Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
aaef169d | 2 | Copyright (C) 2001, 2002, 2003, 2004, 2005, |
5df4f04c | 3 | 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation, Inc. |
7976eda0 | 4 | Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, |
5df4f04c | 5 | 2005, 2006, 2007, 2008, 2009, 2010, 2011 |
ce03bf76 KH |
6 | National Institute of Advanced Industrial Science and Technology (AIST) |
7 | Registration Number H14PRO021 | |
8f924df7 | 8 | Copyright (C) 2003 |
df7492f9 KH |
9 | National Institute of Advanced Industrial Science and Technology (AIST) |
10 | Registration Number H13PRO009 | |
4ed46869 | 11 | |
369314dc KH |
12 | This file is part of GNU Emacs. |
13 | ||
9ec0b715 | 14 | GNU Emacs is free software: you can redistribute it and/or modify |
369314dc | 15 | it under the terms of the GNU General Public License as published by |
9ec0b715 GM |
16 | the Free Software Foundation, either version 3 of the License, or |
17 | (at your option) any later version. | |
4ed46869 | 18 | |
369314dc KH |
19 | GNU Emacs is distributed in the hope that it will be useful, |
20 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
21 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
22 | GNU General Public License for more details. | |
4ed46869 | 23 | |
369314dc | 24 | You should have received a copy of the GNU General Public License |
9ec0b715 | 25 | along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */ |
4ed46869 KH |
26 | |
27 | /*** TABLE OF CONTENTS *** | |
28 | ||
b73bfc1c | 29 | 0. General comments |
4ed46869 | 30 | 1. Preamble |
df7492f9 KH |
31 | 2. Emacs' internal format (emacs-utf-8) handlers |
32 | 3. UTF-8 handlers | |
33 | 4. UTF-16 handlers | |
34 | 5. Charset-base coding systems handlers | |
35 | 6. emacs-mule (old Emacs' internal format) handlers | |
36 | 7. ISO2022 handlers | |
37 | 8. Shift-JIS and BIG5 handlers | |
38 | 9. CCL handlers | |
39 | 10. C library functions | |
40 | 11. Emacs Lisp library functions | |
41 | 12. Postamble | |
4ed46869 KH |
42 | |
43 | */ | |
44 | ||
df7492f9 | 45 | /*** 0. General comments *** |
b73bfc1c KH |
46 | |
47 | ||
df7492f9 | 48 | CODING SYSTEM |
4ed46869 | 49 | |
5bad0796 DL |
50 | A coding system is an object for an encoding mechanism that contains |
51 | information about how to convert byte sequences to character | |
e19c3639 KH |
52 | sequences and vice versa. When we say "decode", it means converting |
53 | a byte sequence of a specific coding system into a character | |
54 | sequence that is represented by Emacs' internal coding system | |
55 | `emacs-utf-8', and when we say "encode", it means converting a | |
56 | character sequence of emacs-utf-8 to a byte sequence of a specific | |
0ef69138 | 57 | coding system. |
4ed46869 | 58 | |
e19c3639 KH |
59 | In Emacs Lisp, a coding system is represented by a Lisp symbol. In |
60 | C level, a coding system is represented by a vector of attributes | |
5bad0796 | 61 | stored in the hash table Vcharset_hash_table. The conversion from |
e19c3639 KH |
62 | coding system symbol to attributes vector is done by looking up |
63 | Vcharset_hash_table by the symbol. | |
4ed46869 | 64 | |
e19c3639 | 65 | Coding systems are classified into the following types depending on |
5bad0796 | 66 | the encoding mechanism. Here's a brief description of the types. |
4ed46869 | 67 | |
df7492f9 KH |
68 | o UTF-8 |
69 | ||
70 | o UTF-16 | |
71 | ||
72 | o Charset-base coding system | |
73 | ||
74 | A coding system defined by one or more (coded) character sets. | |
5bad0796 | 75 | Decoding and encoding are done by a code converter defined for each |
df7492f9 KH |
76 | character set. |
77 | ||
5bad0796 | 78 | o Old Emacs internal format (emacs-mule) |
df7492f9 | 79 | |
5bad0796 | 80 | The coding system adopted by old versions of Emacs (20 and 21). |
4ed46869 | 81 | |
df7492f9 | 82 | o ISO2022-base coding system |
4ed46869 KH |
83 | |
84 | The most famous coding system for multiple character sets. X's | |
df7492f9 KH |
85 | Compound Text, various EUCs (Extended Unix Code), and coding systems |
86 | used in the Internet communication such as ISO-2022-JP are all | |
87 | variants of ISO2022. | |
4ed46869 | 88 | |
df7492f9 | 89 | o SJIS (or Shift-JIS or MS-Kanji-Code) |
93dec019 | 90 | |
4ed46869 KH |
91 | A coding system to encode character sets: ASCII, JISX0201, and |
92 | JISX0208. Widely used for PC's in Japan. Details are described in | |
df7492f9 | 93 | section 8. |
4ed46869 | 94 | |
df7492f9 | 95 | o BIG5 |
4ed46869 | 96 | |
df7492f9 | 97 | A coding system to encode character sets: ASCII and Big5. Widely |
cfb43547 | 98 | used for Chinese (mainly in Taiwan and Hong Kong). Details are |
df7492f9 KH |
99 | described in section 8. In this file, when we write "big5" (all |
100 | lowercase), we mean the coding system, and when we write "Big5" | |
101 | (capitalized), we mean the character set. | |
4ed46869 | 102 | |
df7492f9 | 103 | o CCL |
27901516 | 104 | |
5bad0796 | 105 | If a user wants to decode/encode text encoded in a coding system |
df7492f9 KH |
106 | not listed above, he can supply a decoder and an encoder for it in |
107 | CCL (Code Conversion Language) programs. Emacs executes the CCL | |
108 | program while decoding/encoding. | |
27901516 | 109 | |
df7492f9 | 110 | o Raw-text |
4ed46869 | 111 | |
5a936b46 | 112 | A coding system for text containing raw eight-bit data. Emacs |
5bad0796 | 113 | treats each byte of source text as a character (except for |
df7492f9 | 114 | end-of-line conversion). |
4ed46869 | 115 | |
df7492f9 KH |
116 | o No-conversion |
117 | ||
118 | Like raw text, but don't do end-of-line conversion. | |
4ed46869 | 119 | |
4ed46869 | 120 | |
df7492f9 | 121 | END-OF-LINE FORMAT |
4ed46869 | 122 | |
5bad0796 | 123 | How text end-of-line is encoded depends on operating system. For |
df7492f9 | 124 | instance, Unix's format is just one byte of LF (line-feed) code, |
f4dee582 | 125 | whereas DOS's format is two-byte sequence of `carriage-return' and |
d46c5b12 KH |
126 | `line-feed' codes. MacOS's format is usually one byte of |
127 | `carriage-return'. | |
4ed46869 | 128 | |
cfb43547 | 129 | Since text character encoding and end-of-line encoding are |
df7492f9 KH |
130 | independent, any coding system described above can take any format |
131 | of end-of-line (except for no-conversion). | |
4ed46869 | 132 | |
e19c3639 KH |
133 | STRUCT CODING_SYSTEM |
134 | ||
135 | Before using a coding system for code conversion (i.e. decoding and | |
136 | encoding), we setup a structure of type `struct coding_system'. | |
137 | This structure keeps various information about a specific code | |
5bad0796 | 138 | conversion (e.g. the location of source and destination data). |
4ed46869 KH |
139 | |
140 | */ | |
141 | ||
df7492f9 KH |
142 | /* COMMON MACROS */ |
143 | ||
144 | ||
4ed46869 KH |
145 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
146 | ||
df7492f9 | 147 | These functions check if a byte sequence specified as a source in |
ff0dacd7 KH |
148 | CODING conforms to the format of XXX, and update the members of |
149 | DETECT_INFO. | |
df7492f9 | 150 | |
ff0dacd7 | 151 | Return 1 if the byte sequence conforms to XXX, otherwise return 0. |
df7492f9 KH |
152 | |
153 | Below is the template of these functions. */ | |
154 | ||
4ed46869 | 155 | #if 0 |
df7492f9 | 156 | static int |
cf84bb53 JB |
157 | detect_coding_XXX (struct coding_system *coding, |
158 | struct coding_detection_info *detect_info) | |
4ed46869 | 159 | { |
f1d34bca MB |
160 | const unsigned char *src = coding->source; |
161 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 162 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 163 | int consumed_chars = 0; |
df7492f9 KH |
164 | int found = 0; |
165 | ...; | |
166 | ||
167 | while (1) | |
168 | { | |
ad1746f5 | 169 | /* Get one byte from the source. If the source is exhausted, jump |
df7492f9 KH |
170 | to no_more_source:. */ |
171 | ONE_MORE_BYTE (c); | |
ff0dacd7 KH |
172 | |
173 | if (! __C_conforms_to_XXX___ (c)) | |
174 | break; | |
175 | if (! __C_strongly_suggests_XXX__ (c)) | |
176 | found = CATEGORY_MASK_XXX; | |
df7492f9 | 177 | } |
ff0dacd7 KH |
178 | /* The byte sequence is invalid for XXX. */ |
179 | detect_info->rejected |= CATEGORY_MASK_XXX; | |
df7492f9 | 180 | return 0; |
ff0dacd7 | 181 | |
df7492f9 | 182 | no_more_source: |
ad1746f5 | 183 | /* The source exhausted successfully. */ |
ff0dacd7 | 184 | detect_info->found |= found; |
df7492f9 | 185 | return 1; |
4ed46869 KH |
186 | } |
187 | #endif | |
188 | ||
189 | /*** GENERAL NOTES on `decode_coding_XXX ()' functions *** | |
190 | ||
df7492f9 KH |
191 | These functions decode a byte sequence specified as a source by |
192 | CODING. The resulting multibyte text goes to a place pointed to by | |
193 | CODING->charbuf, the length of which should not exceed | |
194 | CODING->charbuf_size; | |
d46c5b12 | 195 | |
df7492f9 KH |
196 | These functions set the information of original and decoded texts in |
197 | CODING->consumed, CODING->consumed_char, and CODING->charbuf_used. | |
198 | They also set CODING->result to one of CODING_RESULT_XXX indicating | |
199 | how the decoding is finished. | |
d46c5b12 | 200 | |
df7492f9 | 201 | Below is the template of these functions. */ |
d46c5b12 | 202 | |
4ed46869 | 203 | #if 0 |
b73bfc1c | 204 | static void |
cf84bb53 | 205 | decode_coding_XXXX (struct coding_system *coding) |
4ed46869 | 206 | { |
f1d34bca MB |
207 | const unsigned char *src = coding->source + coding->consumed; |
208 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
209 | /* SRC_BASE remembers the start position in source in each loop. |
210 | The loop will be exited when there's not enough source code, or | |
211 | when there's no room in CHARBUF for a decoded character. */ | |
f1d34bca | 212 | const unsigned char *src_base; |
df7492f9 | 213 | /* A buffer to produce decoded characters. */ |
69a80ea3 KH |
214 | int *charbuf = coding->charbuf + coding->charbuf_used; |
215 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
216 | int multibytep = coding->src_multibyte; |
217 | ||
218 | while (1) | |
219 | { | |
220 | src_base = src; | |
221 | if (charbuf < charbuf_end) | |
222 | /* No more room to produce a decoded character. */ | |
223 | break; | |
224 | ONE_MORE_BYTE (c); | |
225 | /* Decode it. */ | |
226 | } | |
227 | ||
228 | no_more_source: | |
229 | if (src_base < src_end | |
230 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
231 | /* If the source ends by partial bytes to construct a character, | |
232 | treat them as eight-bit raw data. */ | |
233 | while (src_base < src_end && charbuf < charbuf_end) | |
234 | *charbuf++ = *src_base++; | |
235 | /* Remember how many bytes and characters we consumed. If the | |
236 | source is multibyte, the bytes and chars are not identical. */ | |
237 | coding->consumed = coding->consumed_char = src_base - coding->source; | |
238 | /* Remember how many characters we produced. */ | |
239 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
240 | } |
241 | #endif | |
242 | ||
243 | /*** GENERAL NOTES on `encode_coding_XXX ()' functions *** | |
244 | ||
df7492f9 KH |
245 | These functions encode SRC_BYTES length text at SOURCE of Emacs' |
246 | internal multibyte format by CODING. The resulting byte sequence | |
b73bfc1c KH |
247 | goes to a place pointed to by DESTINATION, the length of which |
248 | should not exceed DST_BYTES. | |
d46c5b12 | 249 | |
df7492f9 KH |
250 | These functions set the information of original and encoded texts in |
251 | the members produced, produced_char, consumed, and consumed_char of | |
252 | the structure *CODING. They also set the member result to one of | |
253 | CODING_RESULT_XXX indicating how the encoding finished. | |
d46c5b12 | 254 | |
df7492f9 KH |
255 | DST_BYTES zero means that source area and destination area are |
256 | overlapped, which means that we can produce a encoded text until it | |
257 | reaches at the head of not-yet-encoded source text. | |
d46c5b12 | 258 | |
df7492f9 | 259 | Below is a template of these functions. */ |
4ed46869 | 260 | #if 0 |
b73bfc1c | 261 | static void |
cf84bb53 | 262 | encode_coding_XXX (struct coding_system *coding) |
4ed46869 | 263 | { |
df7492f9 KH |
264 | int multibytep = coding->dst_multibyte; |
265 | int *charbuf = coding->charbuf; | |
266 | int *charbuf_end = charbuf->charbuf + coding->charbuf_used; | |
267 | unsigned char *dst = coding->destination + coding->produced; | |
268 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
269 | unsigned char *adjusted_dst_end = dst_end - _MAX_BYTES_PRODUCED_IN_LOOP_; | |
270 | int produced_chars = 0; | |
271 | ||
272 | for (; charbuf < charbuf_end && dst < adjusted_dst_end; charbuf++) | |
273 | { | |
274 | int c = *charbuf; | |
275 | /* Encode C into DST, and increment DST. */ | |
276 | } | |
277 | label_no_more_destination: | |
278 | /* How many chars and bytes we produced. */ | |
279 | coding->produced_char += produced_chars; | |
280 | coding->produced = dst - coding->destination; | |
4ed46869 KH |
281 | } |
282 | #endif | |
283 | ||
4ed46869 KH |
284 | \f |
285 | /*** 1. Preamble ***/ | |
286 | ||
68c45bf0 | 287 | #include <config.h> |
4ed46869 | 288 | #include <stdio.h> |
d7306fe6 | 289 | #include <setjmp.h> |
4ed46869 | 290 | |
4ed46869 KH |
291 | #include "lisp.h" |
292 | #include "buffer.h" | |
df7492f9 | 293 | #include "character.h" |
4ed46869 KH |
294 | #include "charset.h" |
295 | #include "ccl.h" | |
df7492f9 | 296 | #include "composite.h" |
4ed46869 KH |
297 | #include "coding.h" |
298 | #include "window.h" | |
b8299c66 KL |
299 | #include "frame.h" |
300 | #include "termhooks.h" | |
4ed46869 | 301 | |
df7492f9 | 302 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 303 | |
df7492f9 | 304 | Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type; |
1965cb73 | 305 | Lisp_Object Qunix, Qdos; |
4ed46869 KH |
306 | Lisp_Object Qbuffer_file_coding_system; |
307 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
df7492f9 | 308 | Lisp_Object Qdefault_char; |
27901516 | 309 | Lisp_Object Qno_conversion, Qundecided; |
df7492f9 | 310 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
b49a1807 | 311 | Lisp_Object Qbig, Qlittle; |
bb0115a2 | 312 | Lisp_Object Qcoding_system_history; |
1397dc18 | 313 | Lisp_Object Qvalid_codes; |
2133e2d1 | 314 | Lisp_Object QCcategory, QCmnemonic, QCdefault_char; |
a6f87d34 KH |
315 | Lisp_Object QCdecode_translation_table, QCencode_translation_table; |
316 | Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
35befdaa | 317 | Lisp_Object QCascii_compatible_p; |
4ed46869 | 318 | |
387f6ba5 | 319 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 KH |
320 | Lisp_Object Qstart_process, Qopen_network_stream; |
321 | Lisp_Object Qtarget_idx; | |
322 | ||
065e3595 KH |
323 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
324 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
325 | ||
44e8490d KH |
326 | /* If a symbol has this property, evaluate the value to define the |
327 | symbol as a coding system. */ | |
328 | static Lisp_Object Qcoding_system_define_form; | |
329 | ||
fcbcfb64 KH |
330 | /* Format of end-of-line decided by system. This is Qunix on |
331 | Unix and Mac, Qdos on DOS/Windows. | |
332 | This has an effect only for external encoding (i.e. for output to | |
333 | file and process), not for in-buffer or Lisp string encoding. */ | |
334 | static Lisp_Object system_eol_type; | |
335 | ||
4ed46869 KH |
336 | #ifdef emacs |
337 | ||
4608c386 | 338 | Lisp_Object Qcoding_system_p, Qcoding_system_error; |
4ed46869 | 339 | |
d46c5b12 KH |
340 | /* Coding system emacs-mule and raw-text are for converting only |
341 | end-of-line format. */ | |
342 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 343 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 344 | |
4ed46869 KH |
345 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
346 | routines by the following three variables. */ | |
c4825358 KH |
347 | /* Coding system to be used to encode text for terminal display when |
348 | terminal coding system is nil. */ | |
349 | struct coding_system safe_terminal_coding; | |
350 | ||
4ed46869 KH |
351 | #endif /* emacs */ |
352 | ||
f967223b KH |
353 | Lisp_Object Qtranslation_table; |
354 | Lisp_Object Qtranslation_table_id; | |
355 | Lisp_Object Qtranslation_table_for_decode; | |
356 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 | 357 | |
df7492f9 KH |
358 | /* Two special coding systems. */ |
359 | Lisp_Object Vsjis_coding_system; | |
360 | Lisp_Object Vbig5_coding_system; | |
361 | ||
df7492f9 KH |
362 | /* ISO2022 section */ |
363 | ||
364 | #define CODING_ISO_INITIAL(coding, reg) \ | |
365 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
366 | coding_attr_iso_initial), \ | |
367 | reg))) | |
368 | ||
369 | ||
1b3b981b AS |
370 | #define CODING_ISO_REQUEST(coding, charset_id) \ |
371 | (((charset_id) <= (coding)->max_charset_id \ | |
372 | ? ((coding)->safe_charsets[charset_id] != 255 \ | |
373 | ? (coding)->safe_charsets[charset_id] \ | |
374 | : -1) \ | |
df7492f9 KH |
375 | : -1)) |
376 | ||
377 | ||
378 | #define CODING_ISO_FLAGS(coding) \ | |
379 | ((coding)->spec.iso_2022.flags) | |
380 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
381 | ((coding)->spec.iso_2022.current_designation[reg]) | |
382 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
383 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
384 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
385 | ((coding)->spec.iso_2022.single_shifting) | |
386 | #define CODING_ISO_BOL(coding) \ | |
387 | ((coding)->spec.iso_2022.bol) | |
388 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
389 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
e951386e KH |
390 | #define CODING_ISO_CMP_STATUS(coding) \ |
391 | (&(coding)->spec.iso_2022.cmp_status) | |
392 | #define CODING_ISO_EXTSEGMENT_LEN(coding) \ | |
393 | ((coding)->spec.iso_2022.ctext_extended_segment_len) | |
394 | #define CODING_ISO_EMBEDDED_UTF_8(coding) \ | |
395 | ((coding)->spec.iso_2022.embedded_utf_8) | |
df7492f9 KH |
396 | |
397 | /* Control characters of ISO2022. */ | |
398 | /* code */ /* function */ | |
399 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
400 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
401 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
402 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
403 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
404 | #define ISO_CODE_ESC 0x1B /* escape */ | |
405 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
406 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
407 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
408 | ||
409 | /* All code (1-byte) of ISO2022 is classified into one of the | |
410 | followings. */ | |
411 | enum iso_code_class_type | |
412 | { | |
413 | ISO_control_0, /* Control codes in the range | |
414 | 0x00..0x1F and 0x7F, except for the | |
415 | following 5 codes. */ | |
df7492f9 KH |
416 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
417 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
418 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
419 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
420 | ISO_control_1, /* Control codes in the range | |
421 | 0x80..0x9F, except for the | |
422 | following 3 codes. */ | |
423 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
424 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
425 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
426 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
427 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
428 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
429 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
430 | }; | |
05e6f5dc | 431 | |
df7492f9 KH |
432 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
433 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 434 | |
df7492f9 KH |
435 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
436 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
437 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 438 | |
df7492f9 KH |
439 | /* If set, reset graphic planes and registers at end-of-line to the |
440 | initial state. */ | |
441 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 442 | |
df7492f9 KH |
443 | /* If set, reset graphic planes and registers before any control |
444 | characters to the initial state. */ | |
445 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 446 | |
df7492f9 KH |
447 | /* If set, encode by 7-bit environment. */ |
448 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 449 | |
df7492f9 KH |
450 | /* If set, use locking-shift function. */ |
451 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 452 | |
df7492f9 KH |
453 | /* If set, use single-shift function. Overwrite |
454 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
455 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 456 | |
df7492f9 KH |
457 | /* If set, use designation escape sequence. */ |
458 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 459 | |
df7492f9 KH |
460 | /* If set, produce revision number sequence. */ |
461 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 462 | |
df7492f9 KH |
463 | /* If set, produce ISO6429's direction specifying sequence. */ |
464 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 465 | |
df7492f9 KH |
466 | /* If set, assume designation states are reset at beginning of line on |
467 | output. */ | |
468 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 469 | |
df7492f9 KH |
470 | /* If set, designation sequence should be placed at beginning of line |
471 | on output. */ | |
472 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 473 | |
ad1746f5 | 474 | /* If set, do not encode unsafe characters on output. */ |
df7492f9 | 475 | #define CODING_ISO_FLAG_SAFE 0x0800 |
aa72b389 | 476 | |
df7492f9 KH |
477 | /* If set, extra latin codes (128..159) are accepted as a valid code |
478 | on input. */ | |
479 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 480 | |
df7492f9 | 481 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 482 | |
df7492f9 | 483 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 484 | |
bf16eb23 | 485 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 486 | |
bf16eb23 | 487 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 488 | |
bf16eb23 | 489 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 490 | |
df7492f9 KH |
491 | /* A character to be produced on output if encoding of the original |
492 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
493 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 494 | |
a470d443 KH |
495 | /* UTF-8 section */ |
496 | #define CODING_UTF_8_BOM(coding) \ | |
497 | ((coding)->spec.utf_8_bom) | |
4ed46869 | 498 | |
df7492f9 KH |
499 | /* UTF-16 section */ |
500 | #define CODING_UTF_16_BOM(coding) \ | |
501 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 502 | |
df7492f9 KH |
503 | #define CODING_UTF_16_ENDIAN(coding) \ |
504 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 505 | |
df7492f9 KH |
506 | #define CODING_UTF_16_SURROGATE(coding) \ |
507 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 508 | |
4ed46869 | 509 | |
df7492f9 KH |
510 | /* CCL section */ |
511 | #define CODING_CCL_DECODER(coding) \ | |
512 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
513 | #define CODING_CCL_ENCODER(coding) \ | |
514 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
515 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 516 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 517 | |
5a936b46 | 518 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 519 | |
df7492f9 KH |
520 | enum coding_category |
521 | { | |
522 | coding_category_iso_7, | |
523 | coding_category_iso_7_tight, | |
524 | coding_category_iso_8_1, | |
525 | coding_category_iso_8_2, | |
526 | coding_category_iso_7_else, | |
527 | coding_category_iso_8_else, | |
a470d443 KH |
528 | coding_category_utf_8_auto, |
529 | coding_category_utf_8_nosig, | |
530 | coding_category_utf_8_sig, | |
df7492f9 KH |
531 | coding_category_utf_16_auto, |
532 | coding_category_utf_16_be, | |
533 | coding_category_utf_16_le, | |
534 | coding_category_utf_16_be_nosig, | |
535 | coding_category_utf_16_le_nosig, | |
536 | coding_category_charset, | |
537 | coding_category_sjis, | |
538 | coding_category_big5, | |
539 | coding_category_ccl, | |
540 | coding_category_emacs_mule, | |
541 | /* All above are targets of code detection. */ | |
542 | coding_category_raw_text, | |
543 | coding_category_undecided, | |
544 | coding_category_max | |
545 | }; | |
546 | ||
547 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
548 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
549 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
550 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
551 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
552 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
553 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
a470d443 KH |
554 | #define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto) |
555 | #define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig) | |
556 | #define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig) | |
b49a1807 | 557 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
558 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
559 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
560 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
561 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
562 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
563 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
564 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
565 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
566 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 567 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
568 | |
569 | /* This value is returned if detect_coding_mask () find nothing other | |
570 | than ASCII characters. */ | |
571 | #define CATEGORY_MASK_ANY \ | |
572 | (CATEGORY_MASK_ISO_7 \ | |
573 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
574 | | CATEGORY_MASK_ISO_8_1 \ | |
575 | | CATEGORY_MASK_ISO_8_2 \ | |
576 | | CATEGORY_MASK_ISO_7_ELSE \ | |
577 | | CATEGORY_MASK_ISO_8_ELSE \ | |
a470d443 KH |
578 | | CATEGORY_MASK_UTF_8_AUTO \ |
579 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
580 | | CATEGORY_MASK_UTF_8_SIG \ | |
2f3cbb32 | 581 | | CATEGORY_MASK_UTF_16_AUTO \ |
df7492f9 KH |
582 | | CATEGORY_MASK_UTF_16_BE \ |
583 | | CATEGORY_MASK_UTF_16_LE \ | |
584 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
585 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
586 | | CATEGORY_MASK_CHARSET \ | |
587 | | CATEGORY_MASK_SJIS \ | |
588 | | CATEGORY_MASK_BIG5 \ | |
589 | | CATEGORY_MASK_CCL \ | |
590 | | CATEGORY_MASK_EMACS_MULE) | |
591 | ||
592 | ||
593 | #define CATEGORY_MASK_ISO_7BIT \ | |
594 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
595 | ||
596 | #define CATEGORY_MASK_ISO_8BIT \ | |
597 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
598 | ||
599 | #define CATEGORY_MASK_ISO_ELSE \ | |
600 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
601 | ||
602 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
603 | (CATEGORY_MASK_ISO_7 \ | |
604 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
605 | | CATEGORY_MASK_ISO_7_ELSE \ | |
606 | | CATEGORY_MASK_ISO_8_ELSE) | |
607 | ||
608 | #define CATEGORY_MASK_ISO \ | |
609 | ( CATEGORY_MASK_ISO_7BIT \ | |
610 | | CATEGORY_MASK_ISO_8BIT \ | |
611 | | CATEGORY_MASK_ISO_ELSE) | |
612 | ||
613 | #define CATEGORY_MASK_UTF_16 \ | |
2f3cbb32 KH |
614 | (CATEGORY_MASK_UTF_16_AUTO \ |
615 | | CATEGORY_MASK_UTF_16_BE \ | |
df7492f9 KH |
616 | | CATEGORY_MASK_UTF_16_LE \ |
617 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
618 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
619 | ||
a470d443 KH |
620 | #define CATEGORY_MASK_UTF_8 \ |
621 | (CATEGORY_MASK_UTF_8_AUTO \ | |
622 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
623 | | CATEGORY_MASK_UTF_8_SIG) | |
df7492f9 | 624 | |
df7492f9 | 625 | /* Table of coding categories (Lisp symbols). This variable is for |
ad1746f5 | 626 | internal use only. */ |
df7492f9 KH |
627 | static Lisp_Object Vcoding_category_table; |
628 | ||
629 | /* Table of coding-categories ordered by priority. */ | |
630 | static enum coding_category coding_priorities[coding_category_max]; | |
631 | ||
632 | /* Nth element is a coding context for the coding system bound to the | |
633 | Nth coding category. */ | |
634 | static struct coding_system coding_categories[coding_category_max]; | |
635 | ||
df7492f9 KH |
636 | /*** Commonly used macros and functions ***/ |
637 | ||
638 | #ifndef min | |
639 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
640 | #endif | |
641 | #ifndef max | |
642 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
643 | #endif | |
4ed46869 | 644 | |
24a73b0a KH |
645 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
646 | do { \ | |
647 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
648 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 649 | } while (0) |
4ed46869 | 650 | |
4ed46869 | 651 | |
df7492f9 KH |
652 | /* Safely get one byte from the source text pointed by SRC which ends |
653 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
654 | in the source, it jumps to `no_more_source'. If multibytep is |
655 | nonzero, and a multibyte character is found at SRC, set C to the | |
656 | negative value of the character code. The caller should declare | |
657 | and set these variables appropriately in advance: | |
658 | src, src_end, multibytep */ | |
aa72b389 | 659 | |
065e3595 KH |
660 | #define ONE_MORE_BYTE(c) \ |
661 | do { \ | |
662 | if (src == src_end) \ | |
663 | { \ | |
664 | if (src_base < src) \ | |
665 | record_conversion_result \ | |
666 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
667 | goto no_more_source; \ | |
668 | } \ | |
669 | c = *src++; \ | |
670 | if (multibytep && (c & 0x80)) \ | |
671 | { \ | |
672 | if ((c & 0xFE) == 0xC0) \ | |
673 | c = ((c & 1) << 6) | *src++; \ | |
674 | else \ | |
675 | { \ | |
35befdaa KH |
676 | src--; \ |
677 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
678 | record_conversion_result \ |
679 | (coding, CODING_RESULT_INVALID_SRC); \ | |
680 | } \ | |
681 | } \ | |
682 | consumed_chars++; \ | |
aa72b389 KH |
683 | } while (0) |
684 | ||
f56a4450 | 685 | /* Safely get two bytes from the source text pointed by SRC which ends |
220eeac9 KH |
686 | at SRC_END, and set C1 and C2 to those bytes while skipping the |
687 | heading multibyte characters. If there are not enough bytes in the | |
688 | source, it jumps to `no_more_source'. If multibytep is nonzero and | |
689 | a multibyte character is found for C2, set C2 to the negative value | |
690 | of the character code. The caller should declare and set these | |
691 | variables appropriately in advance: | |
f56a4450 KH |
692 | src, src_end, multibytep |
693 | It is intended that this macro is used in detect_coding_utf_16. */ | |
694 | ||
220eeac9 KH |
695 | #define TWO_MORE_BYTES(c1, c2) \ |
696 | do { \ | |
697 | do { \ | |
698 | if (src == src_end) \ | |
699 | goto no_more_source; \ | |
700 | c1 = *src++; \ | |
701 | if (multibytep && (c1 & 0x80)) \ | |
702 | { \ | |
703 | if ((c1 & 0xFE) == 0xC0) \ | |
704 | c1 = ((c1 & 1) << 6) | *src++; \ | |
705 | else \ | |
706 | { \ | |
707 | src += BYTES_BY_CHAR_HEAD (c1) - 1; \ | |
708 | c1 = -1; \ | |
709 | } \ | |
710 | } \ | |
711 | } while (c1 < 0); \ | |
712 | if (src == src_end) \ | |
713 | goto no_more_source; \ | |
714 | c2 = *src++; \ | |
715 | if (multibytep && (c2 & 0x80)) \ | |
716 | { \ | |
717 | if ((c2 & 0xFE) == 0xC0) \ | |
718 | c2 = ((c2 & 1) << 6) | *src++; \ | |
719 | else \ | |
720 | c2 = -1; \ | |
721 | } \ | |
f56a4450 KH |
722 | } while (0) |
723 | ||
aa72b389 | 724 | |
065e3595 KH |
725 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
726 | do { \ | |
727 | c = *src++; \ | |
728 | if (multibytep && (c & 0x80)) \ | |
729 | { \ | |
730 | if ((c & 0xFE) == 0xC0) \ | |
731 | c = ((c & 1) << 6) | *src++; \ | |
732 | else \ | |
733 | { \ | |
35befdaa KH |
734 | src--; \ |
735 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
736 | record_conversion_result \ |
737 | (coding, CODING_RESULT_INVALID_SRC); \ | |
738 | } \ | |
739 | } \ | |
740 | consumed_chars++; \ | |
aa72b389 KH |
741 | } while (0) |
742 | ||
aa72b389 | 743 | |
df7492f9 KH |
744 | /* Store a byte C in the place pointed by DST and increment DST to the |
745 | next free point, and increment PRODUCED_CHARS. The caller should | |
746 | assure that C is 0..127, and declare and set the variable `dst' | |
747 | appropriately in advance. | |
748 | */ | |
aa72b389 KH |
749 | |
750 | ||
df7492f9 KH |
751 | #define EMIT_ONE_ASCII_BYTE(c) \ |
752 | do { \ | |
753 | produced_chars++; \ | |
754 | *dst++ = (c); \ | |
b6871cc7 | 755 | } while (0) |
aa72b389 KH |
756 | |
757 | ||
ad1746f5 | 758 | /* Like EMIT_ONE_ASCII_BYTE but store two bytes; C1 and C2. */ |
aa72b389 | 759 | |
df7492f9 KH |
760 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
761 | do { \ | |
762 | produced_chars += 2; \ | |
763 | *dst++ = (c1), *dst++ = (c2); \ | |
764 | } while (0) | |
aa72b389 KH |
765 | |
766 | ||
df7492f9 KH |
767 | /* Store a byte C in the place pointed by DST and increment DST to the |
768 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
769 | nonzero, store in an appropriate multibyte from. The caller should | |
770 | declare and set the variables `dst' and `multibytep' appropriately | |
771 | in advance. */ | |
772 | ||
773 | #define EMIT_ONE_BYTE(c) \ | |
774 | do { \ | |
775 | produced_chars++; \ | |
776 | if (multibytep) \ | |
777 | { \ | |
778 | int ch = (c); \ | |
779 | if (ch >= 0x80) \ | |
780 | ch = BYTE8_TO_CHAR (ch); \ | |
781 | CHAR_STRING_ADVANCE (ch, dst); \ | |
782 | } \ | |
783 | else \ | |
784 | *dst++ = (c); \ | |
aa72b389 | 785 | } while (0) |
aa72b389 | 786 | |
aa72b389 | 787 | |
df7492f9 | 788 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 789 | |
e19c3639 KH |
790 | #define EMIT_TWO_BYTES(c1, c2) \ |
791 | do { \ | |
792 | produced_chars += 2; \ | |
793 | if (multibytep) \ | |
794 | { \ | |
795 | int ch; \ | |
796 | \ | |
797 | ch = (c1); \ | |
798 | if (ch >= 0x80) \ | |
799 | ch = BYTE8_TO_CHAR (ch); \ | |
800 | CHAR_STRING_ADVANCE (ch, dst); \ | |
801 | ch = (c2); \ | |
802 | if (ch >= 0x80) \ | |
803 | ch = BYTE8_TO_CHAR (ch); \ | |
804 | CHAR_STRING_ADVANCE (ch, dst); \ | |
805 | } \ | |
806 | else \ | |
807 | { \ | |
808 | *dst++ = (c1); \ | |
809 | *dst++ = (c2); \ | |
810 | } \ | |
aa72b389 KH |
811 | } while (0) |
812 | ||
813 | ||
df7492f9 KH |
814 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
815 | do { \ | |
816 | EMIT_ONE_BYTE (c1); \ | |
817 | EMIT_TWO_BYTES (c2, c3); \ | |
818 | } while (0) | |
aa72b389 | 819 | |
aa72b389 | 820 | |
df7492f9 KH |
821 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
822 | do { \ | |
823 | EMIT_TWO_BYTES (c1, c2); \ | |
824 | EMIT_TWO_BYTES (c3, c4); \ | |
825 | } while (0) | |
aa72b389 | 826 | |
aa72b389 | 827 | |
f6cbaf43 | 828 | /* Prototypes for static functions. */ |
f57e2426 J |
829 | static void record_conversion_result (struct coding_system *coding, |
830 | enum coding_result_code result); | |
831 | static int detect_coding_utf_8 (struct coding_system *, | |
832 | struct coding_detection_info *info); | |
833 | static void decode_coding_utf_8 (struct coding_system *); | |
834 | static int encode_coding_utf_8 (struct coding_system *); | |
835 | ||
836 | static int detect_coding_utf_16 (struct coding_system *, | |
837 | struct coding_detection_info *info); | |
838 | static void decode_coding_utf_16 (struct coding_system *); | |
839 | static int encode_coding_utf_16 (struct coding_system *); | |
840 | ||
841 | static int detect_coding_iso_2022 (struct coding_system *, | |
842 | struct coding_detection_info *info); | |
843 | static void decode_coding_iso_2022 (struct coding_system *); | |
844 | static int encode_coding_iso_2022 (struct coding_system *); | |
845 | ||
846 | static int detect_coding_emacs_mule (struct coding_system *, | |
847 | struct coding_detection_info *info); | |
848 | static void decode_coding_emacs_mule (struct coding_system *); | |
849 | static int encode_coding_emacs_mule (struct coding_system *); | |
850 | ||
851 | static int detect_coding_sjis (struct coding_system *, | |
852 | struct coding_detection_info *info); | |
853 | static void decode_coding_sjis (struct coding_system *); | |
854 | static int encode_coding_sjis (struct coding_system *); | |
855 | ||
856 | static int detect_coding_big5 (struct coding_system *, | |
857 | struct coding_detection_info *info); | |
858 | static void decode_coding_big5 (struct coding_system *); | |
859 | static int encode_coding_big5 (struct coding_system *); | |
860 | ||
861 | static int detect_coding_ccl (struct coding_system *, | |
862 | struct coding_detection_info *info); | |
863 | static void decode_coding_ccl (struct coding_system *); | |
864 | static int encode_coding_ccl (struct coding_system *); | |
865 | ||
866 | static void decode_coding_raw_text (struct coding_system *); | |
867 | static int encode_coding_raw_text (struct coding_system *); | |
868 | ||
869 | static void coding_set_source (struct coding_system *); | |
870 | static void coding_set_destination (struct coding_system *); | |
871 | static void coding_alloc_by_realloc (struct coding_system *, EMACS_INT); | |
872 | static void coding_alloc_by_making_gap (struct coding_system *, | |
873 | EMACS_INT, EMACS_INT); | |
874 | static unsigned char *alloc_destination (struct coding_system *, | |
875 | EMACS_INT, unsigned char *); | |
876 | static void setup_iso_safe_charsets (Lisp_Object); | |
877 | static unsigned char *encode_designation_at_bol (struct coding_system *, | |
878 | int *, int *, | |
879 | unsigned char *); | |
880 | static int detect_eol (const unsigned char *, | |
881 | EMACS_INT, enum coding_category); | |
882 | static Lisp_Object adjust_coding_eol_type (struct coding_system *, int); | |
883 | static void decode_eol (struct coding_system *); | |
884 | static Lisp_Object get_translation_table (Lisp_Object, int, int *); | |
885 | static Lisp_Object get_translation (Lisp_Object, int *, int *); | |
886 | static int produce_chars (struct coding_system *, Lisp_Object, int); | |
887 | static INLINE void produce_charset (struct coding_system *, int *, | |
888 | EMACS_INT); | |
889 | static void produce_annotation (struct coding_system *, EMACS_INT); | |
890 | static int decode_coding (struct coding_system *); | |
891 | static INLINE int *handle_composition_annotation (EMACS_INT, EMACS_INT, | |
892 | struct coding_system *, | |
893 | int *, EMACS_INT *); | |
894 | static INLINE int *handle_charset_annotation (EMACS_INT, EMACS_INT, | |
895 | struct coding_system *, | |
896 | int *, EMACS_INT *); | |
897 | static void consume_chars (struct coding_system *, Lisp_Object, int); | |
898 | static int encode_coding (struct coding_system *); | |
899 | static Lisp_Object make_conversion_work_buffer (int); | |
900 | static Lisp_Object code_conversion_restore (Lisp_Object); | |
901 | static INLINE int char_encodable_p (int, Lisp_Object); | |
902 | static Lisp_Object make_subsidiaries (Lisp_Object); | |
f6cbaf43 | 903 | |
065e3595 KH |
904 | static void |
905 | record_conversion_result (struct coding_system *coding, | |
906 | enum coding_result_code result) | |
907 | { | |
908 | coding->result = result; | |
909 | switch (result) | |
910 | { | |
911 | case CODING_RESULT_INSUFFICIENT_SRC: | |
912 | Vlast_code_conversion_error = Qinsufficient_source; | |
913 | break; | |
914 | case CODING_RESULT_INCONSISTENT_EOL: | |
915 | Vlast_code_conversion_error = Qinconsistent_eol; | |
916 | break; | |
917 | case CODING_RESULT_INVALID_SRC: | |
918 | Vlast_code_conversion_error = Qinvalid_source; | |
919 | break; | |
920 | case CODING_RESULT_INTERRUPT: | |
921 | Vlast_code_conversion_error = Qinterrupted; | |
922 | break; | |
923 | case CODING_RESULT_INSUFFICIENT_MEM: | |
924 | Vlast_code_conversion_error = Qinsufficient_memory; | |
925 | break; | |
ebaf11b6 KH |
926 | case CODING_RESULT_INSUFFICIENT_DST: |
927 | /* Don't record this error in Vlast_code_conversion_error | |
928 | because it happens just temporarily and is resolved when the | |
929 | whole conversion is finished. */ | |
930 | break; | |
409ea3a1 AS |
931 | case CODING_RESULT_SUCCESS: |
932 | break; | |
35befdaa KH |
933 | default: |
934 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
935 | } |
936 | } | |
937 | ||
75f80e63 EZ |
938 | /* This wrapper macro is used to preserve validity of pointers into |
939 | buffer text across calls to decode_char, which could cause | |
940 | relocation of buffers if it loads a charset map, because loading a | |
941 | charset map allocates large structures. */ | |
df7492f9 KH |
942 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
943 | do { \ | |
944 | charset_map_loaded = 0; \ | |
945 | c = DECODE_CHAR (charset, code); \ | |
946 | if (charset_map_loaded) \ | |
947 | { \ | |
8f924df7 | 948 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
949 | EMACS_INT offset; \ |
950 | \ | |
951 | coding_set_source (coding); \ | |
952 | offset = coding->source - orig; \ | |
953 | src += offset; \ | |
954 | src_base += offset; \ | |
955 | src_end += offset; \ | |
956 | } \ | |
aa72b389 KH |
957 | } while (0) |
958 | ||
959 | ||
119852e7 KH |
960 | /* If there are at least BYTES length of room at dst, allocate memory |
961 | for coding->destination and update dst and dst_end. We don't have | |
962 | to take care of coding->source which will be relocated. It is | |
963 | handled by calling coding_set_source in encode_coding. */ | |
964 | ||
df7492f9 KH |
965 | #define ASSURE_DESTINATION(bytes) \ |
966 | do { \ | |
967 | if (dst + (bytes) >= dst_end) \ | |
968 | { \ | |
969 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
970 | \ | |
971 | dst = alloc_destination (coding, more_bytes, dst); \ | |
972 | dst_end = coding->destination + coding->dst_bytes; \ | |
973 | } \ | |
974 | } while (0) | |
aa72b389 | 975 | |
aa72b389 | 976 | |
db274c7a KH |
977 | /* Store multibyte form of the character C in P, and advance P to the |
978 | end of the multibyte form. This is like CHAR_STRING_ADVANCE but it | |
979 | never calls MAYBE_UNIFY_CHAR. */ | |
980 | ||
981 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) \ | |
982 | do { \ | |
983 | if ((c) <= MAX_1_BYTE_CHAR) \ | |
984 | *(p)++ = (c); \ | |
985 | else if ((c) <= MAX_2_BYTE_CHAR) \ | |
986 | *(p)++ = (0xC0 | ((c) >> 6)), \ | |
987 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
988 | else if ((c) <= MAX_3_BYTE_CHAR) \ | |
989 | *(p)++ = (0xE0 | ((c) >> 12)), \ | |
990 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ | |
991 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
992 | else if ((c) <= MAX_4_BYTE_CHAR) \ | |
993 | *(p)++ = (0xF0 | (c >> 18)), \ | |
994 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
995 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
996 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
997 | else if ((c) <= MAX_5_BYTE_CHAR) \ | |
998 | *(p)++ = 0xF8, \ | |
999 | *(p)++ = (0x80 | ((c >> 18) & 0x0F)), \ | |
1000 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
1001 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
1002 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
1003 | else \ | |
1004 | (p) += BYTE8_STRING ((c) - 0x3FFF80, p); \ | |
1005 | } while (0) | |
1006 | ||
1007 | ||
1008 | /* Return the character code of character whose multibyte form is at | |
1009 | P, and advance P to the end of the multibyte form. This is like | |
1010 | STRING_CHAR_ADVANCE, but it never calls MAYBE_UNIFY_CHAR. */ | |
1011 | ||
1012 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) \ | |
1013 | (!((p)[0] & 0x80) \ | |
1014 | ? *(p)++ \ | |
1015 | : ! ((p)[0] & 0x20) \ | |
1016 | ? ((p) += 2, \ | |
1017 | ((((p)[-2] & 0x1F) << 6) \ | |
1018 | | ((p)[-1] & 0x3F) \ | |
1019 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
1020 | : ! ((p)[0] & 0x10) \ | |
1021 | ? ((p) += 3, \ | |
1022 | ((((p)[-3] & 0x0F) << 12) \ | |
1023 | | (((p)[-2] & 0x3F) << 6) \ | |
1024 | | ((p)[-1] & 0x3F))) \ | |
1025 | : ! ((p)[0] & 0x08) \ | |
1026 | ? ((p) += 4, \ | |
1027 | ((((p)[-4] & 0xF) << 18) \ | |
1028 | | (((p)[-3] & 0x3F) << 12) \ | |
1029 | | (((p)[-2] & 0x3F) << 6) \ | |
1030 | | ((p)[-1] & 0x3F))) \ | |
1031 | : ((p) += 5, \ | |
1032 | ((((p)[-4] & 0x3F) << 18) \ | |
1033 | | (((p)[-3] & 0x3F) << 12) \ | |
1034 | | (((p)[-2] & 0x3F) << 6) \ | |
1035 | | ((p)[-1] & 0x3F)))) | |
1036 | ||
aa72b389 | 1037 | |
df7492f9 | 1038 | static void |
971de7fb | 1039 | coding_set_source (struct coding_system *coding) |
aa72b389 | 1040 | { |
df7492f9 KH |
1041 | if (BUFFERP (coding->src_object)) |
1042 | { | |
2cb26057 | 1043 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 1044 | |
df7492f9 | 1045 | if (coding->src_pos < 0) |
2cb26057 | 1046 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 1047 | else |
2cb26057 | 1048 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 1049 | } |
df7492f9 | 1050 | else if (STRINGP (coding->src_object)) |
aa72b389 | 1051 | { |
8f924df7 | 1052 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 1053 | } |
df7492f9 KH |
1054 | else |
1055 | /* Otherwise, the source is C string and is never relocated | |
1056 | automatically. Thus we don't have to update anything. */ | |
1057 | ; | |
1058 | } | |
aa72b389 | 1059 | |
df7492f9 | 1060 | static void |
971de7fb | 1061 | coding_set_destination (struct coding_system *coding) |
df7492f9 KH |
1062 | { |
1063 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 1064 | { |
df7492f9 | 1065 | if (coding->src_pos < 0) |
aa72b389 | 1066 | { |
13818c30 | 1067 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
1068 | coding->dst_bytes = (GAP_END_ADDR |
1069 | - (coding->src_bytes - coding->consumed) | |
1070 | - coding->destination); | |
aa72b389 | 1071 | } |
df7492f9 | 1072 | else |
28f67a95 KH |
1073 | { |
1074 | /* We are sure that coding->dst_pos_byte is before the gap | |
1075 | of the buffer. */ | |
1076 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 1077 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
1078 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
1079 | - coding->destination); | |
1080 | } | |
df7492f9 KH |
1081 | } |
1082 | else | |
1083 | /* Otherwise, the destination is C string and is never relocated | |
1084 | automatically. Thus we don't have to update anything. */ | |
1085 | ; | |
1086 | } | |
1087 | ||
1088 | ||
1089 | static void | |
971de7fb | 1090 | coding_alloc_by_realloc (struct coding_system *coding, EMACS_INT bytes) |
df7492f9 KH |
1091 | { |
1092 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
1093 | coding->dst_bytes + bytes); | |
1094 | coding->dst_bytes += bytes; | |
1095 | } | |
1096 | ||
1097 | static void | |
cf84bb53 JB |
1098 | coding_alloc_by_making_gap (struct coding_system *coding, |
1099 | EMACS_INT gap_head_used, EMACS_INT bytes) | |
df7492f9 | 1100 | { |
db274c7a | 1101 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1102 | { |
db274c7a KH |
1103 | /* The gap may contain the produced data at the head and not-yet |
1104 | consumed data at the tail. To preserve those data, we at | |
1105 | first make the gap size to zero, then increase the gap | |
1106 | size. */ | |
1107 | EMACS_INT add = GAP_SIZE; | |
1108 | ||
1109 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1110 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1111 | make_gap (bytes); |
1112 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1113 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1114 | } |
730fff51 | 1115 | else |
df7492f9 | 1116 | { |
2c78b7e1 KH |
1117 | Lisp_Object this_buffer; |
1118 | ||
1119 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1120 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1121 | make_gap (bytes); | |
1122 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1123 | } |
df7492f9 | 1124 | } |
8f924df7 | 1125 | |
df7492f9 KH |
1126 | |
1127 | static unsigned char * | |
cf84bb53 JB |
1128 | alloc_destination (struct coding_system *coding, EMACS_INT nbytes, |
1129 | unsigned char *dst) | |
df7492f9 KH |
1130 | { |
1131 | EMACS_INT offset = dst - coding->destination; | |
1132 | ||
1133 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1134 | { |
1135 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1136 | ||
1137 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1138 | } | |
aa72b389 | 1139 | else |
df7492f9 | 1140 | coding_alloc_by_realloc (coding, nbytes); |
df7492f9 KH |
1141 | coding_set_destination (coding); |
1142 | dst = coding->destination + offset; | |
1143 | return dst; | |
1144 | } | |
aa72b389 | 1145 | |
ff0dacd7 KH |
1146 | /** Macros for annotations. */ |
1147 | ||
ff0dacd7 KH |
1148 | /* An annotation data is stored in the array coding->charbuf in this |
1149 | format: | |
69a80ea3 | 1150 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1151 | LENGTH is the number of elements in the annotation. |
1152 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1153 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1154 | |
1155 | The format of the following elements depend on ANNOTATION_MASK. | |
1156 | ||
1157 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1158 | follows: | |
e951386e KH |
1159 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
1160 | ||
1161 | NBYTES is the number of bytes specified in the header part of | |
1162 | old-style emacs-mule encoding, or 0 for the other kind of | |
1163 | composition. | |
1164 | ||
ff0dacd7 | 1165 | METHOD is one of enum composition_method. |
e951386e | 1166 | |
ad1746f5 | 1167 | Optional COMPOSITION-COMPONENTS are characters and composition |
ff0dacd7 KH |
1168 | rules. |
1169 | ||
1170 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
e951386e KH |
1171 | follows. |
1172 | ||
1173 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | |
1174 | recover from an invalid annotation, and should be skipped by | |
1175 | produce_annotation. */ | |
1176 | ||
1177 | /* Maximum length of the header of annotation data. */ | |
1178 | #define MAX_ANNOTATION_LENGTH 5 | |
ff0dacd7 | 1179 | |
69a80ea3 | 1180 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1181 | do { \ |
1182 | *(buf)++ = -(len); \ | |
1183 | *(buf)++ = (mask); \ | |
69a80ea3 | 1184 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1185 | coding->annotated = 1; \ |
1186 | } while (0); | |
1187 | ||
e951386e | 1188 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
69a80ea3 | 1189 | do { \ |
e951386e KH |
1190 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
1191 | *buf++ = nbytes; \ | |
69a80ea3 | 1192 | *buf++ = method; \ |
ff0dacd7 KH |
1193 | } while (0) |
1194 | ||
1195 | ||
69a80ea3 KH |
1196 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1197 | do { \ | |
1198 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1199 | *buf++ = id; \ | |
ff0dacd7 KH |
1200 | } while (0) |
1201 | ||
df7492f9 KH |
1202 | \f |
1203 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1204 | ||
1205 | ||
1206 | ||
1207 | \f | |
1208 | /*** 3. UTF-8 ***/ | |
1209 | ||
1210 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1211 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1212 | return 0. */ | |
df7492f9 KH |
1213 | |
1214 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1215 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1216 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1217 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1218 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1219 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1220 | ||
a470d443 KH |
1221 | #define UTF_BOM 0xFEFF |
1222 | #define UTF_8_BOM_1 0xEF | |
1223 | #define UTF_8_BOM_2 0xBB | |
1224 | #define UTF_8_BOM_3 0xBF | |
1225 | ||
df7492f9 | 1226 | static int |
cf84bb53 JB |
1227 | detect_coding_utf_8 (struct coding_system *coding, |
1228 | struct coding_detection_info *detect_info) | |
df7492f9 | 1229 | { |
065e3595 | 1230 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1231 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1232 | int multibytep = coding->src_multibyte; |
1233 | int consumed_chars = 0; | |
a470d443 | 1234 | int bom_found = 0; |
df7492f9 KH |
1235 | int found = 0; |
1236 | ||
ff0dacd7 | 1237 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1238 | /* A coding system of this category is always ASCII compatible. */ |
1239 | src += coding->head_ascii; | |
1240 | ||
1241 | while (1) | |
aa72b389 | 1242 | { |
df7492f9 | 1243 | int c, c1, c2, c3, c4; |
aa72b389 | 1244 | |
065e3595 | 1245 | src_base = src; |
df7492f9 | 1246 | ONE_MORE_BYTE (c); |
065e3595 | 1247 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1248 | continue; |
1249 | ONE_MORE_BYTE (c1); | |
065e3595 | 1250 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1251 | break; |
1252 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1253 | { |
a470d443 | 1254 | found = 1; |
df7492f9 | 1255 | continue; |
aa72b389 | 1256 | } |
df7492f9 | 1257 | ONE_MORE_BYTE (c2); |
065e3595 | 1258 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1259 | break; |
1260 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1261 | { |
a470d443 KH |
1262 | found = 1; |
1263 | if (src_base == coding->source | |
1264 | && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3) | |
1265 | bom_found = 1; | |
df7492f9 | 1266 | continue; |
aa72b389 | 1267 | } |
df7492f9 | 1268 | ONE_MORE_BYTE (c3); |
065e3595 | 1269 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1270 | break; |
1271 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1272 | { |
a470d443 | 1273 | found = 1; |
df7492f9 KH |
1274 | continue; |
1275 | } | |
1276 | ONE_MORE_BYTE (c4); | |
065e3595 | 1277 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1278 | break; |
1279 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1280 | { | |
a470d443 | 1281 | found = 1; |
df7492f9 KH |
1282 | continue; |
1283 | } | |
1284 | break; | |
aa72b389 | 1285 | } |
ff0dacd7 | 1286 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1287 | return 0; |
aa72b389 | 1288 | |
df7492f9 | 1289 | no_more_source: |
065e3595 | 1290 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1291 | { |
ff0dacd7 | 1292 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1293 | return 0; |
aa72b389 | 1294 | } |
a470d443 KH |
1295 | if (bom_found) |
1296 | { | |
1297 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
1298 | detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; | |
1299 | } | |
1300 | else | |
1301 | { | |
1302 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
0e17387a KH |
1303 | if (found) |
1304 | detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1305 | } |
ff0dacd7 | 1306 | return 1; |
aa72b389 KH |
1307 | } |
1308 | ||
4ed46869 | 1309 | |
b73bfc1c | 1310 | static void |
971de7fb | 1311 | decode_coding_utf_8 (struct coding_system *coding) |
b73bfc1c | 1312 | { |
8f924df7 KH |
1313 | const unsigned char *src = coding->source + coding->consumed; |
1314 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1315 | const unsigned char *src_base; | |
69a80ea3 KH |
1316 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1317 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
453b38f0 | 1318 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1319 | int multibytep = coding->src_multibyte; |
a470d443 | 1320 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
24a73b0a | 1321 | Lisp_Object attr, charset_list; |
0a9564cb EZ |
1322 | int eol_crlf = |
1323 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1324 | int byte_after_cr = -1; |
4ed46869 | 1325 | |
24a73b0a | 1326 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1327 | |
a470d443 KH |
1328 | if (bom != utf_without_bom) |
1329 | { | |
1330 | int c1, c2, c3; | |
1331 | ||
1332 | src_base = src; | |
1333 | ONE_MORE_BYTE (c1); | |
1334 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1335 | src = src_base; | |
1336 | else | |
1337 | { | |
159bd5a2 | 1338 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1339 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1340 | src = src_base; | |
1341 | else | |
1342 | { | |
159bd5a2 | 1343 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1344 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1345 | src = src_base; | |
1346 | else | |
1347 | { | |
1348 | if ((c1 != UTF_8_BOM_1) | |
1349 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1350 | src = src_base; | |
1351 | else | |
1352 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1353 | } | |
1354 | } | |
1355 | } | |
1356 | } | |
1357 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1358 | ||
df7492f9 | 1359 | while (1) |
b73bfc1c | 1360 | { |
df7492f9 | 1361 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1362 | |
df7492f9 KH |
1363 | src_base = src; |
1364 | consumed_chars_base = consumed_chars; | |
4af310db | 1365 | |
df7492f9 | 1366 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1367 | { |
1368 | if (byte_after_cr >= 0) | |
1369 | src_base--; | |
1370 | break; | |
1371 | } | |
df7492f9 | 1372 | |
119852e7 KH |
1373 | if (byte_after_cr >= 0) |
1374 | c1 = byte_after_cr, byte_after_cr = -1; | |
1375 | else | |
1376 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1377 | if (c1 < 0) |
1378 | { | |
1379 | c = - c1; | |
1380 | } | |
1a4990fb | 1381 | else if (UTF_8_1_OCTET_P (c1)) |
df7492f9 | 1382 | { |
119852e7 KH |
1383 | if (eol_crlf && c1 == '\r') |
1384 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 | 1385 | c = c1; |
4af310db | 1386 | } |
df7492f9 | 1387 | else |
4af310db | 1388 | { |
df7492f9 | 1389 | ONE_MORE_BYTE (c2); |
065e3595 | 1390 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1391 | goto invalid_code; |
1392 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1393 | { |
b0edb2c5 DL |
1394 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1395 | /* Reject overlong sequences here and below. Encoders | |
1396 | producing them are incorrect, they can be misleading, | |
1397 | and they mess up read/write invariance. */ | |
1398 | if (c < 128) | |
1399 | goto invalid_code; | |
4af310db | 1400 | } |
df7492f9 | 1401 | else |
aa72b389 | 1402 | { |
df7492f9 | 1403 | ONE_MORE_BYTE (c3); |
065e3595 | 1404 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1405 | goto invalid_code; |
1406 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1407 | { |
1408 | c = (((c1 & 0xF) << 12) | |
1409 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1410 | if (c < 0x800 |
1411 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1412 | goto invalid_code; |
1413 | } | |
df7492f9 KH |
1414 | else |
1415 | { | |
1416 | ONE_MORE_BYTE (c4); | |
065e3595 | 1417 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1418 | goto invalid_code; |
1419 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1420 | { |
df7492f9 KH |
1421 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1422 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1423 | if (c < 0x10000) |
1424 | goto invalid_code; | |
1425 | } | |
df7492f9 KH |
1426 | else |
1427 | { | |
1428 | ONE_MORE_BYTE (c5); | |
065e3595 | 1429 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1430 | goto invalid_code; |
1431 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1432 | { | |
1433 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1434 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1435 | | (c5 & 0x3F)); | |
b0edb2c5 | 1436 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1437 | goto invalid_code; |
1438 | } | |
1439 | else | |
1440 | goto invalid_code; | |
1441 | } | |
1442 | } | |
aa72b389 | 1443 | } |
b73bfc1c | 1444 | } |
df7492f9 KH |
1445 | |
1446 | *charbuf++ = c; | |
1447 | continue; | |
1448 | ||
1449 | invalid_code: | |
1450 | src = src_base; | |
1451 | consumed_chars = consumed_chars_base; | |
1452 | ONE_MORE_BYTE (c); | |
1453 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1454 | coding->errors++; | |
aa72b389 KH |
1455 | } |
1456 | ||
df7492f9 KH |
1457 | no_more_source: |
1458 | coding->consumed_char += consumed_chars_base; | |
1459 | coding->consumed = src_base - coding->source; | |
1460 | coding->charbuf_used = charbuf - coding->charbuf; | |
1461 | } | |
1462 | ||
1463 | ||
1464 | static int | |
971de7fb | 1465 | encode_coding_utf_8 (struct coding_system *coding) |
df7492f9 KH |
1466 | { |
1467 | int multibytep = coding->dst_multibyte; | |
1468 | int *charbuf = coding->charbuf; | |
1469 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1470 | unsigned char *dst = coding->destination + coding->produced; | |
1471 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1472 | int produced_chars = 0; |
df7492f9 KH |
1473 | int c; |
1474 | ||
a470d443 KH |
1475 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1476 | { | |
1477 | ASSURE_DESTINATION (3); | |
1478 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1479 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1480 | } | |
1481 | ||
df7492f9 | 1482 | if (multibytep) |
aa72b389 | 1483 | { |
df7492f9 KH |
1484 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1485 | ||
1486 | while (charbuf < charbuf_end) | |
b73bfc1c | 1487 | { |
df7492f9 | 1488 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1489 | |
df7492f9 KH |
1490 | ASSURE_DESTINATION (safe_room); |
1491 | c = *charbuf++; | |
28f67a95 KH |
1492 | if (CHAR_BYTE8_P (c)) |
1493 | { | |
1494 | c = CHAR_TO_BYTE8 (c); | |
1495 | EMIT_ONE_BYTE (c); | |
1496 | } | |
1497 | else | |
1498 | { | |
db274c7a | 1499 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1500 | for (p = str; p < pend; p++) |
1501 | EMIT_ONE_BYTE (*p); | |
1502 | } | |
b73bfc1c | 1503 | } |
aa72b389 | 1504 | } |
df7492f9 KH |
1505 | else |
1506 | { | |
1507 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1508 | ||
1509 | while (charbuf < charbuf_end) | |
b73bfc1c | 1510 | { |
df7492f9 KH |
1511 | ASSURE_DESTINATION (safe_room); |
1512 | c = *charbuf++; | |
f03caae0 KH |
1513 | if (CHAR_BYTE8_P (c)) |
1514 | *dst++ = CHAR_TO_BYTE8 (c); | |
1515 | else | |
db274c7a | 1516 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1517 | produced_chars++; |
4ed46869 KH |
1518 | } |
1519 | } | |
065e3595 | 1520 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1521 | coding->produced_char += produced_chars; |
1522 | coding->produced = dst - coding->destination; | |
1523 | return 0; | |
4ed46869 KH |
1524 | } |
1525 | ||
b73bfc1c | 1526 | |
df7492f9 | 1527 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1528 | Check if a text is encoded in one of UTF-16 based coding systems. |
1529 | If it is, return 1, else return 0. */ | |
aa72b389 | 1530 | |
df7492f9 KH |
1531 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1532 | (((val) & 0xFC00) == 0xD800) | |
1533 | ||
1534 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1535 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1536 | |
df7492f9 KH |
1537 | #define UTF_16_INVALID_P(val) \ |
1538 | (((val) == 0xFFFE) \ | |
1539 | || ((val) == 0xFFFF) \ | |
1540 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1541 | |
aa72b389 | 1542 | |
df7492f9 | 1543 | static int |
cf84bb53 JB |
1544 | detect_coding_utf_16 (struct coding_system *coding, |
1545 | struct coding_detection_info *detect_info) | |
aa72b389 | 1546 | { |
ef1b0ba7 | 1547 | const unsigned char *src = coding->source; |
8f924df7 | 1548 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 | 1549 | int multibytep = coding->src_multibyte; |
df7492f9 | 1550 | int c1, c2; |
aa72b389 | 1551 | |
ff0dacd7 | 1552 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1553 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1554 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1555 | { |
1556 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1557 | return 0; | |
1558 | } | |
24a73b0a | 1559 | |
f56a4450 | 1560 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1561 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1562 | { |
b49a1807 KH |
1563 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1564 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1565 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1566 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1567 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1568 | } |
df7492f9 | 1569 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1570 | { |
b49a1807 KH |
1571 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1572 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1573 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1574 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1575 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1576 | } | |
220eeac9 | 1577 | else if (c2 < 0) |
f56a4450 KH |
1578 | { |
1579 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1580 | return 0; | |
1581 | } | |
2f3cbb32 | 1582 | else |
24a73b0a | 1583 | { |
2f3cbb32 KH |
1584 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1585 | O is odd. If both are high, we assume binary data.*/ | |
1586 | unsigned char e[256], o[256]; | |
1587 | unsigned e_num = 1, o_num = 1; | |
1588 | ||
1589 | memset (e, 0, 256); | |
1590 | memset (o, 0, 256); | |
1591 | e[c1] = 1; | |
1592 | o[c2] = 1; | |
1593 | ||
cc13543e KH |
1594 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO |
1595 | |CATEGORY_MASK_UTF_16_BE | |
1596 | | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 | 1597 | |
7f1faf1c KH |
1598 | while ((detect_info->rejected & CATEGORY_MASK_UTF_16) |
1599 | != CATEGORY_MASK_UTF_16) | |
2f3cbb32 | 1600 | { |
f56a4450 | 1601 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1602 | if (c2 < 0) |
f56a4450 | 1603 | break; |
2f3cbb32 KH |
1604 | if (! e[c1]) |
1605 | { | |
1606 | e[c1] = 1; | |
1607 | e_num++; | |
cc13543e KH |
1608 | if (e_num >= 128) |
1609 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
2f3cbb32 KH |
1610 | } |
1611 | if (! o[c2]) | |
1612 | { | |
977b85f4 | 1613 | o[c2] = 1; |
2f3cbb32 | 1614 | o_num++; |
cc13543e KH |
1615 | if (o_num >= 128) |
1616 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
2f3cbb32 KH |
1617 | } |
1618 | } | |
2f3cbb32 | 1619 | return 0; |
ff0dacd7 | 1620 | } |
2f3cbb32 | 1621 | |
df7492f9 | 1622 | no_more_source: |
ff0dacd7 | 1623 | return 1; |
df7492f9 | 1624 | } |
aa72b389 | 1625 | |
df7492f9 | 1626 | static void |
971de7fb | 1627 | decode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1628 | { |
8f924df7 KH |
1629 | const unsigned char *src = coding->source + coding->consumed; |
1630 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1631 | const unsigned char *src_base; | |
69a80ea3 | 1632 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
1633 | /* We may produces at most 3 chars in one loop. */ |
1634 | int *charbuf_end = coding->charbuf + coding->charbuf_size - 2; | |
3a8406e1 | 1635 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1636 | int multibytep = coding->src_multibyte; |
a470d443 | 1637 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1638 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1639 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1640 | Lisp_Object attr, charset_list; |
0a9564cb EZ |
1641 | int eol_crlf = |
1642 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1643 | int byte_after_cr1 = -1, byte_after_cr2 = -1; |
df7492f9 | 1644 | |
24a73b0a | 1645 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1646 | |
a470d443 | 1647 | if (bom == utf_with_bom) |
aa72b389 | 1648 | { |
df7492f9 | 1649 | int c, c1, c2; |
4af310db | 1650 | |
aa72b389 | 1651 | src_base = src; |
df7492f9 KH |
1652 | ONE_MORE_BYTE (c1); |
1653 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1654 | c = (c1 << 8) | c2; |
aa72b389 | 1655 | |
b49a1807 KH |
1656 | if (endian == utf_16_big_endian |
1657 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1658 | { |
b49a1807 KH |
1659 | /* The first two bytes are not BOM. Treat them as bytes |
1660 | for a normal character. */ | |
1661 | src = src_base; | |
1662 | coding->errors++; | |
aa72b389 | 1663 | } |
a470d443 | 1664 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1665 | } |
a470d443 | 1666 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1667 | { |
1668 | /* We have already tried to detect BOM and failed in | |
1669 | detect_coding. */ | |
a470d443 | 1670 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1671 | } |
aa72b389 | 1672 | |
df7492f9 KH |
1673 | while (1) |
1674 | { | |
1675 | int c, c1, c2; | |
1676 | ||
1677 | src_base = src; | |
1678 | consumed_chars_base = consumed_chars; | |
1679 | ||
df80c7f0 | 1680 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1681 | { |
1682 | if (byte_after_cr1 >= 0) | |
1683 | src_base -= 2; | |
1684 | break; | |
1685 | } | |
df7492f9 | 1686 | |
119852e7 KH |
1687 | if (byte_after_cr1 >= 0) |
1688 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1689 | else | |
1690 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1691 | if (c1 < 0) |
1692 | { | |
1693 | *charbuf++ = -c1; | |
1694 | continue; | |
1695 | } | |
119852e7 KH |
1696 | if (byte_after_cr2 >= 0) |
1697 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1698 | else | |
1699 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1700 | if (c2 < 0) |
1701 | { | |
1702 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1703 | *charbuf++ = -c2; | |
1704 | continue; | |
1705 | } | |
df7492f9 | 1706 | c = (endian == utf_16_big_endian |
e19c3639 | 1707 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1708 | |
df7492f9 | 1709 | if (surrogate) |
fd3ae0b9 | 1710 | { |
df7492f9 | 1711 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1712 | { |
df7492f9 KH |
1713 | if (endian == utf_16_big_endian) |
1714 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1715 | else | |
1716 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1717 | *charbuf++ = c1; | |
1718 | *charbuf++ = c2; | |
1719 | coding->errors++; | |
1720 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1721 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1722 | else |
df7492f9 | 1723 | *charbuf++ = c; |
fd3ae0b9 KH |
1724 | } |
1725 | else | |
df7492f9 KH |
1726 | { |
1727 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1728 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1729 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1730 | } |
fd3ae0b9 | 1731 | } |
aa72b389 | 1732 | else |
df7492f9 KH |
1733 | { |
1734 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1735 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1736 | else | |
119852e7 KH |
1737 | { |
1738 | if (eol_crlf && c == '\r') | |
1739 | { | |
1740 | ONE_MORE_BYTE (byte_after_cr1); | |
1741 | ONE_MORE_BYTE (byte_after_cr2); | |
1742 | } | |
1743 | *charbuf++ = c; | |
1744 | } | |
8f924df7 | 1745 | } |
aa72b389 | 1746 | } |
df7492f9 KH |
1747 | |
1748 | no_more_source: | |
1749 | coding->consumed_char += consumed_chars_base; | |
1750 | coding->consumed = src_base - coding->source; | |
1751 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1752 | } |
b73bfc1c | 1753 | |
df7492f9 | 1754 | static int |
971de7fb | 1755 | encode_coding_utf_16 (struct coding_system *coding) |
df7492f9 KH |
1756 | { |
1757 | int multibytep = coding->dst_multibyte; | |
1758 | int *charbuf = coding->charbuf; | |
1759 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1760 | unsigned char *dst = coding->destination + coding->produced; | |
1761 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1762 | int safe_room = 8; | |
a470d443 | 1763 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1764 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
1765 | int produced_chars = 0; | |
24a73b0a | 1766 | Lisp_Object attrs, charset_list; |
df7492f9 | 1767 | int c; |
4ed46869 | 1768 | |
24a73b0a | 1769 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1770 | |
a470d443 | 1771 | if (bom != utf_without_bom) |
df7492f9 KH |
1772 | { |
1773 | ASSURE_DESTINATION (safe_room); | |
1774 | if (big_endian) | |
df7492f9 | 1775 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1776 | else |
1777 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1778 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1779 | } |
1780 | ||
1781 | while (charbuf < charbuf_end) | |
1782 | { | |
1783 | ASSURE_DESTINATION (safe_room); | |
1784 | c = *charbuf++; | |
60afa08d | 1785 | if (c > MAX_UNICODE_CHAR) |
e19c3639 | 1786 | c = coding->default_char; |
df7492f9 KH |
1787 | |
1788 | if (c < 0x10000) | |
1789 | { | |
1790 | if (big_endian) | |
1791 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1792 | else | |
1793 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1794 | } | |
1795 | else | |
1796 | { | |
1797 | int c1, c2; | |
1798 | ||
1799 | c -= 0x10000; | |
1800 | c1 = (c >> 10) + 0xD800; | |
1801 | c2 = (c & 0x3FF) + 0xDC00; | |
1802 | if (big_endian) | |
1803 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1804 | else | |
1805 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1806 | } | |
1807 | } | |
065e3595 | 1808 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1809 | coding->produced = dst - coding->destination; |
1810 | coding->produced_char += produced_chars; | |
1811 | return 0; | |
1812 | } | |
1813 | ||
1814 | \f | |
1815 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1816 | ||
1817 | /* Emacs' internal format for representation of multiple character | |
1818 | sets is a kind of multi-byte encoding, i.e. characters are | |
1819 | represented by variable-length sequences of one-byte codes. | |
1820 | ||
1821 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1822 | represented by one-byte sequences which are their ASCII codes, in | |
1823 | the range 0x00 through 0x7F. | |
1824 | ||
1825 | 8-bit characters of the range 0x80..0x9F are represented by | |
1826 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1827 | code + 0x20). | |
1828 | ||
1829 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1830 | one-byte sequences which are their 8-bit code. | |
1831 | ||
1832 | The other characters are represented by a sequence of `base | |
1833 | leading-code', optional `extended leading-code', and one or two | |
1834 | `position-code's. The length of the sequence is determined by the | |
1835 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1836 | whereas extended leading-code and position-code take the range 0xA0 | |
1837 | through 0xFF. See `charset.h' for more details about leading-code | |
1838 | and position-code. | |
1839 | ||
1840 | --- CODE RANGE of Emacs' internal format --- | |
1841 | character set range | |
1842 | ------------- ----- | |
1843 | ascii 0x00..0x7F | |
1844 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1845 | eight-bit-graphic 0xA0..0xBF | |
1846 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1847 | --------------------------------------------- | |
1848 | ||
1849 | As this is the internal character representation, the format is | |
1850 | usually not used externally (i.e. in a file or in a data sent to a | |
1851 | process). But, it is possible to have a text externally in this | |
1852 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1853 | ||
1854 | In that case, a sequence of one-byte codes has a slightly different | |
1855 | form. | |
1856 | ||
1857 | At first, all characters in eight-bit-control are represented by | |
1858 | one-byte sequences which are their 8-bit code. | |
1859 | ||
1860 | Next, character composition data are represented by the byte | |
1861 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1862 | where, | |
e951386e | 1863 | METHOD is 0xF2 plus one of composition method (enum |
df7492f9 KH |
1864 | composition_method), |
1865 | ||
1866 | BYTES is 0xA0 plus a byte length of this composition data, | |
1867 | ||
e951386e | 1868 | CHARS is 0xA0 plus a number of characters composed by this |
df7492f9 KH |
1869 | data, |
1870 | ||
ad1746f5 | 1871 | COMPONENTs are characters of multibyte form or composition |
df7492f9 KH |
1872 | rules encoded by two-byte of ASCII codes. |
1873 | ||
1874 | In addition, for backward compatibility, the following formats are | |
1875 | also recognized as composition data on decoding. | |
1876 | ||
1877 | 0x80 MSEQ ... | |
1878 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1879 | ||
1880 | Here, | |
1881 | MSEQ is a multibyte form but in these special format: | |
1882 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1883 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1884 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1885 | represents a composition rule. | |
1886 | */ | |
1887 | ||
1888 | char emacs_mule_bytes[256]; | |
1889 | ||
e951386e KH |
1890 | |
1891 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
1892 | Check if a text is encoded in `emacs-mule'. If it is, return 1, | |
1893 | else return 0. */ | |
1894 | ||
1895 | static int | |
cf84bb53 JB |
1896 | detect_coding_emacs_mule (struct coding_system *coding, |
1897 | struct coding_detection_info *detect_info) | |
e951386e KH |
1898 | { |
1899 | const unsigned char *src = coding->source, *src_base; | |
1900 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1901 | int multibytep = coding->src_multibyte; | |
1902 | int consumed_chars = 0; | |
1903 | int c; | |
1904 | int found = 0; | |
1905 | ||
1906 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | |
1907 | /* A coding system of this category is always ASCII compatible. */ | |
1908 | src += coding->head_ascii; | |
1909 | ||
1910 | while (1) | |
1911 | { | |
1912 | src_base = src; | |
1913 | ONE_MORE_BYTE (c); | |
1914 | if (c < 0) | |
1915 | continue; | |
1916 | if (c == 0x80) | |
1917 | { | |
1918 | /* Perhaps the start of composite character. We simply skip | |
1919 | it because analyzing it is too heavy for detecting. But, | |
1920 | at least, we check that the composite character | |
1921 | constitutes of more than 4 bytes. */ | |
1922 | const unsigned char *src_base; | |
1923 | ||
1924 | repeat: | |
1925 | src_base = src; | |
1926 | do | |
1927 | { | |
1928 | ONE_MORE_BYTE (c); | |
1929 | } | |
1930 | while (c >= 0xA0); | |
1931 | ||
1932 | if (src - src_base <= 4) | |
1933 | break; | |
1934 | found = CATEGORY_MASK_EMACS_MULE; | |
1935 | if (c == 0x80) | |
1936 | goto repeat; | |
1937 | } | |
1938 | ||
1939 | if (c < 0x80) | |
1940 | { | |
1941 | if (c < 0x20 | |
1942 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1943 | break; | |
1944 | } | |
1945 | else | |
1946 | { | |
396475b7 | 1947 | int more_bytes = emacs_mule_bytes[c] - 1; |
e951386e KH |
1948 | |
1949 | while (more_bytes > 0) | |
1950 | { | |
1951 | ONE_MORE_BYTE (c); | |
1952 | if (c < 0xA0) | |
1953 | { | |
1954 | src--; /* Unread the last byte. */ | |
1955 | break; | |
1956 | } | |
1957 | more_bytes--; | |
1958 | } | |
1959 | if (more_bytes != 0) | |
1960 | break; | |
1961 | found = CATEGORY_MASK_EMACS_MULE; | |
1962 | } | |
1963 | } | |
1964 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1965 | return 0; | |
1966 | ||
1967 | no_more_source: | |
1968 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | |
1969 | { | |
1970 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1971 | return 0; | |
1972 | } | |
1973 | detect_info->found |= found; | |
1974 | return 1; | |
1975 | } | |
1976 | ||
1977 | ||
1978 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | |
1979 | character. If CMP_STATUS indicates that we must expect MSEQ or | |
1980 | RULE described above, decode it and return the negative value of | |
685ebdc8 | 1981 | the decoded character or rule. If an invalid byte is found, return |
e951386e KH |
1982 | -1. If SRC is too short, return -2. */ |
1983 | ||
df7492f9 | 1984 | int |
cf84bb53 JB |
1985 | emacs_mule_char (struct coding_system *coding, const unsigned char *src, |
1986 | int *nbytes, int *nchars, int *id, | |
1987 | struct composition_status *cmp_status) | |
df7492f9 | 1988 | { |
8f924df7 KH |
1989 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1990 | const unsigned char *src_base = src; | |
df7492f9 | 1991 | int multibytep = coding->src_multibyte; |
b84ae584 | 1992 | int charset_id; |
df7492f9 KH |
1993 | unsigned code; |
1994 | int c; | |
1995 | int consumed_chars = 0; | |
e951386e | 1996 | int mseq_found = 0; |
df7492f9 KH |
1997 | |
1998 | ONE_MORE_BYTE (c); | |
065e3595 | 1999 | if (c < 0) |
df7492f9 | 2000 | { |
065e3595 | 2001 | c = -c; |
b84ae584 | 2002 | charset_id = emacs_mule_charset[0]; |
065e3595 KH |
2003 | } |
2004 | else | |
2005 | { | |
4d41e8b7 KH |
2006 | if (c >= 0xA0) |
2007 | { | |
e951386e KH |
2008 | if (cmp_status->state != COMPOSING_NO |
2009 | && cmp_status->old_form) | |
4d41e8b7 | 2010 | { |
e951386e KH |
2011 | if (cmp_status->state == COMPOSING_CHAR) |
2012 | { | |
2013 | if (c == 0xA0) | |
2014 | { | |
2015 | ONE_MORE_BYTE (c); | |
2016 | c -= 0x80; | |
2017 | if (c < 0) | |
2018 | goto invalid_code; | |
2019 | } | |
2020 | else | |
2021 | c -= 0x20; | |
2022 | mseq_found = 1; | |
2023 | } | |
2024 | else | |
2025 | { | |
2026 | *nbytes = src - src_base; | |
2027 | *nchars = consumed_chars; | |
2028 | return -c; | |
2029 | } | |
4d41e8b7 KH |
2030 | } |
2031 | else | |
e951386e | 2032 | goto invalid_code; |
4d41e8b7 KH |
2033 | } |
2034 | ||
065e3595 | 2035 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 2036 | { |
065e3595 | 2037 | case 2: |
b84ae584 | 2038 | if ((charset_id = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
2039 | goto invalid_code; |
2040 | ONE_MORE_BYTE (c); | |
9ffd559c | 2041 | if (c < 0xA0) |
065e3595 | 2042 | goto invalid_code; |
df7492f9 | 2043 | code = c & 0x7F; |
065e3595 KH |
2044 | break; |
2045 | ||
2046 | case 3: | |
2047 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
2048 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
2049 | { | |
2050 | ONE_MORE_BYTE (c); | |
b84ae584 | 2051 | if (c < 0xA0 || (charset_id = emacs_mule_charset[c]) < 0) |
065e3595 KH |
2052 | goto invalid_code; |
2053 | ONE_MORE_BYTE (c); | |
9ffd559c | 2054 | if (c < 0xA0) |
065e3595 KH |
2055 | goto invalid_code; |
2056 | code = c & 0x7F; | |
2057 | } | |
2058 | else | |
2059 | { | |
b84ae584 | 2060 | if ((charset_id = emacs_mule_charset[c]) < 0) |
065e3595 KH |
2061 | goto invalid_code; |
2062 | ONE_MORE_BYTE (c); | |
9ffd559c | 2063 | if (c < 0xA0) |
065e3595 KH |
2064 | goto invalid_code; |
2065 | code = (c & 0x7F) << 8; | |
2066 | ONE_MORE_BYTE (c); | |
9ffd559c | 2067 | if (c < 0xA0) |
065e3595 KH |
2068 | goto invalid_code; |
2069 | code |= c & 0x7F; | |
2070 | } | |
2071 | break; | |
2072 | ||
2073 | case 4: | |
2074 | ONE_MORE_BYTE (c); | |
b84ae584 | 2075 | if (c < 0 || (charset_id = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
2076 | goto invalid_code; |
2077 | ONE_MORE_BYTE (c); | |
9ffd559c | 2078 | if (c < 0xA0) |
065e3595 | 2079 | goto invalid_code; |
781d7a48 | 2080 | code = (c & 0x7F) << 8; |
df7492f9 | 2081 | ONE_MORE_BYTE (c); |
9ffd559c | 2082 | if (c < 0xA0) |
065e3595 | 2083 | goto invalid_code; |
df7492f9 | 2084 | code |= c & 0x7F; |
065e3595 | 2085 | break; |
df7492f9 | 2086 | |
065e3595 KH |
2087 | case 1: |
2088 | code = c; | |
b84ae584 | 2089 | charset_id = ASCII_BYTE_P (code) ? charset_ascii : charset_eight_bit; |
065e3595 | 2090 | break; |
df7492f9 | 2091 | |
065e3595 KH |
2092 | default: |
2093 | abort (); | |
2094 | } | |
b84ae584 KH |
2095 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
2096 | CHARSET_FROM_ID (charset_id), code, c); | |
065e3595 KH |
2097 | if (c < 0) |
2098 | goto invalid_code; | |
df7492f9 | 2099 | } |
df7492f9 KH |
2100 | *nbytes = src - src_base; |
2101 | *nchars = consumed_chars; | |
ff0dacd7 | 2102 | if (id) |
b84ae584 | 2103 | *id = charset_id; |
e951386e | 2104 | return (mseq_found ? -c : c); |
df7492f9 KH |
2105 | |
2106 | no_more_source: | |
2107 | return -2; | |
2108 | ||
2109 | invalid_code: | |
2110 | return -1; | |
2111 | } | |
2112 | ||
2113 | ||
e951386e | 2114 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
df7492f9 | 2115 | |
e951386e KH |
2116 | /* Handle these composition sequence ('|': the end of header elements, |
2117 | BYTES and CHARS >= 0xA0): | |
df7492f9 | 2118 | |
e951386e KH |
2119 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
2120 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... | |
2121 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... | |
df7492f9 | 2122 | |
e951386e | 2123 | and these old form: |
1a4990fb | 2124 | |
e951386e KH |
2125 | (4) relative composition: 0x80 | MSEQ ... MSEQ |
2126 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ | |
df7492f9 | 2127 | |
e951386e KH |
2128 | When the starter 0x80 and the following header elements are found, |
2129 | this annotation header is produced. | |
df7492f9 | 2130 | |
e951386e | 2131 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
df7492f9 | 2132 | |
e951386e KH |
2133 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
2134 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). | |
df7492f9 | 2135 | |
e951386e KH |
2136 | Then, upon reading the following elements, these codes are produced |
2137 | until the composition end is found: | |
df7492f9 | 2138 | |
e951386e KH |
2139 | (1) CHAR ... CHAR |
2140 | (2) ALT ... ALT CHAR ... CHAR | |
2141 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR | |
2142 | (4) CHAR ... CHAR | |
2143 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
4ed46869 | 2144 | |
e951386e KH |
2145 | When the composition end is found, LENGTH and NCHARS in the |
2146 | annotation header is updated as below: | |
b73bfc1c | 2147 | |
e951386e KH |
2148 | (1) LENGTH: unchanged, NCHARS: unchanged |
2149 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2150 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2151 | (4) LENGTH: unchanged, NCHARS: number of CHARs | |
2152 | (5) LENGTH: unchanged, NCHARS: number of CHARs | |
df7492f9 | 2153 | |
e951386e KH |
2154 | If an error is found while composing, the annotation header is |
2155 | changed to the original composition header (plus filler -1s) as | |
2156 | below: | |
2157 | ||
2158 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] | |
2159 | (5) [ 0x80 0xFF -1 -1- -1 ] | |
2160 | ||
2161 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
2162 | byte sequence as below: | |
2163 | o the original byte sequence is B: [ B -1 ] | |
2164 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
2165 | ||
2166 | Most of the routines are implemented by macros because many | |
2167 | variables and labels in the caller decode_coding_emacs_mule must be | |
2168 | accessible, and they are usually called just once (thus doesn't | |
2169 | increase the size of compiled object). */ | |
2170 | ||
2171 | /* Decode a composition rule represented by C as a component of | |
2172 | composition sequence of Emacs 20 style. Set RULE to the decoded | |
2173 | rule. */ | |
2174 | ||
2175 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ | |
df7492f9 | 2176 | do { \ |
e951386e KH |
2177 | int gref, nref; \ |
2178 | \ | |
4d41e8b7 | 2179 | c -= 0xA0; \ |
df7492f9 KH |
2180 | if (c < 0 || c >= 81) \ |
2181 | goto invalid_code; \ | |
df7492f9 | 2182 | gref = c / 9, nref = c % 9; \ |
e951386e KH |
2183 | if (gref == 4) gref = 10; \ |
2184 | if (nref == 4) nref = 10; \ | |
2185 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
df7492f9 KH |
2186 | } while (0) |
2187 | ||
2188 | ||
e951386e KH |
2189 | /* Decode a composition rule represented by C and the following byte |
2190 | at SRC as a component of composition sequence of Emacs 21 style. | |
2191 | Set RULE to the decoded rule. */ | |
781d7a48 | 2192 | |
e951386e | 2193 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
781d7a48 KH |
2194 | do { \ |
2195 | int gref, nref; \ | |
e951386e KH |
2196 | \ |
2197 | gref = c - 0x20; \ | |
2198 | if (gref < 0 || gref >= 81) \ | |
781d7a48 | 2199 | goto invalid_code; \ |
e951386e KH |
2200 | ONE_MORE_BYTE (c); \ |
2201 | nref = c - 0x20; \ | |
2202 | if (nref < 0 || nref >= 81) \ | |
781d7a48 | 2203 | goto invalid_code; \ |
e951386e | 2204 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
781d7a48 KH |
2205 | } while (0) |
2206 | ||
2207 | ||
e951386e KH |
2208 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
2209 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | |
2210 | byte length of this composition information, CHARS is the number of | |
2211 | characters composed by this composition. */ | |
2212 | ||
2213 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | |
aa72b389 | 2214 | do { \ |
781d7a48 | 2215 | enum composition_method method = c - 0xF2; \ |
df7492f9 | 2216 | int nbytes, nchars; \ |
e951386e | 2217 | \ |
df7492f9 | 2218 | ONE_MORE_BYTE (c); \ |
065e3595 KH |
2219 | if (c < 0) \ |
2220 | goto invalid_code; \ | |
df7492f9 | 2221 | nbytes = c - 0xA0; \ |
e951386e | 2222 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
df7492f9 KH |
2223 | goto invalid_code; \ |
2224 | ONE_MORE_BYTE (c); \ | |
2225 | nchars = c - 0xA0; \ | |
e951386e KH |
2226 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
2227 | goto invalid_code; \ | |
2228 | cmp_status->old_form = 0; \ | |
2229 | cmp_status->method = method; \ | |
2230 | if (method == COMPOSITION_RELATIVE) \ | |
2231 | cmp_status->state = COMPOSING_CHAR; \ | |
2232 | else \ | |
2233 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ | |
2234 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2235 | cmp_status->nchars = nchars; \ | |
2236 | cmp_status->ncomps = nbytes - 4; \ | |
2237 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ | |
aa72b389 | 2238 | } while (0) |
93dec019 | 2239 | |
aa72b389 | 2240 | |
e951386e KH |
2241 | /* Start of Emacs 20 style format for relative composition. */ |
2242 | ||
2243 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ | |
2244 | do { \ | |
2245 | cmp_status->old_form = 1; \ | |
2246 | cmp_status->method = COMPOSITION_RELATIVE; \ | |
2247 | cmp_status->state = COMPOSING_CHAR; \ | |
2248 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2249 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2250 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
2251 | } while (0) | |
2252 | ||
2253 | ||
2254 | /* Start of Emacs 20 style format for rule-base composition. */ | |
2255 | ||
2256 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | |
2257 | do { \ | |
2258 | cmp_status->old_form = 1; \ | |
2259 | cmp_status->method = COMPOSITION_WITH_RULE; \ | |
2260 | cmp_status->state = COMPOSING_CHAR; \ | |
2261 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2262 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2263 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
df7492f9 KH |
2264 | } while (0) |
2265 | ||
2266 | ||
e951386e KH |
2267 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ |
2268 | do { \ | |
2269 | const unsigned char *current_src = src; \ | |
2270 | \ | |
2271 | ONE_MORE_BYTE (c); \ | |
2272 | if (c < 0) \ | |
2273 | goto invalid_code; \ | |
2274 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | |
2275 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | |
2276 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | |
2277 | else if (c < 0xA0) \ | |
2278 | goto invalid_code; \ | |
2279 | else if (c < 0xC0) \ | |
2280 | { \ | |
2281 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | |
2282 | /* Re-read C as a composition component. */ \ | |
2283 | src = current_src; \ | |
2284 | } \ | |
2285 | else if (c == 0xFF) \ | |
2286 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | |
2287 | else \ | |
2288 | goto invalid_code; \ | |
2289 | } while (0) | |
2290 | ||
2291 | #define EMACS_MULE_COMPOSITION_END() \ | |
df7492f9 | 2292 | do { \ |
e951386e | 2293 | int idx = - cmp_status->length; \ |
4d41e8b7 | 2294 | \ |
e951386e KH |
2295 | if (cmp_status->old_form) \ |
2296 | charbuf[idx + 2] = cmp_status->nchars; \ | |
2297 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ | |
2298 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ | |
2299 | cmp_status->state = COMPOSING_NO; \ | |
2300 | } while (0) | |
2301 | ||
2302 | ||
2303 | static int | |
cf84bb53 JB |
2304 | emacs_mule_finish_composition (int *charbuf, |
2305 | struct composition_status *cmp_status) | |
e951386e KH |
2306 | { |
2307 | int idx = - cmp_status->length; | |
2308 | int new_chars; | |
2309 | ||
2310 | if (cmp_status->old_form && cmp_status->nchars > 0) | |
2311 | { | |
2312 | charbuf[idx + 2] = cmp_status->nchars; | |
2313 | new_chars = 0; | |
2314 | if (cmp_status->method == COMPOSITION_WITH_RULE | |
2315 | && cmp_status->state == COMPOSING_CHAR) | |
2316 | { | |
2317 | /* The last rule was invalid. */ | |
2318 | int rule = charbuf[-1] + 0xA0; | |
2319 | ||
2320 | charbuf[-2] = BYTE8_TO_CHAR (rule); | |
2321 | charbuf[-1] = -1; | |
2322 | new_chars = 1; | |
2323 | } | |
2324 | } | |
2325 | else | |
2326 | { | |
2327 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | |
2328 | ||
2329 | if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2330 | { | |
2331 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | |
2332 | charbuf[idx++] = -3; | |
2333 | charbuf[idx++] = 0; | |
2334 | new_chars = 1; | |
2335 | } | |
2336 | else | |
2337 | { | |
2338 | int nchars = charbuf[idx + 1] + 0xA0; | |
2339 | int nbytes = charbuf[idx + 2] + 0xA0; | |
2340 | ||
2341 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | |
2342 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | |
2343 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | |
2344 | charbuf[idx++] = -1; | |
2345 | new_chars = 4; | |
2346 | } | |
2347 | } | |
2348 | cmp_status->state = COMPOSING_NO; | |
2349 | return new_chars; | |
2350 | } | |
2351 | ||
2352 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | |
2353 | do { \ | |
2354 | if (cmp_status->state != COMPOSING_NO) \ | |
2355 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | |
df7492f9 KH |
2356 | } while (0) |
2357 | ||
aa72b389 KH |
2358 | |
2359 | static void | |
971de7fb | 2360 | decode_coding_emacs_mule (struct coding_system *coding) |
aa72b389 | 2361 | { |
8f924df7 KH |
2362 | const unsigned char *src = coding->source + coding->consumed; |
2363 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2364 | const unsigned char *src_base; | |
69a80ea3 | 2365 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
2366 | /* We may produce two annotations (charset and composition) in one |
2367 | loop and one more charset annotation at the end. */ | |
69a80ea3 | 2368 | int *charbuf_end |
df80c7f0 | 2369 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
df7492f9 | 2370 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2371 | int multibytep = coding->src_multibyte; |
24a73b0a | 2372 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2373 | int char_offset = coding->produced_char; |
2374 | int last_offset = char_offset; | |
2375 | int last_id = charset_ascii; | |
0a9564cb EZ |
2376 | int eol_crlf = |
2377 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 2378 | int byte_after_cr = -1; |
e951386e | 2379 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; |
aa72b389 | 2380 | |
24a73b0a | 2381 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2382 | |
e951386e KH |
2383 | if (cmp_status->state != COMPOSING_NO) |
2384 | { | |
2385 | int i; | |
2386 | ||
2387 | for (i = 0; i < cmp_status->length; i++) | |
2388 | *charbuf++ = cmp_status->carryover[i]; | |
2389 | coding->annotated = 1; | |
2390 | } | |
2391 | ||
aa72b389 KH |
2392 | while (1) |
2393 | { | |
e951386e | 2394 | int c, id; |
df7492f9 | 2395 | |
aa72b389 | 2396 | src_base = src; |
df7492f9 KH |
2397 | consumed_chars_base = consumed_chars; |
2398 | ||
2399 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2400 | { |
2401 | if (byte_after_cr >= 0) | |
2402 | src_base--; | |
2403 | break; | |
2404 | } | |
aa72b389 | 2405 | |
119852e7 KH |
2406 | if (byte_after_cr >= 0) |
2407 | c = byte_after_cr, byte_after_cr = -1; | |
2408 | else | |
2409 | ONE_MORE_BYTE (c); | |
e951386e KH |
2410 | |
2411 | if (c < 0 || c == 0x80) | |
065e3595 | 2412 | { |
e951386e KH |
2413 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
2414 | if (c < 0) | |
2415 | { | |
2416 | *charbuf++ = -c; | |
2417 | char_offset++; | |
2418 | } | |
2419 | else | |
2420 | DECODE_EMACS_MULE_COMPOSITION_START (); | |
2421 | continue; | |
065e3595 | 2422 | } |
e951386e KH |
2423 | |
2424 | if (c < 0x80) | |
aa72b389 | 2425 | { |
119852e7 KH |
2426 | if (eol_crlf && c == '\r') |
2427 | ONE_MORE_BYTE (byte_after_cr); | |
e951386e KH |
2428 | id = charset_ascii; |
2429 | if (cmp_status->state != COMPOSING_NO) | |
2430 | { | |
2431 | if (cmp_status->old_form) | |
2432 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2433 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2434 | cmp_status->ncomps--; | |
2435 | } | |
2436 | } | |
2437 | else | |
2438 | { | |
2439 | int nchars, nbytes; | |
75f80e63 EZ |
2440 | /* emacs_mule_char can load a charset map from a file, which |
2441 | allocates a large structure and might cause buffer text | |
2442 | to be relocated as result. Thus, we need to remember the | |
ad1746f5 | 2443 | original pointer to buffer text, and fix up all related |
75f80e63 EZ |
2444 | pointers after the call. */ |
2445 | const unsigned char *orig = coding->source; | |
2446 | EMACS_INT offset; | |
e951386e KH |
2447 | |
2448 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, | |
2449 | cmp_status); | |
75f80e63 EZ |
2450 | offset = coding->source - orig; |
2451 | if (offset) | |
2452 | { | |
2453 | src += offset; | |
2454 | src_base += offset; | |
2455 | src_end += offset; | |
2456 | } | |
e951386e KH |
2457 | if (c < 0) |
2458 | { | |
2459 | if (c == -1) | |
2460 | goto invalid_code; | |
2461 | if (c == -2) | |
2462 | break; | |
2463 | } | |
2464 | src = src_base + nbytes; | |
2465 | consumed_chars = consumed_chars_base + nchars; | |
2466 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2467 | cmp_status->ncomps -= nchars; | |
2468 | } | |
2469 | ||
ad1746f5 | 2470 | /* Now if C >= 0, we found a normally encoded character, if C < |
e951386e KH |
2471 | 0, we found an old-style composition component character or |
2472 | rule. */ | |
2473 | ||
2474 | if (cmp_status->state == COMPOSING_NO) | |
2475 | { | |
2476 | if (last_id != id) | |
2477 | { | |
2478 | if (last_id != charset_ascii) | |
2479 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, | |
2480 | last_id); | |
2481 | last_id = id; | |
2482 | last_offset = char_offset; | |
2483 | } | |
df7492f9 KH |
2484 | *charbuf++ = c; |
2485 | char_offset++; | |
aa72b389 | 2486 | } |
e951386e | 2487 | else if (cmp_status->state == COMPOSING_CHAR) |
df7492f9 | 2488 | { |
e951386e KH |
2489 | if (cmp_status->old_form) |
2490 | { | |
2491 | if (c >= 0) | |
2492 | { | |
2493 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2494 | *charbuf++ = c; | |
2495 | char_offset++; | |
2496 | } | |
2497 | else | |
2498 | { | |
2499 | *charbuf++ = -c; | |
2500 | cmp_status->nchars++; | |
2501 | cmp_status->length++; | |
2502 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | |
2503 | EMACS_MULE_COMPOSITION_END (); | |
2504 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2505 | cmp_status->state = COMPOSING_RULE; | |
2506 | } | |
2507 | } | |
df7492f9 | 2508 | else |
e951386e KH |
2509 | { |
2510 | *charbuf++ = c; | |
2511 | cmp_status->length++; | |
2512 | cmp_status->nchars--; | |
2513 | if (cmp_status->nchars == 0) | |
2514 | EMACS_MULE_COMPOSITION_END (); | |
2515 | } | |
df7492f9 | 2516 | } |
e951386e | 2517 | else if (cmp_status->state == COMPOSING_RULE) |
df7492f9 | 2518 | { |
e951386e | 2519 | int rule; |
ff0dacd7 | 2520 | |
e951386e | 2521 | if (c >= 0) |
df7492f9 | 2522 | { |
e951386e KH |
2523 | EMACS_MULE_COMPOSITION_END (); |
2524 | *charbuf++ = c; | |
2525 | char_offset++; | |
df7492f9 | 2526 | } |
e951386e | 2527 | else |
ff0dacd7 | 2528 | { |
e951386e KH |
2529 | c = -c; |
2530 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | |
2531 | if (rule < 0) | |
2532 | goto invalid_code; | |
2533 | *charbuf++ = -2; | |
2534 | *charbuf++ = rule; | |
2535 | cmp_status->length += 2; | |
2536 | cmp_status->state = COMPOSING_CHAR; | |
ff0dacd7 | 2537 | } |
e951386e KH |
2538 | } |
2539 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | |
2540 | { | |
df7492f9 | 2541 | *charbuf++ = c; |
e951386e KH |
2542 | cmp_status->length++; |
2543 | if (cmp_status->ncomps == 0) | |
2544 | cmp_status->state = COMPOSING_CHAR; | |
2545 | else if (cmp_status->ncomps > 0) | |
2546 | { | |
2547 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | |
2548 | cmp_status->state = COMPOSING_COMPONENT_RULE; | |
2549 | } | |
2550 | else | |
2551 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 2552 | } |
e951386e KH |
2553 | else /* COMPOSING_COMPONENT_RULE */ |
2554 | { | |
2555 | int rule; | |
2556 | ||
2557 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | |
2558 | if (rule < 0) | |
2559 | goto invalid_code; | |
2560 | *charbuf++ = -2; | |
2561 | *charbuf++ = rule; | |
2562 | cmp_status->length += 2; | |
2563 | cmp_status->ncomps--; | |
2564 | if (cmp_status->ncomps > 0) | |
2565 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | |
2566 | else | |
2567 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2568 | } | |
2569 | continue; | |
2570 | ||
df7492f9 | 2571 | invalid_code: |
e951386e | 2572 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
df7492f9 KH |
2573 | src = src_base; |
2574 | consumed_chars = consumed_chars_base; | |
2575 | ONE_MORE_BYTE (c); | |
2576 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2577 | char_offset++; |
df7492f9 KH |
2578 | coding->errors++; |
2579 | } | |
2580 | ||
2581 | no_more_source: | |
e951386e KH |
2582 | if (cmp_status->state != COMPOSING_NO) |
2583 | { | |
2584 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
2585 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2586 | else | |
2587 | { | |
2588 | int i; | |
2589 | ||
2590 | charbuf -= cmp_status->length; | |
2591 | for (i = 0; i < cmp_status->length; i++) | |
2592 | cmp_status->carryover[i] = charbuf[i]; | |
2593 | } | |
2594 | } | |
ff0dacd7 | 2595 | if (last_id != charset_ascii) |
69a80ea3 | 2596 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2597 | coding->consumed_char += consumed_chars_base; |
2598 | coding->consumed = src_base - coding->source; | |
2599 | coding->charbuf_used = charbuf - coding->charbuf; | |
2600 | } | |
2601 | ||
2602 | ||
2603 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2604 | do { \ | |
2605 | if (id < 0xA0) \ | |
2606 | codes[0] = id, codes[1] = 0; \ | |
2607 | else if (id < 0xE0) \ | |
2608 | codes[0] = 0x9A, codes[1] = id; \ | |
2609 | else if (id < 0xF0) \ | |
2610 | codes[0] = 0x9B, codes[1] = id; \ | |
2611 | else if (id < 0xF5) \ | |
2612 | codes[0] = 0x9C, codes[1] = id; \ | |
2613 | else \ | |
2614 | codes[0] = 0x9D, codes[1] = id; \ | |
2615 | } while (0); | |
2616 | ||
aa72b389 | 2617 | |
df7492f9 | 2618 | static int |
971de7fb | 2619 | encode_coding_emacs_mule (struct coding_system *coding) |
df7492f9 KH |
2620 | { |
2621 | int multibytep = coding->dst_multibyte; | |
2622 | int *charbuf = coding->charbuf; | |
2623 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2624 | unsigned char *dst = coding->destination + coding->produced; | |
2625 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2626 | int safe_room = 8; | |
df7492f9 | 2627 | int produced_chars = 0; |
24a73b0a | 2628 | Lisp_Object attrs, charset_list; |
df7492f9 | 2629 | int c; |
ff0dacd7 | 2630 | int preferred_charset_id = -1; |
df7492f9 | 2631 | |
24a73b0a | 2632 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2633 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2634 | { | |
2635 | CODING_ATTR_CHARSET_LIST (attrs) | |
2636 | = charset_list = Vemacs_mule_charset_list; | |
2637 | } | |
df7492f9 KH |
2638 | |
2639 | while (charbuf < charbuf_end) | |
2640 | { | |
2641 | ASSURE_DESTINATION (safe_room); | |
2642 | c = *charbuf++; | |
ff0dacd7 KH |
2643 | |
2644 | if (c < 0) | |
2645 | { | |
2646 | /* Handle an annotation. */ | |
2647 | switch (*charbuf) | |
2648 | { | |
2649 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2650 | /* Not yet implemented. */ | |
2651 | break; | |
2652 | case CODING_ANNOTATE_CHARSET_MASK: | |
2653 | preferred_charset_id = charbuf[3]; | |
2654 | if (preferred_charset_id >= 0 | |
2655 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2656 | charset_list))) | |
2657 | preferred_charset_id = -1; | |
2658 | break; | |
2659 | default: | |
2660 | abort (); | |
2661 | } | |
2662 | charbuf += -c - 1; | |
2663 | continue; | |
2664 | } | |
2665 | ||
df7492f9 KH |
2666 | if (ASCII_CHAR_P (c)) |
2667 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2668 | else if (CHAR_BYTE8_P (c)) |
2669 | { | |
2670 | c = CHAR_TO_BYTE8 (c); | |
2671 | EMIT_ONE_BYTE (c); | |
2672 | } | |
df7492f9 | 2673 | else |
aa72b389 | 2674 | { |
df7492f9 KH |
2675 | struct charset *charset; |
2676 | unsigned code; | |
2677 | int dimension; | |
2678 | int emacs_mule_id; | |
2679 | unsigned char leading_codes[2]; | |
2680 | ||
ff0dacd7 KH |
2681 | if (preferred_charset_id >= 0) |
2682 | { | |
2683 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
905ca9d2 KH |
2684 | if (CHAR_CHARSET_P (c, charset)) |
2685 | code = ENCODE_CHAR (charset, c); | |
2686 | else | |
2687 | charset = char_charset (c, charset_list, &code); | |
ff0dacd7 KH |
2688 | } |
2689 | else | |
2690 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2691 | if (! charset) |
2692 | { | |
2693 | c = coding->default_char; | |
2694 | if (ASCII_CHAR_P (c)) | |
2695 | { | |
2696 | EMIT_ONE_ASCII_BYTE (c); | |
2697 | continue; | |
2698 | } | |
2699 | charset = char_charset (c, charset_list, &code); | |
2700 | } | |
2701 | dimension = CHARSET_DIMENSION (charset); | |
2702 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2703 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2704 | EMIT_ONE_BYTE (leading_codes[0]); | |
2705 | if (leading_codes[1]) | |
2706 | EMIT_ONE_BYTE (leading_codes[1]); | |
2707 | if (dimension == 1) | |
1fa663f9 | 2708 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2709 | else |
df7492f9 | 2710 | { |
1fa663f9 | 2711 | code |= 0x8080; |
df7492f9 KH |
2712 | EMIT_ONE_BYTE (code >> 8); |
2713 | EMIT_ONE_BYTE (code & 0xFF); | |
2714 | } | |
aa72b389 | 2715 | } |
aa72b389 | 2716 | } |
065e3595 | 2717 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2718 | coding->produced_char += produced_chars; |
2719 | coding->produced = dst - coding->destination; | |
2720 | return 0; | |
aa72b389 | 2721 | } |
b73bfc1c | 2722 | |
4ed46869 | 2723 | \f |
df7492f9 | 2724 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2725 | |
2726 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2727 | Since the intention of this note is to help understand the |
5a936b46 | 2728 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2729 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2730 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2731 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2732 | |
2733 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2734 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2735 | is encoded using bytes less than 128. This may make the encoded |
2736 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2737 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2738 | Significant Bit). |
b73bfc1c | 2739 | |
cfb43547 DL |
2740 | There are two kinds of character sets: control character sets and |
2741 | graphic character sets. The former contain control characters such | |
4ed46869 | 2742 | as `newline' and `escape' to provide control functions (control |
39787efd | 2743 | functions are also provided by escape sequences). The latter |
cfb43547 | 2744 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2745 | two control character sets and many graphic character sets. |
2746 | ||
2747 | Graphic character sets are classified into one of the following | |
39787efd KH |
2748 | four classes, according to the number of bytes (DIMENSION) and |
2749 | number of characters in one dimension (CHARS) of the set: | |
2750 | - DIMENSION1_CHARS94 | |
2751 | - DIMENSION1_CHARS96 | |
2752 | - DIMENSION2_CHARS94 | |
2753 | - DIMENSION2_CHARS96 | |
2754 | ||
2755 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2756 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2757 | hereafter). The <F> of each character set is decided by ECMA(*) |
2758 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2759 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2760 | |
2761 | Note (*): ECMA = European Computer Manufacturers Association | |
2762 | ||
cfb43547 | 2763 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2764 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2765 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2766 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2767 | o DIMENSION2_CHARS96 -- none for the moment | |
2768 | ||
39787efd | 2769 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2770 | C0 [0x00..0x1F] -- control character plane 0 |
2771 | GL [0x20..0x7F] -- graphic character plane 0 | |
2772 | C1 [0x80..0x9F] -- control character plane 1 | |
2773 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2774 | ||
2775 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2776 | C1 by an escape sequence. The most common case is that: |
2777 | - ISO646's control character set is designated/invoked to C0, and | |
2778 | - ISO6429's control character set is designated/invoked to C1, | |
2779 | and usually these designations/invocations are omitted in encoded | |
2780 | text. In a 7-bit environment, only C0 can be used, and a control | |
2781 | character for C1 is encoded by an appropriate escape sequence to | |
2782 | fit into the environment. All control characters for C1 are | |
2783 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2784 | |
2785 | A graphic character set is at first designated to one of four | |
2786 | graphic registers (G0 through G3), then these graphic registers are | |
2787 | invoked to GL or GR. These designations and invocations can be | |
2788 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2789 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2790 | these invocations and designations are omitted in encoded text. | |
2791 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2792 | |
39787efd KH |
2793 | When a graphic character set of CHARS94 is invoked to GL, codes |
2794 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2795 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2796 | be used. | |
4ed46869 KH |
2797 | |
2798 | There are two ways of invocation: locking-shift and single-shift. | |
2799 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2800 | invocation, whereas with single-shift, the invocation affects the |
2801 | following character only and doesn't affect the locking-shift | |
2802 | state. Invocations are done by the following control characters or | |
2803 | escape sequences: | |
4ed46869 KH |
2804 | |
2805 | ---------------------------------------------------------------------- | |
39787efd | 2806 | abbrev function cntrl escape seq description |
4ed46869 | 2807 | ---------------------------------------------------------------------- |
39787efd KH |
2808 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2809 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2810 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2811 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2812 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2813 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2814 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2815 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2816 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2817 | ---------------------------------------------------------------------- |
39787efd KH |
2818 | (*) These are not used by any known coding system. |
2819 | ||
2820 | Control characters for these functions are defined by macros | |
2821 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2822 | |
39787efd | 2823 | Designations are done by the following escape sequences: |
4ed46869 KH |
2824 | ---------------------------------------------------------------------- |
2825 | escape sequence description | |
2826 | ---------------------------------------------------------------------- | |
2827 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2828 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2829 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2830 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2831 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2832 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2833 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2834 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2835 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2836 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2837 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2838 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2839 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2840 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2841 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2842 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2843 | ---------------------------------------------------------------------- | |
2844 | ||
2845 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2846 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2847 | |
2848 | Note (*): Although these designations are not allowed in ISO2022, | |
2849 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2850 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2851 | 7-bit environment, non-locking-shift, and non-single-shift. |
2852 | ||
2853 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2854 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2855 | |
cfb43547 | 2856 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2857 | same multilingual text in ISO2022. Actually, there exist many |
2858 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2859 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2860 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2861 | localized platforms), and all of these are variants of ISO2022. |
2862 | ||
2863 | In addition to the above, Emacs handles two more kinds of escape | |
2864 | sequences: ISO6429's direction specification and Emacs' private | |
2865 | sequence for specifying character composition. | |
2866 | ||
39787efd | 2867 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2868 | o CSI ']' -- end of the current direction |
2869 | o CSI '0' ']' -- end of the current direction | |
2870 | o CSI '1' ']' -- start of left-to-right text | |
2871 | o CSI '2' ']' -- start of right-to-left text | |
2872 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2873 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2874 | ||
2875 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2876 | o ESC '0' -- start relative composition |
2877 | o ESC '1' -- end composition | |
2878 | o ESC '2' -- start rule-base composition (*) | |
2879 | o ESC '3' -- start relative composition with alternate chars (**) | |
2880 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2881 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2882 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2883 | |
5a936b46 DL |
2884 | (*) This form is used only in Emacs 20.7 and older versions, |
2885 | but newer versions can safely decode it. | |
cfb43547 | 2886 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2887 | and older versions can't decode it. |
ec6d2bb8 | 2888 | |
cfb43547 | 2889 | Here's a list of example usages of these composition escape |
b73bfc1c | 2890 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2891 | |
b73bfc1c | 2892 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2893 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2894 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2895 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2896 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2897 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2898 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2899 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2900 | |
2901 | enum iso_code_class_type iso_code_class[256]; | |
2902 | ||
df7492f9 KH |
2903 | #define SAFE_CHARSET_P(coding, id) \ |
2904 | ((id) <= (coding)->max_charset_id \ | |
1b3b981b | 2905 | && (coding)->safe_charsets[id] != 255) |
df7492f9 KH |
2906 | |
2907 | ||
2908 | #define SHIFT_OUT_OK(category) \ | |
2909 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2910 | ||
2911 | static void | |
971de7fb | 2912 | setup_iso_safe_charsets (Lisp_Object attrs) |
df7492f9 KH |
2913 | { |
2914 | Lisp_Object charset_list, safe_charsets; | |
2915 | Lisp_Object request; | |
2916 | Lisp_Object reg_usage; | |
2917 | Lisp_Object tail; | |
2918 | int reg94, reg96; | |
2919 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2920 | int max_charset_id; | |
2921 | ||
2922 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2923 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2924 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2925 | { | |
2926 | CODING_ATTR_CHARSET_LIST (attrs) | |
2927 | = charset_list = Viso_2022_charset_list; | |
2928 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2929 | } | |
2930 | ||
2931 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2932 | return; | |
2933 | ||
2934 | max_charset_id = 0; | |
2935 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2936 | { | |
2937 | int id = XINT (XCAR (tail)); | |
2938 | if (max_charset_id < id) | |
2939 | max_charset_id = id; | |
2940 | } | |
d46c5b12 | 2941 | |
1b3b981b AS |
2942 | safe_charsets = make_uninit_string (max_charset_id + 1); |
2943 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
2944 | request = AREF (attrs, coding_attr_iso_request); |
2945 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2946 | reg94 = XINT (XCAR (reg_usage)); | |
2947 | reg96 = XINT (XCDR (reg_usage)); | |
2948 | ||
2949 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2950 | { | |
2951 | Lisp_Object id; | |
2952 | Lisp_Object reg; | |
2953 | struct charset *charset; | |
2954 | ||
2955 | id = XCAR (tail); | |
2956 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2957 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2958 | if (! NILP (reg)) |
8f924df7 | 2959 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2960 | else if (charset->iso_chars_96) |
2961 | { | |
2962 | if (reg96 < 4) | |
8f924df7 | 2963 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2964 | } |
2965 | else | |
2966 | { | |
2967 | if (reg94 < 4) | |
8f924df7 | 2968 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2969 | } |
2970 | } | |
2971 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2972 | } | |
d46c5b12 | 2973 | |
b6871cc7 | 2974 | |
4ed46869 | 2975 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ad1746f5 | 2976 | Check if a text is encoded in one of ISO-2022 based coding systems. |
ff0dacd7 | 2977 | If it is, return 1, else return 0. */ |
4ed46869 | 2978 | |
0a28aafb | 2979 | static int |
cf84bb53 JB |
2980 | detect_coding_iso_2022 (struct coding_system *coding, |
2981 | struct coding_detection_info *detect_info) | |
4ed46869 | 2982 | { |
8f924df7 KH |
2983 | const unsigned char *src = coding->source, *src_base = src; |
2984 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2985 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2986 | int single_shifting = 0; |
df7492f9 KH |
2987 | int id; |
2988 | int c, c1; | |
2989 | int consumed_chars = 0; | |
2990 | int i; | |
ff0dacd7 KH |
2991 | int rejected = 0; |
2992 | int found = 0; | |
cee53ed4 | 2993 | int composition_count = -1; |
ff0dacd7 KH |
2994 | |
2995 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2996 | |
2997 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2998 | { | |
2999 | struct coding_system *this = &(coding_categories[i]); | |
3000 | Lisp_Object attrs, val; | |
3001 | ||
c6b278e7 KH |
3002 | if (this->id < 0) |
3003 | continue; | |
df7492f9 KH |
3004 | attrs = CODING_ID_ATTRS (this->id); |
3005 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
1b3b981b | 3006 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list)) |
df7492f9 KH |
3007 | setup_iso_safe_charsets (attrs); |
3008 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 3009 | this->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 3010 | this->safe_charsets = SDATA (val); |
df7492f9 KH |
3011 | } |
3012 | ||
3013 | /* A coding system of this category is always ASCII compatible. */ | |
3014 | src += coding->head_ascii; | |
3f003981 | 3015 | |
ff0dacd7 | 3016 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 3017 | { |
065e3595 | 3018 | src_base = src; |
df7492f9 | 3019 | ONE_MORE_BYTE (c); |
4ed46869 KH |
3020 | switch (c) |
3021 | { | |
3022 | case ISO_CODE_ESC: | |
74383408 KH |
3023 | if (inhibit_iso_escape_detection) |
3024 | break; | |
f46869e4 | 3025 | single_shifting = 0; |
df7492f9 | 3026 | ONE_MORE_BYTE (c); |
d46c5b12 | 3027 | if (c >= '(' && c <= '/') |
4ed46869 | 3028 | { |
bf9cdd4e | 3029 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 3030 | ONE_MORE_BYTE (c1); |
d46c5b12 | 3031 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 3032 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
3033 | /* Invalid designation sequence. Just ignore. */ |
3034 | break; | |
bf9cdd4e KH |
3035 | } |
3036 | else if (c == '$') | |
3037 | { | |
3038 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 3039 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
3040 | if (c >= '@' && c <= 'B') |
3041 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 3042 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 3043 | else if (c >= '(' && c <= '/') |
bcf26d6a | 3044 | { |
df7492f9 | 3045 | ONE_MORE_BYTE (c1); |
d46c5b12 | 3046 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 3047 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
3048 | /* Invalid designation sequence. Just ignore. */ |
3049 | break; | |
bcf26d6a | 3050 | } |
bf9cdd4e | 3051 | else |
ff0dacd7 | 3052 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
3053 | break; |
3054 | } | |
ae9ff118 | 3055 | else if (c == 'N' || c == 'O') |
d46c5b12 | 3056 | { |
ae9ff118 | 3057 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
3058 | single_shifting = 1; |
3059 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 3060 | break; |
4ed46869 | 3061 | } |
cee53ed4 KH |
3062 | else if (c == '1') |
3063 | { | |
3064 | /* End of composition. */ | |
3065 | if (composition_count < 0 | |
3066 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
3067 | /* Invalid */ | |
3068 | break; | |
3069 | composition_count = -1; | |
3070 | found |= CATEGORY_MASK_ISO; | |
3071 | } | |
ec6d2bb8 KH |
3072 | else if (c >= '0' && c <= '4') |
3073 | { | |
3074 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 3075 | composition_count = 0; |
ec6d2bb8 KH |
3076 | break; |
3077 | } | |
bf9cdd4e | 3078 | else |
df7492f9 | 3079 | { |
ff0dacd7 | 3080 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
3081 | break; |
3082 | } | |
d46c5b12 KH |
3083 | |
3084 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 3085 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
3086 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
3087 | id)) | |
ff0dacd7 | 3088 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 3089 | else |
ff0dacd7 | 3090 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
3091 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
3092 | id)) | |
ff0dacd7 | 3093 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 3094 | else |
ff0dacd7 | 3095 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
3096 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
3097 | id)) | |
ff0dacd7 | 3098 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 3099 | else |
ff0dacd7 | 3100 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
3101 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
3102 | id)) | |
ff0dacd7 | 3103 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 3104 | else |
ff0dacd7 | 3105 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
3106 | break; |
3107 | ||
4ed46869 | 3108 | case ISO_CODE_SO: |
d46c5b12 | 3109 | case ISO_CODE_SI: |
ff0dacd7 | 3110 | /* Locking shift out/in. */ |
74383408 KH |
3111 | if (inhibit_iso_escape_detection) |
3112 | break; | |
f46869e4 | 3113 | single_shifting = 0; |
ff0dacd7 | 3114 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
3115 | break; |
3116 | ||
4ed46869 | 3117 | case ISO_CODE_CSI: |
ff0dacd7 | 3118 | /* Control sequence introducer. */ |
f46869e4 | 3119 | single_shifting = 0; |
ff0dacd7 KH |
3120 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3121 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3122 | goto check_extra_latin; | |
3123 | ||
4ed46869 KH |
3124 | case ISO_CODE_SS2: |
3125 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
3126 | /* Single shift. */ |
3127 | if (inhibit_iso_escape_detection) | |
3128 | break; | |
75e2a253 | 3129 | single_shifting = 0; |
ff0dacd7 KH |
3130 | rejected |= CATEGORY_MASK_ISO_7BIT; |
3131 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3132 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 3133 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
3134 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
3135 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
3136 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
3137 | if (single_shifting) | |
3138 | break; | |
ff0dacd7 | 3139 | goto check_extra_latin; |
4ed46869 KH |
3140 | |
3141 | default: | |
065e3595 KH |
3142 | if (c < 0) |
3143 | continue; | |
4ed46869 | 3144 | if (c < 0x80) |
f46869e4 | 3145 | { |
cee53ed4 KH |
3146 | if (composition_count >= 0) |
3147 | composition_count++; | |
f46869e4 KH |
3148 | single_shifting = 0; |
3149 | break; | |
3150 | } | |
ff0dacd7 | 3151 | if (c >= 0xA0) |
c4825358 | 3152 | { |
ff0dacd7 KH |
3153 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3154 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 3155 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
3156 | 0xA0..0FF. If the byte length is even, we include |
3157 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
3158 | only when we are not single shifting. */ | |
3159 | if (! single_shifting | |
3160 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 3161 | { |
e17de821 | 3162 | int i = 1; |
b73bfc1c KH |
3163 | while (src < src_end) |
3164 | { | |
d12bd917 | 3165 | src_base = src; |
df7492f9 | 3166 | ONE_MORE_BYTE (c); |
b73bfc1c | 3167 | if (c < 0xA0) |
d12bd917 KH |
3168 | { |
3169 | src = src_base; | |
3170 | break; | |
3171 | } | |
b73bfc1c KH |
3172 | i++; |
3173 | } | |
3174 | ||
3175 | if (i & 1 && src < src_end) | |
cee53ed4 KH |
3176 | { |
3177 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3178 | if (composition_count >= 0) | |
3179 | composition_count += i; | |
3180 | } | |
f46869e4 | 3181 | else |
cee53ed4 KH |
3182 | { |
3183 | found |= CATEGORY_MASK_ISO_8_2; | |
3184 | if (composition_count >= 0) | |
3185 | composition_count += i / 2; | |
3186 | } | |
f46869e4 | 3187 | } |
ff0dacd7 | 3188 | break; |
4ed46869 | 3189 | } |
ff0dacd7 KH |
3190 | check_extra_latin: |
3191 | single_shifting = 0; | |
3192 | if (! VECTORP (Vlatin_extra_code_table) | |
3193 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
3194 | { | |
3195 | rejected = CATEGORY_MASK_ISO; | |
3196 | break; | |
3197 | } | |
3198 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3199 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3200 | found |= CATEGORY_MASK_ISO_8_1; | |
3201 | else | |
3202 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 3203 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
3204 | } |
3205 | } | |
ff0dacd7 KH |
3206 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3207 | return 0; | |
4ed46869 | 3208 | |
df7492f9 | 3209 | no_more_source: |
ff0dacd7 KH |
3210 | detect_info->rejected |= rejected; |
3211 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3212 | return 1; |
4ed46869 | 3213 | } |
ec6d2bb8 | 3214 | |
4ed46869 | 3215 | |
134b9549 KH |
3216 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3217 | escape sequence should be kept. */ | |
df7492f9 KH |
3218 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3219 | do { \ | |
3220 | int id, prev; \ | |
3221 | \ | |
3222 | if (final < '0' || final >= 128 \ | |
3223 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3224 | || !SAFE_CHARSET_P (coding, id)) \ | |
3225 | { \ | |
3226 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3227 | chars_96 = -1; \ |
3228 | break; \ | |
df7492f9 KH |
3229 | } \ |
3230 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3231 | if (id == charset_jisx0201_roman) \ |
3232 | { \ | |
3233 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3234 | id = charset_ascii; \ | |
3235 | } \ | |
3236 | else if (id == charset_jisx0208_1978) \ | |
3237 | { \ | |
3238 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3239 | id = charset_jisx0208; \ | |
3240 | } \ | |
df7492f9 KH |
3241 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3242 | /* If there was an invalid designation to REG previously, and this \ | |
3243 | designation is ASCII to REG, we should keep this designation \ | |
3244 | sequence. */ \ | |
3245 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3246 | chars_96 = -1; \ |
4ed46869 KH |
3247 | } while (0) |
3248 | ||
d46c5b12 | 3249 | |
e951386e KH |
3250 | /* Handle these composition sequence (ALT: alternate char): |
3251 | ||
3252 | (1) relative composition: ESC 0 CHAR ... ESC 1 | |
3253 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
3254 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | |
3255 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | |
3256 | ||
3257 | When the start sequence (ESC 0/2/3/4) is found, this annotation | |
3258 | header is produced. | |
3259 | ||
3260 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | |
3261 | ||
3262 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | |
3263 | produced until the end sequence (ESC 1) is found: | |
3264 | ||
3265 | (1) CHAR ... CHAR | |
3266 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
3267 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | |
3268 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | |
3269 | ||
3270 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | |
3271 | annotation header is updated as below: | |
3272 | ||
3273 | (1) LENGTH: unchanged, NCHARS: number of CHARs | |
3274 | (2) LENGTH: unchanged, NCHARS: number of CHARs | |
3275 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | |
3276 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | |
3277 | ||
3278 | If an error is found while composing, the annotation header is | |
3279 | changed to: | |
3280 | ||
3281 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | |
3282 | ||
3283 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
3284 | byte sequence as below: | |
3285 | o the original byte sequence is B: [ B -1 ] | |
3286 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
3287 | and the sequence [ -1 -1 ] is changed to the original byte | |
3288 | sequence: | |
3289 | [ ESC '0' ] | |
3290 | */ | |
3291 | ||
3292 | /* Decode a composition rule C1 and maybe one more byte from the | |
3293 | source, and set RULE to the encoded composition rule, NBYTES to the | |
3294 | length of the composition rule. If the rule is invalid, set RULE | |
3295 | to some negative value. */ | |
3296 | ||
3297 | #define DECODE_COMPOSITION_RULE(rule, nbytes) \ | |
3298 | do { \ | |
3299 | rule = c1 - 32; \ | |
3300 | if (rule < 0) \ | |
3301 | break; \ | |
3302 | if (rule < 81) /* old format (before ver.21) */ \ | |
3303 | { \ | |
3304 | int gref = (rule) / 9; \ | |
3305 | int nref = (rule) % 9; \ | |
3306 | if (gref == 4) gref = 10; \ | |
3307 | if (nref == 4) nref = 10; \ | |
3308 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
3309 | nbytes = 1; \ | |
3310 | } \ | |
3311 | else /* new format (after ver.21) */ \ | |
3312 | { \ | |
3313 | int c; \ | |
3314 | \ | |
3315 | ONE_MORE_BYTE (c); \ | |
3316 | rule = COMPOSITION_ENCODE_RULE (rule - 81, c - 32); \ | |
3317 | if (rule >= 0) \ | |
3318 | rule += 0x100; /* to destinguish it from the old format */ \ | |
3319 | nbytes = 2; \ | |
3320 | } \ | |
3321 | } while (0) | |
3322 | ||
3323 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
df7492f9 | 3324 | do { \ |
e951386e KH |
3325 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
3326 | \ | |
3327 | if (rule < 0x100) /* old format */ \ | |
df7492f9 | 3328 | { \ |
e951386e KH |
3329 | if (gref == 10) gref = 4; \ |
3330 | if (nref == 10) nref = 4; \ | |
3331 | charbuf[idx] = 32 + gref * 9 + nref; \ | |
3332 | charbuf[idx + 1] = -1; \ | |
3333 | new_chars++; \ | |
df7492f9 | 3334 | } \ |
e951386e | 3335 | else /* new format */ \ |
df7492f9 | 3336 | { \ |
e951386e KH |
3337 | charbuf[idx] = 32 + 81 + gref; \ |
3338 | charbuf[idx + 1] = 32 + nref; \ | |
3339 | new_chars += 2; \ | |
df7492f9 KH |
3340 | } \ |
3341 | } while (0) | |
3342 | ||
e951386e KH |
3343 | /* Finish the current composition as invalid. */ |
3344 | ||
f57e2426 | 3345 | static int finish_composition (int *, struct composition_status *); |
e951386e KH |
3346 | |
3347 | static int | |
971de7fb | 3348 | finish_composition (int *charbuf, struct composition_status *cmp_status) |
e951386e KH |
3349 | { |
3350 | int idx = - cmp_status->length; | |
3351 | int new_chars; | |
3352 | ||
3353 | /* Recover the original ESC sequence */ | |
3354 | charbuf[idx++] = ISO_CODE_ESC; | |
3355 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | |
3356 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | |
3357 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | |
3358 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | |
3359 | : '4'); | |
3360 | charbuf[idx++] = -2; | |
3361 | charbuf[idx++] = 0; | |
3362 | charbuf[idx++] = -1; | |
3363 | new_chars = cmp_status->nchars; | |
3364 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | |
3365 | for (; idx < 0; idx++) | |
3366 | { | |
3367 | int elt = charbuf[idx]; | |
3368 | ||
3369 | if (elt == -2) | |
3370 | { | |
3371 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | |
3372 | idx++; | |
3373 | } | |
3374 | else if (elt == -1) | |
3375 | { | |
3376 | charbuf[idx++] = ISO_CODE_ESC; | |
3377 | charbuf[idx] = '0'; | |
3378 | new_chars += 2; | |
3379 | } | |
3380 | } | |
3381 | cmp_status->state = COMPOSING_NO; | |
3382 | return new_chars; | |
3383 | } | |
3384 | ||
ad1746f5 | 3385 | /* If characters are under composition, finish the composition. */ |
e951386e KH |
3386 | #define MAYBE_FINISH_COMPOSITION() \ |
3387 | do { \ | |
3388 | if (cmp_status->state != COMPOSING_NO) \ | |
3389 | char_offset += finish_composition (charbuf, cmp_status); \ | |
3390 | } while (0) | |
d46c5b12 | 3391 | |
aa72b389 | 3392 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
e951386e | 3393 | |
aa72b389 KH |
3394 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
3395 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3396 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3397 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
ec6d2bb8 | 3398 | |
e951386e KH |
3399 | Produce this annotation sequence now: |
3400 | ||
3401 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] | |
3402 | */ | |
3403 | ||
3404 | #define DECODE_COMPOSITION_START(c1) \ | |
3405 | do { \ | |
3406 | if (c1 == '0' \ | |
3407 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ | |
3408 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ | |
3409 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ | |
3410 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ | |
3411 | { \ | |
3412 | *charbuf++ = -1; \ | |
3413 | *charbuf++= -1; \ | |
3414 | cmp_status->state = COMPOSING_CHAR; \ | |
3415 | cmp_status->length += 2; \ | |
3416 | } \ | |
3417 | else \ | |
3418 | { \ | |
3419 | MAYBE_FINISH_COMPOSITION (); \ | |
3420 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3421 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3422 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3423 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3424 | cmp_status->state \ | |
3425 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ | |
3426 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
3427 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
3428 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
3429 | coding->annotated = 1; \ | |
3430 | } \ | |
ec6d2bb8 KH |
3431 | } while (0) |
3432 | ||
ec6d2bb8 | 3433 | |
e951386e | 3434 | /* Handle composition end sequence ESC 1. */ |
df7492f9 KH |
3435 | |
3436 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3437 | do { \ |
e951386e KH |
3438 | if (cmp_status->nchars == 0 \ |
3439 | || ((cmp_status->state == COMPOSING_CHAR) \ | |
3440 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ | |
ec6d2bb8 | 3441 | { \ |
e951386e KH |
3442 | MAYBE_FINISH_COMPOSITION (); \ |
3443 | goto invalid_code; \ | |
ec6d2bb8 | 3444 | } \ |
e951386e KH |
3445 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
3446 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ | |
3447 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
3448 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ | |
3449 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ | |
3450 | char_offset += cmp_status->nchars; \ | |
3451 | cmp_status->state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3452 | } while (0) |
3453 | ||
e951386e | 3454 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ |
df7492f9 | 3455 | |
e951386e KH |
3456 | #define STORE_COMPOSITION_RULE(rule) \ |
3457 | do { \ | |
3458 | *charbuf++ = -2; \ | |
3459 | *charbuf++ = rule; \ | |
3460 | cmp_status->length += 2; \ | |
3461 | cmp_status->state--; \ | |
3462 | } while (0) | |
ec6d2bb8 | 3463 | |
e951386e KH |
3464 | /* Store a composed char or a component char C in charbuf, and update |
3465 | cmp_status. */ | |
3466 | ||
3467 | #define STORE_COMPOSITION_CHAR(c) \ | |
ec6d2bb8 | 3468 | do { \ |
e951386e KH |
3469 | *charbuf++ = (c); \ |
3470 | cmp_status->length++; \ | |
3471 | if (cmp_status->state == COMPOSING_CHAR) \ | |
3472 | cmp_status->nchars++; \ | |
df7492f9 | 3473 | else \ |
e951386e KH |
3474 | cmp_status->ncomps++; \ |
3475 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | |
3476 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | |
3477 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | |
3478 | cmp_status->state++; \ | |
ec6d2bb8 | 3479 | } while (0) |
88993dfd | 3480 | |
d46c5b12 | 3481 | |
4ed46869 KH |
3482 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3483 | ||
b73bfc1c | 3484 | static void |
971de7fb | 3485 | decode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 3486 | { |
8f924df7 KH |
3487 | const unsigned char *src = coding->source + coding->consumed; |
3488 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3489 | const unsigned char *src_base; | |
69a80ea3 | 3490 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
3491 | /* We may produce two annotations (charset and composition) in one |
3492 | loop and one more charset annotation at the end. */ | |
ff0dacd7 | 3493 | int *charbuf_end |
df80c7f0 | 3494 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
df7492f9 | 3495 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 3496 | int multibytep = coding->src_multibyte; |
4ed46869 | 3497 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3498 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3499 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3500 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3501 | struct charset *charset; |
3502 | int c; | |
e951386e | 3503 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
24a73b0a | 3504 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
3505 | int char_offset = coding->produced_char; |
3506 | int last_offset = char_offset; | |
3507 | int last_id = charset_ascii; | |
0a9564cb EZ |
3508 | int eol_crlf = |
3509 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 3510 | int byte_after_cr = -1; |
e951386e | 3511 | int i; |
df7492f9 | 3512 | |
24a73b0a | 3513 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 3514 | setup_iso_safe_charsets (attrs); |
287c57d7 KH |
3515 | /* Charset list may have been changed. */ |
3516 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
1b3b981b | 3517 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
b73bfc1c | 3518 | |
e951386e KH |
3519 | if (cmp_status->state != COMPOSING_NO) |
3520 | { | |
3521 | for (i = 0; i < cmp_status->length; i++) | |
3522 | *charbuf++ = cmp_status->carryover[i]; | |
3523 | coding->annotated = 1; | |
3524 | } | |
3525 | ||
b73bfc1c | 3526 | while (1) |
4ed46869 | 3527 | { |
cf299835 | 3528 | int c1, c2, c3; |
b73bfc1c KH |
3529 | |
3530 | src_base = src; | |
df7492f9 KH |
3531 | consumed_chars_base = consumed_chars; |
3532 | ||
3533 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3534 | { |
3535 | if (byte_after_cr >= 0) | |
3536 | src_base--; | |
3537 | break; | |
3538 | } | |
df7492f9 | 3539 | |
119852e7 KH |
3540 | if (byte_after_cr >= 0) |
3541 | c1 = byte_after_cr, byte_after_cr = -1; | |
3542 | else | |
3543 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3544 | if (c1 < 0) |
3545 | goto invalid_code; | |
4ed46869 | 3546 | |
e951386e | 3547 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
4ed46869 | 3548 | { |
e951386e KH |
3549 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
3550 | char_offset++; | |
3551 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | |
3552 | continue; | |
3553 | } | |
3554 | ||
3555 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | |
3556 | { | |
3557 | if (c1 == ISO_CODE_ESC) | |
ec6d2bb8 | 3558 | { |
e951386e KH |
3559 | if (src + 1 >= src_end) |
3560 | goto no_more_source; | |
3561 | *charbuf++ = ISO_CODE_ESC; | |
3562 | char_offset++; | |
3563 | if (src[0] == '%' && src[1] == '@') | |
df7492f9 | 3564 | { |
e951386e KH |
3565 | src += 2; |
3566 | consumed_chars += 2; | |
3567 | char_offset += 2; | |
3568 | /* We are sure charbuf can contain two more chars. */ | |
3569 | *charbuf++ = '%'; | |
3570 | *charbuf++ = '@'; | |
3571 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
df7492f9 | 3572 | } |
4ed46869 | 3573 | } |
e951386e KH |
3574 | else |
3575 | { | |
3576 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
3577 | char_offset++; | |
3578 | } | |
3579 | continue; | |
3580 | } | |
3581 | ||
3582 | if ((cmp_status->state == COMPOSING_RULE | |
3583 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | |
3584 | && c1 != ISO_CODE_ESC) | |
3585 | { | |
3586 | int rule, nbytes; | |
3587 | ||
3588 | DECODE_COMPOSITION_RULE (rule, nbytes); | |
3589 | if (rule < 0) | |
3590 | goto invalid_code; | |
3591 | STORE_COMPOSITION_RULE (rule); | |
3592 | continue; | |
3593 | } | |
3594 | ||
3595 | /* We produce at most one character. */ | |
3596 | switch (iso_code_class [c1]) | |
3597 | { | |
3598 | case ISO_0x20_or_0x7F: | |
df7492f9 KH |
3599 | if (charset_id_0 < 0 |
3600 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3601 | /* This is SPACE or DEL. */ |
3602 | charset = CHARSET_FROM_ID (charset_ascii); | |
3603 | else | |
3604 | charset = CHARSET_FROM_ID (charset_id_0); | |
3605 | break; | |
4ed46869 KH |
3606 | |
3607 | case ISO_graphic_plane_0: | |
134b9549 KH |
3608 | if (charset_id_0 < 0) |
3609 | charset = CHARSET_FROM_ID (charset_ascii); | |
3610 | else | |
3611 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3612 | break; |
3613 | ||
3614 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3615 | if (charset_id_1 < 0 |
3616 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3617 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3618 | goto invalid_code; | |
4ed46869 KH |
3619 | /* This is a graphic character, we fall down ... */ |
3620 | ||
3621 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3622 | if (charset_id_1 < 0) |
3623 | goto invalid_code; | |
3624 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3625 | break; |
3626 | ||
df7492f9 | 3627 | case ISO_control_0: |
119852e7 KH |
3628 | if (eol_crlf && c1 == '\r') |
3629 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 KH |
3630 | MAYBE_FINISH_COMPOSITION (); |
3631 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3632 | break; |
3633 | ||
df7492f9 | 3634 | case ISO_control_1: |
df7492f9 KH |
3635 | goto invalid_code; |
3636 | ||
4ed46869 | 3637 | case ISO_shift_out: |
df7492f9 KH |
3638 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3639 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3640 | goto invalid_code; | |
3641 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3642 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3643 | continue; |
4ed46869 KH |
3644 | |
3645 | case ISO_shift_in: | |
df7492f9 KH |
3646 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3647 | goto invalid_code; | |
3648 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3649 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3650 | continue; |
4ed46869 KH |
3651 | |
3652 | case ISO_single_shift_2_7: | |
a63dba42 KH |
3653 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)) |
3654 | goto invalid_code; | |
4ed46869 | 3655 | case ISO_single_shift_2: |
df7492f9 KH |
3656 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3657 | goto invalid_code; | |
4ed46869 KH |
3658 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3659 | c1 = 'N'; | |
3660 | goto label_escape_sequence; | |
3661 | ||
3662 | case ISO_single_shift_3: | |
df7492f9 KH |
3663 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3664 | goto invalid_code; | |
4ed46869 KH |
3665 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3666 | c1 = 'O'; | |
3667 | goto label_escape_sequence; | |
3668 | ||
3669 | case ISO_control_sequence_introducer: | |
3670 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3671 | c1 = '['; | |
3672 | goto label_escape_sequence; | |
3673 | ||
3674 | case ISO_escape: | |
3675 | ONE_MORE_BYTE (c1); | |
3676 | label_escape_sequence: | |
df7492f9 | 3677 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3678 | designation, direction specification, and character |
3679 | composition specification. */ | |
3680 | switch (c1) | |
3681 | { | |
3682 | case '&': /* revision of following character set */ | |
3683 | ONE_MORE_BYTE (c1); | |
3684 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3685 | goto invalid_code; |
4ed46869 KH |
3686 | ONE_MORE_BYTE (c1); |
3687 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3688 | goto invalid_code; |
4ed46869 KH |
3689 | ONE_MORE_BYTE (c1); |
3690 | goto label_escape_sequence; | |
3691 | ||
3692 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3693 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3694 | goto invalid_code; | |
134b9549 KH |
3695 | { |
3696 | int reg, chars96; | |
3697 | ||
3698 | ONE_MORE_BYTE (c1); | |
3699 | if (c1 >= '@' && c1 <= 'B') | |
3700 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3701 | or JISX0208.1980 */ |
134b9549 KH |
3702 | reg = 0, chars96 = 0; |
3703 | } | |
3704 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3705 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3706 | reg = c1 - 0x28, chars96 = 0; | |
3707 | ONE_MORE_BYTE (c1); | |
3708 | } | |
3709 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3710 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3711 | reg = c1 - 0x2C, chars96 = 1; | |
3712 | ONE_MORE_BYTE (c1); | |
3713 | } | |
3714 | else | |
3715 | goto invalid_code; | |
3716 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3717 | /* We must update these variables now. */ | |
3718 | if (reg == 0) | |
3719 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3720 | else if (reg == 1) | |
3721 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3722 | if (chars96 < 0) | |
3723 | goto invalid_code; | |
3724 | } | |
b73bfc1c | 3725 | continue; |
4ed46869 KH |
3726 | |
3727 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3728 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3729 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3730 | goto invalid_code; | |
3731 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3732 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3733 | continue; |
4ed46869 KH |
3734 | |
3735 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3736 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3737 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3738 | goto invalid_code; | |
3739 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3740 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3741 | continue; |
4ed46869 KH |
3742 | |
3743 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3744 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3745 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3746 | goto invalid_code; | |
134b9549 KH |
3747 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3748 | if (charset_id_2 < 0) | |
3749 | charset = CHARSET_FROM_ID (charset_ascii); | |
3750 | else | |
3751 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3752 | ONE_MORE_BYTE (c1); |
e7046a18 | 3753 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3754 | goto invalid_code; |
4ed46869 KH |
3755 | break; |
3756 | ||
3757 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3758 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3759 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3760 | goto invalid_code; | |
134b9549 KH |
3761 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3762 | if (charset_id_3 < 0) | |
3763 | charset = CHARSET_FROM_ID (charset_ascii); | |
3764 | else | |
3765 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3766 | ONE_MORE_BYTE (c1); |
e7046a18 | 3767 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3768 | goto invalid_code; |
4ed46869 KH |
3769 | break; |
3770 | ||
ec6d2bb8 | 3771 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3772 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3773 | goto invalid_code; | |
e951386e KH |
3774 | if (last_id != charset_ascii) |
3775 | { | |
3776 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | |
3777 | last_id = charset_ascii; | |
3778 | last_offset = char_offset; | |
3779 | } | |
ec6d2bb8 | 3780 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3781 | continue; |
4ed46869 | 3782 | |
ec6d2bb8 | 3783 | case '1': /* end composition */ |
e951386e | 3784 | if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3785 | goto invalid_code; |
3786 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3787 | continue; |
4ed46869 KH |
3788 | |
3789 | case '[': /* specification of direction */ | |
de59072a | 3790 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)) |
df7492f9 | 3791 | goto invalid_code; |
4ed46869 | 3792 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3793 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
ad1746f5 | 3794 | left-to-right, and nonzero means right-to-left. */ |
4ed46869 KH |
3795 | ONE_MORE_BYTE (c1); |
3796 | switch (c1) | |
3797 | { | |
3798 | case ']': /* end of the current direction */ | |
d46c5b12 | 3799 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3800 | |
3801 | case '0': /* end of the current direction */ | |
3802 | case '1': /* start of left-to-right direction */ | |
3803 | ONE_MORE_BYTE (c1); | |
3804 | if (c1 == ']') | |
d46c5b12 | 3805 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3806 | else |
df7492f9 | 3807 | goto invalid_code; |
4ed46869 KH |
3808 | break; |
3809 | ||
3810 | case '2': /* start of right-to-left direction */ | |
3811 | ONE_MORE_BYTE (c1); | |
3812 | if (c1 == ']') | |
d46c5b12 | 3813 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3814 | else |
df7492f9 | 3815 | goto invalid_code; |
4ed46869 KH |
3816 | break; |
3817 | ||
3818 | default: | |
df7492f9 | 3819 | goto invalid_code; |
4ed46869 | 3820 | } |
b73bfc1c | 3821 | continue; |
4ed46869 | 3822 | |
103e0180 | 3823 | case '%': |
103e0180 KH |
3824 | ONE_MORE_BYTE (c1); |
3825 | if (c1 == '/') | |
3826 | { | |
3827 | /* CTEXT extended segment: | |
3828 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3829 | We keep these bytes as is for the moment. | |
3830 | They may be decoded by post-read-conversion. */ | |
3831 | int dim, M, L; | |
4776e638 | 3832 | int size; |
8f924df7 | 3833 | |
103e0180 | 3834 | ONE_MORE_BYTE (dim); |
7a84eee5 | 3835 | if (dim < '0' || dim > '4') |
e951386e | 3836 | goto invalid_code; |
103e0180 | 3837 | ONE_MORE_BYTE (M); |
e951386e KH |
3838 | if (M < 128) |
3839 | goto invalid_code; | |
103e0180 | 3840 | ONE_MORE_BYTE (L); |
e951386e KH |
3841 | if (L < 128) |
3842 | goto invalid_code; | |
103e0180 | 3843 | size = ((M - 128) * 128) + (L - 128); |
e951386e | 3844 | if (charbuf + 6 > charbuf_end) |
4776e638 KH |
3845 | goto break_loop; |
3846 | *charbuf++ = ISO_CODE_ESC; | |
3847 | *charbuf++ = '%'; | |
3848 | *charbuf++ = '/'; | |
3849 | *charbuf++ = dim; | |
3850 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3851 | *charbuf++ = BYTE8_TO_CHAR (L); | |
e951386e | 3852 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
103e0180 KH |
3853 | } |
3854 | else if (c1 == 'G') | |
3855 | { | |
103e0180 KH |
3856 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3857 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3858 | We keep these bytes as is for the moment. | |
3859 | They may be decoded by post-read-conversion. */ | |
e951386e | 3860 | if (charbuf + 3 > charbuf_end) |
4776e638 | 3861 | goto break_loop; |
e951386e KH |
3862 | *charbuf++ = ISO_CODE_ESC; |
3863 | *charbuf++ = '%'; | |
3864 | *charbuf++ = 'G'; | |
3865 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; | |
103e0180 KH |
3866 | } |
3867 | else | |
4776e638 | 3868 | goto invalid_code; |
103e0180 | 3869 | continue; |
4776e638 | 3870 | break; |
103e0180 | 3871 | |
4ed46869 | 3872 | default: |
df7492f9 KH |
3873 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3874 | goto invalid_code; | |
134b9549 KH |
3875 | { |
3876 | int reg, chars96; | |
3877 | ||
3878 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3879 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3880 | reg = c1 - 0x28, chars96 = 0; | |
3881 | ONE_MORE_BYTE (c1); | |
3882 | } | |
3883 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3884 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3885 | reg = c1 - 0x2C, chars96 = 1; | |
3886 | ONE_MORE_BYTE (c1); | |
3887 | } | |
3888 | else | |
3889 | goto invalid_code; | |
3890 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3891 | /* We must update these variables now. */ | |
3892 | if (reg == 0) | |
3893 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3894 | else if (reg == 1) | |
3895 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3896 | if (chars96 < 0) | |
3897 | goto invalid_code; | |
3898 | } | |
b73bfc1c | 3899 | continue; |
4ed46869 | 3900 | } |
b73bfc1c | 3901 | } |
4ed46869 | 3902 | |
e951386e KH |
3903 | if (cmp_status->state == COMPOSING_NO |
3904 | && charset->id != charset_ascii | |
ff0dacd7 KH |
3905 | && last_id != charset->id) |
3906 | { | |
3907 | if (last_id != charset_ascii) | |
69a80ea3 | 3908 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3909 | last_id = charset->id; |
3910 | last_offset = char_offset; | |
3911 | } | |
3912 | ||
b73bfc1c | 3913 | /* Now we know CHARSET and 1st position code C1 of a character. |
cf299835 KH |
3914 | Produce a decoded character while getting 2nd and 3rd |
3915 | position codes C2, C3 if necessary. */ | |
df7492f9 | 3916 | if (CHARSET_DIMENSION (charset) > 1) |
b73bfc1c KH |
3917 | { |
3918 | ONE_MORE_BYTE (c2); | |
cf299835 KH |
3919 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0) |
3920 | || ((c1 & 0x80) != (c2 & 0x80))) | |
b73bfc1c | 3921 | /* C2 is not in a valid range. */ |
df7492f9 | 3922 | goto invalid_code; |
cf299835 KH |
3923 | if (CHARSET_DIMENSION (charset) == 2) |
3924 | c1 = (c1 << 8) | c2; | |
3925 | else | |
df7492f9 | 3926 | { |
cf299835 KH |
3927 | ONE_MORE_BYTE (c3); |
3928 | if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0) | |
3929 | || ((c1 & 0x80) != (c3 & 0x80))) | |
3930 | /* C3 is not in a valid range. */ | |
df7492f9 | 3931 | goto invalid_code; |
cf299835 | 3932 | c1 = (c1 << 16) | (c2 << 8) | c2; |
df7492f9 KH |
3933 | } |
3934 | } | |
cf299835 | 3935 | c1 &= 0x7F7F7F; |
df7492f9 KH |
3936 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); |
3937 | if (c < 0) | |
3938 | { | |
3939 | MAYBE_FINISH_COMPOSITION (); | |
3940 | for (; src_base < src; src_base++, char_offset++) | |
3941 | { | |
3942 | if (ASCII_BYTE_P (*src_base)) | |
3943 | *charbuf++ = *src_base; | |
3944 | else | |
3945 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3946 | } | |
3947 | } | |
e951386e | 3948 | else if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3949 | { |
3950 | *charbuf++ = c; | |
3951 | char_offset++; | |
4ed46869 | 3952 | } |
e951386e KH |
3953 | else if ((cmp_status->state == COMPOSING_CHAR |
3954 | ? cmp_status->nchars | |
3955 | : cmp_status->ncomps) | |
3956 | >= MAX_COMPOSITION_COMPONENTS) | |
781d7a48 | 3957 | { |
e951386e KH |
3958 | /* Too long composition. */ |
3959 | MAYBE_FINISH_COMPOSITION (); | |
3960 | *charbuf++ = c; | |
3961 | char_offset++; | |
4ed46869 | 3962 | } |
e951386e KH |
3963 | else |
3964 | STORE_COMPOSITION_CHAR (c); | |
4ed46869 KH |
3965 | continue; |
3966 | ||
df7492f9 KH |
3967 | invalid_code: |
3968 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3969 | src = src_base; |
df7492f9 KH |
3970 | consumed_chars = consumed_chars_base; |
3971 | ONE_MORE_BYTE (c); | |
065e3595 | 3972 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3973 | char_offset++; |
df7492f9 | 3974 | coding->errors++; |
4776e638 KH |
3975 | continue; |
3976 | ||
3977 | break_loop: | |
3978 | break; | |
4ed46869 | 3979 | } |
fb88bf2d | 3980 | |
df7492f9 | 3981 | no_more_source: |
e951386e KH |
3982 | if (cmp_status->state != COMPOSING_NO) |
3983 | { | |
3984 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
3985 | MAYBE_FINISH_COMPOSITION (); | |
3986 | else | |
3987 | { | |
3988 | charbuf -= cmp_status->length; | |
3989 | for (i = 0; i < cmp_status->length; i++) | |
3990 | cmp_status->carryover[i] = charbuf[i]; | |
3991 | } | |
3992 | } | |
3993 | else if (last_id != charset_ascii) | |
69a80ea3 | 3994 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3995 | coding->consumed_char += consumed_chars_base; |
3996 | coding->consumed = src_base - coding->source; | |
3997 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3998 | } |
3999 | ||
b73bfc1c | 4000 | |
f4dee582 | 4001 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
4002 | |
4003 | /* | |
f4dee582 | 4004 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 4005 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 4006 | variant has the following specifications: |
df7492f9 | 4007 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
4008 | 2. Allows short-form designation? |
4009 | 3. ASCII should be designated to G0 before control characters? | |
4010 | 4. ASCII should be designated to G0 at end of line? | |
4011 | 5. 7-bit environment or 8-bit environment? | |
4012 | 6. Use locking-shift? | |
4013 | 7. Use Single-shift? | |
4014 | And the following two are only for Japanese: | |
4015 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
4016 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
4017 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
4018 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 4019 | details. |
4ed46869 KH |
4020 | */ |
4021 | ||
4022 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
4023 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
4024 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
4025 | designation sequence of short-form. */ | |
4ed46869 KH |
4026 | |
4027 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
4028 | do { \ | |
df7492f9 | 4029 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
675e2c69 DN |
4030 | const char *intermediate_char_94 = "()*+"; \ |
4031 | const char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
4032 | int revision = -1; \ |
4033 | int c; \ | |
4034 | \ | |
4035 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 4036 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
4037 | \ |
4038 | if (revision >= 0) \ | |
70c22245 | 4039 | { \ |
df7492f9 KH |
4040 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
4041 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 4042 | } \ |
df7492f9 | 4043 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
4044 | if (CHARSET_DIMENSION (charset) == 1) \ |
4045 | { \ | |
df7492f9 KH |
4046 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
4047 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 4048 | else \ |
df7492f9 KH |
4049 | c = intermediate_char_96[reg]; \ |
4050 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
4051 | } \ |
4052 | else \ | |
4053 | { \ | |
df7492f9 KH |
4054 | EMIT_ONE_ASCII_BYTE ('$'); \ |
4055 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 4056 | { \ |
df7492f9 | 4057 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
4058 | || reg != 0 \ |
4059 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 4060 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
4061 | } \ |
4062 | else \ | |
df7492f9 | 4063 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 4064 | } \ |
df7492f9 KH |
4065 | EMIT_ONE_ASCII_BYTE (final_char); \ |
4066 | \ | |
4067 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
4068 | } while (0) |
4069 | ||
df7492f9 | 4070 | |
4ed46869 KH |
4071 | /* The following two macros produce codes (control character or escape |
4072 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
4073 | single-shift-3). */ | |
4074 | ||
df7492f9 KH |
4075 | #define ENCODE_SINGLE_SHIFT_2 \ |
4076 | do { \ | |
4077 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4078 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
4079 | else \ | |
4080 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
4081 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4082 | } while (0) |
4083 | ||
df7492f9 KH |
4084 | |
4085 | #define ENCODE_SINGLE_SHIFT_3 \ | |
4086 | do { \ | |
4087 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4088 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
4089 | else \ | |
4090 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
4091 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4092 | } while (0) |
4093 | ||
df7492f9 | 4094 | |
4ed46869 KH |
4095 | /* The following four macros produce codes (control character or |
4096 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
4097 | shift-out, locking-shift-2, and locking-shift-3). */ | |
4098 | ||
df7492f9 KH |
4099 | #define ENCODE_SHIFT_IN \ |
4100 | do { \ | |
4101 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
4102 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
4103 | } while (0) |
4104 | ||
df7492f9 KH |
4105 | |
4106 | #define ENCODE_SHIFT_OUT \ | |
4107 | do { \ | |
4108 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
4109 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
4110 | } while (0) |
4111 | ||
df7492f9 KH |
4112 | |
4113 | #define ENCODE_LOCKING_SHIFT_2 \ | |
4114 | do { \ | |
4115 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4116 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
4117 | } while (0) |
4118 | ||
df7492f9 KH |
4119 | |
4120 | #define ENCODE_LOCKING_SHIFT_3 \ | |
4121 | do { \ | |
4122 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4123 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
4124 | } while (0) |
4125 | ||
df7492f9 | 4126 | |
f4dee582 RS |
4127 | /* Produce codes for a DIMENSION1 character whose character set is |
4128 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
4129 | sequences are also produced in advance if necessary. */ |
4130 | ||
6e85d753 KH |
4131 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
4132 | do { \ | |
df7492f9 | 4133 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4134 | \ |
4135 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
4136 | && id == charset_ascii) \ | |
4137 | { \ | |
4138 | id = charset_jisx0201_roman; \ | |
4139 | charset = CHARSET_FROM_ID (id); \ | |
4140 | } \ | |
4141 | \ | |
df7492f9 | 4142 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4143 | { \ |
df7492f9 KH |
4144 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4145 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 4146 | else \ |
df7492f9 KH |
4147 | EMIT_ONE_BYTE (c1 | 0x80); \ |
4148 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4149 | break; \ |
4150 | } \ | |
df7492f9 | 4151 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4152 | { \ |
df7492f9 | 4153 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
4154 | break; \ |
4155 | } \ | |
df7492f9 | 4156 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4157 | { \ |
df7492f9 | 4158 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
4159 | break; \ |
4160 | } \ | |
6e85d753 KH |
4161 | else \ |
4162 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4163 | must invoke it, or, at first, designate it to some graphic \ | |
4164 | register. Then repeat the loop to actually produce the \ | |
4165 | character. */ \ | |
df7492f9 KH |
4166 | dst = encode_invocation_designation (charset, coding, dst, \ |
4167 | &produced_chars); \ | |
4ed46869 KH |
4168 | } while (1) |
4169 | ||
df7492f9 | 4170 | |
f4dee582 RS |
4171 | /* Produce codes for a DIMENSION2 character whose character set is |
4172 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
4173 | invocation codes are also produced in advance if necessary. */ |
4174 | ||
6e85d753 KH |
4175 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
4176 | do { \ | |
df7492f9 | 4177 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4178 | \ |
4179 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
4180 | && id == charset_jisx0208) \ | |
4181 | { \ | |
4182 | id = charset_jisx0208_1978; \ | |
4183 | charset = CHARSET_FROM_ID (id); \ | |
4184 | } \ | |
4185 | \ | |
df7492f9 | 4186 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4187 | { \ |
df7492f9 KH |
4188 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4189 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 4190 | else \ |
df7492f9 KH |
4191 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
4192 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4193 | break; \ |
4194 | } \ | |
df7492f9 | 4195 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4196 | { \ |
df7492f9 | 4197 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
4198 | break; \ |
4199 | } \ | |
df7492f9 | 4200 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4201 | { \ |
df7492f9 | 4202 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
4203 | break; \ |
4204 | } \ | |
6e85d753 KH |
4205 | else \ |
4206 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4207 | must invoke it, or, at first, designate it to some graphic \ | |
4208 | register. Then repeat the loop to actually produce the \ | |
4209 | character. */ \ | |
df7492f9 KH |
4210 | dst = encode_invocation_designation (charset, coding, dst, \ |
4211 | &produced_chars); \ | |
4ed46869 KH |
4212 | } while (1) |
4213 | ||
05e6f5dc | 4214 | |
df7492f9 KH |
4215 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
4216 | do { \ | |
1a4990fb | 4217 | int code = ENCODE_CHAR ((charset), (c)); \ |
df7492f9 KH |
4218 | \ |
4219 | if (CHARSET_DIMENSION (charset) == 1) \ | |
4220 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
4221 | else \ | |
4222 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 4223 | } while (0) |
bdd9fb48 | 4224 | |
05e6f5dc | 4225 | |
4ed46869 | 4226 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 4227 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
4228 | Return new DST. */ |
4229 | ||
4230 | unsigned char * | |
cf84bb53 JB |
4231 | encode_invocation_designation (struct charset *charset, |
4232 | struct coding_system *coding, | |
4233 | unsigned char *dst, int *p_nchars) | |
4ed46869 | 4234 | { |
df7492f9 KH |
4235 | int multibytep = coding->dst_multibyte; |
4236 | int produced_chars = *p_nchars; | |
4ed46869 | 4237 | int reg; /* graphic register number */ |
df7492f9 | 4238 | int id = CHARSET_ID (charset); |
4ed46869 KH |
4239 | |
4240 | /* At first, check designations. */ | |
4241 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 4242 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
4243 | break; |
4244 | ||
4245 | if (reg >= 4) | |
4246 | { | |
4247 | /* CHARSET is not yet designated to any graphic registers. */ | |
4248 | /* At first check the requested designation. */ | |
df7492f9 KH |
4249 | reg = CODING_ISO_REQUEST (coding, id); |
4250 | if (reg < 0) | |
1ba9e4ab KH |
4251 | /* Since CHARSET requests no special designation, designate it |
4252 | to graphic register 0. */ | |
4ed46869 KH |
4253 | reg = 0; |
4254 | ||
4255 | ENCODE_DESIGNATION (charset, reg, coding); | |
4256 | } | |
4257 | ||
df7492f9 KH |
4258 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
4259 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
4260 | { |
4261 | /* Since the graphic register REG is not invoked to any graphic | |
4262 | planes, invoke it to graphic plane 0. */ | |
4263 | switch (reg) | |
4264 | { | |
4265 | case 0: /* graphic register 0 */ | |
4266 | ENCODE_SHIFT_IN; | |
4267 | break; | |
4268 | ||
4269 | case 1: /* graphic register 1 */ | |
4270 | ENCODE_SHIFT_OUT; | |
4271 | break; | |
4272 | ||
4273 | case 2: /* graphic register 2 */ | |
df7492f9 | 4274 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4275 | ENCODE_SINGLE_SHIFT_2; |
4276 | else | |
4277 | ENCODE_LOCKING_SHIFT_2; | |
4278 | break; | |
4279 | ||
4280 | case 3: /* graphic register 3 */ | |
df7492f9 | 4281 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4282 | ENCODE_SINGLE_SHIFT_3; |
4283 | else | |
4284 | ENCODE_LOCKING_SHIFT_3; | |
4285 | break; | |
4286 | } | |
4287 | } | |
b73bfc1c | 4288 | |
df7492f9 | 4289 | *p_nchars = produced_chars; |
4ed46869 KH |
4290 | return dst; |
4291 | } | |
4292 | ||
df7492f9 KH |
4293 | /* The following three macros produce codes for indicating direction |
4294 | of text. */ | |
4295 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 4296 | do { \ |
df7492f9 KH |
4297 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
4298 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 4299 | else \ |
df7492f9 | 4300 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
4301 | } while (0) |
4302 | ||
ec6d2bb8 | 4303 | |
df7492f9 KH |
4304 | #define ENCODE_DIRECTION_R2L() \ |
4305 | do { \ | |
4306 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
4307 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
4308 | } while (0) |
4309 | ||
ec6d2bb8 | 4310 | |
df7492f9 | 4311 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 4312 | do { \ |
df7492f9 KH |
4313 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
4314 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 4315 | } while (0) |
4ed46869 | 4316 | |
4ed46869 KH |
4317 | |
4318 | /* Produce codes for designation and invocation to reset the graphic | |
4319 | planes and registers to initial state. */ | |
df7492f9 KH |
4320 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4321 | do { \ | |
4322 | int reg; \ | |
4323 | struct charset *charset; \ | |
4324 | \ | |
4325 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4326 | ENCODE_SHIFT_IN; \ | |
4327 | for (reg = 0; reg < 4; reg++) \ | |
4328 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4329 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4330 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4331 | { \ | |
4332 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4333 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4334 | } \ | |
4ed46869 KH |
4335 | } while (0) |
4336 | ||
df7492f9 | 4337 | |
bdd9fb48 | 4338 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 4339 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
4340 | |
4341 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4342 | find all the necessary designations. */ |
4343 | ||
b73bfc1c | 4344 | static unsigned char * |
cf84bb53 JB |
4345 | encode_designation_at_bol (struct coding_system *coding, int *charbuf, |
4346 | int *charbuf_end, unsigned char *dst) | |
e0e989f6 | 4347 | { |
df7492f9 | 4348 | struct charset *charset; |
bdd9fb48 KH |
4349 | /* Table of charsets to be designated to each graphic register. */ |
4350 | int r[4]; | |
df7492f9 KH |
4351 | int c, found = 0, reg; |
4352 | int produced_chars = 0; | |
4353 | int multibytep = coding->dst_multibyte; | |
4354 | Lisp_Object attrs; | |
4355 | Lisp_Object charset_list; | |
4356 | ||
4357 | attrs = CODING_ID_ATTRS (coding->id); | |
4358 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4359 | if (EQ (charset_list, Qiso_2022)) | |
4360 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4361 | |
4362 | for (reg = 0; reg < 4; reg++) | |
4363 | r[reg] = -1; | |
4364 | ||
b73bfc1c | 4365 | while (found < 4) |
e0e989f6 | 4366 | { |
df7492f9 KH |
4367 | int id; |
4368 | ||
4369 | c = *charbuf++; | |
b73bfc1c KH |
4370 | if (c == '\n') |
4371 | break; | |
df7492f9 KH |
4372 | charset = char_charset (c, charset_list, NULL); |
4373 | id = CHARSET_ID (charset); | |
4374 | reg = CODING_ISO_REQUEST (coding, id); | |
4375 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4376 | { |
4377 | found++; | |
df7492f9 | 4378 | r[reg] = id; |
bdd9fb48 | 4379 | } |
bdd9fb48 KH |
4380 | } |
4381 | ||
4382 | if (found) | |
4383 | { | |
4384 | for (reg = 0; reg < 4; reg++) | |
4385 | if (r[reg] >= 0 | |
df7492f9 KH |
4386 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4387 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4388 | } |
b73bfc1c KH |
4389 | |
4390 | return dst; | |
e0e989f6 KH |
4391 | } |
4392 | ||
4ed46869 KH |
4393 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4394 | ||
df7492f9 | 4395 | static int |
971de7fb | 4396 | encode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 4397 | { |
df7492f9 KH |
4398 | int multibytep = coding->dst_multibyte; |
4399 | int *charbuf = coding->charbuf; | |
4400 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4401 | unsigned char *dst = coding->destination + coding->produced; | |
4402 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4403 | int safe_room = 16; | |
4404 | int bol_designation | |
4405 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
4406 | && CODING_ISO_BOL (coding)); | |
4407 | int produced_chars = 0; | |
4408 | Lisp_Object attrs, eol_type, charset_list; | |
4409 | int ascii_compatible; | |
b73bfc1c | 4410 | int c; |
ff0dacd7 | 4411 | int preferred_charset_id = -1; |
05e6f5dc | 4412 | |
24a73b0a | 4413 | CODING_GET_INFO (coding, attrs, charset_list); |
0a9564cb | 4414 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
24a73b0a KH |
4415 | if (VECTORP (eol_type)) |
4416 | eol_type = Qunix; | |
4417 | ||
004068e4 | 4418 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4419 | /* Charset list may have been changed. */ |
287c57d7 | 4420 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
1b3b981b | 4421 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
0eecad43 | 4422 | |
a552b35a KH |
4423 | ascii_compatible |
4424 | = (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)) | |
4425 | && ! (CODING_ISO_FLAGS (coding) & (CODING_ISO_FLAG_DESIGNATION | |
4426 | | CODING_ISO_FLAG_LOCKING_SHIFT))); | |
bdd9fb48 | 4427 | |
df7492f9 | 4428 | while (charbuf < charbuf_end) |
4ed46869 | 4429 | { |
df7492f9 | 4430 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4431 | |
df7492f9 | 4432 | if (bol_designation) |
b73bfc1c | 4433 | { |
df7492f9 | 4434 | unsigned char *dst_prev = dst; |
4ed46869 | 4435 | |
bdd9fb48 | 4436 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
4437 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
4438 | bol_designation = 0; | |
4439 | /* We are sure that designation sequences are all ASCII bytes. */ | |
4440 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
4441 | } |
4442 | ||
df7492f9 | 4443 | c = *charbuf++; |
ec6d2bb8 | 4444 | |
ff0dacd7 KH |
4445 | if (c < 0) |
4446 | { | |
4447 | /* Handle an annotation. */ | |
4448 | switch (*charbuf) | |
ec6d2bb8 | 4449 | { |
ff0dacd7 KH |
4450 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4451 | /* Not yet implemented. */ | |
4452 | break; | |
4453 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4454 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4455 | if (preferred_charset_id >= 0 |
4456 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4457 | charset_list))) | |
4458 | preferred_charset_id = -1; | |
4459 | break; | |
4460 | default: | |
4461 | abort (); | |
4ed46869 | 4462 | } |
ff0dacd7 KH |
4463 | charbuf += -c - 1; |
4464 | continue; | |
4ed46869 | 4465 | } |
ec6d2bb8 | 4466 | |
b73bfc1c KH |
4467 | /* Now encode the character C. */ |
4468 | if (c < 0x20 || c == 0x7F) | |
4469 | { | |
df7492f9 KH |
4470 | if (c == '\n' |
4471 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4472 | { |
df7492f9 KH |
4473 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4474 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4475 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4476 | { |
df7492f9 KH |
4477 | int i; |
4478 | ||
4479 | for (i = 0; i < 4; i++) | |
4480 | CODING_ISO_DESIGNATION (coding, i) | |
4481 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4482 | } |
df7492f9 KH |
4483 | bol_designation |
4484 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 4485 | } |
df7492f9 KH |
4486 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4487 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4488 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4489 | } |
df7492f9 | 4490 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4491 | { |
df7492f9 KH |
4492 | if (ascii_compatible) |
4493 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4494 | else |
19a8d9e0 | 4495 | { |
bf16eb23 KH |
4496 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4497 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4498 | } |
4ed46869 | 4499 | } |
16eafb5d | 4500 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4501 | { |
16eafb5d KH |
4502 | c = CHAR_TO_BYTE8 (c); |
4503 | EMIT_ONE_BYTE (c); | |
88993dfd | 4504 | } |
b73bfc1c | 4505 | else |
df7492f9 | 4506 | { |
ff0dacd7 | 4507 | struct charset *charset; |
b73bfc1c | 4508 | |
ff0dacd7 KH |
4509 | if (preferred_charset_id >= 0) |
4510 | { | |
4511 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
4512 | if (! CHAR_CHARSET_P (c, charset)) | |
4513 | charset = char_charset (c, charset_list, NULL); | |
4514 | } | |
4515 | else | |
4516 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
4517 | if (!charset) |
4518 | { | |
41cbe562 KH |
4519 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4520 | { | |
4521 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4522 | charset = CHARSET_FROM_ID (charset_ascii); | |
4523 | } | |
4524 | else | |
4525 | { | |
4526 | c = coding->default_char; | |
4527 | charset = char_charset (c, charset_list, NULL); | |
4528 | } | |
df7492f9 KH |
4529 | } |
4530 | ENCODE_ISO_CHARACTER (charset, c); | |
4531 | } | |
84fbb8a0 | 4532 | } |
b73bfc1c | 4533 | |
df7492f9 KH |
4534 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4535 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4536 | { | |
4537 | ASSURE_DESTINATION (safe_room); | |
4538 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4539 | } | |
065e3595 | 4540 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4541 | CODING_ISO_BOL (coding) = bol_designation; |
4542 | coding->produced_char += produced_chars; | |
4543 | coding->produced = dst - coding->destination; | |
4544 | return 0; | |
4ed46869 KH |
4545 | } |
4546 | ||
4547 | \f | |
df7492f9 | 4548 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4549 | |
df7492f9 | 4550 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4551 | quite widely. So, for the moment, Emacs supports them in the bare |
4552 | C code. But, in the future, they may be supported only by CCL. */ | |
4553 | ||
4554 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4555 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4556 | as is. A character of charset katakana-jisx0201 is encoded by | |
4557 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4558 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4559 | so that it fit in the range below. |
4ed46869 KH |
4560 | |
4561 | --- CODE RANGE of SJIS --- | |
4562 | (character set) (range) | |
4563 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4564 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4565 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4566 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4567 | ------------------------------- |
4568 | ||
4569 | */ | |
4570 | ||
4571 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4572 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4573 | character set and is encoded in two-byte. |
4ed46869 KH |
4574 | |
4575 | --- CODE RANGE of BIG5 --- | |
4576 | (character set) (range) | |
4577 | ASCII 0x00 .. 0x7F | |
4578 | Big5 (1st byte) 0xA1 .. 0xFE | |
4579 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4580 | -------------------------- | |
4581 | ||
df7492f9 | 4582 | */ |
4ed46869 KH |
4583 | |
4584 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4585 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 4586 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 4587 | |
0a28aafb | 4588 | static int |
cf84bb53 JB |
4589 | detect_coding_sjis (struct coding_system *coding, |
4590 | struct coding_detection_info *detect_info) | |
4ed46869 | 4591 | { |
065e3595 | 4592 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4593 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4594 | int multibytep = coding->src_multibyte; |
4595 | int consumed_chars = 0; | |
4596 | int found = 0; | |
b73bfc1c | 4597 | int c; |
f07190ca KH |
4598 | Lisp_Object attrs, charset_list; |
4599 | int max_first_byte_of_2_byte_code; | |
4600 | ||
4601 | CODING_GET_INFO (coding, attrs, charset_list); | |
4602 | max_first_byte_of_2_byte_code | |
4603 | = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF); | |
df7492f9 | 4604 | |
ff0dacd7 | 4605 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4606 | /* A coding system of this category is always ASCII compatible. */ |
4607 | src += coding->head_ascii; | |
4ed46869 | 4608 | |
b73bfc1c | 4609 | while (1) |
4ed46869 | 4610 | { |
065e3595 | 4611 | src_base = src; |
df7492f9 | 4612 | ONE_MORE_BYTE (c); |
682169fe KH |
4613 | if (c < 0x80) |
4614 | continue; | |
f07190ca KH |
4615 | if ((c >= 0x81 && c <= 0x9F) |
4616 | || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code)) | |
4ed46869 | 4617 | { |
df7492f9 | 4618 | ONE_MORE_BYTE (c); |
682169fe | 4619 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4620 | break; |
ff0dacd7 | 4621 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4622 | } |
df7492f9 | 4623 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4624 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4625 | else |
4626 | break; | |
4ed46869 | 4627 | } |
ff0dacd7 | 4628 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4629 | return 0; |
4630 | ||
4631 | no_more_source: | |
065e3595 | 4632 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4633 | { |
ff0dacd7 | 4634 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 4635 | return 0; |
4ed46869 | 4636 | } |
ff0dacd7 KH |
4637 | detect_info->found |= found; |
4638 | return 1; | |
4ed46869 KH |
4639 | } |
4640 | ||
4641 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4642 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 4643 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 4644 | |
0a28aafb | 4645 | static int |
cf84bb53 JB |
4646 | detect_coding_big5 (struct coding_system *coding, |
4647 | struct coding_detection_info *detect_info) | |
4ed46869 | 4648 | { |
065e3595 | 4649 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4650 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4651 | int multibytep = coding->src_multibyte; |
4652 | int consumed_chars = 0; | |
4653 | int found = 0; | |
b73bfc1c | 4654 | int c; |
fa42c37f | 4655 | |
ff0dacd7 | 4656 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4657 | /* A coding system of this category is always ASCII compatible. */ |
4658 | src += coding->head_ascii; | |
fa42c37f | 4659 | |
b73bfc1c | 4660 | while (1) |
fa42c37f | 4661 | { |
065e3595 | 4662 | src_base = src; |
df7492f9 KH |
4663 | ONE_MORE_BYTE (c); |
4664 | if (c < 0x80) | |
fa42c37f | 4665 | continue; |
df7492f9 | 4666 | if (c >= 0xA1) |
fa42c37f | 4667 | { |
df7492f9 KH |
4668 | ONE_MORE_BYTE (c); |
4669 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4670 | return 0; |
ff0dacd7 | 4671 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4672 | } |
df7492f9 KH |
4673 | else |
4674 | break; | |
fa42c37f | 4675 | } |
ff0dacd7 | 4676 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4677 | return 0; |
fa42c37f | 4678 | |
df7492f9 | 4679 | no_more_source: |
065e3595 | 4680 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4681 | { |
ff0dacd7 | 4682 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4683 | return 0; |
4684 | } | |
ff0dacd7 KH |
4685 | detect_info->found |= found; |
4686 | return 1; | |
fa42c37f KH |
4687 | } |
4688 | ||
4ed46869 KH |
4689 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4690 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4691 | |
b73bfc1c | 4692 | static void |
971de7fb | 4693 | decode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4694 | { |
8f924df7 KH |
4695 | const unsigned char *src = coding->source + coding->consumed; |
4696 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4697 | const unsigned char *src_base; | |
69a80ea3 | 4698 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4699 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4700 | the end. */ |
69a80ea3 | 4701 | int *charbuf_end |
df80c7f0 | 4702 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
4703 | int consumed_chars = 0, consumed_chars_base; |
4704 | int multibytep = coding->src_multibyte; | |
4705 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4706 | struct charset *charset_kanji2; |
24a73b0a | 4707 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4708 | int char_offset = coding->produced_char; |
4709 | int last_offset = char_offset; | |
4710 | int last_id = charset_ascii; | |
0a9564cb EZ |
4711 | int eol_crlf = |
4712 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4713 | int byte_after_cr = -1; |
a5d301df | 4714 | |
24a73b0a | 4715 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4716 | |
4717 | val = charset_list; | |
4718 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4719 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4720 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4721 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4722 | |
b73bfc1c | 4723 | while (1) |
4ed46869 | 4724 | { |
df7492f9 | 4725 | int c, c1; |
24a73b0a | 4726 | struct charset *charset; |
fa42c37f | 4727 | |
b73bfc1c | 4728 | src_base = src; |
df7492f9 | 4729 | consumed_chars_base = consumed_chars; |
fa42c37f | 4730 | |
df7492f9 | 4731 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4732 | { |
4733 | if (byte_after_cr >= 0) | |
4734 | src_base--; | |
4735 | break; | |
4736 | } | |
df7492f9 | 4737 | |
119852e7 KH |
4738 | if (byte_after_cr >= 0) |
4739 | c = byte_after_cr, byte_after_cr = -1; | |
4740 | else | |
4741 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4742 | if (c < 0) |
4743 | goto invalid_code; | |
24a73b0a | 4744 | if (c < 0x80) |
119852e7 KH |
4745 | { |
4746 | if (eol_crlf && c == '\r') | |
4747 | ONE_MORE_BYTE (byte_after_cr); | |
4748 | charset = charset_roman; | |
4749 | } | |
57a47f8a | 4750 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4751 | goto invalid_code; |
57a47f8a KH |
4752 | else if (c >= 0xA1 && c <= 0xDF) |
4753 | { | |
4754 | /* SJIS -> JISX0201-Kana */ | |
4755 | c &= 0x7F; | |
4756 | charset = charset_kana; | |
4757 | } | |
4758 | else if (c <= 0xEF) | |
df7492f9 | 4759 | { |
57a47f8a KH |
4760 | /* SJIS -> JISX0208 */ |
4761 | ONE_MORE_BYTE (c1); | |
4762 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4763 | goto invalid_code; |
57a47f8a KH |
4764 | c = (c << 8) | c1; |
4765 | SJIS_TO_JIS (c); | |
4766 | charset = charset_kanji; | |
4767 | } | |
4768 | else if (c <= 0xFC && charset_kanji2) | |
4769 | { | |
c6876370 | 4770 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4771 | ONE_MORE_BYTE (c1); |
4772 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4773 | goto invalid_code; |
57a47f8a KH |
4774 | c = (c << 8) | c1; |
4775 | SJIS_TO_JIS2 (c); | |
4776 | charset = charset_kanji2; | |
df7492f9 | 4777 | } |
57a47f8a KH |
4778 | else |
4779 | goto invalid_code; | |
24a73b0a KH |
4780 | if (charset->id != charset_ascii |
4781 | && last_id != charset->id) | |
4782 | { | |
4783 | if (last_id != charset_ascii) | |
69a80ea3 | 4784 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4785 | last_id = charset->id; |
4786 | last_offset = char_offset; | |
4787 | } | |
4788 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4789 | *charbuf++ = c; |
ff0dacd7 | 4790 | char_offset++; |
df7492f9 | 4791 | continue; |
b73bfc1c | 4792 | |
df7492f9 KH |
4793 | invalid_code: |
4794 | src = src_base; | |
4795 | consumed_chars = consumed_chars_base; | |
4796 | ONE_MORE_BYTE (c); | |
065e3595 | 4797 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4798 | char_offset++; |
df7492f9 KH |
4799 | coding->errors++; |
4800 | } | |
fa42c37f | 4801 | |
df7492f9 | 4802 | no_more_source: |
ff0dacd7 | 4803 | if (last_id != charset_ascii) |
69a80ea3 | 4804 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4805 | coding->consumed_char += consumed_chars_base; |
4806 | coding->consumed = src_base - coding->source; | |
4807 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4808 | } |
4809 | ||
b73bfc1c | 4810 | static void |
971de7fb | 4811 | decode_coding_big5 (struct coding_system *coding) |
4ed46869 | 4812 | { |
8f924df7 KH |
4813 | const unsigned char *src = coding->source + coding->consumed; |
4814 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4815 | const unsigned char *src_base; | |
69a80ea3 | 4816 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4817 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4818 | the end. */ |
69a80ea3 | 4819 | int *charbuf_end |
df80c7f0 | 4820 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
4821 | int consumed_chars = 0, consumed_chars_base; |
4822 | int multibytep = coding->src_multibyte; | |
4823 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4824 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4825 | int char_offset = coding->produced_char; |
4826 | int last_offset = char_offset; | |
4827 | int last_id = charset_ascii; | |
0a9564cb EZ |
4828 | int eol_crlf = |
4829 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4830 | int byte_after_cr = -1; |
df7492f9 | 4831 | |
24a73b0a | 4832 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4833 | val = charset_list; |
4834 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4835 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4836 | |
b73bfc1c | 4837 | while (1) |
4ed46869 | 4838 | { |
df7492f9 | 4839 | int c, c1; |
24a73b0a | 4840 | struct charset *charset; |
b73bfc1c KH |
4841 | |
4842 | src_base = src; | |
df7492f9 KH |
4843 | consumed_chars_base = consumed_chars; |
4844 | ||
4845 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4846 | { |
4847 | if (byte_after_cr >= 0) | |
4848 | src_base--; | |
4849 | break; | |
4850 | } | |
df7492f9 | 4851 | |
119852e7 | 4852 | if (byte_after_cr >= 0) |
14daee73 | 4853 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4854 | else |
4855 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4856 | |
065e3595 KH |
4857 | if (c < 0) |
4858 | goto invalid_code; | |
24a73b0a | 4859 | if (c < 0x80) |
119852e7 | 4860 | { |
14daee73 | 4861 | if (eol_crlf && c == '\r') |
119852e7 KH |
4862 | ONE_MORE_BYTE (byte_after_cr); |
4863 | charset = charset_roman; | |
4864 | } | |
24a73b0a | 4865 | else |
4ed46869 | 4866 | { |
24a73b0a KH |
4867 | /* BIG5 -> Big5 */ |
4868 | if (c < 0xA1 || c > 0xFE) | |
4869 | goto invalid_code; | |
4870 | ONE_MORE_BYTE (c1); | |
4871 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4872 | goto invalid_code; | |
4873 | c = c << 8 | c1; | |
4874 | charset = charset_big5; | |
4ed46869 | 4875 | } |
24a73b0a KH |
4876 | if (charset->id != charset_ascii |
4877 | && last_id != charset->id) | |
df7492f9 | 4878 | { |
24a73b0a | 4879 | if (last_id != charset_ascii) |
69a80ea3 | 4880 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4881 | last_id = charset->id; |
4882 | last_offset = char_offset; | |
4ed46869 | 4883 | } |
24a73b0a | 4884 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4885 | *charbuf++ = c; |
ff0dacd7 | 4886 | char_offset++; |
fb88bf2d KH |
4887 | continue; |
4888 | ||
df7492f9 | 4889 | invalid_code: |
4ed46869 | 4890 | src = src_base; |
df7492f9 KH |
4891 | consumed_chars = consumed_chars_base; |
4892 | ONE_MORE_BYTE (c); | |
065e3595 | 4893 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4894 | char_offset++; |
df7492f9 | 4895 | coding->errors++; |
fb88bf2d | 4896 | } |
d46c5b12 | 4897 | |
df7492f9 | 4898 | no_more_source: |
ff0dacd7 | 4899 | if (last_id != charset_ascii) |
69a80ea3 | 4900 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4901 | coding->consumed_char += consumed_chars_base; |
4902 | coding->consumed = src_base - coding->source; | |
4903 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4904 | } |
4905 | ||
4906 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4907 | This function can encode charsets `ascii', `katakana-jisx0201', |
4908 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4909 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4910 | (i.e. do not have extended leading-codes). Characters of other |
4911 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4912 | SJIS text, else encode BIG5 text. */ | |
4913 | ||
df7492f9 | 4914 | static int |
971de7fb | 4915 | encode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4916 | { |
df7492f9 KH |
4917 | int multibytep = coding->dst_multibyte; |
4918 | int *charbuf = coding->charbuf; | |
4919 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4920 | unsigned char *dst = coding->destination + coding->produced; | |
4921 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4922 | int safe_room = 4; | |
4923 | int produced_chars = 0; | |
24a73b0a | 4924 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4925 | int ascii_compatible; |
4926 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4927 | struct charset *charset_kanji2; |
df7492f9 | 4928 | int c; |
a5d301df | 4929 | |
24a73b0a | 4930 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4931 | val = charset_list; |
4932 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4933 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
4934 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4935 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4936 | |
df7492f9 | 4937 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4938 | |
df7492f9 KH |
4939 | while (charbuf < charbuf_end) |
4940 | { | |
4941 | ASSURE_DESTINATION (safe_room); | |
4942 | c = *charbuf++; | |
b73bfc1c | 4943 | /* Now encode the character C. */ |
df7492f9 KH |
4944 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4945 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4946 | else if (CHAR_BYTE8_P (c)) |
4947 | { | |
4948 | c = CHAR_TO_BYTE8 (c); | |
4949 | EMIT_ONE_BYTE (c); | |
4950 | } | |
df7492f9 | 4951 | else |
b73bfc1c | 4952 | { |
df7492f9 KH |
4953 | unsigned code; |
4954 | struct charset *charset = char_charset (c, charset_list, &code); | |
4955 | ||
4956 | if (!charset) | |
4ed46869 | 4957 | { |
41cbe562 | 4958 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4959 | { |
41cbe562 KH |
4960 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4961 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4962 | } |
41cbe562 | 4963 | else |
b73bfc1c | 4964 | { |
41cbe562 KH |
4965 | c = coding->default_char; |
4966 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4967 | } |
b73bfc1c | 4968 | } |
df7492f9 KH |
4969 | if (code == CHARSET_INVALID_CODE (charset)) |
4970 | abort (); | |
4971 | if (charset == charset_kanji) | |
4972 | { | |
4973 | int c1, c2; | |
4974 | JIS_TO_SJIS (code); | |
4975 | c1 = code >> 8, c2 = code & 0xFF; | |
4976 | EMIT_TWO_BYTES (c1, c2); | |
4977 | } | |
4978 | else if (charset == charset_kana) | |
4979 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4980 | else if (charset_kanji2 && charset == charset_kanji2) |
4981 | { | |
4982 | int c1, c2; | |
4983 | ||
4984 | c1 = code >> 8; | |
f07190ca KH |
4985 | if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25) |
4986 | || c1 == 0x28 | |
57a47f8a KH |
4987 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) |
4988 | { | |
4989 | JIS_TO_SJIS2 (code); | |
4990 | c1 = code >> 8, c2 = code & 0xFF; | |
4991 | EMIT_TWO_BYTES (c1, c2); | |
4992 | } | |
4993 | else | |
4994 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4995 | } | |
df7492f9 KH |
4996 | else |
4997 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4998 | } | |
4999 | } | |
065e3595 | 5000 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5001 | coding->produced_char += produced_chars; |
5002 | coding->produced = dst - coding->destination; | |
5003 | return 0; | |
5004 | } | |
5005 | ||
5006 | static int | |
971de7fb | 5007 | encode_coding_big5 (struct coding_system *coding) |
df7492f9 KH |
5008 | { |
5009 | int multibytep = coding->dst_multibyte; | |
5010 | int *charbuf = coding->charbuf; | |
5011 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5012 | unsigned char *dst = coding->destination + coding->produced; | |
5013 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5014 | int safe_room = 4; | |
5015 | int produced_chars = 0; | |
24a73b0a | 5016 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
5017 | int ascii_compatible; |
5018 | struct charset *charset_roman, *charset_big5; | |
5019 | int c; | |
5020 | ||
24a73b0a | 5021 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
5022 | val = charset_list; |
5023 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
5024 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
5025 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
5026 | ||
5027 | while (charbuf < charbuf_end) | |
5028 | { | |
5029 | ASSURE_DESTINATION (safe_room); | |
5030 | c = *charbuf++; | |
5031 | /* Now encode the character C. */ | |
5032 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
5033 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
5034 | else if (CHAR_BYTE8_P (c)) |
5035 | { | |
5036 | c = CHAR_TO_BYTE8 (c); | |
5037 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
5038 | } |
5039 | else | |
5040 | { | |
df7492f9 KH |
5041 | unsigned code; |
5042 | struct charset *charset = char_charset (c, charset_list, &code); | |
5043 | ||
5044 | if (! charset) | |
b73bfc1c | 5045 | { |
41cbe562 | 5046 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 5047 | { |
41cbe562 KH |
5048 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
5049 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 5050 | } |
41cbe562 | 5051 | else |
0eecad43 | 5052 | { |
41cbe562 KH |
5053 | c = coding->default_char; |
5054 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 5055 | } |
4ed46869 | 5056 | } |
df7492f9 KH |
5057 | if (code == CHARSET_INVALID_CODE (charset)) |
5058 | abort (); | |
5059 | if (charset == charset_big5) | |
b73bfc1c | 5060 | { |
df7492f9 KH |
5061 | int c1, c2; |
5062 | ||
5063 | c1 = code >> 8, c2 = code & 0xFF; | |
5064 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 5065 | } |
df7492f9 KH |
5066 | else |
5067 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 5068 | } |
4ed46869 | 5069 | } |
065e3595 | 5070 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5071 | coding->produced_char += produced_chars; |
5072 | coding->produced = dst - coding->destination; | |
5073 | return 0; | |
4ed46869 KH |
5074 | } |
5075 | ||
5076 | \f | |
df7492f9 | 5077 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
5078 | |
5079 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
5080 | Check if a text is encoded in a coding system of which | |
5081 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 5082 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 5083 | |
0a28aafb | 5084 | static int |
cf84bb53 JB |
5085 | detect_coding_ccl (struct coding_system *coding, |
5086 | struct coding_detection_info *detect_info) | |
1397dc18 | 5087 | { |
065e3595 | 5088 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5089 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5090 | int multibytep = coding->src_multibyte; |
5091 | int consumed_chars = 0; | |
5092 | int found = 0; | |
0e219d54 | 5093 | unsigned char *valids; |
df7492f9 KH |
5094 | int head_ascii = coding->head_ascii; |
5095 | Lisp_Object attrs; | |
5096 | ||
ff0dacd7 KH |
5097 | detect_info->checked |= CATEGORY_MASK_CCL; |
5098 | ||
df7492f9 | 5099 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 5100 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
5101 | attrs = CODING_ID_ATTRS (coding->id); |
5102 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
5103 | src += head_ascii; | |
1397dc18 | 5104 | |
b73bfc1c | 5105 | while (1) |
1397dc18 | 5106 | { |
df7492f9 | 5107 | int c; |
065e3595 KH |
5108 | |
5109 | src_base = src; | |
df7492f9 | 5110 | ONE_MORE_BYTE (c); |
065e3595 | 5111 | if (c < 0 || ! valids[c]) |
df7492f9 | 5112 | break; |
ff0dacd7 KH |
5113 | if ((valids[c] > 1)) |
5114 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 5115 | } |
ff0dacd7 | 5116 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
5117 | return 0; |
5118 | ||
5119 | no_more_source: | |
ff0dacd7 KH |
5120 | detect_info->found |= found; |
5121 | return 1; | |
df7492f9 KH |
5122 | } |
5123 | ||
5124 | static void | |
971de7fb | 5125 | decode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5126 | { |
7c78e542 | 5127 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 5128 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
5129 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5130 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
5131 | int consumed_chars = 0; |
5132 | int multibytep = coding->src_multibyte; | |
d0396581 | 5133 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 | 5134 | int source_charbuf[1024]; |
fbdc1721 | 5135 | int source_byteidx[1025]; |
24a73b0a | 5136 | Lisp_Object attrs, charset_list; |
df7492f9 | 5137 | |
24a73b0a | 5138 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5139 | |
d0396581 | 5140 | while (1) |
df7492f9 | 5141 | { |
7c78e542 | 5142 | const unsigned char *p = src; |
df7492f9 KH |
5143 | int i = 0; |
5144 | ||
5145 | if (multibytep) | |
fbdc1721 KH |
5146 | { |
5147 | while (i < 1024 && p < src_end) | |
5148 | { | |
5149 | source_byteidx[i] = p - src; | |
5150 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
5151 | } | |
5152 | source_byteidx[i] = p - src; | |
5153 | } | |
df7492f9 KH |
5154 | else |
5155 | while (i < 1024 && p < src_end) | |
5156 | source_charbuf[i++] = *p++; | |
8f924df7 | 5157 | |
df7492f9 | 5158 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
d0396581 KH |
5159 | ccl->last_block = 1; |
5160 | ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf, | |
5161 | charset_list); | |
5162 | charbuf += ccl->produced; | |
fbdc1721 | 5163 | if (multibytep) |
d0396581 | 5164 | src += source_byteidx[ccl->consumed]; |
df7492f9 | 5165 | else |
d0396581 KH |
5166 | src += ccl->consumed; |
5167 | consumed_chars += ccl->consumed; | |
5168 | if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC) | |
df7492f9 KH |
5169 | break; |
5170 | } | |
5171 | ||
d0396581 | 5172 | switch (ccl->status) |
df7492f9 KH |
5173 | { |
5174 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5175 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5176 | break; |
5177 | case CCL_STAT_SUSPEND_BY_DST: | |
d0396581 | 5178 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5179 | break; |
5180 | case CCL_STAT_QUIT: | |
5181 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5182 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5183 | break; |
5184 | default: | |
065e3595 | 5185 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5186 | break; |
5187 | } | |
5188 | coding->consumed_char += consumed_chars; | |
5189 | coding->consumed = src - coding->source; | |
5190 | coding->charbuf_used = charbuf - coding->charbuf; | |
5191 | } | |
5192 | ||
5193 | static int | |
971de7fb | 5194 | encode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5195 | { |
fb608df3 | 5196 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 KH |
5197 | int multibytep = coding->dst_multibyte; |
5198 | int *charbuf = coding->charbuf; | |
5199 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5200 | unsigned char *dst = coding->destination + coding->produced; | |
5201 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 KH |
5202 | int destination_charbuf[1024]; |
5203 | int i, produced_chars = 0; | |
24a73b0a | 5204 | Lisp_Object attrs, charset_list; |
df7492f9 | 5205 | |
24a73b0a | 5206 | CODING_GET_INFO (coding, attrs, charset_list); |
fb608df3 KH |
5207 | if (coding->consumed_char == coding->src_chars |
5208 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
5209 | ccl->last_block = 1; | |
df7492f9 | 5210 | |
8cffd3e7 | 5211 | while (charbuf < charbuf_end) |
df7492f9 | 5212 | { |
fb608df3 | 5213 | ccl_driver (ccl, charbuf, destination_charbuf, |
8cffd3e7 | 5214 | charbuf_end - charbuf, 1024, charset_list); |
df7492f9 | 5215 | if (multibytep) |
8cffd3e7 | 5216 | { |
fb608df3 KH |
5217 | ASSURE_DESTINATION (ccl->produced * 2); |
5218 | for (i = 0; i < ccl->produced; i++) | |
8cffd3e7 KH |
5219 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); |
5220 | } | |
df7492f9 KH |
5221 | else |
5222 | { | |
fb608df3 KH |
5223 | ASSURE_DESTINATION (ccl->produced); |
5224 | for (i = 0; i < ccl->produced; i++) | |
df7492f9 | 5225 | *dst++ = destination_charbuf[i] & 0xFF; |
fb608df3 | 5226 | produced_chars += ccl->produced; |
df7492f9 | 5227 | } |
fb608df3 KH |
5228 | charbuf += ccl->consumed; |
5229 | if (ccl->status == CCL_STAT_QUIT | |
5230 | || ccl->status == CCL_STAT_INVALID_CMD) | |
8cffd3e7 | 5231 | break; |
df7492f9 KH |
5232 | } |
5233 | ||
fb608df3 | 5234 | switch (ccl->status) |
df7492f9 KH |
5235 | { |
5236 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5237 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5238 | break; |
5239 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 5240 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5241 | break; |
5242 | case CCL_STAT_QUIT: | |
5243 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5244 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5245 | break; |
5246 | default: | |
065e3595 | 5247 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5248 | break; |
1397dc18 | 5249 | } |
df7492f9 KH |
5250 | |
5251 | coding->produced_char += produced_chars; | |
5252 | coding->produced = dst - coding->destination; | |
5253 | return 0; | |
1397dc18 KH |
5254 | } |
5255 | ||
df7492f9 | 5256 | |
1397dc18 | 5257 | \f |
df7492f9 | 5258 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 5259 | |
b73bfc1c | 5260 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 5261 | |
b73bfc1c | 5262 | static void |
971de7fb | 5263 | decode_coding_raw_text (struct coding_system *coding) |
4ed46869 | 5264 | { |
0a9564cb EZ |
5265 | int eol_crlf = |
5266 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5267 | |
df7492f9 | 5268 | coding->chars_at_source = 1; |
119852e7 KH |
5269 | coding->consumed_char = coding->src_chars; |
5270 | coding->consumed = coding->src_bytes; | |
5271 | if (eol_crlf && coding->source[coding->src_bytes - 1] == '\r') | |
5272 | { | |
5273 | coding->consumed_char--; | |
5274 | coding->consumed--; | |
5275 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
5276 | } | |
5277 | else | |
5278 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 5279 | } |
4ed46869 | 5280 | |
df7492f9 | 5281 | static int |
971de7fb | 5282 | encode_coding_raw_text (struct coding_system *coding) |
df7492f9 KH |
5283 | { |
5284 | int multibytep = coding->dst_multibyte; | |
5285 | int *charbuf = coding->charbuf; | |
5286 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5287 | unsigned char *dst = coding->destination + coding->produced; | |
5288 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
a0ed9b27 | 5289 | int produced_chars = 0; |
b73bfc1c KH |
5290 | int c; |
5291 | ||
df7492f9 | 5292 | if (multibytep) |
b73bfc1c | 5293 | { |
df7492f9 | 5294 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5295 | |
df7492f9 KH |
5296 | if (coding->src_multibyte) |
5297 | while (charbuf < charbuf_end) | |
5298 | { | |
5299 | ASSURE_DESTINATION (safe_room); | |
5300 | c = *charbuf++; | |
5301 | if (ASCII_CHAR_P (c)) | |
5302 | EMIT_ONE_ASCII_BYTE (c); | |
5303 | else if (CHAR_BYTE8_P (c)) | |
5304 | { | |
5305 | c = CHAR_TO_BYTE8 (c); | |
5306 | EMIT_ONE_BYTE (c); | |
5307 | } | |
5308 | else | |
5309 | { | |
5310 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5311 | |
df7492f9 KH |
5312 | CHAR_STRING_ADVANCE (c, p1); |
5313 | while (p0 < p1) | |
9d123124 KH |
5314 | { |
5315 | EMIT_ONE_BYTE (*p0); | |
5316 | p0++; | |
5317 | } | |
df7492f9 KH |
5318 | } |
5319 | } | |
b73bfc1c | 5320 | else |
df7492f9 KH |
5321 | while (charbuf < charbuf_end) |
5322 | { | |
5323 | ASSURE_DESTINATION (safe_room); | |
5324 | c = *charbuf++; | |
5325 | EMIT_ONE_BYTE (c); | |
5326 | } | |
5327 | } | |
5328 | else | |
4ed46869 | 5329 | { |
df7492f9 | 5330 | if (coding->src_multibyte) |
d46c5b12 | 5331 | { |
df7492f9 KH |
5332 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5333 | ||
5334 | while (charbuf < charbuf_end) | |
d46c5b12 | 5335 | { |
df7492f9 KH |
5336 | ASSURE_DESTINATION (safe_room); |
5337 | c = *charbuf++; | |
5338 | if (ASCII_CHAR_P (c)) | |
5339 | *dst++ = c; | |
5340 | else if (CHAR_BYTE8_P (c)) | |
5341 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5342 | else |
df7492f9 | 5343 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5344 | } |
5345 | } | |
df7492f9 KH |
5346 | else |
5347 | { | |
5348 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5349 | while (charbuf < charbuf_end && dst < dst_end) | |
5350 | *dst++ = *charbuf++; | |
8f924df7 | 5351 | } |
319a3947 | 5352 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5353 | } |
065e3595 | 5354 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5355 | coding->produced_char += produced_chars; |
df7492f9 KH |
5356 | coding->produced = dst - coding->destination; |
5357 | return 0; | |
4ed46869 KH |
5358 | } |
5359 | ||
ff0dacd7 KH |
5360 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
5361 | Check if a text is encoded in a charset-based coding system. If it | |
5362 | is, return 1, else return 0. */ | |
5363 | ||
0a28aafb | 5364 | static int |
cf84bb53 JB |
5365 | detect_coding_charset (struct coding_system *coding, |
5366 | struct coding_detection_info *detect_info) | |
1397dc18 | 5367 | { |
065e3595 | 5368 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5369 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5370 | int multibytep = coding->src_multibyte; |
5371 | int consumed_chars = 0; | |
07295713 | 5372 | Lisp_Object attrs, valids, name; |
584948ac | 5373 | int found = 0; |
716b3fa0 | 5374 | int head_ascii = coding->head_ascii; |
07295713 | 5375 | int check_latin_extra = 0; |
1397dc18 | 5376 | |
ff0dacd7 KH |
5377 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5378 | ||
df7492f9 KH |
5379 | coding = &coding_categories[coding_category_charset]; |
5380 | attrs = CODING_ID_ATTRS (coding->id); | |
5381 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 | 5382 | name = CODING_ID_NAME (coding->id); |
51b59d79 | 5383 | if (strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5384 | "iso-8859-", sizeof ("iso-8859-") - 1) == 0 |
51b59d79 | 5385 | || strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5386 | "iso-latin-", sizeof ("iso-latin-") - 1) == 0) |
07295713 | 5387 | check_latin_extra = 1; |
237aabf4 | 5388 | |
df7492f9 | 5389 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5390 | src += head_ascii; |
1397dc18 | 5391 | |
b73bfc1c | 5392 | while (1) |
1397dc18 | 5393 | { |
df7492f9 | 5394 | int c; |
716b3fa0 KH |
5395 | Lisp_Object val; |
5396 | struct charset *charset; | |
5397 | int dim, idx; | |
1397dc18 | 5398 | |
065e3595 | 5399 | src_base = src; |
df7492f9 | 5400 | ONE_MORE_BYTE (c); |
065e3595 KH |
5401 | if (c < 0) |
5402 | continue; | |
716b3fa0 KH |
5403 | val = AREF (valids, c); |
5404 | if (NILP (val)) | |
df7492f9 | 5405 | break; |
584948ac | 5406 | if (c >= 0x80) |
07295713 KH |
5407 | { |
5408 | if (c < 0xA0 | |
237aabf4 JR |
5409 | && check_latin_extra |
5410 | && (!VECTORP (Vlatin_extra_code_table) | |
9f0526cb | 5411 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))) |
07295713 KH |
5412 | break; |
5413 | found = CATEGORY_MASK_CHARSET; | |
5414 | } | |
716b3fa0 KH |
5415 | if (INTEGERP (val)) |
5416 | { | |
5417 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5418 | dim = CHARSET_DIMENSION (charset); | |
5419 | for (idx = 1; idx < dim; idx++) | |
5420 | { | |
5421 | if (src == src_end) | |
5422 | goto too_short; | |
5423 | ONE_MORE_BYTE (c); | |
3ed051d4 | 5424 | if (c < charset->code_space[(dim - 1 - idx) * 2] |
716b3fa0 KH |
5425 | || c > charset->code_space[(dim - 1 - idx) * 2 + 1]) |
5426 | break; | |
5427 | } | |
5428 | if (idx < dim) | |
5429 | break; | |
5430 | } | |
5431 | else | |
5432 | { | |
5433 | idx = 1; | |
5434 | for (; CONSP (val); val = XCDR (val)) | |
5435 | { | |
5436 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5437 | dim = CHARSET_DIMENSION (charset); | |
5438 | while (idx < dim) | |
5439 | { | |
5440 | if (src == src_end) | |
5441 | goto too_short; | |
5442 | ONE_MORE_BYTE (c); | |
5443 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5444 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5445 | break; | |
5446 | idx++; | |
5447 | } | |
5448 | if (idx == dim) | |
5449 | { | |
5450 | val = Qnil; | |
5451 | break; | |
5452 | } | |
5453 | } | |
5454 | if (CONSP (val)) | |
5455 | break; | |
5456 | } | |
df7492f9 | 5457 | } |
716b3fa0 | 5458 | too_short: |
ff0dacd7 | 5459 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5460 | return 0; |
4ed46869 | 5461 | |
df7492f9 | 5462 | no_more_source: |
ff0dacd7 KH |
5463 | detect_info->found |= found; |
5464 | return 1; | |
df7492f9 | 5465 | } |
b73bfc1c | 5466 | |
b73bfc1c | 5467 | static void |
971de7fb | 5468 | decode_coding_charset (struct coding_system *coding) |
4ed46869 | 5469 | { |
8f924df7 KH |
5470 | const unsigned char *src = coding->source + coding->consumed; |
5471 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5472 | const unsigned char *src_base; | |
69a80ea3 | 5473 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 5474 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 5475 | the end. */ |
69a80ea3 | 5476 | int *charbuf_end |
df80c7f0 | 5477 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
5478 | int consumed_chars = 0, consumed_chars_base; |
5479 | int multibytep = coding->src_multibyte; | |
24a73b0a | 5480 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
5481 | int char_offset = coding->produced_char; |
5482 | int last_offset = char_offset; | |
5483 | int last_id = charset_ascii; | |
0a9564cb EZ |
5484 | int eol_crlf = |
5485 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5486 | int byte_after_cr = -1; |
df7492f9 | 5487 | |
24a73b0a | 5488 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 5489 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5490 | |
df7492f9 | 5491 | while (1) |
4ed46869 | 5492 | { |
4eb6d3f1 | 5493 | int c; |
24a73b0a KH |
5494 | Lisp_Object val; |
5495 | struct charset *charset; | |
5496 | int dim; | |
5497 | int len = 1; | |
5498 | unsigned code; | |
df7492f9 KH |
5499 | |
5500 | src_base = src; | |
5501 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5502 | |
df7492f9 | 5503 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5504 | { |
5505 | if (byte_after_cr >= 0) | |
5506 | src_base--; | |
5507 | break; | |
5508 | } | |
df7492f9 | 5509 | |
119852e7 KH |
5510 | if (byte_after_cr >= 0) |
5511 | { | |
5512 | c = byte_after_cr; | |
5513 | byte_after_cr = -1; | |
5514 | } | |
5515 | else | |
5516 | { | |
5517 | ONE_MORE_BYTE (c); | |
5518 | if (eol_crlf && c == '\r') | |
5519 | ONE_MORE_BYTE (byte_after_cr); | |
5520 | } | |
065e3595 KH |
5521 | if (c < 0) |
5522 | goto invalid_code; | |
24a73b0a KH |
5523 | code = c; |
5524 | ||
5525 | val = AREF (valids, c); | |
1b17adfd | 5526 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5527 | goto invalid_code; |
5528 | if (INTEGERP (val)) | |
d46c5b12 | 5529 | { |
24a73b0a KH |
5530 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5531 | dim = CHARSET_DIMENSION (charset); | |
5532 | while (len < dim) | |
b73bfc1c | 5533 | { |
24a73b0a KH |
5534 | ONE_MORE_BYTE (c); |
5535 | code = (code << 8) | c; | |
5536 | len++; | |
b73bfc1c | 5537 | } |
24a73b0a KH |
5538 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5539 | charset, code, c); | |
d46c5b12 | 5540 | } |
df7492f9 | 5541 | else |
d46c5b12 | 5542 | { |
24a73b0a KH |
5543 | /* VAL is a list of charset IDs. It is assured that the |
5544 | list is sorted by charset dimensions (smaller one | |
5545 | comes first). */ | |
5546 | while (CONSP (val)) | |
4eb6d3f1 | 5547 | { |
24a73b0a | 5548 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5549 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5550 | while (len < dim) |
4eb6d3f1 | 5551 | { |
acb2a965 KH |
5552 | ONE_MORE_BYTE (c); |
5553 | code = (code << 8) | c; | |
f9d71dcd | 5554 | len++; |
4eb6d3f1 | 5555 | } |
24a73b0a KH |
5556 | CODING_DECODE_CHAR (coding, src, src_base, |
5557 | src_end, charset, code, c); | |
5558 | if (c >= 0) | |
5559 | break; | |
5560 | val = XCDR (val); | |
ff0dacd7 | 5561 | } |
d46c5b12 | 5562 | } |
24a73b0a KH |
5563 | if (c < 0) |
5564 | goto invalid_code; | |
5565 | if (charset->id != charset_ascii | |
5566 | && last_id != charset->id) | |
5567 | { | |
5568 | if (last_id != charset_ascii) | |
69a80ea3 | 5569 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5570 | last_id = charset->id; |
5571 | last_offset = char_offset; | |
5572 | } | |
5573 | ||
df7492f9 | 5574 | *charbuf++ = c; |
ff0dacd7 | 5575 | char_offset++; |
df7492f9 KH |
5576 | continue; |
5577 | ||
5578 | invalid_code: | |
5579 | src = src_base; | |
5580 | consumed_chars = consumed_chars_base; | |
5581 | ONE_MORE_BYTE (c); | |
065e3595 | 5582 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5583 | char_offset++; |
df7492f9 | 5584 | coding->errors++; |
4ed46869 KH |
5585 | } |
5586 | ||
df7492f9 | 5587 | no_more_source: |
ff0dacd7 | 5588 | if (last_id != charset_ascii) |
69a80ea3 | 5589 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5590 | coding->consumed_char += consumed_chars_base; |
5591 | coding->consumed = src_base - coding->source; | |
5592 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5593 | } |
5594 | ||
df7492f9 | 5595 | static int |
971de7fb | 5596 | encode_coding_charset (struct coding_system *coding) |
4ed46869 | 5597 | { |
df7492f9 KH |
5598 | int multibytep = coding->dst_multibyte; |
5599 | int *charbuf = coding->charbuf; | |
5600 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5601 | unsigned char *dst = coding->destination + coding->produced; | |
5602 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5603 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
5604 | int produced_chars = 0; | |
24a73b0a | 5605 | Lisp_Object attrs, charset_list; |
df7492f9 | 5606 | int ascii_compatible; |
b73bfc1c | 5607 | int c; |
b73bfc1c | 5608 | |
24a73b0a | 5609 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5610 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5611 | |
df7492f9 | 5612 | while (charbuf < charbuf_end) |
4ed46869 | 5613 | { |
4eb6d3f1 | 5614 | struct charset *charset; |
df7492f9 | 5615 | unsigned code; |
8f924df7 | 5616 | |
df7492f9 KH |
5617 | ASSURE_DESTINATION (safe_room); |
5618 | c = *charbuf++; | |
5619 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5620 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5621 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5622 | { |
16eafb5d KH |
5623 | c = CHAR_TO_BYTE8 (c); |
5624 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5625 | } |
d46c5b12 | 5626 | else |
b73bfc1c | 5627 | { |
4eb6d3f1 KH |
5628 | charset = char_charset (c, charset_list, &code); |
5629 | if (charset) | |
5630 | { | |
5631 | if (CHARSET_DIMENSION (charset) == 1) | |
5632 | EMIT_ONE_BYTE (code); | |
5633 | else if (CHARSET_DIMENSION (charset) == 2) | |
5634 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5635 | else if (CHARSET_DIMENSION (charset) == 3) | |
5636 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5637 | else | |
5638 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5639 | (code >> 8) & 0xFF, code & 0xFF); | |
5640 | } | |
5641 | else | |
41cbe562 KH |
5642 | { |
5643 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5644 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5645 | else | |
5646 | c = coding->default_char; | |
5647 | EMIT_ONE_BYTE (c); | |
5648 | } | |
4ed46869 | 5649 | } |
4ed46869 KH |
5650 | } |
5651 | ||
065e3595 | 5652 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5653 | coding->produced_char += produced_chars; |
5654 | coding->produced = dst - coding->destination; | |
5655 | return 0; | |
4ed46869 KH |
5656 | } |
5657 | ||
5658 | \f | |
1397dc18 | 5659 | /*** 7. C library functions ***/ |
4ed46869 | 5660 | |
df7492f9 KH |
5661 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5662 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5663 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5664 | |
ec6d2bb8 | 5665 | void |
971de7fb | 5666 | setup_coding_system (Lisp_Object coding_system, struct coding_system *coding) |
4ed46869 | 5667 | { |
df7492f9 KH |
5668 | Lisp_Object attrs; |
5669 | Lisp_Object eol_type; | |
5670 | Lisp_Object coding_type; | |
4608c386 | 5671 | Lisp_Object val; |
4ed46869 | 5672 | |
df7492f9 | 5673 | if (NILP (coding_system)) |
ae6f73fa | 5674 | coding_system = Qundecided; |
c07c8e12 | 5675 | |
df7492f9 | 5676 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5677 | |
df7492f9 | 5678 | attrs = CODING_ID_ATTRS (coding->id); |
0a9564cb | 5679 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
1f5dbf34 | 5680 | |
df7492f9 KH |
5681 | coding->mode = 0; |
5682 | coding->head_ascii = -1; | |
4a015c45 KH |
5683 | if (VECTORP (eol_type)) |
5684 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5685 | | CODING_REQUIRE_DETECTION_MASK); | |
5686 | else if (! EQ (eol_type, Qunix)) | |
5687 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5688 | | CODING_REQUIRE_ENCODING_MASK); | |
5689 | else | |
5690 | coding->common_flags = 0; | |
5e5c78be KH |
5691 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5692 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5693 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5694 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5695 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5696 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5697 | |
df7492f9 | 5698 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 | 5699 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5700 | coding->safe_charsets = SDATA (val); |
df7492f9 | 5701 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
624bda09 | 5702 | coding->carryover_bytes = 0; |
4608c386 | 5703 | |
df7492f9 KH |
5704 | coding_type = CODING_ATTR_TYPE (attrs); |
5705 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5706 | { |
df7492f9 KH |
5707 | coding->detector = NULL; |
5708 | coding->decoder = decode_coding_raw_text; | |
5709 | coding->encoder = encode_coding_raw_text; | |
5710 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5711 | } |
df7492f9 | 5712 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5713 | { |
df7492f9 KH |
5714 | int i; |
5715 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5716 | ||
5717 | /* Invoke graphic register 0 to plane 0. */ | |
5718 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5719 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5720 | CODING_ISO_INVOCATION (coding, 1) | |
5721 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5722 | /* Setup the initial status of designation. */ | |
5723 | for (i = 0; i < 4; i++) | |
5724 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5725 | /* Not single shifting initially. */ | |
5726 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5727 | /* Beginning of buffer should also be regarded as bol. */ | |
5728 | CODING_ISO_BOL (coding) = 1; | |
5729 | coding->detector = detect_coding_iso_2022; | |
5730 | coding->decoder = decode_coding_iso_2022; | |
5731 | coding->encoder = encode_coding_iso_2022; | |
5732 | if (flags & CODING_ISO_FLAG_SAFE) | |
5733 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5734 | coding->common_flags |
df7492f9 KH |
5735 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5736 | | CODING_REQUIRE_FLUSHING_MASK); | |
5737 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5738 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5739 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5740 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5741 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5742 | { | |
5743 | setup_iso_safe_charsets (attrs); | |
5744 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 5745 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5746 | coding->safe_charsets = SDATA (val); |
df7492f9 KH |
5747 | } |
5748 | CODING_ISO_FLAGS (coding) = flags; | |
e951386e KH |
5749 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; |
5750 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | |
5751 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | |
5752 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
d46c5b12 | 5753 | } |
df7492f9 | 5754 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5755 | { |
df7492f9 KH |
5756 | coding->detector = detect_coding_charset; |
5757 | coding->decoder = decode_coding_charset; | |
5758 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5759 | coding->common_flags |
df7492f9 | 5760 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5761 | } |
df7492f9 | 5762 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5763 | { |
a470d443 KH |
5764 | val = AREF (attrs, coding_attr_utf_bom); |
5765 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5766 | : EQ (val, Qt) ? utf_with_bom | |
5767 | : utf_without_bom); | |
df7492f9 KH |
5768 | coding->detector = detect_coding_utf_8; |
5769 | coding->decoder = decode_coding_utf_8; | |
5770 | coding->encoder = encode_coding_utf_8; | |
5771 | coding->common_flags | |
5772 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5773 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5774 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5775 | } |
5776 | else if (EQ (coding_type, Qutf_16)) | |
5777 | { | |
a470d443 KH |
5778 | val = AREF (attrs, coding_attr_utf_bom); |
5779 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5780 | : EQ (val, Qt) ? utf_with_bom | |
5781 | : utf_without_bom); | |
df7492f9 | 5782 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5783 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5784 | : utf_16_little_endian); |
e19c3639 | 5785 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5786 | coding->detector = detect_coding_utf_16; |
5787 | coding->decoder = decode_coding_utf_16; | |
5788 | coding->encoder = encode_coding_utf_16; | |
5789 | coding->common_flags | |
5790 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5791 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5792 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5793 | } |
df7492f9 | 5794 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5795 | { |
df7492f9 KH |
5796 | coding->detector = detect_coding_ccl; |
5797 | coding->decoder = decode_coding_ccl; | |
5798 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5799 | coding->common_flags |
df7492f9 KH |
5800 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5801 | | CODING_REQUIRE_FLUSHING_MASK); | |
5802 | } | |
5803 | else if (EQ (coding_type, Qemacs_mule)) | |
5804 | { | |
5805 | coding->detector = detect_coding_emacs_mule; | |
5806 | coding->decoder = decode_coding_emacs_mule; | |
5807 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5808 | coding->common_flags |
df7492f9 | 5809 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
e951386e | 5810 | coding->spec.emacs_mule.full_support = 1; |
df7492f9 KH |
5811 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) |
5812 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5813 | { | |
5814 | Lisp_Object tail, safe_charsets; | |
5815 | int max_charset_id = 0; | |
5816 | ||
5817 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5818 | tail = XCDR (tail)) | |
5819 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5820 | max_charset_id = XFASTINT (XCAR (tail)); | |
1b3b981b AS |
5821 | safe_charsets = make_uninit_string (max_charset_id + 1); |
5822 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
5823 | for (tail = Vemacs_mule_charset_list; CONSP (tail); |
5824 | tail = XCDR (tail)) | |
8f924df7 | 5825 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5826 | coding->max_charset_id = max_charset_id; |
1b3b981b | 5827 | coding->safe_charsets = SDATA (safe_charsets); |
e951386e | 5828 | coding->spec.emacs_mule.full_support = 1; |
df7492f9 | 5829 | } |
e951386e KH |
5830 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; |
5831 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | |
df7492f9 KH |
5832 | } |
5833 | else if (EQ (coding_type, Qshift_jis)) | |
5834 | { | |
5835 | coding->detector = detect_coding_sjis; | |
5836 | coding->decoder = decode_coding_sjis; | |
5837 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5838 | coding->common_flags |
df7492f9 KH |
5839 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5840 | } | |
5841 | else if (EQ (coding_type, Qbig5)) | |
5842 | { | |
5843 | coding->detector = detect_coding_big5; | |
5844 | coding->decoder = decode_coding_big5; | |
5845 | coding->encoder = encode_coding_big5; | |
c952af22 | 5846 | coding->common_flags |
df7492f9 KH |
5847 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5848 | } | |
5849 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5850 | { |
df7492f9 KH |
5851 | coding->detector = NULL; |
5852 | coding->decoder = decode_coding_raw_text; | |
5853 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5854 | if (! EQ (eol_type, Qunix)) |
5855 | { | |
5856 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5857 | if (! VECTORP (eol_type)) | |
5858 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5859 | } | |
5860 | ||
4ed46869 | 5861 | } |
4ed46869 | 5862 | |
df7492f9 | 5863 | return; |
4ed46869 KH |
5864 | } |
5865 | ||
0ff61e78 KH |
5866 | /* Return a list of charsets supported by CODING. */ |
5867 | ||
5868 | Lisp_Object | |
971de7fb | 5869 | coding_charset_list (struct coding_system *coding) |
0ff61e78 | 5870 | { |
35befdaa | 5871 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5872 | |
5873 | CODING_GET_INFO (coding, attrs, charset_list); | |
5874 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5875 | { | |
5876 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5877 | ||
5878 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5879 | charset_list = Viso_2022_charset_list; | |
5880 | } | |
5881 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5882 | { | |
5883 | charset_list = Vemacs_mule_charset_list; | |
5884 | } | |
5885 | return charset_list; | |
5886 | } | |
5887 | ||
5888 | ||
e9f91ece KH |
5889 | /* Return a list of charsets supported by CODING-SYSTEM. */ |
5890 | ||
5891 | Lisp_Object | |
971de7fb | 5892 | coding_system_charset_list (Lisp_Object coding_system) |
e9f91ece KH |
5893 | { |
5894 | int id; | |
5895 | Lisp_Object attrs, charset_list; | |
5896 | ||
5897 | CHECK_CODING_SYSTEM_GET_ID (coding_system, id); | |
5898 | attrs = CODING_ID_ATTRS (id); | |
5899 | ||
5900 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5901 | { | |
5902 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5903 | ||
5904 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5905 | charset_list = Viso_2022_charset_list; | |
5906 | else | |
5907 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5908 | } | |
5909 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5910 | { | |
5911 | charset_list = Vemacs_mule_charset_list; | |
5912 | } | |
5913 | else | |
5914 | { | |
5915 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5916 | } | |
5917 | return charset_list; | |
5918 | } | |
5919 | ||
5920 | ||
df7492f9 KH |
5921 | /* Return raw-text or one of its subsidiaries that has the same |
5922 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5923 | |
df7492f9 | 5924 | Lisp_Object |
971de7fb | 5925 | raw_text_coding_system (Lisp_Object coding_system) |
ec6d2bb8 | 5926 | { |
0be8721c | 5927 | Lisp_Object spec, attrs; |
df7492f9 | 5928 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5929 | |
d3e4cb56 KH |
5930 | if (NILP (coding_system)) |
5931 | return Qraw_text; | |
df7492f9 KH |
5932 | spec = CODING_SYSTEM_SPEC (coding_system); |
5933 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5934 | |
df7492f9 KH |
5935 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5936 | return coding_system; | |
ec6d2bb8 | 5937 | |
df7492f9 KH |
5938 | eol_type = AREF (spec, 2); |
5939 | if (VECTORP (eol_type)) | |
5940 | return Qraw_text; | |
5941 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5942 | raw_text_eol_type = AREF (spec, 2); | |
5943 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5944 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5945 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5946 | } |
5947 | ||
54f78171 | 5948 | |
1911a33b KH |
5949 | /* If CODING_SYSTEM doesn't specify end-of-line format, return one of |
5950 | the subsidiary that has the same eol-spec as PARENT (if it is not | |
5951 | nil and specifies end-of-line format) or the system's setting | |
fcbcfb64 | 5952 | (system_eol_type). */ |
df7492f9 KH |
5953 | |
5954 | Lisp_Object | |
971de7fb | 5955 | coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent) |
54f78171 | 5956 | { |
3e139625 | 5957 | Lisp_Object spec, eol_type; |
54f78171 | 5958 | |
d3e4cb56 KH |
5959 | if (NILP (coding_system)) |
5960 | coding_system = Qraw_text; | |
df7492f9 | 5961 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5962 | eol_type = AREF (spec, 2); |
fcbcfb64 | 5963 | if (VECTORP (eol_type)) |
df7492f9 | 5964 | { |
df7492f9 KH |
5965 | Lisp_Object parent_eol_type; |
5966 | ||
fcbcfb64 KH |
5967 | if (! NILP (parent)) |
5968 | { | |
5969 | Lisp_Object parent_spec; | |
5970 | ||
4a015c45 | 5971 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 | 5972 | parent_eol_type = AREF (parent_spec, 2); |
1911a33b | 5973 | if (VECTORP (parent_eol_type)) |
4628bef1 | 5974 | parent_eol_type = system_eol_type; |
fcbcfb64 KH |
5975 | } |
5976 | else | |
5977 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
5978 | if (EQ (parent_eol_type, Qunix)) |
5979 | coding_system = AREF (eol_type, 0); | |
5980 | else if (EQ (parent_eol_type, Qdos)) | |
5981 | coding_system = AREF (eol_type, 1); | |
5982 | else if (EQ (parent_eol_type, Qmac)) | |
5983 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5984 | } |
df7492f9 | 5985 | return coding_system; |
54f78171 KH |
5986 | } |
5987 | ||
fcaf8878 KH |
5988 | |
5989 | /* Check if text-conversion and eol-conversion of CODING_SYSTEM are | |
5990 | decided for writing to a process. If not, complement them, and | |
5991 | return a new coding system. */ | |
5992 | ||
5993 | Lisp_Object | |
4628bef1 | 5994 | complement_process_encoding_system (Lisp_Object coding_system) |
fcaf8878 | 5995 | { |
5886ec9c KH |
5996 | Lisp_Object coding_base = Qnil, eol_base = Qnil; |
5997 | Lisp_Object spec, attrs; | |
93d50df8 | 5998 | int i; |
fcaf8878 | 5999 | |
93d50df8 | 6000 | for (i = 0; i < 3; i++) |
fcaf8878 | 6001 | { |
93d50df8 KH |
6002 | if (i == 1) |
6003 | coding_system = CDR_SAFE (Vdefault_process_coding_system); | |
6004 | else if (i == 2) | |
6005 | coding_system = preferred_coding_system (); | |
6006 | spec = CODING_SYSTEM_SPEC (coding_system); | |
6007 | if (NILP (spec)) | |
6008 | continue; | |
6009 | attrs = AREF (spec, 0); | |
6010 | if (NILP (coding_base) && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
6011 | coding_base = CODING_ATTR_BASE_NAME (attrs); | |
6012 | if (NILP (eol_base) && ! VECTORP (AREF (spec, 2))) | |
6013 | eol_base = coding_system; | |
6014 | if (! NILP (coding_base) && ! NILP (eol_base)) | |
6015 | break; | |
fcaf8878 | 6016 | } |
fcaf8878 | 6017 | |
93d50df8 KH |
6018 | if (i > 0) |
6019 | /* The original CODING_SYSTEM didn't specify text-conversion or | |
6020 | eol-conversion. Be sure that we return a fully complemented | |
6021 | coding system. */ | |
6022 | coding_system = coding_inherit_eol_type (coding_base, eol_base); | |
6023 | return coding_system; | |
fcaf8878 KH |
6024 | } |
6025 | ||
6026 | ||
4ed46869 KH |
6027 | /* Emacs has a mechanism to automatically detect a coding system if it |
6028 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
6029 | it's impossible to distinguish some coding systems accurately | |
6030 | because they use the same range of codes. So, at first, coding | |
6031 | systems are categorized into 7, those are: | |
6032 | ||
0ef69138 | 6033 | o coding-category-emacs-mule |
4ed46869 KH |
6034 | |
6035 | The category for a coding system which has the same code range | |
6036 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 6037 | symbol) `emacs-mule' by default. |
4ed46869 KH |
6038 | |
6039 | o coding-category-sjis | |
6040 | ||
6041 | The category for a coding system which has the same code range | |
6042 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 6043 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
6044 | |
6045 | o coding-category-iso-7 | |
6046 | ||
6047 | The category for a coding system which has the same code range | |
7717c392 | 6048 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
6049 | shift and single shift functions. This can encode/decode all |
6050 | charsets. Assigned the coding-system (Lisp symbol) | |
6051 | `iso-2022-7bit' by default. | |
6052 | ||
6053 | o coding-category-iso-7-tight | |
6054 | ||
6055 | Same as coding-category-iso-7 except that this can | |
6056 | encode/decode only the specified charsets. | |
4ed46869 KH |
6057 | |
6058 | o coding-category-iso-8-1 | |
6059 | ||
6060 | The category for a coding system which has the same code range | |
6061 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6062 | for DIMENSION1 charset. This doesn't use any locking shift |
6063 | and single shift functions. Assigned the coding-system (Lisp | |
6064 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
6065 | |
6066 | o coding-category-iso-8-2 | |
6067 | ||
6068 | The category for a coding system which has the same code range | |
6069 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6070 | for DIMENSION2 charset. This doesn't use any locking shift |
6071 | and single shift functions. Assigned the coding-system (Lisp | |
6072 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 6073 | |
7717c392 | 6074 | o coding-category-iso-7-else |
4ed46869 KH |
6075 | |
6076 | The category for a coding system which has the same code range | |
ad1746f5 | 6077 | as ISO2022 of 7-bit environment but uses locking shift or |
7717c392 KH |
6078 | single shift functions. Assigned the coding-system (Lisp |
6079 | symbol) `iso-2022-7bit-lock' by default. | |
6080 | ||
6081 | o coding-category-iso-8-else | |
6082 | ||
6083 | The category for a coding system which has the same code range | |
ad1746f5 | 6084 | as ISO2022 of 8-bit environment but uses locking shift or |
7717c392 KH |
6085 | single shift functions. Assigned the coding-system (Lisp |
6086 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
6087 | |
6088 | o coding-category-big5 | |
6089 | ||
6090 | The category for a coding system which has the same code range | |
6091 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6092 | `cn-big5' by default. |
4ed46869 | 6093 | |
fa42c37f KH |
6094 | o coding-category-utf-8 |
6095 | ||
6096 | The category for a coding system which has the same code range | |
6e76ae91 | 6097 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
6098 | symbol) `utf-8' by default. |
6099 | ||
6100 | o coding-category-utf-16-be | |
6101 | ||
6102 | The category for a coding system in which a text has an | |
6103 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
6104 | endian at the head. Assigned the coding-system (Lisp symbol) | |
6105 | `utf-16-be' by default. | |
6106 | ||
6107 | o coding-category-utf-16-le | |
6108 | ||
6109 | The category for a coding system in which a text has an | |
6110 | Unicode signature (cf. Unicode Standard) in the order of | |
6111 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
6112 | symbol) `utf-16-le' by default. | |
6113 | ||
1397dc18 KH |
6114 | o coding-category-ccl |
6115 | ||
6116 | The category for a coding system of which encoder/decoder is | |
6117 | written in CCL programs. The default value is nil, i.e., no | |
6118 | coding system is assigned. | |
6119 | ||
4ed46869 KH |
6120 | o coding-category-binary |
6121 | ||
6122 | The category for a coding system not categorized in any of the | |
6123 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6124 | `no-conversion' by default. |
4ed46869 KH |
6125 | |
6126 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 6127 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
6128 | What Emacs does actually is to detect a category of coding system. |
6129 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 6130 | decide only one possible category, it selects a category of the |
4ed46869 KH |
6131 | highest priority. Priorities of categories are also specified by a |
6132 | user in a Lisp variable `coding-category-list'. | |
6133 | ||
6134 | */ | |
6135 | ||
df7492f9 KH |
6136 | #define EOL_SEEN_NONE 0 |
6137 | #define EOL_SEEN_LF 1 | |
6138 | #define EOL_SEEN_CR 2 | |
6139 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 6140 | |
ff0dacd7 KH |
6141 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
6142 | SOURCE is encoded. If CATEGORY is one of | |
6143 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
6144 | two-byte, else they are encoded by one-byte. | |
6145 | ||
6146 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 6147 | |
bc4bc72a | 6148 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
6149 | |
6150 | static int | |
cf84bb53 JB |
6151 | detect_eol (const unsigned char *source, EMACS_INT src_bytes, |
6152 | enum coding_category category) | |
4ed46869 | 6153 | { |
f6cbaf43 | 6154 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 6155 | unsigned char c; |
df7492f9 KH |
6156 | int total = 0; |
6157 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 6158 | |
89528eb3 | 6159 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 6160 | { |
df7492f9 | 6161 | int msb, lsb; |
fa42c37f | 6162 | |
89528eb3 KH |
6163 | msb = category == (coding_category_utf_16_le |
6164 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 6165 | lsb = 1 - msb; |
fa42c37f | 6166 | |
df7492f9 | 6167 | while (src + 1 < src_end) |
fa42c37f | 6168 | { |
df7492f9 KH |
6169 | c = src[lsb]; |
6170 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 6171 | { |
df7492f9 KH |
6172 | int this_eol; |
6173 | ||
6174 | if (c == '\n') | |
6175 | this_eol = EOL_SEEN_LF; | |
6176 | else if (src + 3 >= src_end | |
6177 | || src[msb + 2] != 0 | |
6178 | || src[lsb + 2] != '\n') | |
6179 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 6180 | else |
75f4f1ac EZ |
6181 | { |
6182 | this_eol = EOL_SEEN_CRLF; | |
6183 | src += 2; | |
6184 | } | |
df7492f9 KH |
6185 | |
6186 | if (eol_seen == EOL_SEEN_NONE) | |
6187 | /* This is the first end-of-line. */ | |
6188 | eol_seen = this_eol; | |
6189 | else if (eol_seen != this_eol) | |
fa42c37f | 6190 | { |
75f4f1ac EZ |
6191 | /* The found type is different from what found before. |
6192 | Allow for stray ^M characters in DOS EOL files. */ | |
ef1b0ba7 SM |
6193 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) |
6194 | || (eol_seen == EOL_SEEN_CRLF | |
6195 | && this_eol == EOL_SEEN_CR)) | |
75f4f1ac EZ |
6196 | eol_seen = EOL_SEEN_CRLF; |
6197 | else | |
6198 | { | |
6199 | eol_seen = EOL_SEEN_LF; | |
6200 | break; | |
6201 | } | |
fa42c37f | 6202 | } |
df7492f9 KH |
6203 | if (++total == MAX_EOL_CHECK_COUNT) |
6204 | break; | |
fa42c37f | 6205 | } |
df7492f9 | 6206 | src += 2; |
fa42c37f | 6207 | } |
bcf26d6a | 6208 | } |
d46c5b12 | 6209 | else |
ef1b0ba7 SM |
6210 | while (src < src_end) |
6211 | { | |
6212 | c = *src++; | |
6213 | if (c == '\n' || c == '\r') | |
6214 | { | |
6215 | int this_eol; | |
d46c5b12 | 6216 | |
ef1b0ba7 SM |
6217 | if (c == '\n') |
6218 | this_eol = EOL_SEEN_LF; | |
6219 | else if (src >= src_end || *src != '\n') | |
6220 | this_eol = EOL_SEEN_CR; | |
6221 | else | |
6222 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 6223 | |
ef1b0ba7 SM |
6224 | if (eol_seen == EOL_SEEN_NONE) |
6225 | /* This is the first end-of-line. */ | |
6226 | eol_seen = this_eol; | |
6227 | else if (eol_seen != this_eol) | |
6228 | { | |
6229 | /* The found type is different from what found before. | |
6230 | Allow for stray ^M characters in DOS EOL files. */ | |
6231 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) | |
6232 | || (eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR)) | |
6233 | eol_seen = EOL_SEEN_CRLF; | |
6234 | else | |
6235 | { | |
6236 | eol_seen = EOL_SEEN_LF; | |
6237 | break; | |
6238 | } | |
6239 | } | |
6240 | if (++total == MAX_EOL_CHECK_COUNT) | |
6241 | break; | |
6242 | } | |
6243 | } | |
df7492f9 | 6244 | return eol_seen; |
73be902c KH |
6245 | } |
6246 | ||
df7492f9 | 6247 | |
24a73b0a | 6248 | static Lisp_Object |
971de7fb | 6249 | adjust_coding_eol_type (struct coding_system *coding, int eol_seen) |
73be902c | 6250 | { |
0be8721c | 6251 | Lisp_Object eol_type; |
8f924df7 | 6252 | |
df7492f9 KH |
6253 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6254 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
6255 | { |
6256 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6257 | eol_type = Qunix; | |
6258 | } | |
6f197c07 | 6259 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
6260 | { |
6261 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
6262 | eol_type = Qdos; | |
6263 | } | |
6f197c07 | 6264 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
6265 | { |
6266 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
6267 | eol_type = Qmac; | |
6268 | } | |
6269 | return eol_type; | |
d46c5b12 | 6270 | } |
4ed46869 | 6271 | |
df7492f9 KH |
6272 | /* Detect how a text specified in CODING is encoded. If a coding |
6273 | system is detected, update fields of CODING by the detected coding | |
6274 | system. */ | |
0a28aafb | 6275 | |
df7492f9 | 6276 | void |
971de7fb | 6277 | detect_coding (struct coding_system *coding) |
d46c5b12 | 6278 | { |
8f924df7 | 6279 | const unsigned char *src, *src_end; |
73cce38d | 6280 | int saved_mode = coding->mode; |
d46c5b12 | 6281 | |
df7492f9 KH |
6282 | coding->consumed = coding->consumed_char = 0; |
6283 | coding->produced = coding->produced_char = 0; | |
6284 | coding_set_source (coding); | |
1c3478b0 | 6285 | |
df7492f9 | 6286 | src_end = coding->source + coding->src_bytes; |
c0e16b14 | 6287 | coding->head_ascii = 0; |
1c3478b0 | 6288 | |
df7492f9 KH |
6289 | /* If we have not yet decided the text encoding type, detect it |
6290 | now. */ | |
6291 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 6292 | { |
df7492f9 | 6293 | int c, i; |
6cb21a4f | 6294 | struct coding_detection_info detect_info; |
2f3cbb32 | 6295 | int null_byte_found = 0, eight_bit_found = 0; |
df7492f9 | 6296 | |
6cb21a4f | 6297 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 6298 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 6299 | { |
df7492f9 | 6300 | c = *src; |
6cb21a4f | 6301 | if (c & 0x80) |
6cb21a4f | 6302 | { |
2f3cbb32 | 6303 | eight_bit_found = 1; |
2f3cbb32 KH |
6304 | if (null_byte_found) |
6305 | break; | |
6306 | } | |
6307 | else if (c < 0x20) | |
6308 | { | |
6309 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
6310 | && ! inhibit_iso_escape_detection | |
6311 | && ! detect_info.checked) | |
6cb21a4f | 6312 | { |
2f3cbb32 KH |
6313 | if (detect_coding_iso_2022 (coding, &detect_info)) |
6314 | { | |
6315 | /* We have scanned the whole data. */ | |
6316 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
6317 | { |
6318 | /* We didn't find an 8-bit code. We may | |
6319 | have found a null-byte, but it's very | |
ce5b453a | 6320 | rare that a binary file conforms to |
c0e16b14 KH |
6321 | ISO-2022. */ |
6322 | src = src_end; | |
6323 | coding->head_ascii = src - coding->source; | |
6324 | } | |
6325 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
6326 | break; |
6327 | } | |
6328 | } | |
97b1b294 | 6329 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
6330 | { |
6331 | null_byte_found = 1; | |
6332 | if (eight_bit_found) | |
6333 | break; | |
6cb21a4f | 6334 | } |
c006c0c8 KH |
6335 | if (! eight_bit_found) |
6336 | coding->head_ascii++; | |
6cb21a4f | 6337 | } |
c006c0c8 | 6338 | else if (! eight_bit_found) |
c0e16b14 | 6339 | coding->head_ascii++; |
d46c5b12 | 6340 | } |
df7492f9 | 6341 | |
2f3cbb32 KH |
6342 | if (null_byte_found || eight_bit_found |
6343 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 6344 | || detect_info.found) |
d46c5b12 | 6345 | { |
ff0dacd7 KH |
6346 | enum coding_category category; |
6347 | struct coding_system *this; | |
df7492f9 | 6348 | |
6cb21a4f KH |
6349 | if (coding->head_ascii == coding->src_bytes) |
6350 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
6351 | for (i = 0; i < coding_category_raw_text; i++) | |
6352 | { | |
6353 | category = coding_priorities[i]; | |
6354 | this = coding_categories + category; | |
6355 | if (detect_info.found & (1 << category)) | |
24a73b0a | 6356 | break; |
6cb21a4f KH |
6357 | } |
6358 | else | |
2f3cbb32 KH |
6359 | { |
6360 | if (null_byte_found) | |
ff0dacd7 | 6361 | { |
2f3cbb32 KH |
6362 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
6363 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 6364 | } |
2f3cbb32 KH |
6365 | for (i = 0; i < coding_category_raw_text; i++) |
6366 | { | |
6367 | category = coding_priorities[i]; | |
6368 | this = coding_categories + category; | |
6369 | if (this->id < 0) | |
6370 | { | |
6371 | /* No coding system of this category is defined. */ | |
6372 | detect_info.rejected |= (1 << category); | |
6373 | } | |
6374 | else if (category >= coding_category_raw_text) | |
6375 | continue; | |
6376 | else if (detect_info.checked & (1 << category)) | |
6377 | { | |
6378 | if (detect_info.found & (1 << category)) | |
6379 | break; | |
6380 | } | |
6381 | else if ((*(this->detector)) (coding, &detect_info) | |
6382 | && detect_info.found & (1 << category)) | |
6383 | { | |
6384 | if (category == coding_category_utf_16_auto) | |
6385 | { | |
6386 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6387 | category = coding_category_utf_16_le; | |
6388 | else | |
6389 | category = coding_category_utf_16_be; | |
6390 | } | |
6391 | break; | |
6392 | } | |
6393 | } | |
2f3cbb32 | 6394 | } |
c0e16b14 KH |
6395 | |
6396 | if (i < coding_category_raw_text) | |
6397 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6398 | else if (null_byte_found) | |
6399 | setup_coding_system (Qno_conversion, coding); | |
6400 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) | |
6401 | == CATEGORY_MASK_ANY) | |
6402 | setup_coding_system (Qraw_text, coding); | |
6403 | else if (detect_info.rejected) | |
6404 | for (i = 0; i < coding_category_raw_text; i++) | |
6405 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6406 | { | |
6407 | this = coding_categories + coding_priorities[i]; | |
6408 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6409 | break; | |
6410 | } | |
d46c5b12 | 6411 | } |
b73bfc1c | 6412 | } |
a470d443 KH |
6413 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6414 | == coding_category_utf_8_auto) | |
6415 | { | |
6416 | Lisp_Object coding_systems; | |
6417 | struct coding_detection_info detect_info; | |
6418 | ||
6419 | coding_systems | |
6420 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6421 | detect_info.found = detect_info.rejected = 0; | |
6422 | coding->head_ascii = 0; | |
6423 | if (CONSP (coding_systems) | |
6424 | && detect_coding_utf_8 (coding, &detect_info)) | |
6425 | { | |
6426 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6427 | setup_coding_system (XCAR (coding_systems), coding); | |
6428 | else | |
6429 | setup_coding_system (XCDR (coding_systems), coding); | |
6430 | } | |
6431 | } | |
24a73b0a KH |
6432 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6433 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6434 | { |
6435 | Lisp_Object coding_systems; | |
6436 | struct coding_detection_info detect_info; | |
6437 | ||
6438 | coding_systems | |
a470d443 | 6439 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6440 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6441 | coding->head_ascii = 0; |
b49a1807 | 6442 | if (CONSP (coding_systems) |
24a73b0a | 6443 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6444 | { |
6445 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6446 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 6447 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
6448 | setup_coding_system (XCDR (coding_systems), coding); |
6449 | } | |
6450 | } | |
73cce38d | 6451 | coding->mode = saved_mode; |
4ed46869 | 6452 | } |
4ed46869 | 6453 | |
d46c5b12 | 6454 | |
aaaf0b1e | 6455 | static void |
971de7fb | 6456 | decode_eol (struct coding_system *coding) |
aaaf0b1e | 6457 | { |
24a73b0a KH |
6458 | Lisp_Object eol_type; |
6459 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6460 | |
24a73b0a | 6461 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
0a9564cb | 6462 | if (EQ (eol_type, Qunix) || inhibit_eol_conversion) |
24a73b0a KH |
6463 | return; |
6464 | ||
6465 | if (NILP (coding->dst_object)) | |
6466 | pbeg = coding->destination; | |
6467 | else | |
6468 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6469 | pend = pbeg + coding->produced; | |
6470 | ||
6471 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6472 | { |
df7492f9 | 6473 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6474 | |
24a73b0a | 6475 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6476 | { |
df7492f9 KH |
6477 | if (*p == '\n') |
6478 | eol_seen |= EOL_SEEN_LF; | |
6479 | else if (*p == '\r') | |
aaaf0b1e | 6480 | { |
df7492f9 | 6481 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6482 | { |
df7492f9 KH |
6483 | eol_seen |= EOL_SEEN_CRLF; |
6484 | p++; | |
aaaf0b1e | 6485 | } |
aaaf0b1e | 6486 | else |
df7492f9 | 6487 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6488 | } |
aaaf0b1e | 6489 | } |
75f4f1ac EZ |
6490 | /* Handle DOS-style EOLs in a file with stray ^M characters. */ |
6491 | if ((eol_seen & EOL_SEEN_CRLF) != 0 | |
6492 | && (eol_seen & EOL_SEEN_CR) != 0 | |
6493 | && (eol_seen & EOL_SEEN_LF) == 0) | |
6494 | eol_seen = EOL_SEEN_CRLF; | |
6495 | else if (eol_seen != EOL_SEEN_NONE | |
24a73b0a KH |
6496 | && eol_seen != EOL_SEEN_LF |
6497 | && eol_seen != EOL_SEEN_CRLF | |
6498 | && eol_seen != EOL_SEEN_CR) | |
6499 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6500 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6501 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6502 | } |
d46c5b12 | 6503 | |
24a73b0a | 6504 | if (EQ (eol_type, Qmac)) |
27901516 | 6505 | { |
24a73b0a | 6506 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6507 | if (*p == '\r') |
6508 | *p = '\n'; | |
4ed46869 | 6509 | } |
24a73b0a | 6510 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6511 | { |
24a73b0a | 6512 | int n = 0; |
b73bfc1c | 6513 | |
24a73b0a KH |
6514 | if (NILP (coding->dst_object)) |
6515 | { | |
4347441b KH |
6516 | /* Start deleting '\r' from the tail to minimize the memory |
6517 | movement. */ | |
24a73b0a KH |
6518 | for (p = pend - 2; p >= pbeg; p--) |
6519 | if (*p == '\r') | |
6520 | { | |
72af86bd | 6521 | memmove (p, p + 1, pend-- - p - 1); |
24a73b0a KH |
6522 | n++; |
6523 | } | |
6524 | } | |
6525 | else | |
6526 | { | |
4347441b KH |
6527 | int pos_byte = coding->dst_pos_byte; |
6528 | int pos = coding->dst_pos; | |
6529 | int pos_end = pos + coding->produced_char - 1; | |
6530 | ||
6531 | while (pos < pos_end) | |
6532 | { | |
6533 | p = BYTE_POS_ADDR (pos_byte); | |
6534 | if (*p == '\r' && p[1] == '\n') | |
6535 | { | |
6536 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6537 | n++; | |
6538 | pos_end--; | |
6539 | } | |
6540 | pos++; | |
69b8522d KH |
6541 | if (coding->dst_multibyte) |
6542 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6543 | else | |
6544 | pos_byte++; | |
4347441b | 6545 | } |
24a73b0a KH |
6546 | } |
6547 | coding->produced -= n; | |
6548 | coding->produced_char -= n; | |
aaaf0b1e | 6549 | } |
4ed46869 KH |
6550 | } |
6551 | ||
7d64c6ad | 6552 | |
a6f87d34 KH |
6553 | /* Return a translation table (or list of them) from coding system |
6554 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
6555 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 6556 | |
e6a54062 | 6557 | static Lisp_Object |
971de7fb | 6558 | get_translation_table (Lisp_Object attrs, int encodep, int *max_lookup) |
7d64c6ad KH |
6559 | { |
6560 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6561 | Lisp_Object val; |
7d64c6ad | 6562 | |
4bed5909 CY |
6563 | if (NILP (Venable_character_translation)) |
6564 | { | |
6565 | if (max_lookup) | |
6566 | *max_lookup = 0; | |
6567 | return Qnil; | |
6568 | } | |
7d64c6ad KH |
6569 | if (encodep) |
6570 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6571 | standard = Vstandard_translation_table_for_encode; | |
6572 | else | |
6573 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6574 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6575 | if (NILP (translation_table)) |
09ee6fdd KH |
6576 | translation_table = standard; |
6577 | else | |
a6f87d34 | 6578 | { |
09ee6fdd KH |
6579 | if (SYMBOLP (translation_table)) |
6580 | translation_table = Fget (translation_table, Qtranslation_table); | |
6581 | else if (CONSP (translation_table)) | |
6582 | { | |
6583 | translation_table = Fcopy_sequence (translation_table); | |
6584 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6585 | if (SYMBOLP (XCAR (val))) | |
6586 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6587 | } | |
6588 | if (CHAR_TABLE_P (standard)) | |
6589 | { | |
6590 | if (CONSP (translation_table)) | |
6591 | translation_table = nconc2 (translation_table, | |
6592 | Fcons (standard, Qnil)); | |
6593 | else | |
6594 | translation_table = Fcons (translation_table, | |
6595 | Fcons (standard, Qnil)); | |
6596 | } | |
a6f87d34 | 6597 | } |
2170c8f0 KH |
6598 | |
6599 | if (max_lookup) | |
09ee6fdd | 6600 | { |
2170c8f0 KH |
6601 | *max_lookup = 1; |
6602 | if (CHAR_TABLE_P (translation_table) | |
6603 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6604 | { | |
6605 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6606 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6607 | *max_lookup = XFASTINT (val); | |
6608 | } | |
6609 | else if (CONSP (translation_table)) | |
6610 | { | |
6611 | Lisp_Object tail, val; | |
09ee6fdd | 6612 | |
2170c8f0 KH |
6613 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6614 | if (CHAR_TABLE_P (XCAR (tail)) | |
6615 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6616 | { | |
6617 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
6618 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6619 | *max_lookup = XFASTINT (val); | |
6620 | } | |
6621 | } | |
a6f87d34 | 6622 | } |
7d64c6ad KH |
6623 | return translation_table; |
6624 | } | |
6625 | ||
09ee6fdd KH |
6626 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6627 | do { \ | |
6628 | trans = Qnil; \ | |
6629 | if (CHAR_TABLE_P (table)) \ | |
6630 | { \ | |
6631 | trans = CHAR_TABLE_REF (table, c); \ | |
6632 | if (CHARACTERP (trans)) \ | |
6633 | c = XFASTINT (trans), trans = Qnil; \ | |
6634 | } \ | |
6635 | else if (CONSP (table)) \ | |
6636 | { \ | |
6637 | Lisp_Object tail; \ | |
6638 | \ | |
6639 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6640 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6641 | { \ | |
6642 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6643 | if (CHARACTERP (trans)) \ | |
6644 | c = XFASTINT (trans), trans = Qnil; \ | |
6645 | else if (! NILP (trans)) \ | |
6646 | break; \ | |
6647 | } \ | |
6648 | } \ | |
e6a54062 KH |
6649 | } while (0) |
6650 | ||
7d64c6ad | 6651 | |
e951386e KH |
6652 | /* Return a translation of character(s) at BUF according to TRANS. |
6653 | TRANS is TO-CHAR or ((FROM . TO) ...) where | |
6654 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | |
6655 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | |
6656 | translation is found, and Qnil if not found.. | |
6657 | If BUF is too short to lookup characters in FROM, return Qt. */ | |
6658 | ||
69a80ea3 | 6659 | static Lisp_Object |
971de7fb | 6660 | get_translation (Lisp_Object trans, int *buf, int *buf_end) |
69a80ea3 | 6661 | { |
e951386e KH |
6662 | |
6663 | if (INTEGERP (trans)) | |
6664 | return trans; | |
6665 | for (; CONSP (trans); trans = XCDR (trans)) | |
69a80ea3 | 6666 | { |
e951386e KH |
6667 | Lisp_Object val = XCAR (trans); |
6668 | Lisp_Object from = XCAR (val); | |
6669 | int len = ASIZE (from); | |
6670 | int i; | |
69a80ea3 | 6671 | |
e951386e | 6672 | for (i = 0; i < len; i++) |
69a80ea3 | 6673 | { |
e951386e KH |
6674 | if (buf + i == buf_end) |
6675 | return Qt; | |
6676 | if (XINT (AREF (from, i)) != buf[i]) | |
6677 | break; | |
69a80ea3 | 6678 | } |
e951386e KH |
6679 | if (i == len) |
6680 | return val; | |
69a80ea3 | 6681 | } |
e951386e | 6682 | return Qnil; |
69a80ea3 KH |
6683 | } |
6684 | ||
6685 | ||
d46c5b12 | 6686 | static int |
cf84bb53 JB |
6687 | produce_chars (struct coding_system *coding, Lisp_Object translation_table, |
6688 | int last_block) | |
4ed46869 | 6689 | { |
df7492f9 KH |
6690 | unsigned char *dst = coding->destination + coding->produced; |
6691 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
119852e7 KH |
6692 | EMACS_INT produced; |
6693 | EMACS_INT produced_chars = 0; | |
69a80ea3 | 6694 | int carryover = 0; |
4ed46869 | 6695 | |
df7492f9 | 6696 | if (! coding->chars_at_source) |
4ed46869 | 6697 | { |
119852e7 | 6698 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6699 | int *buf = coding->charbuf; |
6700 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6701 | |
db274c7a KH |
6702 | if (EQ (coding->src_object, coding->dst_object)) |
6703 | { | |
6704 | coding_set_source (coding); | |
6705 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6706 | } | |
4ed46869 | 6707 | |
df7492f9 | 6708 | while (buf < buf_end) |
4ed46869 | 6709 | { |
69a80ea3 | 6710 | int c = *buf, i; |
bc4bc72a | 6711 | |
df7492f9 KH |
6712 | if (c >= 0) |
6713 | { | |
69a80ea3 KH |
6714 | int from_nchars = 1, to_nchars = 1; |
6715 | Lisp_Object trans = Qnil; | |
6716 | ||
09ee6fdd | 6717 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6718 | if (! NILP (trans)) |
69a80ea3 | 6719 | { |
e951386e KH |
6720 | trans = get_translation (trans, buf, buf_end); |
6721 | if (INTEGERP (trans)) | |
6722 | c = XINT (trans); | |
6723 | else if (CONSP (trans)) | |
6724 | { | |
6725 | from_nchars = ASIZE (XCAR (trans)); | |
6726 | trans = XCDR (trans); | |
6727 | if (INTEGERP (trans)) | |
6728 | c = XINT (trans); | |
6729 | else | |
6730 | { | |
6731 | to_nchars = ASIZE (trans); | |
6732 | c = XINT (AREF (trans, 0)); | |
6733 | } | |
6734 | } | |
6735 | else if (EQ (trans, Qt) && ! last_block) | |
69a80ea3 | 6736 | break; |
69a80ea3 KH |
6737 | } |
6738 | ||
6739 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
6740 | { | |
6741 | dst = alloc_destination (coding, | |
6742 | buf_end - buf | |
6743 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
6744 | dst); | |
db274c7a KH |
6745 | if (EQ (coding->src_object, coding->dst_object)) |
6746 | { | |
6747 | coding_set_source (coding); | |
e951386e KH |
6748 | dst_end = (((unsigned char *) coding->source) |
6749 | + coding->consumed); | |
db274c7a KH |
6750 | } |
6751 | else | |
6752 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
6753 | } |
6754 | ||
433f7f87 | 6755 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 6756 | { |
433f7f87 KH |
6757 | if (i > 0) |
6758 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
6759 | if (coding->dst_multibyte |
6760 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 6761 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
6762 | else |
6763 | *dst++ = CHAR_TO_BYTE8 (c); | |
6764 | } | |
6765 | produced_chars += to_nchars; | |
e951386e | 6766 | buf += from_nchars; |
d46c5b12 | 6767 | } |
df7492f9 | 6768 | else |
69a80ea3 KH |
6769 | /* This is an annotation datum. (-C) is the length. */ |
6770 | buf += -c; | |
4ed46869 | 6771 | } |
69a80ea3 | 6772 | carryover = buf_end - buf; |
4ed46869 | 6773 | } |
fa42c37f | 6774 | else |
fa42c37f | 6775 | { |
119852e7 | 6776 | /* Source characters are at coding->source. */ |
8f924df7 | 6777 | const unsigned char *src = coding->source; |
119852e7 | 6778 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 6779 | |
db274c7a KH |
6780 | if (EQ (coding->dst_object, coding->src_object)) |
6781 | dst_end = (unsigned char *) src; | |
df7492f9 | 6782 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 6783 | { |
df7492f9 | 6784 | if (coding->src_multibyte) |
fa42c37f | 6785 | { |
71c81426 | 6786 | int multibytep = 1; |
4533845d | 6787 | EMACS_INT consumed_chars = 0; |
d46c5b12 | 6788 | |
df7492f9 KH |
6789 | while (1) |
6790 | { | |
8f924df7 | 6791 | const unsigned char *src_base = src; |
df7492f9 | 6792 | int c; |
b73bfc1c | 6793 | |
df7492f9 | 6794 | ONE_MORE_BYTE (c); |
119852e7 | 6795 | if (dst == dst_end) |
df7492f9 | 6796 | { |
119852e7 KH |
6797 | if (EQ (coding->src_object, coding->dst_object)) |
6798 | dst_end = (unsigned char *) src; | |
6799 | if (dst == dst_end) | |
df7492f9 | 6800 | { |
119852e7 KH |
6801 | EMACS_INT offset = src - coding->source; |
6802 | ||
6803 | dst = alloc_destination (coding, src_end - src + 1, | |
6804 | dst); | |
6805 | dst_end = coding->destination + coding->dst_bytes; | |
6806 | coding_set_source (coding); | |
6807 | src = coding->source + offset; | |
6808 | src_end = coding->source + coding->src_bytes; | |
db274c7a KH |
6809 | if (EQ (coding->src_object, coding->dst_object)) |
6810 | dst_end = (unsigned char *) src; | |
df7492f9 | 6811 | } |
df7492f9 KH |
6812 | } |
6813 | *dst++ = c; | |
6814 | produced_chars++; | |
6815 | } | |
6816 | no_more_source: | |
6817 | ; | |
fa42c37f KH |
6818 | } |
6819 | else | |
df7492f9 KH |
6820 | while (src < src_end) |
6821 | { | |
71c81426 | 6822 | int multibytep = 1; |
df7492f9 | 6823 | int c = *src++; |
b73bfc1c | 6824 | |
df7492f9 KH |
6825 | if (dst >= dst_end - 1) |
6826 | { | |
2c78b7e1 | 6827 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 6828 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
6829 | if (dst >= dst_end - 1) |
6830 | { | |
119852e7 | 6831 | EMACS_INT offset = src - coding->source; |
db274c7a | 6832 | EMACS_INT more_bytes; |
119852e7 | 6833 | |
db274c7a KH |
6834 | if (EQ (coding->src_object, coding->dst_object)) |
6835 | more_bytes = ((src_end - src) / 2) + 2; | |
6836 | else | |
6837 | more_bytes = src_end - src + 2; | |
6838 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
6839 | dst_end = coding->destination + coding->dst_bytes; |
6840 | coding_set_source (coding); | |
119852e7 | 6841 | src = coding->source + offset; |
2c78b7e1 | 6842 | src_end = coding->source + coding->src_bytes; |
db274c7a KH |
6843 | if (EQ (coding->src_object, coding->dst_object)) |
6844 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 6845 | } |
df7492f9 KH |
6846 | } |
6847 | EMIT_ONE_BYTE (c); | |
6848 | } | |
d46c5b12 | 6849 | } |
df7492f9 KH |
6850 | else |
6851 | { | |
6852 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 6853 | { |
119852e7 | 6854 | EMACS_INT require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 6855 | |
df7492f9 | 6856 | if (require > 0) |
fa42c37f | 6857 | { |
df7492f9 KH |
6858 | EMACS_INT offset = src - coding->source; |
6859 | ||
6860 | dst = alloc_destination (coding, require, dst); | |
6861 | coding_set_source (coding); | |
6862 | src = coding->source + offset; | |
6863 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
6864 | } |
6865 | } | |
119852e7 | 6866 | produced_chars = coding->consumed_char; |
df7492f9 | 6867 | while (src < src_end) |
14daee73 | 6868 | *dst++ = *src++; |
fa42c37f KH |
6869 | } |
6870 | } | |
6871 | ||
df7492f9 | 6872 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 6873 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
df7492f9 KH |
6874 | insert_from_gap (produced_chars, produced); |
6875 | coding->produced += produced; | |
6876 | coding->produced_char += produced_chars; | |
69a80ea3 | 6877 | return carryover; |
fa42c37f KH |
6878 | } |
6879 | ||
ff0dacd7 KH |
6880 | /* Compose text in CODING->object according to the annotation data at |
6881 | CHARBUF. CHARBUF is an array: | |
e951386e | 6882 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
df7492f9 | 6883 | */ |
4ed46869 | 6884 | |
df7492f9 | 6885 | static INLINE void |
971de7fb | 6886 | produce_composition (struct coding_system *coding, int *charbuf, EMACS_INT pos) |
4ed46869 | 6887 | { |
df7492f9 | 6888 | int len; |
69a80ea3 | 6889 | EMACS_INT to; |
df7492f9 | 6890 | enum composition_method method; |
df7492f9 | 6891 | Lisp_Object components; |
fa42c37f | 6892 | |
e951386e | 6893 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
69a80ea3 | 6894 | to = pos + charbuf[2]; |
e951386e | 6895 | method = (enum composition_method) (charbuf[4]); |
d46c5b12 | 6896 | |
df7492f9 KH |
6897 | if (method == COMPOSITION_RELATIVE) |
6898 | components = Qnil; | |
e951386e | 6899 | else |
d46c5b12 | 6900 | { |
df7492f9 | 6901 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
e951386e | 6902 | int i, j; |
b73bfc1c | 6903 | |
e951386e KH |
6904 | if (method == COMPOSITION_WITH_RULE) |
6905 | len = charbuf[2] * 3 - 2; | |
6906 | charbuf += MAX_ANNOTATION_LENGTH; | |
6907 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | |
6908 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | |
9ffd559c | 6909 | { |
e951386e KH |
6910 | if (charbuf[i] >= 0) |
6911 | args[j] = make_number (charbuf[i]); | |
6912 | else | |
6913 | { | |
6914 | i++; | |
6915 | args[j] = make_number (charbuf[i] % 0x100); | |
6916 | } | |
9ffd559c | 6917 | } |
e951386e | 6918 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
d46c5b12 | 6919 | } |
69a80ea3 | 6920 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6921 | } |
6922 | ||
d46c5b12 | 6923 | |
ff0dacd7 KH |
6924 | /* Put `charset' property on text in CODING->object according to |
6925 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6926 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6927 | */ |
d46c5b12 | 6928 | |
ff0dacd7 | 6929 | static INLINE void |
971de7fb | 6930 | produce_charset (struct coding_system *coding, int *charbuf, EMACS_INT pos) |
d46c5b12 | 6931 | { |
69a80ea3 KH |
6932 | EMACS_INT from = pos - charbuf[2]; |
6933 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 6934 | |
69a80ea3 | 6935 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6936 | Qcharset, CHARSET_NAME (charset), |
6937 | coding->dst_object); | |
d46c5b12 KH |
6938 | } |
6939 | ||
d46c5b12 | 6940 | |
df7492f9 KH |
6941 | #define CHARBUF_SIZE 0x4000 |
6942 | ||
6943 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6944 | do { \ | |
8510724d | 6945 | int size = CHARBUF_SIZE; \ |
df7492f9 KH |
6946 | \ |
6947 | coding->charbuf = NULL; \ | |
6948 | while (size > 1024) \ | |
6949 | { \ | |
6950 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
6951 | if (coding->charbuf) \ | |
6952 | break; \ | |
6953 | size >>= 1; \ | |
6954 | } \ | |
6955 | if (! coding->charbuf) \ | |
6956 | { \ | |
065e3595 | 6957 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
6958 | return coding->result; \ |
6959 | } \ | |
6960 | coding->charbuf_size = size; \ | |
6961 | } while (0) | |
4ed46869 | 6962 | |
d46c5b12 KH |
6963 | |
6964 | static void | |
971de7fb | 6965 | produce_annotation (struct coding_system *coding, EMACS_INT pos) |
d46c5b12 | 6966 | { |
df7492f9 KH |
6967 | int *charbuf = coding->charbuf; |
6968 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6969 | |
ff0dacd7 KH |
6970 | if (NILP (coding->dst_object)) |
6971 | return; | |
d46c5b12 | 6972 | |
df7492f9 | 6973 | while (charbuf < charbuf_end) |
a84f1519 | 6974 | { |
df7492f9 | 6975 | if (*charbuf >= 0) |
e951386e | 6976 | pos++, charbuf++; |
d46c5b12 | 6977 | else |
d46c5b12 | 6978 | { |
df7492f9 | 6979 | int len = -*charbuf; |
e951386e KH |
6980 | |
6981 | if (len > 2) | |
6982 | switch (charbuf[1]) | |
6983 | { | |
6984 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
6985 | produce_composition (coding, charbuf, pos); | |
6986 | break; | |
6987 | case CODING_ANNOTATE_CHARSET_MASK: | |
6988 | produce_charset (coding, charbuf, pos); | |
6989 | break; | |
6990 | } | |
df7492f9 | 6991 | charbuf += len; |
d46c5b12 | 6992 | } |
a84f1519 | 6993 | } |
d46c5b12 KH |
6994 | } |
6995 | ||
df7492f9 KH |
6996 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6997 | CODING->src_object is a buffer, a string, or nil. | |
6998 | CODING->dst_object is a buffer. | |
d46c5b12 | 6999 | |
df7492f9 KH |
7000 | If CODING->src_object is a buffer, it must be the current buffer. |
7001 | In this case, if CODING->src_pos is positive, it is a position of | |
7002 | the source text in the buffer, otherwise, the source text is in the | |
7003 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
7004 | the text from GPT (which must be the same as PT). If this is the | |
7005 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7006 | negative. | |
d46c5b12 | 7007 | |
b6828792 | 7008 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 7009 | that string. |
d46c5b12 | 7010 | |
df7492f9 KH |
7011 | If CODING->src_object is nil, CODING->source must already point to |
7012 | the non-relocatable memory area. In this case, CODING->src_pos is | |
7013 | an offset from CODING->source. | |
73be902c | 7014 | |
df7492f9 KH |
7015 | The decoded data is inserted at the current point of the buffer |
7016 | CODING->dst_object. | |
7017 | */ | |
d46c5b12 | 7018 | |
df7492f9 | 7019 | static int |
971de7fb | 7020 | decode_coding (struct coding_system *coding) |
d46c5b12 | 7021 | { |
df7492f9 | 7022 | Lisp_Object attrs; |
24a73b0a | 7023 | Lisp_Object undo_list; |
7d64c6ad | 7024 | Lisp_Object translation_table; |
d0396581 | 7025 | struct ccl_spec cclspec; |
69a80ea3 KH |
7026 | int carryover; |
7027 | int i; | |
d46c5b12 | 7028 | |
df7492f9 KH |
7029 | if (BUFFERP (coding->src_object) |
7030 | && coding->src_pos > 0 | |
7031 | && coding->src_pos < GPT | |
7032 | && coding->src_pos + coding->src_chars > GPT) | |
7033 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 7034 | |
24a73b0a | 7035 | undo_list = Qt; |
df7492f9 | 7036 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 7037 | { |
df7492f9 KH |
7038 | if (current_buffer != XBUFFER (coding->dst_object)) |
7039 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7040 | if (GPT != PT) | |
7041 | move_gap_both (PT, PT_BYTE); | |
24a73b0a KH |
7042 | undo_list = current_buffer->undo_list; |
7043 | current_buffer->undo_list = Qt; | |
1c3478b0 KH |
7044 | } |
7045 | ||
df7492f9 KH |
7046 | coding->consumed = coding->consumed_char = 0; |
7047 | coding->produced = coding->produced_char = 0; | |
7048 | coding->chars_at_source = 0; | |
065e3595 | 7049 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 7050 | coding->errors = 0; |
1c3478b0 | 7051 | |
df7492f9 KH |
7052 | ALLOC_CONVERSION_WORK_AREA (coding); |
7053 | ||
7054 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 7055 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 7056 | |
69a80ea3 | 7057 | carryover = 0; |
d0396581 KH |
7058 | if (coding->decoder == decode_coding_ccl) |
7059 | { | |
7060 | coding->spec.ccl = &cclspec; | |
7061 | setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding)); | |
7062 | } | |
df7492f9 | 7063 | do |
b73bfc1c | 7064 | { |
69a80ea3 KH |
7065 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
7066 | ||
df7492f9 KH |
7067 | coding_set_source (coding); |
7068 | coding->annotated = 0; | |
69a80ea3 | 7069 | coding->charbuf_used = carryover; |
df7492f9 | 7070 | (*(coding->decoder)) (coding); |
df7492f9 | 7071 | coding_set_destination (coding); |
69a80ea3 | 7072 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 7073 | if (coding->annotated) |
69a80ea3 KH |
7074 | produce_annotation (coding, pos); |
7075 | for (i = 0; i < carryover; i++) | |
7076 | coding->charbuf[i] | |
7077 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 7078 | } |
d0396581 KH |
7079 | while (coding->result == CODING_RESULT_INSUFFICIENT_DST |
7080 | || (coding->consumed < coding->src_bytes | |
7081 | && (coding->result == CODING_RESULT_SUCCESS | |
7082 | || coding->result == CODING_RESULT_INVALID_SRC))); | |
d46c5b12 | 7083 | |
69a80ea3 KH |
7084 | if (carryover > 0) |
7085 | { | |
7086 | coding_set_destination (coding); | |
7087 | coding->charbuf_used = carryover; | |
7088 | produce_chars (coding, translation_table, 1); | |
7089 | } | |
7090 | ||
df7492f9 KH |
7091 | coding->carryover_bytes = 0; |
7092 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 7093 | { |
df7492f9 | 7094 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 7095 | const unsigned char *src; |
df7492f9 KH |
7096 | |
7097 | coding_set_source (coding); | |
7098 | coding_set_destination (coding); | |
7099 | src = coding->source + coding->consumed; | |
7100 | ||
7101 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 7102 | { |
df7492f9 KH |
7103 | /* Flush out unprocessed data as binary chars. We are sure |
7104 | that the number of data is less than the size of | |
7105 | coding->charbuf. */ | |
065e3595 | 7106 | coding->charbuf_used = 0; |
b2dab6c8 JR |
7107 | coding->chars_at_source = 0; |
7108 | ||
df7492f9 | 7109 | while (nbytes-- > 0) |
1c3478b0 | 7110 | { |
df7492f9 | 7111 | int c = *src++; |
98725083 | 7112 | |
1c91457d KH |
7113 | if (c & 0x80) |
7114 | c = BYTE8_TO_CHAR (c); | |
7115 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 7116 | } |
f6cbaf43 | 7117 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 7118 | } |
d46c5b12 | 7119 | else |
df7492f9 KH |
7120 | { |
7121 | /* Record unprocessed bytes in coding->carryover. We are | |
7122 | sure that the number of data is less than the size of | |
7123 | coding->carryover. */ | |
7124 | unsigned char *p = coding->carryover; | |
7125 | ||
f289d375 KH |
7126 | if (nbytes > sizeof coding->carryover) |
7127 | nbytes = sizeof coding->carryover; | |
df7492f9 KH |
7128 | coding->carryover_bytes = nbytes; |
7129 | while (nbytes-- > 0) | |
7130 | *p++ = *src++; | |
1c3478b0 | 7131 | } |
df7492f9 | 7132 | coding->consumed = coding->src_bytes; |
b73bfc1c | 7133 | } |
69f76525 | 7134 | |
0a9564cb EZ |
7135 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix) |
7136 | && !inhibit_eol_conversion) | |
4347441b | 7137 | decode_eol (coding); |
24a73b0a KH |
7138 | if (BUFFERP (coding->dst_object)) |
7139 | { | |
7140 | current_buffer->undo_list = undo_list; | |
7141 | record_insert (coding->dst_pos, coding->produced_char); | |
7142 | } | |
73be902c | 7143 | return coding->result; |
4ed46869 KH |
7144 | } |
7145 | ||
aaaf0b1e | 7146 | |
e1c23804 | 7147 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
7148 | ending before LIMIT of CODING->src_object (buffer or string), store |
7149 | the data in BUF, set *STOP to a starting position of the next | |
7150 | composition (if any) or to LIMIT, and return the address of the | |
7151 | next element of BUF. | |
7152 | ||
7153 | If such an annotation is not found, set *STOP to a starting | |
7154 | position of a composition after POS (if any) or to LIMIT, and | |
7155 | return BUF. */ | |
7156 | ||
7157 | static INLINE int * | |
cf84bb53 JB |
7158 | handle_composition_annotation (EMACS_INT pos, EMACS_INT limit, |
7159 | struct coding_system *coding, int *buf, | |
7160 | EMACS_INT *stop) | |
aaaf0b1e | 7161 | { |
ff0dacd7 KH |
7162 | EMACS_INT start, end; |
7163 | Lisp_Object prop; | |
aaaf0b1e | 7164 | |
ff0dacd7 KH |
7165 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
7166 | || end > limit) | |
7167 | *stop = limit; | |
7168 | else if (start > pos) | |
7169 | *stop = start; | |
7170 | else | |
aaaf0b1e | 7171 | { |
ff0dacd7 | 7172 | if (start == pos) |
aaaf0b1e | 7173 | { |
ff0dacd7 KH |
7174 | /* We found a composition. Store the corresponding |
7175 | annotation data in BUF. */ | |
7176 | int *head = buf; | |
7177 | enum composition_method method = COMPOSITION_METHOD (prop); | |
7178 | int nchars = COMPOSITION_LENGTH (prop); | |
7179 | ||
e951386e | 7180 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
ff0dacd7 | 7181 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 7182 | { |
ff0dacd7 KH |
7183 | Lisp_Object components; |
7184 | int len, i, i_byte; | |
7185 | ||
7186 | components = COMPOSITION_COMPONENTS (prop); | |
7187 | if (VECTORP (components)) | |
aaaf0b1e | 7188 | { |
ff0dacd7 KH |
7189 | len = XVECTOR (components)->size; |
7190 | for (i = 0; i < len; i++) | |
7191 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 7192 | } |
ff0dacd7 | 7193 | else if (STRINGP (components)) |
aaaf0b1e | 7194 | { |
8f924df7 | 7195 | len = SCHARS (components); |
ff0dacd7 KH |
7196 | i = i_byte = 0; |
7197 | while (i < len) | |
7198 | { | |
7199 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
7200 | buf++; | |
7201 | } | |
7202 | } | |
7203 | else if (INTEGERP (components)) | |
7204 | { | |
7205 | len = 1; | |
7206 | *buf++ = XINT (components); | |
7207 | } | |
7208 | else if (CONSP (components)) | |
7209 | { | |
7210 | for (len = 0; CONSP (components); | |
7211 | len++, components = XCDR (components)) | |
7212 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 7213 | } |
aaaf0b1e | 7214 | else |
ff0dacd7 KH |
7215 | abort (); |
7216 | *head -= len; | |
aaaf0b1e | 7217 | } |
aaaf0b1e | 7218 | } |
ff0dacd7 KH |
7219 | |
7220 | if (find_composition (end, limit, &start, &end, &prop, | |
7221 | coding->src_object) | |
7222 | && end <= limit) | |
7223 | *stop = start; | |
7224 | else | |
7225 | *stop = limit; | |
aaaf0b1e | 7226 | } |
ff0dacd7 KH |
7227 | return buf; |
7228 | } | |
7229 | ||
7230 | ||
e1c23804 | 7231 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
7232 | CODING->src_object (buffer of string), store the data in BUF, set |
7233 | *STOP to the position where the value of `charset' property changes | |
7234 | (limiting by LIMIT), and return the address of the next element of | |
7235 | BUF. | |
7236 | ||
7237 | If the property value is nil, set *STOP to the position where the | |
7238 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
7239 | ||
7240 | static INLINE int * | |
cf84bb53 JB |
7241 | handle_charset_annotation (EMACS_INT pos, EMACS_INT limit, |
7242 | struct coding_system *coding, int *buf, | |
7243 | EMACS_INT *stop) | |
ff0dacd7 KH |
7244 | { |
7245 | Lisp_Object val, next; | |
7246 | int id; | |
7247 | ||
7248 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
7249 | if (! NILP (val) && CHARSETP (val)) | |
7250 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
7251 | else | |
7252 | id = -1; | |
69a80ea3 | 7253 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
7254 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
7255 | coding->src_object, | |
7256 | make_number (limit)); | |
7257 | *stop = XINT (next); | |
7258 | return buf; | |
7259 | } | |
7260 | ||
7261 | ||
df7492f9 | 7262 | static void |
cf84bb53 JB |
7263 | consume_chars (struct coding_system *coding, Lisp_Object translation_table, |
7264 | int max_lookup) | |
df7492f9 KH |
7265 | { |
7266 | int *buf = coding->charbuf; | |
ff0dacd7 | 7267 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 7268 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 7269 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
7270 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
7271 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
7272 | int multibytep = coding->src_multibyte; |
7273 | Lisp_Object eol_type; | |
7274 | int c; | |
ff0dacd7 | 7275 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 7276 | int *lookup_buf = NULL; |
433f7f87 KH |
7277 | |
7278 | if (! NILP (translation_table)) | |
09ee6fdd | 7279 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 7280 | |
0a9564cb | 7281 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
df7492f9 KH |
7282 | if (VECTORP (eol_type)) |
7283 | eol_type = Qunix; | |
88993dfd | 7284 | |
df7492f9 KH |
7285 | /* Note: composition handling is not yet implemented. */ |
7286 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 7287 | |
0b5670c9 KH |
7288 | if (NILP (coding->src_object)) |
7289 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 7290 | else |
0b5670c9 KH |
7291 | { |
7292 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
7293 | stop = stop_composition = pos; | |
7294 | else | |
7295 | stop = stop_composition = end_pos; | |
7296 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
7297 | stop = stop_charset = pos; | |
7298 | else | |
7299 | stop_charset = end_pos; | |
7300 | } | |
ec6d2bb8 | 7301 | |
24a73b0a | 7302 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 7303 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 7304 | while (buf < buf_end) |
aaaf0b1e | 7305 | { |
433f7f87 KH |
7306 | Lisp_Object trans; |
7307 | ||
df7492f9 | 7308 | if (pos == stop) |
ec6d2bb8 | 7309 | { |
df7492f9 KH |
7310 | if (pos == end_pos) |
7311 | break; | |
ff0dacd7 KH |
7312 | if (pos == stop_composition) |
7313 | buf = handle_composition_annotation (pos, end_pos, coding, | |
7314 | buf, &stop_composition); | |
7315 | if (pos == stop_charset) | |
7316 | buf = handle_charset_annotation (pos, end_pos, coding, | |
7317 | buf, &stop_charset); | |
7318 | stop = (stop_composition < stop_charset | |
7319 | ? stop_composition : stop_charset); | |
df7492f9 KH |
7320 | } |
7321 | ||
7322 | if (! multibytep) | |
4776e638 | 7323 | { |
d3e4cb56 | 7324 | EMACS_INT bytes; |
aaaf0b1e | 7325 | |
4d1e6632 KH |
7326 | if (coding->encoder == encode_coding_raw_text |
7327 | || coding->encoder == encode_coding_ccl) | |
ea29edf2 KH |
7328 | c = *src++, pos++; |
7329 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 7330 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 7331 | else |
f03caae0 | 7332 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 7333 | } |
df7492f9 | 7334 | else |
db274c7a | 7335 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
7336 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
7337 | c = '\n'; | |
7338 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 7339 | { |
df7492f9 | 7340 | if (c == '\n') |
aaaf0b1e | 7341 | { |
df7492f9 KH |
7342 | if (EQ (eol_type, Qdos)) |
7343 | *buf++ = '\r'; | |
7344 | else | |
7345 | c = '\r'; | |
aaaf0b1e KH |
7346 | } |
7347 | } | |
433f7f87 | 7348 | |
e6a54062 | 7349 | trans = Qnil; |
09ee6fdd | 7350 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 7351 | if (NILP (trans)) |
433f7f87 KH |
7352 | *buf++ = c; |
7353 | else | |
7354 | { | |
7355 | int from_nchars = 1, to_nchars = 1; | |
7356 | int *lookup_buf_end; | |
7357 | const unsigned char *p = src; | |
7358 | int i; | |
7359 | ||
7360 | lookup_buf[0] = c; | |
7361 | for (i = 1; i < max_lookup && p < src_end; i++) | |
7362 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
7363 | lookup_buf_end = lookup_buf + i; | |
e951386e KH |
7364 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
7365 | if (INTEGERP (trans)) | |
7366 | c = XINT (trans); | |
7367 | else if (CONSP (trans)) | |
7368 | { | |
7369 | from_nchars = ASIZE (XCAR (trans)); | |
7370 | trans = XCDR (trans); | |
7371 | if (INTEGERP (trans)) | |
7372 | c = XINT (trans); | |
7373 | else | |
7374 | { | |
7375 | to_nchars = ASIZE (trans); | |
7376 | if (buf + to_nchars > buf_end) | |
7377 | break; | |
7378 | c = XINT (AREF (trans, 0)); | |
7379 | } | |
7380 | } | |
7381 | else | |
433f7f87 | 7382 | break; |
e951386e | 7383 | *buf++ = c; |
433f7f87 KH |
7384 | for (i = 1; i < to_nchars; i++) |
7385 | *buf++ = XINT (AREF (trans, i)); | |
7386 | for (i = 1; i < from_nchars; i++, pos++) | |
7387 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7388 | } | |
aaaf0b1e | 7389 | } |
ec6d2bb8 | 7390 | |
df7492f9 KH |
7391 | coding->consumed = src - coding->source; |
7392 | coding->consumed_char = pos - coding->src_pos; | |
7393 | coding->charbuf_used = buf - coding->charbuf; | |
7394 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7395 | } |
7396 | ||
4ed46869 | 7397 | |
df7492f9 KH |
7398 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7399 | CODING->src_object is a buffer or a string. | |
7400 | CODING->dst_object is a buffer or nil. | |
7401 | ||
7402 | If CODING->src_object is a buffer, it must be the current buffer. | |
7403 | In this case, if CODING->src_pos is positive, it is a position of | |
7404 | the source text in the buffer, otherwise. the source text is in the | |
7405 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7406 | the text from GPT (which must be the same as PT). If this is the | |
7407 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7408 | negative and CODING should not have `pre-write-conversion'. | |
7409 | ||
7410 | If CODING->src_object is a string, CODING should not have | |
7411 | `pre-write-conversion'. | |
7412 | ||
7413 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7414 | the current point of that buffer. | |
7415 | ||
7416 | If CODING->dst_object is nil, the encoded data is placed at the | |
7417 | memory area specified by CODING->destination. */ | |
7418 | ||
7419 | static int | |
971de7fb | 7420 | encode_coding (struct coding_system *coding) |
4ed46869 | 7421 | { |
df7492f9 | 7422 | Lisp_Object attrs; |
7d64c6ad | 7423 | Lisp_Object translation_table; |
09ee6fdd | 7424 | int max_lookup; |
fb608df3 | 7425 | struct ccl_spec cclspec; |
9861e777 | 7426 | |
df7492f9 | 7427 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7428 | if (coding->encoder == encode_coding_raw_text) |
7429 | translation_table = Qnil, max_lookup = 0; | |
7430 | else | |
7431 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7432 | |
df7492f9 | 7433 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7434 | { |
df7492f9 KH |
7435 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7436 | coding->dst_multibyte | |
7437 | = ! NILP (current_buffer->enable_multibyte_characters); | |
8844fa83 | 7438 | } |
4ed46869 | 7439 | |
b73bfc1c | 7440 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7441 | coding->produced = coding->produced_char = 0; |
065e3595 | 7442 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7443 | coding->errors = 0; |
b73bfc1c | 7444 | |
df7492f9 | 7445 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7446 | |
fb608df3 KH |
7447 | if (coding->encoder == encode_coding_ccl) |
7448 | { | |
7449 | coding->spec.ccl = &cclspec; | |
7450 | setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding)); | |
7451 | } | |
df7492f9 KH |
7452 | do { |
7453 | coding_set_source (coding); | |
09ee6fdd | 7454 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7455 | coding_set_destination (coding); |
7456 | (*(coding->encoder)) (coding); | |
7457 | } while (coding->consumed_char < coding->src_chars); | |
7458 | ||
284201e4 | 7459 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
df7492f9 KH |
7460 | insert_from_gap (coding->produced_char, coding->produced); |
7461 | ||
7462 | return (coding->result); | |
ec6d2bb8 KH |
7463 | } |
7464 | ||
fb88bf2d | 7465 | |
24a73b0a KH |
7466 | /* Name (or base name) of work buffer for code conversion. */ |
7467 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7468 | |
24a73b0a KH |
7469 | /* A working buffer used by the top level conversion. Once it is |
7470 | created, it is never destroyed. It has the name | |
7471 | Vcode_conversion_workbuf_name. The other working buffers are | |
7472 | destroyed after the use is finished, and their names are modified | |
7473 | versions of Vcode_conversion_workbuf_name. */ | |
7474 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7475 | |
24a73b0a KH |
7476 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
7477 | static int reused_workbuf_in_use; | |
4ed46869 | 7478 | |
24a73b0a | 7479 | |
ad1746f5 | 7480 | /* Return a working buffer of code conversion. MULTIBYTE specifies the |
24a73b0a | 7481 | multibyteness of returning buffer. */ |
b73bfc1c | 7482 | |
f6cbaf43 | 7483 | static Lisp_Object |
971de7fb | 7484 | make_conversion_work_buffer (int multibyte) |
df7492f9 | 7485 | { |
24a73b0a KH |
7486 | Lisp_Object name, workbuf; |
7487 | struct buffer *current; | |
4ed46869 | 7488 | |
24a73b0a | 7489 | if (reused_workbuf_in_use++) |
065e3595 KH |
7490 | { |
7491 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7492 | workbuf = Fget_buffer_create (name); | |
7493 | } | |
df7492f9 | 7494 | else |
065e3595 | 7495 | { |
159bd5a2 | 7496 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7497 | Vcode_conversion_reused_workbuf |
7498 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7499 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7500 | } |
24a73b0a KH |
7501 | current = current_buffer; |
7502 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7503 | /* We can't allow modification hooks to run in the work buffer. For |
7504 | instance, directory_files_internal assumes that file decoding | |
7505 | doesn't compile new regexps. */ | |
7506 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7507 | Ferase_buffer (); |
df7492f9 | 7508 | current_buffer->undo_list = Qt; |
24a73b0a | 7509 | current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil; |
df7492f9 | 7510 | set_buffer_internal (current); |
24a73b0a | 7511 | return workbuf; |
df7492f9 | 7512 | } |
d46c5b12 | 7513 | |
24a73b0a | 7514 | |
4776e638 | 7515 | static Lisp_Object |
971de7fb | 7516 | code_conversion_restore (Lisp_Object arg) |
4776e638 | 7517 | { |
24a73b0a | 7518 | Lisp_Object current, workbuf; |
948bdcf3 | 7519 | struct gcpro gcpro1; |
24a73b0a | 7520 | |
948bdcf3 | 7521 | GCPRO1 (arg); |
24a73b0a KH |
7522 | current = XCAR (arg); |
7523 | workbuf = XCDR (arg); | |
7524 | if (! NILP (workbuf)) | |
7525 | { | |
7526 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7527 | reused_workbuf_in_use = 0; | |
7528 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
7529 | Fkill_buffer (workbuf); | |
7530 | } | |
7531 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7532 | UNGCPRO; |
4776e638 KH |
7533 | return Qnil; |
7534 | } | |
b73bfc1c | 7535 | |
24a73b0a | 7536 | Lisp_Object |
971de7fb | 7537 | code_conversion_save (int with_work_buf, int multibyte) |
df7492f9 | 7538 | { |
24a73b0a | 7539 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7540 | |
4776e638 | 7541 | if (with_work_buf) |
24a73b0a KH |
7542 | workbuf = make_conversion_work_buffer (multibyte); |
7543 | record_unwind_protect (code_conversion_restore, | |
7544 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7545 | return workbuf; |
df7492f9 | 7546 | } |
d46c5b12 | 7547 | |
df7492f9 | 7548 | int |
cf84bb53 JB |
7549 | decode_coding_gap (struct coding_system *coding, |
7550 | EMACS_INT chars, EMACS_INT bytes) | |
df7492f9 | 7551 | { |
1a4990fb | 7552 | int count = SPECPDL_INDEX (); |
5e5c78be | 7553 | Lisp_Object attrs; |
fb88bf2d | 7554 | |
24a73b0a | 7555 | code_conversion_save (0, 0); |
ec6d2bb8 | 7556 | |
24a73b0a | 7557 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7558 | coding->src_chars = chars; |
7559 | coding->src_bytes = bytes; | |
7560 | coding->src_pos = -chars; | |
7561 | coding->src_pos_byte = -bytes; | |
7562 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7563 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7564 | coding->dst_pos = PT; |
7565 | coding->dst_pos_byte = PT_BYTE; | |
71c81426 | 7566 | coding->dst_multibyte = ! NILP (current_buffer->enable_multibyte_characters); |
4ed46869 | 7567 | |
df7492f9 KH |
7568 | if (CODING_REQUIRE_DETECTION (coding)) |
7569 | detect_coding (coding); | |
8f924df7 | 7570 | |
9286b333 | 7571 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7572 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7573 | decode_coding (coding); |
287c57d7 | 7574 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7575 | |
5e5c78be KH |
7576 | attrs = CODING_ID_ATTRS (coding->id); |
7577 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 7578 | { |
5e5c78be KH |
7579 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
7580 | Lisp_Object val; | |
7581 | ||
7582 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7583 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7584 | make_number (coding->produced_char)); | |
5e5c78be KH |
7585 | CHECK_NATNUM (val); |
7586 | coding->produced_char += Z - prev_Z; | |
7587 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7588 | } |
4ed46869 | 7589 | |
df7492f9 | 7590 | unbind_to (count, Qnil); |
b73bfc1c KH |
7591 | return coding->result; |
7592 | } | |
52d41803 | 7593 | |
4ed46869 | 7594 | int |
cf84bb53 JB |
7595 | encode_coding_gap (struct coding_system *coding, |
7596 | EMACS_INT chars, EMACS_INT bytes) | |
4ed46869 | 7597 | { |
1a4990fb | 7598 | int count = SPECPDL_INDEX (); |
4ed46869 | 7599 | |
24a73b0a | 7600 | code_conversion_save (0, 0); |
4ed46869 | 7601 | |
24a73b0a | 7602 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7603 | coding->src_chars = chars; |
7604 | coding->src_bytes = bytes; | |
7605 | coding->src_pos = -chars; | |
7606 | coding->src_pos_byte = -bytes; | |
7607 | coding->src_multibyte = chars < bytes; | |
7608 | coding->dst_object = coding->src_object; | |
7609 | coding->dst_pos = PT; | |
7610 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 7611 | |
df7492f9 | 7612 | encode_coding (coding); |
b73bfc1c | 7613 | |
df7492f9 KH |
7614 | unbind_to (count, Qnil); |
7615 | return coding->result; | |
7616 | } | |
4ed46869 | 7617 | |
d46c5b12 | 7618 | |
df7492f9 KH |
7619 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7620 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7621 | |
df7492f9 | 7622 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7623 | |
df7492f9 KH |
7624 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7625 | are positions in the buffer. | |
b73bfc1c | 7626 | |
df7492f9 KH |
7627 | If it is a string, the text is at the beginning of the string. |
7628 | FROM and TO are indices to the string. | |
4ed46869 | 7629 | |
df7492f9 KH |
7630 | If it is nil, the text is at coding->source. FROM and TO are |
7631 | indices to coding->source. | |
bb10be8b | 7632 | |
df7492f9 | 7633 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7634 | |
df7492f9 KH |
7635 | If it is a buffer, the decoded text is inserted at point of the |
7636 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7637 | is deleted. | |
4ed46869 | 7638 | |
df7492f9 KH |
7639 | If it is Qt, a string is made from the decoded text, and |
7640 | set in CODING->dst_object. | |
d46c5b12 | 7641 | |
df7492f9 | 7642 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7643 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7644 | CODING->destination by xmalloc. If the decoded text is longer than |
7645 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7646 | */ | |
d46c5b12 | 7647 | |
df7492f9 | 7648 | void |
cf84bb53 JB |
7649 | decode_coding_object (struct coding_system *coding, |
7650 | Lisp_Object src_object, | |
7651 | EMACS_INT from, EMACS_INT from_byte, | |
7652 | EMACS_INT to, EMACS_INT to_byte, | |
7653 | Lisp_Object dst_object) | |
d46c5b12 | 7654 | { |
1a4990fb | 7655 | int count = SPECPDL_INDEX (); |
df7492f9 KH |
7656 | unsigned char *destination; |
7657 | EMACS_INT dst_bytes; | |
7658 | EMACS_INT chars = to - from; | |
7659 | EMACS_INT bytes = to_byte - from_byte; | |
7660 | Lisp_Object attrs; | |
4776e638 | 7661 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7662 | int need_marker_adjustment = 0; |
b3bfad50 | 7663 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7664 | |
b3bfad50 | 7665 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 7666 | |
df7492f9 | 7667 | if (NILP (dst_object)) |
d46c5b12 | 7668 | { |
df7492f9 KH |
7669 | destination = coding->destination; |
7670 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 7671 | } |
93dec019 | 7672 | |
df7492f9 KH |
7673 | coding->src_object = src_object; |
7674 | coding->src_chars = chars; | |
7675 | coding->src_bytes = bytes; | |
7676 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 7677 | |
df7492f9 | 7678 | if (STRINGP (src_object)) |
d46c5b12 | 7679 | { |
df7492f9 KH |
7680 | coding->src_pos = from; |
7681 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7682 | } |
df7492f9 | 7683 | else if (BUFFERP (src_object)) |
88993dfd | 7684 | { |
df7492f9 KH |
7685 | set_buffer_internal (XBUFFER (src_object)); |
7686 | if (from != GPT) | |
7687 | move_gap_both (from, from_byte); | |
7688 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 7689 | { |
64cedb0c KH |
7690 | struct Lisp_Marker *tail; |
7691 | ||
7692 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7693 | { | |
7694 | tail->need_adjustment | |
7695 | = tail->charpos == (tail->insertion_type ? from : to); | |
7696 | need_marker_adjustment |= tail->need_adjustment; | |
7697 | } | |
4776e638 | 7698 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 7699 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 7700 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
7701 | del_range_both (from, from_byte, to, to_byte, 1); |
7702 | coding->src_pos = -chars; | |
7703 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 7704 | } |
df7492f9 | 7705 | else |
fb88bf2d | 7706 | { |
df7492f9 KH |
7707 | coding->src_pos = from; |
7708 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 7709 | } |
88993dfd KH |
7710 | } |
7711 | ||
df7492f9 KH |
7712 | if (CODING_REQUIRE_DETECTION (coding)) |
7713 | detect_coding (coding); | |
7714 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 7715 | |
2cb26057 KH |
7716 | if (EQ (dst_object, Qt) |
7717 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
7718 | && NILP (dst_object))) | |
b73bfc1c | 7719 | { |
a1567c45 SM |
7720 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
7721 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
7722 | coding->dst_pos = BEG; |
7723 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 7724 | } |
df7492f9 | 7725 | else if (BUFFERP (dst_object)) |
d46c5b12 | 7726 | { |
24a73b0a | 7727 | code_conversion_save (0, 0); |
df7492f9 KH |
7728 | coding->dst_object = dst_object; |
7729 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
7730 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
7731 | coding->dst_multibyte | |
7732 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
d46c5b12 KH |
7733 | } |
7734 | else | |
7735 | { | |
24a73b0a | 7736 | code_conversion_save (0, 0); |
df7492f9 | 7737 | coding->dst_object = Qnil; |
0154725e SM |
7738 | /* Most callers presume this will return a multibyte result, and they |
7739 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
7740 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 7741 | coding->dst_multibyte = 1; |
d46c5b12 KH |
7742 | } |
7743 | ||
df7492f9 | 7744 | decode_coding (coding); |
fa46990e | 7745 | |
df7492f9 KH |
7746 | if (BUFFERP (coding->dst_object)) |
7747 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 7748 | |
df7492f9 | 7749 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 7750 | { |
b3bfad50 | 7751 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
df7492f9 | 7752 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 7753 | Lisp_Object val; |
d46c5b12 | 7754 | |
c0cc7f7f | 7755 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
7756 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7757 | old_deactivate_mark); | |
d4850d67 KH |
7758 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
7759 | make_number (coding->produced_char)); | |
df7492f9 KH |
7760 | UNGCPRO; |
7761 | CHECK_NATNUM (val); | |
7762 | coding->produced_char += Z - prev_Z; | |
7763 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 7764 | } |
de79a6a5 | 7765 | |
df7492f9 | 7766 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 7767 | { |
df7492f9 KH |
7768 | coding->dst_object = Fbuffer_string (); |
7769 | } | |
7770 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
7771 | { | |
7772 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7773 | if (dst_bytes < coding->produced) | |
7774 | { | |
b3bfad50 | 7775 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
7776 | if (! destination) |
7777 | { | |
065e3595 | 7778 | record_conversion_result (coding, |
ebaf11b6 | 7779 | CODING_RESULT_INSUFFICIENT_MEM); |
df7492f9 KH |
7780 | unbind_to (count, Qnil); |
7781 | return; | |
7782 | } | |
7783 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
7784 | move_gap_both (BEGV, BEGV_BYTE); | |
72af86bd | 7785 | memcpy (destination, BEGV_ADDR, coding->produced); |
df7492f9 | 7786 | coding->destination = destination; |
d46c5b12 | 7787 | } |
ec6d2bb8 | 7788 | } |
b73bfc1c | 7789 | |
4776e638 KH |
7790 | if (saved_pt >= 0) |
7791 | { | |
7792 | /* This is the case of: | |
7793 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7794 | As we have moved PT while replacing the original buffer | |
7795 | contents, we must recover it now. */ | |
7796 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 7797 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
7798 | if (saved_pt < from) |
7799 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7800 | else if (saved_pt < from + chars) | |
7801 | TEMP_SET_PT_BOTH (from, from_byte); | |
7802 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
7803 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
7804 | saved_pt_byte + (coding->produced - bytes)); | |
7805 | else | |
7806 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
7807 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7808 | |
7809 | if (need_marker_adjustment) | |
7810 | { | |
7811 | struct Lisp_Marker *tail; | |
7812 | ||
7813 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7814 | if (tail->need_adjustment) | |
7815 | { | |
7816 | tail->need_adjustment = 0; | |
7817 | if (tail->insertion_type) | |
7818 | { | |
7819 | tail->bytepos = from_byte; | |
7820 | tail->charpos = from; | |
7821 | } | |
7822 | else | |
7823 | { | |
7824 | tail->bytepos = from_byte + coding->produced; | |
7825 | tail->charpos | |
7826 | = (NILP (current_buffer->enable_multibyte_characters) | |
7827 | ? tail->bytepos : from + coding->produced_char); | |
7828 | } | |
7829 | } | |
7830 | } | |
d46c5b12 | 7831 | } |
4776e638 | 7832 | |
b3bfad50 | 7833 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 7834 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
7835 | } |
7836 | ||
d46c5b12 | 7837 | |
df7492f9 | 7838 | void |
cf84bb53 JB |
7839 | encode_coding_object (struct coding_system *coding, |
7840 | Lisp_Object src_object, | |
7841 | EMACS_INT from, EMACS_INT from_byte, | |
7842 | EMACS_INT to, EMACS_INT to_byte, | |
7843 | Lisp_Object dst_object) | |
d46c5b12 | 7844 | { |
1a4990fb | 7845 | int count = SPECPDL_INDEX (); |
df7492f9 KH |
7846 | EMACS_INT chars = to - from; |
7847 | EMACS_INT bytes = to_byte - from_byte; | |
7848 | Lisp_Object attrs; | |
4776e638 | 7849 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7850 | int need_marker_adjustment = 0; |
c02d943b | 7851 | int kill_src_buffer = 0; |
b3bfad50 | 7852 | Lisp_Object old_deactivate_mark; |
df7492f9 | 7853 | |
b3bfad50 | 7854 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
7855 | |
7856 | coding->src_object = src_object; | |
7857 | coding->src_chars = chars; | |
7858 | coding->src_bytes = bytes; | |
7859 | coding->src_multibyte = chars < bytes; | |
7860 | ||
7861 | attrs = CODING_ID_ATTRS (coding->id); | |
7862 | ||
64cedb0c KH |
7863 | if (EQ (src_object, dst_object)) |
7864 | { | |
7865 | struct Lisp_Marker *tail; | |
7866 | ||
7867 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7868 | { | |
7869 | tail->need_adjustment | |
7870 | = tail->charpos == (tail->insertion_type ? from : to); | |
7871 | need_marker_adjustment |= tail->need_adjustment; | |
7872 | } | |
7873 | } | |
7874 | ||
df7492f9 | 7875 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 7876 | { |
24a73b0a | 7877 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
7878 | set_buffer_internal (XBUFFER (coding->src_object)); |
7879 | if (STRINGP (src_object)) | |
7880 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
7881 | else if (BUFFERP (src_object)) | |
7882 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
7883 | else | |
7884 | insert_1_both (coding->source + from, chars, bytes, 0, 0, 0); | |
d46c5b12 | 7885 | |
df7492f9 KH |
7886 | if (EQ (src_object, dst_object)) |
7887 | { | |
7888 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 7889 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
7890 | del_range_both (from, from_byte, to, to_byte, 1); |
7891 | set_buffer_internal (XBUFFER (coding->src_object)); | |
7892 | } | |
7893 | ||
d4850d67 KH |
7894 | { |
7895 | Lisp_Object args[3]; | |
b3bfad50 | 7896 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 7897 | |
b3bfad50 KH |
7898 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7899 | old_deactivate_mark); | |
d4850d67 KH |
7900 | args[0] = CODING_ATTR_PRE_WRITE (attrs); |
7901 | args[1] = make_number (BEG); | |
7902 | args[2] = make_number (Z); | |
7903 | safe_call (3, args); | |
b3bfad50 | 7904 | UNGCPRO; |
d4850d67 | 7905 | } |
c02d943b KH |
7906 | if (XBUFFER (coding->src_object) != current_buffer) |
7907 | kill_src_buffer = 1; | |
ac87bbef | 7908 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7909 | if (BEG != GPT) |
7910 | move_gap_both (BEG, BEG_BYTE); | |
7911 | coding->src_chars = Z - BEG; | |
7912 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
7913 | coding->src_pos = BEG; | |
7914 | coding->src_pos_byte = BEG_BYTE; | |
7915 | coding->src_multibyte = Z < Z_BYTE; | |
7916 | } | |
7917 | else if (STRINGP (src_object)) | |
d46c5b12 | 7918 | { |
24a73b0a | 7919 | code_conversion_save (0, 0); |
df7492f9 KH |
7920 | coding->src_pos = from; |
7921 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 7922 | } |
df7492f9 | 7923 | else if (BUFFERP (src_object)) |
b73bfc1c | 7924 | { |
24a73b0a | 7925 | code_conversion_save (0, 0); |
df7492f9 | 7926 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 7927 | if (EQ (src_object, dst_object)) |
d46c5b12 | 7928 | { |
4776e638 | 7929 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
7930 | coding->src_object = del_range_1 (from, to, 1, 1); |
7931 | coding->src_pos = 0; | |
7932 | coding->src_pos_byte = 0; | |
d46c5b12 | 7933 | } |
df7492f9 | 7934 | else |
d46c5b12 | 7935 | { |
ff0dacd7 KH |
7936 | if (from < GPT && to >= GPT) |
7937 | move_gap_both (from, from_byte); | |
df7492f9 KH |
7938 | coding->src_pos = from; |
7939 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7940 | } |
d46c5b12 | 7941 | } |
4776e638 | 7942 | else |
24a73b0a | 7943 | code_conversion_save (0, 0); |
d46c5b12 | 7944 | |
df7492f9 | 7945 | if (BUFFERP (dst_object)) |
88993dfd | 7946 | { |
df7492f9 | 7947 | coding->dst_object = dst_object; |
28f67a95 KH |
7948 | if (EQ (src_object, dst_object)) |
7949 | { | |
7950 | coding->dst_pos = from; | |
7951 | coding->dst_pos_byte = from_byte; | |
7952 | } | |
7953 | else | |
7954 | { | |
319a3947 KH |
7955 | struct buffer *current = current_buffer; |
7956 | ||
7957 | set_buffer_temp (XBUFFER (dst_object)); | |
7958 | coding->dst_pos = PT; | |
7959 | coding->dst_pos_byte = PT_BYTE; | |
7960 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
7961 | set_buffer_temp (current); | |
28f67a95 | 7962 | } |
df7492f9 KH |
7963 | coding->dst_multibyte |
7964 | = ! NILP (XBUFFER (dst_object)->enable_multibyte_characters); | |
88993dfd | 7965 | } |
df7492f9 | 7966 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 7967 | { |
df7492f9 | 7968 | coding->dst_object = Qnil; |
df7492f9 | 7969 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
7970 | if (coding->dst_bytes == 0) |
7971 | coding->dst_bytes = 1; | |
7972 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 7973 | coding->dst_multibyte = 0; |
d46c5b12 KH |
7974 | } |
7975 | else | |
7976 | { | |
df7492f9 KH |
7977 | coding->dst_object = Qnil; |
7978 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
7979 | } |
7980 | ||
df7492f9 | 7981 | encode_coding (coding); |
d46c5b12 | 7982 | |
df7492f9 | 7983 | if (EQ (dst_object, Qt)) |
d46c5b12 | 7984 | { |
df7492f9 KH |
7985 | if (BUFFERP (coding->dst_object)) |
7986 | coding->dst_object = Fbuffer_string (); | |
7987 | else | |
d46c5b12 | 7988 | { |
df7492f9 KH |
7989 | coding->dst_object |
7990 | = make_unibyte_string ((char *) coding->destination, | |
7991 | coding->produced); | |
7992 | xfree (coding->destination); | |
d46c5b12 | 7993 | } |
4ed46869 | 7994 | } |
d46c5b12 | 7995 | |
4776e638 KH |
7996 | if (saved_pt >= 0) |
7997 | { | |
7998 | /* This is the case of: | |
7999 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
8000 | As we have moved PT while replacing the original buffer | |
8001 | contents, we must recover it now. */ | |
8002 | set_buffer_internal (XBUFFER (src_object)); | |
8003 | if (saved_pt < from) | |
8004 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
8005 | else if (saved_pt < from + chars) | |
8006 | TEMP_SET_PT_BOTH (from, from_byte); | |
8007 | else if (! NILP (current_buffer->enable_multibyte_characters)) | |
8008 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), | |
8009 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 8010 | else |
4776e638 KH |
8011 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
8012 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
8013 | |
8014 | if (need_marker_adjustment) | |
8015 | { | |
8016 | struct Lisp_Marker *tail; | |
8017 | ||
8018 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
8019 | if (tail->need_adjustment) | |
8020 | { | |
8021 | tail->need_adjustment = 0; | |
8022 | if (tail->insertion_type) | |
8023 | { | |
8024 | tail->bytepos = from_byte; | |
8025 | tail->charpos = from; | |
8026 | } | |
8027 | else | |
8028 | { | |
8029 | tail->bytepos = from_byte + coding->produced; | |
8030 | tail->charpos | |
8031 | = (NILP (current_buffer->enable_multibyte_characters) | |
8032 | ? tail->bytepos : from + coding->produced_char); | |
8033 | } | |
8034 | } | |
8035 | } | |
4776e638 KH |
8036 | } |
8037 | ||
c02d943b KH |
8038 | if (kill_src_buffer) |
8039 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
8040 | |
8041 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 8042 | unbind_to (count, Qnil); |
b73bfc1c KH |
8043 | } |
8044 | ||
df7492f9 | 8045 | |
b73bfc1c | 8046 | Lisp_Object |
971de7fb | 8047 | preferred_coding_system (void) |
b73bfc1c | 8048 | { |
df7492f9 | 8049 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 8050 | |
df7492f9 | 8051 | return CODING_ID_NAME (id); |
4ed46869 KH |
8052 | } |
8053 | ||
8054 | \f | |
8055 | #ifdef emacs | |
1397dc18 | 8056 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 8057 | |
4ed46869 | 8058 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 8059 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 8060 | See the documentation of `define-coding-system' for information |
48b0f3ae | 8061 | about coding-system objects. */) |
5842a27b | 8062 | (Lisp_Object object) |
4ed46869 | 8063 | { |
d4a1d553 JB |
8064 | if (NILP (object) |
8065 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 8066 | return Qt; |
d4a1d553 JB |
8067 | if (! SYMBOLP (object) |
8068 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
8069 | return Qnil; |
8070 | return Qt; | |
4ed46869 KH |
8071 | } |
8072 | ||
9d991de8 RS |
8073 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
8074 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae | 8075 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
5842a27b | 8076 | (Lisp_Object prompt) |
4ed46869 | 8077 | { |
e0e989f6 | 8078 | Lisp_Object val; |
9d991de8 RS |
8079 | do |
8080 | { | |
4608c386 KH |
8081 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
8082 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 8083 | } |
8f924df7 | 8084 | while (SCHARS (val) == 0); |
e0e989f6 | 8085 | return (Fintern (val, Qnil)); |
4ed46869 KH |
8086 | } |
8087 | ||
9b787f3e | 8088 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 8089 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
8090 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
8091 | Ignores case when completing coding systems (all Emacs coding systems | |
8092 | are lower-case). */) | |
5842a27b | 8093 | (Lisp_Object prompt, Lisp_Object default_coding_system) |
4ed46869 | 8094 | { |
f44d27ce | 8095 | Lisp_Object val; |
c7183fb8 GM |
8096 | int count = SPECPDL_INDEX (); |
8097 | ||
9b787f3e | 8098 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 8099 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 8100 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 8101 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
8102 | Qt, Qnil, Qcoding_system_history, |
8103 | default_coding_system, Qnil); | |
c7183fb8 | 8104 | unbind_to (count, Qnil); |
8f924df7 | 8105 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
8106 | } |
8107 | ||
8108 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
8109 | 1, 1, 0, | |
48b0f3ae | 8110 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
8111 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
8112 | It is valid if it is nil or a symbol defined as a coding system by the | |
8113 | function `define-coding-system'. */) | |
5842a27b | 8114 | (Lisp_Object coding_system) |
4ed46869 | 8115 | { |
44e8490d KH |
8116 | Lisp_Object define_form; |
8117 | ||
8118 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
8119 | if (! NILP (define_form)) | |
8120 | { | |
8121 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
8122 | safe_eval (define_form); | |
8123 | } | |
4ed46869 KH |
8124 | if (!NILP (Fcoding_system_p (coding_system))) |
8125 | return coding_system; | |
fcad4ec4 | 8126 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 8127 | } |
df7492f9 | 8128 | |
3a73fa5d | 8129 | \f |
89528eb3 KH |
8130 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
8131 | HIGHEST is nonzero, return the coding system of the highest | |
ad1746f5 | 8132 | priority among the detected coding systems. Otherwise return a |
89528eb3 KH |
8133 | list of detected coding systems sorted by their priorities. If |
8134 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
8135 | multibyte form but contains only ASCII and eight-bit chars. | |
8136 | Otherwise, the bytes are raw bytes. | |
8137 | ||
8138 | CODING-SYSTEM controls the detection as below: | |
8139 | ||
8140 | If it is nil, detect both text-format and eol-format. If the | |
8141 | text-format part of CODING-SYSTEM is already specified | |
8142 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
8143 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
8144 | detect only text-format. */ | |
8145 | ||
d46c5b12 | 8146 | Lisp_Object |
cf84bb53 JB |
8147 | detect_coding_system (const unsigned char *src, |
8148 | EMACS_INT src_chars, EMACS_INT src_bytes, | |
8149 | int highest, int multibytep, | |
8150 | Lisp_Object coding_system) | |
4ed46869 | 8151 | { |
8f924df7 | 8152 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 8153 | Lisp_Object attrs, eol_type; |
4533845d | 8154 | Lisp_Object val = Qnil; |
df7492f9 | 8155 | struct coding_system coding; |
89528eb3 | 8156 | int id; |
ff0dacd7 | 8157 | struct coding_detection_info detect_info; |
24a73b0a | 8158 | enum coding_category base_category; |
2f3cbb32 | 8159 | int null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 8160 | |
df7492f9 KH |
8161 | if (NILP (coding_system)) |
8162 | coding_system = Qundecided; | |
8163 | setup_coding_system (coding_system, &coding); | |
8164 | attrs = CODING_ID_ATTRS (coding.id); | |
8165 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 8166 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 8167 | |
df7492f9 | 8168 | coding.source = src; |
24a73b0a | 8169 | coding.src_chars = src_chars; |
df7492f9 KH |
8170 | coding.src_bytes = src_bytes; |
8171 | coding.src_multibyte = multibytep; | |
8172 | coding.consumed = 0; | |
89528eb3 | 8173 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 8174 | coding.head_ascii = 0; |
d46c5b12 | 8175 | |
ff0dacd7 | 8176 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 8177 | |
89528eb3 | 8178 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
8179 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
8180 | if (base_category == coding_category_undecided) | |
4ed46869 | 8181 | { |
ff0dacd7 KH |
8182 | enum coding_category category; |
8183 | struct coding_system *this; | |
8184 | int c, i; | |
88993dfd | 8185 | |
24a73b0a | 8186 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 8187 | for (; src < src_end; src++) |
4ed46869 | 8188 | { |
df7492f9 | 8189 | c = *src; |
6cb21a4f | 8190 | if (c & 0x80) |
6cb21a4f | 8191 | { |
2f3cbb32 | 8192 | eight_bit_found = 1; |
2f3cbb32 KH |
8193 | if (null_byte_found) |
8194 | break; | |
8195 | } | |
c0e16b14 | 8196 | else if (c < 0x20) |
2f3cbb32 KH |
8197 | { |
8198 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
8199 | && ! inhibit_iso_escape_detection | |
8200 | && ! detect_info.checked) | |
6cb21a4f | 8201 | { |
2f3cbb32 KH |
8202 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
8203 | { | |
8204 | /* We have scanned the whole data. */ | |
8205 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
8206 | { |
8207 | /* We didn't find an 8-bit code. We may | |
8208 | have found a null-byte, but it's very | |
8209 | rare that a binary file confirm to | |
8210 | ISO-2022. */ | |
8211 | src = src_end; | |
8212 | coding.head_ascii = src - coding.source; | |
8213 | } | |
8214 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
8215 | break; |
8216 | } | |
8217 | } | |
97b1b294 | 8218 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
8219 | { |
8220 | null_byte_found = 1; | |
8221 | if (eight_bit_found) | |
8222 | break; | |
6cb21a4f | 8223 | } |
c006c0c8 KH |
8224 | if (! eight_bit_found) |
8225 | coding.head_ascii++; | |
6cb21a4f | 8226 | } |
c006c0c8 | 8227 | else if (! eight_bit_found) |
c0e16b14 | 8228 | coding.head_ascii++; |
4ed46869 | 8229 | } |
88993dfd | 8230 | |
2f3cbb32 KH |
8231 | if (null_byte_found || eight_bit_found |
8232 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
8233 | || detect_info.found) |
8234 | { | |
2f3cbb32 | 8235 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
8236 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
8237 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 8238 | { |
6cb21a4f | 8239 | category = coding_priorities[i]; |
c7266f4a | 8240 | this = coding_categories + category; |
6cb21a4f | 8241 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
8242 | break; |
8243 | } | |
6cb21a4f | 8244 | else |
2f3cbb32 KH |
8245 | { |
8246 | if (null_byte_found) | |
8247 | { | |
8248 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
8249 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
8250 | } | |
8251 | for (i = 0; i < coding_category_raw_text; i++) | |
8252 | { | |
8253 | category = coding_priorities[i]; | |
8254 | this = coding_categories + category; | |
6cb21a4f | 8255 | |
2f3cbb32 KH |
8256 | if (this->id < 0) |
8257 | { | |
8258 | /* No coding system of this category is defined. */ | |
8259 | detect_info.rejected |= (1 << category); | |
8260 | } | |
8261 | else if (category >= coding_category_raw_text) | |
8262 | continue; | |
8263 | else if (detect_info.checked & (1 << category)) | |
8264 | { | |
8265 | if (highest | |
8266 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 8267 | break; |
2f3cbb32 KH |
8268 | } |
8269 | else if ((*(this->detector)) (&coding, &detect_info) | |
8270 | && highest | |
8271 | && (detect_info.found & (1 << category))) | |
8272 | { | |
8273 | if (category == coding_category_utf_16_auto) | |
8274 | { | |
8275 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8276 | category = coding_category_utf_16_le; | |
8277 | else | |
8278 | category = coding_category_utf_16_be; | |
8279 | } | |
8280 | break; | |
8281 | } | |
8282 | } | |
8283 | } | |
6cb21a4f | 8284 | } |
ec6d2bb8 | 8285 | |
4cddb209 KH |
8286 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
8287 | || null_byte_found) | |
ec6d2bb8 | 8288 | { |
ff0dacd7 | 8289 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 8290 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
8291 | val = Fcons (make_number (id), Qnil); |
8292 | } | |
ff0dacd7 | 8293 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 8294 | { |
ff0dacd7 | 8295 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
8296 | id = coding_categories[coding_category_undecided].id; |
8297 | val = Fcons (make_number (id), Qnil); | |
8298 | } | |
8299 | else if (highest) | |
8300 | { | |
ff0dacd7 | 8301 | if (detect_info.found) |
ec6d2bb8 | 8302 | { |
ff0dacd7 KH |
8303 | detect_info.found = 1 << category; |
8304 | val = Fcons (make_number (this->id), Qnil); | |
8305 | } | |
8306 | else | |
8307 | for (i = 0; i < coding_category_raw_text; i++) | |
8308 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
8309 | { | |
8310 | detect_info.found = 1 << coding_priorities[i]; | |
8311 | id = coding_categories[coding_priorities[i]].id; | |
8312 | val = Fcons (make_number (id), Qnil); | |
8313 | break; | |
8314 | } | |
8315 | } | |
89528eb3 KH |
8316 | else |
8317 | { | |
ff0dacd7 KH |
8318 | int mask = detect_info.rejected | detect_info.found; |
8319 | int found = 0; | |
ec6d2bb8 | 8320 | |
89528eb3 | 8321 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
8322 | { |
8323 | category = coding_priorities[i]; | |
8324 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 8325 | { |
ff0dacd7 KH |
8326 | found |= 1 << category; |
8327 | id = coding_categories[category].id; | |
c7266f4a KH |
8328 | if (id >= 0) |
8329 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
8330 | } |
8331 | } | |
8332 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
8333 | { | |
8334 | category = coding_priorities[i]; | |
8335 | if (detect_info.found & (1 << category)) | |
8336 | { | |
8337 | id = coding_categories[category].id; | |
8338 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 8339 | } |
ec6d2bb8 | 8340 | } |
ff0dacd7 | 8341 | detect_info.found |= found; |
ec6d2bb8 | 8342 | } |
ec6d2bb8 | 8343 | } |
a470d443 KH |
8344 | else if (base_category == coding_category_utf_8_auto) |
8345 | { | |
8346 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
8347 | { | |
8348 | struct coding_system *this; | |
8349 | ||
8350 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
8351 | this = coding_categories + coding_category_utf_8_sig; | |
8352 | else | |
8353 | this = coding_categories + coding_category_utf_8_nosig; | |
8354 | val = Fcons (make_number (this->id), Qnil); | |
8355 | } | |
8356 | } | |
24a73b0a KH |
8357 | else if (base_category == coding_category_utf_16_auto) |
8358 | { | |
8359 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
8360 | { | |
24a73b0a KH |
8361 | struct coding_system *this; |
8362 | ||
8363 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8364 | this = coding_categories + coding_category_utf_16_le; | |
8365 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
8366 | this = coding_categories + coding_category_utf_16_be; | |
8367 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
8368 | this = coding_categories + coding_category_utf_16_be_nosig; | |
8369 | else | |
8370 | this = coding_categories + coding_category_utf_16_le_nosig; | |
8371 | val = Fcons (make_number (this->id), Qnil); | |
8372 | } | |
8373 | } | |
df7492f9 KH |
8374 | else |
8375 | { | |
ff0dacd7 | 8376 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 8377 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8378 | } |
df7492f9 | 8379 | |
89528eb3 | 8380 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8381 | { |
4533845d | 8382 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8383 | Lisp_Object tail; |
8384 | ||
89528eb3 KH |
8385 | if (VECTORP (eol_type)) |
8386 | { | |
ff0dacd7 | 8387 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8388 | { |
8389 | if (null_byte_found) | |
8390 | normal_eol = EOL_SEEN_LF; | |
8391 | else | |
8392 | normal_eol = detect_eol (coding.source, src_bytes, | |
8393 | coding_category_raw_text); | |
8394 | } | |
ff0dacd7 KH |
8395 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8396 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8397 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8398 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8399 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8400 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8401 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8402 | coding_category_utf_16_le); | |
8403 | } | |
8404 | else | |
8405 | { | |
8406 | if (EQ (eol_type, Qunix)) | |
8407 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8408 | else if (EQ (eol_type, Qdos)) | |
8409 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8410 | else | |
8411 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8412 | } | |
8413 | ||
df7492f9 KH |
8414 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8415 | { | |
89528eb3 | 8416 | enum coding_category category; |
df7492f9 | 8417 | int this_eol; |
89528eb3 KH |
8418 | |
8419 | id = XINT (XCAR (tail)); | |
8420 | attrs = CODING_ID_ATTRS (id); | |
8421 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8422 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8423 | if (VECTORP (eol_type)) |
8424 | { | |
89528eb3 KH |
8425 | if (category == coding_category_utf_16_be |
8426 | || category == coding_category_utf_16_be_nosig) | |
8427 | this_eol = utf_16_be_eol; | |
8428 | else if (category == coding_category_utf_16_le | |
8429 | || category == coding_category_utf_16_le_nosig) | |
8430 | this_eol = utf_16_le_eol; | |
df7492f9 | 8431 | else |
89528eb3 KH |
8432 | this_eol = normal_eol; |
8433 | ||
df7492f9 KH |
8434 | if (this_eol == EOL_SEEN_LF) |
8435 | XSETCAR (tail, AREF (eol_type, 0)); | |
8436 | else if (this_eol == EOL_SEEN_CRLF) | |
8437 | XSETCAR (tail, AREF (eol_type, 1)); | |
8438 | else if (this_eol == EOL_SEEN_CR) | |
8439 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8440 | else |
8441 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8442 | } |
89528eb3 KH |
8443 | else |
8444 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8445 | } |
8446 | } | |
ec6d2bb8 | 8447 | |
4533845d | 8448 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8449 | } |
8450 | ||
ec6d2bb8 | 8451 | |
d46c5b12 KH |
8452 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8453 | 2, 3, 0, | |
48b0f3ae PJ |
8454 | doc: /* Detect coding system of the text in the region between START and END. |
8455 | Return a list of possible coding systems ordered by priority. | |
b811c52b KH |
8456 | The coding systems to try and their priorities follows what |
8457 | the function `coding-system-priority-list' (which see) returns. | |
ec6d2bb8 | 8458 | |
12e0131a | 8459 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8460 | characters as ESC), it returns a list of single element `undecided' |
8461 | or its subsidiary coding system according to a detected end-of-line | |
8462 | format. | |
ec6d2bb8 | 8463 | |
48b0f3ae PJ |
8464 | If optional argument HIGHEST is non-nil, return the coding system of |
8465 | highest priority. */) | |
5842a27b | 8466 | (Lisp_Object start, Lisp_Object end, Lisp_Object highest) |
d46c5b12 KH |
8467 | { |
8468 | int from, to; | |
8469 | int from_byte, to_byte; | |
ec6d2bb8 | 8470 | |
b7826503 PJ |
8471 | CHECK_NUMBER_COERCE_MARKER (start); |
8472 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 8473 | |
d46c5b12 KH |
8474 | validate_region (&start, &end); |
8475 | from = XINT (start), to = XINT (end); | |
8476 | from_byte = CHAR_TO_BYTE (from); | |
8477 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8478 | |
d46c5b12 KH |
8479 | if (from < GPT && to >= GPT) |
8480 | move_gap_both (to, to_byte); | |
c210f766 | 8481 | |
d46c5b12 | 8482 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8483 | to - from, to_byte - from_byte, |
0a28aafb KH |
8484 | !NILP (highest), |
8485 | !NILP (current_buffer | |
df7492f9 KH |
8486 | ->enable_multibyte_characters), |
8487 | Qnil); | |
ec6d2bb8 KH |
8488 | } |
8489 | ||
d46c5b12 KH |
8490 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8491 | 1, 2, 0, | |
48b0f3ae PJ |
8492 | doc: /* Detect coding system of the text in STRING. |
8493 | Return a list of possible coding systems ordered by priority. | |
67ceab9d KH |
8494 | The coding systems to try and their priorities follows what |
8495 | the function `coding-system-priority-list' (which see) returns. | |
fb88bf2d | 8496 | |
12e0131a | 8497 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8498 | characters as ESC), it returns a list of single element `undecided' |
8499 | or its subsidiary coding system according to a detected end-of-line | |
8500 | format. | |
d46c5b12 | 8501 | |
48b0f3ae PJ |
8502 | If optional argument HIGHEST is non-nil, return the coding system of |
8503 | highest priority. */) | |
5842a27b | 8504 | (Lisp_Object string, Lisp_Object highest) |
d46c5b12 | 8505 | { |
b7826503 | 8506 | CHECK_STRING (string); |
b73bfc1c | 8507 | |
24a73b0a KH |
8508 | return detect_coding_system (SDATA (string), |
8509 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8510 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8511 | Qnil); |
4ed46869 | 8512 | } |
4ed46869 | 8513 | |
b73bfc1c | 8514 | |
df7492f9 | 8515 | static INLINE int |
971de7fb | 8516 | char_encodable_p (int c, Lisp_Object attrs) |
05e6f5dc | 8517 | { |
df7492f9 | 8518 | Lisp_Object tail; |
df7492f9 | 8519 | struct charset *charset; |
7d64c6ad | 8520 | Lisp_Object translation_table; |
d46c5b12 | 8521 | |
7d64c6ad | 8522 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8523 | if (! NILP (translation_table)) |
7d64c6ad | 8524 | c = translate_char (translation_table, c); |
df7492f9 KH |
8525 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8526 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8527 | { |
df7492f9 KH |
8528 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8529 | if (CHAR_CHARSET_P (c, charset)) | |
8530 | break; | |
e133c8fa | 8531 | } |
df7492f9 | 8532 | return (! NILP (tail)); |
05e6f5dc | 8533 | } |
83fa074f | 8534 | |
fb88bf2d | 8535 | |
df7492f9 KH |
8536 | /* Return a list of coding systems that safely encode the text between |
8537 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8538 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8539 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8540 | unibyte, return t. */ |
e077cc80 | 8541 | |
df7492f9 KH |
8542 | DEFUN ("find-coding-systems-region-internal", |
8543 | Ffind_coding_systems_region_internal, | |
8544 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8545 | doc: /* Internal use only. */) | |
5842a27b | 8546 | (Lisp_Object start, Lisp_Object end, Lisp_Object exclude) |
df7492f9 KH |
8547 | { |
8548 | Lisp_Object coding_attrs_list, safe_codings; | |
8549 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 8550 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8551 | int c; |
0e727afa | 8552 | Lisp_Object tail, elt, work_table; |
d46c5b12 | 8553 | |
df7492f9 KH |
8554 | if (STRINGP (start)) |
8555 | { | |
8556 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8557 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8558 | return Qt; |
8559 | start_byte = 0; | |
8f924df7 | 8560 | end_byte = SBYTES (start); |
df7492f9 KH |
8561 | } |
8562 | else | |
d46c5b12 | 8563 | { |
df7492f9 KH |
8564 | CHECK_NUMBER_COERCE_MARKER (start); |
8565 | CHECK_NUMBER_COERCE_MARKER (end); | |
8566 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8567 | args_out_of_range (start, end); | |
8568 | if (NILP (current_buffer->enable_multibyte_characters)) | |
8569 | return Qt; | |
8570 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8571 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8572 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8573 | return Qt; | |
d46c5b12 | 8574 | |
e1c23804 | 8575 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8576 | { |
e1c23804 DL |
8577 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8578 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8579 | else |
e1c23804 | 8580 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8581 | } |
8582 | } | |
8583 | ||
df7492f9 KH |
8584 | coding_attrs_list = Qnil; |
8585 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8586 | if (NILP (exclude) | |
8587 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8588 | { | |
8589 | Lisp_Object attrs; | |
d46c5b12 | 8590 | |
df7492f9 KH |
8591 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
8592 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
8593 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
8594 | { |
8595 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8596 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8597 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8598 | } | |
df7492f9 | 8599 | } |
d46c5b12 | 8600 | |
df7492f9 | 8601 | if (STRINGP (start)) |
8f924df7 | 8602 | p = pbeg = SDATA (start); |
df7492f9 KH |
8603 | else |
8604 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8605 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8606 | |
df7492f9 KH |
8607 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8608 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8609 | |
0e727afa | 8610 | work_table = Fmake_char_table (Qnil, Qnil); |
05e6f5dc | 8611 | while (p < pend) |
72d1a715 | 8612 | { |
df7492f9 KH |
8613 | if (ASCII_BYTE_P (*p)) |
8614 | p++; | |
72d1a715 RS |
8615 | else |
8616 | { | |
df7492f9 | 8617 | c = STRING_CHAR_ADVANCE (p); |
0e727afa YM |
8618 | if (!NILP (char_table_ref (work_table, c))) |
8619 | /* This character was already checked. Ignore it. */ | |
8620 | continue; | |
12410ef1 | 8621 | |
df7492f9 KH |
8622 | charset_map_loaded = 0; |
8623 | for (tail = coding_attrs_list; CONSP (tail);) | |
8624 | { | |
8625 | elt = XCAR (tail); | |
8626 | if (NILP (elt)) | |
8627 | tail = XCDR (tail); | |
8628 | else if (char_encodable_p (c, elt)) | |
8629 | tail = XCDR (tail); | |
8630 | else if (CONSP (XCDR (tail))) | |
8631 | { | |
8632 | XSETCAR (tail, XCAR (XCDR (tail))); | |
8633 | XSETCDR (tail, XCDR (XCDR (tail))); | |
8634 | } | |
8635 | else | |
8636 | { | |
8637 | XSETCAR (tail, Qnil); | |
8638 | tail = XCDR (tail); | |
8639 | } | |
8640 | } | |
8641 | if (charset_map_loaded) | |
8642 | { | |
8643 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 8644 | |
df7492f9 | 8645 | if (STRINGP (start)) |
8f924df7 | 8646 | pbeg = SDATA (start); |
df7492f9 KH |
8647 | else |
8648 | pbeg = BYTE_POS_ADDR (start_byte); | |
8649 | p = pbeg + p_offset; | |
8650 | pend = pbeg + pend_offset; | |
8651 | } | |
0e727afa | 8652 | char_table_set (work_table, c, Qt); |
df7492f9 | 8653 | } |
ec6d2bb8 | 8654 | } |
fb88bf2d | 8655 | |
988b3759 | 8656 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
8657 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
8658 | if (! NILP (XCAR (tail))) | |
8659 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 8660 | |
05e6f5dc KH |
8661 | return safe_codings; |
8662 | } | |
4956c225 | 8663 | |
d46c5b12 | 8664 | |
8f924df7 KH |
8665 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
8666 | Sunencodable_char_position, 3, 5, 0, | |
8667 | doc: /* | |
8668 | Return position of first un-encodable character in a region. | |
d4a1d553 | 8669 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 8670 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 8671 | |
8f924df7 KH |
8672 | If optional 4th argument COUNT is non-nil, it specifies at most how |
8673 | many un-encodable characters to search. In this case, the value is a | |
8674 | list of positions. | |
d46c5b12 | 8675 | |
8f924df7 KH |
8676 | If optional 5th argument STRING is non-nil, it is a string to search |
8677 | for un-encodable characters. In that case, START and END are indexes | |
8678 | to the string. */) | |
5842a27b | 8679 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object count, Lisp_Object string) |
8f924df7 KH |
8680 | { |
8681 | int n; | |
8682 | struct coding_system coding; | |
7d64c6ad | 8683 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
8684 | Lisp_Object positions; |
8685 | int from, to; | |
8686 | const unsigned char *p, *stop, *pend; | |
8687 | int ascii_compatible; | |
fb88bf2d | 8688 | |
8f924df7 KH |
8689 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
8690 | attrs = CODING_ID_ATTRS (coding.id); | |
8691 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
8692 | return Qnil; | |
8693 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
8694 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 8695 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 8696 | |
8f924df7 KH |
8697 | if (NILP (string)) |
8698 | { | |
8699 | validate_region (&start, &end); | |
8700 | from = XINT (start); | |
8701 | to = XINT (end); | |
8702 | if (NILP (current_buffer->enable_multibyte_characters) | |
8703 | || (ascii_compatible | |
8704 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
8705 | return Qnil; | |
8706 | p = CHAR_POS_ADDR (from); | |
8707 | pend = CHAR_POS_ADDR (to); | |
8708 | if (from < GPT && to >= GPT) | |
8709 | stop = GPT_ADDR; | |
8710 | else | |
8711 | stop = pend; | |
8712 | } | |
8713 | else | |
8714 | { | |
8715 | CHECK_STRING (string); | |
8716 | CHECK_NATNUM (start); | |
8717 | CHECK_NATNUM (end); | |
8718 | from = XINT (start); | |
8719 | to = XINT (end); | |
8720 | if (from > to | |
8721 | || to > SCHARS (string)) | |
8722 | args_out_of_range_3 (string, start, end); | |
8723 | if (! STRING_MULTIBYTE (string)) | |
8724 | return Qnil; | |
8725 | p = SDATA (string) + string_char_to_byte (string, from); | |
8726 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
8727 | if (ascii_compatible && (to - from) == (pend - p)) | |
8728 | return Qnil; | |
8729 | } | |
f2558efd | 8730 | |
8f924df7 KH |
8731 | if (NILP (count)) |
8732 | n = 1; | |
8733 | else | |
b73bfc1c | 8734 | { |
8f924df7 KH |
8735 | CHECK_NATNUM (count); |
8736 | n = XINT (count); | |
b73bfc1c KH |
8737 | } |
8738 | ||
8f924df7 KH |
8739 | positions = Qnil; |
8740 | while (1) | |
d46c5b12 | 8741 | { |
8f924df7 | 8742 | int c; |
ec6d2bb8 | 8743 | |
8f924df7 KH |
8744 | if (ascii_compatible) |
8745 | while (p < stop && ASCII_BYTE_P (*p)) | |
8746 | p++, from++; | |
8747 | if (p >= stop) | |
0e79d667 | 8748 | { |
8f924df7 KH |
8749 | if (p >= pend) |
8750 | break; | |
8751 | stop = pend; | |
8752 | p = GAP_END_ADDR; | |
0e79d667 | 8753 | } |
ec6d2bb8 | 8754 | |
8f924df7 KH |
8755 | c = STRING_CHAR_ADVANCE (p); |
8756 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
8757 | && ! char_charset (translate_char (translation_table, c), |
8758 | charset_list, NULL)) | |
ec6d2bb8 | 8759 | { |
8f924df7 KH |
8760 | positions = Fcons (make_number (from), positions); |
8761 | n--; | |
8762 | if (n == 0) | |
8763 | break; | |
ec6d2bb8 KH |
8764 | } |
8765 | ||
8f924df7 KH |
8766 | from++; |
8767 | } | |
d46c5b12 | 8768 | |
8f924df7 KH |
8769 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
8770 | } | |
d46c5b12 | 8771 | |
d46c5b12 | 8772 | |
df7492f9 KH |
8773 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
8774 | Scheck_coding_systems_region, 3, 3, 0, | |
8775 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 8776 | |
df7492f9 KH |
8777 | START and END are buffer positions specifying the region. |
8778 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 8779 | |
df7492f9 | 8780 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 8781 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
8782 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
8783 | characters are found. | |
93dec019 | 8784 | |
df7492f9 KH |
8785 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
8786 | value is nil. | |
93dec019 | 8787 | |
df7492f9 KH |
8788 | START may be a string. In that case, check if the string is |
8789 | encodable, and the value contains indices to the string instead of | |
5704f39a KH |
8790 | buffer positions. END is ignored. |
8791 | ||
4c1958f4 | 8792 | If the current buffer (or START if it is a string) is unibyte, the value |
5704f39a | 8793 | is nil. */) |
5842a27b | 8794 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system_list) |
05e6f5dc | 8795 | { |
df7492f9 KH |
8796 | Lisp_Object list; |
8797 | EMACS_INT start_byte, end_byte; | |
8798 | int pos; | |
7c78e542 | 8799 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8800 | int c; |
7d64c6ad | 8801 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 8802 | |
05e6f5dc KH |
8803 | if (STRINGP (start)) |
8804 | { | |
df7492f9 | 8805 | if (!STRING_MULTIBYTE (start) |
4c1958f4 | 8806 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8807 | return Qnil; |
8808 | start_byte = 0; | |
8f924df7 | 8809 | end_byte = SBYTES (start); |
df7492f9 | 8810 | pos = 0; |
d46c5b12 | 8811 | } |
05e6f5dc | 8812 | else |
b73bfc1c | 8813 | { |
b7826503 PJ |
8814 | CHECK_NUMBER_COERCE_MARKER (start); |
8815 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
8816 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
8817 | args_out_of_range (start, end); | |
8818 | if (NILP (current_buffer->enable_multibyte_characters)) | |
df7492f9 KH |
8819 | return Qnil; |
8820 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8821 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8822 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
5704f39a | 8823 | return Qnil; |
df7492f9 | 8824 | |
e1c23804 | 8825 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 8826 | { |
e1c23804 DL |
8827 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8828 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8829 | else |
e1c23804 | 8830 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 8831 | } |
e1c23804 | 8832 | pos = XINT (start); |
b73bfc1c | 8833 | } |
7553d0e1 | 8834 | |
df7492f9 KH |
8835 | list = Qnil; |
8836 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 8837 | { |
df7492f9 | 8838 | elt = XCAR (tail); |
7d64c6ad | 8839 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
8840 | ASET (attrs, coding_attr_trans_tbl, |
8841 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 8842 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
8843 | } |
8844 | ||
df7492f9 | 8845 | if (STRINGP (start)) |
8f924df7 | 8846 | p = pbeg = SDATA (start); |
72d1a715 | 8847 | else |
df7492f9 KH |
8848 | p = pbeg = BYTE_POS_ADDR (start_byte); |
8849 | pend = p + (end_byte - start_byte); | |
4ed46869 | 8850 | |
df7492f9 KH |
8851 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
8852 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 8853 | |
df7492f9 | 8854 | while (p < pend) |
d46c5b12 | 8855 | { |
df7492f9 KH |
8856 | if (ASCII_BYTE_P (*p)) |
8857 | p++; | |
e133c8fa | 8858 | else |
05e6f5dc | 8859 | { |
df7492f9 KH |
8860 | c = STRING_CHAR_ADVANCE (p); |
8861 | ||
8862 | charset_map_loaded = 0; | |
8863 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
8864 | { | |
8865 | elt = XCDR (XCAR (tail)); | |
8866 | if (! char_encodable_p (c, XCAR (elt))) | |
8867 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
8868 | } | |
8869 | if (charset_map_loaded) | |
8870 | { | |
8871 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
8872 | ||
8873 | if (STRINGP (start)) | |
8f924df7 | 8874 | pbeg = SDATA (start); |
df7492f9 KH |
8875 | else |
8876 | pbeg = BYTE_POS_ADDR (start_byte); | |
8877 | p = pbeg + p_offset; | |
8878 | pend = pbeg + pend_offset; | |
8879 | } | |
05e6f5dc | 8880 | } |
df7492f9 | 8881 | pos++; |
d46c5b12 | 8882 | } |
4ed46869 | 8883 | |
df7492f9 KH |
8884 | tail = list; |
8885 | list = Qnil; | |
8886 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 8887 | { |
df7492f9 KH |
8888 | elt = XCAR (tail); |
8889 | if (CONSP (XCDR (XCDR (elt)))) | |
8890 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
8891 | list); | |
ec6d2bb8 | 8892 | } |
2b4f9037 | 8893 | |
df7492f9 | 8894 | return list; |
d46c5b12 KH |
8895 | } |
8896 | ||
3fd9494b | 8897 | |
b73bfc1c | 8898 | Lisp_Object |
cf84bb53 JB |
8899 | code_convert_region (Lisp_Object start, Lisp_Object end, |
8900 | Lisp_Object coding_system, Lisp_Object dst_object, | |
8901 | int encodep, int norecord) | |
4ed46869 | 8902 | { |
3a73fa5d | 8903 | struct coding_system coding; |
df7492f9 KH |
8904 | EMACS_INT from, from_byte, to, to_byte; |
8905 | Lisp_Object src_object; | |
4ed46869 | 8906 | |
b7826503 PJ |
8907 | CHECK_NUMBER_COERCE_MARKER (start); |
8908 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
8909 | if (NILP (coding_system)) |
8910 | coding_system = Qno_conversion; | |
8911 | else | |
8912 | CHECK_CODING_SYSTEM (coding_system); | |
8913 | src_object = Fcurrent_buffer (); | |
8914 | if (NILP (dst_object)) | |
8915 | dst_object = src_object; | |
8916 | else if (! EQ (dst_object, Qt)) | |
8917 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 8918 | |
d46c5b12 KH |
8919 | validate_region (&start, &end); |
8920 | from = XFASTINT (start); | |
df7492f9 | 8921 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 8922 | to = XFASTINT (end); |
df7492f9 | 8923 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 8924 | |
df7492f9 KH |
8925 | setup_coding_system (coding_system, &coding); |
8926 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 8927 | |
df7492f9 KH |
8928 | if (encodep) |
8929 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8930 | dst_object); | |
8931 | else | |
8932 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8933 | dst_object); | |
8934 | if (! norecord) | |
8935 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 8936 | |
df7492f9 KH |
8937 | return (BUFFERP (dst_object) |
8938 | ? make_number (coding.produced_char) | |
8939 | : coding.dst_object); | |
4031e2bf | 8940 | } |
78108bcd | 8941 | |
4ed46869 | 8942 | |
4031e2bf | 8943 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 8944 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 8945 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
8946 | When called from a program, takes four arguments: |
8947 | START, END, CODING-SYSTEM, and DESTINATION. | |
8948 | START and END are buffer positions. | |
8844fa83 | 8949 | |
df7492f9 | 8950 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 8951 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
8952 | If buffer, the decoded text is inserted in that buffer after point (point |
8953 | does not move). | |
446dcd75 | 8954 | In those cases, the length of the decoded text is returned. |
319a3947 | 8955 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 8956 | |
48b0f3ae PJ |
8957 | This function sets `last-coding-system-used' to the precise coding system |
8958 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8959 | not fully specified.) */) |
5842a27b | 8960 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
4031e2bf | 8961 | { |
df7492f9 | 8962 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 8963 | } |
8844fa83 | 8964 | |
3a73fa5d | 8965 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
8966 | 3, 4, "r\nzCoding system: ", |
8967 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
8968 | When called from a program, takes four arguments: |
8969 | START, END, CODING-SYSTEM and DESTINATION. | |
8970 | START and END are buffer positions. | |
d46c5b12 | 8971 | |
df7492f9 KH |
8972 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
8973 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
8974 | If buffer, the encoded text is inserted in that buffer after point (point |
8975 | does not move). | |
446dcd75 | 8976 | In those cases, the length of the encoded text is returned. |
319a3947 | 8977 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 8978 | |
48b0f3ae PJ |
8979 | This function sets `last-coding-system-used' to the precise coding system |
8980 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8981 | not fully specified.) */) |
5842a27b | 8982 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
3a73fa5d | 8983 | { |
df7492f9 | 8984 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
8985 | } |
8986 | ||
8987 | Lisp_Object | |
6f704c76 DN |
8988 | code_convert_string (Lisp_Object string, Lisp_Object coding_system, |
8989 | Lisp_Object dst_object, int encodep, int nocopy, int norecord) | |
b73bfc1c | 8990 | { |
4031e2bf | 8991 | struct coding_system coding; |
df7492f9 | 8992 | EMACS_INT chars, bytes; |
ec6d2bb8 | 8993 | |
b7826503 | 8994 | CHECK_STRING (string); |
d46c5b12 | 8995 | if (NILP (coding_system)) |
4956c225 | 8996 | { |
df7492f9 KH |
8997 | if (! norecord) |
8998 | Vlast_coding_system_used = Qno_conversion; | |
8999 | if (NILP (dst_object)) | |
9000 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 9001 | } |
b73bfc1c | 9002 | |
df7492f9 KH |
9003 | if (NILP (coding_system)) |
9004 | coding_system = Qno_conversion; | |
9005 | else | |
9006 | CHECK_CODING_SYSTEM (coding_system); | |
9007 | if (NILP (dst_object)) | |
9008 | dst_object = Qt; | |
9009 | else if (! EQ (dst_object, Qt)) | |
9010 | CHECK_BUFFER (dst_object); | |
73be902c | 9011 | |
df7492f9 | 9012 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 9013 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
9014 | chars = SCHARS (string); |
9015 | bytes = SBYTES (string); | |
df7492f9 KH |
9016 | if (encodep) |
9017 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9018 | else | |
9019 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9020 | if (! norecord) | |
9021 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 9022 | |
df7492f9 KH |
9023 | return (BUFFERP (dst_object) |
9024 | ? make_number (coding.produced_char) | |
9025 | : coding.dst_object); | |
4ed46869 | 9026 | } |
73be902c | 9027 | |
b73bfc1c | 9028 | |
ecec61c1 | 9029 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 9030 | Do not set Vlast_coding_system_used. |
4ed46869 | 9031 | |
ec6d2bb8 KH |
9032 | This function is called only from macros DECODE_FILE and |
9033 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 9034 | |
ecec61c1 | 9035 | Lisp_Object |
cf84bb53 JB |
9036 | code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system, |
9037 | int encodep) | |
4ed46869 | 9038 | { |
0be8721c | 9039 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
9040 | } |
9041 | ||
4ed46869 | 9042 | |
df7492f9 KH |
9043 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
9044 | 2, 4, 0, | |
9045 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
9046 | ||
9047 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
9048 | if the decoding operation is trivial. | |
ecec61c1 | 9049 | |
d4a1d553 | 9050 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
9051 | inserted in that buffer after point (point does not move). In this |
9052 | case, the return value is the length of the decoded text. | |
ecec61c1 | 9053 | |
df7492f9 KH |
9054 | This function sets `last-coding-system-used' to the precise coding system |
9055 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 9056 | not fully specified.) */) |
5842a27b | 9057 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9058 | { |
df7492f9 KH |
9059 | return code_convert_string (string, coding_system, buffer, |
9060 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
9061 | } |
9062 | ||
df7492f9 KH |
9063 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
9064 | 2, 4, 0, | |
9065 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
9066 | ||
9067 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
9068 | itself if the encoding operation is trivial. | |
9069 | ||
d4a1d553 | 9070 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
9071 | inserted in that buffer after point (point does not move). In this |
9072 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
9073 | |
9074 | This function sets `last-coding-system-used' to the precise coding system | |
9075 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
9076 | not fully specified.) */) | |
5842a27b | 9077 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9078 | { |
df7492f9 | 9079 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 9080 | 1, ! NILP (nocopy), 1); |
4ed46869 | 9081 | } |
df7492f9 | 9082 | |
3a73fa5d | 9083 | \f |
4ed46869 | 9084 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
9085 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
9086 | Return the corresponding character. */) | |
5842a27b | 9087 | (Lisp_Object code) |
4ed46869 | 9088 | { |
df7492f9 KH |
9089 | Lisp_Object spec, attrs, val; |
9090 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
9091 | int c; | |
4ed46869 | 9092 | |
df7492f9 KH |
9093 | CHECK_NATNUM (code); |
9094 | c = XFASTINT (code); | |
9095 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9096 | attrs = AREF (spec, 0); | |
4ed46869 | 9097 | |
df7492f9 KH |
9098 | if (ASCII_BYTE_P (c) |
9099 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9100 | return code; | |
4ed46869 | 9101 | |
df7492f9 KH |
9102 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9103 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
9104 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
9105 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 9106 | |
df7492f9 KH |
9107 | if (c <= 0x7F) |
9108 | charset = charset_roman; | |
9109 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 9110 | { |
df7492f9 KH |
9111 | charset = charset_kana; |
9112 | c -= 0x80; | |
4ed46869 | 9113 | } |
55ab7be3 | 9114 | else |
4ed46869 | 9115 | { |
004068e4 | 9116 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
9117 | |
9118 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
9119 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
9120 | error ("Invalid code: %d", code); | |
9121 | SJIS_TO_JIS (c); | |
9122 | charset = charset_kanji; | |
4ed46869 | 9123 | } |
df7492f9 KH |
9124 | c = DECODE_CHAR (charset, c); |
9125 | if (c < 0) | |
9126 | error ("Invalid code: %d", code); | |
9127 | return make_number (c); | |
93dec019 | 9128 | } |
4ed46869 | 9129 | |
48b0f3ae | 9130 | |
4ed46869 | 9131 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 9132 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae | 9133 | Return the corresponding code in SJIS. */) |
5842a27b | 9134 | (Lisp_Object ch) |
4ed46869 | 9135 | { |
df7492f9 KH |
9136 | Lisp_Object spec, attrs, charset_list; |
9137 | int c; | |
9138 | struct charset *charset; | |
9139 | unsigned code; | |
48b0f3ae | 9140 | |
df7492f9 KH |
9141 | CHECK_CHARACTER (ch); |
9142 | c = XFASTINT (ch); | |
9143 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9144 | attrs = AREF (spec, 0); | |
9145 | ||
9146 | if (ASCII_CHAR_P (c) | |
9147 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9148 | return ch; | |
9149 | ||
9150 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9151 | charset = char_charset (c, charset_list, &code); | |
9152 | if (code == CHARSET_INVALID_CODE (charset)) | |
9153 | error ("Can't encode by shift_jis encoding: %d", c); | |
9154 | JIS_TO_SJIS (code); | |
9155 | ||
9156 | return make_number (code); | |
4ed46869 KH |
9157 | } |
9158 | ||
9159 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
9160 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
9161 | Return the corresponding character. */) | |
5842a27b | 9162 | (Lisp_Object code) |
d46c5b12 | 9163 | { |
df7492f9 KH |
9164 | Lisp_Object spec, attrs, val; |
9165 | struct charset *charset_roman, *charset_big5, *charset; | |
9166 | int c; | |
6289dd10 | 9167 | |
df7492f9 KH |
9168 | CHECK_NATNUM (code); |
9169 | c = XFASTINT (code); | |
9170 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9171 | attrs = AREF (spec, 0); | |
4ed46869 | 9172 | |
df7492f9 KH |
9173 | if (ASCII_BYTE_P (c) |
9174 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9175 | return code; | |
6289dd10 | 9176 | |
df7492f9 KH |
9177 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9178 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
9179 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 9180 | |
df7492f9 KH |
9181 | if (c <= 0x7F) |
9182 | charset = charset_roman; | |
c28a9453 KH |
9183 | else |
9184 | { | |
df7492f9 KH |
9185 | int b1 = c >> 8, b2 = c & 0x7F; |
9186 | if (b1 < 0xA1 || b1 > 0xFE | |
9187 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
9188 | error ("Invalid code: %d", code); | |
9189 | charset = charset_big5; | |
c28a9453 | 9190 | } |
df7492f9 KH |
9191 | c = DECODE_CHAR (charset, (unsigned )c); |
9192 | if (c < 0) | |
9193 | error ("Invalid code: %d", code); | |
9194 | return make_number (c); | |
d46c5b12 | 9195 | } |
6289dd10 | 9196 | |
4ed46869 | 9197 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 9198 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae | 9199 | Return the corresponding character code in Big5. */) |
5842a27b | 9200 | (Lisp_Object ch) |
4ed46869 | 9201 | { |
df7492f9 KH |
9202 | Lisp_Object spec, attrs, charset_list; |
9203 | struct charset *charset; | |
9204 | int c; | |
9205 | unsigned code; | |
9206 | ||
9207 | CHECK_CHARACTER (ch); | |
9208 | c = XFASTINT (ch); | |
9209 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9210 | attrs = AREF (spec, 0); | |
9211 | if (ASCII_CHAR_P (c) | |
9212 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9213 | return ch; | |
9214 | ||
9215 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9216 | charset = char_charset (c, charset_list, &code); | |
9217 | if (code == CHARSET_INVALID_CODE (charset)) | |
9218 | error ("Can't encode by Big5 encoding: %d", c); | |
9219 | ||
9220 | return make_number (code); | |
4ed46869 | 9221 | } |
48b0f3ae | 9222 | |
3a73fa5d | 9223 | \f |
002fdb44 | 9224 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 9225 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9226 | doc: /* Internal use only. */) |
5842a27b | 9227 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9228 | { |
b18fad6d KH |
9229 | struct terminal *term = get_terminal (terminal, 1); |
9230 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term); | |
b7826503 | 9231 | CHECK_SYMBOL (coding_system); |
b8299c66 | 9232 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 9233 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 9234 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
ad1746f5 | 9235 | /* Character composition should be disabled. */ |
c73bd236 | 9236 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
9237 | terminal_coding->src_multibyte = 1; |
9238 | terminal_coding->dst_multibyte = 0; | |
b18fad6d KH |
9239 | if (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK) |
9240 | term->charset_list = coding_charset_list (terminal_coding); | |
9241 | else | |
6b4bb703 | 9242 | term->charset_list = Fcons (make_number (charset_ascii), Qnil); |
4ed46869 KH |
9243 | return Qnil; |
9244 | } | |
9245 | ||
c4825358 KH |
9246 | DEFUN ("set-safe-terminal-coding-system-internal", |
9247 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 9248 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 9249 | doc: /* Internal use only. */) |
5842a27b | 9250 | (Lisp_Object coding_system) |
d46c5b12 | 9251 | { |
b7826503 | 9252 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
9253 | setup_coding_system (Fcheck_coding_system (coding_system), |
9254 | &safe_terminal_coding); | |
ad1746f5 | 9255 | /* Character composition should be disabled. */ |
df7492f9 | 9256 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b73bfc1c KH |
9257 | safe_terminal_coding.src_multibyte = 1; |
9258 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
9259 | return Qnil; |
9260 | } | |
4ed46869 | 9261 | |
002fdb44 | 9262 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 9263 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff | 9264 | doc: /* Return coding system specified for terminal output on the given terminal. |
708e05dc | 9265 | TERMINAL may be a terminal object, a frame, or nil for the selected |
6ed8eeff | 9266 | frame's terminal device. */) |
5842a27b | 9267 | (Lisp_Object terminal) |
4ed46869 | 9268 | { |
985773c9 MB |
9269 | struct coding_system *terminal_coding |
9270 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
9271 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 9272 | |
ae6f73fa | 9273 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 9274 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
9275 | } |
9276 | ||
002fdb44 | 9277 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 9278 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9279 | doc: /* Internal use only. */) |
5842a27b | 9280 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9281 | { |
6ed8eeff | 9282 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 9283 | CHECK_SYMBOL (coding_system); |
624bda09 KH |
9284 | if (NILP (coding_system)) |
9285 | coding_system = Qno_conversion; | |
9286 | else | |
9287 | Fcheck_coding_system (coding_system); | |
9288 | setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t)); | |
ad1746f5 | 9289 | /* Character composition should be disabled. */ |
c73bd236 MB |
9290 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
9291 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
9292 | return Qnil; |
9293 | } | |
9294 | ||
9295 | DEFUN ("keyboard-coding-system", | |
985773c9 | 9296 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 9297 | doc: /* Return coding system specified for decoding keyboard input. */) |
5842a27b | 9298 | (Lisp_Object terminal) |
4ed46869 | 9299 | { |
985773c9 MB |
9300 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
9301 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
9302 | } |
9303 | ||
4ed46869 | 9304 | \f |
a5d301df KH |
9305 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
9306 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
9307 | doc: /* Choose a coding system for an operation based on the target name. |
9308 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
9309 | DECODING-SYSTEM is the coding system to use for decoding | |
9310 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
9311 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 9312 | |
48b0f3ae PJ |
9313 | The first argument OPERATION specifies an I/O primitive: |
9314 | For file I/O, `insert-file-contents' or `write-region'. | |
9315 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
9316 | For network I/O, `open-network-stream'. | |
05e6f5dc | 9317 | |
48b0f3ae PJ |
9318 | The remaining arguments should be the same arguments that were passed |
9319 | to the primitive. Depending on which primitive, one of those arguments | |
9320 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
9321 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 9322 | |
48b0f3ae | 9323 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 9324 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 9325 | For process I/O, TARGET is a process name. |
d4a1d553 | 9326 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 9327 | |
d4a1d553 | 9328 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
9329 | `file-coding-system-alist', `process-coding-system-alist', |
9330 | or `network-coding-system-alist' depending on OPERATION. | |
9331 | They may specify a coding system, a cons of coding systems, | |
9332 | or a function symbol to call. | |
9333 | In the last case, we call the function with one argument, | |
9334 | which is a list of all the arguments given to this function. | |
1011c487 MB |
9335 | If the function can't decide a coding system, it can return |
9336 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 9337 | |
b883cdb2 MB |
9338 | If OPERATION is `insert-file-contents', the argument corresponding to |
9339 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
9340 | file name to look up, and BUFFER is a buffer that contains the file's | |
9341 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
9342 | function to call for FILENAME, that function should examine the | |
9343 | contents of BUFFER instead of reading the file. | |
9344 | ||
d918f936 | 9345 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
5842a27b | 9346 | (int nargs, Lisp_Object *args) |
6b89e3aa | 9347 | { |
4ed46869 KH |
9348 | Lisp_Object operation, target_idx, target, val; |
9349 | register Lisp_Object chain; | |
177c0ea7 | 9350 | |
4ed46869 KH |
9351 | if (nargs < 2) |
9352 | error ("Too few arguments"); | |
9353 | operation = args[0]; | |
9354 | if (!SYMBOLP (operation) | |
9355 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
3ed051d4 | 9356 | error ("Invalid first argument"); |
4ed46869 KH |
9357 | if (nargs < 1 + XINT (target_idx)) |
9358 | error ("Too few arguments for operation: %s", | |
8f924df7 | 9359 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
9360 | target = args[XINT (target_idx) + 1]; |
9361 | if (!(STRINGP (target) | |
091a0ff0 KH |
9362 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
9363 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 9364 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
df7492f9 | 9365 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
091a0ff0 KH |
9366 | if (CONSP (target)) |
9367 | target = XCAR (target); | |
4ed46869 | 9368 | |
2e34157c RS |
9369 | chain = ((EQ (operation, Qinsert_file_contents) |
9370 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9371 | ? Vfile_coding_system_alist |
2e34157c | 9372 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9373 | ? Vnetwork_coding_system_alist |
9374 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9375 | if (NILP (chain)) |
9376 | return Qnil; | |
9377 | ||
03699b14 | 9378 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9379 | { |
f44d27ce | 9380 | Lisp_Object elt; |
6b89e3aa | 9381 | |
df7492f9 | 9382 | elt = XCAR (chain); |
4ed46869 KH |
9383 | if (CONSP (elt) |
9384 | && ((STRINGP (target) | |
03699b14 KR |
9385 | && STRINGP (XCAR (elt)) |
9386 | && fast_string_match (XCAR (elt), target) >= 0) | |
9387 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9388 | { |
03699b14 | 9389 | val = XCDR (elt); |
b19fd4c5 KH |
9390 | /* Here, if VAL is both a valid coding system and a valid |
9391 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9392 | if (CONSP (val)) |
9393 | return val; | |
9394 | if (! SYMBOLP (val)) | |
9395 | return Qnil; | |
9396 | if (! NILP (Fcoding_system_p (val))) | |
9397 | return Fcons (val, val); | |
b19fd4c5 | 9398 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9399 | { |
e2b97060 MB |
9400 | /* We use call1 rather than safe_call1 |
9401 | so as to get bug reports about functions called here | |
9402 | which don't handle the current interface. */ | |
9403 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9404 | if (CONSP (val)) |
9405 | return val; | |
9406 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9407 | return Fcons (val, val); | |
6b89e3aa | 9408 | } |
02ba4723 | 9409 | return Qnil; |
6b89e3aa KH |
9410 | } |
9411 | } | |
4ed46869 | 9412 | return Qnil; |
6b89e3aa KH |
9413 | } |
9414 | ||
df7492f9 | 9415 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9416 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9417 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9418 | If multiple coding systems belong to the same category, |
a3181084 DL |
9419 | all but the first one are ignored. |
9420 | ||
d4a1d553 | 9421 | usage: (set-coding-system-priority &rest coding-systems) */) |
5842a27b | 9422 | (int nargs, Lisp_Object *args) |
df7492f9 KH |
9423 | { |
9424 | int i, j; | |
9425 | int changed[coding_category_max]; | |
9426 | enum coding_category priorities[coding_category_max]; | |
9427 | ||
72af86bd | 9428 | memset (changed, 0, sizeof changed); |
6b89e3aa | 9429 | |
df7492f9 | 9430 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9431 | { |
df7492f9 KH |
9432 | enum coding_category category; |
9433 | Lisp_Object spec, attrs; | |
6b89e3aa | 9434 | |
df7492f9 KH |
9435 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9436 | attrs = AREF (spec, 0); | |
9437 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9438 | if (changed[category]) | |
9439 | /* Ignore this coding system because a coding system of the | |
9440 | same category already had a higher priority. */ | |
9441 | continue; | |
9442 | changed[category] = 1; | |
9443 | priorities[j++] = category; | |
9444 | if (coding_categories[category].id >= 0 | |
9445 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9446 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9447 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9448 | } |
6b89e3aa | 9449 | |
df7492f9 KH |
9450 | /* Now we have decided top J priorities. Reflect the order of the |
9451 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9452 | |
df7492f9 | 9453 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9454 | { |
df7492f9 KH |
9455 | while (j < coding_category_max |
9456 | && changed[coding_priorities[j]]) | |
9457 | j++; | |
9458 | if (j == coding_category_max) | |
9459 | abort (); | |
9460 | priorities[i] = coding_priorities[j]; | |
9461 | } | |
6b89e3aa | 9462 | |
72af86bd | 9463 | memcpy (coding_priorities, priorities, sizeof priorities); |
177c0ea7 | 9464 | |
ff563fce KH |
9465 | /* Update `coding-category-list'. */ |
9466 | Vcoding_category_list = Qnil; | |
9467 | for (i = coding_category_max - 1; i >= 0; i--) | |
9468 | Vcoding_category_list | |
9469 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9470 | Vcoding_category_list); | |
6b89e3aa | 9471 | |
df7492f9 | 9472 | return Qnil; |
6b89e3aa KH |
9473 | } |
9474 | ||
df7492f9 KH |
9475 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9476 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 | 9477 | doc: /* Return a list of coding systems ordered by their priorities. |
b811c52b KH |
9478 | The list contains a subset of coding systems; i.e. coding systems |
9479 | assigned to each coding category (see `coding-category-list'). | |
9480 | ||
da7db224 | 9481 | HIGHESTP non-nil means just return the highest priority one. */) |
5842a27b | 9482 | (Lisp_Object highestp) |
d46c5b12 KH |
9483 | { |
9484 | int i; | |
df7492f9 | 9485 | Lisp_Object val; |
6b89e3aa | 9486 | |
df7492f9 | 9487 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9488 | { |
df7492f9 KH |
9489 | enum coding_category category = coding_priorities[i]; |
9490 | int id = coding_categories[category].id; | |
9491 | Lisp_Object attrs; | |
068a9dbd | 9492 | |
df7492f9 KH |
9493 | if (id < 0) |
9494 | continue; | |
9495 | attrs = CODING_ID_ATTRS (id); | |
9496 | if (! NILP (highestp)) | |
9497 | return CODING_ATTR_BASE_NAME (attrs); | |
9498 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9499 | } | |
9500 | return Fnreverse (val); | |
9501 | } | |
068a9dbd | 9502 | |
91433552 | 9503 | static const char *const suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9504 | |
9505 | static Lisp_Object | |
971de7fb | 9506 | make_subsidiaries (Lisp_Object base) |
068a9dbd | 9507 | { |
df7492f9 | 9508 | Lisp_Object subsidiaries; |
8f924df7 | 9509 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
9510 | char *buf = (char *) alloca (base_name_len + 6); |
9511 | int i; | |
068a9dbd | 9512 | |
72af86bd | 9513 | memcpy (buf, SDATA (SYMBOL_NAME (base)), base_name_len); |
df7492f9 KH |
9514 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
9515 | for (i = 0; i < 3; i++) | |
068a9dbd | 9516 | { |
72af86bd | 9517 | memcpy (buf + base_name_len, suffixes[i], strlen (suffixes[i]) + 1); |
df7492f9 | 9518 | ASET (subsidiaries, i, intern (buf)); |
068a9dbd | 9519 | } |
df7492f9 | 9520 | return subsidiaries; |
068a9dbd KH |
9521 | } |
9522 | ||
9523 | ||
df7492f9 KH |
9524 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9525 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9526 | doc: /* For internal use only. |
9527 | usage: (define-coding-system-internal ...) */) | |
5842a27b | 9528 | (int nargs, Lisp_Object *args) |
068a9dbd | 9529 | { |
df7492f9 KH |
9530 | Lisp_Object name; |
9531 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9532 | Lisp_Object attrs; /* Vector of attributes. */ | |
9533 | Lisp_Object eol_type; | |
9534 | Lisp_Object aliases; | |
9535 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9536 | enum coding_category category; | |
9537 | Lisp_Object tail, val; | |
9538 | int max_charset_id = 0; | |
9539 | int i; | |
068a9dbd | 9540 | |
df7492f9 KH |
9541 | if (nargs < coding_arg_max) |
9542 | goto short_args; | |
068a9dbd | 9543 | |
df7492f9 | 9544 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9545 | |
df7492f9 KH |
9546 | name = args[coding_arg_name]; |
9547 | CHECK_SYMBOL (name); | |
9548 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 9549 | |
df7492f9 KH |
9550 | val = args[coding_arg_mnemonic]; |
9551 | if (! STRINGP (val)) | |
9552 | CHECK_CHARACTER (val); | |
9553 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 9554 | |
df7492f9 KH |
9555 | coding_type = args[coding_arg_coding_type]; |
9556 | CHECK_SYMBOL (coding_type); | |
9557 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 9558 | |
df7492f9 KH |
9559 | charset_list = args[coding_arg_charset_list]; |
9560 | if (SYMBOLP (charset_list)) | |
9561 | { | |
9562 | if (EQ (charset_list, Qiso_2022)) | |
9563 | { | |
9564 | if (! EQ (coding_type, Qiso_2022)) | |
9565 | error ("Invalid charset-list"); | |
9566 | charset_list = Viso_2022_charset_list; | |
9567 | } | |
9568 | else if (EQ (charset_list, Qemacs_mule)) | |
9569 | { | |
9570 | if (! EQ (coding_type, Qemacs_mule)) | |
9571 | error ("Invalid charset-list"); | |
9572 | charset_list = Vemacs_mule_charset_list; | |
9573 | } | |
9574 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
9575 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9576 | max_charset_id = XFASTINT (XCAR (tail)); | |
9577 | } | |
068a9dbd KH |
9578 | else |
9579 | { | |
df7492f9 | 9580 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9581 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9582 | { |
df7492f9 KH |
9583 | struct charset *charset; |
9584 | ||
985773c9 | 9585 | val = XCAR (tail); |
df7492f9 KH |
9586 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9587 | if (EQ (coding_type, Qiso_2022) | |
9588 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9589 | : EQ (coding_type, Qemacs_mule) | |
9590 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9591 | : 0) | |
9592 | error ("Can't handle charset `%s'", | |
8f924df7 | 9593 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9594 | |
8f924df7 | 9595 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9596 | if (max_charset_id < charset->id) |
9597 | max_charset_id = charset->id; | |
068a9dbd KH |
9598 | } |
9599 | } | |
df7492f9 | 9600 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 9601 | |
1b3b981b AS |
9602 | safe_charsets = make_uninit_string (max_charset_id + 1); |
9603 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 | 9604 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8f924df7 | 9605 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 9606 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 9607 | |
584948ac | 9608 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 9609 | |
df7492f9 | 9610 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 9611 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9612 | CHECK_SYMBOL (val); |
df7492f9 | 9613 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 9614 | |
df7492f9 | 9615 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 9616 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9617 | CHECK_SYMBOL (val); |
df7492f9 | 9618 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 9619 | |
df7492f9 KH |
9620 | val = args[coding_arg_post_read_conversion]; |
9621 | CHECK_SYMBOL (val); | |
9622 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 9623 | |
df7492f9 KH |
9624 | val = args[coding_arg_pre_write_conversion]; |
9625 | CHECK_SYMBOL (val); | |
9626 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 9627 | |
df7492f9 KH |
9628 | val = args[coding_arg_default_char]; |
9629 | if (NILP (val)) | |
9630 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
9631 | else | |
9632 | { | |
8f924df7 | 9633 | CHECK_CHARACTER (val); |
df7492f9 KH |
9634 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
9635 | } | |
4031e2bf | 9636 | |
8f924df7 KH |
9637 | val = args[coding_arg_for_unibyte]; |
9638 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 9639 | |
df7492f9 KH |
9640 | val = args[coding_arg_plist]; |
9641 | CHECK_LIST (val); | |
9642 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 9643 | |
df7492f9 KH |
9644 | if (EQ (coding_type, Qcharset)) |
9645 | { | |
c7c66a95 KH |
9646 | /* Generate a lisp vector of 256 elements. Each element is nil, |
9647 | integer, or a list of charset IDs. | |
3a73fa5d | 9648 | |
c7c66a95 KH |
9649 | If Nth element is nil, the byte code N is invalid in this |
9650 | coding system. | |
4ed46869 | 9651 | |
c7c66a95 KH |
9652 | If Nth element is a number NUM, N is the first byte of a |
9653 | charset whose ID is NUM. | |
4ed46869 | 9654 | |
c7c66a95 KH |
9655 | If Nth element is a list of charset IDs, N is the first byte |
9656 | of one of them. The list is sorted by dimensions of the | |
ad1746f5 | 9657 | charsets. A charset of smaller dimension comes first. */ |
df7492f9 | 9658 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 9659 | |
5c99c2e6 | 9660 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9661 | { |
c7c66a95 KH |
9662 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
9663 | int dim = CHARSET_DIMENSION (charset); | |
9664 | int idx = (dim - 1) * 4; | |
4ed46869 | 9665 | |
5c99c2e6 | 9666 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 9667 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 9668 | |
15d143f7 KH |
9669 | for (i = charset->code_space[idx]; |
9670 | i <= charset->code_space[idx + 1]; i++) | |
9671 | { | |
c7c66a95 KH |
9672 | Lisp_Object tmp, tmp2; |
9673 | int dim2; | |
ec6d2bb8 | 9674 | |
c7c66a95 KH |
9675 | tmp = AREF (val, i); |
9676 | if (NILP (tmp)) | |
9677 | tmp = XCAR (tail); | |
9678 | else if (NUMBERP (tmp)) | |
9679 | { | |
9680 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
9681 | if (dim < dim2) | |
c7c66a95 | 9682 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
9683 | else |
9684 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 9685 | } |
15d143f7 | 9686 | else |
c7c66a95 KH |
9687 | { |
9688 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
9689 | { | |
9690 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
9691 | if (dim < dim2) | |
9692 | break; | |
9693 | } | |
9694 | if (NILP (tmp2)) | |
9695 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
9696 | else | |
9697 | { | |
9698 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
9699 | XSETCAR (tmp2, XCAR (tail)); | |
9700 | } | |
9701 | } | |
9702 | ASET (val, i, tmp); | |
15d143f7 | 9703 | } |
df7492f9 KH |
9704 | } |
9705 | ASET (attrs, coding_attr_charset_valids, val); | |
9706 | category = coding_category_charset; | |
9707 | } | |
9708 | else if (EQ (coding_type, Qccl)) | |
9709 | { | |
9710 | Lisp_Object valids; | |
ecec61c1 | 9711 | |
df7492f9 KH |
9712 | if (nargs < coding_arg_ccl_max) |
9713 | goto short_args; | |
ecec61c1 | 9714 | |
df7492f9 KH |
9715 | val = args[coding_arg_ccl_decoder]; |
9716 | CHECK_CCL_PROGRAM (val); | |
9717 | if (VECTORP (val)) | |
9718 | val = Fcopy_sequence (val); | |
9719 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 9720 | |
df7492f9 KH |
9721 | val = args[coding_arg_ccl_encoder]; |
9722 | CHECK_CCL_PROGRAM (val); | |
9723 | if (VECTORP (val)) | |
9724 | val = Fcopy_sequence (val); | |
9725 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 9726 | |
df7492f9 KH |
9727 | val = args[coding_arg_ccl_valids]; |
9728 | valids = Fmake_string (make_number (256), make_number (0)); | |
9729 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
9730 | { | |
8dcbea82 | 9731 | int from, to; |
ecec61c1 | 9732 | |
df7492f9 KH |
9733 | val = Fcar (tail); |
9734 | if (INTEGERP (val)) | |
8dcbea82 KH |
9735 | { |
9736 | from = to = XINT (val); | |
9737 | if (from < 0 || from > 255) | |
9738 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
9739 | } | |
df7492f9 KH |
9740 | else |
9741 | { | |
df7492f9 | 9742 | CHECK_CONS (val); |
8f924df7 KH |
9743 | CHECK_NATNUM_CAR (val); |
9744 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 9745 | from = XINT (XCAR (val)); |
8f924df7 | 9746 | if (from > 255) |
8dcbea82 KH |
9747 | args_out_of_range_3 (XCAR (val), |
9748 | make_number (0), make_number (255)); | |
df7492f9 | 9749 | to = XINT (XCDR (val)); |
8dcbea82 KH |
9750 | if (to < from || to > 255) |
9751 | args_out_of_range_3 (XCDR (val), | |
9752 | XCAR (val), make_number (255)); | |
df7492f9 | 9753 | } |
8dcbea82 | 9754 | for (i = from; i <= to; i++) |
8f924df7 | 9755 | SSET (valids, i, 1); |
df7492f9 KH |
9756 | } |
9757 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 9758 | |
df7492f9 | 9759 | category = coding_category_ccl; |
55ab7be3 | 9760 | } |
df7492f9 | 9761 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 9762 | { |
df7492f9 | 9763 | Lisp_Object bom, endian; |
4ed46869 | 9764 | |
584948ac | 9765 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 9766 | |
df7492f9 KH |
9767 | if (nargs < coding_arg_utf16_max) |
9768 | goto short_args; | |
4ed46869 | 9769 | |
df7492f9 KH |
9770 | bom = args[coding_arg_utf16_bom]; |
9771 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9772 | { | |
9773 | CHECK_CONS (bom); | |
8f924df7 KH |
9774 | val = XCAR (bom); |
9775 | CHECK_CODING_SYSTEM (val); | |
9776 | val = XCDR (bom); | |
9777 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 9778 | } |
a470d443 | 9779 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
9780 | |
9781 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
9782 | CHECK_SYMBOL (endian); |
9783 | if (NILP (endian)) | |
9784 | endian = Qbig; | |
9785 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 9786 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
9787 | ASET (attrs, coding_attr_utf_16_endian, endian); |
9788 | ||
9789 | category = (CONSP (bom) | |
9790 | ? coding_category_utf_16_auto | |
9791 | : NILP (bom) | |
b49a1807 | 9792 | ? (EQ (endian, Qbig) |
df7492f9 KH |
9793 | ? coding_category_utf_16_be_nosig |
9794 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 9795 | : (EQ (endian, Qbig) |
df7492f9 KH |
9796 | ? coding_category_utf_16_be |
9797 | : coding_category_utf_16_le)); | |
9798 | } | |
9799 | else if (EQ (coding_type, Qiso_2022)) | |
9800 | { | |
9801 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 9802 | int i; |
1397dc18 | 9803 | |
df7492f9 KH |
9804 | if (nargs < coding_arg_iso2022_max) |
9805 | goto short_args; | |
9806 | ||
9807 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
9808 | CHECK_VECTOR (initial); | |
9809 | for (i = 0; i < 4; i++) | |
9810 | { | |
9811 | val = Faref (initial, make_number (i)); | |
9812 | if (! NILP (val)) | |
9813 | { | |
584948ac KH |
9814 | struct charset *charset; |
9815 | ||
9816 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
9817 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
9818 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
9819 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9820 | } |
9821 | else | |
9822 | ASET (initial, i, make_number (-1)); | |
9823 | } | |
9824 | ||
9825 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
9826 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
9827 | CHECK_NUMBER_CAR (reg_usage); |
9828 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
9829 | |
9830 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
9831 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 9832 | { |
df7492f9 | 9833 | int id; |
8f924df7 | 9834 | Lisp_Object tmp; |
df7492f9 KH |
9835 | |
9836 | val = Fcar (tail); | |
9837 | CHECK_CONS (val); | |
8f924df7 KH |
9838 | tmp = XCAR (val); |
9839 | CHECK_CHARSET_GET_ID (tmp, id); | |
9840 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
9841 | if (XINT (XCDR (val)) >= 4) |
9842 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 9843 | XSETCAR (val, make_number (id)); |
1397dc18 | 9844 | } |
4ed46869 | 9845 | |
df7492f9 KH |
9846 | flags = args[coding_arg_iso2022_flags]; |
9847 | CHECK_NATNUM (flags); | |
9848 | i = XINT (flags); | |
9849 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
9850 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
9851 | ||
9852 | ASET (attrs, coding_attr_iso_initial, initial); | |
9853 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
9854 | ASET (attrs, coding_attr_iso_request, request); | |
9855 | ASET (attrs, coding_attr_iso_flags, flags); | |
9856 | setup_iso_safe_charsets (attrs); | |
9857 | ||
9858 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
9859 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
9860 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
9861 | ? coding_category_iso_7_else | |
9862 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
9863 | ? coding_category_iso_7 | |
9864 | : coding_category_iso_7_tight); | |
9865 | else | |
9866 | { | |
9867 | int id = XINT (AREF (initial, 1)); | |
9868 | ||
c6fb6e98 | 9869 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
9870 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
9871 | || id < 0) | |
9872 | ? coding_category_iso_8_else | |
9873 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
9874 | ? coding_category_iso_8_1 | |
9875 | : coding_category_iso_8_2); | |
9876 | } | |
0ce7886f KH |
9877 | if (category != coding_category_iso_8_1 |
9878 | && category != coding_category_iso_8_2) | |
9879 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
9880 | } |
9881 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 9882 | { |
df7492f9 KH |
9883 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
9884 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 9885 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 9886 | category = coding_category_emacs_mule; |
c28a9453 | 9887 | } |
df7492f9 | 9888 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 9889 | { |
df7492f9 KH |
9890 | |
9891 | struct charset *charset; | |
9892 | ||
7d64c6ad | 9893 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 9894 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 9895 | error ("There should be three or four charsets"); |
df7492f9 KH |
9896 | |
9897 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9898 | if (CHARSET_DIMENSION (charset) != 1) | |
9899 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9900 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
9901 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
9902 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9903 | |
9904 | charset_list = XCDR (charset_list); | |
9905 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9906 | if (CHARSET_DIMENSION (charset) != 1) | |
9907 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9908 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
9909 | |
9910 | charset_list = XCDR (charset_list); | |
9911 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9912 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
9913 | error ("Dimension of charset %s is not two", |
9914 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9915 | ||
9916 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
9917 | if (! NILP (charset_list)) |
9918 | { | |
9919 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9920 | if (CHARSET_DIMENSION (charset) != 2) | |
9921 | error ("Dimension of charset %s is not two", | |
9922 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9923 | } | |
df7492f9 KH |
9924 | |
9925 | category = coding_category_sjis; | |
9926 | Vsjis_coding_system = name; | |
c28a9453 | 9927 | } |
df7492f9 KH |
9928 | else if (EQ (coding_type, Qbig5)) |
9929 | { | |
9930 | struct charset *charset; | |
4ed46869 | 9931 | |
df7492f9 KH |
9932 | if (XINT (Flength (charset_list)) != 2) |
9933 | error ("There should be just two charsets"); | |
9934 | ||
9935 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9936 | if (CHARSET_DIMENSION (charset) != 1) | |
9937 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9938 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
9939 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
9940 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9941 | |
9942 | charset_list = XCDR (charset_list); | |
9943 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9944 | if (CHARSET_DIMENSION (charset) != 2) | |
9945 | error ("Dimension of charset %s is not two", | |
8f924df7 | 9946 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 9947 | |
df7492f9 KH |
9948 | category = coding_category_big5; |
9949 | Vbig5_coding_system = name; | |
9950 | } | |
9951 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 9952 | { |
584948ac KH |
9953 | category = coding_category_raw_text; |
9954 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 9955 | } |
df7492f9 | 9956 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 9957 | { |
a470d443 KH |
9958 | Lisp_Object bom; |
9959 | ||
584948ac | 9960 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
a470d443 KH |
9961 | |
9962 | if (nargs < coding_arg_utf8_max) | |
9963 | goto short_args; | |
9964 | ||
9965 | bom = args[coding_arg_utf8_bom]; | |
9966 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9967 | { | |
9968 | CHECK_CONS (bom); | |
9969 | val = XCAR (bom); | |
9970 | CHECK_CODING_SYSTEM (val); | |
9971 | val = XCDR (bom); | |
9972 | CHECK_CODING_SYSTEM (val); | |
9973 | } | |
9974 | ASET (attrs, coding_attr_utf_bom, bom); | |
9975 | ||
9976 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
9977 | : NILP (bom) ? coding_category_utf_8_nosig | |
9978 | : coding_category_utf_8_sig); | |
4ed46869 | 9979 | } |
df7492f9 KH |
9980 | else if (EQ (coding_type, Qundecided)) |
9981 | category = coding_category_undecided; | |
4ed46869 | 9982 | else |
df7492f9 | 9983 | error ("Invalid coding system type: %s", |
8f924df7 | 9984 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 9985 | |
df7492f9 | 9986 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
9987 | CODING_ATTR_PLIST (attrs) |
9988 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
9989 | CODING_ATTR_PLIST (attrs))); | |
35befdaa | 9990 | CODING_ATTR_PLIST (attrs) |
3ed051d4 | 9991 | = Fcons (QCascii_compatible_p, |
35befdaa KH |
9992 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), |
9993 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 9994 | |
df7492f9 KH |
9995 | eol_type = args[coding_arg_eol_type]; |
9996 | if (! NILP (eol_type) | |
9997 | && ! EQ (eol_type, Qunix) | |
9998 | && ! EQ (eol_type, Qdos) | |
9999 | && ! EQ (eol_type, Qmac)) | |
10000 | error ("Invalid eol-type"); | |
4ed46869 | 10001 | |
df7492f9 | 10002 | aliases = Fcons (name, Qnil); |
4ed46869 | 10003 | |
df7492f9 KH |
10004 | if (NILP (eol_type)) |
10005 | { | |
10006 | eol_type = make_subsidiaries (name); | |
10007 | for (i = 0; i < 3; i++) | |
1397dc18 | 10008 | { |
df7492f9 KH |
10009 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
10010 | ||
10011 | this_name = AREF (eol_type, i); | |
10012 | this_aliases = Fcons (this_name, Qnil); | |
10013 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
10014 | this_spec = Fmake_vector (make_number (3), attrs); | |
10015 | ASET (this_spec, 1, this_aliases); | |
10016 | ASET (this_spec, 2, this_eol_type); | |
10017 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
10018 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
10019 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
10020 | if (NILP (val)) | |
10021 | Vcoding_system_alist | |
10022 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
10023 | Vcoding_system_alist); | |
1397dc18 | 10024 | } |
d46c5b12 | 10025 | } |
4ed46869 | 10026 | |
df7492f9 KH |
10027 | spec_vec = Fmake_vector (make_number (3), attrs); |
10028 | ASET (spec_vec, 1, aliases); | |
10029 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 10030 | |
df7492f9 KH |
10031 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
10032 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
10033 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
10034 | if (NILP (val)) | |
10035 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
10036 | Vcoding_system_alist); | |
48b0f3ae | 10037 | |
df7492f9 KH |
10038 | { |
10039 | int id = coding_categories[category].id; | |
48b0f3ae | 10040 | |
df7492f9 KH |
10041 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
10042 | setup_coding_system (name, &coding_categories[category]); | |
10043 | } | |
48b0f3ae | 10044 | |
d46c5b12 | 10045 | return Qnil; |
48b0f3ae | 10046 | |
df7492f9 KH |
10047 | short_args: |
10048 | return Fsignal (Qwrong_number_of_arguments, | |
10049 | Fcons (intern ("define-coding-system-internal"), | |
10050 | make_number (nargs))); | |
d46c5b12 | 10051 | } |
4ed46869 | 10052 | |
d6925f38 | 10053 | |
a6f87d34 KH |
10054 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
10055 | 3, 3, 0, | |
10056 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
5842a27b | 10057 | (Lisp_Object coding_system, Lisp_Object prop, Lisp_Object val) |
a6f87d34 | 10058 | { |
3dbe7859 | 10059 | Lisp_Object spec, attrs; |
a6f87d34 KH |
10060 | |
10061 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10062 | attrs = AREF (spec, 0); | |
10063 | if (EQ (prop, QCmnemonic)) | |
10064 | { | |
10065 | if (! STRINGP (val)) | |
10066 | CHECK_CHARACTER (val); | |
10067 | CODING_ATTR_MNEMONIC (attrs) = val; | |
10068 | } | |
2133e2d1 | 10069 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
10070 | { |
10071 | if (NILP (val)) | |
10072 | val = make_number (' '); | |
10073 | else | |
10074 | CHECK_CHARACTER (val); | |
10075 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
10076 | } | |
10077 | else if (EQ (prop, QCdecode_translation_table)) | |
10078 | { | |
10079 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10080 | CHECK_SYMBOL (val); | |
10081 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
10082 | } | |
10083 | else if (EQ (prop, QCencode_translation_table)) | |
10084 | { | |
10085 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10086 | CHECK_SYMBOL (val); | |
10087 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
10088 | } | |
10089 | else if (EQ (prop, QCpost_read_conversion)) | |
10090 | { | |
10091 | CHECK_SYMBOL (val); | |
10092 | CODING_ATTR_POST_READ (attrs) = val; | |
10093 | } | |
10094 | else if (EQ (prop, QCpre_write_conversion)) | |
10095 | { | |
10096 | CHECK_SYMBOL (val); | |
10097 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
10098 | } | |
35befdaa KH |
10099 | else if (EQ (prop, QCascii_compatible_p)) |
10100 | { | |
10101 | CODING_ATTR_ASCII_COMPAT (attrs) = val; | |
10102 | } | |
a6f87d34 KH |
10103 | |
10104 | CODING_ATTR_PLIST (attrs) | |
10105 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
10106 | return val; | |
10107 | } | |
10108 | ||
10109 | ||
df7492f9 KH |
10110 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
10111 | Sdefine_coding_system_alias, 2, 2, 0, | |
10112 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
5842a27b | 10113 | (Lisp_Object alias, Lisp_Object coding_system) |
66cfb530 | 10114 | { |
583f71ca | 10115 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 10116 | |
df7492f9 KH |
10117 | CHECK_SYMBOL (alias); |
10118 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10119 | aliases = AREF (spec, 1); | |
d4a1d553 | 10120 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
10121 | element is a base coding system. Append ALIAS at the tail of the |
10122 | list. */ | |
df7492f9 KH |
10123 | while (!NILP (XCDR (aliases))) |
10124 | aliases = XCDR (aliases); | |
8f924df7 | 10125 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 10126 | |
df7492f9 KH |
10127 | eol_type = AREF (spec, 2); |
10128 | if (VECTORP (eol_type)) | |
4ed46869 | 10129 | { |
df7492f9 KH |
10130 | Lisp_Object subsidiaries; |
10131 | int i; | |
4ed46869 | 10132 | |
df7492f9 KH |
10133 | subsidiaries = make_subsidiaries (alias); |
10134 | for (i = 0; i < 3; i++) | |
10135 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
10136 | AREF (eol_type, i)); | |
4ed46869 | 10137 | } |
df7492f9 KH |
10138 | |
10139 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 10140 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
10141 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
10142 | if (NILP (val)) | |
10143 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
10144 | Vcoding_system_alist); | |
66cfb530 | 10145 | |
4ed46869 KH |
10146 | return Qnil; |
10147 | } | |
10148 | ||
df7492f9 KH |
10149 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
10150 | 1, 1, 0, | |
10151 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 10152 | Any alias or subsidiary coding system is not a base coding system. */) |
5842a27b | 10153 | (Lisp_Object coding_system) |
d46c5b12 | 10154 | { |
df7492f9 | 10155 | Lisp_Object spec, attrs; |
d46c5b12 | 10156 | |
df7492f9 KH |
10157 | if (NILP (coding_system)) |
10158 | return (Qno_conversion); | |
10159 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10160 | attrs = AREF (spec, 0); | |
10161 | return CODING_ATTR_BASE_NAME (attrs); | |
10162 | } | |
1397dc18 | 10163 | |
df7492f9 KH |
10164 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
10165 | 1, 1, 0, | |
10166 | doc: "Return the property list of CODING-SYSTEM.") | |
5842a27b | 10167 | (Lisp_Object coding_system) |
df7492f9 KH |
10168 | { |
10169 | Lisp_Object spec, attrs; | |
1397dc18 | 10170 | |
df7492f9 KH |
10171 | if (NILP (coding_system)) |
10172 | coding_system = Qno_conversion; | |
10173 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10174 | attrs = AREF (spec, 0); | |
10175 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
10176 | } |
10177 | ||
df7492f9 KH |
10178 | |
10179 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
10180 | 1, 1, 0, | |
da7db224 | 10181 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
5842a27b | 10182 | (Lisp_Object coding_system) |
66cfb530 | 10183 | { |
df7492f9 | 10184 | Lisp_Object spec; |
84d60297 | 10185 | |
df7492f9 KH |
10186 | if (NILP (coding_system)) |
10187 | coding_system = Qno_conversion; | |
10188 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 10189 | return AREF (spec, 1); |
df7492f9 | 10190 | } |
66cfb530 | 10191 | |
df7492f9 KH |
10192 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
10193 | Scoding_system_eol_type, 1, 1, 0, | |
10194 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 10195 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 10196 | |
df7492f9 KH |
10197 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
10198 | and CR respectively. | |
66cfb530 | 10199 | |
df7492f9 KH |
10200 | A vector value indicates that a format of end-of-line should be |
10201 | detected automatically. Nth element of the vector is the subsidiary | |
10202 | coding system whose eol-type is N. */) | |
5842a27b | 10203 | (Lisp_Object coding_system) |
6b89e3aa | 10204 | { |
df7492f9 KH |
10205 | Lisp_Object spec, eol_type; |
10206 | int n; | |
6b89e3aa | 10207 | |
df7492f9 KH |
10208 | if (NILP (coding_system)) |
10209 | coding_system = Qno_conversion; | |
10210 | if (! CODING_SYSTEM_P (coding_system)) | |
10211 | return Qnil; | |
10212 | spec = CODING_SYSTEM_SPEC (coding_system); | |
10213 | eol_type = AREF (spec, 2); | |
10214 | if (VECTORP (eol_type)) | |
10215 | return Fcopy_sequence (eol_type); | |
10216 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
10217 | return make_number (n); | |
6b89e3aa KH |
10218 | } |
10219 | ||
4ed46869 KH |
10220 | #endif /* emacs */ |
10221 | ||
10222 | \f | |
1397dc18 | 10223 | /*** 9. Post-amble ***/ |
4ed46869 | 10224 | |
dfcf069d | 10225 | void |
971de7fb | 10226 | init_coding_once (void) |
4ed46869 KH |
10227 | { |
10228 | int i; | |
10229 | ||
df7492f9 KH |
10230 | for (i = 0; i < coding_category_max; i++) |
10231 | { | |
10232 | coding_categories[i].id = -1; | |
10233 | coding_priorities[i] = i; | |
10234 | } | |
4ed46869 KH |
10235 | |
10236 | /* ISO2022 specific initialize routine. */ | |
10237 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 10238 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
10239 | for (i = 0x21; i < 0x7F; i++) |
10240 | iso_code_class[i] = ISO_graphic_plane_0; | |
10241 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 10242 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
10243 | for (i = 0xA1; i < 0xFF; i++) |
10244 | iso_code_class[i] = ISO_graphic_plane_1; | |
10245 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
10246 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
10247 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
10248 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
10249 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
10250 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
10251 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
10252 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
10253 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
10254 | ||
df7492f9 KH |
10255 | for (i = 0; i < 256; i++) |
10256 | { | |
10257 | emacs_mule_bytes[i] = 1; | |
10258 | } | |
7c78e542 KH |
10259 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
10260 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
10261 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
10262 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
10263 | } |
10264 | ||
10265 | #ifdef emacs | |
10266 | ||
dfcf069d | 10267 | void |
971de7fb | 10268 | syms_of_coding (void) |
e0e989f6 | 10269 | { |
df7492f9 | 10270 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
10271 | { |
10272 | Lisp_Object args[2]; | |
10273 | args[0] = QCtest; | |
10274 | args[1] = Qeq; | |
10275 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
10276 | } | |
df7492f9 KH |
10277 | |
10278 | staticpro (&Vsjis_coding_system); | |
10279 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 10280 | |
df7492f9 KH |
10281 | staticpro (&Vbig5_coding_system); |
10282 | Vbig5_coding_system = Qnil; | |
10283 | ||
24a73b0a KH |
10284 | staticpro (&Vcode_conversion_reused_workbuf); |
10285 | Vcode_conversion_reused_workbuf = Qnil; | |
10286 | ||
10287 | staticpro (&Vcode_conversion_workbuf_name); | |
d67b4f80 | 10288 | Vcode_conversion_workbuf_name = make_pure_c_string (" *code-conversion-work*"); |
e0e989f6 | 10289 | |
24a73b0a | 10290 | reused_workbuf_in_use = 0; |
df7492f9 KH |
10291 | |
10292 | DEFSYM (Qcharset, "charset"); | |
10293 | DEFSYM (Qtarget_idx, "target-idx"); | |
10294 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
10295 | Fset (Qcoding_system_history, Qnil); |
10296 | ||
9ce27fde | 10297 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 10298 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 10299 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
10300 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
10301 | ||
df7492f9 | 10302 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 10303 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
10304 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
10305 | ||
df7492f9 | 10306 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 10307 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10308 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
10309 | ||
df7492f9 | 10310 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 10311 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10312 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
10313 | ||
df7492f9 | 10314 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 10315 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
10316 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
10317 | ||
df7492f9 KH |
10318 | DEFSYM (Qcoding_system, "coding-system"); |
10319 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 10320 | |
df7492f9 KH |
10321 | DEFSYM (Qeol_type, "eol-type"); |
10322 | DEFSYM (Qunix, "unix"); | |
10323 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 10324 | |
df7492f9 KH |
10325 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
10326 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
10327 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
10328 | DEFSYM (Qdefault_char, "default-char"); | |
10329 | DEFSYM (Qundecided, "undecided"); | |
10330 | DEFSYM (Qno_conversion, "no-conversion"); | |
10331 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 10332 | |
df7492f9 | 10333 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 10334 | |
df7492f9 | 10335 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 10336 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 10337 | |
df7492f9 | 10338 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
10339 | DEFSYM (Qbig, "big"); |
10340 | DEFSYM (Qlittle, "little"); | |
27901516 | 10341 | |
df7492f9 KH |
10342 | DEFSYM (Qshift_jis, "shift-jis"); |
10343 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 10344 | |
df7492f9 | 10345 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 10346 | |
df7492f9 | 10347 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 | 10348 | Fput (Qcoding_system_error, Qerror_conditions, |
d67b4f80 | 10349 | pure_cons (Qcoding_system_error, pure_cons (Qerror, Qnil))); |
4ed46869 | 10350 | Fput (Qcoding_system_error, Qerror_message, |
d67b4f80 | 10351 | make_pure_c_string ("Invalid coding system")); |
4ed46869 | 10352 | |
05e6f5dc KH |
10353 | /* Intern this now in case it isn't already done. |
10354 | Setting this variable twice is harmless. | |
10355 | But don't staticpro it here--that is done in alloc.c. */ | |
d67b4f80 | 10356 | Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots"); |
70c22245 | 10357 | |
df7492f9 | 10358 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 10359 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
10360 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
10361 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10362 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10363 | |
df7492f9 | 10364 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10365 | |
df7492f9 | 10366 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10367 | |
01378f49 | 10368 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10369 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10370 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10371 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10372 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10373 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10374 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10375 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10376 | |
df7492f9 KH |
10377 | Vcoding_category_table |
10378 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10379 | staticpro (&Vcoding_category_table); | |
10380 | /* Followings are target of code detection. */ | |
10381 | ASET (Vcoding_category_table, coding_category_iso_7, | |
d67b4f80 | 10382 | intern_c_string ("coding-category-iso-7")); |
df7492f9 | 10383 | ASET (Vcoding_category_table, coding_category_iso_7_tight, |
d67b4f80 | 10384 | intern_c_string ("coding-category-iso-7-tight")); |
df7492f9 | 10385 | ASET (Vcoding_category_table, coding_category_iso_8_1, |
d67b4f80 | 10386 | intern_c_string ("coding-category-iso-8-1")); |
df7492f9 | 10387 | ASET (Vcoding_category_table, coding_category_iso_8_2, |
d67b4f80 | 10388 | intern_c_string ("coding-category-iso-8-2")); |
df7492f9 | 10389 | ASET (Vcoding_category_table, coding_category_iso_7_else, |
d67b4f80 | 10390 | intern_c_string ("coding-category-iso-7-else")); |
df7492f9 | 10391 | ASET (Vcoding_category_table, coding_category_iso_8_else, |
d67b4f80 | 10392 | intern_c_string ("coding-category-iso-8-else")); |
a470d443 | 10393 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
d67b4f80 | 10394 | intern_c_string ("coding-category-utf-8-auto")); |
a470d443 | 10395 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, |
d67b4f80 | 10396 | intern_c_string ("coding-category-utf-8")); |
a470d443 | 10397 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
d67b4f80 | 10398 | intern_c_string ("coding-category-utf-8-sig")); |
df7492f9 | 10399 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
d67b4f80 | 10400 | intern_c_string ("coding-category-utf-16-be")); |
ff563fce | 10401 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
d67b4f80 | 10402 | intern_c_string ("coding-category-utf-16-auto")); |
df7492f9 | 10403 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
d67b4f80 | 10404 | intern_c_string ("coding-category-utf-16-le")); |
df7492f9 | 10405 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, |
d67b4f80 | 10406 | intern_c_string ("coding-category-utf-16-be-nosig")); |
df7492f9 | 10407 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, |
d67b4f80 | 10408 | intern_c_string ("coding-category-utf-16-le-nosig")); |
df7492f9 | 10409 | ASET (Vcoding_category_table, coding_category_charset, |
d67b4f80 | 10410 | intern_c_string ("coding-category-charset")); |
df7492f9 | 10411 | ASET (Vcoding_category_table, coding_category_sjis, |
d67b4f80 | 10412 | intern_c_string ("coding-category-sjis")); |
df7492f9 | 10413 | ASET (Vcoding_category_table, coding_category_big5, |
d67b4f80 | 10414 | intern_c_string ("coding-category-big5")); |
df7492f9 | 10415 | ASET (Vcoding_category_table, coding_category_ccl, |
d67b4f80 | 10416 | intern_c_string ("coding-category-ccl")); |
df7492f9 | 10417 | ASET (Vcoding_category_table, coding_category_emacs_mule, |
d67b4f80 | 10418 | intern_c_string ("coding-category-emacs-mule")); |
df7492f9 KH |
10419 | /* Followings are NOT target of code detection. */ |
10420 | ASET (Vcoding_category_table, coding_category_raw_text, | |
d67b4f80 | 10421 | intern_c_string ("coding-category-raw-text")); |
df7492f9 | 10422 | ASET (Vcoding_category_table, coding_category_undecided, |
d67b4f80 | 10423 | intern_c_string ("coding-category-undecided")); |
ecf488bc | 10424 | |
065e3595 KH |
10425 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
10426 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
10427 | DEFSYM (Qinvalid_source, "invalid-source"); | |
10428 | DEFSYM (Qinterrupted, "interrupted"); | |
10429 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 10430 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10431 | |
4ed46869 KH |
10432 | defsubr (&Scoding_system_p); |
10433 | defsubr (&Sread_coding_system); | |
10434 | defsubr (&Sread_non_nil_coding_system); | |
10435 | defsubr (&Scheck_coding_system); | |
10436 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10437 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10438 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10439 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10440 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10441 | defsubr (&Sdecode_coding_region); |
10442 | defsubr (&Sencode_coding_region); | |
10443 | defsubr (&Sdecode_coding_string); | |
10444 | defsubr (&Sencode_coding_string); | |
10445 | defsubr (&Sdecode_sjis_char); | |
10446 | defsubr (&Sencode_sjis_char); | |
10447 | defsubr (&Sdecode_big5_char); | |
10448 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10449 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10450 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10451 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10452 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10453 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10454 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10455 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10456 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10457 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10458 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10459 | defsubr (&Scoding_system_base); |
10460 | defsubr (&Scoding_system_plist); | |
10461 | defsubr (&Scoding_system_aliases); | |
10462 | defsubr (&Scoding_system_eol_type); | |
10463 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10464 | |
29208e82 | 10465 | DEFVAR_LISP ("coding-system-list", Vcoding_system_list, |
48b0f3ae PJ |
10466 | doc: /* List of coding systems. |
10467 | ||
10468 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10469 | updated by the functions `define-coding-system' and |
48b0f3ae | 10470 | `define-coding-system-alias'. */); |
4608c386 KH |
10471 | Vcoding_system_list = Qnil; |
10472 | ||
29208e82 | 10473 | DEFVAR_LISP ("coding-system-alist", Vcoding_system_alist, |
48b0f3ae PJ |
10474 | doc: /* Alist of coding system names. |
10475 | Each element is one element list of coding system name. | |
446dcd75 | 10476 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10477 | |
10478 | Do not alter the value of this variable manually. This variable should be | |
10479 | updated by the functions `make-coding-system' and | |
10480 | `define-coding-system-alias'. */); | |
4608c386 KH |
10481 | Vcoding_system_alist = Qnil; |
10482 | ||
29208e82 | 10483 | DEFVAR_LISP ("coding-category-list", Vcoding_category_list, |
48b0f3ae PJ |
10484 | doc: /* List of coding-categories (symbols) ordered by priority. |
10485 | ||
10486 | On detecting a coding system, Emacs tries code detection algorithms | |
10487 | associated with each coding-category one by one in this order. When | |
10488 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10489 | system bound to the corresponding coding-category is selected. |
10490 | ||
448e17d6 | 10491 | Don't modify this variable directly, but use `set-coding-system-priority'. */); |
4ed46869 KH |
10492 | { |
10493 | int i; | |
10494 | ||
10495 | Vcoding_category_list = Qnil; | |
df7492f9 | 10496 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10497 | Vcoding_category_list |
d46c5b12 KH |
10498 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
10499 | Vcoding_category_list); | |
4ed46869 KH |
10500 | } |
10501 | ||
29208e82 | 10502 | DEFVAR_LISP ("coding-system-for-read", Vcoding_system_for_read, |
48b0f3ae PJ |
10503 | doc: /* Specify the coding system for read operations. |
10504 | It is useful to bind this variable with `let', but do not set it globally. | |
10505 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10506 | If not, an appropriate element is used from one of the coding system alists. |
10507 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10508 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10509 | Vcoding_system_for_read = Qnil; |
10510 | ||
29208e82 | 10511 | DEFVAR_LISP ("coding-system-for-write", Vcoding_system_for_write, |
48b0f3ae PJ |
10512 | doc: /* Specify the coding system for write operations. |
10513 | Programs bind this variable with `let', but you should not set it globally. | |
10514 | If the value is a coding system, it is used for encoding of output, | |
10515 | when writing it to a file and when sending it to a file or subprocess. | |
10516 | ||
10517 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10518 | is used from one of the coding system alists. |
10519 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10520 | `process-coding-system-alist', and `network-coding-system-alist'. |
10521 | For output to files, if the above procedure does not specify a coding system, | |
10522 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10523 | Vcoding_system_for_write = Qnil; |
10524 | ||
29208e82 | 10525 | DEFVAR_LISP ("last-coding-system-used", Vlast_coding_system_used, |
df7492f9 KH |
10526 | doc: /* |
10527 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10528 | Vlast_coding_system_used = Qnil; |
10529 | ||
29208e82 | 10530 | DEFVAR_LISP ("last-code-conversion-error", Vlast_code_conversion_error, |
065e3595 KH |
10531 | doc: /* |
10532 | Error status of the last code conversion. | |
10533 | ||
10534 | When an error was detected in the last code conversion, this variable | |
10535 | is set to one of the following symbols. | |
10536 | `insufficient-source' | |
10537 | `inconsistent-eol' | |
10538 | `invalid-source' | |
10539 | `interrupted' | |
10540 | `insufficient-memory' | |
10541 | When no error was detected, the value doesn't change. So, to check | |
10542 | the error status of a code conversion by this variable, you must | |
10543 | explicitly set this variable to nil before performing code | |
10544 | conversion. */); | |
10545 | Vlast_code_conversion_error = Qnil; | |
10546 | ||
29208e82 | 10547 | DEFVAR_BOOL ("inhibit-eol-conversion", inhibit_eol_conversion, |
df7492f9 KH |
10548 | doc: /* |
10549 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10550 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10551 | such conversion. */); | |
9ce27fde KH |
10552 | inhibit_eol_conversion = 0; |
10553 | ||
29208e82 | 10554 | DEFVAR_BOOL ("inherit-process-coding-system", inherit_process_coding_system, |
df7492f9 KH |
10555 | doc: /* |
10556 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10557 | Bind it to t if the process output is to be treated as if it were a file |
10558 | read from some filesystem. */); | |
ed29121d EZ |
10559 | inherit_process_coding_system = 0; |
10560 | ||
29208e82 | 10561 | DEFVAR_LISP ("file-coding-system-alist", Vfile_coding_system_alist, |
df7492f9 KH |
10562 | doc: /* |
10563 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10564 | The format is ((PATTERN . VAL) ...), |
10565 | where PATTERN is a regular expression matching a file name, | |
10566 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10567 | If VAL is a coding system, it is used for both decoding and encoding | |
10568 | the file contents. | |
10569 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10570 | and the cdr part is used for encoding. | |
10571 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10572 | or a cons of coding systems which are used as above. The function is |
10573 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10574 | `find-operation-coding-system' was called. If the function can't decide |
10575 | a coding system, it can return `undecided' so that the normal | |
10576 | code-detection is performed. | |
48b0f3ae PJ |
10577 | |
10578 | See also the function `find-operation-coding-system' | |
10579 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10580 | Vfile_coding_system_alist = Qnil; |
10581 | ||
29208e82 | 10582 | DEFVAR_LISP ("process-coding-system-alist", Vprocess_coding_system_alist, |
df7492f9 KH |
10583 | doc: /* |
10584 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
10585 | The format is ((PATTERN . VAL) ...), |
10586 | where PATTERN is a regular expression matching a program name, | |
10587 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10588 | If VAL is a coding system, it is used for both decoding what received | |
10589 | from the program and encoding what sent to the program. | |
10590 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10591 | and the cdr part is used for encoding. | |
10592 | If VAL is a function symbol, the function must return a coding system | |
10593 | or a cons of coding systems which are used as above. | |
10594 | ||
10595 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
10596 | Vprocess_coding_system_alist = Qnil; |
10597 | ||
29208e82 | 10598 | DEFVAR_LISP ("network-coding-system-alist", Vnetwork_coding_system_alist, |
df7492f9 KH |
10599 | doc: /* |
10600 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
10601 | The format is ((PATTERN . VAL) ...), |
10602 | where PATTERN is a regular expression matching a network service name | |
10603 | or is a port number to connect to, | |
10604 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10605 | If VAL is a coding system, it is used for both decoding what received | |
10606 | from the network stream and encoding what sent to the network stream. | |
10607 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10608 | and the cdr part is used for encoding. | |
10609 | If VAL is a function symbol, the function must return a coding system | |
10610 | or a cons of coding systems which are used as above. | |
10611 | ||
10612 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 10613 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 10614 | |
29208e82 | 10615 | DEFVAR_LISP ("locale-coding-system", Vlocale_coding_system, |
75205970 RS |
10616 | doc: /* Coding system to use with system messages. |
10617 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
10618 | Vlocale_coding_system = Qnil; |
10619 | ||
005f0d35 | 10620 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
29208e82 | 10621 | DEFVAR_LISP ("eol-mnemonic-unix", eol_mnemonic_unix, |
df7492f9 KH |
10622 | doc: /* |
10623 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
d67b4f80 | 10624 | eol_mnemonic_unix = make_pure_c_string (":"); |
4ed46869 | 10625 | |
29208e82 | 10626 | DEFVAR_LISP ("eol-mnemonic-dos", eol_mnemonic_dos, |
df7492f9 KH |
10627 | doc: /* |
10628 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
d67b4f80 | 10629 | eol_mnemonic_dos = make_pure_c_string ("\\"); |
4ed46869 | 10630 | |
29208e82 | 10631 | DEFVAR_LISP ("eol-mnemonic-mac", eol_mnemonic_mac, |
df7492f9 KH |
10632 | doc: /* |
10633 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
d67b4f80 | 10634 | eol_mnemonic_mac = make_pure_c_string ("/"); |
4ed46869 | 10635 | |
29208e82 | 10636 | DEFVAR_LISP ("eol-mnemonic-undecided", eol_mnemonic_undecided, |
df7492f9 KH |
10637 | doc: /* |
10638 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
d67b4f80 | 10639 | eol_mnemonic_undecided = make_pure_c_string (":"); |
4ed46869 | 10640 | |
29208e82 | 10641 | DEFVAR_LISP ("enable-character-translation", Venable_character_translation, |
df7492f9 KH |
10642 | doc: /* |
10643 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 10644 | Venable_character_translation = Qt; |
bdd9fb48 | 10645 | |
f967223b | 10646 | DEFVAR_LISP ("standard-translation-table-for-decode", |
29208e82 | 10647 | Vstandard_translation_table_for_decode, |
48b0f3ae | 10648 | doc: /* Table for translating characters while decoding. */); |
f967223b | 10649 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 10650 | |
f967223b | 10651 | DEFVAR_LISP ("standard-translation-table-for-encode", |
29208e82 | 10652 | Vstandard_translation_table_for_encode, |
48b0f3ae | 10653 | doc: /* Table for translating characters while encoding. */); |
f967223b | 10654 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 10655 | |
29208e82 | 10656 | DEFVAR_LISP ("charset-revision-table", Vcharset_revision_table, |
48b0f3ae PJ |
10657 | doc: /* Alist of charsets vs revision numbers. |
10658 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
10659 | designate it with the escape sequence identifying revision (cdr part |
10660 | of the element). */); | |
10661 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
10662 | |
10663 | DEFVAR_LISP ("default-process-coding-system", | |
29208e82 | 10664 | Vdefault_process_coding_system, |
48b0f3ae PJ |
10665 | doc: /* Cons of coding systems used for process I/O by default. |
10666 | The car part is used for decoding a process output, | |
10667 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 10668 | Vdefault_process_coding_system = Qnil; |
c4825358 | 10669 | |
29208e82 | 10670 | DEFVAR_LISP ("latin-extra-code-table", Vlatin_extra_code_table, |
df7492f9 KH |
10671 | doc: /* |
10672 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
10673 | This is a vector of length 256. |
10674 | If Nth element is non-nil, the existence of code N in a file | |
10675 | \(or output of subprocess) doesn't prevent it to be detected as | |
10676 | a coding system of ISO 2022 variant which has a flag | |
10677 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
10678 | or reading output of a subprocess. | |
446dcd75 | 10679 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 10680 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
10681 | |
10682 | DEFVAR_LISP ("select-safe-coding-system-function", | |
29208e82 | 10683 | Vselect_safe_coding_system_function, |
df7492f9 KH |
10684 | doc: /* |
10685 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
10686 | |
10687 | If set, this function is called to force a user to select a proper | |
10688 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
10689 | coding system used in each operation can't encode the text. The |
10690 | function should take care that the buffer is not modified while | |
10691 | the coding system is being selected. | |
48b0f3ae PJ |
10692 | |
10693 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
10694 | Vselect_safe_coding_system_function = Qnil; |
10695 | ||
5d5bf4d8 | 10696 | DEFVAR_BOOL ("coding-system-require-warning", |
29208e82 | 10697 | coding_system_require_warning, |
5d5bf4d8 | 10698 | doc: /* Internal use only. |
6b89e3aa KH |
10699 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
10700 | called even if `coding-system-for-write' is non-nil. The command | |
10701 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
10702 | coding_system_require_warning = 0; |
10703 | ||
10704 | ||
22ab2303 | 10705 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
29208e82 | 10706 | inhibit_iso_escape_detection, |
df7492f9 | 10707 | doc: /* |
97b1b294 | 10708 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 10709 | |
97b1b294 EZ |
10710 | When Emacs reads text, it tries to detect how the text is encoded. |
10711 | This code detection is sensitive to escape sequences. If Emacs sees | |
10712 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
10713 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
10714 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
10715 | |
10716 | However, there may be a case that you want to read escape sequences in | |
10717 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
10718 | Then the code detection will ignore any escape sequences, and no text is |
10719 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
10720 | escape sequences become visible in a buffer. |
10721 | ||
10722 | The default value is nil, and it is strongly recommended not to change | |
10723 | it. That is because many Emacs Lisp source files that contain | |
10724 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
10725 | in Emacs's distribution, and they won't be decoded correctly on | |
10726 | reading if you suppress escape sequence detection. | |
10727 | ||
10728 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 10729 | to explicitly specify some coding system that doesn't use ISO-2022 |
48b0f3ae | 10730 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 10731 | inhibit_iso_escape_detection = 0; |
002fdb44 | 10732 | |
97b1b294 | 10733 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
29208e82 | 10734 | inhibit_null_byte_detection, |
97b1b294 EZ |
10735 | doc: /* If non-nil, Emacs ignores null bytes on code detection. |
10736 | By default, Emacs treats it as binary data, and does not attempt to | |
10737 | decode it. The effect is as if you specified `no-conversion' for | |
10738 | reading that text. | |
10739 | ||
10740 | Set this to non-nil when a regular text happens to include null bytes. | |
10741 | Examples are Index nodes of Info files and null-byte delimited output | |
10742 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
10743 | decode text as usual. */); | |
10744 | inhibit_null_byte_detection = 0; | |
10745 | ||
29208e82 | 10746 | DEFVAR_LISP ("translation-table-for-input", Vtranslation_table_for_input, |
15c8f9d1 | 10747 | doc: /* Char table for translating self-inserting characters. |
446dcd75 | 10748 | This is applied to the result of input methods, not their input. |
8434d0b8 EZ |
10749 | See also `keyboard-translate-table'. |
10750 | ||
10751 | Use of this variable for character code unification was rendered | |
10752 | obsolete in Emacs 23.1 and later, since Unicode is now the basis of | |
10753 | internal character representation. */); | |
002fdb44 | 10754 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 10755 | |
2c78b7e1 KH |
10756 | { |
10757 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 10758 | Lisp_Object plist[16]; |
2c78b7e1 KH |
10759 | int i; |
10760 | ||
10761 | for (i = 0; i < coding_arg_max; i++) | |
10762 | args[i] = Qnil; | |
10763 | ||
d67b4f80 | 10764 | plist[0] = intern_c_string (":name"); |
2c78b7e1 | 10765 | plist[1] = args[coding_arg_name] = Qno_conversion; |
d67b4f80 | 10766 | plist[2] = intern_c_string (":mnemonic"); |
2c78b7e1 | 10767 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); |
d67b4f80 | 10768 | plist[4] = intern_c_string (":coding-type"); |
2c78b7e1 | 10769 | plist[5] = args[coding_arg_coding_type] = Qraw_text; |
d67b4f80 | 10770 | plist[6] = intern_c_string (":ascii-compatible-p"); |
2c78b7e1 | 10771 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; |
d67b4f80 | 10772 | plist[8] = intern_c_string (":default-char"); |
2c78b7e1 | 10773 | plist[9] = args[coding_arg_default_char] = make_number (0); |
d67b4f80 | 10774 | plist[10] = intern_c_string (":for-unibyte"); |
8f924df7 | 10775 | plist[11] = args[coding_arg_for_unibyte] = Qt; |
d67b4f80 DN |
10776 | plist[12] = intern_c_string (":docstring"); |
10777 | plist[13] = make_pure_c_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
10778 | \n\ |
10779 | When you visit a file with this coding, the file is read into a\n\ | |
10780 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
10781 | character."); | |
d67b4f80 | 10782 | plist[14] = intern_c_string (":eol-type"); |
8f924df7 KH |
10783 | plist[15] = args[coding_arg_eol_type] = Qunix; |
10784 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 10785 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
10786 | |
10787 | plist[1] = args[coding_arg_name] = Qundecided; | |
10788 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
10789 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
10790 | /* This is already set. | |
35befdaa | 10791 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
d67b4f80 | 10792 | plist[8] = intern_c_string (":charset-list"); |
ae6f73fa KH |
10793 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); |
10794 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
d67b4f80 | 10795 | plist[13] = make_pure_c_string ("No conversion on encoding, automatic conversion on decoding."); |
ae6f73fa KH |
10796 | plist[15] = args[coding_arg_eol_type] = Qnil; |
10797 | args[coding_arg_plist] = Flist (16, plist); | |
10798 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
10799 | } |
10800 | ||
2c78b7e1 | 10801 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
10802 | |
10803 | { | |
10804 | int i; | |
10805 | ||
10806 | for (i = 0; i < coding_category_max; i++) | |
10807 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
10808 | } | |
1a4990fb | 10809 | #if defined (DOS_NT) |
fcbcfb64 KH |
10810 | system_eol_type = Qdos; |
10811 | #else | |
10812 | system_eol_type = Qunix; | |
10813 | #endif | |
10814 | staticpro (&system_eol_type); | |
4ed46869 KH |
10815 | } |
10816 | ||
68c45bf0 | 10817 | char * |
971de7fb | 10818 | emacs_strerror (int error_number) |
68c45bf0 PE |
10819 | { |
10820 | char *str; | |
10821 | ||
ca9c0567 | 10822 | synchronize_system_messages_locale (); |
68c45bf0 PE |
10823 | str = strerror (error_number); |
10824 | ||
10825 | if (! NILP (Vlocale_coding_system)) | |
10826 | { | |
10827 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
10828 | Vlocale_coding_system, | |
10829 | 0); | |
51b59d79 | 10830 | str = SSDATA (dec); |
68c45bf0 PE |
10831 | } |
10832 | ||
10833 | return str; | |
10834 | } | |
10835 | ||
4ed46869 | 10836 | #endif /* emacs */ |