ed46869 | 6322 | } |
df7492f9 KH |
6323 | |
6324 | { | |
6325 | int one_byte_eol = -1, two_byte_eol = -1; | |
6326 | Lisp_Object tail; | |
6327 | ||
6328 | for (tail = val; CONSP (tail); tail = XCDR (tail)) | |
6329 | { | |
6330 | struct coding_system *this | |
6331 | = (NILP (coding_system) ? coding_categories + XINT (XCAR (tail)) | |
6332 | : &coding); | |
6333 | int this_eol; | |
6334 | ||
6335 | attrs = CODING_ID_ATTRS (this->id); | |
6336 | eol_type = CODING_ID_EOL_TYPE (this->id); | |
6337 | XSETCAR (tail, CODING_ID_NAME (this->id)); | |
6338 | if (VECTORP (eol_type)) | |
6339 | { | |
6340 | if (EQ (CODING_ATTR_TYPE (attrs), Qutf_16)) | |
6341 | { | |
6342 | if (two_byte_eol < 0) | |
6343 | two_byte_eol = detect_eol (this, coding.source, src_bytes); | |
6344 | this_eol = two_byte_eol; | |
6345 | } | |
6346 | else | |
6347 | { | |
6348 | if (one_byte_eol < 0) | |
6349 | one_byte_eol =detect_eol (this, coding.source, src_bytes); | |
6350 | this_eol = one_byte_eol; | |
6351 | } | |
6352 | if (this_eol == EOL_SEEN_LF) | |
6353 | XSETCAR (tail, AREF (eol_type, 0)); | |
6354 | else if (this_eol == EOL_SEEN_CRLF) | |
6355 | XSETCAR (tail, AREF (eol_type, 1)); | |
6356 | else if (this_eol == EOL_SEEN_CR) | |
6357 | XSETCAR (tail, AREF (eol_type, 2)); | |
6358 | } | |
6359 | } | |
6360 | } | |
6361 | ||
03699b14 | 6362 | return (highest ? XCAR (val) : val); |
93dec019 | 6363 | } |
4ed46869 | 6364 | |
df7492f9 | 6365 | |
d46c5b12 KH |
6366 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
6367 | 2, 3, 0, | |
48b0f3ae PJ |
6368 | doc: /* Detect coding system of the text in the region between START and END. |
6369 | Return a list of possible coding systems ordered by priority. | |
6370 | ||
6371 | If only ASCII characters are found, it returns a list of single element | |
6372 | `undecided' or its subsidiary coding system according to a detected | |
6373 | end-of-line format. | |
6374 | ||
6375 | If optional argument HIGHEST is non-nil, return the coding system of | |
6376 | highest priority. */) | |
6377 | (start, end, highest) | |
d46c5b12 KH |
6378 | Lisp_Object start, end, highest; |
6379 | { | |
6380 | int from, to; | |
6381 | int from_byte, to_byte; | |
6289dd10 | 6382 | |
b7826503 PJ |
6383 | CHECK_NUMBER_COERCE_MARKER (start); |
6384 | CHECK_NUMBER_COERCE_MARKER (end); | |
4ed46869 | 6385 | |
d46c5b12 KH |
6386 | validate_region (&start, &end); |
6387 | from = XINT (start), to = XINT (end); | |
6388 | from_byte = CHAR_TO_BYTE (from); | |
6389 | to_byte = CHAR_TO_BYTE (to); | |
6289dd10 | 6390 | |
d46c5b12 KH |
6391 | if (from < GPT && to >= GPT) |
6392 | move_gap_both (to, to_byte); | |
c210f766 | 6393 | |
d46c5b12 | 6394 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
df7492f9 | 6395 | to_byte - from_byte, |
0a28aafb KH |
6396 | !NILP (highest), |
6397 | !NILP (current_buffer | |
df7492f9 KH |
6398 | ->enable_multibyte_characters), |
6399 | Qnil); | |
d46c5b12 | 6400 | } |
6289dd10 | 6401 | |
d46c5b12 KH |
6402 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
6403 | 1, 2, 0, | |
48b0f3ae PJ |
6404 | doc: /* Detect coding system of the text in STRING. |
6405 | Return a list of possible coding systems ordered by priority. | |
6406 | ||
6407 | If only ASCII characters are found, it returns a list of single element | |
6408 | `undecided' or its subsidiary coding system according to a detected | |
6409 | end-of-line format. | |
6410 | ||
6411 | If optional argument HIGHEST is non-nil, return the coding system of | |
6412 | highest priority. */) | |
6413 | (string, highest) | |
d46c5b12 KH |
6414 | Lisp_Object string, highest; |
6415 | { | |
b7826503 | 6416 | CHECK_STRING (string); |
4ed46869 | 6417 | |
d46c5b12 | 6418 | return detect_coding_system (XSTRING (string)->data, |
df7492f9 | 6419 | STRING_BYTES (XSTRING (string)), |
0a28aafb | 6420 | !NILP (highest), |
df7492f9 KH |
6421 | STRING_MULTIBYTE (string), |
6422 | Qnil); | |
4ed46869 KH |
6423 | } |
6424 | ||
05e6f5dc | 6425 | |
df7492f9 KH |
6426 | static INLINE int |
6427 | char_encodable_p (c, attrs) | |
6428 | int c; | |
6429 | Lisp_Object attrs; | |
05e6f5dc | 6430 | { |
df7492f9 | 6431 | Lisp_Object tail; |
df7492f9 | 6432 | struct charset *charset; |
05e6f5dc | 6433 | |
df7492f9 KH |
6434 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
6435 | CONSP (tail); tail = XCDR (tail)) | |
05e6f5dc | 6436 | { |
df7492f9 KH |
6437 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
6438 | if (CHAR_CHARSET_P (c, charset)) | |
6439 | break; | |
05e6f5dc | 6440 | } |
df7492f9 | 6441 | return (! NILP (tail)); |
05e6f5dc KH |
6442 | } |
6443 | ||
6444 | ||
df7492f9 KH |
6445 | /* Return a list of coding systems that safely encode the text between |
6446 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
6447 | systems not to check. The returned list doesn't contain any such | |
6448 | coding systems. In any case, If the text contains only ASCII or is | |
6449 | unibyte, return t. */ | |
6450 | ||
6451 | DEFUN ("find-coding-systems-region-internal", | |
6452 | Ffind_coding_systems_region_internal, | |
6453 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
6454 | doc: /* Internal use only. */) | |
6455 | (start, end, exclude) | |
6456 | Lisp_Object start, end, exclude; | |
6457 | { | |
6458 | Lisp_Object coding_attrs_list, safe_codings; | |
6459 | EMACS_INT start_byte, end_byte; | |
6460 | unsigned char *p, *pbeg, *pend; | |
6461 | int c; | |
6462 | Lisp_Object tail, elt; | |
05e6f5dc | 6463 | |
df7492f9 KH |
6464 | if (STRINGP (start)) |
6465 | { | |
6466 | if (!STRING_MULTIBYTE (start) | |
6467 | && XSTRING (start)->size != STRING_BYTES (XSTRING (start))) | |
6468 | return Qt; | |
6469 | start_byte = 0; | |
6470 | end_byte = STRING_BYTES (XSTRING (start)); | |
6471 | } | |
6472 | else | |
6473 | { | |
6474 | CHECK_NUMBER_COERCE_MARKER (start); | |
6475 | CHECK_NUMBER_COERCE_MARKER (end); | |
6476 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
6477 | args_out_of_range (start, end); | |
6478 | if (NILP (current_buffer->enable_multibyte_characters)) | |
6479 | return Qt; | |
6480 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
6481 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
6482 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
6483 | return Qt; | |
05e6f5dc | 6484 | |
df7492f9 KH |
6485 | if (start < GPT && end > GPT) |
6486 | { | |
6487 | if ((GPT - start) < (end - GPT)) | |
6488 | move_gap_both (start, start_byte); | |
6489 | else | |
6490 | move_gap_both (end, end_byte); | |
6491 | } | |
6492 | } | |
05e6f5dc | 6493 | |
df7492f9 KH |
6494 | coding_attrs_list = Qnil; |
6495 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
6496 | if (NILP (exclude) | |
6497 | || NILP (Fmemq (XCAR (tail), exclude))) | |
6498 | { | |
6499 | Lisp_Object attrs; | |
05e6f5dc | 6500 | |
df7492f9 KH |
6501 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
6502 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
6503 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
6504 | coding_attrs_list = Fcons (attrs, coding_attrs_list); | |
6505 | } | |
6506 | ||
6507 | if (STRINGP (start)) | |
6508 | p = pbeg = XSTRING (start)->data; | |
6509 | else | |
6510 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
6511 | pend = p + (end_byte - start_byte); | |
6512 | ||
6513 | while (p < pend && ASCII_BYTE_P (*p)) p++; | |
6514 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
05e6f5dc KH |
6515 | |
6516 | while (p < pend) | |
6517 | { | |
df7492f9 KH |
6518 | if (ASCII_BYTE_P (*p)) |
6519 | p++; | |
6520 | else | |
6521 | { | |
6522 | c = STRING_CHAR_ADVANCE (p); | |
6523 | ||
6524 | charset_map_loaded = 0; | |
6525 | for (tail = coding_attrs_list; CONSP (tail);) | |
6526 | { | |
6527 | elt = XCAR (tail); | |
6528 | if (NILP (elt)) | |
6529 | tail = XCDR (tail); | |
6530 | else if (char_encodable_p (c, elt)) | |
6531 | tail = XCDR (tail); | |
6532 | else if (CONSP (XCDR (tail))) | |
6533 | { | |
6534 | XSETCAR (tail, XCAR (XCDR (tail))); | |
6535 | XSETCDR (tail, XCDR (XCDR (tail))); | |
6536 | } | |
6537 | else | |
6538 | { | |
6539 | XSETCAR (tail, Qnil); | |
6540 | tail = XCDR (tail); | |
6541 | } | |
6542 | } | |
6543 | if (charset_map_loaded) | |
6544 | { | |
6545 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 6546 | |
df7492f9 KH |
6547 | if (STRINGP (start)) |
6548 | pbeg = XSTRING (start)->data; | |
6549 | else | |
6550 | pbeg = BYTE_POS_ADDR (start_byte); | |
6551 | p = pbeg + p_offset; | |
6552 | pend = pbeg + pend_offset; | |
6553 | } | |
6554 | } | |
05e6f5dc | 6555 | } |
df7492f9 KH |
6556 | |
6557 | safe_codings = Qnil; | |
6558 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) | |
6559 | if (! NILP (XCAR (tail))) | |
6560 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
6561 | ||
05e6f5dc KH |
6562 | return safe_codings; |
6563 | } | |
6564 | ||
6565 | ||
df7492f9 KH |
6566 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
6567 | Scheck_coding_systems_region, 3, 3, 0, | |
6568 | doc: /* Check if the region is encodable by coding systems. | |
05e6f5dc | 6569 | |
df7492f9 KH |
6570 | START and END are buffer positions specifying the region. |
6571 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
6572 | ||
6573 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where | |
6574 | CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the | |
6575 | whole region, POS0, POS1, ... are buffer positions where non-encodable | |
6576 | characters are found. | |
6577 | ||
6578 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the | |
6579 | value is nil. | |
6580 | ||
6581 | START may be a string. In that case, check if the string is | |
6582 | encodable, and the value contains indices to the string instead of | |
6583 | buffer positions. END is ignored. */) | |
6584 | (start, end, coding_system_list) | |
6585 | Lisp_Object start, end, coding_system_list; | |
05e6f5dc | 6586 | { |
df7492f9 KH |
6587 | Lisp_Object list; |
6588 | EMACS_INT start_byte, end_byte; | |
6589 | int pos; | |
6590 | unsigned char *p, *pbeg, *pend; | |
6591 | int c; | |
6592 | Lisp_Object tail, elt; | |
05e6f5dc KH |
6593 | |
6594 | if (STRINGP (start)) | |
6595 | { | |
df7492f9 KH |
6596 | if (!STRING_MULTIBYTE (start) |
6597 | && XSTRING (start)->size != STRING_BYTES (XSTRING (start))) | |
6598 | return Qnil; | |
6599 | start_byte = 0; | |
6600 | end_byte = STRING_BYTES (XSTRING (start)); | |
6601 | pos = 0; | |
05e6f5dc KH |
6602 | } |
6603 | else | |
6604 | { | |
b7826503 PJ |
6605 | CHECK_NUMBER_COERCE_MARKER (start); |
6606 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
6607 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
6608 | args_out_of_range (start, end); | |
6609 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
6610 | return Qnil; |
6611 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
6612 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
6613 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
05e6f5dc | 6614 | return Qt; |
df7492f9 KH |
6615 | |
6616 | if (start < GPT && end > GPT) | |
6617 | { | |
6618 | if ((GPT - start) < (end - GPT)) | |
6619 | move_gap_both (start, start_byte); | |
6620 | else | |
6621 | move_gap_both (end, end_byte); | |
6622 | } | |
6623 | pos = start; | |
6624 | } | |
6625 | ||
6626 | list = Qnil; | |
6627 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
6628 | { | |
6629 | elt = XCAR (tail); | |
6630 | list = Fcons (Fcons (elt, Fcons (AREF (CODING_SYSTEM_SPEC (elt), 0), | |
6631 | Qnil)), | |
6632 | list); | |
05e6f5dc KH |
6633 | } |
6634 | ||
df7492f9 KH |
6635 | if (STRINGP (start)) |
6636 | p = pbeg = XSTRING (start)->data; | |
6637 | else | |
6638 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
6639 | pend = p + (end_byte - start_byte); | |
6640 | ||
6641 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; | |
6642 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
6643 | ||
6644 | while (p < pend) | |
05e6f5dc | 6645 | { |
df7492f9 KH |
6646 | if (ASCII_BYTE_P (*p)) |
6647 | p++; | |
6648 | else | |
05e6f5dc | 6649 | { |
df7492f9 KH |
6650 | c = STRING_CHAR_ADVANCE (p); |
6651 | ||
6652 | charset_map_loaded = 0; | |
6653 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
6654 | { | |
6655 | elt = XCDR (XCAR (tail)); | |
6656 | if (! char_encodable_p (c, XCAR (elt))) | |
6657 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
6658 | } | |
6659 | if (charset_map_loaded) | |
6660 | { | |
6661 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
6662 | ||
6663 | if (STRINGP (start)) | |
6664 | pbeg = XSTRING (start)->data; | |
6665 | else | |
6666 | pbeg = BYTE_POS_ADDR (start_byte); | |
6667 | p = pbeg + p_offset; | |
6668 | pend = pbeg + pend_offset; | |
6669 | } | |
05e6f5dc | 6670 | } |
df7492f9 | 6671 | pos++; |
05e6f5dc KH |
6672 | } |
6673 | ||
df7492f9 KH |
6674 | tail = list; |
6675 | list = Qnil; | |
6676 | for (; CONSP (tail); tail = XCDR (tail)) | |
05e6f5dc | 6677 | { |
df7492f9 KH |
6678 | elt = XCAR (tail); |
6679 | if (CONSP (XCDR (XCDR (elt)))) | |
6680 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
6681 | list); | |
05e6f5dc | 6682 | } |
df7492f9 KH |
6683 | |
6684 | return list; | |
05e6f5dc KH |
6685 | } |
6686 | ||
6687 | ||
df7492f9 | 6688 | |
4031e2bf | 6689 | Lisp_Object |
df7492f9 KH |
6690 | code_convert_region (start, end, coding_system, dst_object, encodep, norecord) |
6691 | Lisp_Object start, end, coding_system, dst_object; | |
6692 | int encodep, norecord; | |
3a73fa5d RS |
6693 | { |
6694 | struct coding_system coding; | |
df7492f9 KH |
6695 | EMACS_INT from, from_byte, to, to_byte; |
6696 | Lisp_Object src_object; | |
3a73fa5d | 6697 | |
b7826503 PJ |
6698 | CHECK_NUMBER_COERCE_MARKER (start); |
6699 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
6700 | if (NILP (coding_system)) |
6701 | coding_system = Qno_conversion; | |
6702 | else | |
6703 | CHECK_CODING_SYSTEM (coding_system); | |
6704 | src_object = Fcurrent_buffer (); | |
6705 | if (NILP (dst_object)) | |
6706 | dst_object = src_object; | |
6707 | else if (! EQ (dst_object, Qt)) | |
6708 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 6709 | |
d46c5b12 KH |
6710 | validate_region (&start, &end); |
6711 | from = XFASTINT (start); | |
df7492f9 | 6712 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 6713 | to = XFASTINT (end); |
df7492f9 | 6714 | to_byte = CHAR_TO_BYTE (to); |
d46c5b12 | 6715 | |
df7492f9 KH |
6716 | setup_coding_system (coding_system, &coding); |
6717 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
6718 | ||
6719 | if (encodep) | |
6720 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
6721 | dst_object); | |
6722 | else | |
6723 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
6724 | dst_object); | |
6725 | if (! norecord) | |
6726 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
d46c5b12 | 6727 | |
df7492f9 KH |
6728 | if (coding.result != CODING_RESULT_SUCCESS) |
6729 | error ("Code conversion error: %d", coding.result); | |
3a73fa5d | 6730 | |
df7492f9 KH |
6731 | return (BUFFERP (dst_object) |
6732 | ? make_number (coding.produced_char) | |
6733 | : coding.dst_object); | |
4031e2bf KH |
6734 | } |
6735 | ||
df7492f9 | 6736 | |
4031e2bf | 6737 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 6738 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 6739 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
6740 | When called from a program, takes four arguments: |
6741 | START, END, CODING-SYSTEM, and DESTINATION. | |
6742 | START and END are buffer positions. | |
6743 | ||
6744 | Optional 4th arguments DESTINATION specifies where the decoded text goes. | |
6745 | If nil, the region between START and END is replace by the decoded text. | |
6746 | If buffer, the decoded text is inserted in the buffer. | |
6747 | If t, the decoded text is returned. | |
6748 | ||
48b0f3ae PJ |
6749 | This function sets `last-coding-system-used' to the precise coding system |
6750 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
6751 | not fully specified.) | |
6752 | It returns the length of the decoded text. */) | |
df7492f9 KH |
6753 | (start, end, coding_system, destination) |
6754 | Lisp_Object start, end, coding_system, destination; | |
4031e2bf | 6755 | { |
df7492f9 | 6756 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d RS |
6757 | } |
6758 | ||
6759 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, | |
df7492f9 KH |
6760 | 3, 4, "r\nzCoding system: ", |
6761 | doc: /* Encode the current region by specified coding system. | |
48b0f3ae PJ |
6762 | When called from a program, takes three arguments: |
6763 | START, END, and CODING-SYSTEM. START and END are buffer positions. | |
df7492f9 KH |
6764 | |
6765 | Optional 4th arguments DESTINATION specifies where the encoded text goes. | |
6766 | If nil, the region between START and END is replace by the encoded text. | |
6767 | If buffer, the encoded text is inserted in the buffer. | |
6768 | If t, the encoded text is returned. | |
6769 | ||
48b0f3ae PJ |
6770 | This function sets `last-coding-system-used' to the precise coding system |
6771 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
6772 | not fully specified.) | |
6773 | It returns the length of the encoded text. */) | |
df7492f9 KH |
6774 | (start, end, coding_system, destination) |
6775 | Lisp_Object start, end, coding_system, destination; | |
3a73fa5d | 6776 | { |
df7492f9 | 6777 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
4031e2bf | 6778 | } |
3a73fa5d | 6779 | |
4031e2bf | 6780 | Lisp_Object |
df7492f9 KH |
6781 | code_convert_string (string, coding_system, dst_object, |
6782 | encodep, nocopy, norecord) | |
6783 | Lisp_Object string, coding_system, dst_object; | |
6784 | int encodep, nocopy, norecord; | |
4031e2bf KH |
6785 | { |
6786 | struct coding_system coding; | |
df7492f9 | 6787 | EMACS_INT chars, bytes; |
3a73fa5d | 6788 | |
b7826503 | 6789 | CHECK_STRING (string); |
d46c5b12 | 6790 | if (NILP (coding_system)) |
df7492f9 KH |
6791 | { |
6792 | if (! norecord) | |
6793 | Vlast_coding_system_used = Qno_conversion; | |
6794 | if (NILP (dst_object)) | |
6795 | return (nocopy ? Fcopy_sequence (string) : string); | |
6796 | } | |
4ed46869 | 6797 | |
df7492f9 KH |
6798 | if (NILP (coding_system)) |
6799 | coding_system = Qno_conversion; | |
6800 | else | |
6801 | CHECK_CODING_SYSTEM (coding_system); | |
6802 | if (NILP (dst_object)) | |
6803 | dst_object = Qt; | |
6804 | else if (! EQ (dst_object, Qt)) | |
6805 | CHECK_BUFFER (dst_object); | |
5f1cd180 | 6806 | |
df7492f9 | 6807 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 6808 | coding.mode |= CODING_MODE_LAST_BLOCK; |
df7492f9 KH |
6809 | chars = XSTRING (string)->size; |
6810 | bytes = STRING_BYTES (XSTRING (string)); | |
6811 | if (encodep) | |
6812 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
6813 | else | |
6814 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
6815 | if (! norecord) | |
6816 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 6817 | |
df7492f9 KH |
6818 | if (coding.result != CODING_RESULT_SUCCESS) |
6819 | error ("Code conversion error: %d", coding.result); | |
4ed46869 | 6820 | |
df7492f9 KH |
6821 | return (BUFFERP (dst_object) |
6822 | ? make_number (coding.produced_char) | |
6823 | : coding.dst_object); | |
4ed46869 KH |
6824 | } |
6825 | ||
4031e2bf | 6826 | |
ecec61c1 | 6827 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 KH |
6828 | Do not set Vlast_coding_system_used. |
6829 | ||
6830 | This function is called only from macros DECODE_FILE and | |
6831 | ENCODE_FILE, thus we ignore character composition. */ | |
ecec61c1 KH |
6832 | |
6833 | Lisp_Object | |
6834 | code_convert_string_norecord (string, coding_system, encodep) | |
6835 | Lisp_Object string, coding_system; | |
6836 | int encodep; | |
6837 | { | |
0be8721c | 6838 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
df7492f9 | 6839 | } |
ecec61c1 | 6840 | |
ecec61c1 | 6841 | |
df7492f9 KH |
6842 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
6843 | 2, 4, 0, | |
6844 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
6845 | ||
6846 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
6847 | if the decoding operation is trivial. | |
ecec61c1 | 6848 | |
df7492f9 KH |
6849 | Optional fourth arg BUFFER non-nil meant that the decoded text is |
6850 | inserted in BUFFER instead of returned as a astring. In this case, | |
6851 | the return value is BUFFER. | |
ecec61c1 | 6852 | |
df7492f9 KH |
6853 | This function sets `last-coding-system-used' to the precise coding system |
6854 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
6855 | not fully specified. */) | |
6856 | (string, coding_system, nocopy, buffer) | |
6857 | Lisp_Object string, coding_system, nocopy, buffer; | |
6858 | { | |
6859 | return code_convert_string (string, coding_system, buffer, | |
6860 | 0, ! NILP (nocopy), 0); | |
6861 | } | |
6862 | ||
6863 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, | |
6864 | 2, 4, 0, | |
6865 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
6866 | ||
6867 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
6868 | itself if the encoding operation is trivial. | |
6869 | ||
6870 | Optional fourth arg BUFFER non-nil meant that the encoded text is | |
6871 | inserted in BUFFER instead of returned as a astring. In this case, | |
6872 | the return value is BUFFER. | |
6873 | ||
6874 | This function sets `last-coding-system-used' to the precise coding system | |
6875 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
6876 | not fully specified.) */) | |
6877 | (string, coding_system, nocopy, buffer) | |
6878 | Lisp_Object string, coding_system, nocopy, buffer; | |
6879 | { | |
6880 | return code_convert_string (string, coding_system, buffer, | |
6881 | nocopy, ! NILP (nocopy), 1); | |
ecec61c1 | 6882 | } |
df7492f9 | 6883 | |
3a73fa5d | 6884 | \f |
4ed46869 | 6885 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
6886 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
6887 | Return the corresponding character. */) | |
6888 | (code) | |
4ed46869 KH |
6889 | Lisp_Object code; |
6890 | { | |
df7492f9 KH |
6891 | Lisp_Object spec, attrs, val; |
6892 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
6893 | int c; | |
6894 | ||
6895 | CHECK_NATNUM (code); | |
6896 | c = XFASTINT (code); | |
6897 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
6898 | attrs = AREF (spec, 0); | |
4ed46869 | 6899 | |
df7492f9 KH |
6900 | if (ASCII_BYTE_P (c) |
6901 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
6902 | return code; | |
6903 | ||
6904 | val = CODING_ATTR_CHARSET_LIST (attrs); | |
6905 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
6906 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
6907 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
df7492f9 KH |
6908 | |
6909 | if (c <= 0x7F) | |
6910 | charset = charset_roman; | |
6911 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 6912 | { |
df7492f9 KH |
6913 | charset = charset_kana; |
6914 | c -= 0x80; | |
55ab7be3 KH |
6915 | } |
6916 | else | |
6917 | { | |
004068e4 | 6918 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
6919 | |
6920 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
6921 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
6922 | error ("Invalid code: %d", code); | |
6923 | SJIS_TO_JIS (c); | |
6924 | charset = charset_kanji; | |
55ab7be3 | 6925 | } |
df7492f9 KH |
6926 | c = DECODE_CHAR (charset, c); |
6927 | if (c < 0) | |
6928 | error ("Invalid code: %d", code); | |
6929 | return make_number (c); | |
4ed46869 KH |
6930 | } |
6931 | ||
df7492f9 | 6932 | |
4ed46869 | 6933 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
6934 | doc: /* Encode a Japanese character CHAR to shift_jis encoding. |
6935 | Return the corresponding code in SJIS. */) | |
6936 | (ch) | |
df7492f9 | 6937 | Lisp_Object ch; |
4ed46869 | 6938 | { |
df7492f9 KH |
6939 | Lisp_Object spec, attrs, charset_list; |
6940 | int c; | |
6941 | struct charset *charset; | |
6942 | unsigned code; | |
4ed46869 | 6943 | |
df7492f9 KH |
6944 | CHECK_CHARACTER (ch); |
6945 | c = XFASTINT (ch); | |
6946 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
6947 | attrs = AREF (spec, 0); | |
6948 | ||
6949 | if (ASCII_CHAR_P (c) | |
6950 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
6951 | return ch; | |
6952 | ||
6953 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
6954 | charset = char_charset (c, charset_list, &code); | |
6955 | if (code == CHARSET_INVALID_CODE (charset)) | |
6956 | error ("Can't encode by shift_jis encoding: %d", c); | |
6957 | JIS_TO_SJIS (code); | |
6958 | ||
6959 | return make_number (code); | |
4ed46869 KH |
6960 | } |
6961 | ||
6962 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
6963 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
6964 | Return the corresponding character. */) | |
6965 | (code) | |
4ed46869 KH |
6966 | Lisp_Object code; |
6967 | { | |
df7492f9 KH |
6968 | Lisp_Object spec, attrs, val; |
6969 | struct charset *charset_roman, *charset_big5, *charset; | |
6970 | int c; | |
4ed46869 | 6971 | |
df7492f9 KH |
6972 | CHECK_NATNUM (code); |
6973 | c = XFASTINT (code); | |
6974 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
6975 | attrs = AREF (spec, 0); | |
6976 | ||
6977 | if (ASCII_BYTE_P (c) | |
6978 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
6979 | return code; | |
6980 | ||
6981 | val = CODING_ATTR_CHARSET_LIST (attrs); | |
6982 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
6983 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
6984 | ||
6985 | if (c <= 0x7F) | |
6986 | charset = charset_roman; | |
c28a9453 KH |
6987 | else |
6988 | { | |
df7492f9 KH |
6989 | int b1 = c >> 8, b2 = c & 0x7F; |
6990 | if (b1 < 0xA1 || b1 > 0xFE | |
6991 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
6992 | error ("Invalid code: %d", code); | |
6993 | charset = charset_big5; | |
c28a9453 | 6994 | } |
df7492f9 KH |
6995 | c = DECODE_CHAR (charset, (unsigned )c); |
6996 | if (c < 0) | |
6997 | error ("Invalid code: %d", code); | |
6998 | return make_number (c); | |
4ed46869 KH |
6999 | } |
7000 | ||
7001 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
7002 | doc: /* Encode the Big5 character CHAR to BIG5 coding system. |
7003 | Return the corresponding character code in Big5. */) | |
7004 | (ch) | |
4ed46869 KH |
7005 | Lisp_Object ch; |
7006 | { | |
df7492f9 KH |
7007 | Lisp_Object spec, attrs, charset_list; |
7008 | struct charset *charset; | |
7009 | int c; | |
7010 | unsigned code; | |
7011 | ||
7012 | CHECK_CHARACTER (ch); | |
7013 | c = XFASTINT (ch); | |
7014 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
7015 | attrs = AREF (spec, 0); | |
7016 | if (ASCII_CHAR_P (c) | |
7017 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
7018 | return ch; | |
7019 | ||
7020 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
7021 | charset = char_charset (c, charset_list, &code); | |
7022 | if (code == CHARSET_INVALID_CODE (charset)) | |
7023 | error ("Can't encode by Big5 encoding: %d", c); | |
7024 | ||
7025 | return make_number (code); | |
4ed46869 | 7026 | } |
df7492f9 | 7027 | |
3a73fa5d | 7028 | \f |
1ba9e4ab KH |
7029 | DEFUN ("set-terminal-coding-system-internal", |
7030 | Fset_terminal_coding_system_internal, | |
48b0f3ae PJ |
7031 | Sset_terminal_coding_system_internal, 1, 1, 0, |
7032 | doc: /* Internal use only. */) | |
7033 | (coding_system) | |
b74e4686 | 7034 | Lisp_Object coding_system; |
4ed46869 | 7035 | { |
b7826503 | 7036 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
7037 | setup_coding_system (Fcheck_coding_system (coding_system), |
7038 | &terminal_coding); | |
7039 | ||
70c22245 | 7040 | /* We had better not send unsafe characters to terminal. */ |
df7492f9 KH |
7041 | terminal_coding.mode |= CODING_MODE_SAFE_ENCODING; |
7042 | /* Characer composition should be disabled. */ | |
7043 | terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
7044 | terminal_coding.src_multibyte = 1; |
7045 | terminal_coding.dst_multibyte = 0; | |
4ed46869 KH |
7046 | return Qnil; |
7047 | } | |
7048 | ||
c4825358 KH |
7049 | DEFUN ("set-safe-terminal-coding-system-internal", |
7050 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 7051 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 7052 | doc: /* Internal use only. */) |
48b0f3ae | 7053 | (coding_system) |
b74e4686 | 7054 | Lisp_Object coding_system; |
c4825358 | 7055 | { |
b7826503 | 7056 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
7057 | setup_coding_system (Fcheck_coding_system (coding_system), |
7058 | &safe_terminal_coding); | |
df7492f9 KH |
7059 | /* Characer composition should be disabled. */ |
7060 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
b73bfc1c KH |
7061 | safe_terminal_coding.src_multibyte = 1; |
7062 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
7063 | return Qnil; |
7064 | } | |
7065 | ||
4ed46869 KH |
7066 | DEFUN ("terminal-coding-system", |
7067 | Fterminal_coding_system, Sterminal_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
7068 | doc: /* Return coding system specified for terminal output. */) |
7069 | () | |
4ed46869 | 7070 | { |
df7492f9 | 7071 | return CODING_ID_NAME (terminal_coding.id); |
4ed46869 KH |
7072 | } |
7073 | ||
1ba9e4ab KH |
7074 | DEFUN ("set-keyboard-coding-system-internal", |
7075 | Fset_keyboard_coding_system_internal, | |
48b0f3ae PJ |
7076 | Sset_keyboard_coding_system_internal, 1, 1, 0, |
7077 | doc: /* Internal use only. */) | |
7078 | (coding_system) | |
4ed46869 KH |
7079 | Lisp_Object coding_system; |
7080 | { | |
b7826503 | 7081 | CHECK_SYMBOL (coding_system); |
df7492f9 KH |
7082 | setup_coding_system (Fcheck_coding_system (coding_system), |
7083 | &keyboard_coding); | |
7084 | /* Characer composition should be disabled. */ | |
7085 | keyboard_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
7086 | return Qnil; |
7087 | } | |
7088 | ||
7089 | DEFUN ("keyboard-coding-system", | |
7090 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 0, 0, | |
48b0f3ae PJ |
7091 | doc: /* Return coding system specified for decoding keyboard input. */) |
7092 | () | |
4ed46869 | 7093 | { |
df7492f9 | 7094 | return CODING_ID_NAME (keyboard_coding.id); |
4ed46869 KH |
7095 | } |
7096 | ||
7097 | \f | |
a5d301df KH |
7098 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
7099 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
7100 | doc: /* Choose a coding system for an operation based on the target name. |
7101 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
7102 | DECODING-SYSTEM is the coding system to use for decoding | |
7103 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
7104 | for encoding (in case OPERATION does encoding). | |
7105 | ||
7106 | The first argument OPERATION specifies an I/O primitive: | |
7107 | For file I/O, `insert-file-contents' or `write-region'. | |
7108 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
7109 | For network I/O, `open-network-stream'. | |
7110 | ||
7111 | The remaining arguments should be the same arguments that were passed | |
7112 | to the primitive. Depending on which primitive, one of those arguments | |
7113 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
7114 | whichever argument specifies the file name is TARGET. | |
7115 | ||
7116 | TARGET has a meaning which depends on OPERATION: | |
7117 | For file I/O, TARGET is a file name. | |
7118 | For process I/O, TARGET is a process name. | |
7119 | For network I/O, TARGET is a service name or a port number | |
7120 | ||
7121 | This function looks up what specified for TARGET in, | |
7122 | `file-coding-system-alist', `process-coding-system-alist', | |
7123 | or `network-coding-system-alist' depending on OPERATION. | |
7124 | They may specify a coding system, a cons of coding systems, | |
7125 | or a function symbol to call. | |
7126 | In the last case, we call the function with one argument, | |
7127 | which is a list of all the arguments given to this function. | |
7128 | ||
7129 | usage: (find-operation-coding-system OPERATION ARGUMENTS ...) */) | |
7130 | (nargs, args) | |
4ed46869 KH |
7131 | int nargs; |
7132 | Lisp_Object *args; | |
7133 | { | |
7134 | Lisp_Object operation, target_idx, target, val; | |
7135 | register Lisp_Object chain; | |
7136 | ||
7137 | if (nargs < 2) | |
7138 | error ("Too few arguments"); | |
7139 | operation = args[0]; | |
7140 | if (!SYMBOLP (operation) | |
7141 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
df7492f9 | 7142 | error ("Invalid first arguement"); |
4ed46869 KH |
7143 | if (nargs < 1 + XINT (target_idx)) |
7144 | error ("Too few arguments for operation: %s", | |
7145 | XSYMBOL (operation)->name->data); | |
7146 | target = args[XINT (target_idx) + 1]; | |
7147 | if (!(STRINGP (target) | |
7148 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) | |
df7492f9 | 7149 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
4ed46869 | 7150 | |
2e34157c RS |
7151 | chain = ((EQ (operation, Qinsert_file_contents) |
7152 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 7153 | ? Vfile_coding_system_alist |
2e34157c | 7154 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
7155 | ? Vnetwork_coding_system_alist |
7156 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
7157 | if (NILP (chain)) |
7158 | return Qnil; | |
7159 | ||
03699b14 | 7160 | for (; CONSP (chain); chain = XCDR (chain)) |
4ed46869 | 7161 | { |
f44d27ce | 7162 | Lisp_Object elt; |
4ed46869 | 7163 | |
df7492f9 | 7164 | elt = XCAR (chain); |
4ed46869 KH |
7165 | if (CONSP (elt) |
7166 | && ((STRINGP (target) | |
03699b14 KR |
7167 | && STRINGP (XCAR (elt)) |
7168 | && fast_string_match (XCAR (elt), target) >= 0) | |
7169 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
02ba4723 | 7170 | { |
03699b14 | 7171 | val = XCDR (elt); |
b19fd4c5 KH |
7172 | /* Here, if VAL is both a valid coding system and a valid |
7173 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
7174 | if (CONSP (val)) |
7175 | return val; | |
7176 | if (! SYMBOLP (val)) | |
7177 | return Qnil; | |
7178 | if (! NILP (Fcoding_system_p (val))) | |
7179 | return Fcons (val, val); | |
b19fd4c5 KH |
7180 | if (! NILP (Ffboundp (val))) |
7181 | { | |
7182 | val = call1 (val, Flist (nargs, args)); | |
7183 | if (CONSP (val)) | |
7184 | return val; | |
7185 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
7186 | return Fcons (val, val); | |
7187 | } | |
02ba4723 KH |
7188 | return Qnil; |
7189 | } | |
4ed46869 KH |
7190 | } |
7191 | return Qnil; | |
7192 | } | |
7193 | ||
df7492f9 KH |
7194 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
7195 | Sset_coding_system_priority, 1, MANY, 0, | |
da7db224 | 7196 | doc: /* Assign higher priority to the coding systems given as arguments. |
1fcd6c8b | 7197 | usage: (set-coding-system-priority CODING-SYSTEM ...) */) |
df7492f9 KH |
7198 | (nargs, args) |
7199 | int nargs; | |
7200 | Lisp_Object *args; | |
7201 | { | |
7202 | int i, j; | |
7203 | int changed[coding_category_max]; | |
7204 | enum coding_category priorities[coding_category_max]; | |
7205 | ||
7206 | bzero (changed, sizeof changed); | |
7207 | ||
7208 | for (i = j = 0; i < nargs; i++) | |
7209 | { | |
7210 | enum coding_category category; | |
7211 | Lisp_Object spec, attrs; | |
7212 | ||
7213 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); | |
7214 | attrs = AREF (spec, 0); | |
7215 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
7216 | if (changed[category]) | |
7217 | /* Ignore this coding system because a coding system of the | |
7218 | same category already had a higher priority. */ | |
7219 | continue; | |
7220 | changed[category] = 1; | |
7221 | priorities[j++] = category; | |
7222 | if (coding_categories[category].id >= 0 | |
7223 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
7224 | setup_coding_system (args[i], &coding_categories[category]); | |
7225 | } | |
7226 | ||
7227 | /* Now we have decided top J priorities. Reflect the order of the | |
7228 | original priorities to the remaining priorities. */ | |
7229 | ||
7230 | for (i = j, j = 0; i < coding_category_max; i++, j++) | |
7231 | { | |
7232 | while (j < coding_category_max | |
7233 | && changed[coding_priorities[j]]) | |
7234 | j++; | |
7235 | if (j == coding_category_max) | |
7236 | abort (); | |
7237 | priorities[i] = coding_priorities[j]; | |
7238 | } | |
7239 | ||
7240 | bcopy (priorities, coding_priorities, sizeof priorities); | |
7241 | return Qnil; | |
7242 | } | |
7243 | ||
7244 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, | |
7245 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 DL |
7246 | doc: /* Return a list of coding systems ordered by their priorities. |
7247 | HIGHESTP non-nil means just return the highest priority one. */) | |
df7492f9 KH |
7248 | (highestp) |
7249 | Lisp_Object highestp; | |
d46c5b12 KH |
7250 | { |
7251 | int i; | |
df7492f9 | 7252 | Lisp_Object val; |
d46c5b12 | 7253 | |
df7492f9 | 7254 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 7255 | { |
df7492f9 KH |
7256 | enum coding_category category = coding_priorities[i]; |
7257 | int id = coding_categories[category].id; | |
7258 | Lisp_Object attrs; | |
7259 | ||
7260 | if (id < 0) | |
7261 | continue; | |
7262 | attrs = CODING_ID_ATTRS (id); | |
7263 | if (! NILP (highestp)) | |
7264 | return CODING_ATTR_BASE_NAME (attrs); | |
7265 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
7266 | } | |
7267 | return Fnreverse (val); | |
7268 | } | |
7269 | ||
f0064e1f DL |
7270 | static char *suffixes[] = { "-unix", "-dos", "-mac" }; |
7271 | ||
df7492f9 KH |
7272 | static Lisp_Object |
7273 | make_subsidiaries (base) | |
7274 | Lisp_Object base; | |
7275 | { | |
7276 | Lisp_Object subsidiaries; | |
df7492f9 KH |
7277 | int base_name_len = STRING_BYTES (XSYMBOL (base)->name); |
7278 | char *buf = (char *) alloca (base_name_len + 6); | |
7279 | int i; | |
7280 | ||
7281 | bcopy (XSYMBOL (base)->name->data, buf, base_name_len); | |
7282 | subsidiaries = Fmake_vector (make_number (3), Qnil); | |
7283 | for (i = 0; i < 3; i++) | |
7284 | { | |
7285 | bcopy (suffixes[i], buf + base_name_len, strlen (suffixes[i]) + 1); | |
7286 | ASET (subsidiaries, i, intern (buf)); | |
7287 | } | |
7288 | return subsidiaries; | |
7289 | } | |
7290 | ||
7291 | ||
7292 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, | |
7293 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
7294 | doc: /* For internal use only. |
7295 | usage: (define-coding-system-internal ...) */) | |
df7492f9 KH |
7296 | (nargs, args) |
7297 | int nargs; | |
7298 | Lisp_Object *args; | |
7299 | { | |
7300 | Lisp_Object name; | |
7301 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
7302 | Lisp_Object attrs; /* Vector of attributes. */ | |
7303 | Lisp_Object eol_type; | |
7304 | Lisp_Object aliases; | |
7305 | Lisp_Object coding_type, charset_list, safe_charsets; | |
7306 | enum coding_category category; | |
7307 | Lisp_Object tail, val; | |
7308 | int max_charset_id = 0; | |
7309 | int i; | |
7310 | ||
7311 | if (nargs < coding_arg_max) | |
7312 | goto short_args; | |
7313 | ||
7314 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); | |
7315 | ||
7316 | name = args[coding_arg_name]; | |
7317 | CHECK_SYMBOL (name); | |
7318 | CODING_ATTR_BASE_NAME (attrs) = name; | |
7319 | ||
7320 | val = args[coding_arg_mnemonic]; | |
7321 | if (! STRINGP (val)) | |
7322 | CHECK_CHARACTER (val); | |
7323 | CODING_ATTR_MNEMONIC (attrs) = val; | |
7324 | ||
7325 | coding_type = args[coding_arg_coding_type]; | |
7326 | CHECK_SYMBOL (coding_type); | |
7327 | CODING_ATTR_TYPE (attrs) = coding_type; | |
7328 | ||
7329 | charset_list = args[coding_arg_charset_list]; | |
7330 | if (SYMBOLP (charset_list)) | |
7331 | { | |
7332 | if (EQ (charset_list, Qiso_2022)) | |
7333 | { | |
7334 | if (! EQ (coding_type, Qiso_2022)) | |
7335 | error ("Invalid charset-list"); | |
7336 | charset_list = Viso_2022_charset_list; | |
7337 | } | |
7338 | else if (EQ (charset_list, Qemacs_mule)) | |
7339 | { | |
7340 | if (! EQ (coding_type, Qemacs_mule)) | |
7341 | error ("Invalid charset-list"); | |
7342 | charset_list = Vemacs_mule_charset_list; | |
7343 | } | |
7344 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
7345 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
7346 | max_charset_id = XFASTINT (XCAR (tail)); | |
7347 | } | |
7348 | else | |
7349 | { | |
7350 | charset_list = Fcopy_sequence (charset_list); | |
7351 | for (tail = charset_list; !NILP (tail); tail = Fcdr (tail)) | |
7352 | { | |
7353 | struct charset *charset; | |
7354 | ||
7355 | val = Fcar (tail); | |
7356 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
7357 | if (EQ (coding_type, Qiso_2022) | |
7358 | ? CHARSET_ISO_FINAL (charset) < 0 | |
7359 | : EQ (coding_type, Qemacs_mule) | |
7360 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
7361 | : 0) | |
7362 | error ("Can't handle charset `%s'", | |
7363 | XSYMBOL (CHARSET_NAME (charset))->name->data); | |
7364 | ||
7365 | XCAR (tail) = make_number (charset->id); | |
7366 | if (max_charset_id < charset->id) | |
7367 | max_charset_id = charset->id; | |
7368 | } | |
7369 | } | |
7370 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; | |
7371 | ||
7372 | safe_charsets = Fmake_string (make_number (max_charset_id + 1), | |
7373 | make_number (255)); | |
7374 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
7375 | XSTRING (safe_charsets)->data[XFASTINT (XCAR (tail))] = 0; | |
7376 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; | |
7377 | ||
7378 | val = args[coding_arg_decode_translation_table]; | |
7379 | if (! NILP (val)) | |
7380 | CHECK_CHAR_TABLE (val); | |
7381 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
7382 | ||
7383 | val = args[coding_arg_encode_translation_table]; | |
7384 | if (! NILP (val)) | |
7385 | CHECK_CHAR_TABLE (val); | |
7386 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
7387 | ||
7388 | val = args[coding_arg_post_read_conversion]; | |
7389 | CHECK_SYMBOL (val); | |
7390 | CODING_ATTR_POST_READ (attrs) = val; | |
7391 | ||
7392 | val = args[coding_arg_pre_write_conversion]; | |
7393 | CHECK_SYMBOL (val); | |
7394 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
7395 | ||
7396 | val = args[coding_arg_default_char]; | |
7397 | if (NILP (val)) | |
7398 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
7399 | else | |
7400 | { | |
7401 | CHECK_CHARACTER (val); | |
7402 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
7403 | } | |
7404 | ||
7405 | val = args[coding_arg_plist]; | |
7406 | CHECK_LIST (val); | |
7407 | CODING_ATTR_PLIST (attrs) = val; | |
7408 | ||
7409 | if (EQ (coding_type, Qcharset)) | |
7410 | { | |
c7c66a95 KH |
7411 | /* Generate a lisp vector of 256 elements. Each element is nil, |
7412 | integer, or a list of charset IDs. | |
7413 | ||
7414 | If Nth element is nil, the byte code N is invalid in this | |
7415 | coding system. | |
7416 | ||
7417 | If Nth element is a number NUM, N is the first byte of a | |
7418 | charset whose ID is NUM. | |
7419 | ||
7420 | If Nth element is a list of charset IDs, N is the first byte | |
7421 | of one of them. The list is sorted by dimensions of the | |
7422 | charsets. A charset of smaller dimension comes firtst. | |
7423 | */ | |
df7492f9 KH |
7424 | val = Fmake_vector (make_number (256), Qnil); |
7425 | ||
7426 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
7427 | { | |
c7c66a95 KH |
7428 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
7429 | int dim = CHARSET_DIMENSION (charset); | |
7430 | int idx = (dim - 1) * 4; | |
7431 | ||
15d143f7 KH |
7432 | for (i = charset->code_space[idx]; |
7433 | i <= charset->code_space[idx + 1]; i++) | |
7434 | { | |
c7c66a95 KH |
7435 | Lisp_Object tmp, tmp2; |
7436 | int dim2; | |
7437 | ||
7438 | tmp = AREF (val, i); | |
7439 | if (NILP (tmp)) | |
7440 | tmp = XCAR (tail); | |
7441 | else if (NUMBERP (tmp)) | |
7442 | { | |
7443 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
7444 | if (dim < dim2) | |
c7c66a95 | 7445 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
7446 | else |
7447 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 7448 | } |
15d143f7 | 7449 | else |
c7c66a95 KH |
7450 | { |
7451 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
7452 | { | |
7453 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
7454 | if (dim < dim2) | |
7455 | break; | |
7456 | } | |
7457 | if (NILP (tmp2)) | |
7458 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
7459 | else | |
7460 | { | |
7461 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
7462 | XSETCAR (tmp2, XCAR (tail)); | |
7463 | } | |
7464 | } | |
7465 | ASET (val, i, tmp); | |
15d143f7 | 7466 | } |
df7492f9 KH |
7467 | } |
7468 | ASET (attrs, coding_attr_charset_valids, val); | |
7469 | category = coding_category_charset; | |
7470 | } | |
7471 | else if (EQ (coding_type, Qccl)) | |
7472 | { | |
7473 | Lisp_Object valids; | |
7474 | ||
7475 | if (nargs < coding_arg_ccl_max) | |
7476 | goto short_args; | |
7477 | ||
7478 | val = args[coding_arg_ccl_decoder]; | |
7479 | CHECK_CCL_PROGRAM (val); | |
7480 | if (VECTORP (val)) | |
7481 | val = Fcopy_sequence (val); | |
7482 | ASET (attrs, coding_attr_ccl_decoder, val); | |
7483 | ||
7484 | val = args[coding_arg_ccl_encoder]; | |
7485 | CHECK_CCL_PROGRAM (val); | |
7486 | if (VECTORP (val)) | |
7487 | val = Fcopy_sequence (val); | |
7488 | ASET (attrs, coding_attr_ccl_encoder, val); | |
7489 | ||
7490 | val = args[coding_arg_ccl_valids]; | |
7491 | valids = Fmake_string (make_number (256), make_number (0)); | |
7492 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
7493 | { | |
7494 | val = Fcar (tail); | |
7495 | if (INTEGERP (val)) | |
7496 | ASET (valids, XINT (val), 1); | |
7497 | else | |
7498 | { | |
7499 | int from, to; | |
7500 | ||
7501 | CHECK_CONS (val); | |
7502 | CHECK_NUMBER (XCAR (val)); | |
7503 | CHECK_NUMBER (XCDR (val)); | |
7504 | from = XINT (XCAR (val)); | |
7505 | to = XINT (XCDR (val)); | |
7506 | for (i = from; i <= to; i++) | |
7507 | ASET (valids, i, 1); | |
7508 | } | |
7509 | } | |
7510 | ASET (attrs, coding_attr_ccl_valids, valids); | |
7511 | ||
7512 | category = coding_category_ccl; | |
7513 | } | |
7514 | else if (EQ (coding_type, Qutf_16)) | |
7515 | { | |
7516 | Lisp_Object bom, endian; | |
7517 | ||
7518 | if (nargs < coding_arg_utf16_max) | |
7519 | goto short_args; | |
7520 | ||
7521 | bom = args[coding_arg_utf16_bom]; | |
7522 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
7523 | { | |
7524 | CHECK_CONS (bom); | |
7525 | CHECK_CODING_SYSTEM (XCAR (bom)); | |
7526 | CHECK_CODING_SYSTEM (XCDR (bom)); | |
7527 | } | |
7528 | ASET (attrs, coding_attr_utf_16_bom, bom); | |
7529 | ||
7530 | endian = args[coding_arg_utf16_endian]; | |
7531 | ASET (attrs, coding_attr_utf_16_endian, endian); | |
7532 | ||
7533 | category = (CONSP (bom) | |
7534 | ? coding_category_utf_16_auto | |
7535 | : NILP (bom) | |
7536 | ? (NILP (endian) | |
7537 | ? coding_category_utf_16_be_nosig | |
7538 | : coding_category_utf_16_le_nosig) | |
7539 | : (NILP (endian) | |
7540 | ? coding_category_utf_16_be | |
7541 | : coding_category_utf_16_le)); | |
7542 | } | |
7543 | else if (EQ (coding_type, Qiso_2022)) | |
7544 | { | |
7545 | Lisp_Object initial, reg_usage, request, flags; | |
0be8721c | 7546 | int i, id; |
1397dc18 | 7547 | |
df7492f9 KH |
7548 | if (nargs < coding_arg_iso2022_max) |
7549 | goto short_args; | |
7550 | ||
7551 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
7552 | CHECK_VECTOR (initial); | |
7553 | for (i = 0; i < 4; i++) | |
7554 | { | |
7555 | val = Faref (initial, make_number (i)); | |
7556 | if (! NILP (val)) | |
7557 | { | |
7558 | CHECK_CHARSET_GET_ID (val, id); | |
7559 | ASET (initial, i, make_number (id)); | |
7560 | } | |
7561 | else | |
7562 | ASET (initial, i, make_number (-1)); | |
7563 | } | |
7564 | ||
7565 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
7566 | CHECK_CONS (reg_usage); | |
7567 | CHECK_NATNUM (XCAR (reg_usage)); | |
7568 | CHECK_NATNUM (XCDR (reg_usage)); | |
7569 | ||
7570 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
7571 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 7572 | { |
df7492f9 KH |
7573 | int id; |
7574 | ||
7575 | val = Fcar (tail); | |
7576 | CHECK_CONS (val); | |
7577 | CHECK_CHARSET_GET_ID (XCAR (val), id); | |
7578 | CHECK_NATNUM (XCDR (val)); | |
7579 | if (XINT (XCDR (val)) >= 4) | |
7580 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
7581 | XCAR (val) = make_number (id); | |
1397dc18 | 7582 | } |
df7492f9 KH |
7583 | |
7584 | flags = args[coding_arg_iso2022_flags]; | |
7585 | CHECK_NATNUM (flags); | |
7586 | i = XINT (flags); | |
7587 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
7588 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
7589 | ||
7590 | ASET (attrs, coding_attr_iso_initial, initial); | |
7591 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
7592 | ASET (attrs, coding_attr_iso_request, request); | |
7593 | ASET (attrs, coding_attr_iso_flags, flags); | |
7594 | setup_iso_safe_charsets (attrs); | |
7595 | ||
7596 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
7597 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
7598 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
7599 | ? coding_category_iso_7_else | |
7600 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
7601 | ? coding_category_iso_7 | |
7602 | : coding_category_iso_7_tight); | |
7603 | else | |
7604 | { | |
7605 | int id = XINT (AREF (initial, 1)); | |
7606 | ||
7607 | category = (((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
7608 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
7609 | || EQ (args[coding_arg_charset_list], Qiso_2022) | |
7610 | || id < 0) | |
7611 | ? coding_category_iso_8_else | |
7612 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
7613 | ? coding_category_iso_8_1 | |
7614 | : coding_category_iso_8_2); | |
7615 | } | |
7616 | } | |
7617 | else if (EQ (coding_type, Qemacs_mule)) | |
7618 | { | |
7619 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) | |
7620 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
7621 | ||
7622 | category = coding_category_emacs_mule; | |
7623 | } | |
7624 | else if (EQ (coding_type, Qshift_jis)) | |
7625 | { | |
7626 | ||
7627 | struct charset *charset; | |
7628 | ||
7629 | if (XINT (Flength (charset_list)) != 3) | |
7630 | error ("There should be just three charsets"); | |
7631 | ||
7632 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
7633 | if (CHARSET_DIMENSION (charset) != 1) | |
7634 | error ("Dimension of charset %s is not one", | |
7635 | XSYMBOL (CHARSET_NAME (charset))->name->data); | |
7636 | ||
7637 | charset_list = XCDR (charset_list); | |
7638 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
7639 | if (CHARSET_DIMENSION (charset) != 1) | |
7640 | error ("Dimension of charset %s is not one", | |
7641 | XSYMBOL (CHARSET_NAME (charset))->name->data); | |
7642 | ||
7643 | charset_list = XCDR (charset_list); | |
7644 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
7645 | if (CHARSET_DIMENSION (charset) != 2) | |
7646 | error ("Dimension of charset %s is not two", | |
7647 | XSYMBOL (CHARSET_NAME (charset))->name->data); | |
7648 | ||
7649 | category = coding_category_sjis; | |
7650 | Vsjis_coding_system = name; | |
7651 | } | |
7652 | else if (EQ (coding_type, Qbig5)) | |
7653 | { | |
7654 | struct charset *charset; | |
7655 | ||
7656 | if (XINT (Flength (charset_list)) != 2) | |
7657 | error ("There should be just two charsets"); | |
7658 | ||
7659 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
7660 | if (CHARSET_DIMENSION (charset) != 1) | |
7661 | error ("Dimension of charset %s is not one", | |
7662 | XSYMBOL (CHARSET_NAME (charset))->name->data); | |
7663 | ||
7664 | charset_list = XCDR (charset_list); | |
7665 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
7666 | if (CHARSET_DIMENSION (charset) != 2) | |
7667 | error ("Dimension of charset %s is not two", | |
7668 | XSYMBOL (CHARSET_NAME (charset))->name->data); | |
7669 | ||
7670 | category = coding_category_big5; | |
7671 | Vbig5_coding_system = name; | |
7672 | } | |
7673 | else if (EQ (coding_type, Qraw_text)) | |
7674 | category = coding_category_raw_text; | |
7675 | else if (EQ (coding_type, Qutf_8)) | |
7676 | category = coding_category_utf_8; | |
7677 | else if (EQ (coding_type, Qundecided)) | |
7678 | category = coding_category_undecided; | |
7679 | else | |
7680 | error ("Invalid coding system type: %s", | |
7681 | XSYMBOL (coding_type)->name->data); | |
7682 | ||
7683 | CODING_ATTR_CATEGORY (attrs) = make_number (category); | |
7684 | ||
7685 | eol_type = args[coding_arg_eol_type]; | |
7686 | if (! NILP (eol_type) | |
7687 | && ! EQ (eol_type, Qunix) | |
7688 | && ! EQ (eol_type, Qdos) | |
7689 | && ! EQ (eol_type, Qmac)) | |
7690 | error ("Invalid eol-type"); | |
7691 | ||
7692 | aliases = Fcons (name, Qnil); | |
7693 | ||
7694 | if (NILP (eol_type)) | |
7695 | { | |
7696 | eol_type = make_subsidiaries (name); | |
7697 | for (i = 0; i < 3; i++) | |
1397dc18 | 7698 | { |
df7492f9 KH |
7699 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
7700 | ||
7701 | this_name = AREF (eol_type, i); | |
7702 | this_aliases = Fcons (this_name, Qnil); | |
7703 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
7704 | this_spec = Fmake_vector (make_number (3), attrs); | |
7705 | ASET (this_spec, 1, this_aliases); | |
7706 | ASET (this_spec, 2, this_eol_type); | |
7707 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
7708 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
7709 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
7710 | Vcoding_system_alist); | |
1397dc18 | 7711 | } |
d46c5b12 | 7712 | } |
1397dc18 | 7713 | |
df7492f9 KH |
7714 | spec_vec = Fmake_vector (make_number (3), attrs); |
7715 | ASET (spec_vec, 1, aliases); | |
7716 | ASET (spec_vec, 2, eol_type); | |
7717 | ||
7718 | Fputhash (name, spec_vec, Vcoding_system_hash_table); | |
7719 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
7720 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
7721 | Vcoding_system_alist); | |
7722 | ||
7723 | { | |
7724 | int id = coding_categories[category].id; | |
7725 | ||
7726 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) | |
7727 | setup_coding_system (name, &coding_categories[category]); | |
7728 | } | |
7729 | ||
d46c5b12 | 7730 | return Qnil; |
df7492f9 KH |
7731 | |
7732 | short_args: | |
7733 | return Fsignal (Qwrong_number_of_arguments, | |
7734 | Fcons (intern ("define-coding-system-internal"), | |
7735 | make_number (nargs))); | |
d46c5b12 KH |
7736 | } |
7737 | ||
da7db224 DL |
7738 | /* Fixme: should this record the alias relationships for |
7739 | diagnostics? */ | |
df7492f9 KH |
7740 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
7741 | Sdefine_coding_system_alias, 2, 2, 0, | |
7742 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
7743 | (alias, coding_system) | |
7744 | Lisp_Object alias, coding_system; | |
66cfb530 | 7745 | { |
df7492f9 | 7746 | Lisp_Object spec, aliases, eol_type; |
84d60297 | 7747 | |
df7492f9 KH |
7748 | CHECK_SYMBOL (alias); |
7749 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
7750 | aliases = AREF (spec, 1); | |
7751 | while (!NILP (XCDR (aliases))) | |
7752 | aliases = XCDR (aliases); | |
7753 | XCDR (aliases) = Fcons (alias, Qnil); | |
66cfb530 | 7754 | |
df7492f9 KH |
7755 | eol_type = AREF (spec, 2); |
7756 | if (VECTORP (eol_type)) | |
66cfb530 | 7757 | { |
df7492f9 KH |
7758 | Lisp_Object subsidiaries; |
7759 | int i; | |
7760 | ||
7761 | subsidiaries = make_subsidiaries (alias); | |
7762 | for (i = 0; i < 3; i++) | |
7763 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
7764 | AREF (eol_type, i)); | |
7765 | ||
7766 | ASET (spec, 2, subsidiaries); | |
66cfb530 | 7767 | } |
df7492f9 KH |
7768 | |
7769 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
5bad0796 DL |
7770 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), |
7771 | Vcoding_system_alist); | |
66cfb530 KH |
7772 | |
7773 | return Qnil; | |
7774 | } | |
7775 | ||
df7492f9 KH |
7776 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
7777 | 1, 1, 0, | |
7778 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 7779 | Any alias or subsidiary coding system is not a base coding system. */) |
df7492f9 KH |
7780 | (coding_system) |
7781 | Lisp_Object coding_system; | |
7782 | { | |
7783 | Lisp_Object spec, attrs; | |
7784 | ||
7785 | if (NILP (coding_system)) | |
7786 | return (Qno_conversion); | |
7787 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
7788 | attrs = AREF (spec, 0); | |
7789 | return CODING_ATTR_BASE_NAME (attrs); | |
7790 | } | |
7791 | ||
7792 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, | |
7793 | 1, 1, 0, | |
7794 | doc: "Return the property list of CODING-SYSTEM.") | |
7795 | (coding_system) | |
7796 | Lisp_Object coding_system; | |
7797 | { | |
7798 | Lisp_Object spec, attrs; | |
7799 | ||
7800 | if (NILP (coding_system)) | |
7801 | coding_system = Qno_conversion; | |
7802 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
7803 | attrs = AREF (spec, 0); | |
7804 | return CODING_ATTR_PLIST (attrs); | |
7805 | } | |
7806 | ||
7807 | ||
7808 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
7809 | 1, 1, 0, | |
da7db224 | 7810 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
df7492f9 KH |
7811 | (coding_system) |
7812 | Lisp_Object coding_system; | |
7813 | { | |
7814 | Lisp_Object spec; | |
7815 | ||
7816 | if (NILP (coding_system)) | |
7817 | coding_system = Qno_conversion; | |
7818 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 7819 | return AREF (spec, 1); |
df7492f9 KH |
7820 | } |
7821 | ||
7822 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, | |
7823 | Scoding_system_eol_type, 1, 1, 0, | |
7824 | doc: /* Return eol-type of CODING-SYSTEM. | |
7825 | An eol-type is integer 0, 1, 2, or a vector of coding systems. | |
7826 | ||
7827 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, | |
7828 | and CR respectively. | |
7829 | ||
7830 | A vector value indicates that a format of end-of-line should be | |
7831 | detected automatically. Nth element of the vector is the subsidiary | |
7832 | coding system whose eol-type is N. */) | |
7833 | (coding_system) | |
7834 | Lisp_Object coding_system; | |
7835 | { | |
7836 | Lisp_Object spec, eol_type; | |
7837 | int n; | |
7838 | ||
7839 | if (NILP (coding_system)) | |
7840 | coding_system = Qno_conversion; | |
7841 | if (! CODING_SYSTEM_P (coding_system)) | |
7842 | return Qnil; | |
7843 | spec = CODING_SYSTEM_SPEC (coding_system); | |
7844 | eol_type = AREF (spec, 2); | |
7845 | if (VECTORP (eol_type)) | |
7846 | return Fcopy_sequence (eol_type); | |
7847 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
7848 | return make_number (n); | |
7849 | } | |
7850 | ||
4ed46869 KH |
7851 | #endif /* emacs */ |
7852 | ||
7853 | \f | |
1397dc18 | 7854 | /*** 9. Post-amble ***/ |
4ed46869 | 7855 | |
dfcf069d | 7856 | void |
4ed46869 KH |
7857 | init_coding_once () |
7858 | { | |
7859 | int i; | |
7860 | ||
df7492f9 KH |
7861 | for (i = 0; i < coding_category_max; i++) |
7862 | { | |
7863 | coding_categories[i].id = -1; | |
7864 | coding_priorities[i] = i; | |
7865 | } | |
4ed46869 KH |
7866 | |
7867 | /* ISO2022 specific initialize routine. */ | |
7868 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 7869 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
7870 | for (i = 0x21; i < 0x7F; i++) |
7871 | iso_code_class[i] = ISO_graphic_plane_0; | |
7872 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 7873 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
7874 | for (i = 0xA1; i < 0xFF; i++) |
7875 | iso_code_class[i] = ISO_graphic_plane_1; | |
7876 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
7877 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
7878 | iso_code_class[ISO_CODE_CR] = ISO_carriage_return; | |
7879 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; | |
7880 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
7881 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
7882 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
7883 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
7884 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
7885 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
7886 | ||
b843d1ae | 7887 | inhibit_pre_post_conversion = 0; |
df7492f9 KH |
7888 | |
7889 | for (i = 0; i < 256; i++) | |
7890 | { | |
7891 | emacs_mule_bytes[i] = 1; | |
7892 | } | |
781d7a48 KH |
7893 | emacs_mule_bytes[LEADING_CODE_PRIVATE_11] = 3; |
7894 | emacs_mule_bytes[LEADING_CODE_PRIVATE_12] = 3; | |
7895 | emacs_mule_bytes[LEADING_CODE_PRIVATE_21] = 4; | |
7896 | emacs_mule_bytes[LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
7897 | } |
7898 | ||
7899 | #ifdef emacs | |
7900 | ||
dfcf069d | 7901 | void |
e0e989f6 KH |
7902 | syms_of_coding () |
7903 | { | |
df7492f9 KH |
7904 | staticpro (&Vcoding_system_hash_table); |
7905 | Vcoding_system_hash_table = Fmakehash (Qeq); | |
7906 | ||
7907 | staticpro (&Vsjis_coding_system); | |
7908 | Vsjis_coding_system = Qnil; | |
7909 | ||
7910 | staticpro (&Vbig5_coding_system); | |
7911 | Vbig5_coding_system = Qnil; | |
7912 | ||
7913 | staticpro (&Vcode_conversion_work_buf_list); | |
7914 | Vcode_conversion_work_buf_list = Qnil; | |
e0e989f6 | 7915 | |
df7492f9 KH |
7916 | staticpro (&Vcode_conversion_reused_work_buf); |
7917 | Vcode_conversion_reused_work_buf = Qnil; | |
7918 | ||
7919 | DEFSYM (Qcharset, "charset"); | |
7920 | DEFSYM (Qtarget_idx, "target-idx"); | |
7921 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
7922 | Fset (Qcoding_system_history, Qnil); |
7923 | ||
9ce27fde | 7924 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 7925 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 7926 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
7927 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
7928 | ||
df7492f9 | 7929 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 7930 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
7931 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
7932 | ||
df7492f9 | 7933 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 7934 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
7935 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
7936 | ||
df7492f9 | 7937 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 7938 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
7939 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
7940 | ||
df7492f9 | 7941 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 7942 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
7943 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
7944 | ||
df7492f9 KH |
7945 | DEFSYM (Qcoding_system, "coding-system"); |
7946 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 7947 | |
df7492f9 KH |
7948 | DEFSYM (Qeol_type, "eol-type"); |
7949 | DEFSYM (Qunix, "unix"); | |
7950 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 7951 | |
df7492f9 KH |
7952 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
7953 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
7954 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
7955 | DEFSYM (Qdefault_char, "default-char"); | |
7956 | DEFSYM (Qundecided, "undecided"); | |
7957 | DEFSYM (Qno_conversion, "no-conversion"); | |
7958 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 7959 | |
df7492f9 | 7960 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 7961 | |
df7492f9 | 7962 | DEFSYM (Qutf_8, "utf-8"); |
27901516 | 7963 | |
df7492f9 KH |
7964 | DEFSYM (Qutf_16, "utf-16"); |
7965 | DEFSYM (Qutf_16_be, "utf-16-be"); | |
7966 | DEFSYM (Qutf_16_be_nosig, "utf-16-be-nosig"); | |
7967 | DEFSYM (Qutf_16_le, "utf-16-l3"); | |
7968 | DEFSYM (Qutf_16_le_nosig, "utf-16-le-nosig"); | |
7969 | DEFSYM (Qsignature, "signature"); | |
7970 | DEFSYM (Qendian, "endian"); | |
7971 | DEFSYM (Qbig, "big"); | |
7972 | DEFSYM (Qlittle, "little"); | |
27901516 | 7973 | |
df7492f9 KH |
7974 | DEFSYM (Qshift_jis, "shift-jis"); |
7975 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 7976 | |
df7492f9 | 7977 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 7978 | |
df7492f9 | 7979 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 KH |
7980 | Fput (Qcoding_system_error, Qerror_conditions, |
7981 | Fcons (Qcoding_system_error, Fcons (Qerror, Qnil))); | |
7982 | Fput (Qcoding_system_error, Qerror_message, | |
9ce27fde | 7983 | build_string ("Invalid coding system")); |
4ed46869 | 7984 | |
df7492f9 KH |
7985 | /* Intern this now in case it isn't already done. |
7986 | Setting this variable twice is harmless. | |
7987 | But don't staticpro it here--that is done in alloc.c. */ | |
7988 | Qchar_table_extra_slots = intern ("char-table-extra-slots"); | |
4ed46869 | 7989 | |
df7492f9 | 7990 | DEFSYM (Qtranslation_table, "translation-table"); |
1397dc18 | 7991 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (1)); |
df7492f9 KH |
7992 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
7993 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
7994 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
bdd9fb48 | 7995 | |
df7492f9 | 7996 | DEFSYM (Qvalid_codes, "valid-codes"); |
05e6f5dc | 7997 | |
df7492f9 | 7998 | DEFSYM (Qemacs_mule, "emacs-mule"); |
05e6f5dc | 7999 | |
df7492f9 KH |
8000 | Vcoding_category_table |
8001 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
8002 | staticpro (&Vcoding_category_table); | |
8003 | /* Followings are target of code detection. */ | |
8004 | ASET (Vcoding_category_table, coding_category_iso_7, | |
8005 | intern ("coding-category-iso-7")); | |
8006 | ASET (Vcoding_category_table, coding_category_iso_7_tight, | |
8007 | intern ("coding-category-iso-7-tight")); | |
8008 | ASET (Vcoding_category_table, coding_category_iso_8_1, | |
8009 | intern ("coding-category-iso-8-1")); | |
8010 | ASET (Vcoding_category_table, coding_category_iso_8_2, | |
8011 | intern ("coding-category-iso-8-2")); | |
8012 | ASET (Vcoding_category_table, coding_category_iso_7_else, | |
8013 | intern ("coding-category-iso-7-else")); | |
8014 | ASET (Vcoding_category_table, coding_category_iso_8_else, | |
8015 | intern ("coding-category-iso-8-else")); | |
8016 | ASET (Vcoding_category_table, coding_category_utf_8, | |
8017 | intern ("coding-category-utf-8")); | |
8018 | ASET (Vcoding_category_table, coding_category_utf_16_be, | |
8019 | intern ("coding-category-utf-16-be")); | |
8020 | ASET (Vcoding_category_table, coding_category_utf_16_le, | |
8021 | intern ("coding-category-utf-16-le")); | |
8022 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, | |
8023 | intern ("coding-category-utf-16-be-nosig")); | |
8024 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, | |
8025 | intern ("coding-category-utf-16-le-nosig")); | |
8026 | ASET (Vcoding_category_table, coding_category_charset, | |
8027 | intern ("coding-category-charset")); | |
8028 | ASET (Vcoding_category_table, coding_category_sjis, | |
8029 | intern ("coding-category-sjis")); | |
8030 | ASET (Vcoding_category_table, coding_category_big5, | |
8031 | intern ("coding-category-big5")); | |
8032 | ASET (Vcoding_category_table, coding_category_ccl, | |
8033 | intern ("coding-category-ccl")); | |
8034 | ASET (Vcoding_category_table, coding_category_emacs_mule, | |
8035 | intern ("coding-category-emacs-mule")); | |
8036 | /* Followings are NOT target of code detection. */ | |
8037 | ASET (Vcoding_category_table, coding_category_raw_text, | |
8038 | intern ("coding-category-raw-text")); | |
8039 | ASET (Vcoding_category_table, coding_category_undecided, | |
8040 | intern ("coding-category-undecided")); | |
70c22245 | 8041 | |
4ed46869 KH |
8042 | defsubr (&Scoding_system_p); |
8043 | defsubr (&Sread_coding_system); | |
8044 | defsubr (&Sread_non_nil_coding_system); | |
8045 | defsubr (&Scheck_coding_system); | |
8046 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 8047 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 8048 | defsubr (&Sfind_coding_systems_region_internal); |
df7492f9 | 8049 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
8050 | defsubr (&Sdecode_coding_region); |
8051 | defsubr (&Sencode_coding_region); | |
8052 | defsubr (&Sdecode_coding_string); | |
8053 | defsubr (&Sencode_coding_string); | |
8054 | defsubr (&Sdecode_sjis_char); | |
8055 | defsubr (&Sencode_sjis_char); | |
8056 | defsubr (&Sdecode_big5_char); | |
8057 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 8058 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 8059 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 8060 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 8061 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 8062 | defsubr (&Skeyboard_coding_system); |
a5d301df | 8063 | defsubr (&Sfind_operation_coding_system); |
df7492f9 KH |
8064 | defsubr (&Sset_coding_system_priority); |
8065 | defsubr (&Sdefine_coding_system_internal); | |
8066 | defsubr (&Sdefine_coding_system_alias); | |
8067 | defsubr (&Scoding_system_base); | |
8068 | defsubr (&Scoding_system_plist); | |
8069 | defsubr (&Scoding_system_aliases); | |
8070 | defsubr (&Scoding_system_eol_type); | |
8071 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 8072 | |
4608c386 | 8073 | DEFVAR_LISP ("coding-system-list", &Vcoding_system_list, |
48b0f3ae PJ |
8074 | doc: /* List of coding systems. |
8075 | ||
8076 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 8077 | updated by the functions `define-coding-system' and |
48b0f3ae | 8078 | `define-coding-system-alias'. */); |
4608c386 KH |
8079 | Vcoding_system_list = Qnil; |
8080 | ||
8081 | DEFVAR_LISP ("coding-system-alist", &Vcoding_system_alist, | |
48b0f3ae PJ |
8082 | doc: /* Alist of coding system names. |
8083 | Each element is one element list of coding system name. | |
8084 | This variable is given to `completing-read' as TABLE argument. | |
8085 | ||
8086 | Do not alter the value of this variable manually. This variable should be | |
8087 | updated by the functions `make-coding-system' and | |
8088 | `define-coding-system-alias'. */); | |
4608c386 KH |
8089 | Vcoding_system_alist = Qnil; |
8090 | ||
4ed46869 | 8091 | DEFVAR_LISP ("coding-category-list", &Vcoding_category_list, |
48b0f3ae PJ |
8092 | doc: /* List of coding-categories (symbols) ordered by priority. |
8093 | ||
8094 | On detecting a coding system, Emacs tries code detection algorithms | |
8095 | associated with each coding-category one by one in this order. When | |
8096 | one algorithm agrees with a byte sequence of source text, the coding | |
8097 | system bound to the corresponding coding-category is selected. */); | |
4ed46869 KH |
8098 | { |
8099 | int i; | |
8100 | ||
8101 | Vcoding_category_list = Qnil; | |
df7492f9 | 8102 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 8103 | Vcoding_category_list |
d46c5b12 KH |
8104 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
8105 | Vcoding_category_list); | |
4ed46869 KH |
8106 | } |
8107 | ||
8108 | DEFVAR_LISP ("coding-system-for-read", &Vcoding_system_for_read, | |
48b0f3ae PJ |
8109 | doc: /* Specify the coding system for read operations. |
8110 | It is useful to bind this variable with `let', but do not set it globally. | |
8111 | If the value is a coding system, it is used for decoding on read operation. | |
8112 | If not, an appropriate element is used from one of the coding system alists: | |
8113 | There are three such tables, `file-coding-system-alist', | |
8114 | `process-coding-system-alist', and `network-coding-system-alist'. */); | |
4ed46869 KH |
8115 | Vcoding_system_for_read = Qnil; |
8116 | ||
8117 | DEFVAR_LISP ("coding-system-for-write", &Vcoding_system_for_write, | |
48b0f3ae PJ |
8118 | doc: /* Specify the coding system for write operations. |
8119 | Programs bind this variable with `let', but you should not set it globally. | |
8120 | If the value is a coding system, it is used for encoding of output, | |
8121 | when writing it to a file and when sending it to a file or subprocess. | |
8122 | ||
8123 | If this does not specify a coding system, an appropriate element | |
8124 | is used from one of the coding system alists: | |
8125 | There are three such tables, `file-coding-system-alist', | |
8126 | `process-coding-system-alist', and `network-coding-system-alist'. | |
8127 | For output to files, if the above procedure does not specify a coding system, | |
8128 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
8129 | Vcoding_system_for_write = Qnil; |
8130 | ||
8131 | DEFVAR_LISP ("last-coding-system-used", &Vlast_coding_system_used, | |
df7492f9 KH |
8132 | doc: /* |
8133 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
8134 | Vlast_coding_system_used = Qnil; |
8135 | ||
9ce27fde | 8136 | DEFVAR_BOOL ("inhibit-eol-conversion", &inhibit_eol_conversion, |
df7492f9 KH |
8137 | doc: /* |
8138 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
8139 | See info node `Coding Systems' and info node `Text and Binary' concerning |
8140 | such conversion. */); | |
9ce27fde KH |
8141 | inhibit_eol_conversion = 0; |
8142 | ||
ed29121d | 8143 | DEFVAR_BOOL ("inherit-process-coding-system", &inherit_process_coding_system, |
df7492f9 KH |
8144 | doc: /* |
8145 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
8146 | Bind it to t if the process output is to be treated as if it were a file |
8147 | read from some filesystem. */); | |
ed29121d EZ |
8148 | inherit_process_coding_system = 0; |
8149 | ||
02ba4723 | 8150 | DEFVAR_LISP ("file-coding-system-alist", &Vfile_coding_system_alist, |
df7492f9 KH |
8151 | doc: /* |
8152 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
8153 | The format is ((PATTERN . VAL) ...), |
8154 | where PATTERN is a regular expression matching a file name, | |
8155 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
8156 | If VAL is a coding system, it is used for both decoding and encoding | |
8157 | the file contents. | |
8158 | If VAL is a cons of coding systems, the car part is used for decoding, | |
8159 | and the cdr part is used for encoding. | |
8160 | If VAL is a function symbol, the function must return a coding system | |
0192762c DL |
8161 | or a cons of coding systems which are used as above. The function gets |
8162 | the arguments with which `find-operation-coding-systems' was called. | |
48b0f3ae PJ |
8163 | |
8164 | See also the function `find-operation-coding-system' | |
8165 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
8166 | Vfile_coding_system_alist = Qnil; |
8167 | ||
8168 | DEFVAR_LISP ("process-coding-system-alist", &Vprocess_coding_system_alist, | |
df7492f9 KH |
8169 | doc: /* |
8170 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
8171 | The format is ((PATTERN . VAL) ...), |
8172 | where PATTERN is a regular expression matching a program name, | |
8173 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
8174 | If VAL is a coding system, it is used for both decoding what received | |
8175 | from the program and encoding what sent to the program. | |
8176 | If VAL is a cons of coding systems, the car part is used for decoding, | |
8177 | and the cdr part is used for encoding. | |
8178 | If VAL is a function symbol, the function must return a coding system | |
8179 | or a cons of coding systems which are used as above. | |
8180 | ||
8181 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
8182 | Vprocess_coding_system_alist = Qnil; |
8183 | ||
8184 | DEFVAR_LISP ("network-coding-system-alist", &Vnetwork_coding_system_alist, | |
df7492f9 KH |
8185 | doc: /* |
8186 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
8187 | The format is ((PATTERN . VAL) ...), |
8188 | where PATTERN is a regular expression matching a network service name | |
8189 | or is a port number to connect to, | |
8190 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
8191 | If VAL is a coding system, it is used for both decoding what received | |
8192 | from the network stream and encoding what sent to the network stream. | |
8193 | If VAL is a cons of coding systems, the car part is used for decoding, | |
8194 | and the cdr part is used for encoding. | |
8195 | If VAL is a function symbol, the function must return a coding system | |
8196 | or a cons of coding systems which are used as above. | |
8197 | ||
8198 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 8199 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 8200 | |
68c45bf0 | 8201 | DEFVAR_LISP ("locale-coding-system", &Vlocale_coding_system, |
75205970 RS |
8202 | doc: /* Coding system to use with system messages. |
8203 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
8204 | Vlocale_coding_system = Qnil; |
8205 | ||
005f0d35 | 8206 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
7722baf9 | 8207 | DEFVAR_LISP ("eol-mnemonic-unix", &eol_mnemonic_unix, |
df7492f9 KH |
8208 | doc: /* |
8209 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
7722baf9 | 8210 | eol_mnemonic_unix = build_string (":"); |
4ed46869 | 8211 | |
7722baf9 | 8212 | DEFVAR_LISP ("eol-mnemonic-dos", &eol_mnemonic_dos, |
df7492f9 KH |
8213 | doc: /* |
8214 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
7722baf9 | 8215 | eol_mnemonic_dos = build_string ("\\"); |
4ed46869 | 8216 | |
7722baf9 | 8217 | DEFVAR_LISP ("eol-mnemonic-mac", &eol_mnemonic_mac, |
df7492f9 KH |
8218 | doc: /* |
8219 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
7722baf9 | 8220 | eol_mnemonic_mac = build_string ("/"); |
4ed46869 | 8221 | |
7722baf9 | 8222 | DEFVAR_LISP ("eol-mnemonic-undecided", &eol_mnemonic_undecided, |
df7492f9 KH |
8223 | doc: /* |
8224 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
7722baf9 | 8225 | eol_mnemonic_undecided = build_string (":"); |
4ed46869 | 8226 | |
84fbb8a0 | 8227 | DEFVAR_LISP ("enable-character-translation", &Venable_character_translation, |
df7492f9 KH |
8228 | doc: /* |
8229 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 8230 | Venable_character_translation = Qt; |
bdd9fb48 | 8231 | |
f967223b | 8232 | DEFVAR_LISP ("standard-translation-table-for-decode", |
48b0f3ae PJ |
8233 | &Vstandard_translation_table_for_decode, |
8234 | doc: /* Table for translating characters while decoding. */); | |
f967223b | 8235 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 8236 | |
f967223b | 8237 | DEFVAR_LISP ("standard-translation-table-for-encode", |
48b0f3ae PJ |
8238 | &Vstandard_translation_table_for_encode, |
8239 | doc: /* Table for translating characters while encoding. */); | |
f967223b | 8240 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 8241 | |
df7492f9 | 8242 | DEFVAR_LISP ("charset-revision-table", &Vcharset_revision_table, |
48b0f3ae PJ |
8243 | doc: /* Alist of charsets vs revision numbers. |
8244 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
8245 | designate it with the escape sequence identifying revision (cdr part |
8246 | of the element). */); | |
8247 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
8248 | |
8249 | DEFVAR_LISP ("default-process-coding-system", | |
8250 | &Vdefault_process_coding_system, | |
48b0f3ae PJ |
8251 | doc: /* Cons of coding systems used for process I/O by default. |
8252 | The car part is used for decoding a process output, | |
8253 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 8254 | Vdefault_process_coding_system = Qnil; |
c4825358 | 8255 | |
3f003981 | 8256 | DEFVAR_LISP ("latin-extra-code-table", &Vlatin_extra_code_table, |
df7492f9 KH |
8257 | doc: /* |
8258 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
8259 | This is a vector of length 256. |
8260 | If Nth element is non-nil, the existence of code N in a file | |
8261 | \(or output of subprocess) doesn't prevent it to be detected as | |
8262 | a coding system of ISO 2022 variant which has a flag | |
8263 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
8264 | or reading output of a subprocess. | |
8265 | Only 128th through 159th elements has a meaning. */); | |
3f003981 | 8266 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
8267 | |
8268 | DEFVAR_LISP ("select-safe-coding-system-function", | |
8269 | &Vselect_safe_coding_system_function, | |
df7492f9 KH |
8270 | doc: /* |
8271 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
8272 | |
8273 | If set, this function is called to force a user to select a proper | |
8274 | coding system which can encode the text in the case that a default | |
8275 | coding system used in each operation can't encode the text. | |
8276 | ||
8277 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
8278 | Vselect_safe_coding_system_function = Qnil; |
8279 | ||
22ab2303 | 8280 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
74383408 | 8281 | &inhibit_iso_escape_detection, |
df7492f9 KH |
8282 | doc: /* |
8283 | If non-nil, Emacs ignores ISO2022's escape sequence on code detection. | |
48b0f3ae PJ |
8284 | |
8285 | By default, on reading a file, Emacs tries to detect how the text is | |
8286 | encoded. This code detection is sensitive to escape sequences. If | |
8287 | the sequence is valid as ISO2022, the code is determined as one of | |
8288 | the ISO2022 encodings, and the file is decoded by the corresponding | |
8289 | coding system (e.g. `iso-2022-7bit'). | |
8290 | ||
8291 | However, there may be a case that you want to read escape sequences in | |
8292 | a file as is. In such a case, you can set this variable to non-nil. | |
8293 | Then, as the code detection ignores any escape sequences, no file is | |
8294 | detected as encoded in some ISO2022 encoding. The result is that all | |
8295 | escape sequences become visible in a buffer. | |
8296 | ||
8297 | The default value is nil, and it is strongly recommended not to change | |
8298 | it. That is because many Emacs Lisp source files that contain | |
8299 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
8300 | in Emacs's distribution, and they won't be decoded correctly on | |
8301 | reading if you suppress escape sequence detection. | |
8302 | ||
8303 | The other way to read escape sequences in a file without decoding is | |
8304 | to explicitly specify some coding system that doesn't use ISO2022's | |
8305 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); | |
74383408 | 8306 | inhibit_iso_escape_detection = 0; |
2c78b7e1 KH |
8307 | |
8308 | { | |
8309 | Lisp_Object args[coding_arg_max]; | |
8310 | Lisp_Object plist[14]; | |
8311 | int i; | |
8312 | ||
8313 | for (i = 0; i < coding_arg_max; i++) | |
8314 | args[i] = Qnil; | |
8315 | ||
8316 | plist[0] = intern (":name"); | |
8317 | plist[1] = args[coding_arg_name] = Qno_conversion; | |
8318 | plist[2] = intern (":mnemonic"); | |
8319 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); | |
8320 | plist[4] = intern (":coding-type"); | |
8321 | plist[5] = args[coding_arg_coding_type] = Qraw_text; | |
8322 | plist[6] = intern (":ascii-compatible-p"); | |
8323 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; | |
8324 | plist[8] = intern (":default-char"); | |
8325 | plist[9] = args[coding_arg_default_char] = make_number (0); | |
8326 | plist[10] = intern (":docstring"); | |
8327 | plist[11] = build_string ("Do no conversion.\n\ | |
8328 | \n\ | |
8329 | When you visit a file with this coding, the file is read into a\n\ | |
8330 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
8331 | character."); | |
8332 | plist[12] = intern (":eol-type"); | |
8333 | plist[13] = args[coding_arg_eol_type] = Qunix; | |
8334 | args[coding_arg_plist] = Flist (14, plist); | |
8335 | Fdefine_coding_system_internal (coding_arg_max, args); | |
8336 | } | |
8337 | ||
8338 | setup_coding_system (Qno_conversion, &keyboard_coding); | |
8339 | setup_coding_system (Qno_conversion, &terminal_coding); | |
8340 | setup_coding_system (Qno_conversion, &safe_terminal_coding); | |
4ed46869 KH |
8341 | } |
8342 | ||
68c45bf0 PE |
8343 | char * |
8344 | emacs_strerror (error_number) | |
8345 | int error_number; | |
8346 | { | |
8347 | char *str; | |
8348 | ||
ca9c0567 | 8349 | synchronize_system_messages_locale (); |
68c45bf0 PE |
8350 | str = strerror (error_number); |
8351 | ||
8352 | if (! NILP (Vlocale_coding_system)) | |
8353 | { | |
8354 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
8355 | Vlocale_coding_system, | |
8356 | 0); | |
8357 | str = (char *) XSTRING (dec)->data; | |
8358 | } | |
8359 | ||
8360 | return str; | |
8361 | } | |
8362 | ||
4ed46869 | 8363 | #endif /* emacs */ |