Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
73b0cd50 | 2 | Copyright (C) 2001-2011 Free Software Foundation, Inc. |
7976eda0 | 3 | Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, |
5df4f04c | 4 | 2005, 2006, 2007, 2008, 2009, 2010, 2011 |
ce03bf76 KH |
5 | National Institute of Advanced Industrial Science and Technology (AIST) |
6 | Registration Number H14PRO021 | |
8f924df7 | 7 | Copyright (C) 2003 |
df7492f9 KH |
8 | National Institute of Advanced Industrial Science and Technology (AIST) |
9 | Registration Number H13PRO009 | |
4ed46869 | 10 | |
369314dc KH |
11 | This file is part of GNU Emacs. |
12 | ||
9ec0b715 | 13 | GNU Emacs is free software: you can redistribute it and/or modify |
369314dc | 14 | it under the terms of the GNU General Public License as published by |
9ec0b715 GM |
15 | the Free Software Foundation, either version 3 of the License, or |
16 | (at your option) any later version. | |
4ed46869 | 17 | |
369314dc KH |
18 | GNU Emacs is distributed in the hope that it will be useful, |
19 | but WITHOUT ANY WARRANTY; without even the implied warranty of | |
20 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
21 | GNU General Public License for more details. | |
4ed46869 | 22 | |
369314dc | 23 | You should have received a copy of the GNU General Public License |
9ec0b715 | 24 | along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */ |
4ed46869 KH |
25 | |
26 | /*** TABLE OF CONTENTS *** | |
27 | ||
b73bfc1c | 28 | 0. General comments |
4ed46869 | 29 | 1. Preamble |
df7492f9 KH |
30 | 2. Emacs' internal format (emacs-utf-8) handlers |
31 | 3. UTF-8 handlers | |
32 | 4. UTF-16 handlers | |
33 | 5. Charset-base coding systems handlers | |
34 | 6. emacs-mule (old Emacs' internal format) handlers | |
35 | 7. ISO2022 handlers | |
36 | 8. Shift-JIS and BIG5 handlers | |
37 | 9. CCL handlers | |
38 | 10. C library functions | |
39 | 11. Emacs Lisp library functions | |
40 | 12. Postamble | |
4ed46869 KH |
41 | |
42 | */ | |
43 | ||
df7492f9 | 44 | /*** 0. General comments *** |
b73bfc1c KH |
45 | |
46 | ||
df7492f9 | 47 | CODING SYSTEM |
4ed46869 | 48 | |
5bad0796 DL |
49 | A coding system is an object for an encoding mechanism that contains |
50 | information about how to convert byte sequences to character | |
e19c3639 KH |
51 | sequences and vice versa. When we say "decode", it means converting |
52 | a byte sequence of a specific coding system into a character | |
53 | sequence that is represented by Emacs' internal coding system | |
54 | `emacs-utf-8', and when we say "encode", it means converting a | |
55 | character sequence of emacs-utf-8 to a byte sequence of a specific | |
0ef69138 | 56 | coding system. |
4ed46869 | 57 | |
e19c3639 KH |
58 | In Emacs Lisp, a coding system is represented by a Lisp symbol. In |
59 | C level, a coding system is represented by a vector of attributes | |
5bad0796 | 60 | stored in the hash table Vcharset_hash_table. The conversion from |
e19c3639 KH |
61 | coding system symbol to attributes vector is done by looking up |
62 | Vcharset_hash_table by the symbol. | |
4ed46869 | 63 | |
e19c3639 | 64 | Coding systems are classified into the following types depending on |
5bad0796 | 65 | the encoding mechanism. Here's a brief description of the types. |
4ed46869 | 66 | |
df7492f9 KH |
67 | o UTF-8 |
68 | ||
69 | o UTF-16 | |
70 | ||
71 | o Charset-base coding system | |
72 | ||
73 | A coding system defined by one or more (coded) character sets. | |
5bad0796 | 74 | Decoding and encoding are done by a code converter defined for each |
df7492f9 KH |
75 | character set. |
76 | ||
5bad0796 | 77 | o Old Emacs internal format (emacs-mule) |
df7492f9 | 78 | |
5bad0796 | 79 | The coding system adopted by old versions of Emacs (20 and 21). |
4ed46869 | 80 | |
df7492f9 | 81 | o ISO2022-base coding system |
4ed46869 KH |
82 | |
83 | The most famous coding system for multiple character sets. X's | |
df7492f9 KH |
84 | Compound Text, various EUCs (Extended Unix Code), and coding systems |
85 | used in the Internet communication such as ISO-2022-JP are all | |
86 | variants of ISO2022. | |
4ed46869 | 87 | |
df7492f9 | 88 | o SJIS (or Shift-JIS or MS-Kanji-Code) |
93dec019 | 89 | |
4ed46869 KH |
90 | A coding system to encode character sets: ASCII, JISX0201, and |
91 | JISX0208. Widely used for PC's in Japan. Details are described in | |
df7492f9 | 92 | section 8. |
4ed46869 | 93 | |
df7492f9 | 94 | o BIG5 |
4ed46869 | 95 | |
df7492f9 | 96 | A coding system to encode character sets: ASCII and Big5. Widely |
cfb43547 | 97 | used for Chinese (mainly in Taiwan and Hong Kong). Details are |
df7492f9 KH |
98 | described in section 8. In this file, when we write "big5" (all |
99 | lowercase), we mean the coding system, and when we write "Big5" | |
100 | (capitalized), we mean the character set. | |
4ed46869 | 101 | |
df7492f9 | 102 | o CCL |
27901516 | 103 | |
5bad0796 | 104 | If a user wants to decode/encode text encoded in a coding system |
df7492f9 KH |
105 | not listed above, he can supply a decoder and an encoder for it in |
106 | CCL (Code Conversion Language) programs. Emacs executes the CCL | |
107 | program while decoding/encoding. | |
27901516 | 108 | |
df7492f9 | 109 | o Raw-text |
4ed46869 | 110 | |
5a936b46 | 111 | A coding system for text containing raw eight-bit data. Emacs |
5bad0796 | 112 | treats each byte of source text as a character (except for |
df7492f9 | 113 | end-of-line conversion). |
4ed46869 | 114 | |
df7492f9 KH |
115 | o No-conversion |
116 | ||
117 | Like raw text, but don't do end-of-line conversion. | |
4ed46869 | 118 | |
4ed46869 | 119 | |
df7492f9 | 120 | END-OF-LINE FORMAT |
4ed46869 | 121 | |
5bad0796 | 122 | How text end-of-line is encoded depends on operating system. For |
df7492f9 | 123 | instance, Unix's format is just one byte of LF (line-feed) code, |
f4dee582 | 124 | whereas DOS's format is two-byte sequence of `carriage-return' and |
d46c5b12 KH |
125 | `line-feed' codes. MacOS's format is usually one byte of |
126 | `carriage-return'. | |
4ed46869 | 127 | |
cfb43547 | 128 | Since text character encoding and end-of-line encoding are |
df7492f9 KH |
129 | independent, any coding system described above can take any format |
130 | of end-of-line (except for no-conversion). | |
4ed46869 | 131 | |
e19c3639 KH |
132 | STRUCT CODING_SYSTEM |
133 | ||
134 | Before using a coding system for code conversion (i.e. decoding and | |
135 | encoding), we setup a structure of type `struct coding_system'. | |
136 | This structure keeps various information about a specific code | |
5bad0796 | 137 | conversion (e.g. the location of source and destination data). |
4ed46869 KH |
138 | |
139 | */ | |
140 | ||
df7492f9 KH |
141 | /* COMMON MACROS */ |
142 | ||
143 | ||
4ed46869 KH |
144 | /*** GENERAL NOTES on `detect_coding_XXX ()' functions *** |
145 | ||
df7492f9 | 146 | These functions check if a byte sequence specified as a source in |
ff0dacd7 KH |
147 | CODING conforms to the format of XXX, and update the members of |
148 | DETECT_INFO. | |
df7492f9 | 149 | |
ff0dacd7 | 150 | Return 1 if the byte sequence conforms to XXX, otherwise return 0. |
df7492f9 KH |
151 | |
152 | Below is the template of these functions. */ | |
153 | ||
4ed46869 | 154 | #if 0 |
df7492f9 | 155 | static int |
cf84bb53 JB |
156 | detect_coding_XXX (struct coding_system *coding, |
157 | struct coding_detection_info *detect_info) | |
4ed46869 | 158 | { |
f1d34bca MB |
159 | const unsigned char *src = coding->source; |
160 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 161 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 162 | int consumed_chars = 0; |
df7492f9 KH |
163 | int found = 0; |
164 | ...; | |
165 | ||
166 | while (1) | |
167 | { | |
ad1746f5 | 168 | /* Get one byte from the source. If the source is exhausted, jump |
df7492f9 KH |
169 | to no_more_source:. */ |
170 | ONE_MORE_BYTE (c); | |
ff0dacd7 KH |
171 | |
172 | if (! __C_conforms_to_XXX___ (c)) | |
173 | break; | |
174 | if (! __C_strongly_suggests_XXX__ (c)) | |
175 | found = CATEGORY_MASK_XXX; | |
df7492f9 | 176 | } |
ff0dacd7 KH |
177 | /* The byte sequence is invalid for XXX. */ |
178 | detect_info->rejected |= CATEGORY_MASK_XXX; | |
df7492f9 | 179 | return 0; |
ff0dacd7 | 180 | |
df7492f9 | 181 | no_more_source: |
ad1746f5 | 182 | /* The source exhausted successfully. */ |
ff0dacd7 | 183 | detect_info->found |= found; |
df7492f9 | 184 | return 1; |
4ed46869 KH |
185 | } |
186 | #endif | |
187 | ||
188 | /*** GENERAL NOTES on `decode_coding_XXX ()' functions *** | |
189 | ||
df7492f9 KH |
190 | These functions decode a byte sequence specified as a source by |
191 | CODING. The resulting multibyte text goes to a place pointed to by | |
192 | CODING->charbuf, the length of which should not exceed | |
193 | CODING->charbuf_size; | |
d46c5b12 | 194 | |
df7492f9 KH |
195 | These functions set the information of original and decoded texts in |
196 | CODING->consumed, CODING->consumed_char, and CODING->charbuf_used. | |
197 | They also set CODING->result to one of CODING_RESULT_XXX indicating | |
198 | how the decoding is finished. | |
d46c5b12 | 199 | |
df7492f9 | 200 | Below is the template of these functions. */ |
d46c5b12 | 201 | |
4ed46869 | 202 | #if 0 |
b73bfc1c | 203 | static void |
cf84bb53 | 204 | decode_coding_XXXX (struct coding_system *coding) |
4ed46869 | 205 | { |
f1d34bca MB |
206 | const unsigned char *src = coding->source + coding->consumed; |
207 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 KH |
208 | /* SRC_BASE remembers the start position in source in each loop. |
209 | The loop will be exited when there's not enough source code, or | |
210 | when there's no room in CHARBUF for a decoded character. */ | |
f1d34bca | 211 | const unsigned char *src_base; |
df7492f9 | 212 | /* A buffer to produce decoded characters. */ |
69a80ea3 KH |
213 | int *charbuf = coding->charbuf + coding->charbuf_used; |
214 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
215 | int multibytep = coding->src_multibyte; |
216 | ||
217 | while (1) | |
218 | { | |
219 | src_base = src; | |
220 | if (charbuf < charbuf_end) | |
221 | /* No more room to produce a decoded character. */ | |
222 | break; | |
223 | ONE_MORE_BYTE (c); | |
224 | /* Decode it. */ | |
225 | } | |
226 | ||
227 | no_more_source: | |
228 | if (src_base < src_end | |
229 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
230 | /* If the source ends by partial bytes to construct a character, | |
231 | treat them as eight-bit raw data. */ | |
232 | while (src_base < src_end && charbuf < charbuf_end) | |
233 | *charbuf++ = *src_base++; | |
234 | /* Remember how many bytes and characters we consumed. If the | |
235 | source is multibyte, the bytes and chars are not identical. */ | |
236 | coding->consumed = coding->consumed_char = src_base - coding->source; | |
237 | /* Remember how many characters we produced. */ | |
238 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
239 | } |
240 | #endif | |
241 | ||
242 | /*** GENERAL NOTES on `encode_coding_XXX ()' functions *** | |
243 | ||
df7492f9 KH |
244 | These functions encode SRC_BYTES length text at SOURCE of Emacs' |
245 | internal multibyte format by CODING. The resulting byte sequence | |
b73bfc1c KH |
246 | goes to a place pointed to by DESTINATION, the length of which |
247 | should not exceed DST_BYTES. | |
d46c5b12 | 248 | |
df7492f9 KH |
249 | These functions set the information of original and encoded texts in |
250 | the members produced, produced_char, consumed, and consumed_char of | |
251 | the structure *CODING. They also set the member result to one of | |
252 | CODING_RESULT_XXX indicating how the encoding finished. | |
d46c5b12 | 253 | |
df7492f9 KH |
254 | DST_BYTES zero means that source area and destination area are |
255 | overlapped, which means that we can produce a encoded text until it | |
256 | reaches at the head of not-yet-encoded source text. | |
d46c5b12 | 257 | |
df7492f9 | 258 | Below is a template of these functions. */ |
4ed46869 | 259 | #if 0 |
b73bfc1c | 260 | static void |
cf84bb53 | 261 | encode_coding_XXX (struct coding_system *coding) |
4ed46869 | 262 | { |
df7492f9 KH |
263 | int multibytep = coding->dst_multibyte; |
264 | int *charbuf = coding->charbuf; | |
265 | int *charbuf_end = charbuf->charbuf + coding->charbuf_used; | |
266 | unsigned char *dst = coding->destination + coding->produced; | |
267 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
268 | unsigned char *adjusted_dst_end = dst_end - _MAX_BYTES_PRODUCED_IN_LOOP_; | |
269 | int produced_chars = 0; | |
270 | ||
271 | for (; charbuf < charbuf_end && dst < adjusted_dst_end; charbuf++) | |
272 | { | |
273 | int c = *charbuf; | |
274 | /* Encode C into DST, and increment DST. */ | |
275 | } | |
276 | label_no_more_destination: | |
277 | /* How many chars and bytes we produced. */ | |
278 | coding->produced_char += produced_chars; | |
279 | coding->produced = dst - coding->destination; | |
4ed46869 KH |
280 | } |
281 | #endif | |
282 | ||
4ed46869 KH |
283 | \f |
284 | /*** 1. Preamble ***/ | |
285 | ||
68c45bf0 | 286 | #include <config.h> |
4ed46869 | 287 | #include <stdio.h> |
d7306fe6 | 288 | #include <setjmp.h> |
4ed46869 | 289 | |
4ed46869 KH |
290 | #include "lisp.h" |
291 | #include "buffer.h" | |
df7492f9 | 292 | #include "character.h" |
4ed46869 KH |
293 | #include "charset.h" |
294 | #include "ccl.h" | |
df7492f9 | 295 | #include "composite.h" |
4ed46869 KH |
296 | #include "coding.h" |
297 | #include "window.h" | |
b8299c66 KL |
298 | #include "frame.h" |
299 | #include "termhooks.h" | |
4ed46869 | 300 | |
df7492f9 | 301 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 302 | |
df7492f9 | 303 | Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type; |
1965cb73 | 304 | Lisp_Object Qunix, Qdos; |
4ed46869 KH |
305 | Lisp_Object Qbuffer_file_coding_system; |
306 | Lisp_Object Qpost_read_conversion, Qpre_write_conversion; | |
df7492f9 | 307 | Lisp_Object Qdefault_char; |
27901516 | 308 | Lisp_Object Qno_conversion, Qundecided; |
df7492f9 | 309 | Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5; |
b49a1807 | 310 | Lisp_Object Qbig, Qlittle; |
bb0115a2 | 311 | Lisp_Object Qcoding_system_history; |
1397dc18 | 312 | Lisp_Object Qvalid_codes; |
2133e2d1 | 313 | Lisp_Object QCcategory, QCmnemonic, QCdefault_char; |
a6f87d34 KH |
314 | Lisp_Object QCdecode_translation_table, QCencode_translation_table; |
315 | Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
35befdaa | 316 | Lisp_Object QCascii_compatible_p; |
4ed46869 | 317 | |
387f6ba5 | 318 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 KH |
319 | Lisp_Object Qstart_process, Qopen_network_stream; |
320 | Lisp_Object Qtarget_idx; | |
321 | ||
065e3595 KH |
322 | Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
323 | Lisp_Object Qinterrupted, Qinsufficient_memory; | |
324 | ||
44e8490d KH |
325 | /* If a symbol has this property, evaluate the value to define the |
326 | symbol as a coding system. */ | |
327 | static Lisp_Object Qcoding_system_define_form; | |
328 | ||
fcbcfb64 KH |
329 | /* Format of end-of-line decided by system. This is Qunix on |
330 | Unix and Mac, Qdos on DOS/Windows. | |
331 | This has an effect only for external encoding (i.e. for output to | |
332 | file and process), not for in-buffer or Lisp string encoding. */ | |
333 | static Lisp_Object system_eol_type; | |
334 | ||
4ed46869 KH |
335 | #ifdef emacs |
336 | ||
4608c386 | 337 | Lisp_Object Qcoding_system_p, Qcoding_system_error; |
4ed46869 | 338 | |
d46c5b12 KH |
339 | /* Coding system emacs-mule and raw-text are for converting only |
340 | end-of-line format. */ | |
341 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 342 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 343 | |
4ed46869 KH |
344 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
345 | routines by the following three variables. */ | |
c4825358 KH |
346 | /* Coding system to be used to encode text for terminal display when |
347 | terminal coding system is nil. */ | |
348 | struct coding_system safe_terminal_coding; | |
349 | ||
4ed46869 KH |
350 | #endif /* emacs */ |
351 | ||
f967223b KH |
352 | Lisp_Object Qtranslation_table; |
353 | Lisp_Object Qtranslation_table_id; | |
354 | Lisp_Object Qtranslation_table_for_decode; | |
355 | Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 | 356 | |
df7492f9 KH |
357 | /* Two special coding systems. */ |
358 | Lisp_Object Vsjis_coding_system; | |
359 | Lisp_Object Vbig5_coding_system; | |
360 | ||
df7492f9 KH |
361 | /* ISO2022 section */ |
362 | ||
363 | #define CODING_ISO_INITIAL(coding, reg) \ | |
364 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
365 | coding_attr_iso_initial), \ | |
366 | reg))) | |
367 | ||
368 | ||
1b3b981b AS |
369 | #define CODING_ISO_REQUEST(coding, charset_id) \ |
370 | (((charset_id) <= (coding)->max_charset_id \ | |
371 | ? ((coding)->safe_charsets[charset_id] != 255 \ | |
372 | ? (coding)->safe_charsets[charset_id] \ | |
373 | : -1) \ | |
df7492f9 KH |
374 | : -1)) |
375 | ||
376 | ||
377 | #define CODING_ISO_FLAGS(coding) \ | |
378 | ((coding)->spec.iso_2022.flags) | |
379 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
380 | ((coding)->spec.iso_2022.current_designation[reg]) | |
381 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
382 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
383 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
384 | ((coding)->spec.iso_2022.single_shifting) | |
385 | #define CODING_ISO_BOL(coding) \ | |
386 | ((coding)->spec.iso_2022.bol) | |
387 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
388 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
e951386e KH |
389 | #define CODING_ISO_CMP_STATUS(coding) \ |
390 | (&(coding)->spec.iso_2022.cmp_status) | |
391 | #define CODING_ISO_EXTSEGMENT_LEN(coding) \ | |
392 | ((coding)->spec.iso_2022.ctext_extended_segment_len) | |
393 | #define CODING_ISO_EMBEDDED_UTF_8(coding) \ | |
394 | ((coding)->spec.iso_2022.embedded_utf_8) | |
df7492f9 KH |
395 | |
396 | /* Control characters of ISO2022. */ | |
397 | /* code */ /* function */ | |
398 | #define ISO_CODE_LF 0x0A /* line-feed */ | |
399 | #define ISO_CODE_CR 0x0D /* carriage-return */ | |
400 | #define ISO_CODE_SO 0x0E /* shift-out */ | |
401 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
402 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
403 | #define ISO_CODE_ESC 0x1B /* escape */ | |
404 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
405 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
406 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
407 | ||
408 | /* All code (1-byte) of ISO2022 is classified into one of the | |
409 | followings. */ | |
410 | enum iso_code_class_type | |
411 | { | |
412 | ISO_control_0, /* Control codes in the range | |
413 | 0x00..0x1F and 0x7F, except for the | |
414 | following 5 codes. */ | |
df7492f9 KH |
415 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
416 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
417 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
418 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
419 | ISO_control_1, /* Control codes in the range | |
420 | 0x80..0x9F, except for the | |
421 | following 3 codes. */ | |
422 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
423 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
424 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
425 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
426 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
427 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
428 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
429 | }; | |
05e6f5dc | 430 | |
df7492f9 KH |
431 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
432 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 433 | |
df7492f9 KH |
434 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
435 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
436 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 437 | |
df7492f9 KH |
438 | /* If set, reset graphic planes and registers at end-of-line to the |
439 | initial state. */ | |
440 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 441 | |
df7492f9 KH |
442 | /* If set, reset graphic planes and registers before any control |
443 | characters to the initial state. */ | |
444 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 445 | |
df7492f9 KH |
446 | /* If set, encode by 7-bit environment. */ |
447 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 448 | |
df7492f9 KH |
449 | /* If set, use locking-shift function. */ |
450 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 451 | |
df7492f9 KH |
452 | /* If set, use single-shift function. Overwrite |
453 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
454 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 455 | |
df7492f9 KH |
456 | /* If set, use designation escape sequence. */ |
457 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 458 | |
df7492f9 KH |
459 | /* If set, produce revision number sequence. */ |
460 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 461 | |
df7492f9 KH |
462 | /* If set, produce ISO6429's direction specifying sequence. */ |
463 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 464 | |
df7492f9 KH |
465 | /* If set, assume designation states are reset at beginning of line on |
466 | output. */ | |
467 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 468 | |
df7492f9 KH |
469 | /* If set, designation sequence should be placed at beginning of line |
470 | on output. */ | |
471 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 472 | |
ad1746f5 | 473 | /* If set, do not encode unsafe characters on output. */ |
df7492f9 | 474 | #define CODING_ISO_FLAG_SAFE 0x0800 |
aa72b389 | 475 | |
df7492f9 KH |
476 | /* If set, extra latin codes (128..159) are accepted as a valid code |
477 | on input. */ | |
478 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 479 | |
df7492f9 | 480 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 481 | |
df7492f9 | 482 | #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 |
aa72b389 | 483 | |
bf16eb23 | 484 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 485 | |
bf16eb23 | 486 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 487 | |
bf16eb23 | 488 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 489 | |
df7492f9 KH |
490 | /* A character to be produced on output if encoding of the original |
491 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
492 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 493 | |
a470d443 KH |
494 | /* UTF-8 section */ |
495 | #define CODING_UTF_8_BOM(coding) \ | |
496 | ((coding)->spec.utf_8_bom) | |
4ed46869 | 497 | |
df7492f9 KH |
498 | /* UTF-16 section */ |
499 | #define CODING_UTF_16_BOM(coding) \ | |
500 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 501 | |
df7492f9 KH |
502 | #define CODING_UTF_16_ENDIAN(coding) \ |
503 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 504 | |
df7492f9 KH |
505 | #define CODING_UTF_16_SURROGATE(coding) \ |
506 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 507 | |
4ed46869 | 508 | |
df7492f9 KH |
509 | /* CCL section */ |
510 | #define CODING_CCL_DECODER(coding) \ | |
511 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
512 | #define CODING_CCL_ENCODER(coding) \ | |
513 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
514 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 515 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 516 | |
5a936b46 | 517 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 518 | |
df7492f9 KH |
519 | enum coding_category |
520 | { | |
521 | coding_category_iso_7, | |
522 | coding_category_iso_7_tight, | |
523 | coding_category_iso_8_1, | |
524 | coding_category_iso_8_2, | |
525 | coding_category_iso_7_else, | |
526 | coding_category_iso_8_else, | |
a470d443 KH |
527 | coding_category_utf_8_auto, |
528 | coding_category_utf_8_nosig, | |
529 | coding_category_utf_8_sig, | |
df7492f9 KH |
530 | coding_category_utf_16_auto, |
531 | coding_category_utf_16_be, | |
532 | coding_category_utf_16_le, | |
533 | coding_category_utf_16_be_nosig, | |
534 | coding_category_utf_16_le_nosig, | |
535 | coding_category_charset, | |
536 | coding_category_sjis, | |
537 | coding_category_big5, | |
538 | coding_category_ccl, | |
539 | coding_category_emacs_mule, | |
540 | /* All above are targets of code detection. */ | |
541 | coding_category_raw_text, | |
542 | coding_category_undecided, | |
543 | coding_category_max | |
544 | }; | |
545 | ||
546 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
547 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
548 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
549 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
550 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
551 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
552 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
a470d443 KH |
553 | #define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto) |
554 | #define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig) | |
555 | #define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig) | |
b49a1807 | 556 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
557 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
558 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
559 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
560 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
561 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
562 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
563 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
564 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
565 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 566 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
567 | |
568 | /* This value is returned if detect_coding_mask () find nothing other | |
569 | than ASCII characters. */ | |
570 | #define CATEGORY_MASK_ANY \ | |
571 | (CATEGORY_MASK_ISO_7 \ | |
572 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
573 | | CATEGORY_MASK_ISO_8_1 \ | |
574 | | CATEGORY_MASK_ISO_8_2 \ | |
575 | | CATEGORY_MASK_ISO_7_ELSE \ | |
576 | | CATEGORY_MASK_ISO_8_ELSE \ | |
a470d443 KH |
577 | | CATEGORY_MASK_UTF_8_AUTO \ |
578 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
579 | | CATEGORY_MASK_UTF_8_SIG \ | |
2f3cbb32 | 580 | | CATEGORY_MASK_UTF_16_AUTO \ |
df7492f9 KH |
581 | | CATEGORY_MASK_UTF_16_BE \ |
582 | | CATEGORY_MASK_UTF_16_LE \ | |
583 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
584 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
585 | | CATEGORY_MASK_CHARSET \ | |
586 | | CATEGORY_MASK_SJIS \ | |
587 | | CATEGORY_MASK_BIG5 \ | |
588 | | CATEGORY_MASK_CCL \ | |
589 | | CATEGORY_MASK_EMACS_MULE) | |
590 | ||
591 | ||
592 | #define CATEGORY_MASK_ISO_7BIT \ | |
593 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
594 | ||
595 | #define CATEGORY_MASK_ISO_8BIT \ | |
596 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
597 | ||
598 | #define CATEGORY_MASK_ISO_ELSE \ | |
599 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
600 | ||
601 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
602 | (CATEGORY_MASK_ISO_7 \ | |
603 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
604 | | CATEGORY_MASK_ISO_7_ELSE \ | |
605 | | CATEGORY_MASK_ISO_8_ELSE) | |
606 | ||
607 | #define CATEGORY_MASK_ISO \ | |
608 | ( CATEGORY_MASK_ISO_7BIT \ | |
609 | | CATEGORY_MASK_ISO_8BIT \ | |
610 | | CATEGORY_MASK_ISO_ELSE) | |
611 | ||
612 | #define CATEGORY_MASK_UTF_16 \ | |
2f3cbb32 KH |
613 | (CATEGORY_MASK_UTF_16_AUTO \ |
614 | | CATEGORY_MASK_UTF_16_BE \ | |
df7492f9 KH |
615 | | CATEGORY_MASK_UTF_16_LE \ |
616 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
617 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
618 | ||
a470d443 KH |
619 | #define CATEGORY_MASK_UTF_8 \ |
620 | (CATEGORY_MASK_UTF_8_AUTO \ | |
621 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
622 | | CATEGORY_MASK_UTF_8_SIG) | |
df7492f9 | 623 | |
df7492f9 | 624 | /* Table of coding categories (Lisp symbols). This variable is for |
ad1746f5 | 625 | internal use only. */ |
df7492f9 KH |
626 | static Lisp_Object Vcoding_category_table; |
627 | ||
628 | /* Table of coding-categories ordered by priority. */ | |
629 | static enum coding_category coding_priorities[coding_category_max]; | |
630 | ||
631 | /* Nth element is a coding context for the coding system bound to the | |
632 | Nth coding category. */ | |
633 | static struct coding_system coding_categories[coding_category_max]; | |
634 | ||
df7492f9 KH |
635 | /*** Commonly used macros and functions ***/ |
636 | ||
637 | #ifndef min | |
638 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
639 | #endif | |
640 | #ifndef max | |
641 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
642 | #endif | |
4ed46869 | 643 | |
24a73b0a KH |
644 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
645 | do { \ | |
646 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
647 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 648 | } while (0) |
4ed46869 | 649 | |
4ed46869 | 650 | |
df7492f9 KH |
651 | /* Safely get one byte from the source text pointed by SRC which ends |
652 | at SRC_END, and set C to that byte. If there are not enough bytes | |
065e3595 KH |
653 | in the source, it jumps to `no_more_source'. If multibytep is |
654 | nonzero, and a multibyte character is found at SRC, set C to the | |
655 | negative value of the character code. The caller should declare | |
656 | and set these variables appropriately in advance: | |
657 | src, src_end, multibytep */ | |
aa72b389 | 658 | |
065e3595 KH |
659 | #define ONE_MORE_BYTE(c) \ |
660 | do { \ | |
661 | if (src == src_end) \ | |
662 | { \ | |
663 | if (src_base < src) \ | |
664 | record_conversion_result \ | |
665 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
666 | goto no_more_source; \ | |
667 | } \ | |
668 | c = *src++; \ | |
669 | if (multibytep && (c & 0x80)) \ | |
670 | { \ | |
671 | if ((c & 0xFE) == 0xC0) \ | |
672 | c = ((c & 1) << 6) | *src++; \ | |
673 | else \ | |
674 | { \ | |
35befdaa KH |
675 | src--; \ |
676 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
677 | record_conversion_result \ |
678 | (coding, CODING_RESULT_INVALID_SRC); \ | |
679 | } \ | |
680 | } \ | |
681 | consumed_chars++; \ | |
aa72b389 KH |
682 | } while (0) |
683 | ||
f56a4450 | 684 | /* Safely get two bytes from the source text pointed by SRC which ends |
220eeac9 KH |
685 | at SRC_END, and set C1 and C2 to those bytes while skipping the |
686 | heading multibyte characters. If there are not enough bytes in the | |
687 | source, it jumps to `no_more_source'. If multibytep is nonzero and | |
688 | a multibyte character is found for C2, set C2 to the negative value | |
689 | of the character code. The caller should declare and set these | |
690 | variables appropriately in advance: | |
f56a4450 KH |
691 | src, src_end, multibytep |
692 | It is intended that this macro is used in detect_coding_utf_16. */ | |
693 | ||
220eeac9 KH |
694 | #define TWO_MORE_BYTES(c1, c2) \ |
695 | do { \ | |
696 | do { \ | |
697 | if (src == src_end) \ | |
698 | goto no_more_source; \ | |
699 | c1 = *src++; \ | |
700 | if (multibytep && (c1 & 0x80)) \ | |
701 | { \ | |
702 | if ((c1 & 0xFE) == 0xC0) \ | |
703 | c1 = ((c1 & 1) << 6) | *src++; \ | |
704 | else \ | |
705 | { \ | |
706 | src += BYTES_BY_CHAR_HEAD (c1) - 1; \ | |
707 | c1 = -1; \ | |
708 | } \ | |
709 | } \ | |
710 | } while (c1 < 0); \ | |
711 | if (src == src_end) \ | |
712 | goto no_more_source; \ | |
713 | c2 = *src++; \ | |
714 | if (multibytep && (c2 & 0x80)) \ | |
715 | { \ | |
716 | if ((c2 & 0xFE) == 0xC0) \ | |
717 | c2 = ((c2 & 1) << 6) | *src++; \ | |
718 | else \ | |
719 | c2 = -1; \ | |
720 | } \ | |
f56a4450 KH |
721 | } while (0) |
722 | ||
aa72b389 | 723 | |
065e3595 KH |
724 | #define ONE_MORE_BYTE_NO_CHECK(c) \ |
725 | do { \ | |
726 | c = *src++; \ | |
727 | if (multibytep && (c & 0x80)) \ | |
728 | { \ | |
729 | if ((c & 0xFE) == 0xC0) \ | |
730 | c = ((c & 1) << 6) | *src++; \ | |
731 | else \ | |
732 | { \ | |
35befdaa KH |
733 | src--; \ |
734 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
735 | record_conversion_result \ |
736 | (coding, CODING_RESULT_INVALID_SRC); \ | |
737 | } \ | |
738 | } \ | |
739 | consumed_chars++; \ | |
aa72b389 KH |
740 | } while (0) |
741 | ||
aa72b389 | 742 | |
df7492f9 KH |
743 | /* Store a byte C in the place pointed by DST and increment DST to the |
744 | next free point, and increment PRODUCED_CHARS. The caller should | |
745 | assure that C is 0..127, and declare and set the variable `dst' | |
746 | appropriately in advance. | |
747 | */ | |
aa72b389 KH |
748 | |
749 | ||
df7492f9 KH |
750 | #define EMIT_ONE_ASCII_BYTE(c) \ |
751 | do { \ | |
752 | produced_chars++; \ | |
753 | *dst++ = (c); \ | |
b6871cc7 | 754 | } while (0) |
aa72b389 KH |
755 | |
756 | ||
ad1746f5 | 757 | /* Like EMIT_ONE_ASCII_BYTE but store two bytes; C1 and C2. */ |
aa72b389 | 758 | |
df7492f9 KH |
759 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
760 | do { \ | |
761 | produced_chars += 2; \ | |
762 | *dst++ = (c1), *dst++ = (c2); \ | |
763 | } while (0) | |
aa72b389 KH |
764 | |
765 | ||
df7492f9 KH |
766 | /* Store a byte C in the place pointed by DST and increment DST to the |
767 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP is | |
768 | nonzero, store in an appropriate multibyte from. The caller should | |
769 | declare and set the variables `dst' and `multibytep' appropriately | |
770 | in advance. */ | |
771 | ||
772 | #define EMIT_ONE_BYTE(c) \ | |
773 | do { \ | |
774 | produced_chars++; \ | |
775 | if (multibytep) \ | |
776 | { \ | |
777 | int ch = (c); \ | |
778 | if (ch >= 0x80) \ | |
779 | ch = BYTE8_TO_CHAR (ch); \ | |
780 | CHAR_STRING_ADVANCE (ch, dst); \ | |
781 | } \ | |
782 | else \ | |
783 | *dst++ = (c); \ | |
aa72b389 | 784 | } while (0) |
aa72b389 | 785 | |
aa72b389 | 786 | |
df7492f9 | 787 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 788 | |
e19c3639 KH |
789 | #define EMIT_TWO_BYTES(c1, c2) \ |
790 | do { \ | |
791 | produced_chars += 2; \ | |
792 | if (multibytep) \ | |
793 | { \ | |
794 | int ch; \ | |
795 | \ | |
796 | ch = (c1); \ | |
797 | if (ch >= 0x80) \ | |
798 | ch = BYTE8_TO_CHAR (ch); \ | |
799 | CHAR_STRING_ADVANCE (ch, dst); \ | |
800 | ch = (c2); \ | |
801 | if (ch >= 0x80) \ | |
802 | ch = BYTE8_TO_CHAR (ch); \ | |
803 | CHAR_STRING_ADVANCE (ch, dst); \ | |
804 | } \ | |
805 | else \ | |
806 | { \ | |
807 | *dst++ = (c1); \ | |
808 | *dst++ = (c2); \ | |
809 | } \ | |
aa72b389 KH |
810 | } while (0) |
811 | ||
812 | ||
df7492f9 KH |
813 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
814 | do { \ | |
815 | EMIT_ONE_BYTE (c1); \ | |
816 | EMIT_TWO_BYTES (c2, c3); \ | |
817 | } while (0) | |
aa72b389 | 818 | |
aa72b389 | 819 | |
df7492f9 KH |
820 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
821 | do { \ | |
822 | EMIT_TWO_BYTES (c1, c2); \ | |
823 | EMIT_TWO_BYTES (c3, c4); \ | |
824 | } while (0) | |
aa72b389 | 825 | |
aa72b389 | 826 | |
f6cbaf43 | 827 | /* Prototypes for static functions. */ |
f57e2426 J |
828 | static void record_conversion_result (struct coding_system *coding, |
829 | enum coding_result_code result); | |
830 | static int detect_coding_utf_8 (struct coding_system *, | |
831 | struct coding_detection_info *info); | |
832 | static void decode_coding_utf_8 (struct coding_system *); | |
833 | static int encode_coding_utf_8 (struct coding_system *); | |
834 | ||
835 | static int detect_coding_utf_16 (struct coding_system *, | |
836 | struct coding_detection_info *info); | |
837 | static void decode_coding_utf_16 (struct coding_system *); | |
838 | static int encode_coding_utf_16 (struct coding_system *); | |
839 | ||
840 | static int detect_coding_iso_2022 (struct coding_system *, | |
841 | struct coding_detection_info *info); | |
842 | static void decode_coding_iso_2022 (struct coding_system *); | |
843 | static int encode_coding_iso_2022 (struct coding_system *); | |
844 | ||
845 | static int detect_coding_emacs_mule (struct coding_system *, | |
846 | struct coding_detection_info *info); | |
847 | static void decode_coding_emacs_mule (struct coding_system *); | |
848 | static int encode_coding_emacs_mule (struct coding_system *); | |
849 | ||
850 | static int detect_coding_sjis (struct coding_system *, | |
851 | struct coding_detection_info *info); | |
852 | static void decode_coding_sjis (struct coding_system *); | |
853 | static int encode_coding_sjis (struct coding_system *); | |
854 | ||
855 | static int detect_coding_big5 (struct coding_system *, | |
856 | struct coding_detection_info *info); | |
857 | static void decode_coding_big5 (struct coding_system *); | |
858 | static int encode_coding_big5 (struct coding_system *); | |
859 | ||
860 | static int detect_coding_ccl (struct coding_system *, | |
861 | struct coding_detection_info *info); | |
862 | static void decode_coding_ccl (struct coding_system *); | |
863 | static int encode_coding_ccl (struct coding_system *); | |
864 | ||
865 | static void decode_coding_raw_text (struct coding_system *); | |
866 | static int encode_coding_raw_text (struct coding_system *); | |
867 | ||
868 | static void coding_set_source (struct coding_system *); | |
869 | static void coding_set_destination (struct coding_system *); | |
870 | static void coding_alloc_by_realloc (struct coding_system *, EMACS_INT); | |
871 | static void coding_alloc_by_making_gap (struct coding_system *, | |
872 | EMACS_INT, EMACS_INT); | |
873 | static unsigned char *alloc_destination (struct coding_system *, | |
874 | EMACS_INT, unsigned char *); | |
875 | static void setup_iso_safe_charsets (Lisp_Object); | |
876 | static unsigned char *encode_designation_at_bol (struct coding_system *, | |
877 | int *, int *, | |
878 | unsigned char *); | |
879 | static int detect_eol (const unsigned char *, | |
880 | EMACS_INT, enum coding_category); | |
881 | static Lisp_Object adjust_coding_eol_type (struct coding_system *, int); | |
882 | static void decode_eol (struct coding_system *); | |
883 | static Lisp_Object get_translation_table (Lisp_Object, int, int *); | |
884 | static Lisp_Object get_translation (Lisp_Object, int *, int *); | |
885 | static int produce_chars (struct coding_system *, Lisp_Object, int); | |
886 | static INLINE void produce_charset (struct coding_system *, int *, | |
887 | EMACS_INT); | |
888 | static void produce_annotation (struct coding_system *, EMACS_INT); | |
889 | static int decode_coding (struct coding_system *); | |
890 | static INLINE int *handle_composition_annotation (EMACS_INT, EMACS_INT, | |
891 | struct coding_system *, | |
892 | int *, EMACS_INT *); | |
893 | static INLINE int *handle_charset_annotation (EMACS_INT, EMACS_INT, | |
894 | struct coding_system *, | |
895 | int *, EMACS_INT *); | |
896 | static void consume_chars (struct coding_system *, Lisp_Object, int); | |
897 | static int encode_coding (struct coding_system *); | |
898 | static Lisp_Object make_conversion_work_buffer (int); | |
899 | static Lisp_Object code_conversion_restore (Lisp_Object); | |
900 | static INLINE int char_encodable_p (int, Lisp_Object); | |
901 | static Lisp_Object make_subsidiaries (Lisp_Object); | |
f6cbaf43 | 902 | |
065e3595 KH |
903 | static void |
904 | record_conversion_result (struct coding_system *coding, | |
905 | enum coding_result_code result) | |
906 | { | |
907 | coding->result = result; | |
908 | switch (result) | |
909 | { | |
910 | case CODING_RESULT_INSUFFICIENT_SRC: | |
911 | Vlast_code_conversion_error = Qinsufficient_source; | |
912 | break; | |
913 | case CODING_RESULT_INCONSISTENT_EOL: | |
914 | Vlast_code_conversion_error = Qinconsistent_eol; | |
915 | break; | |
916 | case CODING_RESULT_INVALID_SRC: | |
917 | Vlast_code_conversion_error = Qinvalid_source; | |
918 | break; | |
919 | case CODING_RESULT_INTERRUPT: | |
920 | Vlast_code_conversion_error = Qinterrupted; | |
921 | break; | |
922 | case CODING_RESULT_INSUFFICIENT_MEM: | |
923 | Vlast_code_conversion_error = Qinsufficient_memory; | |
924 | break; | |
ebaf11b6 KH |
925 | case CODING_RESULT_INSUFFICIENT_DST: |
926 | /* Don't record this error in Vlast_code_conversion_error | |
927 | because it happens just temporarily and is resolved when the | |
928 | whole conversion is finished. */ | |
929 | break; | |
409ea3a1 AS |
930 | case CODING_RESULT_SUCCESS: |
931 | break; | |
35befdaa KH |
932 | default: |
933 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
934 | } |
935 | } | |
936 | ||
75f80e63 EZ |
937 | /* This wrapper macro is used to preserve validity of pointers into |
938 | buffer text across calls to decode_char, which could cause | |
939 | relocation of buffers if it loads a charset map, because loading a | |
940 | charset map allocates large structures. */ | |
df7492f9 KH |
941 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
942 | do { \ | |
943 | charset_map_loaded = 0; \ | |
944 | c = DECODE_CHAR (charset, code); \ | |
945 | if (charset_map_loaded) \ | |
946 | { \ | |
8f924df7 | 947 | const unsigned char *orig = coding->source; \ |
df7492f9 KH |
948 | EMACS_INT offset; \ |
949 | \ | |
950 | coding_set_source (coding); \ | |
951 | offset = coding->source - orig; \ | |
952 | src += offset; \ | |
953 | src_base += offset; \ | |
954 | src_end += offset; \ | |
955 | } \ | |
aa72b389 KH |
956 | } while (0) |
957 | ||
958 | ||
119852e7 KH |
959 | /* If there are at least BYTES length of room at dst, allocate memory |
960 | for coding->destination and update dst and dst_end. We don't have | |
961 | to take care of coding->source which will be relocated. It is | |
962 | handled by calling coding_set_source in encode_coding. */ | |
963 | ||
df7492f9 KH |
964 | #define ASSURE_DESTINATION(bytes) \ |
965 | do { \ | |
966 | if (dst + (bytes) >= dst_end) \ | |
967 | { \ | |
968 | int more_bytes = charbuf_end - charbuf + (bytes); \ | |
969 | \ | |
970 | dst = alloc_destination (coding, more_bytes, dst); \ | |
971 | dst_end = coding->destination + coding->dst_bytes; \ | |
972 | } \ | |
973 | } while (0) | |
aa72b389 | 974 | |
aa72b389 | 975 | |
db274c7a KH |
976 | /* Store multibyte form of the character C in P, and advance P to the |
977 | end of the multibyte form. This is like CHAR_STRING_ADVANCE but it | |
978 | never calls MAYBE_UNIFY_CHAR. */ | |
979 | ||
980 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) \ | |
981 | do { \ | |
982 | if ((c) <= MAX_1_BYTE_CHAR) \ | |
983 | *(p)++ = (c); \ | |
984 | else if ((c) <= MAX_2_BYTE_CHAR) \ | |
985 | *(p)++ = (0xC0 | ((c) >> 6)), \ | |
986 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
987 | else if ((c) <= MAX_3_BYTE_CHAR) \ | |
988 | *(p)++ = (0xE0 | ((c) >> 12)), \ | |
989 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ | |
990 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
991 | else if ((c) <= MAX_4_BYTE_CHAR) \ | |
992 | *(p)++ = (0xF0 | (c >> 18)), \ | |
993 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
994 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
995 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
996 | else if ((c) <= MAX_5_BYTE_CHAR) \ | |
997 | *(p)++ = 0xF8, \ | |
998 | *(p)++ = (0x80 | ((c >> 18) & 0x0F)), \ | |
999 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
1000 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
1001 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
1002 | else \ | |
1003 | (p) += BYTE8_STRING ((c) - 0x3FFF80, p); \ | |
1004 | } while (0) | |
1005 | ||
1006 | ||
1007 | /* Return the character code of character whose multibyte form is at | |
1008 | P, and advance P to the end of the multibyte form. This is like | |
1009 | STRING_CHAR_ADVANCE, but it never calls MAYBE_UNIFY_CHAR. */ | |
1010 | ||
1011 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) \ | |
1012 | (!((p)[0] & 0x80) \ | |
1013 | ? *(p)++ \ | |
1014 | : ! ((p)[0] & 0x20) \ | |
1015 | ? ((p) += 2, \ | |
1016 | ((((p)[-2] & 0x1F) << 6) \ | |
1017 | | ((p)[-1] & 0x3F) \ | |
1018 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
1019 | : ! ((p)[0] & 0x10) \ | |
1020 | ? ((p) += 3, \ | |
1021 | ((((p)[-3] & 0x0F) << 12) \ | |
1022 | | (((p)[-2] & 0x3F) << 6) \ | |
1023 | | ((p)[-1] & 0x3F))) \ | |
1024 | : ! ((p)[0] & 0x08) \ | |
1025 | ? ((p) += 4, \ | |
1026 | ((((p)[-4] & 0xF) << 18) \ | |
1027 | | (((p)[-3] & 0x3F) << 12) \ | |
1028 | | (((p)[-2] & 0x3F) << 6) \ | |
1029 | | ((p)[-1] & 0x3F))) \ | |
1030 | : ((p) += 5, \ | |
1031 | ((((p)[-4] & 0x3F) << 18) \ | |
1032 | | (((p)[-3] & 0x3F) << 12) \ | |
1033 | | (((p)[-2] & 0x3F) << 6) \ | |
1034 | | ((p)[-1] & 0x3F)))) | |
1035 | ||
aa72b389 | 1036 | |
df7492f9 | 1037 | static void |
971de7fb | 1038 | coding_set_source (struct coding_system *coding) |
aa72b389 | 1039 | { |
df7492f9 KH |
1040 | if (BUFFERP (coding->src_object)) |
1041 | { | |
2cb26057 | 1042 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 1043 | |
df7492f9 | 1044 | if (coding->src_pos < 0) |
2cb26057 | 1045 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 1046 | else |
2cb26057 | 1047 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 1048 | } |
df7492f9 | 1049 | else if (STRINGP (coding->src_object)) |
aa72b389 | 1050 | { |
8f924df7 | 1051 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 1052 | } |
df7492f9 KH |
1053 | else |
1054 | /* Otherwise, the source is C string and is never relocated | |
1055 | automatically. Thus we don't have to update anything. */ | |
1056 | ; | |
1057 | } | |
aa72b389 | 1058 | |
df7492f9 | 1059 | static void |
971de7fb | 1060 | coding_set_destination (struct coding_system *coding) |
df7492f9 KH |
1061 | { |
1062 | if (BUFFERP (coding->dst_object)) | |
aa72b389 | 1063 | { |
df7492f9 | 1064 | if (coding->src_pos < 0) |
aa72b389 | 1065 | { |
13818c30 | 1066 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
1067 | coding->dst_bytes = (GAP_END_ADDR |
1068 | - (coding->src_bytes - coding->consumed) | |
1069 | - coding->destination); | |
aa72b389 | 1070 | } |
df7492f9 | 1071 | else |
28f67a95 KH |
1072 | { |
1073 | /* We are sure that coding->dst_pos_byte is before the gap | |
1074 | of the buffer. */ | |
1075 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 1076 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
1077 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
1078 | - coding->destination); | |
1079 | } | |
df7492f9 KH |
1080 | } |
1081 | else | |
1082 | /* Otherwise, the destination is C string and is never relocated | |
1083 | automatically. Thus we don't have to update anything. */ | |
1084 | ; | |
1085 | } | |
1086 | ||
1087 | ||
1088 | static void | |
971de7fb | 1089 | coding_alloc_by_realloc (struct coding_system *coding, EMACS_INT bytes) |
df7492f9 KH |
1090 | { |
1091 | coding->destination = (unsigned char *) xrealloc (coding->destination, | |
1092 | coding->dst_bytes + bytes); | |
1093 | coding->dst_bytes += bytes; | |
1094 | } | |
1095 | ||
1096 | static void | |
cf84bb53 JB |
1097 | coding_alloc_by_making_gap (struct coding_system *coding, |
1098 | EMACS_INT gap_head_used, EMACS_INT bytes) | |
df7492f9 | 1099 | { |
db274c7a | 1100 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1101 | { |
db274c7a KH |
1102 | /* The gap may contain the produced data at the head and not-yet |
1103 | consumed data at the tail. To preserve those data, we at | |
1104 | first make the gap size to zero, then increase the gap | |
1105 | size. */ | |
1106 | EMACS_INT add = GAP_SIZE; | |
1107 | ||
1108 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1109 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1110 | make_gap (bytes); |
1111 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1112 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1113 | } |
730fff51 | 1114 | else |
df7492f9 | 1115 | { |
2c78b7e1 KH |
1116 | Lisp_Object this_buffer; |
1117 | ||
1118 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1119 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1120 | make_gap (bytes); | |
1121 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1122 | } |
df7492f9 | 1123 | } |
8f924df7 | 1124 | |
df7492f9 KH |
1125 | |
1126 | static unsigned char * | |
cf84bb53 JB |
1127 | alloc_destination (struct coding_system *coding, EMACS_INT nbytes, |
1128 | unsigned char *dst) | |
df7492f9 KH |
1129 | { |
1130 | EMACS_INT offset = dst - coding->destination; | |
1131 | ||
1132 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1133 | { |
1134 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1135 | ||
1136 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1137 | } | |
aa72b389 | 1138 | else |
df7492f9 | 1139 | coding_alloc_by_realloc (coding, nbytes); |
df7492f9 KH |
1140 | coding_set_destination (coding); |
1141 | dst = coding->destination + offset; | |
1142 | return dst; | |
1143 | } | |
aa72b389 | 1144 | |
ff0dacd7 KH |
1145 | /** Macros for annotations. */ |
1146 | ||
ff0dacd7 KH |
1147 | /* An annotation data is stored in the array coding->charbuf in this |
1148 | format: | |
69a80ea3 | 1149 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1150 | LENGTH is the number of elements in the annotation. |
1151 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1152 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1153 | |
1154 | The format of the following elements depend on ANNOTATION_MASK. | |
1155 | ||
1156 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1157 | follows: | |
e951386e KH |
1158 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
1159 | ||
1160 | NBYTES is the number of bytes specified in the header part of | |
1161 | old-style emacs-mule encoding, or 0 for the other kind of | |
1162 | composition. | |
1163 | ||
ff0dacd7 | 1164 | METHOD is one of enum composition_method. |
e951386e | 1165 | |
ad1746f5 | 1166 | Optional COMPOSITION-COMPONENTS are characters and composition |
ff0dacd7 KH |
1167 | rules. |
1168 | ||
1169 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
e951386e KH |
1170 | follows. |
1171 | ||
1172 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | |
1173 | recover from an invalid annotation, and should be skipped by | |
1174 | produce_annotation. */ | |
1175 | ||
1176 | /* Maximum length of the header of annotation data. */ | |
1177 | #define MAX_ANNOTATION_LENGTH 5 | |
ff0dacd7 | 1178 | |
69a80ea3 | 1179 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1180 | do { \ |
1181 | *(buf)++ = -(len); \ | |
1182 | *(buf)++ = (mask); \ | |
69a80ea3 | 1183 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1184 | coding->annotated = 1; \ |
1185 | } while (0); | |
1186 | ||
e951386e | 1187 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
69a80ea3 | 1188 | do { \ |
e951386e KH |
1189 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
1190 | *buf++ = nbytes; \ | |
69a80ea3 | 1191 | *buf++ = method; \ |
ff0dacd7 KH |
1192 | } while (0) |
1193 | ||
1194 | ||
69a80ea3 KH |
1195 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1196 | do { \ | |
1197 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1198 | *buf++ = id; \ | |
ff0dacd7 KH |
1199 | } while (0) |
1200 | ||
df7492f9 KH |
1201 | \f |
1202 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1203 | ||
1204 | ||
1205 | ||
1206 | \f | |
1207 | /*** 3. UTF-8 ***/ | |
1208 | ||
1209 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
ff0dacd7 KH |
1210 | Check if a text is encoded in UTF-8. If it is, return 1, else |
1211 | return 0. */ | |
df7492f9 KH |
1212 | |
1213 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1214 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1215 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1216 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1217 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1218 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1219 | ||
a470d443 KH |
1220 | #define UTF_BOM 0xFEFF |
1221 | #define UTF_8_BOM_1 0xEF | |
1222 | #define UTF_8_BOM_2 0xBB | |
1223 | #define UTF_8_BOM_3 0xBF | |
1224 | ||
df7492f9 | 1225 | static int |
cf84bb53 JB |
1226 | detect_coding_utf_8 (struct coding_system *coding, |
1227 | struct coding_detection_info *detect_info) | |
df7492f9 | 1228 | { |
065e3595 | 1229 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1230 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
1231 | int multibytep = coding->src_multibyte; |
1232 | int consumed_chars = 0; | |
a470d443 | 1233 | int bom_found = 0; |
df7492f9 KH |
1234 | int found = 0; |
1235 | ||
ff0dacd7 | 1236 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1237 | /* A coding system of this category is always ASCII compatible. */ |
1238 | src += coding->head_ascii; | |
1239 | ||
1240 | while (1) | |
aa72b389 | 1241 | { |
df7492f9 | 1242 | int c, c1, c2, c3, c4; |
aa72b389 | 1243 | |
065e3595 | 1244 | src_base = src; |
df7492f9 | 1245 | ONE_MORE_BYTE (c); |
065e3595 | 1246 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1247 | continue; |
1248 | ONE_MORE_BYTE (c1); | |
065e3595 | 1249 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1250 | break; |
1251 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1252 | { |
a470d443 | 1253 | found = 1; |
df7492f9 | 1254 | continue; |
aa72b389 | 1255 | } |
df7492f9 | 1256 | ONE_MORE_BYTE (c2); |
065e3595 | 1257 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1258 | break; |
1259 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1260 | { |
a470d443 KH |
1261 | found = 1; |
1262 | if (src_base == coding->source | |
1263 | && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3) | |
1264 | bom_found = 1; | |
df7492f9 | 1265 | continue; |
aa72b389 | 1266 | } |
df7492f9 | 1267 | ONE_MORE_BYTE (c3); |
065e3595 | 1268 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1269 | break; |
1270 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1271 | { |
a470d443 | 1272 | found = 1; |
df7492f9 KH |
1273 | continue; |
1274 | } | |
1275 | ONE_MORE_BYTE (c4); | |
065e3595 | 1276 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1277 | break; |
1278 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1279 | { | |
a470d443 | 1280 | found = 1; |
df7492f9 KH |
1281 | continue; |
1282 | } | |
1283 | break; | |
aa72b389 | 1284 | } |
ff0dacd7 | 1285 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1286 | return 0; |
aa72b389 | 1287 | |
df7492f9 | 1288 | no_more_source: |
065e3595 | 1289 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1290 | { |
ff0dacd7 | 1291 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1292 | return 0; |
aa72b389 | 1293 | } |
a470d443 KH |
1294 | if (bom_found) |
1295 | { | |
1296 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
1297 | detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; | |
1298 | } | |
1299 | else | |
1300 | { | |
1301 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
0e17387a KH |
1302 | if (found) |
1303 | detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1304 | } |
ff0dacd7 | 1305 | return 1; |
aa72b389 KH |
1306 | } |
1307 | ||
4ed46869 | 1308 | |
b73bfc1c | 1309 | static void |
971de7fb | 1310 | decode_coding_utf_8 (struct coding_system *coding) |
b73bfc1c | 1311 | { |
8f924df7 KH |
1312 | const unsigned char *src = coding->source + coding->consumed; |
1313 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1314 | const unsigned char *src_base; | |
69a80ea3 KH |
1315 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1316 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
453b38f0 | 1317 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1318 | int multibytep = coding->src_multibyte; |
a470d443 | 1319 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
24a73b0a | 1320 | Lisp_Object attr, charset_list; |
0a9564cb EZ |
1321 | int eol_crlf = |
1322 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1323 | int byte_after_cr = -1; |
4ed46869 | 1324 | |
24a73b0a | 1325 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1326 | |
a470d443 KH |
1327 | if (bom != utf_without_bom) |
1328 | { | |
1329 | int c1, c2, c3; | |
1330 | ||
1331 | src_base = src; | |
1332 | ONE_MORE_BYTE (c1); | |
1333 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1334 | src = src_base; | |
1335 | else | |
1336 | { | |
159bd5a2 | 1337 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1338 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1339 | src = src_base; | |
1340 | else | |
1341 | { | |
159bd5a2 | 1342 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1343 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1344 | src = src_base; | |
1345 | else | |
1346 | { | |
1347 | if ((c1 != UTF_8_BOM_1) | |
1348 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1349 | src = src_base; | |
1350 | else | |
1351 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1352 | } | |
1353 | } | |
1354 | } | |
1355 | } | |
1356 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1357 | ||
df7492f9 | 1358 | while (1) |
b73bfc1c | 1359 | { |
df7492f9 | 1360 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1361 | |
df7492f9 KH |
1362 | src_base = src; |
1363 | consumed_chars_base = consumed_chars; | |
4af310db | 1364 | |
df7492f9 | 1365 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1366 | { |
1367 | if (byte_after_cr >= 0) | |
1368 | src_base--; | |
1369 | break; | |
1370 | } | |
df7492f9 | 1371 | |
119852e7 KH |
1372 | if (byte_after_cr >= 0) |
1373 | c1 = byte_after_cr, byte_after_cr = -1; | |
1374 | else | |
1375 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1376 | if (c1 < 0) |
1377 | { | |
1378 | c = - c1; | |
1379 | } | |
1a4990fb | 1380 | else if (UTF_8_1_OCTET_P (c1)) |
df7492f9 | 1381 | { |
119852e7 KH |
1382 | if (eol_crlf && c1 == '\r') |
1383 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 | 1384 | c = c1; |
4af310db | 1385 | } |
df7492f9 | 1386 | else |
4af310db | 1387 | { |
df7492f9 | 1388 | ONE_MORE_BYTE (c2); |
065e3595 | 1389 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1390 | goto invalid_code; |
1391 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1392 | { |
b0edb2c5 DL |
1393 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1394 | /* Reject overlong sequences here and below. Encoders | |
1395 | producing them are incorrect, they can be misleading, | |
1396 | and they mess up read/write invariance. */ | |
1397 | if (c < 128) | |
1398 | goto invalid_code; | |
4af310db | 1399 | } |
df7492f9 | 1400 | else |
aa72b389 | 1401 | { |
df7492f9 | 1402 | ONE_MORE_BYTE (c3); |
065e3595 | 1403 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1404 | goto invalid_code; |
1405 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1406 | { |
1407 | c = (((c1 & 0xF) << 12) | |
1408 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1409 | if (c < 0x800 |
1410 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1411 | goto invalid_code; |
1412 | } | |
df7492f9 KH |
1413 | else |
1414 | { | |
1415 | ONE_MORE_BYTE (c4); | |
065e3595 | 1416 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1417 | goto invalid_code; |
1418 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1419 | { |
df7492f9 KH |
1420 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1421 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1422 | if (c < 0x10000) |
1423 | goto invalid_code; | |
1424 | } | |
df7492f9 KH |
1425 | else |
1426 | { | |
1427 | ONE_MORE_BYTE (c5); | |
065e3595 | 1428 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1429 | goto invalid_code; |
1430 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1431 | { | |
1432 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1433 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1434 | | (c5 & 0x3F)); | |
b0edb2c5 | 1435 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1436 | goto invalid_code; |
1437 | } | |
1438 | else | |
1439 | goto invalid_code; | |
1440 | } | |
1441 | } | |
aa72b389 | 1442 | } |
b73bfc1c | 1443 | } |
df7492f9 KH |
1444 | |
1445 | *charbuf++ = c; | |
1446 | continue; | |
1447 | ||
1448 | invalid_code: | |
1449 | src = src_base; | |
1450 | consumed_chars = consumed_chars_base; | |
1451 | ONE_MORE_BYTE (c); | |
1452 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1453 | coding->errors++; | |
aa72b389 KH |
1454 | } |
1455 | ||
df7492f9 KH |
1456 | no_more_source: |
1457 | coding->consumed_char += consumed_chars_base; | |
1458 | coding->consumed = src_base - coding->source; | |
1459 | coding->charbuf_used = charbuf - coding->charbuf; | |
1460 | } | |
1461 | ||
1462 | ||
1463 | static int | |
971de7fb | 1464 | encode_coding_utf_8 (struct coding_system *coding) |
df7492f9 KH |
1465 | { |
1466 | int multibytep = coding->dst_multibyte; | |
1467 | int *charbuf = coding->charbuf; | |
1468 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1469 | unsigned char *dst = coding->destination + coding->produced; | |
1470 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
e19c3639 | 1471 | int produced_chars = 0; |
df7492f9 KH |
1472 | int c; |
1473 | ||
a470d443 KH |
1474 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1475 | { | |
1476 | ASSURE_DESTINATION (3); | |
1477 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1478 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1479 | } | |
1480 | ||
df7492f9 | 1481 | if (multibytep) |
aa72b389 | 1482 | { |
df7492f9 KH |
1483 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1484 | ||
1485 | while (charbuf < charbuf_end) | |
b73bfc1c | 1486 | { |
df7492f9 | 1487 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1488 | |
df7492f9 KH |
1489 | ASSURE_DESTINATION (safe_room); |
1490 | c = *charbuf++; | |
28f67a95 KH |
1491 | if (CHAR_BYTE8_P (c)) |
1492 | { | |
1493 | c = CHAR_TO_BYTE8 (c); | |
1494 | EMIT_ONE_BYTE (c); | |
1495 | } | |
1496 | else | |
1497 | { | |
db274c7a | 1498 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1499 | for (p = str; p < pend; p++) |
1500 | EMIT_ONE_BYTE (*p); | |
1501 | } | |
b73bfc1c | 1502 | } |
aa72b389 | 1503 | } |
df7492f9 KH |
1504 | else |
1505 | { | |
1506 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1507 | ||
1508 | while (charbuf < charbuf_end) | |
b73bfc1c | 1509 | { |
df7492f9 KH |
1510 | ASSURE_DESTINATION (safe_room); |
1511 | c = *charbuf++; | |
f03caae0 KH |
1512 | if (CHAR_BYTE8_P (c)) |
1513 | *dst++ = CHAR_TO_BYTE8 (c); | |
1514 | else | |
db274c7a | 1515 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1516 | produced_chars++; |
4ed46869 KH |
1517 | } |
1518 | } | |
065e3595 | 1519 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1520 | coding->produced_char += produced_chars; |
1521 | coding->produced = dst - coding->destination; | |
1522 | return 0; | |
4ed46869 KH |
1523 | } |
1524 | ||
b73bfc1c | 1525 | |
df7492f9 | 1526 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ff0dacd7 KH |
1527 | Check if a text is encoded in one of UTF-16 based coding systems. |
1528 | If it is, return 1, else return 0. */ | |
aa72b389 | 1529 | |
df7492f9 KH |
1530 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1531 | (((val) & 0xFC00) == 0xD800) | |
1532 | ||
1533 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1534 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1535 | |
df7492f9 KH |
1536 | #define UTF_16_INVALID_P(val) \ |
1537 | (((val) == 0xFFFE) \ | |
1538 | || ((val) == 0xFFFF) \ | |
1539 | || UTF_16_LOW_SURROGATE_P (val)) | |
aa72b389 | 1540 | |
aa72b389 | 1541 | |
df7492f9 | 1542 | static int |
cf84bb53 JB |
1543 | detect_coding_utf_16 (struct coding_system *coding, |
1544 | struct coding_detection_info *detect_info) | |
aa72b389 | 1545 | { |
ef1b0ba7 | 1546 | const unsigned char *src = coding->source; |
8f924df7 | 1547 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 | 1548 | int multibytep = coding->src_multibyte; |
df7492f9 | 1549 | int c1, c2; |
aa72b389 | 1550 | |
ff0dacd7 | 1551 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1552 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1553 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1554 | { |
1555 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1556 | return 0; | |
1557 | } | |
24a73b0a | 1558 | |
f56a4450 | 1559 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1560 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1561 | { |
b49a1807 KH |
1562 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1563 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1564 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1565 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1566 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1567 | } |
df7492f9 | 1568 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1569 | { |
b49a1807 KH |
1570 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1571 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1572 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1573 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1574 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1575 | } | |
220eeac9 | 1576 | else if (c2 < 0) |
f56a4450 KH |
1577 | { |
1578 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1579 | return 0; | |
1580 | } | |
2f3cbb32 | 1581 | else |
24a73b0a | 1582 | { |
2f3cbb32 KH |
1583 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1584 | O is odd. If both are high, we assume binary data.*/ | |
1585 | unsigned char e[256], o[256]; | |
1586 | unsigned e_num = 1, o_num = 1; | |
1587 | ||
1588 | memset (e, 0, 256); | |
1589 | memset (o, 0, 256); | |
1590 | e[c1] = 1; | |
1591 | o[c2] = 1; | |
1592 | ||
cc13543e KH |
1593 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO |
1594 | |CATEGORY_MASK_UTF_16_BE | |
1595 | | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 | 1596 | |
7f1faf1c KH |
1597 | while ((detect_info->rejected & CATEGORY_MASK_UTF_16) |
1598 | != CATEGORY_MASK_UTF_16) | |
2f3cbb32 | 1599 | { |
f56a4450 | 1600 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1601 | if (c2 < 0) |
f56a4450 | 1602 | break; |
2f3cbb32 KH |
1603 | if (! e[c1]) |
1604 | { | |
1605 | e[c1] = 1; | |
1606 | e_num++; | |
cc13543e KH |
1607 | if (e_num >= 128) |
1608 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
2f3cbb32 KH |
1609 | } |
1610 | if (! o[c2]) | |
1611 | { | |
977b85f4 | 1612 | o[c2] = 1; |
2f3cbb32 | 1613 | o_num++; |
cc13543e KH |
1614 | if (o_num >= 128) |
1615 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
2f3cbb32 KH |
1616 | } |
1617 | } | |
2f3cbb32 | 1618 | return 0; |
ff0dacd7 | 1619 | } |
2f3cbb32 | 1620 | |
df7492f9 | 1621 | no_more_source: |
ff0dacd7 | 1622 | return 1; |
df7492f9 | 1623 | } |
aa72b389 | 1624 | |
df7492f9 | 1625 | static void |
971de7fb | 1626 | decode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1627 | { |
8f924df7 KH |
1628 | const unsigned char *src = coding->source + coding->consumed; |
1629 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1630 | const unsigned char *src_base; | |
69a80ea3 | 1631 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
1632 | /* We may produces at most 3 chars in one loop. */ |
1633 | int *charbuf_end = coding->charbuf + coding->charbuf_size - 2; | |
3a8406e1 | 1634 | int consumed_chars = 0, consumed_chars_base = 0; |
df7492f9 | 1635 | int multibytep = coding->src_multibyte; |
a470d443 | 1636 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1637 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1638 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
24a73b0a | 1639 | Lisp_Object attr, charset_list; |
0a9564cb EZ |
1640 | int eol_crlf = |
1641 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1642 | int byte_after_cr1 = -1, byte_after_cr2 = -1; |
df7492f9 | 1643 | |
24a73b0a | 1644 | CODING_GET_INFO (coding, attr, charset_list); |
df7492f9 | 1645 | |
a470d443 | 1646 | if (bom == utf_with_bom) |
aa72b389 | 1647 | { |
df7492f9 | 1648 | int c, c1, c2; |
4af310db | 1649 | |
aa72b389 | 1650 | src_base = src; |
df7492f9 KH |
1651 | ONE_MORE_BYTE (c1); |
1652 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1653 | c = (c1 << 8) | c2; |
aa72b389 | 1654 | |
b49a1807 KH |
1655 | if (endian == utf_16_big_endian |
1656 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1657 | { |
b49a1807 KH |
1658 | /* The first two bytes are not BOM. Treat them as bytes |
1659 | for a normal character. */ | |
1660 | src = src_base; | |
1661 | coding->errors++; | |
aa72b389 | 1662 | } |
a470d443 | 1663 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1664 | } |
a470d443 | 1665 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1666 | { |
1667 | /* We have already tried to detect BOM and failed in | |
1668 | detect_coding. */ | |
a470d443 | 1669 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1670 | } |
aa72b389 | 1671 | |
df7492f9 KH |
1672 | while (1) |
1673 | { | |
1674 | int c, c1, c2; | |
1675 | ||
1676 | src_base = src; | |
1677 | consumed_chars_base = consumed_chars; | |
1678 | ||
df80c7f0 | 1679 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1680 | { |
1681 | if (byte_after_cr1 >= 0) | |
1682 | src_base -= 2; | |
1683 | break; | |
1684 | } | |
df7492f9 | 1685 | |
119852e7 KH |
1686 | if (byte_after_cr1 >= 0) |
1687 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1688 | else | |
1689 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1690 | if (c1 < 0) |
1691 | { | |
1692 | *charbuf++ = -c1; | |
1693 | continue; | |
1694 | } | |
119852e7 KH |
1695 | if (byte_after_cr2 >= 0) |
1696 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1697 | else | |
1698 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1699 | if (c2 < 0) |
1700 | { | |
1701 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1702 | *charbuf++ = -c2; | |
1703 | continue; | |
1704 | } | |
df7492f9 | 1705 | c = (endian == utf_16_big_endian |
e19c3639 | 1706 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1707 | |
df7492f9 | 1708 | if (surrogate) |
fd3ae0b9 | 1709 | { |
df7492f9 | 1710 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1711 | { |
df7492f9 KH |
1712 | if (endian == utf_16_big_endian) |
1713 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1714 | else | |
1715 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1716 | *charbuf++ = c1; | |
1717 | *charbuf++ = c2; | |
1718 | coding->errors++; | |
1719 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1720 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1721 | else |
df7492f9 | 1722 | *charbuf++ = c; |
fd3ae0b9 KH |
1723 | } |
1724 | else | |
df7492f9 KH |
1725 | { |
1726 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1727 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1728 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1729 | } |
fd3ae0b9 | 1730 | } |
aa72b389 | 1731 | else |
df7492f9 KH |
1732 | { |
1733 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1734 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1735 | else | |
119852e7 KH |
1736 | { |
1737 | if (eol_crlf && c == '\r') | |
1738 | { | |
1739 | ONE_MORE_BYTE (byte_after_cr1); | |
1740 | ONE_MORE_BYTE (byte_after_cr2); | |
1741 | } | |
1742 | *charbuf++ = c; | |
1743 | } | |
8f924df7 | 1744 | } |
aa72b389 | 1745 | } |
df7492f9 KH |
1746 | |
1747 | no_more_source: | |
1748 | coding->consumed_char += consumed_chars_base; | |
1749 | coding->consumed = src_base - coding->source; | |
1750 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1751 | } |
b73bfc1c | 1752 | |
df7492f9 | 1753 | static int |
971de7fb | 1754 | encode_coding_utf_16 (struct coding_system *coding) |
df7492f9 KH |
1755 | { |
1756 | int multibytep = coding->dst_multibyte; | |
1757 | int *charbuf = coding->charbuf; | |
1758 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1759 | unsigned char *dst = coding->destination + coding->produced; | |
1760 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1761 | int safe_room = 8; | |
a470d443 | 1762 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1763 | int big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
1764 | int produced_chars = 0; | |
24a73b0a | 1765 | Lisp_Object attrs, charset_list; |
df7492f9 | 1766 | int c; |
4ed46869 | 1767 | |
24a73b0a | 1768 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 1769 | |
a470d443 | 1770 | if (bom != utf_without_bom) |
df7492f9 KH |
1771 | { |
1772 | ASSURE_DESTINATION (safe_room); | |
1773 | if (big_endian) | |
df7492f9 | 1774 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1775 | else |
1776 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1777 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1778 | } |
1779 | ||
1780 | while (charbuf < charbuf_end) | |
1781 | { | |
1782 | ASSURE_DESTINATION (safe_room); | |
1783 | c = *charbuf++; | |
60afa08d | 1784 | if (c > MAX_UNICODE_CHAR) |
e19c3639 | 1785 | c = coding->default_char; |
df7492f9 KH |
1786 | |
1787 | if (c < 0x10000) | |
1788 | { | |
1789 | if (big_endian) | |
1790 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1791 | else | |
1792 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1793 | } | |
1794 | else | |
1795 | { | |
1796 | int c1, c2; | |
1797 | ||
1798 | c -= 0x10000; | |
1799 | c1 = (c >> 10) + 0xD800; | |
1800 | c2 = (c & 0x3FF) + 0xDC00; | |
1801 | if (big_endian) | |
1802 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1803 | else | |
1804 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1805 | } | |
1806 | } | |
065e3595 | 1807 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1808 | coding->produced = dst - coding->destination; |
1809 | coding->produced_char += produced_chars; | |
1810 | return 0; | |
1811 | } | |
1812 | ||
1813 | \f | |
1814 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1815 | ||
1816 | /* Emacs' internal format for representation of multiple character | |
1817 | sets is a kind of multi-byte encoding, i.e. characters are | |
1818 | represented by variable-length sequences of one-byte codes. | |
1819 | ||
1820 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1821 | represented by one-byte sequences which are their ASCII codes, in | |
1822 | the range 0x00 through 0x7F. | |
1823 | ||
1824 | 8-bit characters of the range 0x80..0x9F are represented by | |
1825 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1826 | code + 0x20). | |
1827 | ||
1828 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1829 | one-byte sequences which are their 8-bit code. | |
1830 | ||
1831 | The other characters are represented by a sequence of `base | |
1832 | leading-code', optional `extended leading-code', and one or two | |
1833 | `position-code's. The length of the sequence is determined by the | |
1834 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1835 | whereas extended leading-code and position-code take the range 0xA0 | |
1836 | through 0xFF. See `charset.h' for more details about leading-code | |
1837 | and position-code. | |
1838 | ||
1839 | --- CODE RANGE of Emacs' internal format --- | |
1840 | character set range | |
1841 | ------------- ----- | |
1842 | ascii 0x00..0x7F | |
1843 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1844 | eight-bit-graphic 0xA0..0xBF | |
1845 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1846 | --------------------------------------------- | |
1847 | ||
1848 | As this is the internal character representation, the format is | |
1849 | usually not used externally (i.e. in a file or in a data sent to a | |
1850 | process). But, it is possible to have a text externally in this | |
1851 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1852 | ||
1853 | In that case, a sequence of one-byte codes has a slightly different | |
1854 | form. | |
1855 | ||
1856 | At first, all characters in eight-bit-control are represented by | |
1857 | one-byte sequences which are their 8-bit code. | |
1858 | ||
1859 | Next, character composition data are represented by the byte | |
1860 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1861 | where, | |
e951386e | 1862 | METHOD is 0xF2 plus one of composition method (enum |
df7492f9 KH |
1863 | composition_method), |
1864 | ||
1865 | BYTES is 0xA0 plus a byte length of this composition data, | |
1866 | ||
e951386e | 1867 | CHARS is 0xA0 plus a number of characters composed by this |
df7492f9 KH |
1868 | data, |
1869 | ||
ad1746f5 | 1870 | COMPONENTs are characters of multibyte form or composition |
df7492f9 KH |
1871 | rules encoded by two-byte of ASCII codes. |
1872 | ||
1873 | In addition, for backward compatibility, the following formats are | |
1874 | also recognized as composition data on decoding. | |
1875 | ||
1876 | 0x80 MSEQ ... | |
1877 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1878 | ||
1879 | Here, | |
1880 | MSEQ is a multibyte form but in these special format: | |
1881 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1882 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1883 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1884 | represents a composition rule. | |
1885 | */ | |
1886 | ||
1887 | char emacs_mule_bytes[256]; | |
1888 | ||
e951386e KH |
1889 | |
1890 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
1891 | Check if a text is encoded in `emacs-mule'. If it is, return 1, | |
1892 | else return 0. */ | |
1893 | ||
1894 | static int | |
cf84bb53 JB |
1895 | detect_coding_emacs_mule (struct coding_system *coding, |
1896 | struct coding_detection_info *detect_info) | |
e951386e KH |
1897 | { |
1898 | const unsigned char *src = coding->source, *src_base; | |
1899 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1900 | int multibytep = coding->src_multibyte; | |
1901 | int consumed_chars = 0; | |
1902 | int c; | |
1903 | int found = 0; | |
1904 | ||
1905 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | |
1906 | /* A coding system of this category is always ASCII compatible. */ | |
1907 | src += coding->head_ascii; | |
1908 | ||
1909 | while (1) | |
1910 | { | |
1911 | src_base = src; | |
1912 | ONE_MORE_BYTE (c); | |
1913 | if (c < 0) | |
1914 | continue; | |
1915 | if (c == 0x80) | |
1916 | { | |
1917 | /* Perhaps the start of composite character. We simply skip | |
1918 | it because analyzing it is too heavy for detecting. But, | |
1919 | at least, we check that the composite character | |
1920 | constitutes of more than 4 bytes. */ | |
1921 | const unsigned char *src_base; | |
1922 | ||
1923 | repeat: | |
1924 | src_base = src; | |
1925 | do | |
1926 | { | |
1927 | ONE_MORE_BYTE (c); | |
1928 | } | |
1929 | while (c >= 0xA0); | |
1930 | ||
1931 | if (src - src_base <= 4) | |
1932 | break; | |
1933 | found = CATEGORY_MASK_EMACS_MULE; | |
1934 | if (c == 0x80) | |
1935 | goto repeat; | |
1936 | } | |
1937 | ||
1938 | if (c < 0x80) | |
1939 | { | |
1940 | if (c < 0x20 | |
1941 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1942 | break; | |
1943 | } | |
1944 | else | |
1945 | { | |
396475b7 | 1946 | int more_bytes = emacs_mule_bytes[c] - 1; |
e951386e KH |
1947 | |
1948 | while (more_bytes > 0) | |
1949 | { | |
1950 | ONE_MORE_BYTE (c); | |
1951 | if (c < 0xA0) | |
1952 | { | |
1953 | src--; /* Unread the last byte. */ | |
1954 | break; | |
1955 | } | |
1956 | more_bytes--; | |
1957 | } | |
1958 | if (more_bytes != 0) | |
1959 | break; | |
1960 | found = CATEGORY_MASK_EMACS_MULE; | |
1961 | } | |
1962 | } | |
1963 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1964 | return 0; | |
1965 | ||
1966 | no_more_source: | |
1967 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | |
1968 | { | |
1969 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1970 | return 0; | |
1971 | } | |
1972 | detect_info->found |= found; | |
1973 | return 1; | |
1974 | } | |
1975 | ||
1976 | ||
1977 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | |
1978 | character. If CMP_STATUS indicates that we must expect MSEQ or | |
1979 | RULE described above, decode it and return the negative value of | |
685ebdc8 | 1980 | the decoded character or rule. If an invalid byte is found, return |
e951386e KH |
1981 | -1. If SRC is too short, return -2. */ |
1982 | ||
df7492f9 | 1983 | int |
cf84bb53 JB |
1984 | emacs_mule_char (struct coding_system *coding, const unsigned char *src, |
1985 | int *nbytes, int *nchars, int *id, | |
1986 | struct composition_status *cmp_status) | |
df7492f9 | 1987 | { |
8f924df7 KH |
1988 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1989 | const unsigned char *src_base = src; | |
df7492f9 | 1990 | int multibytep = coding->src_multibyte; |
b84ae584 | 1991 | int charset_id; |
df7492f9 KH |
1992 | unsigned code; |
1993 | int c; | |
1994 | int consumed_chars = 0; | |
e951386e | 1995 | int mseq_found = 0; |
df7492f9 KH |
1996 | |
1997 | ONE_MORE_BYTE (c); | |
065e3595 | 1998 | if (c < 0) |
df7492f9 | 1999 | { |
065e3595 | 2000 | c = -c; |
b84ae584 | 2001 | charset_id = emacs_mule_charset[0]; |
065e3595 KH |
2002 | } |
2003 | else | |
2004 | { | |
4d41e8b7 KH |
2005 | if (c >= 0xA0) |
2006 | { | |
e951386e KH |
2007 | if (cmp_status->state != COMPOSING_NO |
2008 | && cmp_status->old_form) | |
4d41e8b7 | 2009 | { |
e951386e KH |
2010 | if (cmp_status->state == COMPOSING_CHAR) |
2011 | { | |
2012 | if (c == 0xA0) | |
2013 | { | |
2014 | ONE_MORE_BYTE (c); | |
2015 | c -= 0x80; | |
2016 | if (c < 0) | |
2017 | goto invalid_code; | |
2018 | } | |
2019 | else | |
2020 | c -= 0x20; | |
2021 | mseq_found = 1; | |
2022 | } | |
2023 | else | |
2024 | { | |
2025 | *nbytes = src - src_base; | |
2026 | *nchars = consumed_chars; | |
2027 | return -c; | |
2028 | } | |
4d41e8b7 KH |
2029 | } |
2030 | else | |
e951386e | 2031 | goto invalid_code; |
4d41e8b7 KH |
2032 | } |
2033 | ||
065e3595 | 2034 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 2035 | { |
065e3595 | 2036 | case 2: |
b84ae584 | 2037 | if ((charset_id = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
2038 | goto invalid_code; |
2039 | ONE_MORE_BYTE (c); | |
9ffd559c | 2040 | if (c < 0xA0) |
065e3595 | 2041 | goto invalid_code; |
df7492f9 | 2042 | code = c & 0x7F; |
065e3595 KH |
2043 | break; |
2044 | ||
2045 | case 3: | |
2046 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
2047 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
2048 | { | |
2049 | ONE_MORE_BYTE (c); | |
b84ae584 | 2050 | if (c < 0xA0 || (charset_id = emacs_mule_charset[c]) < 0) |
065e3595 KH |
2051 | goto invalid_code; |
2052 | ONE_MORE_BYTE (c); | |
9ffd559c | 2053 | if (c < 0xA0) |
065e3595 KH |
2054 | goto invalid_code; |
2055 | code = c & 0x7F; | |
2056 | } | |
2057 | else | |
2058 | { | |
b84ae584 | 2059 | if ((charset_id = emacs_mule_charset[c]) < 0) |
065e3595 KH |
2060 | goto invalid_code; |
2061 | ONE_MORE_BYTE (c); | |
9ffd559c | 2062 | if (c < 0xA0) |
065e3595 KH |
2063 | goto invalid_code; |
2064 | code = (c & 0x7F) << 8; | |
2065 | ONE_MORE_BYTE (c); | |
9ffd559c | 2066 | if (c < 0xA0) |
065e3595 KH |
2067 | goto invalid_code; |
2068 | code |= c & 0x7F; | |
2069 | } | |
2070 | break; | |
2071 | ||
2072 | case 4: | |
2073 | ONE_MORE_BYTE (c); | |
b84ae584 | 2074 | if (c < 0 || (charset_id = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
2075 | goto invalid_code; |
2076 | ONE_MORE_BYTE (c); | |
9ffd559c | 2077 | if (c < 0xA0) |
065e3595 | 2078 | goto invalid_code; |
781d7a48 | 2079 | code = (c & 0x7F) << 8; |
df7492f9 | 2080 | ONE_MORE_BYTE (c); |
9ffd559c | 2081 | if (c < 0xA0) |
065e3595 | 2082 | goto invalid_code; |
df7492f9 | 2083 | code |= c & 0x7F; |
065e3595 | 2084 | break; |
df7492f9 | 2085 | |
065e3595 KH |
2086 | case 1: |
2087 | code = c; | |
b84ae584 | 2088 | charset_id = ASCII_BYTE_P (code) ? charset_ascii : charset_eight_bit; |
065e3595 | 2089 | break; |
df7492f9 | 2090 | |
065e3595 KH |
2091 | default: |
2092 | abort (); | |
2093 | } | |
b84ae584 KH |
2094 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
2095 | CHARSET_FROM_ID (charset_id), code, c); | |
065e3595 KH |
2096 | if (c < 0) |
2097 | goto invalid_code; | |
df7492f9 | 2098 | } |
df7492f9 KH |
2099 | *nbytes = src - src_base; |
2100 | *nchars = consumed_chars; | |
ff0dacd7 | 2101 | if (id) |
b84ae584 | 2102 | *id = charset_id; |
e951386e | 2103 | return (mseq_found ? -c : c); |
df7492f9 KH |
2104 | |
2105 | no_more_source: | |
2106 | return -2; | |
2107 | ||
2108 | invalid_code: | |
2109 | return -1; | |
2110 | } | |
2111 | ||
2112 | ||
e951386e | 2113 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
df7492f9 | 2114 | |
e951386e KH |
2115 | /* Handle these composition sequence ('|': the end of header elements, |
2116 | BYTES and CHARS >= 0xA0): | |
df7492f9 | 2117 | |
e951386e KH |
2118 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
2119 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... | |
2120 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... | |
df7492f9 | 2121 | |
e951386e | 2122 | and these old form: |
1a4990fb | 2123 | |
e951386e KH |
2124 | (4) relative composition: 0x80 | MSEQ ... MSEQ |
2125 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ | |
df7492f9 | 2126 | |
e951386e KH |
2127 | When the starter 0x80 and the following header elements are found, |
2128 | this annotation header is produced. | |
df7492f9 | 2129 | |
e951386e | 2130 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
df7492f9 | 2131 | |
e951386e KH |
2132 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
2133 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). | |
df7492f9 | 2134 | |
e951386e KH |
2135 | Then, upon reading the following elements, these codes are produced |
2136 | until the composition end is found: | |
df7492f9 | 2137 | |
e951386e KH |
2138 | (1) CHAR ... CHAR |
2139 | (2) ALT ... ALT CHAR ... CHAR | |
2140 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR | |
2141 | (4) CHAR ... CHAR | |
2142 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
4ed46869 | 2143 | |
e951386e KH |
2144 | When the composition end is found, LENGTH and NCHARS in the |
2145 | annotation header is updated as below: | |
b73bfc1c | 2146 | |
e951386e KH |
2147 | (1) LENGTH: unchanged, NCHARS: unchanged |
2148 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2149 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2150 | (4) LENGTH: unchanged, NCHARS: number of CHARs | |
2151 | (5) LENGTH: unchanged, NCHARS: number of CHARs | |
df7492f9 | 2152 | |
e951386e KH |
2153 | If an error is found while composing, the annotation header is |
2154 | changed to the original composition header (plus filler -1s) as | |
2155 | below: | |
2156 | ||
2157 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] | |
2158 | (5) [ 0x80 0xFF -1 -1- -1 ] | |
2159 | ||
2160 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
2161 | byte sequence as below: | |
2162 | o the original byte sequence is B: [ B -1 ] | |
2163 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
2164 | ||
2165 | Most of the routines are implemented by macros because many | |
2166 | variables and labels in the caller decode_coding_emacs_mule must be | |
2167 | accessible, and they are usually called just once (thus doesn't | |
2168 | increase the size of compiled object). */ | |
2169 | ||
2170 | /* Decode a composition rule represented by C as a component of | |
2171 | composition sequence of Emacs 20 style. Set RULE to the decoded | |
2172 | rule. */ | |
2173 | ||
2174 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ | |
df7492f9 | 2175 | do { \ |
e951386e KH |
2176 | int gref, nref; \ |
2177 | \ | |
4d41e8b7 | 2178 | c -= 0xA0; \ |
df7492f9 KH |
2179 | if (c < 0 || c >= 81) \ |
2180 | goto invalid_code; \ | |
df7492f9 | 2181 | gref = c / 9, nref = c % 9; \ |
e951386e KH |
2182 | if (gref == 4) gref = 10; \ |
2183 | if (nref == 4) nref = 10; \ | |
2184 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
df7492f9 KH |
2185 | } while (0) |
2186 | ||
2187 | ||
e951386e KH |
2188 | /* Decode a composition rule represented by C and the following byte |
2189 | at SRC as a component of composition sequence of Emacs 21 style. | |
2190 | Set RULE to the decoded rule. */ | |
781d7a48 | 2191 | |
e951386e | 2192 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
781d7a48 KH |
2193 | do { \ |
2194 | int gref, nref; \ | |
e951386e KH |
2195 | \ |
2196 | gref = c - 0x20; \ | |
2197 | if (gref < 0 || gref >= 81) \ | |
781d7a48 | 2198 | goto invalid_code; \ |
e951386e KH |
2199 | ONE_MORE_BYTE (c); \ |
2200 | nref = c - 0x20; \ | |
2201 | if (nref < 0 || nref >= 81) \ | |
781d7a48 | 2202 | goto invalid_code; \ |
e951386e | 2203 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
781d7a48 KH |
2204 | } while (0) |
2205 | ||
2206 | ||
e951386e KH |
2207 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
2208 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | |
2209 | byte length of this composition information, CHARS is the number of | |
2210 | characters composed by this composition. */ | |
2211 | ||
2212 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | |
aa72b389 | 2213 | do { \ |
781d7a48 | 2214 | enum composition_method method = c - 0xF2; \ |
df7492f9 | 2215 | int nbytes, nchars; \ |
e951386e | 2216 | \ |
df7492f9 | 2217 | ONE_MORE_BYTE (c); \ |
065e3595 KH |
2218 | if (c < 0) \ |
2219 | goto invalid_code; \ | |
df7492f9 | 2220 | nbytes = c - 0xA0; \ |
e951386e | 2221 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
df7492f9 KH |
2222 | goto invalid_code; \ |
2223 | ONE_MORE_BYTE (c); \ | |
2224 | nchars = c - 0xA0; \ | |
e951386e KH |
2225 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
2226 | goto invalid_code; \ | |
2227 | cmp_status->old_form = 0; \ | |
2228 | cmp_status->method = method; \ | |
2229 | if (method == COMPOSITION_RELATIVE) \ | |
2230 | cmp_status->state = COMPOSING_CHAR; \ | |
2231 | else \ | |
2232 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ | |
2233 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2234 | cmp_status->nchars = nchars; \ | |
2235 | cmp_status->ncomps = nbytes - 4; \ | |
2236 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ | |
aa72b389 | 2237 | } while (0) |
93dec019 | 2238 | |
aa72b389 | 2239 | |
e951386e KH |
2240 | /* Start of Emacs 20 style format for relative composition. */ |
2241 | ||
2242 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ | |
2243 | do { \ | |
2244 | cmp_status->old_form = 1; \ | |
2245 | cmp_status->method = COMPOSITION_RELATIVE; \ | |
2246 | cmp_status->state = COMPOSING_CHAR; \ | |
2247 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2248 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2249 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
2250 | } while (0) | |
2251 | ||
2252 | ||
2253 | /* Start of Emacs 20 style format for rule-base composition. */ | |
2254 | ||
2255 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | |
2256 | do { \ | |
2257 | cmp_status->old_form = 1; \ | |
2258 | cmp_status->method = COMPOSITION_WITH_RULE; \ | |
2259 | cmp_status->state = COMPOSING_CHAR; \ | |
2260 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2261 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2262 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
df7492f9 KH |
2263 | } while (0) |
2264 | ||
2265 | ||
e951386e KH |
2266 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ |
2267 | do { \ | |
2268 | const unsigned char *current_src = src; \ | |
2269 | \ | |
2270 | ONE_MORE_BYTE (c); \ | |
2271 | if (c < 0) \ | |
2272 | goto invalid_code; \ | |
2273 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | |
2274 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | |
2275 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | |
2276 | else if (c < 0xA0) \ | |
2277 | goto invalid_code; \ | |
2278 | else if (c < 0xC0) \ | |
2279 | { \ | |
2280 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | |
2281 | /* Re-read C as a composition component. */ \ | |
2282 | src = current_src; \ | |
2283 | } \ | |
2284 | else if (c == 0xFF) \ | |
2285 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | |
2286 | else \ | |
2287 | goto invalid_code; \ | |
2288 | } while (0) | |
2289 | ||
2290 | #define EMACS_MULE_COMPOSITION_END() \ | |
df7492f9 | 2291 | do { \ |
e951386e | 2292 | int idx = - cmp_status->length; \ |
4d41e8b7 | 2293 | \ |
e951386e KH |
2294 | if (cmp_status->old_form) \ |
2295 | charbuf[idx + 2] = cmp_status->nchars; \ | |
2296 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ | |
2297 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ | |
2298 | cmp_status->state = COMPOSING_NO; \ | |
2299 | } while (0) | |
2300 | ||
2301 | ||
2302 | static int | |
cf84bb53 JB |
2303 | emacs_mule_finish_composition (int *charbuf, |
2304 | struct composition_status *cmp_status) | |
e951386e KH |
2305 | { |
2306 | int idx = - cmp_status->length; | |
2307 | int new_chars; | |
2308 | ||
2309 | if (cmp_status->old_form && cmp_status->nchars > 0) | |
2310 | { | |
2311 | charbuf[idx + 2] = cmp_status->nchars; | |
2312 | new_chars = 0; | |
2313 | if (cmp_status->method == COMPOSITION_WITH_RULE | |
2314 | && cmp_status->state == COMPOSING_CHAR) | |
2315 | { | |
2316 | /* The last rule was invalid. */ | |
2317 | int rule = charbuf[-1] + 0xA0; | |
2318 | ||
2319 | charbuf[-2] = BYTE8_TO_CHAR (rule); | |
2320 | charbuf[-1] = -1; | |
2321 | new_chars = 1; | |
2322 | } | |
2323 | } | |
2324 | else | |
2325 | { | |
2326 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | |
2327 | ||
2328 | if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2329 | { | |
2330 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | |
2331 | charbuf[idx++] = -3; | |
2332 | charbuf[idx++] = 0; | |
2333 | new_chars = 1; | |
2334 | } | |
2335 | else | |
2336 | { | |
2337 | int nchars = charbuf[idx + 1] + 0xA0; | |
2338 | int nbytes = charbuf[idx + 2] + 0xA0; | |
2339 | ||
2340 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | |
2341 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | |
2342 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | |
2343 | charbuf[idx++] = -1; | |
2344 | new_chars = 4; | |
2345 | } | |
2346 | } | |
2347 | cmp_status->state = COMPOSING_NO; | |
2348 | return new_chars; | |
2349 | } | |
2350 | ||
2351 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | |
2352 | do { \ | |
2353 | if (cmp_status->state != COMPOSING_NO) \ | |
2354 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | |
df7492f9 KH |
2355 | } while (0) |
2356 | ||
aa72b389 KH |
2357 | |
2358 | static void | |
971de7fb | 2359 | decode_coding_emacs_mule (struct coding_system *coding) |
aa72b389 | 2360 | { |
8f924df7 KH |
2361 | const unsigned char *src = coding->source + coding->consumed; |
2362 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2363 | const unsigned char *src_base; | |
69a80ea3 | 2364 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
2365 | /* We may produce two annotations (charset and composition) in one |
2366 | loop and one more charset annotation at the end. */ | |
69a80ea3 | 2367 | int *charbuf_end |
df80c7f0 | 2368 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
df7492f9 | 2369 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 2370 | int multibytep = coding->src_multibyte; |
24a73b0a | 2371 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
2372 | int char_offset = coding->produced_char; |
2373 | int last_offset = char_offset; | |
2374 | int last_id = charset_ascii; | |
0a9564cb EZ |
2375 | int eol_crlf = |
2376 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 2377 | int byte_after_cr = -1; |
e951386e | 2378 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; |
aa72b389 | 2379 | |
24a73b0a | 2380 | CODING_GET_INFO (coding, attrs, charset_list); |
aa72b389 | 2381 | |
e951386e KH |
2382 | if (cmp_status->state != COMPOSING_NO) |
2383 | { | |
2384 | int i; | |
2385 | ||
2386 | for (i = 0; i < cmp_status->length; i++) | |
2387 | *charbuf++ = cmp_status->carryover[i]; | |
2388 | coding->annotated = 1; | |
2389 | } | |
2390 | ||
aa72b389 KH |
2391 | while (1) |
2392 | { | |
e951386e | 2393 | int c, id; |
df7492f9 | 2394 | |
aa72b389 | 2395 | src_base = src; |
df7492f9 KH |
2396 | consumed_chars_base = consumed_chars; |
2397 | ||
2398 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2399 | { |
2400 | if (byte_after_cr >= 0) | |
2401 | src_base--; | |
2402 | break; | |
2403 | } | |
aa72b389 | 2404 | |
119852e7 KH |
2405 | if (byte_after_cr >= 0) |
2406 | c = byte_after_cr, byte_after_cr = -1; | |
2407 | else | |
2408 | ONE_MORE_BYTE (c); | |
e951386e KH |
2409 | |
2410 | if (c < 0 || c == 0x80) | |
065e3595 | 2411 | { |
e951386e KH |
2412 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
2413 | if (c < 0) | |
2414 | { | |
2415 | *charbuf++ = -c; | |
2416 | char_offset++; | |
2417 | } | |
2418 | else | |
2419 | DECODE_EMACS_MULE_COMPOSITION_START (); | |
2420 | continue; | |
065e3595 | 2421 | } |
e951386e KH |
2422 | |
2423 | if (c < 0x80) | |
aa72b389 | 2424 | { |
119852e7 KH |
2425 | if (eol_crlf && c == '\r') |
2426 | ONE_MORE_BYTE (byte_after_cr); | |
e951386e KH |
2427 | id = charset_ascii; |
2428 | if (cmp_status->state != COMPOSING_NO) | |
2429 | { | |
2430 | if (cmp_status->old_form) | |
2431 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2432 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2433 | cmp_status->ncomps--; | |
2434 | } | |
2435 | } | |
2436 | else | |
2437 | { | |
2438 | int nchars, nbytes; | |
75f80e63 EZ |
2439 | /* emacs_mule_char can load a charset map from a file, which |
2440 | allocates a large structure and might cause buffer text | |
2441 | to be relocated as result. Thus, we need to remember the | |
ad1746f5 | 2442 | original pointer to buffer text, and fix up all related |
75f80e63 EZ |
2443 | pointers after the call. */ |
2444 | const unsigned char *orig = coding->source; | |
2445 | EMACS_INT offset; | |
e951386e KH |
2446 | |
2447 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, | |
2448 | cmp_status); | |
75f80e63 EZ |
2449 | offset = coding->source - orig; |
2450 | if (offset) | |
2451 | { | |
2452 | src += offset; | |
2453 | src_base += offset; | |
2454 | src_end += offset; | |
2455 | } | |
e951386e KH |
2456 | if (c < 0) |
2457 | { | |
2458 | if (c == -1) | |
2459 | goto invalid_code; | |
2460 | if (c == -2) | |
2461 | break; | |
2462 | } | |
2463 | src = src_base + nbytes; | |
2464 | consumed_chars = consumed_chars_base + nchars; | |
2465 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2466 | cmp_status->ncomps -= nchars; | |
2467 | } | |
2468 | ||
ad1746f5 | 2469 | /* Now if C >= 0, we found a normally encoded character, if C < |
e951386e KH |
2470 | 0, we found an old-style composition component character or |
2471 | rule. */ | |
2472 | ||
2473 | if (cmp_status->state == COMPOSING_NO) | |
2474 | { | |
2475 | if (last_id != id) | |
2476 | { | |
2477 | if (last_id != charset_ascii) | |
2478 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, | |
2479 | last_id); | |
2480 | last_id = id; | |
2481 | last_offset = char_offset; | |
2482 | } | |
df7492f9 KH |
2483 | *charbuf++ = c; |
2484 | char_offset++; | |
aa72b389 | 2485 | } |
e951386e | 2486 | else if (cmp_status->state == COMPOSING_CHAR) |
df7492f9 | 2487 | { |
e951386e KH |
2488 | if (cmp_status->old_form) |
2489 | { | |
2490 | if (c >= 0) | |
2491 | { | |
2492 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2493 | *charbuf++ = c; | |
2494 | char_offset++; | |
2495 | } | |
2496 | else | |
2497 | { | |
2498 | *charbuf++ = -c; | |
2499 | cmp_status->nchars++; | |
2500 | cmp_status->length++; | |
2501 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | |
2502 | EMACS_MULE_COMPOSITION_END (); | |
2503 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2504 | cmp_status->state = COMPOSING_RULE; | |
2505 | } | |
2506 | } | |
df7492f9 | 2507 | else |
e951386e KH |
2508 | { |
2509 | *charbuf++ = c; | |
2510 | cmp_status->length++; | |
2511 | cmp_status->nchars--; | |
2512 | if (cmp_status->nchars == 0) | |
2513 | EMACS_MULE_COMPOSITION_END (); | |
2514 | } | |
df7492f9 | 2515 | } |
e951386e | 2516 | else if (cmp_status->state == COMPOSING_RULE) |
df7492f9 | 2517 | { |
e951386e | 2518 | int rule; |
ff0dacd7 | 2519 | |
e951386e | 2520 | if (c >= 0) |
df7492f9 | 2521 | { |
e951386e KH |
2522 | EMACS_MULE_COMPOSITION_END (); |
2523 | *charbuf++ = c; | |
2524 | char_offset++; | |
df7492f9 | 2525 | } |
e951386e | 2526 | else |
ff0dacd7 | 2527 | { |
e951386e KH |
2528 | c = -c; |
2529 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | |
2530 | if (rule < 0) | |
2531 | goto invalid_code; | |
2532 | *charbuf++ = -2; | |
2533 | *charbuf++ = rule; | |
2534 | cmp_status->length += 2; | |
2535 | cmp_status->state = COMPOSING_CHAR; | |
ff0dacd7 | 2536 | } |
e951386e KH |
2537 | } |
2538 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | |
2539 | { | |
df7492f9 | 2540 | *charbuf++ = c; |
e951386e KH |
2541 | cmp_status->length++; |
2542 | if (cmp_status->ncomps == 0) | |
2543 | cmp_status->state = COMPOSING_CHAR; | |
2544 | else if (cmp_status->ncomps > 0) | |
2545 | { | |
2546 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | |
2547 | cmp_status->state = COMPOSING_COMPONENT_RULE; | |
2548 | } | |
2549 | else | |
2550 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 2551 | } |
e951386e KH |
2552 | else /* COMPOSING_COMPONENT_RULE */ |
2553 | { | |
2554 | int rule; | |
2555 | ||
2556 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | |
2557 | if (rule < 0) | |
2558 | goto invalid_code; | |
2559 | *charbuf++ = -2; | |
2560 | *charbuf++ = rule; | |
2561 | cmp_status->length += 2; | |
2562 | cmp_status->ncomps--; | |
2563 | if (cmp_status->ncomps > 0) | |
2564 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | |
2565 | else | |
2566 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2567 | } | |
2568 | continue; | |
2569 | ||
df7492f9 | 2570 | invalid_code: |
e951386e | 2571 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
df7492f9 KH |
2572 | src = src_base; |
2573 | consumed_chars = consumed_chars_base; | |
2574 | ONE_MORE_BYTE (c); | |
2575 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2576 | char_offset++; |
df7492f9 KH |
2577 | coding->errors++; |
2578 | } | |
2579 | ||
2580 | no_more_source: | |
e951386e KH |
2581 | if (cmp_status->state != COMPOSING_NO) |
2582 | { | |
2583 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
2584 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2585 | else | |
2586 | { | |
2587 | int i; | |
2588 | ||
2589 | charbuf -= cmp_status->length; | |
2590 | for (i = 0; i < cmp_status->length; i++) | |
2591 | cmp_status->carryover[i] = charbuf[i]; | |
2592 | } | |
2593 | } | |
ff0dacd7 | 2594 | if (last_id != charset_ascii) |
69a80ea3 | 2595 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2596 | coding->consumed_char += consumed_chars_base; |
2597 | coding->consumed = src_base - coding->source; | |
2598 | coding->charbuf_used = charbuf - coding->charbuf; | |
2599 | } | |
2600 | ||
2601 | ||
2602 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2603 | do { \ | |
2604 | if (id < 0xA0) \ | |
2605 | codes[0] = id, codes[1] = 0; \ | |
2606 | else if (id < 0xE0) \ | |
2607 | codes[0] = 0x9A, codes[1] = id; \ | |
2608 | else if (id < 0xF0) \ | |
2609 | codes[0] = 0x9B, codes[1] = id; \ | |
2610 | else if (id < 0xF5) \ | |
2611 | codes[0] = 0x9C, codes[1] = id; \ | |
2612 | else \ | |
2613 | codes[0] = 0x9D, codes[1] = id; \ | |
2614 | } while (0); | |
2615 | ||
aa72b389 | 2616 | |
df7492f9 | 2617 | static int |
971de7fb | 2618 | encode_coding_emacs_mule (struct coding_system *coding) |
df7492f9 KH |
2619 | { |
2620 | int multibytep = coding->dst_multibyte; | |
2621 | int *charbuf = coding->charbuf; | |
2622 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2623 | unsigned char *dst = coding->destination + coding->produced; | |
2624 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2625 | int safe_room = 8; | |
df7492f9 | 2626 | int produced_chars = 0; |
24a73b0a | 2627 | Lisp_Object attrs, charset_list; |
df7492f9 | 2628 | int c; |
ff0dacd7 | 2629 | int preferred_charset_id = -1; |
df7492f9 | 2630 | |
24a73b0a | 2631 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2632 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2633 | { | |
2634 | CODING_ATTR_CHARSET_LIST (attrs) | |
2635 | = charset_list = Vemacs_mule_charset_list; | |
2636 | } | |
df7492f9 KH |
2637 | |
2638 | while (charbuf < charbuf_end) | |
2639 | { | |
2640 | ASSURE_DESTINATION (safe_room); | |
2641 | c = *charbuf++; | |
ff0dacd7 KH |
2642 | |
2643 | if (c < 0) | |
2644 | { | |
2645 | /* Handle an annotation. */ | |
2646 | switch (*charbuf) | |
2647 | { | |
2648 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2649 | /* Not yet implemented. */ | |
2650 | break; | |
2651 | case CODING_ANNOTATE_CHARSET_MASK: | |
2652 | preferred_charset_id = charbuf[3]; | |
2653 | if (preferred_charset_id >= 0 | |
2654 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2655 | charset_list))) | |
2656 | preferred_charset_id = -1; | |
2657 | break; | |
2658 | default: | |
2659 | abort (); | |
2660 | } | |
2661 | charbuf += -c - 1; | |
2662 | continue; | |
2663 | } | |
2664 | ||
df7492f9 KH |
2665 | if (ASCII_CHAR_P (c)) |
2666 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2667 | else if (CHAR_BYTE8_P (c)) |
2668 | { | |
2669 | c = CHAR_TO_BYTE8 (c); | |
2670 | EMIT_ONE_BYTE (c); | |
2671 | } | |
df7492f9 | 2672 | else |
aa72b389 | 2673 | { |
df7492f9 KH |
2674 | struct charset *charset; |
2675 | unsigned code; | |
2676 | int dimension; | |
2677 | int emacs_mule_id; | |
2678 | unsigned char leading_codes[2]; | |
2679 | ||
ff0dacd7 KH |
2680 | if (preferred_charset_id >= 0) |
2681 | { | |
2682 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
905ca9d2 KH |
2683 | if (CHAR_CHARSET_P (c, charset)) |
2684 | code = ENCODE_CHAR (charset, c); | |
2685 | else | |
2686 | charset = char_charset (c, charset_list, &code); | |
ff0dacd7 KH |
2687 | } |
2688 | else | |
2689 | charset = char_charset (c, charset_list, &code); | |
df7492f9 KH |
2690 | if (! charset) |
2691 | { | |
2692 | c = coding->default_char; | |
2693 | if (ASCII_CHAR_P (c)) | |
2694 | { | |
2695 | EMIT_ONE_ASCII_BYTE (c); | |
2696 | continue; | |
2697 | } | |
2698 | charset = char_charset (c, charset_list, &code); | |
2699 | } | |
2700 | dimension = CHARSET_DIMENSION (charset); | |
2701 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2702 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2703 | EMIT_ONE_BYTE (leading_codes[0]); | |
2704 | if (leading_codes[1]) | |
2705 | EMIT_ONE_BYTE (leading_codes[1]); | |
2706 | if (dimension == 1) | |
1fa663f9 | 2707 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2708 | else |
df7492f9 | 2709 | { |
1fa663f9 | 2710 | code |= 0x8080; |
df7492f9 KH |
2711 | EMIT_ONE_BYTE (code >> 8); |
2712 | EMIT_ONE_BYTE (code & 0xFF); | |
2713 | } | |
aa72b389 | 2714 | } |
aa72b389 | 2715 | } |
065e3595 | 2716 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2717 | coding->produced_char += produced_chars; |
2718 | coding->produced = dst - coding->destination; | |
2719 | return 0; | |
aa72b389 | 2720 | } |
b73bfc1c | 2721 | |
4ed46869 | 2722 | \f |
df7492f9 | 2723 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2724 | |
2725 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2726 | Since the intention of this note is to help understand the |
5a936b46 | 2727 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2728 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2729 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2730 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2731 | |
2732 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2733 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2734 | is encoded using bytes less than 128. This may make the encoded |
2735 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2736 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2737 | Significant Bit). |
b73bfc1c | 2738 | |
cfb43547 DL |
2739 | There are two kinds of character sets: control character sets and |
2740 | graphic character sets. The former contain control characters such | |
4ed46869 | 2741 | as `newline' and `escape' to provide control functions (control |
39787efd | 2742 | functions are also provided by escape sequences). The latter |
cfb43547 | 2743 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2744 | two control character sets and many graphic character sets. |
2745 | ||
2746 | Graphic character sets are classified into one of the following | |
39787efd KH |
2747 | four classes, according to the number of bytes (DIMENSION) and |
2748 | number of characters in one dimension (CHARS) of the set: | |
2749 | - DIMENSION1_CHARS94 | |
2750 | - DIMENSION1_CHARS96 | |
2751 | - DIMENSION2_CHARS94 | |
2752 | - DIMENSION2_CHARS96 | |
2753 | ||
2754 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2755 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2756 | hereafter). The <F> of each character set is decided by ECMA(*) |
2757 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2758 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2759 | |
2760 | Note (*): ECMA = European Computer Manufacturers Association | |
2761 | ||
cfb43547 | 2762 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2763 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2764 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2765 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2766 | o DIMENSION2_CHARS96 -- none for the moment | |
2767 | ||
39787efd | 2768 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2769 | C0 [0x00..0x1F] -- control character plane 0 |
2770 | GL [0x20..0x7F] -- graphic character plane 0 | |
2771 | C1 [0x80..0x9F] -- control character plane 1 | |
2772 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2773 | ||
2774 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2775 | C1 by an escape sequence. The most common case is that: |
2776 | - ISO646's control character set is designated/invoked to C0, and | |
2777 | - ISO6429's control character set is designated/invoked to C1, | |
2778 | and usually these designations/invocations are omitted in encoded | |
2779 | text. In a 7-bit environment, only C0 can be used, and a control | |
2780 | character for C1 is encoded by an appropriate escape sequence to | |
2781 | fit into the environment. All control characters for C1 are | |
2782 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2783 | |
2784 | A graphic character set is at first designated to one of four | |
2785 | graphic registers (G0 through G3), then these graphic registers are | |
2786 | invoked to GL or GR. These designations and invocations can be | |
2787 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2788 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2789 | these invocations and designations are omitted in encoded text. | |
2790 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2791 | |
39787efd KH |
2792 | When a graphic character set of CHARS94 is invoked to GL, codes |
2793 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2794 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2795 | be used. | |
4ed46869 KH |
2796 | |
2797 | There are two ways of invocation: locking-shift and single-shift. | |
2798 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2799 | invocation, whereas with single-shift, the invocation affects the |
2800 | following character only and doesn't affect the locking-shift | |
2801 | state. Invocations are done by the following control characters or | |
2802 | escape sequences: | |
4ed46869 KH |
2803 | |
2804 | ---------------------------------------------------------------------- | |
39787efd | 2805 | abbrev function cntrl escape seq description |
4ed46869 | 2806 | ---------------------------------------------------------------------- |
39787efd KH |
2807 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2808 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2809 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2810 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2811 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2812 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2813 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2814 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2815 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2816 | ---------------------------------------------------------------------- |
39787efd KH |
2817 | (*) These are not used by any known coding system. |
2818 | ||
2819 | Control characters for these functions are defined by macros | |
2820 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2821 | |
39787efd | 2822 | Designations are done by the following escape sequences: |
4ed46869 KH |
2823 | ---------------------------------------------------------------------- |
2824 | escape sequence description | |
2825 | ---------------------------------------------------------------------- | |
2826 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2827 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2828 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2829 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2830 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2831 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2832 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2833 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2834 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2835 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2836 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2837 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2838 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2839 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2840 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2841 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2842 | ---------------------------------------------------------------------- | |
2843 | ||
2844 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2845 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2846 | |
2847 | Note (*): Although these designations are not allowed in ISO2022, | |
2848 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2849 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2850 | 7-bit environment, non-locking-shift, and non-single-shift. |
2851 | ||
2852 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2853 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2854 | |
cfb43547 | 2855 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2856 | same multilingual text in ISO2022. Actually, there exist many |
2857 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2858 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2859 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2860 | localized platforms), and all of these are variants of ISO2022. |
2861 | ||
2862 | In addition to the above, Emacs handles two more kinds of escape | |
2863 | sequences: ISO6429's direction specification and Emacs' private | |
2864 | sequence for specifying character composition. | |
2865 | ||
39787efd | 2866 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2867 | o CSI ']' -- end of the current direction |
2868 | o CSI '0' ']' -- end of the current direction | |
2869 | o CSI '1' ']' -- start of left-to-right text | |
2870 | o CSI '2' ']' -- start of right-to-left text | |
2871 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2872 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2873 | ||
2874 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2875 | o ESC '0' -- start relative composition |
2876 | o ESC '1' -- end composition | |
2877 | o ESC '2' -- start rule-base composition (*) | |
2878 | o ESC '3' -- start relative composition with alternate chars (**) | |
2879 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2880 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2881 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2882 | |
5a936b46 DL |
2883 | (*) This form is used only in Emacs 20.7 and older versions, |
2884 | but newer versions can safely decode it. | |
cfb43547 | 2885 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2886 | and older versions can't decode it. |
ec6d2bb8 | 2887 | |
cfb43547 | 2888 | Here's a list of example usages of these composition escape |
b73bfc1c | 2889 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2890 | |
b73bfc1c | 2891 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2892 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2893 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2894 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2895 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2896 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2897 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2898 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 KH |
2899 | |
2900 | enum iso_code_class_type iso_code_class[256]; | |
2901 | ||
df7492f9 KH |
2902 | #define SAFE_CHARSET_P(coding, id) \ |
2903 | ((id) <= (coding)->max_charset_id \ | |
1b3b981b | 2904 | && (coding)->safe_charsets[id] != 255) |
df7492f9 KH |
2905 | |
2906 | ||
2907 | #define SHIFT_OUT_OK(category) \ | |
2908 | (CODING_ISO_INITIAL (&coding_categories[category], 1) >= 0) | |
2909 | ||
2910 | static void | |
971de7fb | 2911 | setup_iso_safe_charsets (Lisp_Object attrs) |
df7492f9 KH |
2912 | { |
2913 | Lisp_Object charset_list, safe_charsets; | |
2914 | Lisp_Object request; | |
2915 | Lisp_Object reg_usage; | |
2916 | Lisp_Object tail; | |
2917 | int reg94, reg96; | |
2918 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
2919 | int max_charset_id; | |
2920 | ||
2921 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2922 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2923 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2924 | { | |
2925 | CODING_ATTR_CHARSET_LIST (attrs) | |
2926 | = charset_list = Viso_2022_charset_list; | |
2927 | ASET (attrs, coding_attr_safe_charsets, Qnil); | |
2928 | } | |
2929 | ||
2930 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2931 | return; | |
2932 | ||
2933 | max_charset_id = 0; | |
2934 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2935 | { | |
2936 | int id = XINT (XCAR (tail)); | |
2937 | if (max_charset_id < id) | |
2938 | max_charset_id = id; | |
2939 | } | |
d46c5b12 | 2940 | |
1b3b981b AS |
2941 | safe_charsets = make_uninit_string (max_charset_id + 1); |
2942 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
2943 | request = AREF (attrs, coding_attr_iso_request); |
2944 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2945 | reg94 = XINT (XCAR (reg_usage)); | |
2946 | reg96 = XINT (XCDR (reg_usage)); | |
2947 | ||
2948 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2949 | { | |
2950 | Lisp_Object id; | |
2951 | Lisp_Object reg; | |
2952 | struct charset *charset; | |
2953 | ||
2954 | id = XCAR (tail); | |
2955 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2956 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2957 | if (! NILP (reg)) |
8f924df7 | 2958 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2959 | else if (charset->iso_chars_96) |
2960 | { | |
2961 | if (reg96 < 4) | |
8f924df7 | 2962 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2963 | } |
2964 | else | |
2965 | { | |
2966 | if (reg94 < 4) | |
8f924df7 | 2967 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2968 | } |
2969 | } | |
2970 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2971 | } | |
d46c5b12 | 2972 | |
b6871cc7 | 2973 | |
4ed46869 | 2974 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
ad1746f5 | 2975 | Check if a text is encoded in one of ISO-2022 based coding systems. |
ff0dacd7 | 2976 | If it is, return 1, else return 0. */ |
4ed46869 | 2977 | |
0a28aafb | 2978 | static int |
cf84bb53 JB |
2979 | detect_coding_iso_2022 (struct coding_system *coding, |
2980 | struct coding_detection_info *detect_info) | |
4ed46869 | 2981 | { |
8f924df7 KH |
2982 | const unsigned char *src = coding->source, *src_base = src; |
2983 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
df7492f9 | 2984 | int multibytep = coding->src_multibyte; |
ff0dacd7 | 2985 | int single_shifting = 0; |
df7492f9 KH |
2986 | int id; |
2987 | int c, c1; | |
2988 | int consumed_chars = 0; | |
2989 | int i; | |
ff0dacd7 KH |
2990 | int rejected = 0; |
2991 | int found = 0; | |
cee53ed4 | 2992 | int composition_count = -1; |
ff0dacd7 KH |
2993 | |
2994 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2995 | |
2996 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2997 | { | |
2998 | struct coding_system *this = &(coding_categories[i]); | |
2999 | Lisp_Object attrs, val; | |
3000 | ||
c6b278e7 KH |
3001 | if (this->id < 0) |
3002 | continue; | |
df7492f9 KH |
3003 | attrs = CODING_ID_ATTRS (this->id); |
3004 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
1b3b981b | 3005 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list)) |
df7492f9 KH |
3006 | setup_iso_safe_charsets (attrs); |
3007 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 3008 | this->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 3009 | this->safe_charsets = SDATA (val); |
df7492f9 KH |
3010 | } |
3011 | ||
3012 | /* A coding system of this category is always ASCII compatible. */ | |
3013 | src += coding->head_ascii; | |
3f003981 | 3014 | |
ff0dacd7 | 3015 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 3016 | { |
065e3595 | 3017 | src_base = src; |
df7492f9 | 3018 | ONE_MORE_BYTE (c); |
4ed46869 KH |
3019 | switch (c) |
3020 | { | |
3021 | case ISO_CODE_ESC: | |
74383408 KH |
3022 | if (inhibit_iso_escape_detection) |
3023 | break; | |
f46869e4 | 3024 | single_shifting = 0; |
df7492f9 | 3025 | ONE_MORE_BYTE (c); |
d46c5b12 | 3026 | if (c >= '(' && c <= '/') |
4ed46869 | 3027 | { |
bf9cdd4e | 3028 | /* Designation sequence for a charset of dimension 1. */ |
df7492f9 | 3029 | ONE_MORE_BYTE (c1); |
d46c5b12 | 3030 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 3031 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) |
d46c5b12 KH |
3032 | /* Invalid designation sequence. Just ignore. */ |
3033 | break; | |
bf9cdd4e KH |
3034 | } |
3035 | else if (c == '$') | |
3036 | { | |
3037 | /* Designation sequence for a charset of dimension 2. */ | |
df7492f9 | 3038 | ONE_MORE_BYTE (c); |
bf9cdd4e KH |
3039 | if (c >= '@' && c <= 'B') |
3040 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
ff0dacd7 | 3041 | id = iso_charset_table[1][0][c]; |
bf9cdd4e | 3042 | else if (c >= '(' && c <= '/') |
bcf26d6a | 3043 | { |
df7492f9 | 3044 | ONE_MORE_BYTE (c1); |
d46c5b12 | 3045 | if (c1 < ' ' || c1 >= 0x80 |
df7492f9 | 3046 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) |
d46c5b12 KH |
3047 | /* Invalid designation sequence. Just ignore. */ |
3048 | break; | |
bcf26d6a | 3049 | } |
bf9cdd4e | 3050 | else |
ff0dacd7 | 3051 | /* Invalid designation sequence. Just ignore it. */ |
d46c5b12 KH |
3052 | break; |
3053 | } | |
ae9ff118 | 3054 | else if (c == 'N' || c == 'O') |
d46c5b12 | 3055 | { |
ae9ff118 | 3056 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
3057 | single_shifting = 1; |
3058 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
d46c5b12 | 3059 | break; |
4ed46869 | 3060 | } |
cee53ed4 KH |
3061 | else if (c == '1') |
3062 | { | |
3063 | /* End of composition. */ | |
3064 | if (composition_count < 0 | |
3065 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
3066 | /* Invalid */ | |
3067 | break; | |
3068 | composition_count = -1; | |
3069 | found |= CATEGORY_MASK_ISO; | |
3070 | } | |
ec6d2bb8 KH |
3071 | else if (c >= '0' && c <= '4') |
3072 | { | |
3073 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 3074 | composition_count = 0; |
ec6d2bb8 KH |
3075 | break; |
3076 | } | |
bf9cdd4e | 3077 | else |
df7492f9 | 3078 | { |
ff0dacd7 | 3079 | /* Invalid escape sequence. Just ignore it. */ |
df7492f9 KH |
3080 | break; |
3081 | } | |
d46c5b12 KH |
3082 | |
3083 | /* We found a valid designation sequence for CHARSET. */ | |
ff0dacd7 | 3084 | rejected |= CATEGORY_MASK_ISO_8BIT; |
df7492f9 KH |
3085 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], |
3086 | id)) | |
ff0dacd7 | 3087 | found |= CATEGORY_MASK_ISO_7; |
d46c5b12 | 3088 | else |
ff0dacd7 | 3089 | rejected |= CATEGORY_MASK_ISO_7; |
df7492f9 KH |
3090 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], |
3091 | id)) | |
ff0dacd7 | 3092 | found |= CATEGORY_MASK_ISO_7_TIGHT; |
d46c5b12 | 3093 | else |
ff0dacd7 | 3094 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; |
df7492f9 KH |
3095 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], |
3096 | id)) | |
ff0dacd7 | 3097 | found |= CATEGORY_MASK_ISO_7_ELSE; |
ae9ff118 | 3098 | else |
ff0dacd7 | 3099 | rejected |= CATEGORY_MASK_ISO_7_ELSE; |
df7492f9 KH |
3100 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], |
3101 | id)) | |
ff0dacd7 | 3102 | found |= CATEGORY_MASK_ISO_8_ELSE; |
ae9ff118 | 3103 | else |
ff0dacd7 | 3104 | rejected |= CATEGORY_MASK_ISO_8_ELSE; |
4ed46869 KH |
3105 | break; |
3106 | ||
4ed46869 | 3107 | case ISO_CODE_SO: |
d46c5b12 | 3108 | case ISO_CODE_SI: |
ff0dacd7 | 3109 | /* Locking shift out/in. */ |
74383408 KH |
3110 | if (inhibit_iso_escape_detection) |
3111 | break; | |
f46869e4 | 3112 | single_shifting = 0; |
ff0dacd7 | 3113 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
3114 | break; |
3115 | ||
4ed46869 | 3116 | case ISO_CODE_CSI: |
ff0dacd7 | 3117 | /* Control sequence introducer. */ |
f46869e4 | 3118 | single_shifting = 0; |
ff0dacd7 KH |
3119 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3120 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3121 | goto check_extra_latin; | |
3122 | ||
4ed46869 KH |
3123 | case ISO_CODE_SS2: |
3124 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
3125 | /* Single shift. */ |
3126 | if (inhibit_iso_escape_detection) | |
3127 | break; | |
75e2a253 | 3128 | single_shifting = 0; |
ff0dacd7 KH |
3129 | rejected |= CATEGORY_MASK_ISO_7BIT; |
3130 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3131 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 | 3132 | found |= CATEGORY_MASK_ISO_8_1, single_shifting = 1; |
ff0dacd7 KH |
3133 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
3134 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
75e2a253 KH |
3135 | found |= CATEGORY_MASK_ISO_8_2, single_shifting = 1; |
3136 | if (single_shifting) | |
3137 | break; | |
ff0dacd7 | 3138 | goto check_extra_latin; |
4ed46869 KH |
3139 | |
3140 | default: | |
065e3595 KH |
3141 | if (c < 0) |
3142 | continue; | |
4ed46869 | 3143 | if (c < 0x80) |
f46869e4 | 3144 | { |
cee53ed4 KH |
3145 | if (composition_count >= 0) |
3146 | composition_count++; | |
f46869e4 KH |
3147 | single_shifting = 0; |
3148 | break; | |
3149 | } | |
ff0dacd7 | 3150 | if (c >= 0xA0) |
c4825358 | 3151 | { |
ff0dacd7 KH |
3152 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3153 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 3154 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
3155 | 0xA0..0FF. If the byte length is even, we include |
3156 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
3157 | only when we are not single shifting. */ | |
3158 | if (! single_shifting | |
3159 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 3160 | { |
e17de821 | 3161 | int i = 1; |
b73bfc1c KH |
3162 | while (src < src_end) |
3163 | { | |
d12bd917 | 3164 | src_base = src; |
df7492f9 | 3165 | ONE_MORE_BYTE (c); |
b73bfc1c | 3166 | if (c < 0xA0) |
d12bd917 KH |
3167 | { |
3168 | src = src_base; | |
3169 | break; | |
3170 | } | |
b73bfc1c KH |
3171 | i++; |
3172 | } | |
3173 | ||
3174 | if (i & 1 && src < src_end) | |
cee53ed4 KH |
3175 | { |
3176 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3177 | if (composition_count >= 0) | |
3178 | composition_count += i; | |
3179 | } | |
f46869e4 | 3180 | else |
cee53ed4 KH |
3181 | { |
3182 | found |= CATEGORY_MASK_ISO_8_2; | |
3183 | if (composition_count >= 0) | |
3184 | composition_count += i / 2; | |
3185 | } | |
f46869e4 | 3186 | } |
ff0dacd7 | 3187 | break; |
4ed46869 | 3188 | } |
ff0dacd7 KH |
3189 | check_extra_latin: |
3190 | single_shifting = 0; | |
3191 | if (! VECTORP (Vlatin_extra_code_table) | |
3192 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c])) | |
3193 | { | |
3194 | rejected = CATEGORY_MASK_ISO; | |
3195 | break; | |
3196 | } | |
3197 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3198 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3199 | found |= CATEGORY_MASK_ISO_8_1; | |
3200 | else | |
3201 | rejected |= CATEGORY_MASK_ISO_8_1; | |
75e2a253 | 3202 | rejected |= CATEGORY_MASK_ISO_8_2; |
4ed46869 KH |
3203 | } |
3204 | } | |
ff0dacd7 KH |
3205 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3206 | return 0; | |
4ed46869 | 3207 | |
df7492f9 | 3208 | no_more_source: |
ff0dacd7 KH |
3209 | detect_info->rejected |= rejected; |
3210 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3211 | return 1; |
4ed46869 | 3212 | } |
ec6d2bb8 | 3213 | |
4ed46869 | 3214 | |
134b9549 KH |
3215 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3216 | escape sequence should be kept. */ | |
df7492f9 KH |
3217 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3218 | do { \ | |
3219 | int id, prev; \ | |
3220 | \ | |
3221 | if (final < '0' || final >= 128 \ | |
3222 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3223 | || !SAFE_CHARSET_P (coding, id)) \ | |
3224 | { \ | |
3225 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3226 | chars_96 = -1; \ |
3227 | break; \ | |
df7492f9 KH |
3228 | } \ |
3229 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3230 | if (id == charset_jisx0201_roman) \ |
3231 | { \ | |
3232 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3233 | id = charset_ascii; \ | |
3234 | } \ | |
3235 | else if (id == charset_jisx0208_1978) \ | |
3236 | { \ | |
3237 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3238 | id = charset_jisx0208; \ | |
3239 | } \ | |
df7492f9 KH |
3240 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3241 | /* If there was an invalid designation to REG previously, and this \ | |
3242 | designation is ASCII to REG, we should keep this designation \ | |
3243 | sequence. */ \ | |
3244 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3245 | chars_96 = -1; \ |
4ed46869 KH |
3246 | } while (0) |
3247 | ||
d46c5b12 | 3248 | |
e951386e KH |
3249 | /* Handle these composition sequence (ALT: alternate char): |
3250 | ||
3251 | (1) relative composition: ESC 0 CHAR ... ESC 1 | |
3252 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
3253 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | |
3254 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | |
3255 | ||
3256 | When the start sequence (ESC 0/2/3/4) is found, this annotation | |
3257 | header is produced. | |
3258 | ||
3259 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | |
3260 | ||
3261 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | |
3262 | produced until the end sequence (ESC 1) is found: | |
3263 | ||
3264 | (1) CHAR ... CHAR | |
3265 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
3266 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | |
3267 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | |
3268 | ||
3269 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | |
3270 | annotation header is updated as below: | |
3271 | ||
3272 | (1) LENGTH: unchanged, NCHARS: number of CHARs | |
3273 | (2) LENGTH: unchanged, NCHARS: number of CHARs | |
3274 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | |
3275 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | |
3276 | ||
3277 | If an error is found while composing, the annotation header is | |
3278 | changed to: | |
3279 | ||
3280 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | |
3281 | ||
3282 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
3283 | byte sequence as below: | |
3284 | o the original byte sequence is B: [ B -1 ] | |
3285 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
3286 | and the sequence [ -1 -1 ] is changed to the original byte | |
3287 | sequence: | |
3288 | [ ESC '0' ] | |
3289 | */ | |
3290 | ||
3291 | /* Decode a composition rule C1 and maybe one more byte from the | |
3292 | source, and set RULE to the encoded composition rule, NBYTES to the | |
3293 | length of the composition rule. If the rule is invalid, set RULE | |
3294 | to some negative value. */ | |
3295 | ||
3296 | #define DECODE_COMPOSITION_RULE(rule, nbytes) \ | |
3297 | do { \ | |
3298 | rule = c1 - 32; \ | |
3299 | if (rule < 0) \ | |
3300 | break; \ | |
3301 | if (rule < 81) /* old format (before ver.21) */ \ | |
3302 | { \ | |
3303 | int gref = (rule) / 9; \ | |
3304 | int nref = (rule) % 9; \ | |
3305 | if (gref == 4) gref = 10; \ | |
3306 | if (nref == 4) nref = 10; \ | |
3307 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
3308 | nbytes = 1; \ | |
3309 | } \ | |
3310 | else /* new format (after ver.21) */ \ | |
3311 | { \ | |
3312 | int c; \ | |
3313 | \ | |
3314 | ONE_MORE_BYTE (c); \ | |
3315 | rule = COMPOSITION_ENCODE_RULE (rule - 81, c - 32); \ | |
3316 | if (rule >= 0) \ | |
3317 | rule += 0x100; /* to destinguish it from the old format */ \ | |
3318 | nbytes = 2; \ | |
3319 | } \ | |
3320 | } while (0) | |
3321 | ||
3322 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
df7492f9 | 3323 | do { \ |
e951386e KH |
3324 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
3325 | \ | |
3326 | if (rule < 0x100) /* old format */ \ | |
df7492f9 | 3327 | { \ |
e951386e KH |
3328 | if (gref == 10) gref = 4; \ |
3329 | if (nref == 10) nref = 4; \ | |
3330 | charbuf[idx] = 32 + gref * 9 + nref; \ | |
3331 | charbuf[idx + 1] = -1; \ | |
3332 | new_chars++; \ | |
df7492f9 | 3333 | } \ |
e951386e | 3334 | else /* new format */ \ |
df7492f9 | 3335 | { \ |
e951386e KH |
3336 | charbuf[idx] = 32 + 81 + gref; \ |
3337 | charbuf[idx + 1] = 32 + nref; \ | |
3338 | new_chars += 2; \ | |
df7492f9 KH |
3339 | } \ |
3340 | } while (0) | |
3341 | ||
e951386e KH |
3342 | /* Finish the current composition as invalid. */ |
3343 | ||
f57e2426 | 3344 | static int finish_composition (int *, struct composition_status *); |
e951386e KH |
3345 | |
3346 | static int | |
971de7fb | 3347 | finish_composition (int *charbuf, struct composition_status *cmp_status) |
e951386e KH |
3348 | { |
3349 | int idx = - cmp_status->length; | |
3350 | int new_chars; | |
3351 | ||
3352 | /* Recover the original ESC sequence */ | |
3353 | charbuf[idx++] = ISO_CODE_ESC; | |
3354 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | |
3355 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | |
3356 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | |
3357 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | |
3358 | : '4'); | |
3359 | charbuf[idx++] = -2; | |
3360 | charbuf[idx++] = 0; | |
3361 | charbuf[idx++] = -1; | |
3362 | new_chars = cmp_status->nchars; | |
3363 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | |
3364 | for (; idx < 0; idx++) | |
3365 | { | |
3366 | int elt = charbuf[idx]; | |
3367 | ||
3368 | if (elt == -2) | |
3369 | { | |
3370 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | |
3371 | idx++; | |
3372 | } | |
3373 | else if (elt == -1) | |
3374 | { | |
3375 | charbuf[idx++] = ISO_CODE_ESC; | |
3376 | charbuf[idx] = '0'; | |
3377 | new_chars += 2; | |
3378 | } | |
3379 | } | |
3380 | cmp_status->state = COMPOSING_NO; | |
3381 | return new_chars; | |
3382 | } | |
3383 | ||
ad1746f5 | 3384 | /* If characters are under composition, finish the composition. */ |
e951386e KH |
3385 | #define MAYBE_FINISH_COMPOSITION() \ |
3386 | do { \ | |
3387 | if (cmp_status->state != COMPOSING_NO) \ | |
3388 | char_offset += finish_composition (charbuf, cmp_status); \ | |
3389 | } while (0) | |
d46c5b12 | 3390 | |
aa72b389 | 3391 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
e951386e | 3392 | |
aa72b389 KH |
3393 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
3394 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3395 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3396 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
ec6d2bb8 | 3397 | |
e951386e KH |
3398 | Produce this annotation sequence now: |
3399 | ||
3400 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] | |
3401 | */ | |
3402 | ||
3403 | #define DECODE_COMPOSITION_START(c1) \ | |
3404 | do { \ | |
3405 | if (c1 == '0' \ | |
3406 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ | |
3407 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ | |
3408 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ | |
3409 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ | |
3410 | { \ | |
3411 | *charbuf++ = -1; \ | |
3412 | *charbuf++= -1; \ | |
3413 | cmp_status->state = COMPOSING_CHAR; \ | |
3414 | cmp_status->length += 2; \ | |
3415 | } \ | |
3416 | else \ | |
3417 | { \ | |
3418 | MAYBE_FINISH_COMPOSITION (); \ | |
3419 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3420 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3421 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3422 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3423 | cmp_status->state \ | |
3424 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ | |
3425 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
3426 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
3427 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
3428 | coding->annotated = 1; \ | |
3429 | } \ | |
ec6d2bb8 KH |
3430 | } while (0) |
3431 | ||
ec6d2bb8 | 3432 | |
e951386e | 3433 | /* Handle composition end sequence ESC 1. */ |
df7492f9 KH |
3434 | |
3435 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3436 | do { \ |
e951386e KH |
3437 | if (cmp_status->nchars == 0 \ |
3438 | || ((cmp_status->state == COMPOSING_CHAR) \ | |
3439 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ | |
ec6d2bb8 | 3440 | { \ |
e951386e KH |
3441 | MAYBE_FINISH_COMPOSITION (); \ |
3442 | goto invalid_code; \ | |
ec6d2bb8 | 3443 | } \ |
e951386e KH |
3444 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
3445 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ | |
3446 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
3447 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ | |
3448 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ | |
3449 | char_offset += cmp_status->nchars; \ | |
3450 | cmp_status->state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3451 | } while (0) |
3452 | ||
e951386e | 3453 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ |
df7492f9 | 3454 | |
e951386e KH |
3455 | #define STORE_COMPOSITION_RULE(rule) \ |
3456 | do { \ | |
3457 | *charbuf++ = -2; \ | |
3458 | *charbuf++ = rule; \ | |
3459 | cmp_status->length += 2; \ | |
3460 | cmp_status->state--; \ | |
3461 | } while (0) | |
ec6d2bb8 | 3462 | |
e951386e KH |
3463 | /* Store a composed char or a component char C in charbuf, and update |
3464 | cmp_status. */ | |
3465 | ||
3466 | #define STORE_COMPOSITION_CHAR(c) \ | |
ec6d2bb8 | 3467 | do { \ |
e951386e KH |
3468 | *charbuf++ = (c); \ |
3469 | cmp_status->length++; \ | |
3470 | if (cmp_status->state == COMPOSING_CHAR) \ | |
3471 | cmp_status->nchars++; \ | |
df7492f9 | 3472 | else \ |
e951386e KH |
3473 | cmp_status->ncomps++; \ |
3474 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | |
3475 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | |
3476 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | |
3477 | cmp_status->state++; \ | |
ec6d2bb8 | 3478 | } while (0) |
88993dfd | 3479 | |
d46c5b12 | 3480 | |
4ed46869 KH |
3481 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3482 | ||
b73bfc1c | 3483 | static void |
971de7fb | 3484 | decode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 3485 | { |
8f924df7 KH |
3486 | const unsigned char *src = coding->source + coding->consumed; |
3487 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3488 | const unsigned char *src_base; | |
69a80ea3 | 3489 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
3490 | /* We may produce two annotations (charset and composition) in one |
3491 | loop and one more charset annotation at the end. */ | |
ff0dacd7 | 3492 | int *charbuf_end |
df80c7f0 | 3493 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
df7492f9 | 3494 | int consumed_chars = 0, consumed_chars_base; |
df7492f9 | 3495 | int multibytep = coding->src_multibyte; |
4ed46869 | 3496 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3497 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3498 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3499 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3500 | struct charset *charset; |
3501 | int c; | |
e951386e | 3502 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
24a73b0a | 3503 | Lisp_Object attrs, charset_list; |
ff0dacd7 KH |
3504 | int char_offset = coding->produced_char; |
3505 | int last_offset = char_offset; | |
3506 | int last_id = charset_ascii; | |
0a9564cb EZ |
3507 | int eol_crlf = |
3508 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 3509 | int byte_after_cr = -1; |
e951386e | 3510 | int i; |
df7492f9 | 3511 | |
24a73b0a | 3512 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 3513 | setup_iso_safe_charsets (attrs); |
287c57d7 KH |
3514 | /* Charset list may have been changed. */ |
3515 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
1b3b981b | 3516 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
b73bfc1c | 3517 | |
e951386e KH |
3518 | if (cmp_status->state != COMPOSING_NO) |
3519 | { | |
3520 | for (i = 0; i < cmp_status->length; i++) | |
3521 | *charbuf++ = cmp_status->carryover[i]; | |
3522 | coding->annotated = 1; | |
3523 | } | |
3524 | ||
b73bfc1c | 3525 | while (1) |
4ed46869 | 3526 | { |
cf299835 | 3527 | int c1, c2, c3; |
b73bfc1c KH |
3528 | |
3529 | src_base = src; | |
df7492f9 KH |
3530 | consumed_chars_base = consumed_chars; |
3531 | ||
3532 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3533 | { |
3534 | if (byte_after_cr >= 0) | |
3535 | src_base--; | |
3536 | break; | |
3537 | } | |
df7492f9 | 3538 | |
119852e7 KH |
3539 | if (byte_after_cr >= 0) |
3540 | c1 = byte_after_cr, byte_after_cr = -1; | |
3541 | else | |
3542 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3543 | if (c1 < 0) |
3544 | goto invalid_code; | |
4ed46869 | 3545 | |
e951386e | 3546 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
4ed46869 | 3547 | { |
e951386e KH |
3548 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
3549 | char_offset++; | |
3550 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | |
3551 | continue; | |
3552 | } | |
3553 | ||
3554 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | |
3555 | { | |
3556 | if (c1 == ISO_CODE_ESC) | |
ec6d2bb8 | 3557 | { |
e951386e KH |
3558 | if (src + 1 >= src_end) |
3559 | goto no_more_source; | |
3560 | *charbuf++ = ISO_CODE_ESC; | |
3561 | char_offset++; | |
3562 | if (src[0] == '%' && src[1] == '@') | |
df7492f9 | 3563 | { |
e951386e KH |
3564 | src += 2; |
3565 | consumed_chars += 2; | |
3566 | char_offset += 2; | |
3567 | /* We are sure charbuf can contain two more chars. */ | |
3568 | *charbuf++ = '%'; | |
3569 | *charbuf++ = '@'; | |
3570 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
df7492f9 | 3571 | } |
4ed46869 | 3572 | } |
e951386e KH |
3573 | else |
3574 | { | |
3575 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
3576 | char_offset++; | |
3577 | } | |
3578 | continue; | |
3579 | } | |
3580 | ||
3581 | if ((cmp_status->state == COMPOSING_RULE | |
3582 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | |
3583 | && c1 != ISO_CODE_ESC) | |
3584 | { | |
3585 | int rule, nbytes; | |
3586 | ||
3587 | DECODE_COMPOSITION_RULE (rule, nbytes); | |
3588 | if (rule < 0) | |
3589 | goto invalid_code; | |
3590 | STORE_COMPOSITION_RULE (rule); | |
3591 | continue; | |
3592 | } | |
3593 | ||
3594 | /* We produce at most one character. */ | |
3595 | switch (iso_code_class [c1]) | |
3596 | { | |
3597 | case ISO_0x20_or_0x7F: | |
df7492f9 KH |
3598 | if (charset_id_0 < 0 |
3599 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3600 | /* This is SPACE or DEL. */ |
3601 | charset = CHARSET_FROM_ID (charset_ascii); | |
3602 | else | |
3603 | charset = CHARSET_FROM_ID (charset_id_0); | |
3604 | break; | |
4ed46869 KH |
3605 | |
3606 | case ISO_graphic_plane_0: | |
134b9549 KH |
3607 | if (charset_id_0 < 0) |
3608 | charset = CHARSET_FROM_ID (charset_ascii); | |
3609 | else | |
3610 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3611 | break; |
3612 | ||
3613 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3614 | if (charset_id_1 < 0 |
3615 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3616 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3617 | goto invalid_code; | |
4ed46869 KH |
3618 | /* This is a graphic character, we fall down ... */ |
3619 | ||
3620 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3621 | if (charset_id_1 < 0) |
3622 | goto invalid_code; | |
3623 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3624 | break; |
3625 | ||
df7492f9 | 3626 | case ISO_control_0: |
119852e7 KH |
3627 | if (eol_crlf && c1 == '\r') |
3628 | ONE_MORE_BYTE (byte_after_cr); | |
df7492f9 KH |
3629 | MAYBE_FINISH_COMPOSITION (); |
3630 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3631 | break; |
3632 | ||
df7492f9 | 3633 | case ISO_control_1: |
df7492f9 KH |
3634 | goto invalid_code; |
3635 | ||
4ed46869 | 3636 | case ISO_shift_out: |
df7492f9 KH |
3637 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3638 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3639 | goto invalid_code; | |
3640 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3641 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3642 | continue; |
4ed46869 KH |
3643 | |
3644 | case ISO_shift_in: | |
df7492f9 KH |
3645 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3646 | goto invalid_code; | |
3647 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3648 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3649 | continue; |
4ed46869 KH |
3650 | |
3651 | case ISO_single_shift_2_7: | |
a63dba42 KH |
3652 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)) |
3653 | goto invalid_code; | |
4ed46869 | 3654 | case ISO_single_shift_2: |
df7492f9 KH |
3655 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3656 | goto invalid_code; | |
4ed46869 KH |
3657 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3658 | c1 = 'N'; | |
3659 | goto label_escape_sequence; | |
3660 | ||
3661 | case ISO_single_shift_3: | |
df7492f9 KH |
3662 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3663 | goto invalid_code; | |
4ed46869 KH |
3664 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3665 | c1 = 'O'; | |
3666 | goto label_escape_sequence; | |
3667 | ||
3668 | case ISO_control_sequence_introducer: | |
3669 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3670 | c1 = '['; | |
3671 | goto label_escape_sequence; | |
3672 | ||
3673 | case ISO_escape: | |
3674 | ONE_MORE_BYTE (c1); | |
3675 | label_escape_sequence: | |
df7492f9 | 3676 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3677 | designation, direction specification, and character |
3678 | composition specification. */ | |
3679 | switch (c1) | |
3680 | { | |
3681 | case '&': /* revision of following character set */ | |
3682 | ONE_MORE_BYTE (c1); | |
3683 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3684 | goto invalid_code; |
4ed46869 KH |
3685 | ONE_MORE_BYTE (c1); |
3686 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3687 | goto invalid_code; |
4ed46869 KH |
3688 | ONE_MORE_BYTE (c1); |
3689 | goto label_escape_sequence; | |
3690 | ||
3691 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3692 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3693 | goto invalid_code; | |
134b9549 KH |
3694 | { |
3695 | int reg, chars96; | |
3696 | ||
3697 | ONE_MORE_BYTE (c1); | |
3698 | if (c1 >= '@' && c1 <= 'B') | |
3699 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3700 | or JISX0208.1980 */ |
134b9549 KH |
3701 | reg = 0, chars96 = 0; |
3702 | } | |
3703 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3704 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3705 | reg = c1 - 0x28, chars96 = 0; | |
3706 | ONE_MORE_BYTE (c1); | |
3707 | } | |
3708 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3709 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3710 | reg = c1 - 0x2C, chars96 = 1; | |
3711 | ONE_MORE_BYTE (c1); | |
3712 | } | |
3713 | else | |
3714 | goto invalid_code; | |
3715 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3716 | /* We must update these variables now. */ | |
3717 | if (reg == 0) | |
3718 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3719 | else if (reg == 1) | |
3720 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3721 | if (chars96 < 0) | |
3722 | goto invalid_code; | |
3723 | } | |
b73bfc1c | 3724 | continue; |
4ed46869 KH |
3725 | |
3726 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3727 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3728 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3729 | goto invalid_code; | |
3730 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3731 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3732 | continue; |
4ed46869 KH |
3733 | |
3734 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3735 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3736 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3737 | goto invalid_code; | |
3738 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3739 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3740 | continue; |
4ed46869 KH |
3741 | |
3742 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3743 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3744 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3745 | goto invalid_code; | |
134b9549 KH |
3746 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3747 | if (charset_id_2 < 0) | |
3748 | charset = CHARSET_FROM_ID (charset_ascii); | |
3749 | else | |
3750 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3751 | ONE_MORE_BYTE (c1); |
e7046a18 | 3752 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3753 | goto invalid_code; |
4ed46869 KH |
3754 | break; |
3755 | ||
3756 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3757 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3758 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3759 | goto invalid_code; | |
134b9549 KH |
3760 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3761 | if (charset_id_3 < 0) | |
3762 | charset = CHARSET_FROM_ID (charset_ascii); | |
3763 | else | |
3764 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3765 | ONE_MORE_BYTE (c1); |
e7046a18 | 3766 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3767 | goto invalid_code; |
4ed46869 KH |
3768 | break; |
3769 | ||
ec6d2bb8 | 3770 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3771 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3772 | goto invalid_code; | |
e951386e KH |
3773 | if (last_id != charset_ascii) |
3774 | { | |
3775 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | |
3776 | last_id = charset_ascii; | |
3777 | last_offset = char_offset; | |
3778 | } | |
ec6d2bb8 | 3779 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3780 | continue; |
4ed46869 | 3781 | |
ec6d2bb8 | 3782 | case '1': /* end composition */ |
e951386e | 3783 | if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3784 | goto invalid_code; |
3785 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3786 | continue; |
4ed46869 KH |
3787 | |
3788 | case '[': /* specification of direction */ | |
de59072a | 3789 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)) |
df7492f9 | 3790 | goto invalid_code; |
4ed46869 | 3791 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3792 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
ad1746f5 | 3793 | left-to-right, and nonzero means right-to-left. */ |
4ed46869 KH |
3794 | ONE_MORE_BYTE (c1); |
3795 | switch (c1) | |
3796 | { | |
3797 | case ']': /* end of the current direction */ | |
d46c5b12 | 3798 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3799 | |
3800 | case '0': /* end of the current direction */ | |
3801 | case '1': /* start of left-to-right direction */ | |
3802 | ONE_MORE_BYTE (c1); | |
3803 | if (c1 == ']') | |
d46c5b12 | 3804 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3805 | else |
df7492f9 | 3806 | goto invalid_code; |
4ed46869 KH |
3807 | break; |
3808 | ||
3809 | case '2': /* start of right-to-left direction */ | |
3810 | ONE_MORE_BYTE (c1); | |
3811 | if (c1 == ']') | |
d46c5b12 | 3812 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3813 | else |
df7492f9 | 3814 | goto invalid_code; |
4ed46869 KH |
3815 | break; |
3816 | ||
3817 | default: | |
df7492f9 | 3818 | goto invalid_code; |
4ed46869 | 3819 | } |
b73bfc1c | 3820 | continue; |
4ed46869 | 3821 | |
103e0180 | 3822 | case '%': |
103e0180 KH |
3823 | ONE_MORE_BYTE (c1); |
3824 | if (c1 == '/') | |
3825 | { | |
3826 | /* CTEXT extended segment: | |
3827 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3828 | We keep these bytes as is for the moment. | |
3829 | They may be decoded by post-read-conversion. */ | |
3830 | int dim, M, L; | |
4776e638 | 3831 | int size; |
8f924df7 | 3832 | |
103e0180 | 3833 | ONE_MORE_BYTE (dim); |
7a84eee5 | 3834 | if (dim < '0' || dim > '4') |
e951386e | 3835 | goto invalid_code; |
103e0180 | 3836 | ONE_MORE_BYTE (M); |
e951386e KH |
3837 | if (M < 128) |
3838 | goto invalid_code; | |
103e0180 | 3839 | ONE_MORE_BYTE (L); |
e951386e KH |
3840 | if (L < 128) |
3841 | goto invalid_code; | |
103e0180 | 3842 | size = ((M - 128) * 128) + (L - 128); |
e951386e | 3843 | if (charbuf + 6 > charbuf_end) |
4776e638 KH |
3844 | goto break_loop; |
3845 | *charbuf++ = ISO_CODE_ESC; | |
3846 | *charbuf++ = '%'; | |
3847 | *charbuf++ = '/'; | |
3848 | *charbuf++ = dim; | |
3849 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3850 | *charbuf++ = BYTE8_TO_CHAR (L); | |
e951386e | 3851 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
103e0180 KH |
3852 | } |
3853 | else if (c1 == 'G') | |
3854 | { | |
103e0180 KH |
3855 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3856 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3857 | We keep these bytes as is for the moment. | |
3858 | They may be decoded by post-read-conversion. */ | |
e951386e | 3859 | if (charbuf + 3 > charbuf_end) |
4776e638 | 3860 | goto break_loop; |
e951386e KH |
3861 | *charbuf++ = ISO_CODE_ESC; |
3862 | *charbuf++ = '%'; | |
3863 | *charbuf++ = 'G'; | |
3864 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; | |
103e0180 KH |
3865 | } |
3866 | else | |
4776e638 | 3867 | goto invalid_code; |
103e0180 | 3868 | continue; |
4776e638 | 3869 | break; |
103e0180 | 3870 | |
4ed46869 | 3871 | default: |
df7492f9 KH |
3872 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3873 | goto invalid_code; | |
134b9549 KH |
3874 | { |
3875 | int reg, chars96; | |
3876 | ||
3877 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3878 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3879 | reg = c1 - 0x28, chars96 = 0; | |
3880 | ONE_MORE_BYTE (c1); | |
3881 | } | |
3882 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3883 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3884 | reg = c1 - 0x2C, chars96 = 1; | |
3885 | ONE_MORE_BYTE (c1); | |
3886 | } | |
3887 | else | |
3888 | goto invalid_code; | |
3889 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3890 | /* We must update these variables now. */ | |
3891 | if (reg == 0) | |
3892 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3893 | else if (reg == 1) | |
3894 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3895 | if (chars96 < 0) | |
3896 | goto invalid_code; | |
3897 | } | |
b73bfc1c | 3898 | continue; |
4ed46869 | 3899 | } |
b73bfc1c | 3900 | } |
4ed46869 | 3901 | |
e951386e KH |
3902 | if (cmp_status->state == COMPOSING_NO |
3903 | && charset->id != charset_ascii | |
ff0dacd7 KH |
3904 | && last_id != charset->id) |
3905 | { | |
3906 | if (last_id != charset_ascii) | |
69a80ea3 | 3907 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3908 | last_id = charset->id; |
3909 | last_offset = char_offset; | |
3910 | } | |
3911 | ||
b73bfc1c | 3912 | /* Now we know CHARSET and 1st position code C1 of a character. |
cf299835 KH |
3913 | Produce a decoded character while getting 2nd and 3rd |
3914 | position codes C2, C3 if necessary. */ | |
df7492f9 | 3915 | if (CHARSET_DIMENSION (charset) > 1) |
b73bfc1c KH |
3916 | { |
3917 | ONE_MORE_BYTE (c2); | |
cf299835 KH |
3918 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0) |
3919 | || ((c1 & 0x80) != (c2 & 0x80))) | |
b73bfc1c | 3920 | /* C2 is not in a valid range. */ |
df7492f9 | 3921 | goto invalid_code; |
cf299835 KH |
3922 | if (CHARSET_DIMENSION (charset) == 2) |
3923 | c1 = (c1 << 8) | c2; | |
3924 | else | |
df7492f9 | 3925 | { |
cf299835 KH |
3926 | ONE_MORE_BYTE (c3); |
3927 | if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0) | |
3928 | || ((c1 & 0x80) != (c3 & 0x80))) | |
3929 | /* C3 is not in a valid range. */ | |
df7492f9 | 3930 | goto invalid_code; |
cf299835 | 3931 | c1 = (c1 << 16) | (c2 << 8) | c2; |
df7492f9 KH |
3932 | } |
3933 | } | |
cf299835 | 3934 | c1 &= 0x7F7F7F; |
df7492f9 KH |
3935 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); |
3936 | if (c < 0) | |
3937 | { | |
3938 | MAYBE_FINISH_COMPOSITION (); | |
3939 | for (; src_base < src; src_base++, char_offset++) | |
3940 | { | |
3941 | if (ASCII_BYTE_P (*src_base)) | |
3942 | *charbuf++ = *src_base; | |
3943 | else | |
3944 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3945 | } | |
3946 | } | |
e951386e | 3947 | else if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3948 | { |
3949 | *charbuf++ = c; | |
3950 | char_offset++; | |
4ed46869 | 3951 | } |
e951386e KH |
3952 | else if ((cmp_status->state == COMPOSING_CHAR |
3953 | ? cmp_status->nchars | |
3954 | : cmp_status->ncomps) | |
3955 | >= MAX_COMPOSITION_COMPONENTS) | |
781d7a48 | 3956 | { |
e951386e KH |
3957 | /* Too long composition. */ |
3958 | MAYBE_FINISH_COMPOSITION (); | |
3959 | *charbuf++ = c; | |
3960 | char_offset++; | |
4ed46869 | 3961 | } |
e951386e KH |
3962 | else |
3963 | STORE_COMPOSITION_CHAR (c); | |
4ed46869 KH |
3964 | continue; |
3965 | ||
df7492f9 KH |
3966 | invalid_code: |
3967 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3968 | src = src_base; |
df7492f9 KH |
3969 | consumed_chars = consumed_chars_base; |
3970 | ONE_MORE_BYTE (c); | |
065e3595 | 3971 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3972 | char_offset++; |
df7492f9 | 3973 | coding->errors++; |
4776e638 KH |
3974 | continue; |
3975 | ||
3976 | break_loop: | |
3977 | break; | |
4ed46869 | 3978 | } |
fb88bf2d | 3979 | |
df7492f9 | 3980 | no_more_source: |
e951386e KH |
3981 | if (cmp_status->state != COMPOSING_NO) |
3982 | { | |
3983 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
3984 | MAYBE_FINISH_COMPOSITION (); | |
3985 | else | |
3986 | { | |
3987 | charbuf -= cmp_status->length; | |
3988 | for (i = 0; i < cmp_status->length; i++) | |
3989 | cmp_status->carryover[i] = charbuf[i]; | |
3990 | } | |
3991 | } | |
3992 | else if (last_id != charset_ascii) | |
69a80ea3 | 3993 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3994 | coding->consumed_char += consumed_chars_base; |
3995 | coding->consumed = src_base - coding->source; | |
3996 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3997 | } |
3998 | ||
b73bfc1c | 3999 | |
f4dee582 | 4000 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
4001 | |
4002 | /* | |
f4dee582 | 4003 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 4004 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 4005 | variant has the following specifications: |
df7492f9 | 4006 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
4007 | 2. Allows short-form designation? |
4008 | 3. ASCII should be designated to G0 before control characters? | |
4009 | 4. ASCII should be designated to G0 at end of line? | |
4010 | 5. 7-bit environment or 8-bit environment? | |
4011 | 6. Use locking-shift? | |
4012 | 7. Use Single-shift? | |
4013 | And the following two are only for Japanese: | |
4014 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
4015 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
4016 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
4017 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 4018 | details. |
4ed46869 KH |
4019 | */ |
4020 | ||
4021 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
4022 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
4023 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
4024 | designation sequence of short-form. */ | |
4ed46869 KH |
4025 | |
4026 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
4027 | do { \ | |
df7492f9 | 4028 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
675e2c69 DN |
4029 | const char *intermediate_char_94 = "()*+"; \ |
4030 | const char *intermediate_char_96 = ",-./"; \ | |
df7492f9 KH |
4031 | int revision = -1; \ |
4032 | int c; \ | |
4033 | \ | |
4034 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 4035 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
4036 | \ |
4037 | if (revision >= 0) \ | |
70c22245 | 4038 | { \ |
df7492f9 KH |
4039 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
4040 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 4041 | } \ |
df7492f9 | 4042 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
4043 | if (CHARSET_DIMENSION (charset) == 1) \ |
4044 | { \ | |
df7492f9 KH |
4045 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
4046 | c = intermediate_char_94[reg]; \ | |
4ed46869 | 4047 | else \ |
df7492f9 KH |
4048 | c = intermediate_char_96[reg]; \ |
4049 | EMIT_ONE_ASCII_BYTE (c); \ | |
4ed46869 KH |
4050 | } \ |
4051 | else \ | |
4052 | { \ | |
df7492f9 KH |
4053 | EMIT_ONE_ASCII_BYTE ('$'); \ |
4054 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 4055 | { \ |
df7492f9 | 4056 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
4057 | || reg != 0 \ |
4058 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 4059 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
4060 | } \ |
4061 | else \ | |
df7492f9 | 4062 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 4063 | } \ |
df7492f9 KH |
4064 | EMIT_ONE_ASCII_BYTE (final_char); \ |
4065 | \ | |
4066 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
4067 | } while (0) |
4068 | ||
df7492f9 | 4069 | |
4ed46869 KH |
4070 | /* The following two macros produce codes (control character or escape |
4071 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
4072 | single-shift-3). */ | |
4073 | ||
df7492f9 KH |
4074 | #define ENCODE_SINGLE_SHIFT_2 \ |
4075 | do { \ | |
4076 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4077 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
4078 | else \ | |
4079 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
4080 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4081 | } while (0) |
4082 | ||
df7492f9 KH |
4083 | |
4084 | #define ENCODE_SINGLE_SHIFT_3 \ | |
4085 | do { \ | |
4086 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4087 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
4088 | else \ | |
4089 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
4090 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4091 | } while (0) |
4092 | ||
df7492f9 | 4093 | |
4ed46869 KH |
4094 | /* The following four macros produce codes (control character or |
4095 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
4096 | shift-out, locking-shift-2, and locking-shift-3). */ | |
4097 | ||
df7492f9 KH |
4098 | #define ENCODE_SHIFT_IN \ |
4099 | do { \ | |
4100 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
4101 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
4102 | } while (0) |
4103 | ||
df7492f9 KH |
4104 | |
4105 | #define ENCODE_SHIFT_OUT \ | |
4106 | do { \ | |
4107 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
4108 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
4109 | } while (0) |
4110 | ||
df7492f9 KH |
4111 | |
4112 | #define ENCODE_LOCKING_SHIFT_2 \ | |
4113 | do { \ | |
4114 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4115 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
4116 | } while (0) |
4117 | ||
df7492f9 KH |
4118 | |
4119 | #define ENCODE_LOCKING_SHIFT_3 \ | |
4120 | do { \ | |
4121 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4122 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
4123 | } while (0) |
4124 | ||
df7492f9 | 4125 | |
f4dee582 RS |
4126 | /* Produce codes for a DIMENSION1 character whose character set is |
4127 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
4128 | sequences are also produced in advance if necessary. */ |
4129 | ||
6e85d753 KH |
4130 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
4131 | do { \ | |
df7492f9 | 4132 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4133 | \ |
4134 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
4135 | && id == charset_ascii) \ | |
4136 | { \ | |
4137 | id = charset_jisx0201_roman; \ | |
4138 | charset = CHARSET_FROM_ID (id); \ | |
4139 | } \ | |
4140 | \ | |
df7492f9 | 4141 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4142 | { \ |
df7492f9 KH |
4143 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4144 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 4145 | else \ |
df7492f9 KH |
4146 | EMIT_ONE_BYTE (c1 | 0x80); \ |
4147 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4148 | break; \ |
4149 | } \ | |
df7492f9 | 4150 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4151 | { \ |
df7492f9 | 4152 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
4153 | break; \ |
4154 | } \ | |
df7492f9 | 4155 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4156 | { \ |
df7492f9 | 4157 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
4158 | break; \ |
4159 | } \ | |
6e85d753 KH |
4160 | else \ |
4161 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4162 | must invoke it, or, at first, designate it to some graphic \ | |
4163 | register. Then repeat the loop to actually produce the \ | |
4164 | character. */ \ | |
df7492f9 KH |
4165 | dst = encode_invocation_designation (charset, coding, dst, \ |
4166 | &produced_chars); \ | |
4ed46869 KH |
4167 | } while (1) |
4168 | ||
df7492f9 | 4169 | |
f4dee582 RS |
4170 | /* Produce codes for a DIMENSION2 character whose character set is |
4171 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
4172 | invocation codes are also produced in advance if necessary. */ |
4173 | ||
6e85d753 KH |
4174 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
4175 | do { \ | |
df7492f9 | 4176 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4177 | \ |
4178 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
4179 | && id == charset_jisx0208) \ | |
4180 | { \ | |
4181 | id = charset_jisx0208_1978; \ | |
4182 | charset = CHARSET_FROM_ID (id); \ | |
4183 | } \ | |
4184 | \ | |
df7492f9 | 4185 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4186 | { \ |
df7492f9 KH |
4187 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4188 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 4189 | else \ |
df7492f9 KH |
4190 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
4191 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4192 | break; \ |
4193 | } \ | |
df7492f9 | 4194 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4195 | { \ |
df7492f9 | 4196 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
4197 | break; \ |
4198 | } \ | |
df7492f9 | 4199 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4200 | { \ |
df7492f9 | 4201 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
4202 | break; \ |
4203 | } \ | |
6e85d753 KH |
4204 | else \ |
4205 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4206 | must invoke it, or, at first, designate it to some graphic \ | |
4207 | register. Then repeat the loop to actually produce the \ | |
4208 | character. */ \ | |
df7492f9 KH |
4209 | dst = encode_invocation_designation (charset, coding, dst, \ |
4210 | &produced_chars); \ | |
4ed46869 KH |
4211 | } while (1) |
4212 | ||
05e6f5dc | 4213 | |
df7492f9 KH |
4214 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
4215 | do { \ | |
1a4990fb | 4216 | int code = ENCODE_CHAR ((charset), (c)); \ |
df7492f9 KH |
4217 | \ |
4218 | if (CHARSET_DIMENSION (charset) == 1) \ | |
4219 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
4220 | else \ | |
4221 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 4222 | } while (0) |
bdd9fb48 | 4223 | |
05e6f5dc | 4224 | |
4ed46869 | 4225 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 4226 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
4227 | Return new DST. */ |
4228 | ||
4229 | unsigned char * | |
cf84bb53 JB |
4230 | encode_invocation_designation (struct charset *charset, |
4231 | struct coding_system *coding, | |
4232 | unsigned char *dst, int *p_nchars) | |
4ed46869 | 4233 | { |
df7492f9 KH |
4234 | int multibytep = coding->dst_multibyte; |
4235 | int produced_chars = *p_nchars; | |
4ed46869 | 4236 | int reg; /* graphic register number */ |
df7492f9 | 4237 | int id = CHARSET_ID (charset); |
4ed46869 KH |
4238 | |
4239 | /* At first, check designations. */ | |
4240 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 4241 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
4242 | break; |
4243 | ||
4244 | if (reg >= 4) | |
4245 | { | |
4246 | /* CHARSET is not yet designated to any graphic registers. */ | |
4247 | /* At first check the requested designation. */ | |
df7492f9 KH |
4248 | reg = CODING_ISO_REQUEST (coding, id); |
4249 | if (reg < 0) | |
1ba9e4ab KH |
4250 | /* Since CHARSET requests no special designation, designate it |
4251 | to graphic register 0. */ | |
4ed46869 KH |
4252 | reg = 0; |
4253 | ||
4254 | ENCODE_DESIGNATION (charset, reg, coding); | |
4255 | } | |
4256 | ||
df7492f9 KH |
4257 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
4258 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
4259 | { |
4260 | /* Since the graphic register REG is not invoked to any graphic | |
4261 | planes, invoke it to graphic plane 0. */ | |
4262 | switch (reg) | |
4263 | { | |
4264 | case 0: /* graphic register 0 */ | |
4265 | ENCODE_SHIFT_IN; | |
4266 | break; | |
4267 | ||
4268 | case 1: /* graphic register 1 */ | |
4269 | ENCODE_SHIFT_OUT; | |
4270 | break; | |
4271 | ||
4272 | case 2: /* graphic register 2 */ | |
df7492f9 | 4273 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4274 | ENCODE_SINGLE_SHIFT_2; |
4275 | else | |
4276 | ENCODE_LOCKING_SHIFT_2; | |
4277 | break; | |
4278 | ||
4279 | case 3: /* graphic register 3 */ | |
df7492f9 | 4280 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4281 | ENCODE_SINGLE_SHIFT_3; |
4282 | else | |
4283 | ENCODE_LOCKING_SHIFT_3; | |
4284 | break; | |
4285 | } | |
4286 | } | |
b73bfc1c | 4287 | |
df7492f9 | 4288 | *p_nchars = produced_chars; |
4ed46869 KH |
4289 | return dst; |
4290 | } | |
4291 | ||
df7492f9 KH |
4292 | /* The following three macros produce codes for indicating direction |
4293 | of text. */ | |
4294 | #define ENCODE_CONTROL_SEQUENCE_INTRODUCER \ | |
ec6d2bb8 | 4295 | do { \ |
df7492f9 KH |
4296 | if (CODING_ISO_FLAGS (coding) == CODING_ISO_FLAG_SEVEN_BITS) \ |
4297 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '['); \ | |
ec6d2bb8 | 4298 | else \ |
df7492f9 | 4299 | EMIT_ONE_BYTE (ISO_CODE_CSI); \ |
ec6d2bb8 KH |
4300 | } while (0) |
4301 | ||
ec6d2bb8 | 4302 | |
df7492f9 KH |
4303 | #define ENCODE_DIRECTION_R2L() \ |
4304 | do { \ | |
4305 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ | |
4306 | EMIT_TWO_ASCII_BYTES ('2', ']'); \ | |
ec6d2bb8 KH |
4307 | } while (0) |
4308 | ||
ec6d2bb8 | 4309 | |
df7492f9 | 4310 | #define ENCODE_DIRECTION_L2R() \ |
ec6d2bb8 | 4311 | do { \ |
df7492f9 KH |
4312 | ENCODE_CONTROL_SEQUENCE_INTRODUCER (dst); \ |
4313 | EMIT_TWO_ASCII_BYTES ('0', ']'); \ | |
ec6d2bb8 | 4314 | } while (0) |
4ed46869 | 4315 | |
4ed46869 KH |
4316 | |
4317 | /* Produce codes for designation and invocation to reset the graphic | |
4318 | planes and registers to initial state. */ | |
df7492f9 KH |
4319 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4320 | do { \ | |
4321 | int reg; \ | |
4322 | struct charset *charset; \ | |
4323 | \ | |
4324 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4325 | ENCODE_SHIFT_IN; \ | |
4326 | for (reg = 0; reg < 4; reg++) \ | |
4327 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4328 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4329 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4330 | { \ | |
4331 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4332 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4333 | } \ | |
4ed46869 KH |
4334 | } while (0) |
4335 | ||
df7492f9 | 4336 | |
bdd9fb48 | 4337 | /* Produce designation sequences of charsets in the line started from |
b73bfc1c | 4338 | SRC to a place pointed by DST, and return updated DST. |
bdd9fb48 KH |
4339 | |
4340 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4341 | find all the necessary designations. */ |
4342 | ||
b73bfc1c | 4343 | static unsigned char * |
cf84bb53 JB |
4344 | encode_designation_at_bol (struct coding_system *coding, int *charbuf, |
4345 | int *charbuf_end, unsigned char *dst) | |
e0e989f6 | 4346 | { |
df7492f9 | 4347 | struct charset *charset; |
bdd9fb48 KH |
4348 | /* Table of charsets to be designated to each graphic register. */ |
4349 | int r[4]; | |
df7492f9 KH |
4350 | int c, found = 0, reg; |
4351 | int produced_chars = 0; | |
4352 | int multibytep = coding->dst_multibyte; | |
4353 | Lisp_Object attrs; | |
4354 | Lisp_Object charset_list; | |
4355 | ||
4356 | attrs = CODING_ID_ATTRS (coding->id); | |
4357 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4358 | if (EQ (charset_list, Qiso_2022)) | |
4359 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4360 | |
4361 | for (reg = 0; reg < 4; reg++) | |
4362 | r[reg] = -1; | |
4363 | ||
b73bfc1c | 4364 | while (found < 4) |
e0e989f6 | 4365 | { |
df7492f9 KH |
4366 | int id; |
4367 | ||
4368 | c = *charbuf++; | |
b73bfc1c KH |
4369 | if (c == '\n') |
4370 | break; | |
df7492f9 KH |
4371 | charset = char_charset (c, charset_list, NULL); |
4372 | id = CHARSET_ID (charset); | |
4373 | reg = CODING_ISO_REQUEST (coding, id); | |
4374 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4375 | { |
4376 | found++; | |
df7492f9 | 4377 | r[reg] = id; |
bdd9fb48 | 4378 | } |
bdd9fb48 KH |
4379 | } |
4380 | ||
4381 | if (found) | |
4382 | { | |
4383 | for (reg = 0; reg < 4; reg++) | |
4384 | if (r[reg] >= 0 | |
df7492f9 KH |
4385 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4386 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4387 | } |
b73bfc1c KH |
4388 | |
4389 | return dst; | |
e0e989f6 KH |
4390 | } |
4391 | ||
4ed46869 KH |
4392 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4393 | ||
df7492f9 | 4394 | static int |
971de7fb | 4395 | encode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 4396 | { |
df7492f9 KH |
4397 | int multibytep = coding->dst_multibyte; |
4398 | int *charbuf = coding->charbuf; | |
4399 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4400 | unsigned char *dst = coding->destination + coding->produced; | |
4401 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4402 | int safe_room = 16; | |
4403 | int bol_designation | |
4404 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL | |
4405 | && CODING_ISO_BOL (coding)); | |
4406 | int produced_chars = 0; | |
4407 | Lisp_Object attrs, eol_type, charset_list; | |
4408 | int ascii_compatible; | |
b73bfc1c | 4409 | int c; |
ff0dacd7 | 4410 | int preferred_charset_id = -1; |
05e6f5dc | 4411 | |
24a73b0a | 4412 | CODING_GET_INFO (coding, attrs, charset_list); |
0a9564cb | 4413 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
24a73b0a KH |
4414 | if (VECTORP (eol_type)) |
4415 | eol_type = Qunix; | |
4416 | ||
004068e4 | 4417 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4418 | /* Charset list may have been changed. */ |
287c57d7 | 4419 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
1b3b981b | 4420 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
0eecad43 | 4421 | |
a552b35a KH |
4422 | ascii_compatible |
4423 | = (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)) | |
4424 | && ! (CODING_ISO_FLAGS (coding) & (CODING_ISO_FLAG_DESIGNATION | |
4425 | | CODING_ISO_FLAG_LOCKING_SHIFT))); | |
bdd9fb48 | 4426 | |
df7492f9 | 4427 | while (charbuf < charbuf_end) |
4ed46869 | 4428 | { |
df7492f9 | 4429 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4430 | |
df7492f9 | 4431 | if (bol_designation) |
b73bfc1c | 4432 | { |
df7492f9 | 4433 | unsigned char *dst_prev = dst; |
4ed46869 | 4434 | |
bdd9fb48 | 4435 | /* We have to produce designation sequences if any now. */ |
df7492f9 KH |
4436 | dst = encode_designation_at_bol (coding, charbuf, charbuf_end, dst); |
4437 | bol_designation = 0; | |
4438 | /* We are sure that designation sequences are all ASCII bytes. */ | |
4439 | produced_chars += dst - dst_prev; | |
e0e989f6 KH |
4440 | } |
4441 | ||
df7492f9 | 4442 | c = *charbuf++; |
ec6d2bb8 | 4443 | |
ff0dacd7 KH |
4444 | if (c < 0) |
4445 | { | |
4446 | /* Handle an annotation. */ | |
4447 | switch (*charbuf) | |
ec6d2bb8 | 4448 | { |
ff0dacd7 KH |
4449 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4450 | /* Not yet implemented. */ | |
4451 | break; | |
4452 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4453 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4454 | if (preferred_charset_id >= 0 |
4455 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4456 | charset_list))) | |
4457 | preferred_charset_id = -1; | |
4458 | break; | |
4459 | default: | |
4460 | abort (); | |
4ed46869 | 4461 | } |
ff0dacd7 KH |
4462 | charbuf += -c - 1; |
4463 | continue; | |
4ed46869 | 4464 | } |
ec6d2bb8 | 4465 | |
b73bfc1c KH |
4466 | /* Now encode the character C. */ |
4467 | if (c < 0x20 || c == 0x7F) | |
4468 | { | |
df7492f9 KH |
4469 | if (c == '\n' |
4470 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4471 | { |
df7492f9 KH |
4472 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4473 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4474 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4475 | { |
df7492f9 KH |
4476 | int i; |
4477 | ||
4478 | for (i = 0; i < 4; i++) | |
4479 | CODING_ISO_DESIGNATION (coding, i) | |
4480 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4481 | } |
df7492f9 KH |
4482 | bol_designation |
4483 | = CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL; | |
19a8d9e0 | 4484 | } |
df7492f9 KH |
4485 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4486 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4487 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4488 | } |
df7492f9 | 4489 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4490 | { |
df7492f9 KH |
4491 | if (ascii_compatible) |
4492 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4493 | else |
19a8d9e0 | 4494 | { |
bf16eb23 KH |
4495 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4496 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4497 | } |
4ed46869 | 4498 | } |
16eafb5d | 4499 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4500 | { |
16eafb5d KH |
4501 | c = CHAR_TO_BYTE8 (c); |
4502 | EMIT_ONE_BYTE (c); | |
88993dfd | 4503 | } |
b73bfc1c | 4504 | else |
df7492f9 | 4505 | { |
ff0dacd7 | 4506 | struct charset *charset; |
b73bfc1c | 4507 | |
ff0dacd7 KH |
4508 | if (preferred_charset_id >= 0) |
4509 | { | |
4510 | charset = CHARSET_FROM_ID (preferred_charset_id); | |
4511 | if (! CHAR_CHARSET_P (c, charset)) | |
4512 | charset = char_charset (c, charset_list, NULL); | |
4513 | } | |
4514 | else | |
4515 | charset = char_charset (c, charset_list, NULL); | |
df7492f9 KH |
4516 | if (!charset) |
4517 | { | |
41cbe562 KH |
4518 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4519 | { | |
4520 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4521 | charset = CHARSET_FROM_ID (charset_ascii); | |
4522 | } | |
4523 | else | |
4524 | { | |
4525 | c = coding->default_char; | |
4526 | charset = char_charset (c, charset_list, NULL); | |
4527 | } | |
df7492f9 KH |
4528 | } |
4529 | ENCODE_ISO_CHARACTER (charset, c); | |
4530 | } | |
84fbb8a0 | 4531 | } |
b73bfc1c | 4532 | |
df7492f9 KH |
4533 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4534 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4535 | { | |
4536 | ASSURE_DESTINATION (safe_room); | |
4537 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4538 | } | |
065e3595 | 4539 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4540 | CODING_ISO_BOL (coding) = bol_designation; |
4541 | coding->produced_char += produced_chars; | |
4542 | coding->produced = dst - coding->destination; | |
4543 | return 0; | |
4ed46869 KH |
4544 | } |
4545 | ||
4546 | \f | |
df7492f9 | 4547 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4548 | |
df7492f9 | 4549 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4550 | quite widely. So, for the moment, Emacs supports them in the bare |
4551 | C code. But, in the future, they may be supported only by CCL. */ | |
4552 | ||
4553 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4554 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4555 | as is. A character of charset katakana-jisx0201 is encoded by | |
4556 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4557 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4558 | so that it fit in the range below. |
4ed46869 KH |
4559 | |
4560 | --- CODE RANGE of SJIS --- | |
4561 | (character set) (range) | |
4562 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4563 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4564 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4565 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4566 | ------------------------------- |
4567 | ||
4568 | */ | |
4569 | ||
4570 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4571 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4572 | character set and is encoded in two-byte. |
4ed46869 KH |
4573 | |
4574 | --- CODE RANGE of BIG5 --- | |
4575 | (character set) (range) | |
4576 | ASCII 0x00 .. 0x7F | |
4577 | Big5 (1st byte) 0xA1 .. 0xFE | |
4578 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4579 | -------------------------- | |
4580 | ||
df7492f9 | 4581 | */ |
4ed46869 KH |
4582 | |
4583 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4584 | Check if a text is encoded in SJIS. If it is, return | |
df7492f9 | 4585 | CATEGORY_MASK_SJIS, else return 0. */ |
4ed46869 | 4586 | |
0a28aafb | 4587 | static int |
cf84bb53 JB |
4588 | detect_coding_sjis (struct coding_system *coding, |
4589 | struct coding_detection_info *detect_info) | |
4ed46869 | 4590 | { |
065e3595 | 4591 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4592 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4593 | int multibytep = coding->src_multibyte; |
4594 | int consumed_chars = 0; | |
4595 | int found = 0; | |
b73bfc1c | 4596 | int c; |
f07190ca KH |
4597 | Lisp_Object attrs, charset_list; |
4598 | int max_first_byte_of_2_byte_code; | |
4599 | ||
4600 | CODING_GET_INFO (coding, attrs, charset_list); | |
4601 | max_first_byte_of_2_byte_code | |
4602 | = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF); | |
df7492f9 | 4603 | |
ff0dacd7 | 4604 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4605 | /* A coding system of this category is always ASCII compatible. */ |
4606 | src += coding->head_ascii; | |
4ed46869 | 4607 | |
b73bfc1c | 4608 | while (1) |
4ed46869 | 4609 | { |
065e3595 | 4610 | src_base = src; |
df7492f9 | 4611 | ONE_MORE_BYTE (c); |
682169fe KH |
4612 | if (c < 0x80) |
4613 | continue; | |
f07190ca KH |
4614 | if ((c >= 0x81 && c <= 0x9F) |
4615 | || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code)) | |
4ed46869 | 4616 | { |
df7492f9 | 4617 | ONE_MORE_BYTE (c); |
682169fe | 4618 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4619 | break; |
ff0dacd7 | 4620 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4621 | } |
df7492f9 | 4622 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4623 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4624 | else |
4625 | break; | |
4ed46869 | 4626 | } |
ff0dacd7 | 4627 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4628 | return 0; |
4629 | ||
4630 | no_more_source: | |
065e3595 | 4631 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4632 | { |
ff0dacd7 | 4633 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 4634 | return 0; |
4ed46869 | 4635 | } |
ff0dacd7 KH |
4636 | detect_info->found |= found; |
4637 | return 1; | |
4ed46869 KH |
4638 | } |
4639 | ||
4640 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
4641 | Check if a text is encoded in BIG5. If it is, return | |
df7492f9 | 4642 | CATEGORY_MASK_BIG5, else return 0. */ |
4ed46869 | 4643 | |
0a28aafb | 4644 | static int |
cf84bb53 JB |
4645 | detect_coding_big5 (struct coding_system *coding, |
4646 | struct coding_detection_info *detect_info) | |
4ed46869 | 4647 | { |
065e3595 | 4648 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4649 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
4650 | int multibytep = coding->src_multibyte; |
4651 | int consumed_chars = 0; | |
4652 | int found = 0; | |
b73bfc1c | 4653 | int c; |
fa42c37f | 4654 | |
ff0dacd7 | 4655 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4656 | /* A coding system of this category is always ASCII compatible. */ |
4657 | src += coding->head_ascii; | |
fa42c37f | 4658 | |
b73bfc1c | 4659 | while (1) |
fa42c37f | 4660 | { |
065e3595 | 4661 | src_base = src; |
df7492f9 KH |
4662 | ONE_MORE_BYTE (c); |
4663 | if (c < 0x80) | |
fa42c37f | 4664 | continue; |
df7492f9 | 4665 | if (c >= 0xA1) |
fa42c37f | 4666 | { |
df7492f9 KH |
4667 | ONE_MORE_BYTE (c); |
4668 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4669 | return 0; |
ff0dacd7 | 4670 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4671 | } |
df7492f9 KH |
4672 | else |
4673 | break; | |
fa42c37f | 4674 | } |
ff0dacd7 | 4675 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4676 | return 0; |
fa42c37f | 4677 | |
df7492f9 | 4678 | no_more_source: |
065e3595 | 4679 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4680 | { |
ff0dacd7 | 4681 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4682 | return 0; |
4683 | } | |
ff0dacd7 KH |
4684 | detect_info->found |= found; |
4685 | return 1; | |
fa42c37f KH |
4686 | } |
4687 | ||
4ed46869 KH |
4688 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". |
4689 | If SJIS_P is 1, decode SJIS text, else decode BIG5 test. */ | |
fa42c37f | 4690 | |
b73bfc1c | 4691 | static void |
971de7fb | 4692 | decode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4693 | { |
8f924df7 KH |
4694 | const unsigned char *src = coding->source + coding->consumed; |
4695 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4696 | const unsigned char *src_base; | |
69a80ea3 | 4697 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4698 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4699 | the end. */ |
69a80ea3 | 4700 | int *charbuf_end |
df80c7f0 | 4701 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
4702 | int consumed_chars = 0, consumed_chars_base; |
4703 | int multibytep = coding->src_multibyte; | |
4704 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4705 | struct charset *charset_kanji2; |
24a73b0a | 4706 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4707 | int char_offset = coding->produced_char; |
4708 | int last_offset = char_offset; | |
4709 | int last_id = charset_ascii; | |
0a9564cb EZ |
4710 | int eol_crlf = |
4711 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4712 | int byte_after_cr = -1; |
a5d301df | 4713 | |
24a73b0a | 4714 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4715 | |
4716 | val = charset_list; | |
4717 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4718 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4719 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4720 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4721 | |
b73bfc1c | 4722 | while (1) |
4ed46869 | 4723 | { |
df7492f9 | 4724 | int c, c1; |
24a73b0a | 4725 | struct charset *charset; |
fa42c37f | 4726 | |
b73bfc1c | 4727 | src_base = src; |
df7492f9 | 4728 | consumed_chars_base = consumed_chars; |
fa42c37f | 4729 | |
df7492f9 | 4730 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4731 | { |
4732 | if (byte_after_cr >= 0) | |
4733 | src_base--; | |
4734 | break; | |
4735 | } | |
df7492f9 | 4736 | |
119852e7 KH |
4737 | if (byte_after_cr >= 0) |
4738 | c = byte_after_cr, byte_after_cr = -1; | |
4739 | else | |
4740 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4741 | if (c < 0) |
4742 | goto invalid_code; | |
24a73b0a | 4743 | if (c < 0x80) |
119852e7 KH |
4744 | { |
4745 | if (eol_crlf && c == '\r') | |
4746 | ONE_MORE_BYTE (byte_after_cr); | |
4747 | charset = charset_roman; | |
4748 | } | |
57a47f8a | 4749 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4750 | goto invalid_code; |
57a47f8a KH |
4751 | else if (c >= 0xA1 && c <= 0xDF) |
4752 | { | |
4753 | /* SJIS -> JISX0201-Kana */ | |
4754 | c &= 0x7F; | |
4755 | charset = charset_kana; | |
4756 | } | |
4757 | else if (c <= 0xEF) | |
df7492f9 | 4758 | { |
57a47f8a KH |
4759 | /* SJIS -> JISX0208 */ |
4760 | ONE_MORE_BYTE (c1); | |
4761 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4762 | goto invalid_code; |
57a47f8a KH |
4763 | c = (c << 8) | c1; |
4764 | SJIS_TO_JIS (c); | |
4765 | charset = charset_kanji; | |
4766 | } | |
4767 | else if (c <= 0xFC && charset_kanji2) | |
4768 | { | |
c6876370 | 4769 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4770 | ONE_MORE_BYTE (c1); |
4771 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4772 | goto invalid_code; |
57a47f8a KH |
4773 | c = (c << 8) | c1; |
4774 | SJIS_TO_JIS2 (c); | |
4775 | charset = charset_kanji2; | |
df7492f9 | 4776 | } |
57a47f8a KH |
4777 | else |
4778 | goto invalid_code; | |
24a73b0a KH |
4779 | if (charset->id != charset_ascii |
4780 | && last_id != charset->id) | |
4781 | { | |
4782 | if (last_id != charset_ascii) | |
69a80ea3 | 4783 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4784 | last_id = charset->id; |
4785 | last_offset = char_offset; | |
4786 | } | |
4787 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4788 | *charbuf++ = c; |
ff0dacd7 | 4789 | char_offset++; |
df7492f9 | 4790 | continue; |
b73bfc1c | 4791 | |
df7492f9 KH |
4792 | invalid_code: |
4793 | src = src_base; | |
4794 | consumed_chars = consumed_chars_base; | |
4795 | ONE_MORE_BYTE (c); | |
065e3595 | 4796 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4797 | char_offset++; |
df7492f9 KH |
4798 | coding->errors++; |
4799 | } | |
fa42c37f | 4800 | |
df7492f9 | 4801 | no_more_source: |
ff0dacd7 | 4802 | if (last_id != charset_ascii) |
69a80ea3 | 4803 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4804 | coding->consumed_char += consumed_chars_base; |
4805 | coding->consumed = src_base - coding->source; | |
4806 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4807 | } |
4808 | ||
b73bfc1c | 4809 | static void |
971de7fb | 4810 | decode_coding_big5 (struct coding_system *coding) |
4ed46869 | 4811 | { |
8f924df7 KH |
4812 | const unsigned char *src = coding->source + coding->consumed; |
4813 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4814 | const unsigned char *src_base; | |
69a80ea3 | 4815 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4816 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4817 | the end. */ |
69a80ea3 | 4818 | int *charbuf_end |
df80c7f0 | 4819 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
4820 | int consumed_chars = 0, consumed_chars_base; |
4821 | int multibytep = coding->src_multibyte; | |
4822 | struct charset *charset_roman, *charset_big5; | |
24a73b0a | 4823 | Lisp_Object attrs, charset_list, val; |
ff0dacd7 KH |
4824 | int char_offset = coding->produced_char; |
4825 | int last_offset = char_offset; | |
4826 | int last_id = charset_ascii; | |
0a9564cb EZ |
4827 | int eol_crlf = |
4828 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4829 | int byte_after_cr = -1; |
df7492f9 | 4830 | |
24a73b0a | 4831 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4832 | val = charset_list; |
4833 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4834 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4835 | |
b73bfc1c | 4836 | while (1) |
4ed46869 | 4837 | { |
df7492f9 | 4838 | int c, c1; |
24a73b0a | 4839 | struct charset *charset; |
b73bfc1c KH |
4840 | |
4841 | src_base = src; | |
df7492f9 KH |
4842 | consumed_chars_base = consumed_chars; |
4843 | ||
4844 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4845 | { |
4846 | if (byte_after_cr >= 0) | |
4847 | src_base--; | |
4848 | break; | |
4849 | } | |
df7492f9 | 4850 | |
119852e7 | 4851 | if (byte_after_cr >= 0) |
14daee73 | 4852 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4853 | else |
4854 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4855 | |
065e3595 KH |
4856 | if (c < 0) |
4857 | goto invalid_code; | |
24a73b0a | 4858 | if (c < 0x80) |
119852e7 | 4859 | { |
14daee73 | 4860 | if (eol_crlf && c == '\r') |
119852e7 KH |
4861 | ONE_MORE_BYTE (byte_after_cr); |
4862 | charset = charset_roman; | |
4863 | } | |
24a73b0a | 4864 | else |
4ed46869 | 4865 | { |
24a73b0a KH |
4866 | /* BIG5 -> Big5 */ |
4867 | if (c < 0xA1 || c > 0xFE) | |
4868 | goto invalid_code; | |
4869 | ONE_MORE_BYTE (c1); | |
4870 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4871 | goto invalid_code; | |
4872 | c = c << 8 | c1; | |
4873 | charset = charset_big5; | |
4ed46869 | 4874 | } |
24a73b0a KH |
4875 | if (charset->id != charset_ascii |
4876 | && last_id != charset->id) | |
df7492f9 | 4877 | { |
24a73b0a | 4878 | if (last_id != charset_ascii) |
69a80ea3 | 4879 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4880 | last_id = charset->id; |
4881 | last_offset = char_offset; | |
4ed46869 | 4882 | } |
24a73b0a | 4883 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4884 | *charbuf++ = c; |
ff0dacd7 | 4885 | char_offset++; |
fb88bf2d KH |
4886 | continue; |
4887 | ||
df7492f9 | 4888 | invalid_code: |
4ed46869 | 4889 | src = src_base; |
df7492f9 KH |
4890 | consumed_chars = consumed_chars_base; |
4891 | ONE_MORE_BYTE (c); | |
065e3595 | 4892 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4893 | char_offset++; |
df7492f9 | 4894 | coding->errors++; |
fb88bf2d | 4895 | } |
d46c5b12 | 4896 | |
df7492f9 | 4897 | no_more_source: |
ff0dacd7 | 4898 | if (last_id != charset_ascii) |
69a80ea3 | 4899 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4900 | coding->consumed_char += consumed_chars_base; |
4901 | coding->consumed = src_base - coding->source; | |
4902 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4903 | } |
4904 | ||
4905 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4906 | This function can encode charsets `ascii', `katakana-jisx0201', |
4907 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4908 | are sure that all these charsets are registered as official charset | |
4ed46869 KH |
4909 | (i.e. do not have extended leading-codes). Characters of other |
4910 | charsets are produced without any encoding. If SJIS_P is 1, encode | |
4911 | SJIS text, else encode BIG5 text. */ | |
4912 | ||
df7492f9 | 4913 | static int |
971de7fb | 4914 | encode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4915 | { |
df7492f9 KH |
4916 | int multibytep = coding->dst_multibyte; |
4917 | int *charbuf = coding->charbuf; | |
4918 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4919 | unsigned char *dst = coding->destination + coding->produced; | |
4920 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4921 | int safe_room = 4; | |
4922 | int produced_chars = 0; | |
24a73b0a | 4923 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
4924 | int ascii_compatible; |
4925 | struct charset *charset_roman, *charset_kanji, *charset_kana; | |
57a47f8a | 4926 | struct charset *charset_kanji2; |
df7492f9 | 4927 | int c; |
a5d301df | 4928 | |
24a73b0a | 4929 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4930 | val = charset_list; |
4931 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4932 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
57a47f8a KH |
4933 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4934 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4935 | |
df7492f9 | 4936 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4937 | |
df7492f9 KH |
4938 | while (charbuf < charbuf_end) |
4939 | { | |
4940 | ASSURE_DESTINATION (safe_room); | |
4941 | c = *charbuf++; | |
b73bfc1c | 4942 | /* Now encode the character C. */ |
df7492f9 KH |
4943 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4944 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4945 | else if (CHAR_BYTE8_P (c)) |
4946 | { | |
4947 | c = CHAR_TO_BYTE8 (c); | |
4948 | EMIT_ONE_BYTE (c); | |
4949 | } | |
df7492f9 | 4950 | else |
b73bfc1c | 4951 | { |
df7492f9 KH |
4952 | unsigned code; |
4953 | struct charset *charset = char_charset (c, charset_list, &code); | |
4954 | ||
4955 | if (!charset) | |
4ed46869 | 4956 | { |
41cbe562 | 4957 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4958 | { |
41cbe562 KH |
4959 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4960 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4961 | } |
41cbe562 | 4962 | else |
b73bfc1c | 4963 | { |
41cbe562 KH |
4964 | c = coding->default_char; |
4965 | charset = char_charset (c, charset_list, &code); | |
b73bfc1c | 4966 | } |
b73bfc1c | 4967 | } |
df7492f9 KH |
4968 | if (code == CHARSET_INVALID_CODE (charset)) |
4969 | abort (); | |
4970 | if (charset == charset_kanji) | |
4971 | { | |
4972 | int c1, c2; | |
4973 | JIS_TO_SJIS (code); | |
4974 | c1 = code >> 8, c2 = code & 0xFF; | |
4975 | EMIT_TWO_BYTES (c1, c2); | |
4976 | } | |
4977 | else if (charset == charset_kana) | |
4978 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4979 | else if (charset_kanji2 && charset == charset_kanji2) |
4980 | { | |
4981 | int c1, c2; | |
4982 | ||
4983 | c1 = code >> 8; | |
f07190ca KH |
4984 | if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25) |
4985 | || c1 == 0x28 | |
57a47f8a KH |
4986 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) |
4987 | { | |
4988 | JIS_TO_SJIS2 (code); | |
4989 | c1 = code >> 8, c2 = code & 0xFF; | |
4990 | EMIT_TWO_BYTES (c1, c2); | |
4991 | } | |
4992 | else | |
4993 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4994 | } | |
df7492f9 KH |
4995 | else |
4996 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4997 | } | |
4998 | } | |
065e3595 | 4999 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5000 | coding->produced_char += produced_chars; |
5001 | coding->produced = dst - coding->destination; | |
5002 | return 0; | |
5003 | } | |
5004 | ||
5005 | static int | |
971de7fb | 5006 | encode_coding_big5 (struct coding_system *coding) |
df7492f9 KH |
5007 | { |
5008 | int multibytep = coding->dst_multibyte; | |
5009 | int *charbuf = coding->charbuf; | |
5010 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5011 | unsigned char *dst = coding->destination + coding->produced; | |
5012 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5013 | int safe_room = 4; | |
5014 | int produced_chars = 0; | |
24a73b0a | 5015 | Lisp_Object attrs, charset_list, val; |
df7492f9 KH |
5016 | int ascii_compatible; |
5017 | struct charset *charset_roman, *charset_big5; | |
5018 | int c; | |
5019 | ||
24a73b0a | 5020 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
5021 | val = charset_list; |
5022 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
5023 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
5024 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
5025 | ||
5026 | while (charbuf < charbuf_end) | |
5027 | { | |
5028 | ASSURE_DESTINATION (safe_room); | |
5029 | c = *charbuf++; | |
5030 | /* Now encode the character C. */ | |
5031 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
5032 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
5033 | else if (CHAR_BYTE8_P (c)) |
5034 | { | |
5035 | c = CHAR_TO_BYTE8 (c); | |
5036 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
5037 | } |
5038 | else | |
5039 | { | |
df7492f9 KH |
5040 | unsigned code; |
5041 | struct charset *charset = char_charset (c, charset_list, &code); | |
5042 | ||
5043 | if (! charset) | |
b73bfc1c | 5044 | { |
41cbe562 | 5045 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 5046 | { |
41cbe562 KH |
5047 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
5048 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 5049 | } |
41cbe562 | 5050 | else |
0eecad43 | 5051 | { |
41cbe562 KH |
5052 | c = coding->default_char; |
5053 | charset = char_charset (c, charset_list, &code); | |
0eecad43 | 5054 | } |
4ed46869 | 5055 | } |
df7492f9 KH |
5056 | if (code == CHARSET_INVALID_CODE (charset)) |
5057 | abort (); | |
5058 | if (charset == charset_big5) | |
b73bfc1c | 5059 | { |
df7492f9 KH |
5060 | int c1, c2; |
5061 | ||
5062 | c1 = code >> 8, c2 = code & 0xFF; | |
5063 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 5064 | } |
df7492f9 KH |
5065 | else |
5066 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 5067 | } |
4ed46869 | 5068 | } |
065e3595 | 5069 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5070 | coding->produced_char += produced_chars; |
5071 | coding->produced = dst - coding->destination; | |
5072 | return 0; | |
4ed46869 KH |
5073 | } |
5074 | ||
5075 | \f | |
df7492f9 | 5076 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
5077 | |
5078 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
5079 | Check if a text is encoded in a coding system of which | |
5080 | encoder/decoder are written in CCL program. If it is, return | |
df7492f9 | 5081 | CATEGORY_MASK_CCL, else return 0. */ |
1397dc18 | 5082 | |
0a28aafb | 5083 | static int |
cf84bb53 JB |
5084 | detect_coding_ccl (struct coding_system *coding, |
5085 | struct coding_detection_info *detect_info) | |
1397dc18 | 5086 | { |
065e3595 | 5087 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5088 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5089 | int multibytep = coding->src_multibyte; |
5090 | int consumed_chars = 0; | |
5091 | int found = 0; | |
0e219d54 | 5092 | unsigned char *valids; |
df7492f9 KH |
5093 | int head_ascii = coding->head_ascii; |
5094 | Lisp_Object attrs; | |
5095 | ||
ff0dacd7 KH |
5096 | detect_info->checked |= CATEGORY_MASK_CCL; |
5097 | ||
df7492f9 | 5098 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 5099 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
5100 | attrs = CODING_ID_ATTRS (coding->id); |
5101 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
5102 | src += head_ascii; | |
1397dc18 | 5103 | |
b73bfc1c | 5104 | while (1) |
1397dc18 | 5105 | { |
df7492f9 | 5106 | int c; |
065e3595 KH |
5107 | |
5108 | src_base = src; | |
df7492f9 | 5109 | ONE_MORE_BYTE (c); |
065e3595 | 5110 | if (c < 0 || ! valids[c]) |
df7492f9 | 5111 | break; |
ff0dacd7 KH |
5112 | if ((valids[c] > 1)) |
5113 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 5114 | } |
ff0dacd7 | 5115 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
5116 | return 0; |
5117 | ||
5118 | no_more_source: | |
ff0dacd7 KH |
5119 | detect_info->found |= found; |
5120 | return 1; | |
df7492f9 KH |
5121 | } |
5122 | ||
5123 | static void | |
971de7fb | 5124 | decode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5125 | { |
7c78e542 | 5126 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 5127 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
5128 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5129 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
df7492f9 KH |
5130 | int consumed_chars = 0; |
5131 | int multibytep = coding->src_multibyte; | |
d0396581 | 5132 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 | 5133 | int source_charbuf[1024]; |
fbdc1721 | 5134 | int source_byteidx[1025]; |
24a73b0a | 5135 | Lisp_Object attrs, charset_list; |
df7492f9 | 5136 | |
24a73b0a | 5137 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5138 | |
d0396581 | 5139 | while (1) |
df7492f9 | 5140 | { |
7c78e542 | 5141 | const unsigned char *p = src; |
df7492f9 KH |
5142 | int i = 0; |
5143 | ||
5144 | if (multibytep) | |
fbdc1721 KH |
5145 | { |
5146 | while (i < 1024 && p < src_end) | |
5147 | { | |
5148 | source_byteidx[i] = p - src; | |
5149 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
5150 | } | |
5151 | source_byteidx[i] = p - src; | |
5152 | } | |
df7492f9 KH |
5153 | else |
5154 | while (i < 1024 && p < src_end) | |
5155 | source_charbuf[i++] = *p++; | |
8f924df7 | 5156 | |
df7492f9 | 5157 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
d0396581 KH |
5158 | ccl->last_block = 1; |
5159 | ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf, | |
5160 | charset_list); | |
5161 | charbuf += ccl->produced; | |
fbdc1721 | 5162 | if (multibytep) |
d0396581 | 5163 | src += source_byteidx[ccl->consumed]; |
df7492f9 | 5164 | else |
d0396581 KH |
5165 | src += ccl->consumed; |
5166 | consumed_chars += ccl->consumed; | |
5167 | if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC) | |
df7492f9 KH |
5168 | break; |
5169 | } | |
5170 | ||
d0396581 | 5171 | switch (ccl->status) |
df7492f9 KH |
5172 | { |
5173 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5174 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5175 | break; |
5176 | case CCL_STAT_SUSPEND_BY_DST: | |
d0396581 | 5177 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5178 | break; |
5179 | case CCL_STAT_QUIT: | |
5180 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5181 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5182 | break; |
5183 | default: | |
065e3595 | 5184 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5185 | break; |
5186 | } | |
5187 | coding->consumed_char += consumed_chars; | |
5188 | coding->consumed = src - coding->source; | |
5189 | coding->charbuf_used = charbuf - coding->charbuf; | |
5190 | } | |
5191 | ||
5192 | static int | |
971de7fb | 5193 | encode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5194 | { |
fb608df3 | 5195 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 KH |
5196 | int multibytep = coding->dst_multibyte; |
5197 | int *charbuf = coding->charbuf; | |
5198 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5199 | unsigned char *dst = coding->destination + coding->produced; | |
5200 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 KH |
5201 | int destination_charbuf[1024]; |
5202 | int i, produced_chars = 0; | |
24a73b0a | 5203 | Lisp_Object attrs, charset_list; |
df7492f9 | 5204 | |
24a73b0a | 5205 | CODING_GET_INFO (coding, attrs, charset_list); |
fb608df3 KH |
5206 | if (coding->consumed_char == coding->src_chars |
5207 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
5208 | ccl->last_block = 1; | |
df7492f9 | 5209 | |
8cffd3e7 | 5210 | while (charbuf < charbuf_end) |
df7492f9 | 5211 | { |
fb608df3 | 5212 | ccl_driver (ccl, charbuf, destination_charbuf, |
8cffd3e7 | 5213 | charbuf_end - charbuf, 1024, charset_list); |
df7492f9 | 5214 | if (multibytep) |
8cffd3e7 | 5215 | { |
fb608df3 KH |
5216 | ASSURE_DESTINATION (ccl->produced * 2); |
5217 | for (i = 0; i < ccl->produced; i++) | |
8cffd3e7 KH |
5218 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); |
5219 | } | |
df7492f9 KH |
5220 | else |
5221 | { | |
fb608df3 KH |
5222 | ASSURE_DESTINATION (ccl->produced); |
5223 | for (i = 0; i < ccl->produced; i++) | |
df7492f9 | 5224 | *dst++ = destination_charbuf[i] & 0xFF; |
fb608df3 | 5225 | produced_chars += ccl->produced; |
df7492f9 | 5226 | } |
fb608df3 KH |
5227 | charbuf += ccl->consumed; |
5228 | if (ccl->status == CCL_STAT_QUIT | |
5229 | || ccl->status == CCL_STAT_INVALID_CMD) | |
8cffd3e7 | 5230 | break; |
df7492f9 KH |
5231 | } |
5232 | ||
fb608df3 | 5233 | switch (ccl->status) |
df7492f9 KH |
5234 | { |
5235 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5236 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5237 | break; |
5238 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 5239 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5240 | break; |
5241 | case CCL_STAT_QUIT: | |
5242 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5243 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5244 | break; |
5245 | default: | |
065e3595 | 5246 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5247 | break; |
1397dc18 | 5248 | } |
df7492f9 KH |
5249 | |
5250 | coding->produced_char += produced_chars; | |
5251 | coding->produced = dst - coding->destination; | |
5252 | return 0; | |
1397dc18 KH |
5253 | } |
5254 | ||
df7492f9 | 5255 | |
1397dc18 | 5256 | \f |
df7492f9 | 5257 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 5258 | |
b73bfc1c | 5259 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 5260 | |
b73bfc1c | 5261 | static void |
971de7fb | 5262 | decode_coding_raw_text (struct coding_system *coding) |
4ed46869 | 5263 | { |
0a9564cb EZ |
5264 | int eol_crlf = |
5265 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5266 | |
df7492f9 | 5267 | coding->chars_at_source = 1; |
119852e7 KH |
5268 | coding->consumed_char = coding->src_chars; |
5269 | coding->consumed = coding->src_bytes; | |
5270 | if (eol_crlf && coding->source[coding->src_bytes - 1] == '\r') | |
5271 | { | |
5272 | coding->consumed_char--; | |
5273 | coding->consumed--; | |
5274 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
5275 | } | |
5276 | else | |
5277 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 5278 | } |
4ed46869 | 5279 | |
df7492f9 | 5280 | static int |
971de7fb | 5281 | encode_coding_raw_text (struct coding_system *coding) |
df7492f9 KH |
5282 | { |
5283 | int multibytep = coding->dst_multibyte; | |
5284 | int *charbuf = coding->charbuf; | |
5285 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5286 | unsigned char *dst = coding->destination + coding->produced; | |
5287 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
a0ed9b27 | 5288 | int produced_chars = 0; |
b73bfc1c KH |
5289 | int c; |
5290 | ||
df7492f9 | 5291 | if (multibytep) |
b73bfc1c | 5292 | { |
df7492f9 | 5293 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5294 | |
df7492f9 KH |
5295 | if (coding->src_multibyte) |
5296 | while (charbuf < charbuf_end) | |
5297 | { | |
5298 | ASSURE_DESTINATION (safe_room); | |
5299 | c = *charbuf++; | |
5300 | if (ASCII_CHAR_P (c)) | |
5301 | EMIT_ONE_ASCII_BYTE (c); | |
5302 | else if (CHAR_BYTE8_P (c)) | |
5303 | { | |
5304 | c = CHAR_TO_BYTE8 (c); | |
5305 | EMIT_ONE_BYTE (c); | |
5306 | } | |
5307 | else | |
5308 | { | |
5309 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5310 | |
df7492f9 KH |
5311 | CHAR_STRING_ADVANCE (c, p1); |
5312 | while (p0 < p1) | |
9d123124 KH |
5313 | { |
5314 | EMIT_ONE_BYTE (*p0); | |
5315 | p0++; | |
5316 | } | |
df7492f9 KH |
5317 | } |
5318 | } | |
b73bfc1c | 5319 | else |
df7492f9 KH |
5320 | while (charbuf < charbuf_end) |
5321 | { | |
5322 | ASSURE_DESTINATION (safe_room); | |
5323 | c = *charbuf++; | |
5324 | EMIT_ONE_BYTE (c); | |
5325 | } | |
5326 | } | |
5327 | else | |
4ed46869 | 5328 | { |
df7492f9 | 5329 | if (coding->src_multibyte) |
d46c5b12 | 5330 | { |
df7492f9 KH |
5331 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5332 | ||
5333 | while (charbuf < charbuf_end) | |
d46c5b12 | 5334 | { |
df7492f9 KH |
5335 | ASSURE_DESTINATION (safe_room); |
5336 | c = *charbuf++; | |
5337 | if (ASCII_CHAR_P (c)) | |
5338 | *dst++ = c; | |
5339 | else if (CHAR_BYTE8_P (c)) | |
5340 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5341 | else |
df7492f9 | 5342 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5343 | } |
5344 | } | |
df7492f9 KH |
5345 | else |
5346 | { | |
5347 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5348 | while (charbuf < charbuf_end && dst < dst_end) | |
5349 | *dst++ = *charbuf++; | |
8f924df7 | 5350 | } |
319a3947 | 5351 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5352 | } |
065e3595 | 5353 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5354 | coding->produced_char += produced_chars; |
df7492f9 KH |
5355 | coding->produced = dst - coding->destination; |
5356 | return 0; | |
4ed46869 KH |
5357 | } |
5358 | ||
ff0dacd7 KH |
5359 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
5360 | Check if a text is encoded in a charset-based coding system. If it | |
5361 | is, return 1, else return 0. */ | |
5362 | ||
0a28aafb | 5363 | static int |
cf84bb53 JB |
5364 | detect_coding_charset (struct coding_system *coding, |
5365 | struct coding_detection_info *detect_info) | |
1397dc18 | 5366 | { |
065e3595 | 5367 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5368 | const unsigned char *src_end = coding->source + coding->src_bytes; |
df7492f9 KH |
5369 | int multibytep = coding->src_multibyte; |
5370 | int consumed_chars = 0; | |
07295713 | 5371 | Lisp_Object attrs, valids, name; |
584948ac | 5372 | int found = 0; |
716b3fa0 | 5373 | int head_ascii = coding->head_ascii; |
07295713 | 5374 | int check_latin_extra = 0; |
1397dc18 | 5375 | |
ff0dacd7 KH |
5376 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5377 | ||
df7492f9 KH |
5378 | coding = &coding_categories[coding_category_charset]; |
5379 | attrs = CODING_ID_ATTRS (coding->id); | |
5380 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 | 5381 | name = CODING_ID_NAME (coding->id); |
51b59d79 | 5382 | if (strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5383 | "iso-8859-", sizeof ("iso-8859-") - 1) == 0 |
51b59d79 | 5384 | || strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5385 | "iso-latin-", sizeof ("iso-latin-") - 1) == 0) |
07295713 | 5386 | check_latin_extra = 1; |
237aabf4 | 5387 | |
df7492f9 | 5388 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5389 | src += head_ascii; |
1397dc18 | 5390 | |
b73bfc1c | 5391 | while (1) |
1397dc18 | 5392 | { |
df7492f9 | 5393 | int c; |
716b3fa0 KH |
5394 | Lisp_Object val; |
5395 | struct charset *charset; | |
5396 | int dim, idx; | |
1397dc18 | 5397 | |
065e3595 | 5398 | src_base = src; |
df7492f9 | 5399 | ONE_MORE_BYTE (c); |
065e3595 KH |
5400 | if (c < 0) |
5401 | continue; | |
716b3fa0 KH |
5402 | val = AREF (valids, c); |
5403 | if (NILP (val)) | |
df7492f9 | 5404 | break; |
584948ac | 5405 | if (c >= 0x80) |
07295713 KH |
5406 | { |
5407 | if (c < 0xA0 | |
237aabf4 JR |
5408 | && check_latin_extra |
5409 | && (!VECTORP (Vlatin_extra_code_table) | |
9f0526cb | 5410 | || NILP (XVECTOR (Vlatin_extra_code_table)->contents[c]))) |
07295713 KH |
5411 | break; |
5412 | found = CATEGORY_MASK_CHARSET; | |
5413 | } | |
716b3fa0 KH |
5414 | if (INTEGERP (val)) |
5415 | { | |
5416 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5417 | dim = CHARSET_DIMENSION (charset); | |
5418 | for (idx = 1; idx < dim; idx++) | |
5419 | { | |
5420 | if (src == src_end) | |
5421 | goto too_short; | |
5422 | ONE_MORE_BYTE (c); | |
3ed051d4 | 5423 | if (c < charset->code_space[(dim - 1 - idx) * 2] |
716b3fa0 KH |
5424 | || c > charset->code_space[(dim - 1 - idx) * 2 + 1]) |
5425 | break; | |
5426 | } | |
5427 | if (idx < dim) | |
5428 | break; | |
5429 | } | |
5430 | else | |
5431 | { | |
5432 | idx = 1; | |
5433 | for (; CONSP (val); val = XCDR (val)) | |
5434 | { | |
5435 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5436 | dim = CHARSET_DIMENSION (charset); | |
5437 | while (idx < dim) | |
5438 | { | |
5439 | if (src == src_end) | |
5440 | goto too_short; | |
5441 | ONE_MORE_BYTE (c); | |
5442 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5443 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5444 | break; | |
5445 | idx++; | |
5446 | } | |
5447 | if (idx == dim) | |
5448 | { | |
5449 | val = Qnil; | |
5450 | break; | |
5451 | } | |
5452 | } | |
5453 | if (CONSP (val)) | |
5454 | break; | |
5455 | } | |
df7492f9 | 5456 | } |
716b3fa0 | 5457 | too_short: |
ff0dacd7 | 5458 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5459 | return 0; |
4ed46869 | 5460 | |
df7492f9 | 5461 | no_more_source: |
ff0dacd7 KH |
5462 | detect_info->found |= found; |
5463 | return 1; | |
df7492f9 | 5464 | } |
b73bfc1c | 5465 | |
b73bfc1c | 5466 | static void |
971de7fb | 5467 | decode_coding_charset (struct coding_system *coding) |
4ed46869 | 5468 | { |
8f924df7 KH |
5469 | const unsigned char *src = coding->source + coding->consumed; |
5470 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5471 | const unsigned char *src_base; | |
69a80ea3 | 5472 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 5473 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 5474 | the end. */ |
69a80ea3 | 5475 | int *charbuf_end |
df80c7f0 | 5476 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
df7492f9 KH |
5477 | int consumed_chars = 0, consumed_chars_base; |
5478 | int multibytep = coding->src_multibyte; | |
24a73b0a | 5479 | Lisp_Object attrs, charset_list, valids; |
ff0dacd7 KH |
5480 | int char_offset = coding->produced_char; |
5481 | int last_offset = char_offset; | |
5482 | int last_id = charset_ascii; | |
0a9564cb EZ |
5483 | int eol_crlf = |
5484 | !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5485 | int byte_after_cr = -1; |
df7492f9 | 5486 | |
24a73b0a | 5487 | CODING_GET_INFO (coding, attrs, charset_list); |
4eb6d3f1 | 5488 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5489 | |
df7492f9 | 5490 | while (1) |
4ed46869 | 5491 | { |
4eb6d3f1 | 5492 | int c; |
24a73b0a KH |
5493 | Lisp_Object val; |
5494 | struct charset *charset; | |
5495 | int dim; | |
5496 | int len = 1; | |
5497 | unsigned code; | |
df7492f9 KH |
5498 | |
5499 | src_base = src; | |
5500 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5501 | |
df7492f9 | 5502 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5503 | { |
5504 | if (byte_after_cr >= 0) | |
5505 | src_base--; | |
5506 | break; | |
5507 | } | |
df7492f9 | 5508 | |
119852e7 KH |
5509 | if (byte_after_cr >= 0) |
5510 | { | |
5511 | c = byte_after_cr; | |
5512 | byte_after_cr = -1; | |
5513 | } | |
5514 | else | |
5515 | { | |
5516 | ONE_MORE_BYTE (c); | |
5517 | if (eol_crlf && c == '\r') | |
5518 | ONE_MORE_BYTE (byte_after_cr); | |
5519 | } | |
065e3595 KH |
5520 | if (c < 0) |
5521 | goto invalid_code; | |
24a73b0a KH |
5522 | code = c; |
5523 | ||
5524 | val = AREF (valids, c); | |
1b17adfd | 5525 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5526 | goto invalid_code; |
5527 | if (INTEGERP (val)) | |
d46c5b12 | 5528 | { |
24a73b0a KH |
5529 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5530 | dim = CHARSET_DIMENSION (charset); | |
5531 | while (len < dim) | |
b73bfc1c | 5532 | { |
24a73b0a KH |
5533 | ONE_MORE_BYTE (c); |
5534 | code = (code << 8) | c; | |
5535 | len++; | |
b73bfc1c | 5536 | } |
24a73b0a KH |
5537 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5538 | charset, code, c); | |
d46c5b12 | 5539 | } |
df7492f9 | 5540 | else |
d46c5b12 | 5541 | { |
24a73b0a KH |
5542 | /* VAL is a list of charset IDs. It is assured that the |
5543 | list is sorted by charset dimensions (smaller one | |
5544 | comes first). */ | |
5545 | while (CONSP (val)) | |
4eb6d3f1 | 5546 | { |
24a73b0a | 5547 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5548 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5549 | while (len < dim) |
4eb6d3f1 | 5550 | { |
acb2a965 KH |
5551 | ONE_MORE_BYTE (c); |
5552 | code = (code << 8) | c; | |
f9d71dcd | 5553 | len++; |
4eb6d3f1 | 5554 | } |
24a73b0a KH |
5555 | CODING_DECODE_CHAR (coding, src, src_base, |
5556 | src_end, charset, code, c); | |
5557 | if (c >= 0) | |
5558 | break; | |
5559 | val = XCDR (val); | |
ff0dacd7 | 5560 | } |
d46c5b12 | 5561 | } |
24a73b0a KH |
5562 | if (c < 0) |
5563 | goto invalid_code; | |
5564 | if (charset->id != charset_ascii | |
5565 | && last_id != charset->id) | |
5566 | { | |
5567 | if (last_id != charset_ascii) | |
69a80ea3 | 5568 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5569 | last_id = charset->id; |
5570 | last_offset = char_offset; | |
5571 | } | |
5572 | ||
df7492f9 | 5573 | *charbuf++ = c; |
ff0dacd7 | 5574 | char_offset++; |
df7492f9 KH |
5575 | continue; |
5576 | ||
5577 | invalid_code: | |
5578 | src = src_base; | |
5579 | consumed_chars = consumed_chars_base; | |
5580 | ONE_MORE_BYTE (c); | |
065e3595 | 5581 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5582 | char_offset++; |
df7492f9 | 5583 | coding->errors++; |
4ed46869 KH |
5584 | } |
5585 | ||
df7492f9 | 5586 | no_more_source: |
ff0dacd7 | 5587 | if (last_id != charset_ascii) |
69a80ea3 | 5588 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5589 | coding->consumed_char += consumed_chars_base; |
5590 | coding->consumed = src_base - coding->source; | |
5591 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5592 | } |
5593 | ||
df7492f9 | 5594 | static int |
971de7fb | 5595 | encode_coding_charset (struct coding_system *coding) |
4ed46869 | 5596 | { |
df7492f9 KH |
5597 | int multibytep = coding->dst_multibyte; |
5598 | int *charbuf = coding->charbuf; | |
5599 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5600 | unsigned char *dst = coding->destination + coding->produced; | |
5601 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5602 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
5603 | int produced_chars = 0; | |
24a73b0a | 5604 | Lisp_Object attrs, charset_list; |
df7492f9 | 5605 | int ascii_compatible; |
b73bfc1c | 5606 | int c; |
b73bfc1c | 5607 | |
24a73b0a | 5608 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5609 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5610 | |
df7492f9 | 5611 | while (charbuf < charbuf_end) |
4ed46869 | 5612 | { |
4eb6d3f1 | 5613 | struct charset *charset; |
df7492f9 | 5614 | unsigned code; |
8f924df7 | 5615 | |
df7492f9 KH |
5616 | ASSURE_DESTINATION (safe_room); |
5617 | c = *charbuf++; | |
5618 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5619 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5620 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5621 | { |
16eafb5d KH |
5622 | c = CHAR_TO_BYTE8 (c); |
5623 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5624 | } |
d46c5b12 | 5625 | else |
b73bfc1c | 5626 | { |
4eb6d3f1 KH |
5627 | charset = char_charset (c, charset_list, &code); |
5628 | if (charset) | |
5629 | { | |
5630 | if (CHARSET_DIMENSION (charset) == 1) | |
5631 | EMIT_ONE_BYTE (code); | |
5632 | else if (CHARSET_DIMENSION (charset) == 2) | |
5633 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5634 | else if (CHARSET_DIMENSION (charset) == 3) | |
5635 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5636 | else | |
5637 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5638 | (code >> 8) & 0xFF, code & 0xFF); | |
5639 | } | |
5640 | else | |
41cbe562 KH |
5641 | { |
5642 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5643 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5644 | else | |
5645 | c = coding->default_char; | |
5646 | EMIT_ONE_BYTE (c); | |
5647 | } | |
4ed46869 | 5648 | } |
4ed46869 KH |
5649 | } |
5650 | ||
065e3595 | 5651 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5652 | coding->produced_char += produced_chars; |
5653 | coding->produced = dst - coding->destination; | |
5654 | return 0; | |
4ed46869 KH |
5655 | } |
5656 | ||
5657 | \f | |
1397dc18 | 5658 | /*** 7. C library functions ***/ |
4ed46869 | 5659 | |
df7492f9 KH |
5660 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5661 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5662 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5663 | |
ec6d2bb8 | 5664 | void |
971de7fb | 5665 | setup_coding_system (Lisp_Object coding_system, struct coding_system *coding) |
4ed46869 | 5666 | { |
df7492f9 KH |
5667 | Lisp_Object attrs; |
5668 | Lisp_Object eol_type; | |
5669 | Lisp_Object coding_type; | |
4608c386 | 5670 | Lisp_Object val; |
4ed46869 | 5671 | |
df7492f9 | 5672 | if (NILP (coding_system)) |
ae6f73fa | 5673 | coding_system = Qundecided; |
c07c8e12 | 5674 | |
df7492f9 | 5675 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5676 | |
df7492f9 | 5677 | attrs = CODING_ID_ATTRS (coding->id); |
0a9564cb | 5678 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
1f5dbf34 | 5679 | |
df7492f9 KH |
5680 | coding->mode = 0; |
5681 | coding->head_ascii = -1; | |
4a015c45 KH |
5682 | if (VECTORP (eol_type)) |
5683 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5684 | | CODING_REQUIRE_DETECTION_MASK); | |
5685 | else if (! EQ (eol_type, Qunix)) | |
5686 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5687 | | CODING_REQUIRE_ENCODING_MASK); | |
5688 | else | |
5689 | coding->common_flags = 0; | |
5e5c78be KH |
5690 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5691 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5692 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5693 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5694 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5695 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5696 | |
df7492f9 | 5697 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 | 5698 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5699 | coding->safe_charsets = SDATA (val); |
df7492f9 | 5700 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
624bda09 | 5701 | coding->carryover_bytes = 0; |
4608c386 | 5702 | |
df7492f9 KH |
5703 | coding_type = CODING_ATTR_TYPE (attrs); |
5704 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5705 | { |
df7492f9 KH |
5706 | coding->detector = NULL; |
5707 | coding->decoder = decode_coding_raw_text; | |
5708 | coding->encoder = encode_coding_raw_text; | |
5709 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5710 | } |
df7492f9 | 5711 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5712 | { |
df7492f9 KH |
5713 | int i; |
5714 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5715 | ||
5716 | /* Invoke graphic register 0 to plane 0. */ | |
5717 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5718 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5719 | CODING_ISO_INVOCATION (coding, 1) | |
5720 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5721 | /* Setup the initial status of designation. */ | |
5722 | for (i = 0; i < 4; i++) | |
5723 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5724 | /* Not single shifting initially. */ | |
5725 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5726 | /* Beginning of buffer should also be regarded as bol. */ | |
5727 | CODING_ISO_BOL (coding) = 1; | |
5728 | coding->detector = detect_coding_iso_2022; | |
5729 | coding->decoder = decode_coding_iso_2022; | |
5730 | coding->encoder = encode_coding_iso_2022; | |
5731 | if (flags & CODING_ISO_FLAG_SAFE) | |
5732 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5733 | coding->common_flags |
df7492f9 KH |
5734 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5735 | | CODING_REQUIRE_FLUSHING_MASK); | |
5736 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5737 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5738 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5739 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5740 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5741 | { | |
5742 | setup_iso_safe_charsets (attrs); | |
5743 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 5744 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5745 | coding->safe_charsets = SDATA (val); |
df7492f9 KH |
5746 | } |
5747 | CODING_ISO_FLAGS (coding) = flags; | |
e951386e KH |
5748 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; |
5749 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | |
5750 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | |
5751 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
d46c5b12 | 5752 | } |
df7492f9 | 5753 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5754 | { |
df7492f9 KH |
5755 | coding->detector = detect_coding_charset; |
5756 | coding->decoder = decode_coding_charset; | |
5757 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5758 | coding->common_flags |
df7492f9 | 5759 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5760 | } |
df7492f9 | 5761 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5762 | { |
a470d443 KH |
5763 | val = AREF (attrs, coding_attr_utf_bom); |
5764 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5765 | : EQ (val, Qt) ? utf_with_bom | |
5766 | : utf_without_bom); | |
df7492f9 KH |
5767 | coding->detector = detect_coding_utf_8; |
5768 | coding->decoder = decode_coding_utf_8; | |
5769 | coding->encoder = encode_coding_utf_8; | |
5770 | coding->common_flags | |
5771 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5772 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5773 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5774 | } |
5775 | else if (EQ (coding_type, Qutf_16)) | |
5776 | { | |
a470d443 KH |
5777 | val = AREF (attrs, coding_attr_utf_bom); |
5778 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5779 | : EQ (val, Qt) ? utf_with_bom | |
5780 | : utf_without_bom); | |
df7492f9 | 5781 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5782 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5783 | : utf_16_little_endian); |
e19c3639 | 5784 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5785 | coding->detector = detect_coding_utf_16; |
5786 | coding->decoder = decode_coding_utf_16; | |
5787 | coding->encoder = encode_coding_utf_16; | |
5788 | coding->common_flags | |
5789 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5790 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5791 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5792 | } |
df7492f9 | 5793 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5794 | { |
df7492f9 KH |
5795 | coding->detector = detect_coding_ccl; |
5796 | coding->decoder = decode_coding_ccl; | |
5797 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5798 | coding->common_flags |
df7492f9 KH |
5799 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5800 | | CODING_REQUIRE_FLUSHING_MASK); | |
5801 | } | |
5802 | else if (EQ (coding_type, Qemacs_mule)) | |
5803 | { | |
5804 | coding->detector = detect_coding_emacs_mule; | |
5805 | coding->decoder = decode_coding_emacs_mule; | |
5806 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5807 | coding->common_flags |
df7492f9 | 5808 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
e951386e | 5809 | coding->spec.emacs_mule.full_support = 1; |
df7492f9 KH |
5810 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) |
5811 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5812 | { | |
5813 | Lisp_Object tail, safe_charsets; | |
5814 | int max_charset_id = 0; | |
5815 | ||
5816 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5817 | tail = XCDR (tail)) | |
5818 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5819 | max_charset_id = XFASTINT (XCAR (tail)); | |
1b3b981b AS |
5820 | safe_charsets = make_uninit_string (max_charset_id + 1); |
5821 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
5822 | for (tail = Vemacs_mule_charset_list; CONSP (tail); |
5823 | tail = XCDR (tail)) | |
8f924df7 | 5824 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5825 | coding->max_charset_id = max_charset_id; |
1b3b981b | 5826 | coding->safe_charsets = SDATA (safe_charsets); |
e951386e | 5827 | coding->spec.emacs_mule.full_support = 1; |
df7492f9 | 5828 | } |
e951386e KH |
5829 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; |
5830 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | |
df7492f9 KH |
5831 | } |
5832 | else if (EQ (coding_type, Qshift_jis)) | |
5833 | { | |
5834 | coding->detector = detect_coding_sjis; | |
5835 | coding->decoder = decode_coding_sjis; | |
5836 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5837 | coding->common_flags |
df7492f9 KH |
5838 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5839 | } | |
5840 | else if (EQ (coding_type, Qbig5)) | |
5841 | { | |
5842 | coding->detector = detect_coding_big5; | |
5843 | coding->decoder = decode_coding_big5; | |
5844 | coding->encoder = encode_coding_big5; | |
c952af22 | 5845 | coding->common_flags |
df7492f9 KH |
5846 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5847 | } | |
5848 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5849 | { |
df7492f9 KH |
5850 | coding->detector = NULL; |
5851 | coding->decoder = decode_coding_raw_text; | |
5852 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5853 | if (! EQ (eol_type, Qunix)) |
5854 | { | |
5855 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5856 | if (! VECTORP (eol_type)) | |
5857 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5858 | } | |
5859 | ||
4ed46869 | 5860 | } |
4ed46869 | 5861 | |
df7492f9 | 5862 | return; |
4ed46869 KH |
5863 | } |
5864 | ||
0ff61e78 KH |
5865 | /* Return a list of charsets supported by CODING. */ |
5866 | ||
5867 | Lisp_Object | |
971de7fb | 5868 | coding_charset_list (struct coding_system *coding) |
0ff61e78 | 5869 | { |
35befdaa | 5870 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5871 | |
5872 | CODING_GET_INFO (coding, attrs, charset_list); | |
5873 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5874 | { | |
5875 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5876 | ||
5877 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5878 | charset_list = Viso_2022_charset_list; | |
5879 | } | |
5880 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5881 | { | |
5882 | charset_list = Vemacs_mule_charset_list; | |
5883 | } | |
5884 | return charset_list; | |
5885 | } | |
5886 | ||
5887 | ||
e9f91ece KH |
5888 | /* Return a list of charsets supported by CODING-SYSTEM. */ |
5889 | ||
5890 | Lisp_Object | |
971de7fb | 5891 | coding_system_charset_list (Lisp_Object coding_system) |
e9f91ece KH |
5892 | { |
5893 | int id; | |
5894 | Lisp_Object attrs, charset_list; | |
5895 | ||
5896 | CHECK_CODING_SYSTEM_GET_ID (coding_system, id); | |
5897 | attrs = CODING_ID_ATTRS (id); | |
5898 | ||
5899 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5900 | { | |
5901 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5902 | ||
5903 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5904 | charset_list = Viso_2022_charset_list; | |
5905 | else | |
5906 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5907 | } | |
5908 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5909 | { | |
5910 | charset_list = Vemacs_mule_charset_list; | |
5911 | } | |
5912 | else | |
5913 | { | |
5914 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5915 | } | |
5916 | return charset_list; | |
5917 | } | |
5918 | ||
5919 | ||
df7492f9 KH |
5920 | /* Return raw-text or one of its subsidiaries that has the same |
5921 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5922 | |
df7492f9 | 5923 | Lisp_Object |
971de7fb | 5924 | raw_text_coding_system (Lisp_Object coding_system) |
ec6d2bb8 | 5925 | { |
0be8721c | 5926 | Lisp_Object spec, attrs; |
df7492f9 | 5927 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5928 | |
d3e4cb56 KH |
5929 | if (NILP (coding_system)) |
5930 | return Qraw_text; | |
df7492f9 KH |
5931 | spec = CODING_SYSTEM_SPEC (coding_system); |
5932 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5933 | |
df7492f9 KH |
5934 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5935 | return coding_system; | |
ec6d2bb8 | 5936 | |
df7492f9 KH |
5937 | eol_type = AREF (spec, 2); |
5938 | if (VECTORP (eol_type)) | |
5939 | return Qraw_text; | |
5940 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5941 | raw_text_eol_type = AREF (spec, 2); | |
5942 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5943 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5944 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5945 | } |
5946 | ||
54f78171 | 5947 | |
1911a33b KH |
5948 | /* If CODING_SYSTEM doesn't specify end-of-line format, return one of |
5949 | the subsidiary that has the same eol-spec as PARENT (if it is not | |
5950 | nil and specifies end-of-line format) or the system's setting | |
fcbcfb64 | 5951 | (system_eol_type). */ |
df7492f9 KH |
5952 | |
5953 | Lisp_Object | |
971de7fb | 5954 | coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent) |
54f78171 | 5955 | { |
3e139625 | 5956 | Lisp_Object spec, eol_type; |
54f78171 | 5957 | |
d3e4cb56 KH |
5958 | if (NILP (coding_system)) |
5959 | coding_system = Qraw_text; | |
df7492f9 | 5960 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5961 | eol_type = AREF (spec, 2); |
fcbcfb64 | 5962 | if (VECTORP (eol_type)) |
df7492f9 | 5963 | { |
df7492f9 KH |
5964 | Lisp_Object parent_eol_type; |
5965 | ||
fcbcfb64 KH |
5966 | if (! NILP (parent)) |
5967 | { | |
5968 | Lisp_Object parent_spec; | |
5969 | ||
4a015c45 | 5970 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 | 5971 | parent_eol_type = AREF (parent_spec, 2); |
1911a33b | 5972 | if (VECTORP (parent_eol_type)) |
4628bef1 | 5973 | parent_eol_type = system_eol_type; |
fcbcfb64 KH |
5974 | } |
5975 | else | |
5976 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
5977 | if (EQ (parent_eol_type, Qunix)) |
5978 | coding_system = AREF (eol_type, 0); | |
5979 | else if (EQ (parent_eol_type, Qdos)) | |
5980 | coding_system = AREF (eol_type, 1); | |
5981 | else if (EQ (parent_eol_type, Qmac)) | |
5982 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5983 | } |
df7492f9 | 5984 | return coding_system; |
54f78171 KH |
5985 | } |
5986 | ||
fcaf8878 KH |
5987 | |
5988 | /* Check if text-conversion and eol-conversion of CODING_SYSTEM are | |
5989 | decided for writing to a process. If not, complement them, and | |
5990 | return a new coding system. */ | |
5991 | ||
5992 | Lisp_Object | |
4628bef1 | 5993 | complement_process_encoding_system (Lisp_Object coding_system) |
fcaf8878 | 5994 | { |
5886ec9c KH |
5995 | Lisp_Object coding_base = Qnil, eol_base = Qnil; |
5996 | Lisp_Object spec, attrs; | |
93d50df8 | 5997 | int i; |
fcaf8878 | 5998 | |
93d50df8 | 5999 | for (i = 0; i < 3; i++) |
fcaf8878 | 6000 | { |
93d50df8 KH |
6001 | if (i == 1) |
6002 | coding_system = CDR_SAFE (Vdefault_process_coding_system); | |
6003 | else if (i == 2) | |
6004 | coding_system = preferred_coding_system (); | |
6005 | spec = CODING_SYSTEM_SPEC (coding_system); | |
6006 | if (NILP (spec)) | |
6007 | continue; | |
6008 | attrs = AREF (spec, 0); | |
6009 | if (NILP (coding_base) && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
6010 | coding_base = CODING_ATTR_BASE_NAME (attrs); | |
6011 | if (NILP (eol_base) && ! VECTORP (AREF (spec, 2))) | |
6012 | eol_base = coding_system; | |
6013 | if (! NILP (coding_base) && ! NILP (eol_base)) | |
6014 | break; | |
fcaf8878 | 6015 | } |
fcaf8878 | 6016 | |
93d50df8 KH |
6017 | if (i > 0) |
6018 | /* The original CODING_SYSTEM didn't specify text-conversion or | |
6019 | eol-conversion. Be sure that we return a fully complemented | |
6020 | coding system. */ | |
6021 | coding_system = coding_inherit_eol_type (coding_base, eol_base); | |
6022 | return coding_system; | |
fcaf8878 KH |
6023 | } |
6024 | ||
6025 | ||
4ed46869 KH |
6026 | /* Emacs has a mechanism to automatically detect a coding system if it |
6027 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
6028 | it's impossible to distinguish some coding systems accurately | |
6029 | because they use the same range of codes. So, at first, coding | |
6030 | systems are categorized into 7, those are: | |
6031 | ||
0ef69138 | 6032 | o coding-category-emacs-mule |
4ed46869 KH |
6033 | |
6034 | The category for a coding system which has the same code range | |
6035 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 6036 | symbol) `emacs-mule' by default. |
4ed46869 KH |
6037 | |
6038 | o coding-category-sjis | |
6039 | ||
6040 | The category for a coding system which has the same code range | |
6041 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 6042 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
6043 | |
6044 | o coding-category-iso-7 | |
6045 | ||
6046 | The category for a coding system which has the same code range | |
7717c392 | 6047 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
6048 | shift and single shift functions. This can encode/decode all |
6049 | charsets. Assigned the coding-system (Lisp symbol) | |
6050 | `iso-2022-7bit' by default. | |
6051 | ||
6052 | o coding-category-iso-7-tight | |
6053 | ||
6054 | Same as coding-category-iso-7 except that this can | |
6055 | encode/decode only the specified charsets. | |
4ed46869 KH |
6056 | |
6057 | o coding-category-iso-8-1 | |
6058 | ||
6059 | The category for a coding system which has the same code range | |
6060 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6061 | for DIMENSION1 charset. This doesn't use any locking shift |
6062 | and single shift functions. Assigned the coding-system (Lisp | |
6063 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
6064 | |
6065 | o coding-category-iso-8-2 | |
6066 | ||
6067 | The category for a coding system which has the same code range | |
6068 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6069 | for DIMENSION2 charset. This doesn't use any locking shift |
6070 | and single shift functions. Assigned the coding-system (Lisp | |
6071 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 6072 | |
7717c392 | 6073 | o coding-category-iso-7-else |
4ed46869 KH |
6074 | |
6075 | The category for a coding system which has the same code range | |
ad1746f5 | 6076 | as ISO2022 of 7-bit environment but uses locking shift or |
7717c392 KH |
6077 | single shift functions. Assigned the coding-system (Lisp |
6078 | symbol) `iso-2022-7bit-lock' by default. | |
6079 | ||
6080 | o coding-category-iso-8-else | |
6081 | ||
6082 | The category for a coding system which has the same code range | |
ad1746f5 | 6083 | as ISO2022 of 8-bit environment but uses locking shift or |
7717c392 KH |
6084 | single shift functions. Assigned the coding-system (Lisp |
6085 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
6086 | |
6087 | o coding-category-big5 | |
6088 | ||
6089 | The category for a coding system which has the same code range | |
6090 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6091 | `cn-big5' by default. |
4ed46869 | 6092 | |
fa42c37f KH |
6093 | o coding-category-utf-8 |
6094 | ||
6095 | The category for a coding system which has the same code range | |
6e76ae91 | 6096 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
6097 | symbol) `utf-8' by default. |
6098 | ||
6099 | o coding-category-utf-16-be | |
6100 | ||
6101 | The category for a coding system in which a text has an | |
6102 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
6103 | endian at the head. Assigned the coding-system (Lisp symbol) | |
6104 | `utf-16-be' by default. | |
6105 | ||
6106 | o coding-category-utf-16-le | |
6107 | ||
6108 | The category for a coding system in which a text has an | |
6109 | Unicode signature (cf. Unicode Standard) in the order of | |
6110 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
6111 | symbol) `utf-16-le' by default. | |
6112 | ||
1397dc18 KH |
6113 | o coding-category-ccl |
6114 | ||
6115 | The category for a coding system of which encoder/decoder is | |
6116 | written in CCL programs. The default value is nil, i.e., no | |
6117 | coding system is assigned. | |
6118 | ||
4ed46869 KH |
6119 | o coding-category-binary |
6120 | ||
6121 | The category for a coding system not categorized in any of the | |
6122 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6123 | `no-conversion' by default. |
4ed46869 KH |
6124 | |
6125 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 6126 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
6127 | What Emacs does actually is to detect a category of coding system. |
6128 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 6129 | decide only one possible category, it selects a category of the |
4ed46869 KH |
6130 | highest priority. Priorities of categories are also specified by a |
6131 | user in a Lisp variable `coding-category-list'. | |
6132 | ||
6133 | */ | |
6134 | ||
df7492f9 KH |
6135 | #define EOL_SEEN_NONE 0 |
6136 | #define EOL_SEEN_LF 1 | |
6137 | #define EOL_SEEN_CR 2 | |
6138 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 6139 | |
ff0dacd7 KH |
6140 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
6141 | SOURCE is encoded. If CATEGORY is one of | |
6142 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
6143 | two-byte, else they are encoded by one-byte. | |
6144 | ||
6145 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 6146 | |
bc4bc72a | 6147 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
6148 | |
6149 | static int | |
cf84bb53 JB |
6150 | detect_eol (const unsigned char *source, EMACS_INT src_bytes, |
6151 | enum coding_category category) | |
4ed46869 | 6152 | { |
f6cbaf43 | 6153 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 6154 | unsigned char c; |
df7492f9 KH |
6155 | int total = 0; |
6156 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 6157 | |
89528eb3 | 6158 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 6159 | { |
df7492f9 | 6160 | int msb, lsb; |
fa42c37f | 6161 | |
89528eb3 KH |
6162 | msb = category == (coding_category_utf_16_le |
6163 | | coding_category_utf_16_le_nosig); | |
df7492f9 | 6164 | lsb = 1 - msb; |
fa42c37f | 6165 | |
df7492f9 | 6166 | while (src + 1 < src_end) |
fa42c37f | 6167 | { |
df7492f9 KH |
6168 | c = src[lsb]; |
6169 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 6170 | { |
df7492f9 KH |
6171 | int this_eol; |
6172 | ||
6173 | if (c == '\n') | |
6174 | this_eol = EOL_SEEN_LF; | |
6175 | else if (src + 3 >= src_end | |
6176 | || src[msb + 2] != 0 | |
6177 | || src[lsb + 2] != '\n') | |
6178 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 6179 | else |
75f4f1ac EZ |
6180 | { |
6181 | this_eol = EOL_SEEN_CRLF; | |
6182 | src += 2; | |
6183 | } | |
df7492f9 KH |
6184 | |
6185 | if (eol_seen == EOL_SEEN_NONE) | |
6186 | /* This is the first end-of-line. */ | |
6187 | eol_seen = this_eol; | |
6188 | else if (eol_seen != this_eol) | |
fa42c37f | 6189 | { |
75f4f1ac EZ |
6190 | /* The found type is different from what found before. |
6191 | Allow for stray ^M characters in DOS EOL files. */ | |
ef1b0ba7 SM |
6192 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) |
6193 | || (eol_seen == EOL_SEEN_CRLF | |
6194 | && this_eol == EOL_SEEN_CR)) | |
75f4f1ac EZ |
6195 | eol_seen = EOL_SEEN_CRLF; |
6196 | else | |
6197 | { | |
6198 | eol_seen = EOL_SEEN_LF; | |
6199 | break; | |
6200 | } | |
fa42c37f | 6201 | } |
df7492f9 KH |
6202 | if (++total == MAX_EOL_CHECK_COUNT) |
6203 | break; | |
fa42c37f | 6204 | } |
df7492f9 | 6205 | src += 2; |
fa42c37f | 6206 | } |
bcf26d6a | 6207 | } |
d46c5b12 | 6208 | else |
ef1b0ba7 SM |
6209 | while (src < src_end) |
6210 | { | |
6211 | c = *src++; | |
6212 | if (c == '\n' || c == '\r') | |
6213 | { | |
6214 | int this_eol; | |
d46c5b12 | 6215 | |
ef1b0ba7 SM |
6216 | if (c == '\n') |
6217 | this_eol = EOL_SEEN_LF; | |
6218 | else if (src >= src_end || *src != '\n') | |
6219 | this_eol = EOL_SEEN_CR; | |
6220 | else | |
6221 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 6222 | |
ef1b0ba7 SM |
6223 | if (eol_seen == EOL_SEEN_NONE) |
6224 | /* This is the first end-of-line. */ | |
6225 | eol_seen = this_eol; | |
6226 | else if (eol_seen != this_eol) | |
6227 | { | |
6228 | /* The found type is different from what found before. | |
6229 | Allow for stray ^M characters in DOS EOL files. */ | |
6230 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) | |
6231 | || (eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR)) | |
6232 | eol_seen = EOL_SEEN_CRLF; | |
6233 | else | |
6234 | { | |
6235 | eol_seen = EOL_SEEN_LF; | |
6236 | break; | |
6237 | } | |
6238 | } | |
6239 | if (++total == MAX_EOL_CHECK_COUNT) | |
6240 | break; | |
6241 | } | |
6242 | } | |
df7492f9 | 6243 | return eol_seen; |
73be902c KH |
6244 | } |
6245 | ||
df7492f9 | 6246 | |
24a73b0a | 6247 | static Lisp_Object |
971de7fb | 6248 | adjust_coding_eol_type (struct coding_system *coding, int eol_seen) |
73be902c | 6249 | { |
0be8721c | 6250 | Lisp_Object eol_type; |
8f924df7 | 6251 | |
df7492f9 KH |
6252 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6253 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
6254 | { |
6255 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6256 | eol_type = Qunix; | |
6257 | } | |
6f197c07 | 6258 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
6259 | { |
6260 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
6261 | eol_type = Qdos; | |
6262 | } | |
6f197c07 | 6263 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
6264 | { |
6265 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
6266 | eol_type = Qmac; | |
6267 | } | |
6268 | return eol_type; | |
d46c5b12 | 6269 | } |
4ed46869 | 6270 | |
df7492f9 KH |
6271 | /* Detect how a text specified in CODING is encoded. If a coding |
6272 | system is detected, update fields of CODING by the detected coding | |
6273 | system. */ | |
0a28aafb | 6274 | |
df7492f9 | 6275 | void |
971de7fb | 6276 | detect_coding (struct coding_system *coding) |
d46c5b12 | 6277 | { |
8f924df7 | 6278 | const unsigned char *src, *src_end; |
73cce38d | 6279 | int saved_mode = coding->mode; |
d46c5b12 | 6280 | |
df7492f9 KH |
6281 | coding->consumed = coding->consumed_char = 0; |
6282 | coding->produced = coding->produced_char = 0; | |
6283 | coding_set_source (coding); | |
1c3478b0 | 6284 | |
df7492f9 | 6285 | src_end = coding->source + coding->src_bytes; |
c0e16b14 | 6286 | coding->head_ascii = 0; |
1c3478b0 | 6287 | |
df7492f9 KH |
6288 | /* If we have not yet decided the text encoding type, detect it |
6289 | now. */ | |
6290 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 6291 | { |
df7492f9 | 6292 | int c, i; |
6cb21a4f | 6293 | struct coding_detection_info detect_info; |
2f3cbb32 | 6294 | int null_byte_found = 0, eight_bit_found = 0; |
df7492f9 | 6295 | |
6cb21a4f | 6296 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 6297 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 6298 | { |
df7492f9 | 6299 | c = *src; |
6cb21a4f | 6300 | if (c & 0x80) |
6cb21a4f | 6301 | { |
2f3cbb32 | 6302 | eight_bit_found = 1; |
2f3cbb32 KH |
6303 | if (null_byte_found) |
6304 | break; | |
6305 | } | |
6306 | else if (c < 0x20) | |
6307 | { | |
6308 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
6309 | && ! inhibit_iso_escape_detection | |
6310 | && ! detect_info.checked) | |
6cb21a4f | 6311 | { |
2f3cbb32 KH |
6312 | if (detect_coding_iso_2022 (coding, &detect_info)) |
6313 | { | |
6314 | /* We have scanned the whole data. */ | |
6315 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
6316 | { |
6317 | /* We didn't find an 8-bit code. We may | |
6318 | have found a null-byte, but it's very | |
ce5b453a | 6319 | rare that a binary file conforms to |
c0e16b14 KH |
6320 | ISO-2022. */ |
6321 | src = src_end; | |
6322 | coding->head_ascii = src - coding->source; | |
6323 | } | |
6324 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
6325 | break; |
6326 | } | |
6327 | } | |
97b1b294 | 6328 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
6329 | { |
6330 | null_byte_found = 1; | |
6331 | if (eight_bit_found) | |
6332 | break; | |
6cb21a4f | 6333 | } |
c006c0c8 KH |
6334 | if (! eight_bit_found) |
6335 | coding->head_ascii++; | |
6cb21a4f | 6336 | } |
c006c0c8 | 6337 | else if (! eight_bit_found) |
c0e16b14 | 6338 | coding->head_ascii++; |
d46c5b12 | 6339 | } |
df7492f9 | 6340 | |
2f3cbb32 KH |
6341 | if (null_byte_found || eight_bit_found |
6342 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 6343 | || detect_info.found) |
d46c5b12 | 6344 | { |
ff0dacd7 KH |
6345 | enum coding_category category; |
6346 | struct coding_system *this; | |
df7492f9 | 6347 | |
6cb21a4f KH |
6348 | if (coding->head_ascii == coding->src_bytes) |
6349 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
6350 | for (i = 0; i < coding_category_raw_text; i++) | |
6351 | { | |
6352 | category = coding_priorities[i]; | |
6353 | this = coding_categories + category; | |
6354 | if (detect_info.found & (1 << category)) | |
24a73b0a | 6355 | break; |
6cb21a4f KH |
6356 | } |
6357 | else | |
2f3cbb32 KH |
6358 | { |
6359 | if (null_byte_found) | |
ff0dacd7 | 6360 | { |
2f3cbb32 KH |
6361 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
6362 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 6363 | } |
2f3cbb32 KH |
6364 | for (i = 0; i < coding_category_raw_text; i++) |
6365 | { | |
6366 | category = coding_priorities[i]; | |
6367 | this = coding_categories + category; | |
6368 | if (this->id < 0) | |
6369 | { | |
6370 | /* No coding system of this category is defined. */ | |
6371 | detect_info.rejected |= (1 << category); | |
6372 | } | |
6373 | else if (category >= coding_category_raw_text) | |
6374 | continue; | |
6375 | else if (detect_info.checked & (1 << category)) | |
6376 | { | |
6377 | if (detect_info.found & (1 << category)) | |
6378 | break; | |
6379 | } | |
6380 | else if ((*(this->detector)) (coding, &detect_info) | |
6381 | && detect_info.found & (1 << category)) | |
6382 | { | |
6383 | if (category == coding_category_utf_16_auto) | |
6384 | { | |
6385 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6386 | category = coding_category_utf_16_le; | |
6387 | else | |
6388 | category = coding_category_utf_16_be; | |
6389 | } | |
6390 | break; | |
6391 | } | |
6392 | } | |
2f3cbb32 | 6393 | } |
c0e16b14 KH |
6394 | |
6395 | if (i < coding_category_raw_text) | |
6396 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6397 | else if (null_byte_found) | |
6398 | setup_coding_system (Qno_conversion, coding); | |
6399 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) | |
6400 | == CATEGORY_MASK_ANY) | |
6401 | setup_coding_system (Qraw_text, coding); | |
6402 | else if (detect_info.rejected) | |
6403 | for (i = 0; i < coding_category_raw_text; i++) | |
6404 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6405 | { | |
6406 | this = coding_categories + coding_priorities[i]; | |
6407 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6408 | break; | |
6409 | } | |
d46c5b12 | 6410 | } |
b73bfc1c | 6411 | } |
a470d443 KH |
6412 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6413 | == coding_category_utf_8_auto) | |
6414 | { | |
6415 | Lisp_Object coding_systems; | |
6416 | struct coding_detection_info detect_info; | |
6417 | ||
6418 | coding_systems | |
6419 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6420 | detect_info.found = detect_info.rejected = 0; | |
6421 | coding->head_ascii = 0; | |
6422 | if (CONSP (coding_systems) | |
6423 | && detect_coding_utf_8 (coding, &detect_info)) | |
6424 | { | |
6425 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6426 | setup_coding_system (XCAR (coding_systems), coding); | |
6427 | else | |
6428 | setup_coding_system (XCDR (coding_systems), coding); | |
6429 | } | |
6430 | } | |
24a73b0a KH |
6431 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6432 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6433 | { |
6434 | Lisp_Object coding_systems; | |
6435 | struct coding_detection_info detect_info; | |
6436 | ||
6437 | coding_systems | |
a470d443 | 6438 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6439 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6440 | coding->head_ascii = 0; |
b49a1807 | 6441 | if (CONSP (coding_systems) |
24a73b0a | 6442 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6443 | { |
6444 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6445 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 6446 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
6447 | setup_coding_system (XCDR (coding_systems), coding); |
6448 | } | |
6449 | } | |
73cce38d | 6450 | coding->mode = saved_mode; |
4ed46869 | 6451 | } |
4ed46869 | 6452 | |
d46c5b12 | 6453 | |
aaaf0b1e | 6454 | static void |
971de7fb | 6455 | decode_eol (struct coding_system *coding) |
aaaf0b1e | 6456 | { |
24a73b0a KH |
6457 | Lisp_Object eol_type; |
6458 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6459 | |
24a73b0a | 6460 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
0a9564cb | 6461 | if (EQ (eol_type, Qunix) || inhibit_eol_conversion) |
24a73b0a KH |
6462 | return; |
6463 | ||
6464 | if (NILP (coding->dst_object)) | |
6465 | pbeg = coding->destination; | |
6466 | else | |
6467 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6468 | pend = pbeg + coding->produced; | |
6469 | ||
6470 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6471 | { |
df7492f9 | 6472 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6473 | |
24a73b0a | 6474 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6475 | { |
df7492f9 KH |
6476 | if (*p == '\n') |
6477 | eol_seen |= EOL_SEEN_LF; | |
6478 | else if (*p == '\r') | |
aaaf0b1e | 6479 | { |
df7492f9 | 6480 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6481 | { |
df7492f9 KH |
6482 | eol_seen |= EOL_SEEN_CRLF; |
6483 | p++; | |
aaaf0b1e | 6484 | } |
aaaf0b1e | 6485 | else |
df7492f9 | 6486 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6487 | } |
aaaf0b1e | 6488 | } |
75f4f1ac EZ |
6489 | /* Handle DOS-style EOLs in a file with stray ^M characters. */ |
6490 | if ((eol_seen & EOL_SEEN_CRLF) != 0 | |
6491 | && (eol_seen & EOL_SEEN_CR) != 0 | |
6492 | && (eol_seen & EOL_SEEN_LF) == 0) | |
6493 | eol_seen = EOL_SEEN_CRLF; | |
6494 | else if (eol_seen != EOL_SEEN_NONE | |
24a73b0a KH |
6495 | && eol_seen != EOL_SEEN_LF |
6496 | && eol_seen != EOL_SEEN_CRLF | |
6497 | && eol_seen != EOL_SEEN_CR) | |
6498 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6499 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6500 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6501 | } |
d46c5b12 | 6502 | |
24a73b0a | 6503 | if (EQ (eol_type, Qmac)) |
27901516 | 6504 | { |
24a73b0a | 6505 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6506 | if (*p == '\r') |
6507 | *p = '\n'; | |
4ed46869 | 6508 | } |
24a73b0a | 6509 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6510 | { |
24a73b0a | 6511 | int n = 0; |
b73bfc1c | 6512 | |
24a73b0a KH |
6513 | if (NILP (coding->dst_object)) |
6514 | { | |
4347441b KH |
6515 | /* Start deleting '\r' from the tail to minimize the memory |
6516 | movement. */ | |
24a73b0a KH |
6517 | for (p = pend - 2; p >= pbeg; p--) |
6518 | if (*p == '\r') | |
6519 | { | |
72af86bd | 6520 | memmove (p, p + 1, pend-- - p - 1); |
24a73b0a KH |
6521 | n++; |
6522 | } | |
6523 | } | |
6524 | else | |
6525 | { | |
4347441b KH |
6526 | int pos_byte = coding->dst_pos_byte; |
6527 | int pos = coding->dst_pos; | |
6528 | int pos_end = pos + coding->produced_char - 1; | |
6529 | ||
6530 | while (pos < pos_end) | |
6531 | { | |
6532 | p = BYTE_POS_ADDR (pos_byte); | |
6533 | if (*p == '\r' && p[1] == '\n') | |
6534 | { | |
6535 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6536 | n++; | |
6537 | pos_end--; | |
6538 | } | |
6539 | pos++; | |
69b8522d KH |
6540 | if (coding->dst_multibyte) |
6541 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6542 | else | |
6543 | pos_byte++; | |
4347441b | 6544 | } |
24a73b0a KH |
6545 | } |
6546 | coding->produced -= n; | |
6547 | coding->produced_char -= n; | |
aaaf0b1e | 6548 | } |
4ed46869 KH |
6549 | } |
6550 | ||
7d64c6ad | 6551 | |
a6f87d34 KH |
6552 | /* Return a translation table (or list of them) from coding system |
6553 | attribute vector ATTRS for encoding (ENCODEP is nonzero) or | |
6554 | decoding (ENCODEP is zero). */ | |
7d64c6ad | 6555 | |
e6a54062 | 6556 | static Lisp_Object |
971de7fb | 6557 | get_translation_table (Lisp_Object attrs, int encodep, int *max_lookup) |
7d64c6ad KH |
6558 | { |
6559 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6560 | Lisp_Object val; |
7d64c6ad | 6561 | |
4bed5909 CY |
6562 | if (NILP (Venable_character_translation)) |
6563 | { | |
6564 | if (max_lookup) | |
6565 | *max_lookup = 0; | |
6566 | return Qnil; | |
6567 | } | |
7d64c6ad KH |
6568 | if (encodep) |
6569 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6570 | standard = Vstandard_translation_table_for_encode; | |
6571 | else | |
6572 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6573 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6574 | if (NILP (translation_table)) |
09ee6fdd KH |
6575 | translation_table = standard; |
6576 | else | |
a6f87d34 | 6577 | { |
09ee6fdd KH |
6578 | if (SYMBOLP (translation_table)) |
6579 | translation_table = Fget (translation_table, Qtranslation_table); | |
6580 | else if (CONSP (translation_table)) | |
6581 | { | |
6582 | translation_table = Fcopy_sequence (translation_table); | |
6583 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6584 | if (SYMBOLP (XCAR (val))) | |
6585 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6586 | } | |
6587 | if (CHAR_TABLE_P (standard)) | |
6588 | { | |
6589 | if (CONSP (translation_table)) | |
6590 | translation_table = nconc2 (translation_table, | |
6591 | Fcons (standard, Qnil)); | |
6592 | else | |
6593 | translation_table = Fcons (translation_table, | |
6594 | Fcons (standard, Qnil)); | |
6595 | } | |
a6f87d34 | 6596 | } |
2170c8f0 KH |
6597 | |
6598 | if (max_lookup) | |
09ee6fdd | 6599 | { |
2170c8f0 KH |
6600 | *max_lookup = 1; |
6601 | if (CHAR_TABLE_P (translation_table) | |
6602 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6603 | { | |
6604 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6605 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6606 | *max_lookup = XFASTINT (val); | |
6607 | } | |
6608 | else if (CONSP (translation_table)) | |
6609 | { | |
6610 | Lisp_Object tail, val; | |
09ee6fdd | 6611 | |
2170c8f0 KH |
6612 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6613 | if (CHAR_TABLE_P (XCAR (tail)) | |
6614 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6615 | { | |
6616 | val = XCHAR_TABLE (XCAR (tail))->extras[1]; | |
6617 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6618 | *max_lookup = XFASTINT (val); | |
6619 | } | |
6620 | } | |
a6f87d34 | 6621 | } |
7d64c6ad KH |
6622 | return translation_table; |
6623 | } | |
6624 | ||
09ee6fdd KH |
6625 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6626 | do { \ | |
6627 | trans = Qnil; \ | |
6628 | if (CHAR_TABLE_P (table)) \ | |
6629 | { \ | |
6630 | trans = CHAR_TABLE_REF (table, c); \ | |
6631 | if (CHARACTERP (trans)) \ | |
6632 | c = XFASTINT (trans), trans = Qnil; \ | |
6633 | } \ | |
6634 | else if (CONSP (table)) \ | |
6635 | { \ | |
6636 | Lisp_Object tail; \ | |
6637 | \ | |
6638 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6639 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6640 | { \ | |
6641 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6642 | if (CHARACTERP (trans)) \ | |
6643 | c = XFASTINT (trans), trans = Qnil; \ | |
6644 | else if (! NILP (trans)) \ | |
6645 | break; \ | |
6646 | } \ | |
6647 | } \ | |
e6a54062 KH |
6648 | } while (0) |
6649 | ||
7d64c6ad | 6650 | |
e951386e KH |
6651 | /* Return a translation of character(s) at BUF according to TRANS. |
6652 | TRANS is TO-CHAR or ((FROM . TO) ...) where | |
6653 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | |
6654 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | |
6655 | translation is found, and Qnil if not found.. | |
6656 | If BUF is too short to lookup characters in FROM, return Qt. */ | |
6657 | ||
69a80ea3 | 6658 | static Lisp_Object |
971de7fb | 6659 | get_translation (Lisp_Object trans, int *buf, int *buf_end) |
69a80ea3 | 6660 | { |
e951386e KH |
6661 | |
6662 | if (INTEGERP (trans)) | |
6663 | return trans; | |
6664 | for (; CONSP (trans); trans = XCDR (trans)) | |
69a80ea3 | 6665 | { |
e951386e KH |
6666 | Lisp_Object val = XCAR (trans); |
6667 | Lisp_Object from = XCAR (val); | |
6668 | int len = ASIZE (from); | |
6669 | int i; | |
69a80ea3 | 6670 | |
e951386e | 6671 | for (i = 0; i < len; i++) |
69a80ea3 | 6672 | { |
e951386e KH |
6673 | if (buf + i == buf_end) |
6674 | return Qt; | |
6675 | if (XINT (AREF (from, i)) != buf[i]) | |
6676 | break; | |
69a80ea3 | 6677 | } |
e951386e KH |
6678 | if (i == len) |
6679 | return val; | |
69a80ea3 | 6680 | } |
e951386e | 6681 | return Qnil; |
69a80ea3 KH |
6682 | } |
6683 | ||
6684 | ||
d46c5b12 | 6685 | static int |
cf84bb53 JB |
6686 | produce_chars (struct coding_system *coding, Lisp_Object translation_table, |
6687 | int last_block) | |
4ed46869 | 6688 | { |
df7492f9 KH |
6689 | unsigned char *dst = coding->destination + coding->produced; |
6690 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
119852e7 KH |
6691 | EMACS_INT produced; |
6692 | EMACS_INT produced_chars = 0; | |
69a80ea3 | 6693 | int carryover = 0; |
4ed46869 | 6694 | |
df7492f9 | 6695 | if (! coding->chars_at_source) |
4ed46869 | 6696 | { |
119852e7 | 6697 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6698 | int *buf = coding->charbuf; |
6699 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6700 | |
db274c7a KH |
6701 | if (EQ (coding->src_object, coding->dst_object)) |
6702 | { | |
6703 | coding_set_source (coding); | |
6704 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6705 | } | |
4ed46869 | 6706 | |
df7492f9 | 6707 | while (buf < buf_end) |
4ed46869 | 6708 | { |
69a80ea3 | 6709 | int c = *buf, i; |
bc4bc72a | 6710 | |
df7492f9 KH |
6711 | if (c >= 0) |
6712 | { | |
69a80ea3 KH |
6713 | int from_nchars = 1, to_nchars = 1; |
6714 | Lisp_Object trans = Qnil; | |
6715 | ||
09ee6fdd | 6716 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6717 | if (! NILP (trans)) |
69a80ea3 | 6718 | { |
e951386e KH |
6719 | trans = get_translation (trans, buf, buf_end); |
6720 | if (INTEGERP (trans)) | |
6721 | c = XINT (trans); | |
6722 | else if (CONSP (trans)) | |
6723 | { | |
6724 | from_nchars = ASIZE (XCAR (trans)); | |
6725 | trans = XCDR (trans); | |
6726 | if (INTEGERP (trans)) | |
6727 | c = XINT (trans); | |
6728 | else | |
6729 | { | |
6730 | to_nchars = ASIZE (trans); | |
6731 | c = XINT (AREF (trans, 0)); | |
6732 | } | |
6733 | } | |
6734 | else if (EQ (trans, Qt) && ! last_block) | |
69a80ea3 | 6735 | break; |
69a80ea3 KH |
6736 | } |
6737 | ||
6738 | if (dst + MAX_MULTIBYTE_LENGTH * to_nchars > dst_end) | |
6739 | { | |
6740 | dst = alloc_destination (coding, | |
6741 | buf_end - buf | |
6742 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
6743 | dst); | |
db274c7a KH |
6744 | if (EQ (coding->src_object, coding->dst_object)) |
6745 | { | |
6746 | coding_set_source (coding); | |
e951386e KH |
6747 | dst_end = (((unsigned char *) coding->source) |
6748 | + coding->consumed); | |
db274c7a KH |
6749 | } |
6750 | else | |
6751 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
6752 | } |
6753 | ||
433f7f87 | 6754 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 6755 | { |
433f7f87 KH |
6756 | if (i > 0) |
6757 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
6758 | if (coding->dst_multibyte |
6759 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 6760 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
6761 | else |
6762 | *dst++ = CHAR_TO_BYTE8 (c); | |
6763 | } | |
6764 | produced_chars += to_nchars; | |
e951386e | 6765 | buf += from_nchars; |
d46c5b12 | 6766 | } |
df7492f9 | 6767 | else |
69a80ea3 KH |
6768 | /* This is an annotation datum. (-C) is the length. */ |
6769 | buf += -c; | |
4ed46869 | 6770 | } |
69a80ea3 | 6771 | carryover = buf_end - buf; |
4ed46869 | 6772 | } |
fa42c37f | 6773 | else |
fa42c37f | 6774 | { |
119852e7 | 6775 | /* Source characters are at coding->source. */ |
8f924df7 | 6776 | const unsigned char *src = coding->source; |
119852e7 | 6777 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 6778 | |
db274c7a KH |
6779 | if (EQ (coding->dst_object, coding->src_object)) |
6780 | dst_end = (unsigned char *) src; | |
df7492f9 | 6781 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 6782 | { |
df7492f9 | 6783 | if (coding->src_multibyte) |
fa42c37f | 6784 | { |
71c81426 | 6785 | int multibytep = 1; |
4533845d | 6786 | EMACS_INT consumed_chars = 0; |
d46c5b12 | 6787 | |
df7492f9 KH |
6788 | while (1) |
6789 | { | |
8f924df7 | 6790 | const unsigned char *src_base = src; |
df7492f9 | 6791 | int c; |
b73bfc1c | 6792 | |
df7492f9 | 6793 | ONE_MORE_BYTE (c); |
119852e7 | 6794 | if (dst == dst_end) |
df7492f9 | 6795 | { |
119852e7 KH |
6796 | if (EQ (coding->src_object, coding->dst_object)) |
6797 | dst_end = (unsigned char *) src; | |
6798 | if (dst == dst_end) | |
df7492f9 | 6799 | { |
119852e7 KH |
6800 | EMACS_INT offset = src - coding->source; |
6801 | ||
6802 | dst = alloc_destination (coding, src_end - src + 1, | |
6803 | dst); | |
6804 | dst_end = coding->destination + coding->dst_bytes; | |
6805 | coding_set_source (coding); | |
6806 | src = coding->source + offset; | |
6807 | src_end = coding->source + coding->src_bytes; | |
db274c7a KH |
6808 | if (EQ (coding->src_object, coding->dst_object)) |
6809 | dst_end = (unsigned char *) src; | |
df7492f9 | 6810 | } |
df7492f9 KH |
6811 | } |
6812 | *dst++ = c; | |
6813 | produced_chars++; | |
6814 | } | |
6815 | no_more_source: | |
6816 | ; | |
fa42c37f KH |
6817 | } |
6818 | else | |
df7492f9 KH |
6819 | while (src < src_end) |
6820 | { | |
71c81426 | 6821 | int multibytep = 1; |
df7492f9 | 6822 | int c = *src++; |
b73bfc1c | 6823 | |
df7492f9 KH |
6824 | if (dst >= dst_end - 1) |
6825 | { | |
2c78b7e1 | 6826 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 6827 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
6828 | if (dst >= dst_end - 1) |
6829 | { | |
119852e7 | 6830 | EMACS_INT offset = src - coding->source; |
db274c7a | 6831 | EMACS_INT more_bytes; |
119852e7 | 6832 | |
db274c7a KH |
6833 | if (EQ (coding->src_object, coding->dst_object)) |
6834 | more_bytes = ((src_end - src) / 2) + 2; | |
6835 | else | |
6836 | more_bytes = src_end - src + 2; | |
6837 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
6838 | dst_end = coding->destination + coding->dst_bytes; |
6839 | coding_set_source (coding); | |
119852e7 | 6840 | src = coding->source + offset; |
2c78b7e1 | 6841 | src_end = coding->source + coding->src_bytes; |
db274c7a KH |
6842 | if (EQ (coding->src_object, coding->dst_object)) |
6843 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 6844 | } |
df7492f9 KH |
6845 | } |
6846 | EMIT_ONE_BYTE (c); | |
6847 | } | |
d46c5b12 | 6848 | } |
df7492f9 KH |
6849 | else |
6850 | { | |
6851 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 6852 | { |
119852e7 | 6853 | EMACS_INT require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 6854 | |
df7492f9 | 6855 | if (require > 0) |
fa42c37f | 6856 | { |
df7492f9 KH |
6857 | EMACS_INT offset = src - coding->source; |
6858 | ||
6859 | dst = alloc_destination (coding, require, dst); | |
6860 | coding_set_source (coding); | |
6861 | src = coding->source + offset; | |
6862 | src_end = coding->source + coding->src_bytes; | |
fa42c37f KH |
6863 | } |
6864 | } | |
119852e7 | 6865 | produced_chars = coding->consumed_char; |
df7492f9 | 6866 | while (src < src_end) |
14daee73 | 6867 | *dst++ = *src++; |
fa42c37f KH |
6868 | } |
6869 | } | |
6870 | ||
df7492f9 | 6871 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 6872 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
df7492f9 KH |
6873 | insert_from_gap (produced_chars, produced); |
6874 | coding->produced += produced; | |
6875 | coding->produced_char += produced_chars; | |
69a80ea3 | 6876 | return carryover; |
fa42c37f KH |
6877 | } |
6878 | ||
ff0dacd7 KH |
6879 | /* Compose text in CODING->object according to the annotation data at |
6880 | CHARBUF. CHARBUF is an array: | |
e951386e | 6881 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
df7492f9 | 6882 | */ |
4ed46869 | 6883 | |
df7492f9 | 6884 | static INLINE void |
971de7fb | 6885 | produce_composition (struct coding_system *coding, int *charbuf, EMACS_INT pos) |
4ed46869 | 6886 | { |
df7492f9 | 6887 | int len; |
69a80ea3 | 6888 | EMACS_INT to; |
df7492f9 | 6889 | enum composition_method method; |
df7492f9 | 6890 | Lisp_Object components; |
fa42c37f | 6891 | |
e951386e | 6892 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
69a80ea3 | 6893 | to = pos + charbuf[2]; |
e951386e | 6894 | method = (enum composition_method) (charbuf[4]); |
d46c5b12 | 6895 | |
df7492f9 KH |
6896 | if (method == COMPOSITION_RELATIVE) |
6897 | components = Qnil; | |
e951386e | 6898 | else |
d46c5b12 | 6899 | { |
df7492f9 | 6900 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
e951386e | 6901 | int i, j; |
b73bfc1c | 6902 | |
e951386e KH |
6903 | if (method == COMPOSITION_WITH_RULE) |
6904 | len = charbuf[2] * 3 - 2; | |
6905 | charbuf += MAX_ANNOTATION_LENGTH; | |
6906 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | |
6907 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | |
9ffd559c | 6908 | { |
e951386e KH |
6909 | if (charbuf[i] >= 0) |
6910 | args[j] = make_number (charbuf[i]); | |
6911 | else | |
6912 | { | |
6913 | i++; | |
6914 | args[j] = make_number (charbuf[i] % 0x100); | |
6915 | } | |
9ffd559c | 6916 | } |
e951386e | 6917 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
d46c5b12 | 6918 | } |
69a80ea3 | 6919 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6920 | } |
6921 | ||
d46c5b12 | 6922 | |
ff0dacd7 KH |
6923 | /* Put `charset' property on text in CODING->object according to |
6924 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6925 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6926 | */ |
d46c5b12 | 6927 | |
ff0dacd7 | 6928 | static INLINE void |
971de7fb | 6929 | produce_charset (struct coding_system *coding, int *charbuf, EMACS_INT pos) |
d46c5b12 | 6930 | { |
69a80ea3 KH |
6931 | EMACS_INT from = pos - charbuf[2]; |
6932 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); | |
b73bfc1c | 6933 | |
69a80ea3 | 6934 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6935 | Qcharset, CHARSET_NAME (charset), |
6936 | coding->dst_object); | |
d46c5b12 KH |
6937 | } |
6938 | ||
d46c5b12 | 6939 | |
df7492f9 KH |
6940 | #define CHARBUF_SIZE 0x4000 |
6941 | ||
6942 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6943 | do { \ | |
8510724d | 6944 | int size = CHARBUF_SIZE; \ |
df7492f9 KH |
6945 | \ |
6946 | coding->charbuf = NULL; \ | |
6947 | while (size > 1024) \ | |
6948 | { \ | |
6949 | coding->charbuf = (int *) alloca (sizeof (int) * size); \ | |
6950 | if (coding->charbuf) \ | |
6951 | break; \ | |
6952 | size >>= 1; \ | |
6953 | } \ | |
6954 | if (! coding->charbuf) \ | |
6955 | { \ | |
065e3595 | 6956 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
df7492f9 KH |
6957 | return coding->result; \ |
6958 | } \ | |
6959 | coding->charbuf_size = size; \ | |
6960 | } while (0) | |
4ed46869 | 6961 | |
d46c5b12 KH |
6962 | |
6963 | static void | |
971de7fb | 6964 | produce_annotation (struct coding_system *coding, EMACS_INT pos) |
d46c5b12 | 6965 | { |
df7492f9 KH |
6966 | int *charbuf = coding->charbuf; |
6967 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6968 | |
ff0dacd7 KH |
6969 | if (NILP (coding->dst_object)) |
6970 | return; | |
d46c5b12 | 6971 | |
df7492f9 | 6972 | while (charbuf < charbuf_end) |
a84f1519 | 6973 | { |
df7492f9 | 6974 | if (*charbuf >= 0) |
e951386e | 6975 | pos++, charbuf++; |
d46c5b12 | 6976 | else |
d46c5b12 | 6977 | { |
df7492f9 | 6978 | int len = -*charbuf; |
e951386e KH |
6979 | |
6980 | if (len > 2) | |
6981 | switch (charbuf[1]) | |
6982 | { | |
6983 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
6984 | produce_composition (coding, charbuf, pos); | |
6985 | break; | |
6986 | case CODING_ANNOTATE_CHARSET_MASK: | |
6987 | produce_charset (coding, charbuf, pos); | |
6988 | break; | |
6989 | } | |
df7492f9 | 6990 | charbuf += len; |
d46c5b12 | 6991 | } |
a84f1519 | 6992 | } |
d46c5b12 KH |
6993 | } |
6994 | ||
df7492f9 KH |
6995 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6996 | CODING->src_object is a buffer, a string, or nil. | |
6997 | CODING->dst_object is a buffer. | |
d46c5b12 | 6998 | |
df7492f9 KH |
6999 | If CODING->src_object is a buffer, it must be the current buffer. |
7000 | In this case, if CODING->src_pos is positive, it is a position of | |
7001 | the source text in the buffer, otherwise, the source text is in the | |
7002 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
7003 | the text from GPT (which must be the same as PT). If this is the | |
7004 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7005 | negative. | |
d46c5b12 | 7006 | |
b6828792 | 7007 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 7008 | that string. |
d46c5b12 | 7009 | |
df7492f9 KH |
7010 | If CODING->src_object is nil, CODING->source must already point to |
7011 | the non-relocatable memory area. In this case, CODING->src_pos is | |
7012 | an offset from CODING->source. | |
73be902c | 7013 | |
df7492f9 KH |
7014 | The decoded data is inserted at the current point of the buffer |
7015 | CODING->dst_object. | |
7016 | */ | |
d46c5b12 | 7017 | |
df7492f9 | 7018 | static int |
971de7fb | 7019 | decode_coding (struct coding_system *coding) |
d46c5b12 | 7020 | { |
df7492f9 | 7021 | Lisp_Object attrs; |
24a73b0a | 7022 | Lisp_Object undo_list; |
7d64c6ad | 7023 | Lisp_Object translation_table; |
d0396581 | 7024 | struct ccl_spec cclspec; |
69a80ea3 KH |
7025 | int carryover; |
7026 | int i; | |
d46c5b12 | 7027 | |
df7492f9 KH |
7028 | if (BUFFERP (coding->src_object) |
7029 | && coding->src_pos > 0 | |
7030 | && coding->src_pos < GPT | |
7031 | && coding->src_pos + coding->src_chars > GPT) | |
7032 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 7033 | |
24a73b0a | 7034 | undo_list = Qt; |
df7492f9 | 7035 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 7036 | { |
df7492f9 KH |
7037 | if (current_buffer != XBUFFER (coding->dst_object)) |
7038 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7039 | if (GPT != PT) | |
7040 | move_gap_both (PT, PT_BYTE); | |
5d8ea120 TT |
7041 | undo_list = B_ (current_buffer, undo_list); |
7042 | B_ (current_buffer, undo_list) = Qt; | |
1c3478b0 KH |
7043 | } |
7044 | ||
df7492f9 KH |
7045 | coding->consumed = coding->consumed_char = 0; |
7046 | coding->produced = coding->produced_char = 0; | |
7047 | coding->chars_at_source = 0; | |
065e3595 | 7048 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 7049 | coding->errors = 0; |
1c3478b0 | 7050 | |
df7492f9 KH |
7051 | ALLOC_CONVERSION_WORK_AREA (coding); |
7052 | ||
7053 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 7054 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 7055 | |
69a80ea3 | 7056 | carryover = 0; |
d0396581 KH |
7057 | if (coding->decoder == decode_coding_ccl) |
7058 | { | |
7059 | coding->spec.ccl = &cclspec; | |
7060 | setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding)); | |
7061 | } | |
df7492f9 | 7062 | do |
b73bfc1c | 7063 | { |
69a80ea3 KH |
7064 | EMACS_INT pos = coding->dst_pos + coding->produced_char; |
7065 | ||
df7492f9 KH |
7066 | coding_set_source (coding); |
7067 | coding->annotated = 0; | |
69a80ea3 | 7068 | coding->charbuf_used = carryover; |
df7492f9 | 7069 | (*(coding->decoder)) (coding); |
df7492f9 | 7070 | coding_set_destination (coding); |
69a80ea3 | 7071 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 7072 | if (coding->annotated) |
69a80ea3 KH |
7073 | produce_annotation (coding, pos); |
7074 | for (i = 0; i < carryover; i++) | |
7075 | coding->charbuf[i] | |
7076 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 7077 | } |
d0396581 KH |
7078 | while (coding->result == CODING_RESULT_INSUFFICIENT_DST |
7079 | || (coding->consumed < coding->src_bytes | |
7080 | && (coding->result == CODING_RESULT_SUCCESS | |
7081 | || coding->result == CODING_RESULT_INVALID_SRC))); | |
d46c5b12 | 7082 | |
69a80ea3 KH |
7083 | if (carryover > 0) |
7084 | { | |
7085 | coding_set_destination (coding); | |
7086 | coding->charbuf_used = carryover; | |
7087 | produce_chars (coding, translation_table, 1); | |
7088 | } | |
7089 | ||
df7492f9 KH |
7090 | coding->carryover_bytes = 0; |
7091 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 7092 | { |
df7492f9 | 7093 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 7094 | const unsigned char *src; |
df7492f9 KH |
7095 | |
7096 | coding_set_source (coding); | |
7097 | coding_set_destination (coding); | |
7098 | src = coding->source + coding->consumed; | |
7099 | ||
7100 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 7101 | { |
df7492f9 KH |
7102 | /* Flush out unprocessed data as binary chars. We are sure |
7103 | that the number of data is less than the size of | |
7104 | coding->charbuf. */ | |
065e3595 | 7105 | coding->charbuf_used = 0; |
b2dab6c8 JR |
7106 | coding->chars_at_source = 0; |
7107 | ||
df7492f9 | 7108 | while (nbytes-- > 0) |
1c3478b0 | 7109 | { |
df7492f9 | 7110 | int c = *src++; |
98725083 | 7111 | |
1c91457d KH |
7112 | if (c & 0x80) |
7113 | c = BYTE8_TO_CHAR (c); | |
7114 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 7115 | } |
f6cbaf43 | 7116 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 7117 | } |
d46c5b12 | 7118 | else |
df7492f9 KH |
7119 | { |
7120 | /* Record unprocessed bytes in coding->carryover. We are | |
7121 | sure that the number of data is less than the size of | |
7122 | coding->carryover. */ | |
7123 | unsigned char *p = coding->carryover; | |
7124 | ||
f289d375 KH |
7125 | if (nbytes > sizeof coding->carryover) |
7126 | nbytes = sizeof coding->carryover; | |
df7492f9 KH |
7127 | coding->carryover_bytes = nbytes; |
7128 | while (nbytes-- > 0) | |
7129 | *p++ = *src++; | |
1c3478b0 | 7130 | } |
df7492f9 | 7131 | coding->consumed = coding->src_bytes; |
b73bfc1c | 7132 | } |
69f76525 | 7133 | |
0a9564cb EZ |
7134 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix) |
7135 | && !inhibit_eol_conversion) | |
4347441b | 7136 | decode_eol (coding); |
24a73b0a KH |
7137 | if (BUFFERP (coding->dst_object)) |
7138 | { | |
5d8ea120 | 7139 | B_ (current_buffer, undo_list) = undo_list; |
24a73b0a KH |
7140 | record_insert (coding->dst_pos, coding->produced_char); |
7141 | } | |
73be902c | 7142 | return coding->result; |
4ed46869 KH |
7143 | } |
7144 | ||
aaaf0b1e | 7145 | |
e1c23804 | 7146 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
7147 | ending before LIMIT of CODING->src_object (buffer or string), store |
7148 | the data in BUF, set *STOP to a starting position of the next | |
7149 | composition (if any) or to LIMIT, and return the address of the | |
7150 | next element of BUF. | |
7151 | ||
7152 | If such an annotation is not found, set *STOP to a starting | |
7153 | position of a composition after POS (if any) or to LIMIT, and | |
7154 | return BUF. */ | |
7155 | ||
7156 | static INLINE int * | |
cf84bb53 JB |
7157 | handle_composition_annotation (EMACS_INT pos, EMACS_INT limit, |
7158 | struct coding_system *coding, int *buf, | |
7159 | EMACS_INT *stop) | |
aaaf0b1e | 7160 | { |
ff0dacd7 KH |
7161 | EMACS_INT start, end; |
7162 | Lisp_Object prop; | |
aaaf0b1e | 7163 | |
ff0dacd7 KH |
7164 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
7165 | || end > limit) | |
7166 | *stop = limit; | |
7167 | else if (start > pos) | |
7168 | *stop = start; | |
7169 | else | |
aaaf0b1e | 7170 | { |
ff0dacd7 | 7171 | if (start == pos) |
aaaf0b1e | 7172 | { |
ff0dacd7 KH |
7173 | /* We found a composition. Store the corresponding |
7174 | annotation data in BUF. */ | |
7175 | int *head = buf; | |
7176 | enum composition_method method = COMPOSITION_METHOD (prop); | |
7177 | int nchars = COMPOSITION_LENGTH (prop); | |
7178 | ||
e951386e | 7179 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
ff0dacd7 | 7180 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 7181 | { |
ff0dacd7 KH |
7182 | Lisp_Object components; |
7183 | int len, i, i_byte; | |
7184 | ||
7185 | components = COMPOSITION_COMPONENTS (prop); | |
7186 | if (VECTORP (components)) | |
aaaf0b1e | 7187 | { |
ff0dacd7 KH |
7188 | len = XVECTOR (components)->size; |
7189 | for (i = 0; i < len; i++) | |
7190 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 7191 | } |
ff0dacd7 | 7192 | else if (STRINGP (components)) |
aaaf0b1e | 7193 | { |
8f924df7 | 7194 | len = SCHARS (components); |
ff0dacd7 KH |
7195 | i = i_byte = 0; |
7196 | while (i < len) | |
7197 | { | |
7198 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
7199 | buf++; | |
7200 | } | |
7201 | } | |
7202 | else if (INTEGERP (components)) | |
7203 | { | |
7204 | len = 1; | |
7205 | *buf++ = XINT (components); | |
7206 | } | |
7207 | else if (CONSP (components)) | |
7208 | { | |
7209 | for (len = 0; CONSP (components); | |
7210 | len++, components = XCDR (components)) | |
7211 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 7212 | } |
aaaf0b1e | 7213 | else |
ff0dacd7 KH |
7214 | abort (); |
7215 | *head -= len; | |
aaaf0b1e | 7216 | } |
aaaf0b1e | 7217 | } |
ff0dacd7 KH |
7218 | |
7219 | if (find_composition (end, limit, &start, &end, &prop, | |
7220 | coding->src_object) | |
7221 | && end <= limit) | |
7222 | *stop = start; | |
7223 | else | |
7224 | *stop = limit; | |
aaaf0b1e | 7225 | } |
ff0dacd7 KH |
7226 | return buf; |
7227 | } | |
7228 | ||
7229 | ||
e1c23804 | 7230 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
7231 | CODING->src_object (buffer of string), store the data in BUF, set |
7232 | *STOP to the position where the value of `charset' property changes | |
7233 | (limiting by LIMIT), and return the address of the next element of | |
7234 | BUF. | |
7235 | ||
7236 | If the property value is nil, set *STOP to the position where the | |
7237 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
7238 | ||
7239 | static INLINE int * | |
cf84bb53 JB |
7240 | handle_charset_annotation (EMACS_INT pos, EMACS_INT limit, |
7241 | struct coding_system *coding, int *buf, | |
7242 | EMACS_INT *stop) | |
ff0dacd7 KH |
7243 | { |
7244 | Lisp_Object val, next; | |
7245 | int id; | |
7246 | ||
7247 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
7248 | if (! NILP (val) && CHARSETP (val)) | |
7249 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
7250 | else | |
7251 | id = -1; | |
69a80ea3 | 7252 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
7253 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
7254 | coding->src_object, | |
7255 | make_number (limit)); | |
7256 | *stop = XINT (next); | |
7257 | return buf; | |
7258 | } | |
7259 | ||
7260 | ||
df7492f9 | 7261 | static void |
cf84bb53 JB |
7262 | consume_chars (struct coding_system *coding, Lisp_Object translation_table, |
7263 | int max_lookup) | |
df7492f9 KH |
7264 | { |
7265 | int *buf = coding->charbuf; | |
ff0dacd7 | 7266 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 7267 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 7268 | const unsigned char *src_end = coding->source + coding->src_bytes; |
ff0dacd7 KH |
7269 | EMACS_INT pos = coding->src_pos + coding->consumed_char; |
7270 | EMACS_INT end_pos = coding->src_pos + coding->src_chars; | |
df7492f9 KH |
7271 | int multibytep = coding->src_multibyte; |
7272 | Lisp_Object eol_type; | |
7273 | int c; | |
ff0dacd7 | 7274 | EMACS_INT stop, stop_composition, stop_charset; |
09ee6fdd | 7275 | int *lookup_buf = NULL; |
433f7f87 KH |
7276 | |
7277 | if (! NILP (translation_table)) | |
09ee6fdd | 7278 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 7279 | |
0a9564cb | 7280 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
df7492f9 KH |
7281 | if (VECTORP (eol_type)) |
7282 | eol_type = Qunix; | |
88993dfd | 7283 | |
df7492f9 KH |
7284 | /* Note: composition handling is not yet implemented. */ |
7285 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 7286 | |
0b5670c9 KH |
7287 | if (NILP (coding->src_object)) |
7288 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 7289 | else |
0b5670c9 KH |
7290 | { |
7291 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
7292 | stop = stop_composition = pos; | |
7293 | else | |
7294 | stop = stop_composition = end_pos; | |
7295 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
7296 | stop = stop_charset = pos; | |
7297 | else | |
7298 | stop_charset = end_pos; | |
7299 | } | |
ec6d2bb8 | 7300 | |
24a73b0a | 7301 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 7302 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 7303 | while (buf < buf_end) |
aaaf0b1e | 7304 | { |
433f7f87 KH |
7305 | Lisp_Object trans; |
7306 | ||
df7492f9 | 7307 | if (pos == stop) |
ec6d2bb8 | 7308 | { |
df7492f9 KH |
7309 | if (pos == end_pos) |
7310 | break; | |
ff0dacd7 KH |
7311 | if (pos == stop_composition) |
7312 | buf = handle_composition_annotation (pos, end_pos, coding, | |
7313 | buf, &stop_composition); | |
7314 | if (pos == stop_charset) | |
7315 | buf = handle_charset_annotation (pos, end_pos, coding, | |
7316 | buf, &stop_charset); | |
7317 | stop = (stop_composition < stop_charset | |
7318 | ? stop_composition : stop_charset); | |
df7492f9 KH |
7319 | } |
7320 | ||
7321 | if (! multibytep) | |
4776e638 | 7322 | { |
d3e4cb56 | 7323 | EMACS_INT bytes; |
aaaf0b1e | 7324 | |
4d1e6632 KH |
7325 | if (coding->encoder == encode_coding_raw_text |
7326 | || coding->encoder == encode_coding_ccl) | |
ea29edf2 KH |
7327 | c = *src++, pos++; |
7328 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 7329 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 7330 | else |
f03caae0 | 7331 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 7332 | } |
df7492f9 | 7333 | else |
db274c7a | 7334 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
7335 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
7336 | c = '\n'; | |
7337 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 7338 | { |
df7492f9 | 7339 | if (c == '\n') |
aaaf0b1e | 7340 | { |
df7492f9 KH |
7341 | if (EQ (eol_type, Qdos)) |
7342 | *buf++ = '\r'; | |
7343 | else | |
7344 | c = '\r'; | |
aaaf0b1e KH |
7345 | } |
7346 | } | |
433f7f87 | 7347 | |
e6a54062 | 7348 | trans = Qnil; |
09ee6fdd | 7349 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 7350 | if (NILP (trans)) |
433f7f87 KH |
7351 | *buf++ = c; |
7352 | else | |
7353 | { | |
7354 | int from_nchars = 1, to_nchars = 1; | |
7355 | int *lookup_buf_end; | |
7356 | const unsigned char *p = src; | |
7357 | int i; | |
7358 | ||
7359 | lookup_buf[0] = c; | |
7360 | for (i = 1; i < max_lookup && p < src_end; i++) | |
7361 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
7362 | lookup_buf_end = lookup_buf + i; | |
e951386e KH |
7363 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
7364 | if (INTEGERP (trans)) | |
7365 | c = XINT (trans); | |
7366 | else if (CONSP (trans)) | |
7367 | { | |
7368 | from_nchars = ASIZE (XCAR (trans)); | |
7369 | trans = XCDR (trans); | |
7370 | if (INTEGERP (trans)) | |
7371 | c = XINT (trans); | |
7372 | else | |
7373 | { | |
7374 | to_nchars = ASIZE (trans); | |
7375 | if (buf + to_nchars > buf_end) | |
7376 | break; | |
7377 | c = XINT (AREF (trans, 0)); | |
7378 | } | |
7379 | } | |
7380 | else | |
433f7f87 | 7381 | break; |
e951386e | 7382 | *buf++ = c; |
433f7f87 KH |
7383 | for (i = 1; i < to_nchars; i++) |
7384 | *buf++ = XINT (AREF (trans, i)); | |
7385 | for (i = 1; i < from_nchars; i++, pos++) | |
7386 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7387 | } | |
aaaf0b1e | 7388 | } |
ec6d2bb8 | 7389 | |
df7492f9 KH |
7390 | coding->consumed = src - coding->source; |
7391 | coding->consumed_char = pos - coding->src_pos; | |
7392 | coding->charbuf_used = buf - coding->charbuf; | |
7393 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7394 | } |
7395 | ||
4ed46869 | 7396 | |
df7492f9 KH |
7397 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7398 | CODING->src_object is a buffer or a string. | |
7399 | CODING->dst_object is a buffer or nil. | |
7400 | ||
7401 | If CODING->src_object is a buffer, it must be the current buffer. | |
7402 | In this case, if CODING->src_pos is positive, it is a position of | |
7403 | the source text in the buffer, otherwise. the source text is in the | |
7404 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7405 | the text from GPT (which must be the same as PT). If this is the | |
7406 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7407 | negative and CODING should not have `pre-write-conversion'. | |
7408 | ||
7409 | If CODING->src_object is a string, CODING should not have | |
7410 | `pre-write-conversion'. | |
7411 | ||
7412 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7413 | the current point of that buffer. | |
7414 | ||
7415 | If CODING->dst_object is nil, the encoded data is placed at the | |
7416 | memory area specified by CODING->destination. */ | |
7417 | ||
7418 | static int | |
971de7fb | 7419 | encode_coding (struct coding_system *coding) |
4ed46869 | 7420 | { |
df7492f9 | 7421 | Lisp_Object attrs; |
7d64c6ad | 7422 | Lisp_Object translation_table; |
09ee6fdd | 7423 | int max_lookup; |
fb608df3 | 7424 | struct ccl_spec cclspec; |
9861e777 | 7425 | |
df7492f9 | 7426 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7427 | if (coding->encoder == encode_coding_raw_text) |
7428 | translation_table = Qnil, max_lookup = 0; | |
7429 | else | |
7430 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7431 | |
df7492f9 | 7432 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7433 | { |
df7492f9 KH |
7434 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7435 | coding->dst_multibyte | |
5d8ea120 | 7436 | = ! NILP (B_ (current_buffer, enable_multibyte_characters)); |
8844fa83 | 7437 | } |
4ed46869 | 7438 | |
b73bfc1c | 7439 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7440 | coding->produced = coding->produced_char = 0; |
065e3595 | 7441 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7442 | coding->errors = 0; |
b73bfc1c | 7443 | |
df7492f9 | 7444 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7445 | |
fb608df3 KH |
7446 | if (coding->encoder == encode_coding_ccl) |
7447 | { | |
7448 | coding->spec.ccl = &cclspec; | |
7449 | setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding)); | |
7450 | } | |
df7492f9 KH |
7451 | do { |
7452 | coding_set_source (coding); | |
09ee6fdd | 7453 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7454 | coding_set_destination (coding); |
7455 | (*(coding->encoder)) (coding); | |
7456 | } while (coding->consumed_char < coding->src_chars); | |
7457 | ||
284201e4 | 7458 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
df7492f9 KH |
7459 | insert_from_gap (coding->produced_char, coding->produced); |
7460 | ||
7461 | return (coding->result); | |
ec6d2bb8 KH |
7462 | } |
7463 | ||
fb88bf2d | 7464 | |
24a73b0a KH |
7465 | /* Name (or base name) of work buffer for code conversion. */ |
7466 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7467 | |
24a73b0a KH |
7468 | /* A working buffer used by the top level conversion. Once it is |
7469 | created, it is never destroyed. It has the name | |
7470 | Vcode_conversion_workbuf_name. The other working buffers are | |
7471 | destroyed after the use is finished, and their names are modified | |
7472 | versions of Vcode_conversion_workbuf_name. */ | |
7473 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7474 | |
24a73b0a KH |
7475 | /* 1 iff Vcode_conversion_reused_workbuf is already in use. */ |
7476 | static int reused_workbuf_in_use; | |
4ed46869 | 7477 | |
24a73b0a | 7478 | |
ad1746f5 | 7479 | /* Return a working buffer of code conversion. MULTIBYTE specifies the |
24a73b0a | 7480 | multibyteness of returning buffer. */ |
b73bfc1c | 7481 | |
f6cbaf43 | 7482 | static Lisp_Object |
971de7fb | 7483 | make_conversion_work_buffer (int multibyte) |
df7492f9 | 7484 | { |
24a73b0a KH |
7485 | Lisp_Object name, workbuf; |
7486 | struct buffer *current; | |
4ed46869 | 7487 | |
24a73b0a | 7488 | if (reused_workbuf_in_use++) |
065e3595 KH |
7489 | { |
7490 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7491 | workbuf = Fget_buffer_create (name); | |
7492 | } | |
df7492f9 | 7493 | else |
065e3595 | 7494 | { |
159bd5a2 | 7495 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7496 | Vcode_conversion_reused_workbuf |
7497 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7498 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7499 | } |
24a73b0a KH |
7500 | current = current_buffer; |
7501 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7502 | /* We can't allow modification hooks to run in the work buffer. For |
7503 | instance, directory_files_internal assumes that file decoding | |
7504 | doesn't compile new regexps. */ | |
7505 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7506 | Ferase_buffer (); |
5d8ea120 TT |
7507 | B_ (current_buffer, undo_list) = Qt; |
7508 | B_ (current_buffer, enable_multibyte_characters) = multibyte ? Qt : Qnil; | |
df7492f9 | 7509 | set_buffer_internal (current); |
24a73b0a | 7510 | return workbuf; |
df7492f9 | 7511 | } |
d46c5b12 | 7512 | |
24a73b0a | 7513 | |
4776e638 | 7514 | static Lisp_Object |
971de7fb | 7515 | code_conversion_restore (Lisp_Object arg) |
4776e638 | 7516 | { |
24a73b0a | 7517 | Lisp_Object current, workbuf; |
948bdcf3 | 7518 | struct gcpro gcpro1; |
24a73b0a | 7519 | |
948bdcf3 | 7520 | GCPRO1 (arg); |
24a73b0a KH |
7521 | current = XCAR (arg); |
7522 | workbuf = XCDR (arg); | |
7523 | if (! NILP (workbuf)) | |
7524 | { | |
7525 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7526 | reused_workbuf_in_use = 0; | |
7527 | else if (! NILP (Fbuffer_live_p (workbuf))) | |
7528 | Fkill_buffer (workbuf); | |
7529 | } | |
7530 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7531 | UNGCPRO; |
4776e638 KH |
7532 | return Qnil; |
7533 | } | |
b73bfc1c | 7534 | |
24a73b0a | 7535 | Lisp_Object |
971de7fb | 7536 | code_conversion_save (int with_work_buf, int multibyte) |
df7492f9 | 7537 | { |
24a73b0a | 7538 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7539 | |
4776e638 | 7540 | if (with_work_buf) |
24a73b0a KH |
7541 | workbuf = make_conversion_work_buffer (multibyte); |
7542 | record_unwind_protect (code_conversion_restore, | |
7543 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7544 | return workbuf; |
df7492f9 | 7545 | } |
d46c5b12 | 7546 | |
df7492f9 | 7547 | int |
cf84bb53 JB |
7548 | decode_coding_gap (struct coding_system *coding, |
7549 | EMACS_INT chars, EMACS_INT bytes) | |
df7492f9 | 7550 | { |
1a4990fb | 7551 | int count = SPECPDL_INDEX (); |
5e5c78be | 7552 | Lisp_Object attrs; |
fb88bf2d | 7553 | |
24a73b0a | 7554 | code_conversion_save (0, 0); |
ec6d2bb8 | 7555 | |
24a73b0a | 7556 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7557 | coding->src_chars = chars; |
7558 | coding->src_bytes = bytes; | |
7559 | coding->src_pos = -chars; | |
7560 | coding->src_pos_byte = -bytes; | |
7561 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7562 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7563 | coding->dst_pos = PT; |
7564 | coding->dst_pos_byte = PT_BYTE; | |
5d8ea120 | 7565 | coding->dst_multibyte = ! NILP (B_ (current_buffer, enable_multibyte_characters)); |
4ed46869 | 7566 | |
df7492f9 KH |
7567 | if (CODING_REQUIRE_DETECTION (coding)) |
7568 | detect_coding (coding); | |
8f924df7 | 7569 | |
9286b333 | 7570 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7571 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7572 | decode_coding (coding); |
287c57d7 | 7573 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7574 | |
5e5c78be KH |
7575 | attrs = CODING_ID_ATTRS (coding->id); |
7576 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 7577 | { |
5e5c78be KH |
7578 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
7579 | Lisp_Object val; | |
7580 | ||
7581 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7582 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7583 | make_number (coding->produced_char)); | |
5e5c78be KH |
7584 | CHECK_NATNUM (val); |
7585 | coding->produced_char += Z - prev_Z; | |
7586 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7587 | } |
4ed46869 | 7588 | |
df7492f9 | 7589 | unbind_to (count, Qnil); |
b73bfc1c KH |
7590 | return coding->result; |
7591 | } | |
52d41803 | 7592 | |
4ed46869 | 7593 | int |
cf84bb53 JB |
7594 | encode_coding_gap (struct coding_system *coding, |
7595 | EMACS_INT chars, EMACS_INT bytes) | |
4ed46869 | 7596 | { |
1a4990fb | 7597 | int count = SPECPDL_INDEX (); |
4ed46869 | 7598 | |
24a73b0a | 7599 | code_conversion_save (0, 0); |
4ed46869 | 7600 | |
24a73b0a | 7601 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7602 | coding->src_chars = chars; |
7603 | coding->src_bytes = bytes; | |
7604 | coding->src_pos = -chars; | |
7605 | coding->src_pos_byte = -bytes; | |
7606 | coding->src_multibyte = chars < bytes; | |
7607 | coding->dst_object = coding->src_object; | |
7608 | coding->dst_pos = PT; | |
7609 | coding->dst_pos_byte = PT_BYTE; | |
4ed46869 | 7610 | |
df7492f9 | 7611 | encode_coding (coding); |
b73bfc1c | 7612 | |
df7492f9 KH |
7613 | unbind_to (count, Qnil); |
7614 | return coding->result; | |
7615 | } | |
4ed46869 | 7616 | |
d46c5b12 | 7617 | |
df7492f9 KH |
7618 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7619 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7620 | |
df7492f9 | 7621 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7622 | |
df7492f9 KH |
7623 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7624 | are positions in the buffer. | |
b73bfc1c | 7625 | |
df7492f9 KH |
7626 | If it is a string, the text is at the beginning of the string. |
7627 | FROM and TO are indices to the string. | |
4ed46869 | 7628 | |
df7492f9 KH |
7629 | If it is nil, the text is at coding->source. FROM and TO are |
7630 | indices to coding->source. | |
bb10be8b | 7631 | |
df7492f9 | 7632 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7633 | |
df7492f9 KH |
7634 | If it is a buffer, the decoded text is inserted at point of the |
7635 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7636 | is deleted. | |
4ed46869 | 7637 | |
df7492f9 KH |
7638 | If it is Qt, a string is made from the decoded text, and |
7639 | set in CODING->dst_object. | |
d46c5b12 | 7640 | |
df7492f9 | 7641 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7642 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7643 | CODING->destination by xmalloc. If the decoded text is longer than |
7644 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7645 | */ | |
d46c5b12 | 7646 | |
df7492f9 | 7647 | void |
cf84bb53 JB |
7648 | decode_coding_object (struct coding_system *coding, |
7649 | Lisp_Object src_object, | |
7650 | EMACS_INT from, EMACS_INT from_byte, | |
7651 | EMACS_INT to, EMACS_INT to_byte, | |
7652 | Lisp_Object dst_object) | |
d46c5b12 | 7653 | { |
1a4990fb | 7654 | int count = SPECPDL_INDEX (); |
df7492f9 KH |
7655 | unsigned char *destination; |
7656 | EMACS_INT dst_bytes; | |
7657 | EMACS_INT chars = to - from; | |
7658 | EMACS_INT bytes = to_byte - from_byte; | |
7659 | Lisp_Object attrs; | |
4776e638 | 7660 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7661 | int need_marker_adjustment = 0; |
b3bfad50 | 7662 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7663 | |
b3bfad50 | 7664 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 7665 | |
df7492f9 | 7666 | if (NILP (dst_object)) |
d46c5b12 | 7667 | { |
df7492f9 KH |
7668 | destination = coding->destination; |
7669 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 7670 | } |
93dec019 | 7671 | |
df7492f9 KH |
7672 | coding->src_object = src_object; |
7673 | coding->src_chars = chars; | |
7674 | coding->src_bytes = bytes; | |
7675 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 7676 | |
df7492f9 | 7677 | if (STRINGP (src_object)) |
d46c5b12 | 7678 | { |
df7492f9 KH |
7679 | coding->src_pos = from; |
7680 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7681 | } |
df7492f9 | 7682 | else if (BUFFERP (src_object)) |
88993dfd | 7683 | { |
df7492f9 KH |
7684 | set_buffer_internal (XBUFFER (src_object)); |
7685 | if (from != GPT) | |
7686 | move_gap_both (from, from_byte); | |
7687 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 7688 | { |
64cedb0c KH |
7689 | struct Lisp_Marker *tail; |
7690 | ||
7691 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7692 | { | |
7693 | tail->need_adjustment | |
7694 | = tail->charpos == (tail->insertion_type ? from : to); | |
7695 | need_marker_adjustment |= tail->need_adjustment; | |
7696 | } | |
4776e638 | 7697 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 7698 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 7699 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
7700 | del_range_both (from, from_byte, to, to_byte, 1); |
7701 | coding->src_pos = -chars; | |
7702 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 7703 | } |
df7492f9 | 7704 | else |
fb88bf2d | 7705 | { |
df7492f9 KH |
7706 | coding->src_pos = from; |
7707 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 7708 | } |
88993dfd KH |
7709 | } |
7710 | ||
df7492f9 KH |
7711 | if (CODING_REQUIRE_DETECTION (coding)) |
7712 | detect_coding (coding); | |
7713 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 7714 | |
2cb26057 KH |
7715 | if (EQ (dst_object, Qt) |
7716 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
7717 | && NILP (dst_object))) | |
b73bfc1c | 7718 | { |
a1567c45 SM |
7719 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
7720 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
7721 | coding->dst_pos = BEG; |
7722 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 7723 | } |
df7492f9 | 7724 | else if (BUFFERP (dst_object)) |
d46c5b12 | 7725 | { |
24a73b0a | 7726 | code_conversion_save (0, 0); |
df7492f9 KH |
7727 | coding->dst_object = dst_object; |
7728 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
7729 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
7730 | coding->dst_multibyte | |
5d8ea120 | 7731 | = ! NILP (B_ (XBUFFER (dst_object), enable_multibyte_characters)); |
d46c5b12 KH |
7732 | } |
7733 | else | |
7734 | { | |
24a73b0a | 7735 | code_conversion_save (0, 0); |
df7492f9 | 7736 | coding->dst_object = Qnil; |
0154725e SM |
7737 | /* Most callers presume this will return a multibyte result, and they |
7738 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
7739 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 7740 | coding->dst_multibyte = 1; |
d46c5b12 KH |
7741 | } |
7742 | ||
df7492f9 | 7743 | decode_coding (coding); |
fa46990e | 7744 | |
df7492f9 KH |
7745 | if (BUFFERP (coding->dst_object)) |
7746 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 7747 | |
df7492f9 | 7748 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 7749 | { |
b3bfad50 | 7750 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
df7492f9 | 7751 | EMACS_INT prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 7752 | Lisp_Object val; |
d46c5b12 | 7753 | |
c0cc7f7f | 7754 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
7755 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7756 | old_deactivate_mark); | |
d4850d67 KH |
7757 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
7758 | make_number (coding->produced_char)); | |
df7492f9 KH |
7759 | UNGCPRO; |
7760 | CHECK_NATNUM (val); | |
7761 | coding->produced_char += Z - prev_Z; | |
7762 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 7763 | } |
de79a6a5 | 7764 | |
df7492f9 | 7765 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 7766 | { |
df7492f9 KH |
7767 | coding->dst_object = Fbuffer_string (); |
7768 | } | |
7769 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
7770 | { | |
7771 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7772 | if (dst_bytes < coding->produced) | |
7773 | { | |
b3bfad50 | 7774 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
7775 | if (! destination) |
7776 | { | |
065e3595 | 7777 | record_conversion_result (coding, |
ebaf11b6 | 7778 | CODING_RESULT_INSUFFICIENT_MEM); |
df7492f9 KH |
7779 | unbind_to (count, Qnil); |
7780 | return; | |
7781 | } | |
7782 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
7783 | move_gap_both (BEGV, BEGV_BYTE); | |
72af86bd | 7784 | memcpy (destination, BEGV_ADDR, coding->produced); |
df7492f9 | 7785 | coding->destination = destination; |
d46c5b12 | 7786 | } |
ec6d2bb8 | 7787 | } |
b73bfc1c | 7788 | |
4776e638 KH |
7789 | if (saved_pt >= 0) |
7790 | { | |
7791 | /* This is the case of: | |
7792 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7793 | As we have moved PT while replacing the original buffer | |
7794 | contents, we must recover it now. */ | |
7795 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 7796 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
7797 | if (saved_pt < from) |
7798 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7799 | else if (saved_pt < from + chars) | |
7800 | TEMP_SET_PT_BOTH (from, from_byte); | |
5d8ea120 | 7801 | else if (! NILP (B_ (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
7802 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
7803 | saved_pt_byte + (coding->produced - bytes)); | |
7804 | else | |
7805 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
7806 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7807 | |
7808 | if (need_marker_adjustment) | |
7809 | { | |
7810 | struct Lisp_Marker *tail; | |
7811 | ||
7812 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7813 | if (tail->need_adjustment) | |
7814 | { | |
7815 | tail->need_adjustment = 0; | |
7816 | if (tail->insertion_type) | |
7817 | { | |
7818 | tail->bytepos = from_byte; | |
7819 | tail->charpos = from; | |
7820 | } | |
7821 | else | |
7822 | { | |
7823 | tail->bytepos = from_byte + coding->produced; | |
7824 | tail->charpos | |
5d8ea120 | 7825 | = (NILP (B_ (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
7826 | ? tail->bytepos : from + coding->produced_char); |
7827 | } | |
7828 | } | |
7829 | } | |
d46c5b12 | 7830 | } |
4776e638 | 7831 | |
b3bfad50 | 7832 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 7833 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
7834 | } |
7835 | ||
d46c5b12 | 7836 | |
df7492f9 | 7837 | void |
cf84bb53 JB |
7838 | encode_coding_object (struct coding_system *coding, |
7839 | Lisp_Object src_object, | |
7840 | EMACS_INT from, EMACS_INT from_byte, | |
7841 | EMACS_INT to, EMACS_INT to_byte, | |
7842 | Lisp_Object dst_object) | |
d46c5b12 | 7843 | { |
1a4990fb | 7844 | int count = SPECPDL_INDEX (); |
df7492f9 KH |
7845 | EMACS_INT chars = to - from; |
7846 | EMACS_INT bytes = to_byte - from_byte; | |
7847 | Lisp_Object attrs; | |
4776e638 | 7848 | int saved_pt = -1, saved_pt_byte; |
64cedb0c | 7849 | int need_marker_adjustment = 0; |
c02d943b | 7850 | int kill_src_buffer = 0; |
b3bfad50 | 7851 | Lisp_Object old_deactivate_mark; |
df7492f9 | 7852 | |
b3bfad50 | 7853 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
7854 | |
7855 | coding->src_object = src_object; | |
7856 | coding->src_chars = chars; | |
7857 | coding->src_bytes = bytes; | |
7858 | coding->src_multibyte = chars < bytes; | |
7859 | ||
7860 | attrs = CODING_ID_ATTRS (coding->id); | |
7861 | ||
64cedb0c KH |
7862 | if (EQ (src_object, dst_object)) |
7863 | { | |
7864 | struct Lisp_Marker *tail; | |
7865 | ||
7866 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7867 | { | |
7868 | tail->need_adjustment | |
7869 | = tail->charpos == (tail->insertion_type ? from : to); | |
7870 | need_marker_adjustment |= tail->need_adjustment; | |
7871 | } | |
7872 | } | |
7873 | ||
df7492f9 | 7874 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 7875 | { |
24a73b0a | 7876 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
7877 | set_buffer_internal (XBUFFER (coding->src_object)); |
7878 | if (STRINGP (src_object)) | |
7879 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
7880 | else if (BUFFERP (src_object)) | |
7881 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
7882 | else | |
b68864e5 | 7883 | insert_1_both ((char *) coding->source + from, chars, bytes, 0, 0, 0); |
d46c5b12 | 7884 | |
df7492f9 KH |
7885 | if (EQ (src_object, dst_object)) |
7886 | { | |
7887 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 7888 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
7889 | del_range_both (from, from_byte, to, to_byte, 1); |
7890 | set_buffer_internal (XBUFFER (coding->src_object)); | |
7891 | } | |
7892 | ||
d4850d67 KH |
7893 | { |
7894 | Lisp_Object args[3]; | |
b3bfad50 | 7895 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 7896 | |
b3bfad50 KH |
7897 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7898 | old_deactivate_mark); | |
d4850d67 KH |
7899 | args[0] = CODING_ATTR_PRE_WRITE (attrs); |
7900 | args[1] = make_number (BEG); | |
7901 | args[2] = make_number (Z); | |
7902 | safe_call (3, args); | |
b3bfad50 | 7903 | UNGCPRO; |
d4850d67 | 7904 | } |
c02d943b KH |
7905 | if (XBUFFER (coding->src_object) != current_buffer) |
7906 | kill_src_buffer = 1; | |
ac87bbef | 7907 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7908 | if (BEG != GPT) |
7909 | move_gap_both (BEG, BEG_BYTE); | |
7910 | coding->src_chars = Z - BEG; | |
7911 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
7912 | coding->src_pos = BEG; | |
7913 | coding->src_pos_byte = BEG_BYTE; | |
7914 | coding->src_multibyte = Z < Z_BYTE; | |
7915 | } | |
7916 | else if (STRINGP (src_object)) | |
d46c5b12 | 7917 | { |
24a73b0a | 7918 | code_conversion_save (0, 0); |
df7492f9 KH |
7919 | coding->src_pos = from; |
7920 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 7921 | } |
df7492f9 | 7922 | else if (BUFFERP (src_object)) |
b73bfc1c | 7923 | { |
24a73b0a | 7924 | code_conversion_save (0, 0); |
df7492f9 | 7925 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 7926 | if (EQ (src_object, dst_object)) |
d46c5b12 | 7927 | { |
4776e638 | 7928 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
7929 | coding->src_object = del_range_1 (from, to, 1, 1); |
7930 | coding->src_pos = 0; | |
7931 | coding->src_pos_byte = 0; | |
d46c5b12 | 7932 | } |
df7492f9 | 7933 | else |
d46c5b12 | 7934 | { |
ff0dacd7 KH |
7935 | if (from < GPT && to >= GPT) |
7936 | move_gap_both (from, from_byte); | |
df7492f9 KH |
7937 | coding->src_pos = from; |
7938 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7939 | } |
d46c5b12 | 7940 | } |
4776e638 | 7941 | else |
24a73b0a | 7942 | code_conversion_save (0, 0); |
d46c5b12 | 7943 | |
df7492f9 | 7944 | if (BUFFERP (dst_object)) |
88993dfd | 7945 | { |
df7492f9 | 7946 | coding->dst_object = dst_object; |
28f67a95 KH |
7947 | if (EQ (src_object, dst_object)) |
7948 | { | |
7949 | coding->dst_pos = from; | |
7950 | coding->dst_pos_byte = from_byte; | |
7951 | } | |
7952 | else | |
7953 | { | |
319a3947 KH |
7954 | struct buffer *current = current_buffer; |
7955 | ||
7956 | set_buffer_temp (XBUFFER (dst_object)); | |
7957 | coding->dst_pos = PT; | |
7958 | coding->dst_pos_byte = PT_BYTE; | |
7959 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
7960 | set_buffer_temp (current); | |
28f67a95 | 7961 | } |
df7492f9 | 7962 | coding->dst_multibyte |
5d8ea120 | 7963 | = ! NILP (B_ (XBUFFER (dst_object), enable_multibyte_characters)); |
88993dfd | 7964 | } |
df7492f9 | 7965 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 7966 | { |
df7492f9 | 7967 | coding->dst_object = Qnil; |
df7492f9 | 7968 | coding->dst_bytes = coding->src_chars; |
ac87bbef KH |
7969 | if (coding->dst_bytes == 0) |
7970 | coding->dst_bytes = 1; | |
7971 | coding->destination = (unsigned char *) xmalloc (coding->dst_bytes); | |
df7492f9 | 7972 | coding->dst_multibyte = 0; |
d46c5b12 KH |
7973 | } |
7974 | else | |
7975 | { | |
df7492f9 KH |
7976 | coding->dst_object = Qnil; |
7977 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
7978 | } |
7979 | ||
df7492f9 | 7980 | encode_coding (coding); |
d46c5b12 | 7981 | |
df7492f9 | 7982 | if (EQ (dst_object, Qt)) |
d46c5b12 | 7983 | { |
df7492f9 KH |
7984 | if (BUFFERP (coding->dst_object)) |
7985 | coding->dst_object = Fbuffer_string (); | |
7986 | else | |
d46c5b12 | 7987 | { |
df7492f9 KH |
7988 | coding->dst_object |
7989 | = make_unibyte_string ((char *) coding->destination, | |
7990 | coding->produced); | |
7991 | xfree (coding->destination); | |
d46c5b12 | 7992 | } |
4ed46869 | 7993 | } |
d46c5b12 | 7994 | |
4776e638 KH |
7995 | if (saved_pt >= 0) |
7996 | { | |
7997 | /* This is the case of: | |
7998 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7999 | As we have moved PT while replacing the original buffer | |
8000 | contents, we must recover it now. */ | |
8001 | set_buffer_internal (XBUFFER (src_object)); | |
8002 | if (saved_pt < from) | |
8003 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
8004 | else if (saved_pt < from + chars) | |
8005 | TEMP_SET_PT_BOTH (from, from_byte); | |
5d8ea120 | 8006 | else if (! NILP (B_ (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
8007 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
8008 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 8009 | else |
4776e638 KH |
8010 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
8011 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
8012 | |
8013 | if (need_marker_adjustment) | |
8014 | { | |
8015 | struct Lisp_Marker *tail; | |
8016 | ||
8017 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
8018 | if (tail->need_adjustment) | |
8019 | { | |
8020 | tail->need_adjustment = 0; | |
8021 | if (tail->insertion_type) | |
8022 | { | |
8023 | tail->bytepos = from_byte; | |
8024 | tail->charpos = from; | |
8025 | } | |
8026 | else | |
8027 | { | |
8028 | tail->bytepos = from_byte + coding->produced; | |
8029 | tail->charpos | |
5d8ea120 | 8030 | = (NILP (B_ (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
8031 | ? tail->bytepos : from + coding->produced_char); |
8032 | } | |
8033 | } | |
8034 | } | |
4776e638 KH |
8035 | } |
8036 | ||
c02d943b KH |
8037 | if (kill_src_buffer) |
8038 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
8039 | |
8040 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 8041 | unbind_to (count, Qnil); |
b73bfc1c KH |
8042 | } |
8043 | ||
df7492f9 | 8044 | |
b73bfc1c | 8045 | Lisp_Object |
971de7fb | 8046 | preferred_coding_system (void) |
b73bfc1c | 8047 | { |
df7492f9 | 8048 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 8049 | |
df7492f9 | 8050 | return CODING_ID_NAME (id); |
4ed46869 KH |
8051 | } |
8052 | ||
8053 | \f | |
8054 | #ifdef emacs | |
1397dc18 | 8055 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 8056 | |
4ed46869 | 8057 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 8058 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 8059 | See the documentation of `define-coding-system' for information |
48b0f3ae | 8060 | about coding-system objects. */) |
5842a27b | 8061 | (Lisp_Object object) |
4ed46869 | 8062 | { |
d4a1d553 JB |
8063 | if (NILP (object) |
8064 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 8065 | return Qt; |
d4a1d553 JB |
8066 | if (! SYMBOLP (object) |
8067 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
8068 | return Qnil; |
8069 | return Qt; | |
4ed46869 KH |
8070 | } |
8071 | ||
9d991de8 RS |
8072 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
8073 | Sread_non_nil_coding_system, 1, 1, 0, | |
48b0f3ae | 8074 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
5842a27b | 8075 | (Lisp_Object prompt) |
4ed46869 | 8076 | { |
e0e989f6 | 8077 | Lisp_Object val; |
9d991de8 RS |
8078 | do |
8079 | { | |
4608c386 KH |
8080 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
8081 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 8082 | } |
8f924df7 | 8083 | while (SCHARS (val) == 0); |
e0e989f6 | 8084 | return (Fintern (val, Qnil)); |
4ed46869 KH |
8085 | } |
8086 | ||
9b787f3e | 8087 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 8088 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
8089 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
8090 | Ignores case when completing coding systems (all Emacs coding systems | |
8091 | are lower-case). */) | |
5842a27b | 8092 | (Lisp_Object prompt, Lisp_Object default_coding_system) |
4ed46869 | 8093 | { |
f44d27ce | 8094 | Lisp_Object val; |
c7183fb8 GM |
8095 | int count = SPECPDL_INDEX (); |
8096 | ||
9b787f3e | 8097 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 8098 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 8099 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 8100 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
8101 | Qt, Qnil, Qcoding_system_history, |
8102 | default_coding_system, Qnil); | |
c7183fb8 | 8103 | unbind_to (count, Qnil); |
8f924df7 | 8104 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
8105 | } |
8106 | ||
8107 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, | |
8108 | 1, 1, 0, | |
48b0f3ae | 8109 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
8110 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
8111 | It is valid if it is nil or a symbol defined as a coding system by the | |
8112 | function `define-coding-system'. */) | |
5842a27b | 8113 | (Lisp_Object coding_system) |
4ed46869 | 8114 | { |
44e8490d KH |
8115 | Lisp_Object define_form; |
8116 | ||
8117 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
8118 | if (! NILP (define_form)) | |
8119 | { | |
8120 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
8121 | safe_eval (define_form); | |
8122 | } | |
4ed46869 KH |
8123 | if (!NILP (Fcoding_system_p (coding_system))) |
8124 | return coding_system; | |
fcad4ec4 | 8125 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 8126 | } |
df7492f9 | 8127 | |
3a73fa5d | 8128 | \f |
89528eb3 KH |
8129 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
8130 | HIGHEST is nonzero, return the coding system of the highest | |
ad1746f5 | 8131 | priority among the detected coding systems. Otherwise return a |
89528eb3 KH |
8132 | list of detected coding systems sorted by their priorities. If |
8133 | MULTIBYTEP is nonzero, it is assumed that the bytes are in correct | |
8134 | multibyte form but contains only ASCII and eight-bit chars. | |
8135 | Otherwise, the bytes are raw bytes. | |
8136 | ||
8137 | CODING-SYSTEM controls the detection as below: | |
8138 | ||
8139 | If it is nil, detect both text-format and eol-format. If the | |
8140 | text-format part of CODING-SYSTEM is already specified | |
8141 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
8142 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
8143 | detect only text-format. */ | |
8144 | ||
d46c5b12 | 8145 | Lisp_Object |
cf84bb53 JB |
8146 | detect_coding_system (const unsigned char *src, |
8147 | EMACS_INT src_chars, EMACS_INT src_bytes, | |
8148 | int highest, int multibytep, | |
8149 | Lisp_Object coding_system) | |
4ed46869 | 8150 | { |
8f924df7 | 8151 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 8152 | Lisp_Object attrs, eol_type; |
4533845d | 8153 | Lisp_Object val = Qnil; |
df7492f9 | 8154 | struct coding_system coding; |
89528eb3 | 8155 | int id; |
ff0dacd7 | 8156 | struct coding_detection_info detect_info; |
24a73b0a | 8157 | enum coding_category base_category; |
2f3cbb32 | 8158 | int null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 8159 | |
df7492f9 KH |
8160 | if (NILP (coding_system)) |
8161 | coding_system = Qundecided; | |
8162 | setup_coding_system (coding_system, &coding); | |
8163 | attrs = CODING_ID_ATTRS (coding.id); | |
8164 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 8165 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 8166 | |
df7492f9 | 8167 | coding.source = src; |
24a73b0a | 8168 | coding.src_chars = src_chars; |
df7492f9 KH |
8169 | coding.src_bytes = src_bytes; |
8170 | coding.src_multibyte = multibytep; | |
8171 | coding.consumed = 0; | |
89528eb3 | 8172 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 8173 | coding.head_ascii = 0; |
d46c5b12 | 8174 | |
ff0dacd7 | 8175 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 8176 | |
89528eb3 | 8177 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
8178 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
8179 | if (base_category == coding_category_undecided) | |
4ed46869 | 8180 | { |
ff0dacd7 KH |
8181 | enum coding_category category; |
8182 | struct coding_system *this; | |
8183 | int c, i; | |
88993dfd | 8184 | |
24a73b0a | 8185 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 8186 | for (; src < src_end; src++) |
4ed46869 | 8187 | { |
df7492f9 | 8188 | c = *src; |
6cb21a4f | 8189 | if (c & 0x80) |
6cb21a4f | 8190 | { |
2f3cbb32 | 8191 | eight_bit_found = 1; |
2f3cbb32 KH |
8192 | if (null_byte_found) |
8193 | break; | |
8194 | } | |
c0e16b14 | 8195 | else if (c < 0x20) |
2f3cbb32 KH |
8196 | { |
8197 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
8198 | && ! inhibit_iso_escape_detection | |
8199 | && ! detect_info.checked) | |
6cb21a4f | 8200 | { |
2f3cbb32 KH |
8201 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
8202 | { | |
8203 | /* We have scanned the whole data. */ | |
8204 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
8205 | { |
8206 | /* We didn't find an 8-bit code. We may | |
8207 | have found a null-byte, but it's very | |
8208 | rare that a binary file confirm to | |
8209 | ISO-2022. */ | |
8210 | src = src_end; | |
8211 | coding.head_ascii = src - coding.source; | |
8212 | } | |
8213 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
8214 | break; |
8215 | } | |
8216 | } | |
97b1b294 | 8217 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
8218 | { |
8219 | null_byte_found = 1; | |
8220 | if (eight_bit_found) | |
8221 | break; | |
6cb21a4f | 8222 | } |
c006c0c8 KH |
8223 | if (! eight_bit_found) |
8224 | coding.head_ascii++; | |
6cb21a4f | 8225 | } |
c006c0c8 | 8226 | else if (! eight_bit_found) |
c0e16b14 | 8227 | coding.head_ascii++; |
4ed46869 | 8228 | } |
88993dfd | 8229 | |
2f3cbb32 KH |
8230 | if (null_byte_found || eight_bit_found |
8231 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
8232 | || detect_info.found) |
8233 | { | |
2f3cbb32 | 8234 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
8235 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
8236 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 8237 | { |
6cb21a4f | 8238 | category = coding_priorities[i]; |
c7266f4a | 8239 | this = coding_categories + category; |
6cb21a4f | 8240 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
8241 | break; |
8242 | } | |
6cb21a4f | 8243 | else |
2f3cbb32 KH |
8244 | { |
8245 | if (null_byte_found) | |
8246 | { | |
8247 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
8248 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
8249 | } | |
8250 | for (i = 0; i < coding_category_raw_text; i++) | |
8251 | { | |
8252 | category = coding_priorities[i]; | |
8253 | this = coding_categories + category; | |
6cb21a4f | 8254 | |
2f3cbb32 KH |
8255 | if (this->id < 0) |
8256 | { | |
8257 | /* No coding system of this category is defined. */ | |
8258 | detect_info.rejected |= (1 << category); | |
8259 | } | |
8260 | else if (category >= coding_category_raw_text) | |
8261 | continue; | |
8262 | else if (detect_info.checked & (1 << category)) | |
8263 | { | |
8264 | if (highest | |
8265 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 8266 | break; |
2f3cbb32 KH |
8267 | } |
8268 | else if ((*(this->detector)) (&coding, &detect_info) | |
8269 | && highest | |
8270 | && (detect_info.found & (1 << category))) | |
8271 | { | |
8272 | if (category == coding_category_utf_16_auto) | |
8273 | { | |
8274 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8275 | category = coding_category_utf_16_le; | |
8276 | else | |
8277 | category = coding_category_utf_16_be; | |
8278 | } | |
8279 | break; | |
8280 | } | |
8281 | } | |
8282 | } | |
6cb21a4f | 8283 | } |
ec6d2bb8 | 8284 | |
4cddb209 KH |
8285 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
8286 | || null_byte_found) | |
ec6d2bb8 | 8287 | { |
ff0dacd7 | 8288 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 8289 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
8290 | val = Fcons (make_number (id), Qnil); |
8291 | } | |
ff0dacd7 | 8292 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 8293 | { |
ff0dacd7 | 8294 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
8295 | id = coding_categories[coding_category_undecided].id; |
8296 | val = Fcons (make_number (id), Qnil); | |
8297 | } | |
8298 | else if (highest) | |
8299 | { | |
ff0dacd7 | 8300 | if (detect_info.found) |
ec6d2bb8 | 8301 | { |
ff0dacd7 KH |
8302 | detect_info.found = 1 << category; |
8303 | val = Fcons (make_number (this->id), Qnil); | |
8304 | } | |
8305 | else | |
8306 | for (i = 0; i < coding_category_raw_text; i++) | |
8307 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
8308 | { | |
8309 | detect_info.found = 1 << coding_priorities[i]; | |
8310 | id = coding_categories[coding_priorities[i]].id; | |
8311 | val = Fcons (make_number (id), Qnil); | |
8312 | break; | |
8313 | } | |
8314 | } | |
89528eb3 KH |
8315 | else |
8316 | { | |
ff0dacd7 KH |
8317 | int mask = detect_info.rejected | detect_info.found; |
8318 | int found = 0; | |
ec6d2bb8 | 8319 | |
89528eb3 | 8320 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
8321 | { |
8322 | category = coding_priorities[i]; | |
8323 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 8324 | { |
ff0dacd7 KH |
8325 | found |= 1 << category; |
8326 | id = coding_categories[category].id; | |
c7266f4a KH |
8327 | if (id >= 0) |
8328 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
8329 | } |
8330 | } | |
8331 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
8332 | { | |
8333 | category = coding_priorities[i]; | |
8334 | if (detect_info.found & (1 << category)) | |
8335 | { | |
8336 | id = coding_categories[category].id; | |
8337 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 8338 | } |
ec6d2bb8 | 8339 | } |
ff0dacd7 | 8340 | detect_info.found |= found; |
ec6d2bb8 | 8341 | } |
ec6d2bb8 | 8342 | } |
a470d443 KH |
8343 | else if (base_category == coding_category_utf_8_auto) |
8344 | { | |
8345 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
8346 | { | |
8347 | struct coding_system *this; | |
8348 | ||
8349 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
8350 | this = coding_categories + coding_category_utf_8_sig; | |
8351 | else | |
8352 | this = coding_categories + coding_category_utf_8_nosig; | |
8353 | val = Fcons (make_number (this->id), Qnil); | |
8354 | } | |
8355 | } | |
24a73b0a KH |
8356 | else if (base_category == coding_category_utf_16_auto) |
8357 | { | |
8358 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
8359 | { | |
24a73b0a KH |
8360 | struct coding_system *this; |
8361 | ||
8362 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8363 | this = coding_categories + coding_category_utf_16_le; | |
8364 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
8365 | this = coding_categories + coding_category_utf_16_be; | |
8366 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
8367 | this = coding_categories + coding_category_utf_16_be_nosig; | |
8368 | else | |
8369 | this = coding_categories + coding_category_utf_16_le_nosig; | |
8370 | val = Fcons (make_number (this->id), Qnil); | |
8371 | } | |
8372 | } | |
df7492f9 KH |
8373 | else |
8374 | { | |
ff0dacd7 | 8375 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 8376 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8377 | } |
df7492f9 | 8378 | |
89528eb3 | 8379 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8380 | { |
4533845d | 8381 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8382 | Lisp_Object tail; |
8383 | ||
89528eb3 KH |
8384 | if (VECTORP (eol_type)) |
8385 | { | |
ff0dacd7 | 8386 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8387 | { |
8388 | if (null_byte_found) | |
8389 | normal_eol = EOL_SEEN_LF; | |
8390 | else | |
8391 | normal_eol = detect_eol (coding.source, src_bytes, | |
8392 | coding_category_raw_text); | |
8393 | } | |
ff0dacd7 KH |
8394 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8395 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8396 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8397 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8398 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8399 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8400 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8401 | coding_category_utf_16_le); | |
8402 | } | |
8403 | else | |
8404 | { | |
8405 | if (EQ (eol_type, Qunix)) | |
8406 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8407 | else if (EQ (eol_type, Qdos)) | |
8408 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8409 | else | |
8410 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8411 | } | |
8412 | ||
df7492f9 KH |
8413 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8414 | { | |
89528eb3 | 8415 | enum coding_category category; |
df7492f9 | 8416 | int this_eol; |
89528eb3 KH |
8417 | |
8418 | id = XINT (XCAR (tail)); | |
8419 | attrs = CODING_ID_ATTRS (id); | |
8420 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8421 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8422 | if (VECTORP (eol_type)) |
8423 | { | |
89528eb3 KH |
8424 | if (category == coding_category_utf_16_be |
8425 | || category == coding_category_utf_16_be_nosig) | |
8426 | this_eol = utf_16_be_eol; | |
8427 | else if (category == coding_category_utf_16_le | |
8428 | || category == coding_category_utf_16_le_nosig) | |
8429 | this_eol = utf_16_le_eol; | |
df7492f9 | 8430 | else |
89528eb3 KH |
8431 | this_eol = normal_eol; |
8432 | ||
df7492f9 KH |
8433 | if (this_eol == EOL_SEEN_LF) |
8434 | XSETCAR (tail, AREF (eol_type, 0)); | |
8435 | else if (this_eol == EOL_SEEN_CRLF) | |
8436 | XSETCAR (tail, AREF (eol_type, 1)); | |
8437 | else if (this_eol == EOL_SEEN_CR) | |
8438 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8439 | else |
8440 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8441 | } |
89528eb3 KH |
8442 | else |
8443 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8444 | } |
8445 | } | |
ec6d2bb8 | 8446 | |
4533845d | 8447 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8448 | } |
8449 | ||
ec6d2bb8 | 8450 | |
d46c5b12 KH |
8451 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8452 | 2, 3, 0, | |
48b0f3ae PJ |
8453 | doc: /* Detect coding system of the text in the region between START and END. |
8454 | Return a list of possible coding systems ordered by priority. | |
b811c52b KH |
8455 | The coding systems to try and their priorities follows what |
8456 | the function `coding-system-priority-list' (which see) returns. | |
ec6d2bb8 | 8457 | |
12e0131a | 8458 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8459 | characters as ESC), it returns a list of single element `undecided' |
8460 | or its subsidiary coding system according to a detected end-of-line | |
8461 | format. | |
ec6d2bb8 | 8462 | |
48b0f3ae PJ |
8463 | If optional argument HIGHEST is non-nil, return the coding system of |
8464 | highest priority. */) | |
5842a27b | 8465 | (Lisp_Object start, Lisp_Object end, Lisp_Object highest) |
d46c5b12 KH |
8466 | { |
8467 | int from, to; | |
8468 | int from_byte, to_byte; | |
ec6d2bb8 | 8469 | |
b7826503 PJ |
8470 | CHECK_NUMBER_COERCE_MARKER (start); |
8471 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 8472 | |
d46c5b12 KH |
8473 | validate_region (&start, &end); |
8474 | from = XINT (start), to = XINT (end); | |
8475 | from_byte = CHAR_TO_BYTE (from); | |
8476 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8477 | |
d46c5b12 KH |
8478 | if (from < GPT && to >= GPT) |
8479 | move_gap_both (to, to_byte); | |
c210f766 | 8480 | |
d46c5b12 | 8481 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8482 | to - from, to_byte - from_byte, |
0a28aafb | 8483 | !NILP (highest), |
5d8ea120 TT |
8484 | !NILP (B_ (current_buffer |
8485 | , enable_multibyte_characters)), | |
df7492f9 | 8486 | Qnil); |
ec6d2bb8 KH |
8487 | } |
8488 | ||
d46c5b12 KH |
8489 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8490 | 1, 2, 0, | |
48b0f3ae PJ |
8491 | doc: /* Detect coding system of the text in STRING. |
8492 | Return a list of possible coding systems ordered by priority. | |
67ceab9d KH |
8493 | The coding systems to try and their priorities follows what |
8494 | the function `coding-system-priority-list' (which see) returns. | |
fb88bf2d | 8495 | |
12e0131a | 8496 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8497 | characters as ESC), it returns a list of single element `undecided' |
8498 | or its subsidiary coding system according to a detected end-of-line | |
8499 | format. | |
d46c5b12 | 8500 | |
48b0f3ae PJ |
8501 | If optional argument HIGHEST is non-nil, return the coding system of |
8502 | highest priority. */) | |
5842a27b | 8503 | (Lisp_Object string, Lisp_Object highest) |
d46c5b12 | 8504 | { |
b7826503 | 8505 | CHECK_STRING (string); |
b73bfc1c | 8506 | |
24a73b0a KH |
8507 | return detect_coding_system (SDATA (string), |
8508 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8509 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8510 | Qnil); |
4ed46869 | 8511 | } |
4ed46869 | 8512 | |
b73bfc1c | 8513 | |
df7492f9 | 8514 | static INLINE int |
971de7fb | 8515 | char_encodable_p (int c, Lisp_Object attrs) |
05e6f5dc | 8516 | { |
df7492f9 | 8517 | Lisp_Object tail; |
df7492f9 | 8518 | struct charset *charset; |
7d64c6ad | 8519 | Lisp_Object translation_table; |
d46c5b12 | 8520 | |
7d64c6ad | 8521 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8522 | if (! NILP (translation_table)) |
7d64c6ad | 8523 | c = translate_char (translation_table, c); |
df7492f9 KH |
8524 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8525 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8526 | { |
df7492f9 KH |
8527 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8528 | if (CHAR_CHARSET_P (c, charset)) | |
8529 | break; | |
e133c8fa | 8530 | } |
df7492f9 | 8531 | return (! NILP (tail)); |
05e6f5dc | 8532 | } |
83fa074f | 8533 | |
fb88bf2d | 8534 | |
df7492f9 KH |
8535 | /* Return a list of coding systems that safely encode the text between |
8536 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8537 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8538 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8539 | unibyte, return t. */ |
e077cc80 | 8540 | |
df7492f9 KH |
8541 | DEFUN ("find-coding-systems-region-internal", |
8542 | Ffind_coding_systems_region_internal, | |
8543 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8544 | doc: /* Internal use only. */) | |
5842a27b | 8545 | (Lisp_Object start, Lisp_Object end, Lisp_Object exclude) |
df7492f9 KH |
8546 | { |
8547 | Lisp_Object coding_attrs_list, safe_codings; | |
8548 | EMACS_INT start_byte, end_byte; | |
7c78e542 | 8549 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8550 | int c; |
0e727afa | 8551 | Lisp_Object tail, elt, work_table; |
d46c5b12 | 8552 | |
df7492f9 KH |
8553 | if (STRINGP (start)) |
8554 | { | |
8555 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8556 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8557 | return Qt; |
8558 | start_byte = 0; | |
8f924df7 | 8559 | end_byte = SBYTES (start); |
df7492f9 KH |
8560 | } |
8561 | else | |
d46c5b12 | 8562 | { |
df7492f9 KH |
8563 | CHECK_NUMBER_COERCE_MARKER (start); |
8564 | CHECK_NUMBER_COERCE_MARKER (end); | |
8565 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8566 | args_out_of_range (start, end); | |
5d8ea120 | 8567 | if (NILP (B_ (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8568 | return Qt; |
8569 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8570 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8571 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8572 | return Qt; | |
d46c5b12 | 8573 | |
e1c23804 | 8574 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8575 | { |
e1c23804 DL |
8576 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8577 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8578 | else |
e1c23804 | 8579 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8580 | } |
8581 | } | |
8582 | ||
df7492f9 KH |
8583 | coding_attrs_list = Qnil; |
8584 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8585 | if (NILP (exclude) | |
8586 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8587 | { | |
8588 | Lisp_Object attrs; | |
d46c5b12 | 8589 | |
df7492f9 KH |
8590 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
8591 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
8592 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
8593 | { |
8594 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8595 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8596 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8597 | } | |
df7492f9 | 8598 | } |
d46c5b12 | 8599 | |
df7492f9 | 8600 | if (STRINGP (start)) |
8f924df7 | 8601 | p = pbeg = SDATA (start); |
df7492f9 KH |
8602 | else |
8603 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8604 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8605 | |
df7492f9 KH |
8606 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8607 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8608 | |
0e727afa | 8609 | work_table = Fmake_char_table (Qnil, Qnil); |
05e6f5dc | 8610 | while (p < pend) |
72d1a715 | 8611 | { |
df7492f9 KH |
8612 | if (ASCII_BYTE_P (*p)) |
8613 | p++; | |
72d1a715 RS |
8614 | else |
8615 | { | |
df7492f9 | 8616 | c = STRING_CHAR_ADVANCE (p); |
0e727afa YM |
8617 | if (!NILP (char_table_ref (work_table, c))) |
8618 | /* This character was already checked. Ignore it. */ | |
8619 | continue; | |
12410ef1 | 8620 | |
df7492f9 KH |
8621 | charset_map_loaded = 0; |
8622 | for (tail = coding_attrs_list; CONSP (tail);) | |
8623 | { | |
8624 | elt = XCAR (tail); | |
8625 | if (NILP (elt)) | |
8626 | tail = XCDR (tail); | |
8627 | else if (char_encodable_p (c, elt)) | |
8628 | tail = XCDR (tail); | |
8629 | else if (CONSP (XCDR (tail))) | |
8630 | { | |
8631 | XSETCAR (tail, XCAR (XCDR (tail))); | |
8632 | XSETCDR (tail, XCDR (XCDR (tail))); | |
8633 | } | |
8634 | else | |
8635 | { | |
8636 | XSETCAR (tail, Qnil); | |
8637 | tail = XCDR (tail); | |
8638 | } | |
8639 | } | |
8640 | if (charset_map_loaded) | |
8641 | { | |
8642 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
05e6f5dc | 8643 | |
df7492f9 | 8644 | if (STRINGP (start)) |
8f924df7 | 8645 | pbeg = SDATA (start); |
df7492f9 KH |
8646 | else |
8647 | pbeg = BYTE_POS_ADDR (start_byte); | |
8648 | p = pbeg + p_offset; | |
8649 | pend = pbeg + pend_offset; | |
8650 | } | |
0e727afa | 8651 | char_table_set (work_table, c, Qt); |
df7492f9 | 8652 | } |
ec6d2bb8 | 8653 | } |
fb88bf2d | 8654 | |
988b3759 | 8655 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
8656 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
8657 | if (! NILP (XCAR (tail))) | |
8658 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 8659 | |
05e6f5dc KH |
8660 | return safe_codings; |
8661 | } | |
4956c225 | 8662 | |
d46c5b12 | 8663 | |
8f924df7 KH |
8664 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
8665 | Sunencodable_char_position, 3, 5, 0, | |
8666 | doc: /* | |
8667 | Return position of first un-encodable character in a region. | |
d4a1d553 | 8668 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 8669 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 8670 | |
8f924df7 KH |
8671 | If optional 4th argument COUNT is non-nil, it specifies at most how |
8672 | many un-encodable characters to search. In this case, the value is a | |
8673 | list of positions. | |
d46c5b12 | 8674 | |
8f924df7 KH |
8675 | If optional 5th argument STRING is non-nil, it is a string to search |
8676 | for un-encodable characters. In that case, START and END are indexes | |
8677 | to the string. */) | |
5842a27b | 8678 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object count, Lisp_Object string) |
8f924df7 KH |
8679 | { |
8680 | int n; | |
8681 | struct coding_system coding; | |
7d64c6ad | 8682 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 KH |
8683 | Lisp_Object positions; |
8684 | int from, to; | |
8685 | const unsigned char *p, *stop, *pend; | |
8686 | int ascii_compatible; | |
fb88bf2d | 8687 | |
8f924df7 KH |
8688 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
8689 | attrs = CODING_ID_ATTRS (coding.id); | |
8690 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
8691 | return Qnil; | |
8692 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
8693 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 8694 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 8695 | |
8f924df7 KH |
8696 | if (NILP (string)) |
8697 | { | |
8698 | validate_region (&start, &end); | |
8699 | from = XINT (start); | |
8700 | to = XINT (end); | |
5d8ea120 | 8701 | if (NILP (B_ (current_buffer, enable_multibyte_characters)) |
8f924df7 KH |
8702 | || (ascii_compatible |
8703 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
8704 | return Qnil; | |
8705 | p = CHAR_POS_ADDR (from); | |
8706 | pend = CHAR_POS_ADDR (to); | |
8707 | if (from < GPT && to >= GPT) | |
8708 | stop = GPT_ADDR; | |
8709 | else | |
8710 | stop = pend; | |
8711 | } | |
8712 | else | |
8713 | { | |
8714 | CHECK_STRING (string); | |
8715 | CHECK_NATNUM (start); | |
8716 | CHECK_NATNUM (end); | |
8717 | from = XINT (start); | |
8718 | to = XINT (end); | |
8719 | if (from > to | |
8720 | || to > SCHARS (string)) | |
8721 | args_out_of_range_3 (string, start, end); | |
8722 | if (! STRING_MULTIBYTE (string)) | |
8723 | return Qnil; | |
8724 | p = SDATA (string) + string_char_to_byte (string, from); | |
8725 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
8726 | if (ascii_compatible && (to - from) == (pend - p)) | |
8727 | return Qnil; | |
8728 | } | |
f2558efd | 8729 | |
8f924df7 KH |
8730 | if (NILP (count)) |
8731 | n = 1; | |
8732 | else | |
b73bfc1c | 8733 | { |
8f924df7 KH |
8734 | CHECK_NATNUM (count); |
8735 | n = XINT (count); | |
b73bfc1c KH |
8736 | } |
8737 | ||
8f924df7 KH |
8738 | positions = Qnil; |
8739 | while (1) | |
d46c5b12 | 8740 | { |
8f924df7 | 8741 | int c; |
ec6d2bb8 | 8742 | |
8f924df7 KH |
8743 | if (ascii_compatible) |
8744 | while (p < stop && ASCII_BYTE_P (*p)) | |
8745 | p++, from++; | |
8746 | if (p >= stop) | |
0e79d667 | 8747 | { |
8f924df7 KH |
8748 | if (p >= pend) |
8749 | break; | |
8750 | stop = pend; | |
8751 | p = GAP_END_ADDR; | |
0e79d667 | 8752 | } |
ec6d2bb8 | 8753 | |
8f924df7 KH |
8754 | c = STRING_CHAR_ADVANCE (p); |
8755 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
8756 | && ! char_charset (translate_char (translation_table, c), |
8757 | charset_list, NULL)) | |
ec6d2bb8 | 8758 | { |
8f924df7 KH |
8759 | positions = Fcons (make_number (from), positions); |
8760 | n--; | |
8761 | if (n == 0) | |
8762 | break; | |
ec6d2bb8 KH |
8763 | } |
8764 | ||
8f924df7 KH |
8765 | from++; |
8766 | } | |
d46c5b12 | 8767 | |
8f924df7 KH |
8768 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
8769 | } | |
d46c5b12 | 8770 | |
d46c5b12 | 8771 | |
df7492f9 KH |
8772 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
8773 | Scheck_coding_systems_region, 3, 3, 0, | |
8774 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 8775 | |
df7492f9 KH |
8776 | START and END are buffer positions specifying the region. |
8777 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 8778 | |
df7492f9 | 8779 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 8780 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
8781 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
8782 | characters are found. | |
93dec019 | 8783 | |
df7492f9 KH |
8784 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
8785 | value is nil. | |
93dec019 | 8786 | |
df7492f9 KH |
8787 | START may be a string. In that case, check if the string is |
8788 | encodable, and the value contains indices to the string instead of | |
5704f39a KH |
8789 | buffer positions. END is ignored. |
8790 | ||
4c1958f4 | 8791 | If the current buffer (or START if it is a string) is unibyte, the value |
5704f39a | 8792 | is nil. */) |
5842a27b | 8793 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system_list) |
05e6f5dc | 8794 | { |
df7492f9 KH |
8795 | Lisp_Object list; |
8796 | EMACS_INT start_byte, end_byte; | |
8797 | int pos; | |
7c78e542 | 8798 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8799 | int c; |
7d64c6ad | 8800 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 8801 | |
05e6f5dc KH |
8802 | if (STRINGP (start)) |
8803 | { | |
df7492f9 | 8804 | if (!STRING_MULTIBYTE (start) |
4c1958f4 | 8805 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8806 | return Qnil; |
8807 | start_byte = 0; | |
8f924df7 | 8808 | end_byte = SBYTES (start); |
df7492f9 | 8809 | pos = 0; |
d46c5b12 | 8810 | } |
05e6f5dc | 8811 | else |
b73bfc1c | 8812 | { |
b7826503 PJ |
8813 | CHECK_NUMBER_COERCE_MARKER (start); |
8814 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
8815 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
8816 | args_out_of_range (start, end); | |
5d8ea120 | 8817 | if (NILP (B_ (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8818 | return Qnil; |
8819 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8820 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8821 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
5704f39a | 8822 | return Qnil; |
df7492f9 | 8823 | |
e1c23804 | 8824 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 8825 | { |
e1c23804 DL |
8826 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8827 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8828 | else |
e1c23804 | 8829 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 8830 | } |
e1c23804 | 8831 | pos = XINT (start); |
b73bfc1c | 8832 | } |
7553d0e1 | 8833 | |
df7492f9 KH |
8834 | list = Qnil; |
8835 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 8836 | { |
df7492f9 | 8837 | elt = XCAR (tail); |
7d64c6ad | 8838 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
8839 | ASET (attrs, coding_attr_trans_tbl, |
8840 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 8841 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
8842 | } |
8843 | ||
df7492f9 | 8844 | if (STRINGP (start)) |
8f924df7 | 8845 | p = pbeg = SDATA (start); |
72d1a715 | 8846 | else |
df7492f9 KH |
8847 | p = pbeg = BYTE_POS_ADDR (start_byte); |
8848 | pend = p + (end_byte - start_byte); | |
4ed46869 | 8849 | |
df7492f9 KH |
8850 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
8851 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 8852 | |
df7492f9 | 8853 | while (p < pend) |
d46c5b12 | 8854 | { |
df7492f9 KH |
8855 | if (ASCII_BYTE_P (*p)) |
8856 | p++; | |
e133c8fa | 8857 | else |
05e6f5dc | 8858 | { |
df7492f9 KH |
8859 | c = STRING_CHAR_ADVANCE (p); |
8860 | ||
8861 | charset_map_loaded = 0; | |
8862 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
8863 | { | |
8864 | elt = XCDR (XCAR (tail)); | |
8865 | if (! char_encodable_p (c, XCAR (elt))) | |
8866 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
8867 | } | |
8868 | if (charset_map_loaded) | |
8869 | { | |
8870 | EMACS_INT p_offset = p - pbeg, pend_offset = pend - pbeg; | |
8871 | ||
8872 | if (STRINGP (start)) | |
8f924df7 | 8873 | pbeg = SDATA (start); |
df7492f9 KH |
8874 | else |
8875 | pbeg = BYTE_POS_ADDR (start_byte); | |
8876 | p = pbeg + p_offset; | |
8877 | pend = pbeg + pend_offset; | |
8878 | } | |
05e6f5dc | 8879 | } |
df7492f9 | 8880 | pos++; |
d46c5b12 | 8881 | } |
4ed46869 | 8882 | |
df7492f9 KH |
8883 | tail = list; |
8884 | list = Qnil; | |
8885 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 8886 | { |
df7492f9 KH |
8887 | elt = XCAR (tail); |
8888 | if (CONSP (XCDR (XCDR (elt)))) | |
8889 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
8890 | list); | |
ec6d2bb8 | 8891 | } |
2b4f9037 | 8892 | |
df7492f9 | 8893 | return list; |
d46c5b12 KH |
8894 | } |
8895 | ||
3fd9494b | 8896 | |
b73bfc1c | 8897 | Lisp_Object |
cf84bb53 JB |
8898 | code_convert_region (Lisp_Object start, Lisp_Object end, |
8899 | Lisp_Object coding_system, Lisp_Object dst_object, | |
8900 | int encodep, int norecord) | |
4ed46869 | 8901 | { |
3a73fa5d | 8902 | struct coding_system coding; |
df7492f9 KH |
8903 | EMACS_INT from, from_byte, to, to_byte; |
8904 | Lisp_Object src_object; | |
4ed46869 | 8905 | |
b7826503 PJ |
8906 | CHECK_NUMBER_COERCE_MARKER (start); |
8907 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
8908 | if (NILP (coding_system)) |
8909 | coding_system = Qno_conversion; | |
8910 | else | |
8911 | CHECK_CODING_SYSTEM (coding_system); | |
8912 | src_object = Fcurrent_buffer (); | |
8913 | if (NILP (dst_object)) | |
8914 | dst_object = src_object; | |
8915 | else if (! EQ (dst_object, Qt)) | |
8916 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 8917 | |
d46c5b12 KH |
8918 | validate_region (&start, &end); |
8919 | from = XFASTINT (start); | |
df7492f9 | 8920 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 8921 | to = XFASTINT (end); |
df7492f9 | 8922 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 8923 | |
df7492f9 KH |
8924 | setup_coding_system (coding_system, &coding); |
8925 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 8926 | |
df7492f9 KH |
8927 | if (encodep) |
8928 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8929 | dst_object); | |
8930 | else | |
8931 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8932 | dst_object); | |
8933 | if (! norecord) | |
8934 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 8935 | |
df7492f9 KH |
8936 | return (BUFFERP (dst_object) |
8937 | ? make_number (coding.produced_char) | |
8938 | : coding.dst_object); | |
4031e2bf | 8939 | } |
78108bcd | 8940 | |
4ed46869 | 8941 | |
4031e2bf | 8942 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 8943 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 8944 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
8945 | When called from a program, takes four arguments: |
8946 | START, END, CODING-SYSTEM, and DESTINATION. | |
8947 | START and END are buffer positions. | |
8844fa83 | 8948 | |
df7492f9 | 8949 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 8950 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
8951 | If buffer, the decoded text is inserted in that buffer after point (point |
8952 | does not move). | |
446dcd75 | 8953 | In those cases, the length of the decoded text is returned. |
319a3947 | 8954 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 8955 | |
48b0f3ae PJ |
8956 | This function sets `last-coding-system-used' to the precise coding system |
8957 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8958 | not fully specified.) */) |
5842a27b | 8959 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
4031e2bf | 8960 | { |
df7492f9 | 8961 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 8962 | } |
8844fa83 | 8963 | |
3a73fa5d | 8964 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
8965 | 3, 4, "r\nzCoding system: ", |
8966 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
8967 | When called from a program, takes four arguments: |
8968 | START, END, CODING-SYSTEM and DESTINATION. | |
8969 | START and END are buffer positions. | |
d46c5b12 | 8970 | |
df7492f9 KH |
8971 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
8972 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
8973 | If buffer, the encoded text is inserted in that buffer after point (point |
8974 | does not move). | |
446dcd75 | 8975 | In those cases, the length of the encoded text is returned. |
319a3947 | 8976 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 8977 | |
48b0f3ae PJ |
8978 | This function sets `last-coding-system-used' to the precise coding system |
8979 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8980 | not fully specified.) */) |
5842a27b | 8981 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
3a73fa5d | 8982 | { |
df7492f9 | 8983 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
8984 | } |
8985 | ||
8986 | Lisp_Object | |
6f704c76 DN |
8987 | code_convert_string (Lisp_Object string, Lisp_Object coding_system, |
8988 | Lisp_Object dst_object, int encodep, int nocopy, int norecord) | |
b73bfc1c | 8989 | { |
4031e2bf | 8990 | struct coding_system coding; |
df7492f9 | 8991 | EMACS_INT chars, bytes; |
ec6d2bb8 | 8992 | |
b7826503 | 8993 | CHECK_STRING (string); |
d46c5b12 | 8994 | if (NILP (coding_system)) |
4956c225 | 8995 | { |
df7492f9 KH |
8996 | if (! norecord) |
8997 | Vlast_coding_system_used = Qno_conversion; | |
8998 | if (NILP (dst_object)) | |
8999 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 9000 | } |
b73bfc1c | 9001 | |
df7492f9 KH |
9002 | if (NILP (coding_system)) |
9003 | coding_system = Qno_conversion; | |
9004 | else | |
9005 | CHECK_CODING_SYSTEM (coding_system); | |
9006 | if (NILP (dst_object)) | |
9007 | dst_object = Qt; | |
9008 | else if (! EQ (dst_object, Qt)) | |
9009 | CHECK_BUFFER (dst_object); | |
73be902c | 9010 | |
df7492f9 | 9011 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 9012 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
9013 | chars = SCHARS (string); |
9014 | bytes = SBYTES (string); | |
df7492f9 KH |
9015 | if (encodep) |
9016 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9017 | else | |
9018 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9019 | if (! norecord) | |
9020 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 9021 | |
df7492f9 KH |
9022 | return (BUFFERP (dst_object) |
9023 | ? make_number (coding.produced_char) | |
9024 | : coding.dst_object); | |
4ed46869 | 9025 | } |
73be902c | 9026 | |
b73bfc1c | 9027 | |
ecec61c1 | 9028 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 9029 | Do not set Vlast_coding_system_used. |
4ed46869 | 9030 | |
ec6d2bb8 KH |
9031 | This function is called only from macros DECODE_FILE and |
9032 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 9033 | |
ecec61c1 | 9034 | Lisp_Object |
cf84bb53 JB |
9035 | code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system, |
9036 | int encodep) | |
4ed46869 | 9037 | { |
0be8721c | 9038 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
9039 | } |
9040 | ||
4ed46869 | 9041 | |
df7492f9 KH |
9042 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
9043 | 2, 4, 0, | |
9044 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
9045 | ||
9046 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
9047 | if the decoding operation is trivial. | |
ecec61c1 | 9048 | |
d4a1d553 | 9049 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
9050 | inserted in that buffer after point (point does not move). In this |
9051 | case, the return value is the length of the decoded text. | |
ecec61c1 | 9052 | |
df7492f9 KH |
9053 | This function sets `last-coding-system-used' to the precise coding system |
9054 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 9055 | not fully specified.) */) |
5842a27b | 9056 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9057 | { |
df7492f9 KH |
9058 | return code_convert_string (string, coding_system, buffer, |
9059 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
9060 | } |
9061 | ||
df7492f9 KH |
9062 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
9063 | 2, 4, 0, | |
9064 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
9065 | ||
9066 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
9067 | itself if the encoding operation is trivial. | |
9068 | ||
d4a1d553 | 9069 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
9070 | inserted in that buffer after point (point does not move). In this |
9071 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
9072 | |
9073 | This function sets `last-coding-system-used' to the precise coding system | |
9074 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
9075 | not fully specified.) */) | |
5842a27b | 9076 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9077 | { |
df7492f9 | 9078 | return code_convert_string (string, coding_system, buffer, |
c197f191 | 9079 | 1, ! NILP (nocopy), 1); |
4ed46869 | 9080 | } |
df7492f9 | 9081 | |
3a73fa5d | 9082 | \f |
4ed46869 | 9083 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
9084 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
9085 | Return the corresponding character. */) | |
5842a27b | 9086 | (Lisp_Object code) |
4ed46869 | 9087 | { |
df7492f9 KH |
9088 | Lisp_Object spec, attrs, val; |
9089 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
9090 | int c; | |
4ed46869 | 9091 | |
df7492f9 KH |
9092 | CHECK_NATNUM (code); |
9093 | c = XFASTINT (code); | |
9094 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9095 | attrs = AREF (spec, 0); | |
4ed46869 | 9096 | |
df7492f9 KH |
9097 | if (ASCII_BYTE_P (c) |
9098 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9099 | return code; | |
4ed46869 | 9100 | |
df7492f9 KH |
9101 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9102 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
9103 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
9104 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 9105 | |
df7492f9 KH |
9106 | if (c <= 0x7F) |
9107 | charset = charset_roman; | |
9108 | else if (c >= 0xA0 && c < 0xDF) | |
55ab7be3 | 9109 | { |
df7492f9 KH |
9110 | charset = charset_kana; |
9111 | c -= 0x80; | |
4ed46869 | 9112 | } |
55ab7be3 | 9113 | else |
4ed46869 | 9114 | { |
004068e4 | 9115 | int s1 = c >> 8, s2 = c & 0xFF; |
df7492f9 KH |
9116 | |
9117 | if (s1 < 0x81 || (s1 > 0x9F && s1 < 0xE0) || s1 > 0xEF | |
9118 | || s2 < 0x40 || s2 == 0x7F || s2 > 0xFC) | |
9119 | error ("Invalid code: %d", code); | |
9120 | SJIS_TO_JIS (c); | |
9121 | charset = charset_kanji; | |
4ed46869 | 9122 | } |
df7492f9 KH |
9123 | c = DECODE_CHAR (charset, c); |
9124 | if (c < 0) | |
9125 | error ("Invalid code: %d", code); | |
9126 | return make_number (c); | |
93dec019 | 9127 | } |
4ed46869 | 9128 | |
48b0f3ae | 9129 | |
4ed46869 | 9130 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 9131 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae | 9132 | Return the corresponding code in SJIS. */) |
5842a27b | 9133 | (Lisp_Object ch) |
4ed46869 | 9134 | { |
df7492f9 KH |
9135 | Lisp_Object spec, attrs, charset_list; |
9136 | int c; | |
9137 | struct charset *charset; | |
9138 | unsigned code; | |
48b0f3ae | 9139 | |
df7492f9 KH |
9140 | CHECK_CHARACTER (ch); |
9141 | c = XFASTINT (ch); | |
9142 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9143 | attrs = AREF (spec, 0); | |
9144 | ||
9145 | if (ASCII_CHAR_P (c) | |
9146 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9147 | return ch; | |
9148 | ||
9149 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9150 | charset = char_charset (c, charset_list, &code); | |
9151 | if (code == CHARSET_INVALID_CODE (charset)) | |
9152 | error ("Can't encode by shift_jis encoding: %d", c); | |
9153 | JIS_TO_SJIS (code); | |
9154 | ||
9155 | return make_number (code); | |
4ed46869 KH |
9156 | } |
9157 | ||
9158 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
9159 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
9160 | Return the corresponding character. */) | |
5842a27b | 9161 | (Lisp_Object code) |
d46c5b12 | 9162 | { |
df7492f9 KH |
9163 | Lisp_Object spec, attrs, val; |
9164 | struct charset *charset_roman, *charset_big5, *charset; | |
9165 | int c; | |
6289dd10 | 9166 | |
df7492f9 KH |
9167 | CHECK_NATNUM (code); |
9168 | c = XFASTINT (code); | |
9169 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9170 | attrs = AREF (spec, 0); | |
4ed46869 | 9171 | |
df7492f9 KH |
9172 | if (ASCII_BYTE_P (c) |
9173 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9174 | return code; | |
6289dd10 | 9175 | |
df7492f9 KH |
9176 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9177 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
9178 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 9179 | |
df7492f9 KH |
9180 | if (c <= 0x7F) |
9181 | charset = charset_roman; | |
c28a9453 KH |
9182 | else |
9183 | { | |
df7492f9 KH |
9184 | int b1 = c >> 8, b2 = c & 0x7F; |
9185 | if (b1 < 0xA1 || b1 > 0xFE | |
9186 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
9187 | error ("Invalid code: %d", code); | |
9188 | charset = charset_big5; | |
c28a9453 | 9189 | } |
df7492f9 KH |
9190 | c = DECODE_CHAR (charset, (unsigned )c); |
9191 | if (c < 0) | |
9192 | error ("Invalid code: %d", code); | |
9193 | return make_number (c); | |
d46c5b12 | 9194 | } |
6289dd10 | 9195 | |
4ed46869 | 9196 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 9197 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae | 9198 | Return the corresponding character code in Big5. */) |
5842a27b | 9199 | (Lisp_Object ch) |
4ed46869 | 9200 | { |
df7492f9 KH |
9201 | Lisp_Object spec, attrs, charset_list; |
9202 | struct charset *charset; | |
9203 | int c; | |
9204 | unsigned code; | |
9205 | ||
9206 | CHECK_CHARACTER (ch); | |
9207 | c = XFASTINT (ch); | |
9208 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9209 | attrs = AREF (spec, 0); | |
9210 | if (ASCII_CHAR_P (c) | |
9211 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9212 | return ch; | |
9213 | ||
9214 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9215 | charset = char_charset (c, charset_list, &code); | |
9216 | if (code == CHARSET_INVALID_CODE (charset)) | |
9217 | error ("Can't encode by Big5 encoding: %d", c); | |
9218 | ||
9219 | return make_number (code); | |
4ed46869 | 9220 | } |
48b0f3ae | 9221 | |
3a73fa5d | 9222 | \f |
002fdb44 | 9223 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 9224 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9225 | doc: /* Internal use only. */) |
5842a27b | 9226 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9227 | { |
b18fad6d KH |
9228 | struct terminal *term = get_terminal (terminal, 1); |
9229 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term); | |
b7826503 | 9230 | CHECK_SYMBOL (coding_system); |
b8299c66 | 9231 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 9232 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 9233 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
ad1746f5 | 9234 | /* Character composition should be disabled. */ |
c73bd236 | 9235 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
9236 | terminal_coding->src_multibyte = 1; |
9237 | terminal_coding->dst_multibyte = 0; | |
b18fad6d KH |
9238 | if (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK) |
9239 | term->charset_list = coding_charset_list (terminal_coding); | |
9240 | else | |
6b4bb703 | 9241 | term->charset_list = Fcons (make_number (charset_ascii), Qnil); |
4ed46869 KH |
9242 | return Qnil; |
9243 | } | |
9244 | ||
c4825358 KH |
9245 | DEFUN ("set-safe-terminal-coding-system-internal", |
9246 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 9247 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 9248 | doc: /* Internal use only. */) |
5842a27b | 9249 | (Lisp_Object coding_system) |
d46c5b12 | 9250 | { |
b7826503 | 9251 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
9252 | setup_coding_system (Fcheck_coding_system (coding_system), |
9253 | &safe_terminal_coding); | |
ad1746f5 | 9254 | /* Character composition should be disabled. */ |
df7492f9 | 9255 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b73bfc1c KH |
9256 | safe_terminal_coding.src_multibyte = 1; |
9257 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
9258 | return Qnil; |
9259 | } | |
4ed46869 | 9260 | |
002fdb44 | 9261 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 9262 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff | 9263 | doc: /* Return coding system specified for terminal output on the given terminal. |
708e05dc | 9264 | TERMINAL may be a terminal object, a frame, or nil for the selected |
6ed8eeff | 9265 | frame's terminal device. */) |
5842a27b | 9266 | (Lisp_Object terminal) |
4ed46869 | 9267 | { |
985773c9 MB |
9268 | struct coding_system *terminal_coding |
9269 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
9270 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 9271 | |
ae6f73fa | 9272 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 9273 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
9274 | } |
9275 | ||
002fdb44 | 9276 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 9277 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9278 | doc: /* Internal use only. */) |
5842a27b | 9279 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9280 | { |
6ed8eeff | 9281 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 9282 | CHECK_SYMBOL (coding_system); |
624bda09 KH |
9283 | if (NILP (coding_system)) |
9284 | coding_system = Qno_conversion; | |
9285 | else | |
9286 | Fcheck_coding_system (coding_system); | |
9287 | setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t)); | |
ad1746f5 | 9288 | /* Character composition should be disabled. */ |
c73bd236 MB |
9289 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
9290 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
9291 | return Qnil; |
9292 | } | |
9293 | ||
9294 | DEFUN ("keyboard-coding-system", | |
985773c9 | 9295 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 9296 | doc: /* Return coding system specified for decoding keyboard input. */) |
5842a27b | 9297 | (Lisp_Object terminal) |
4ed46869 | 9298 | { |
985773c9 MB |
9299 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
9300 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
9301 | } |
9302 | ||
4ed46869 | 9303 | \f |
a5d301df KH |
9304 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
9305 | Sfind_operation_coding_system, 1, MANY, 0, | |
48b0f3ae PJ |
9306 | doc: /* Choose a coding system for an operation based on the target name. |
9307 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
9308 | DECODING-SYSTEM is the coding system to use for decoding | |
9309 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
9310 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 9311 | |
48b0f3ae PJ |
9312 | The first argument OPERATION specifies an I/O primitive: |
9313 | For file I/O, `insert-file-contents' or `write-region'. | |
9314 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
9315 | For network I/O, `open-network-stream'. | |
05e6f5dc | 9316 | |
48b0f3ae PJ |
9317 | The remaining arguments should be the same arguments that were passed |
9318 | to the primitive. Depending on which primitive, one of those arguments | |
9319 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
9320 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 9321 | |
48b0f3ae | 9322 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 9323 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 9324 | For process I/O, TARGET is a process name. |
d4a1d553 | 9325 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 9326 | |
d4a1d553 | 9327 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
9328 | `file-coding-system-alist', `process-coding-system-alist', |
9329 | or `network-coding-system-alist' depending on OPERATION. | |
9330 | They may specify a coding system, a cons of coding systems, | |
9331 | or a function symbol to call. | |
9332 | In the last case, we call the function with one argument, | |
9333 | which is a list of all the arguments given to this function. | |
1011c487 MB |
9334 | If the function can't decide a coding system, it can return |
9335 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 9336 | |
b883cdb2 MB |
9337 | If OPERATION is `insert-file-contents', the argument corresponding to |
9338 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
9339 | file name to look up, and BUFFER is a buffer that contains the file's | |
9340 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
9341 | function to call for FILENAME, that function should examine the | |
9342 | contents of BUFFER instead of reading the file. | |
9343 | ||
d918f936 | 9344 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
5842a27b | 9345 | (int nargs, Lisp_Object *args) |
6b89e3aa | 9346 | { |
4ed46869 KH |
9347 | Lisp_Object operation, target_idx, target, val; |
9348 | register Lisp_Object chain; | |
177c0ea7 | 9349 | |
4ed46869 KH |
9350 | if (nargs < 2) |
9351 | error ("Too few arguments"); | |
9352 | operation = args[0]; | |
9353 | if (!SYMBOLP (operation) | |
9354 | || !INTEGERP (target_idx = Fget (operation, Qtarget_idx))) | |
3ed051d4 | 9355 | error ("Invalid first argument"); |
4ed46869 KH |
9356 | if (nargs < 1 + XINT (target_idx)) |
9357 | error ("Too few arguments for operation: %s", | |
8f924df7 | 9358 | SDATA (SYMBOL_NAME (operation))); |
4ed46869 KH |
9359 | target = args[XINT (target_idx) + 1]; |
9360 | if (!(STRINGP (target) | |
091a0ff0 KH |
9361 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
9362 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 9363 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
df7492f9 | 9364 | error ("Invalid %dth argument", XINT (target_idx) + 1); |
091a0ff0 KH |
9365 | if (CONSP (target)) |
9366 | target = XCAR (target); | |
4ed46869 | 9367 | |
2e34157c RS |
9368 | chain = ((EQ (operation, Qinsert_file_contents) |
9369 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9370 | ? Vfile_coding_system_alist |
2e34157c | 9371 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9372 | ? Vnetwork_coding_system_alist |
9373 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9374 | if (NILP (chain)) |
9375 | return Qnil; | |
9376 | ||
03699b14 | 9377 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9378 | { |
f44d27ce | 9379 | Lisp_Object elt; |
6b89e3aa | 9380 | |
df7492f9 | 9381 | elt = XCAR (chain); |
4ed46869 KH |
9382 | if (CONSP (elt) |
9383 | && ((STRINGP (target) | |
03699b14 KR |
9384 | && STRINGP (XCAR (elt)) |
9385 | && fast_string_match (XCAR (elt), target) >= 0) | |
9386 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9387 | { |
03699b14 | 9388 | val = XCDR (elt); |
b19fd4c5 KH |
9389 | /* Here, if VAL is both a valid coding system and a valid |
9390 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9391 | if (CONSP (val)) |
9392 | return val; | |
9393 | if (! SYMBOLP (val)) | |
9394 | return Qnil; | |
9395 | if (! NILP (Fcoding_system_p (val))) | |
9396 | return Fcons (val, val); | |
b19fd4c5 | 9397 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9398 | { |
e2b97060 MB |
9399 | /* We use call1 rather than safe_call1 |
9400 | so as to get bug reports about functions called here | |
9401 | which don't handle the current interface. */ | |
9402 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9403 | if (CONSP (val)) |
9404 | return val; | |
9405 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9406 | return Fcons (val, val); | |
6b89e3aa | 9407 | } |
02ba4723 | 9408 | return Qnil; |
6b89e3aa KH |
9409 | } |
9410 | } | |
4ed46869 | 9411 | return Qnil; |
6b89e3aa KH |
9412 | } |
9413 | ||
df7492f9 | 9414 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9415 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9416 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9417 | If multiple coding systems belong to the same category, |
a3181084 DL |
9418 | all but the first one are ignored. |
9419 | ||
d4a1d553 | 9420 | usage: (set-coding-system-priority &rest coding-systems) */) |
5842a27b | 9421 | (int nargs, Lisp_Object *args) |
df7492f9 KH |
9422 | { |
9423 | int i, j; | |
9424 | int changed[coding_category_max]; | |
9425 | enum coding_category priorities[coding_category_max]; | |
9426 | ||
72af86bd | 9427 | memset (changed, 0, sizeof changed); |
6b89e3aa | 9428 | |
df7492f9 | 9429 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9430 | { |
df7492f9 KH |
9431 | enum coding_category category; |
9432 | Lisp_Object spec, attrs; | |
6b89e3aa | 9433 | |
df7492f9 KH |
9434 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9435 | attrs = AREF (spec, 0); | |
9436 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9437 | if (changed[category]) | |
9438 | /* Ignore this coding system because a coding system of the | |
9439 | same category already had a higher priority. */ | |
9440 | continue; | |
9441 | changed[category] = 1; | |
9442 | priorities[j++] = category; | |
9443 | if (coding_categories[category].id >= 0 | |
9444 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9445 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9446 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9447 | } |
6b89e3aa | 9448 | |
df7492f9 KH |
9449 | /* Now we have decided top J priorities. Reflect the order of the |
9450 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9451 | |
df7492f9 | 9452 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9453 | { |
df7492f9 KH |
9454 | while (j < coding_category_max |
9455 | && changed[coding_priorities[j]]) | |
9456 | j++; | |
9457 | if (j == coding_category_max) | |
9458 | abort (); | |
9459 | priorities[i] = coding_priorities[j]; | |
9460 | } | |
6b89e3aa | 9461 | |
72af86bd | 9462 | memcpy (coding_priorities, priorities, sizeof priorities); |
177c0ea7 | 9463 | |
ff563fce KH |
9464 | /* Update `coding-category-list'. */ |
9465 | Vcoding_category_list = Qnil; | |
9466 | for (i = coding_category_max - 1; i >= 0; i--) | |
9467 | Vcoding_category_list | |
9468 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9469 | Vcoding_category_list); | |
6b89e3aa | 9470 | |
df7492f9 | 9471 | return Qnil; |
6b89e3aa KH |
9472 | } |
9473 | ||
df7492f9 KH |
9474 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9475 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 | 9476 | doc: /* Return a list of coding systems ordered by their priorities. |
b811c52b KH |
9477 | The list contains a subset of coding systems; i.e. coding systems |
9478 | assigned to each coding category (see `coding-category-list'). | |
9479 | ||
da7db224 | 9480 | HIGHESTP non-nil means just return the highest priority one. */) |
5842a27b | 9481 | (Lisp_Object highestp) |
d46c5b12 KH |
9482 | { |
9483 | int i; | |
df7492f9 | 9484 | Lisp_Object val; |
6b89e3aa | 9485 | |
df7492f9 | 9486 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9487 | { |
df7492f9 KH |
9488 | enum coding_category category = coding_priorities[i]; |
9489 | int id = coding_categories[category].id; | |
9490 | Lisp_Object attrs; | |
068a9dbd | 9491 | |
df7492f9 KH |
9492 | if (id < 0) |
9493 | continue; | |
9494 | attrs = CODING_ID_ATTRS (id); | |
9495 | if (! NILP (highestp)) | |
9496 | return CODING_ATTR_BASE_NAME (attrs); | |
9497 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9498 | } | |
9499 | return Fnreverse (val); | |
9500 | } | |
068a9dbd | 9501 | |
91433552 | 9502 | static const char *const suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9503 | |
9504 | static Lisp_Object | |
971de7fb | 9505 | make_subsidiaries (Lisp_Object base) |
068a9dbd | 9506 | { |
df7492f9 | 9507 | Lisp_Object subsidiaries; |
8f924df7 | 9508 | int base_name_len = SBYTES (SYMBOL_NAME (base)); |
df7492f9 KH |
9509 | char *buf = (char *) alloca (base_name_len + 6); |
9510 | int i; | |
068a9dbd | 9511 | |
72af86bd | 9512 | memcpy (buf, SDATA (SYMBOL_NAME (base)), base_name_len); |
df7492f9 KH |
9513 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
9514 | for (i = 0; i < 3; i++) | |
068a9dbd | 9515 | { |
72af86bd | 9516 | memcpy (buf + base_name_len, suffixes[i], strlen (suffixes[i]) + 1); |
df7492f9 | 9517 | ASET (subsidiaries, i, intern (buf)); |
068a9dbd | 9518 | } |
df7492f9 | 9519 | return subsidiaries; |
068a9dbd KH |
9520 | } |
9521 | ||
9522 | ||
df7492f9 KH |
9523 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9524 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9525 | doc: /* For internal use only. |
9526 | usage: (define-coding-system-internal ...) */) | |
5842a27b | 9527 | (int nargs, Lisp_Object *args) |
068a9dbd | 9528 | { |
df7492f9 KH |
9529 | Lisp_Object name; |
9530 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9531 | Lisp_Object attrs; /* Vector of attributes. */ | |
9532 | Lisp_Object eol_type; | |
9533 | Lisp_Object aliases; | |
9534 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9535 | enum coding_category category; | |
9536 | Lisp_Object tail, val; | |
9537 | int max_charset_id = 0; | |
9538 | int i; | |
068a9dbd | 9539 | |
df7492f9 KH |
9540 | if (nargs < coding_arg_max) |
9541 | goto short_args; | |
068a9dbd | 9542 | |
df7492f9 | 9543 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9544 | |
df7492f9 KH |
9545 | name = args[coding_arg_name]; |
9546 | CHECK_SYMBOL (name); | |
9547 | CODING_ATTR_BASE_NAME (attrs) = name; | |
068a9dbd | 9548 | |
df7492f9 KH |
9549 | val = args[coding_arg_mnemonic]; |
9550 | if (! STRINGP (val)) | |
9551 | CHECK_CHARACTER (val); | |
9552 | CODING_ATTR_MNEMONIC (attrs) = val; | |
068a9dbd | 9553 | |
df7492f9 KH |
9554 | coding_type = args[coding_arg_coding_type]; |
9555 | CHECK_SYMBOL (coding_type); | |
9556 | CODING_ATTR_TYPE (attrs) = coding_type; | |
068a9dbd | 9557 | |
df7492f9 KH |
9558 | charset_list = args[coding_arg_charset_list]; |
9559 | if (SYMBOLP (charset_list)) | |
9560 | { | |
9561 | if (EQ (charset_list, Qiso_2022)) | |
9562 | { | |
9563 | if (! EQ (coding_type, Qiso_2022)) | |
9564 | error ("Invalid charset-list"); | |
9565 | charset_list = Viso_2022_charset_list; | |
9566 | } | |
9567 | else if (EQ (charset_list, Qemacs_mule)) | |
9568 | { | |
9569 | if (! EQ (coding_type, Qemacs_mule)) | |
9570 | error ("Invalid charset-list"); | |
9571 | charset_list = Vemacs_mule_charset_list; | |
9572 | } | |
9573 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
9574 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9575 | max_charset_id = XFASTINT (XCAR (tail)); | |
9576 | } | |
068a9dbd KH |
9577 | else |
9578 | { | |
df7492f9 | 9579 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9580 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9581 | { |
df7492f9 KH |
9582 | struct charset *charset; |
9583 | ||
985773c9 | 9584 | val = XCAR (tail); |
df7492f9 KH |
9585 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9586 | if (EQ (coding_type, Qiso_2022) | |
9587 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9588 | : EQ (coding_type, Qemacs_mule) | |
9589 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9590 | : 0) | |
9591 | error ("Can't handle charset `%s'", | |
8f924df7 | 9592 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9593 | |
8f924df7 | 9594 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9595 | if (max_charset_id < charset->id) |
9596 | max_charset_id = charset->id; | |
068a9dbd KH |
9597 | } |
9598 | } | |
df7492f9 | 9599 | CODING_ATTR_CHARSET_LIST (attrs) = charset_list; |
068a9dbd | 9600 | |
1b3b981b AS |
9601 | safe_charsets = make_uninit_string (max_charset_id + 1); |
9602 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 | 9603 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8f924df7 | 9604 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 9605 | CODING_ATTR_SAFE_CHARSETS (attrs) = safe_charsets; |
068a9dbd | 9606 | |
584948ac | 9607 | CODING_ATTR_ASCII_COMPAT (attrs) = args[coding_arg_ascii_compatible_p]; |
3a73fa5d | 9608 | |
df7492f9 | 9609 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 9610 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9611 | CHECK_SYMBOL (val); |
df7492f9 | 9612 | CODING_ATTR_DECODE_TBL (attrs) = val; |
3a73fa5d | 9613 | |
df7492f9 | 9614 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 9615 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9616 | CHECK_SYMBOL (val); |
df7492f9 | 9617 | CODING_ATTR_ENCODE_TBL (attrs) = val; |
d46c5b12 | 9618 | |
df7492f9 KH |
9619 | val = args[coding_arg_post_read_conversion]; |
9620 | CHECK_SYMBOL (val); | |
9621 | CODING_ATTR_POST_READ (attrs) = val; | |
d46c5b12 | 9622 | |
df7492f9 KH |
9623 | val = args[coding_arg_pre_write_conversion]; |
9624 | CHECK_SYMBOL (val); | |
9625 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
3a73fa5d | 9626 | |
df7492f9 KH |
9627 | val = args[coding_arg_default_char]; |
9628 | if (NILP (val)) | |
9629 | CODING_ATTR_DEFAULT_CHAR (attrs) = make_number (' '); | |
9630 | else | |
9631 | { | |
8f924df7 | 9632 | CHECK_CHARACTER (val); |
df7492f9 KH |
9633 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; |
9634 | } | |
4031e2bf | 9635 | |
8f924df7 KH |
9636 | val = args[coding_arg_for_unibyte]; |
9637 | CODING_ATTR_FOR_UNIBYTE (attrs) = NILP (val) ? Qnil : Qt; | |
3a73fa5d | 9638 | |
df7492f9 KH |
9639 | val = args[coding_arg_plist]; |
9640 | CHECK_LIST (val); | |
9641 | CODING_ATTR_PLIST (attrs) = val; | |
3a73fa5d | 9642 | |
df7492f9 KH |
9643 | if (EQ (coding_type, Qcharset)) |
9644 | { | |
c7c66a95 KH |
9645 | /* Generate a lisp vector of 256 elements. Each element is nil, |
9646 | integer, or a list of charset IDs. | |
3a73fa5d | 9647 | |
c7c66a95 KH |
9648 | If Nth element is nil, the byte code N is invalid in this |
9649 | coding system. | |
4ed46869 | 9650 | |
c7c66a95 KH |
9651 | If Nth element is a number NUM, N is the first byte of a |
9652 | charset whose ID is NUM. | |
4ed46869 | 9653 | |
c7c66a95 KH |
9654 | If Nth element is a list of charset IDs, N is the first byte |
9655 | of one of them. The list is sorted by dimensions of the | |
ad1746f5 | 9656 | charsets. A charset of smaller dimension comes first. */ |
df7492f9 | 9657 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 9658 | |
5c99c2e6 | 9659 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9660 | { |
c7c66a95 KH |
9661 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
9662 | int dim = CHARSET_DIMENSION (charset); | |
9663 | int idx = (dim - 1) * 4; | |
4ed46869 | 9664 | |
5c99c2e6 | 9665 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
584948ac | 9666 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
4031e2bf | 9667 | |
15d143f7 KH |
9668 | for (i = charset->code_space[idx]; |
9669 | i <= charset->code_space[idx + 1]; i++) | |
9670 | { | |
c7c66a95 KH |
9671 | Lisp_Object tmp, tmp2; |
9672 | int dim2; | |
ec6d2bb8 | 9673 | |
c7c66a95 KH |
9674 | tmp = AREF (val, i); |
9675 | if (NILP (tmp)) | |
9676 | tmp = XCAR (tail); | |
9677 | else if (NUMBERP (tmp)) | |
9678 | { | |
9679 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
9680 | if (dim < dim2) | |
c7c66a95 | 9681 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
9682 | else |
9683 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 9684 | } |
15d143f7 | 9685 | else |
c7c66a95 KH |
9686 | { |
9687 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
9688 | { | |
9689 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
9690 | if (dim < dim2) | |
9691 | break; | |
9692 | } | |
9693 | if (NILP (tmp2)) | |
9694 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
9695 | else | |
9696 | { | |
9697 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
9698 | XSETCAR (tmp2, XCAR (tail)); | |
9699 | } | |
9700 | } | |
9701 | ASET (val, i, tmp); | |
15d143f7 | 9702 | } |
df7492f9 KH |
9703 | } |
9704 | ASET (attrs, coding_attr_charset_valids, val); | |
9705 | category = coding_category_charset; | |
9706 | } | |
9707 | else if (EQ (coding_type, Qccl)) | |
9708 | { | |
9709 | Lisp_Object valids; | |
ecec61c1 | 9710 | |
df7492f9 KH |
9711 | if (nargs < coding_arg_ccl_max) |
9712 | goto short_args; | |
ecec61c1 | 9713 | |
df7492f9 KH |
9714 | val = args[coding_arg_ccl_decoder]; |
9715 | CHECK_CCL_PROGRAM (val); | |
9716 | if (VECTORP (val)) | |
9717 | val = Fcopy_sequence (val); | |
9718 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 9719 | |
df7492f9 KH |
9720 | val = args[coding_arg_ccl_encoder]; |
9721 | CHECK_CCL_PROGRAM (val); | |
9722 | if (VECTORP (val)) | |
9723 | val = Fcopy_sequence (val); | |
9724 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 9725 | |
df7492f9 KH |
9726 | val = args[coding_arg_ccl_valids]; |
9727 | valids = Fmake_string (make_number (256), make_number (0)); | |
9728 | for (tail = val; !NILP (tail); tail = Fcdr (tail)) | |
9729 | { | |
8dcbea82 | 9730 | int from, to; |
ecec61c1 | 9731 | |
df7492f9 KH |
9732 | val = Fcar (tail); |
9733 | if (INTEGERP (val)) | |
8dcbea82 KH |
9734 | { |
9735 | from = to = XINT (val); | |
9736 | if (from < 0 || from > 255) | |
9737 | args_out_of_range_3 (val, make_number (0), make_number (255)); | |
9738 | } | |
df7492f9 KH |
9739 | else |
9740 | { | |
df7492f9 | 9741 | CHECK_CONS (val); |
8f924df7 KH |
9742 | CHECK_NATNUM_CAR (val); |
9743 | CHECK_NATNUM_CDR (val); | |
df7492f9 | 9744 | from = XINT (XCAR (val)); |
8f924df7 | 9745 | if (from > 255) |
8dcbea82 KH |
9746 | args_out_of_range_3 (XCAR (val), |
9747 | make_number (0), make_number (255)); | |
df7492f9 | 9748 | to = XINT (XCDR (val)); |
8dcbea82 KH |
9749 | if (to < from || to > 255) |
9750 | args_out_of_range_3 (XCDR (val), | |
9751 | XCAR (val), make_number (255)); | |
df7492f9 | 9752 | } |
8dcbea82 | 9753 | for (i = from; i <= to; i++) |
8f924df7 | 9754 | SSET (valids, i, 1); |
df7492f9 KH |
9755 | } |
9756 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 9757 | |
df7492f9 | 9758 | category = coding_category_ccl; |
55ab7be3 | 9759 | } |
df7492f9 | 9760 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 9761 | { |
df7492f9 | 9762 | Lisp_Object bom, endian; |
4ed46869 | 9763 | |
584948ac | 9764 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; |
4ed46869 | 9765 | |
df7492f9 KH |
9766 | if (nargs < coding_arg_utf16_max) |
9767 | goto short_args; | |
4ed46869 | 9768 | |
df7492f9 KH |
9769 | bom = args[coding_arg_utf16_bom]; |
9770 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9771 | { | |
9772 | CHECK_CONS (bom); | |
8f924df7 KH |
9773 | val = XCAR (bom); |
9774 | CHECK_CODING_SYSTEM (val); | |
9775 | val = XCDR (bom); | |
9776 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 9777 | } |
a470d443 | 9778 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
9779 | |
9780 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
9781 | CHECK_SYMBOL (endian); |
9782 | if (NILP (endian)) | |
9783 | endian = Qbig; | |
9784 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 9785 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
9786 | ASET (attrs, coding_attr_utf_16_endian, endian); |
9787 | ||
9788 | category = (CONSP (bom) | |
9789 | ? coding_category_utf_16_auto | |
9790 | : NILP (bom) | |
b49a1807 | 9791 | ? (EQ (endian, Qbig) |
df7492f9 KH |
9792 | ? coding_category_utf_16_be_nosig |
9793 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 9794 | : (EQ (endian, Qbig) |
df7492f9 KH |
9795 | ? coding_category_utf_16_be |
9796 | : coding_category_utf_16_le)); | |
9797 | } | |
9798 | else if (EQ (coding_type, Qiso_2022)) | |
9799 | { | |
9800 | Lisp_Object initial, reg_usage, request, flags; | |
4776e638 | 9801 | int i; |
1397dc18 | 9802 | |
df7492f9 KH |
9803 | if (nargs < coding_arg_iso2022_max) |
9804 | goto short_args; | |
9805 | ||
9806 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
9807 | CHECK_VECTOR (initial); | |
9808 | for (i = 0; i < 4; i++) | |
9809 | { | |
9810 | val = Faref (initial, make_number (i)); | |
9811 | if (! NILP (val)) | |
9812 | { | |
584948ac KH |
9813 | struct charset *charset; |
9814 | ||
9815 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
9816 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
9817 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
9818 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9819 | } |
9820 | else | |
9821 | ASET (initial, i, make_number (-1)); | |
9822 | } | |
9823 | ||
9824 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
9825 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
9826 | CHECK_NUMBER_CAR (reg_usage); |
9827 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
9828 | |
9829 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
9830 | for (tail = request; ! NILP (tail); tail = Fcdr (tail)) | |
1397dc18 | 9831 | { |
df7492f9 | 9832 | int id; |
8f924df7 | 9833 | Lisp_Object tmp; |
df7492f9 KH |
9834 | |
9835 | val = Fcar (tail); | |
9836 | CHECK_CONS (val); | |
8f924df7 KH |
9837 | tmp = XCAR (val); |
9838 | CHECK_CHARSET_GET_ID (tmp, id); | |
9839 | CHECK_NATNUM_CDR (val); | |
df7492f9 KH |
9840 | if (XINT (XCDR (val)) >= 4) |
9841 | error ("Invalid graphic register number: %d", XINT (XCDR (val))); | |
8f924df7 | 9842 | XSETCAR (val, make_number (id)); |
1397dc18 | 9843 | } |
4ed46869 | 9844 | |
df7492f9 KH |
9845 | flags = args[coding_arg_iso2022_flags]; |
9846 | CHECK_NATNUM (flags); | |
9847 | i = XINT (flags); | |
9848 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) | |
9849 | flags = make_number (i | CODING_ISO_FLAG_FULL_SUPPORT); | |
9850 | ||
9851 | ASET (attrs, coding_attr_iso_initial, initial); | |
9852 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
9853 | ASET (attrs, coding_attr_iso_request, request); | |
9854 | ASET (attrs, coding_attr_iso_flags, flags); | |
9855 | setup_iso_safe_charsets (attrs); | |
9856 | ||
9857 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
9858 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
9859 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
9860 | ? coding_category_iso_7_else | |
9861 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
9862 | ? coding_category_iso_7 | |
9863 | : coding_category_iso_7_tight); | |
9864 | else | |
9865 | { | |
9866 | int id = XINT (AREF (initial, 1)); | |
9867 | ||
c6fb6e98 | 9868 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
9869 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
9870 | || id < 0) | |
9871 | ? coding_category_iso_8_else | |
9872 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
9873 | ? coding_category_iso_8_1 | |
9874 | : coding_category_iso_8_2); | |
9875 | } | |
0ce7886f KH |
9876 | if (category != coding_category_iso_8_1 |
9877 | && category != coding_category_iso_8_2) | |
9878 | CODING_ATTR_ASCII_COMPAT (attrs) = Qnil; | |
df7492f9 KH |
9879 | } |
9880 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 9881 | { |
df7492f9 KH |
9882 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
9883 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
584948ac | 9884 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
df7492f9 | 9885 | category = coding_category_emacs_mule; |
c28a9453 | 9886 | } |
df7492f9 | 9887 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 9888 | { |
df7492f9 KH |
9889 | |
9890 | struct charset *charset; | |
9891 | ||
7d64c6ad | 9892 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 9893 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 9894 | error ("There should be three or four charsets"); |
df7492f9 KH |
9895 | |
9896 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9897 | if (CHARSET_DIMENSION (charset) != 1) | |
9898 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9899 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
9900 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
9901 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9902 | |
9903 | charset_list = XCDR (charset_list); | |
9904 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9905 | if (CHARSET_DIMENSION (charset) != 1) | |
9906 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9907 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
9908 | |
9909 | charset_list = XCDR (charset_list); | |
9910 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9911 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
9912 | error ("Dimension of charset %s is not two", |
9913 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9914 | ||
9915 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
9916 | if (! NILP (charset_list)) |
9917 | { | |
9918 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9919 | if (CHARSET_DIMENSION (charset) != 2) | |
9920 | error ("Dimension of charset %s is not two", | |
9921 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9922 | } | |
df7492f9 KH |
9923 | |
9924 | category = coding_category_sjis; | |
9925 | Vsjis_coding_system = name; | |
c28a9453 | 9926 | } |
df7492f9 KH |
9927 | else if (EQ (coding_type, Qbig5)) |
9928 | { | |
9929 | struct charset *charset; | |
4ed46869 | 9930 | |
df7492f9 KH |
9931 | if (XINT (Flength (charset_list)) != 2) |
9932 | error ("There should be just two charsets"); | |
9933 | ||
9934 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9935 | if (CHARSET_DIMENSION (charset) != 1) | |
9936 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9937 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac KH |
9938 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
9939 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
df7492f9 KH |
9940 | |
9941 | charset_list = XCDR (charset_list); | |
9942 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9943 | if (CHARSET_DIMENSION (charset) != 2) | |
9944 | error ("Dimension of charset %s is not two", | |
8f924df7 | 9945 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 9946 | |
df7492f9 KH |
9947 | category = coding_category_big5; |
9948 | Vbig5_coding_system = name; | |
9949 | } | |
9950 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 9951 | { |
584948ac KH |
9952 | category = coding_category_raw_text; |
9953 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; | |
c28a9453 | 9954 | } |
df7492f9 | 9955 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 9956 | { |
a470d443 KH |
9957 | Lisp_Object bom; |
9958 | ||
584948ac | 9959 | CODING_ATTR_ASCII_COMPAT (attrs) = Qt; |
a470d443 KH |
9960 | |
9961 | if (nargs < coding_arg_utf8_max) | |
9962 | goto short_args; | |
9963 | ||
9964 | bom = args[coding_arg_utf8_bom]; | |
9965 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9966 | { | |
9967 | CHECK_CONS (bom); | |
9968 | val = XCAR (bom); | |
9969 | CHECK_CODING_SYSTEM (val); | |
9970 | val = XCDR (bom); | |
9971 | CHECK_CODING_SYSTEM (val); | |
9972 | } | |
9973 | ASET (attrs, coding_attr_utf_bom, bom); | |
9974 | ||
9975 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
9976 | : NILP (bom) ? coding_category_utf_8_nosig | |
9977 | : coding_category_utf_8_sig); | |
4ed46869 | 9978 | } |
df7492f9 KH |
9979 | else if (EQ (coding_type, Qundecided)) |
9980 | category = coding_category_undecided; | |
4ed46869 | 9981 | else |
df7492f9 | 9982 | error ("Invalid coding system type: %s", |
8f924df7 | 9983 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 9984 | |
df7492f9 | 9985 | CODING_ATTR_CATEGORY (attrs) = make_number (category); |
01378f49 KH |
9986 | CODING_ATTR_PLIST (attrs) |
9987 | = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category), | |
9988 | CODING_ATTR_PLIST (attrs))); | |
35befdaa | 9989 | CODING_ATTR_PLIST (attrs) |
3ed051d4 | 9990 | = Fcons (QCascii_compatible_p, |
35befdaa KH |
9991 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), |
9992 | CODING_ATTR_PLIST (attrs))); | |
c4825358 | 9993 | |
df7492f9 KH |
9994 | eol_type = args[coding_arg_eol_type]; |
9995 | if (! NILP (eol_type) | |
9996 | && ! EQ (eol_type, Qunix) | |
9997 | && ! EQ (eol_type, Qdos) | |
9998 | && ! EQ (eol_type, Qmac)) | |
9999 | error ("Invalid eol-type"); | |
4ed46869 | 10000 | |
df7492f9 | 10001 | aliases = Fcons (name, Qnil); |
4ed46869 | 10002 | |
df7492f9 KH |
10003 | if (NILP (eol_type)) |
10004 | { | |
10005 | eol_type = make_subsidiaries (name); | |
10006 | for (i = 0; i < 3; i++) | |
1397dc18 | 10007 | { |
df7492f9 KH |
10008 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
10009 | ||
10010 | this_name = AREF (eol_type, i); | |
10011 | this_aliases = Fcons (this_name, Qnil); | |
10012 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
10013 | this_spec = Fmake_vector (make_number (3), attrs); | |
10014 | ASET (this_spec, 1, this_aliases); | |
10015 | ASET (this_spec, 2, this_eol_type); | |
10016 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
10017 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
10018 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
10019 | if (NILP (val)) | |
10020 | Vcoding_system_alist | |
10021 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
10022 | Vcoding_system_alist); | |
1397dc18 | 10023 | } |
d46c5b12 | 10024 | } |
4ed46869 | 10025 | |
df7492f9 KH |
10026 | spec_vec = Fmake_vector (make_number (3), attrs); |
10027 | ASET (spec_vec, 1, aliases); | |
10028 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 10029 | |
df7492f9 KH |
10030 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
10031 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
10032 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
10033 | if (NILP (val)) | |
10034 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
10035 | Vcoding_system_alist); | |
48b0f3ae | 10036 | |
df7492f9 KH |
10037 | { |
10038 | int id = coding_categories[category].id; | |
48b0f3ae | 10039 | |
df7492f9 KH |
10040 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
10041 | setup_coding_system (name, &coding_categories[category]); | |
10042 | } | |
48b0f3ae | 10043 | |
d46c5b12 | 10044 | return Qnil; |
48b0f3ae | 10045 | |
df7492f9 KH |
10046 | short_args: |
10047 | return Fsignal (Qwrong_number_of_arguments, | |
10048 | Fcons (intern ("define-coding-system-internal"), | |
10049 | make_number (nargs))); | |
d46c5b12 | 10050 | } |
4ed46869 | 10051 | |
d6925f38 | 10052 | |
a6f87d34 KH |
10053 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
10054 | 3, 3, 0, | |
10055 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
5842a27b | 10056 | (Lisp_Object coding_system, Lisp_Object prop, Lisp_Object val) |
a6f87d34 | 10057 | { |
3dbe7859 | 10058 | Lisp_Object spec, attrs; |
a6f87d34 KH |
10059 | |
10060 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10061 | attrs = AREF (spec, 0); | |
10062 | if (EQ (prop, QCmnemonic)) | |
10063 | { | |
10064 | if (! STRINGP (val)) | |
10065 | CHECK_CHARACTER (val); | |
10066 | CODING_ATTR_MNEMONIC (attrs) = val; | |
10067 | } | |
2133e2d1 | 10068 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
10069 | { |
10070 | if (NILP (val)) | |
10071 | val = make_number (' '); | |
10072 | else | |
10073 | CHECK_CHARACTER (val); | |
10074 | CODING_ATTR_DEFAULT_CHAR (attrs) = val; | |
10075 | } | |
10076 | else if (EQ (prop, QCdecode_translation_table)) | |
10077 | { | |
10078 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10079 | CHECK_SYMBOL (val); | |
10080 | CODING_ATTR_DECODE_TBL (attrs) = val; | |
10081 | } | |
10082 | else if (EQ (prop, QCencode_translation_table)) | |
10083 | { | |
10084 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10085 | CHECK_SYMBOL (val); | |
10086 | CODING_ATTR_ENCODE_TBL (attrs) = val; | |
10087 | } | |
10088 | else if (EQ (prop, QCpost_read_conversion)) | |
10089 | { | |
10090 | CHECK_SYMBOL (val); | |
10091 | CODING_ATTR_POST_READ (attrs) = val; | |
10092 | } | |
10093 | else if (EQ (prop, QCpre_write_conversion)) | |
10094 | { | |
10095 | CHECK_SYMBOL (val); | |
10096 | CODING_ATTR_PRE_WRITE (attrs) = val; | |
10097 | } | |
35befdaa KH |
10098 | else if (EQ (prop, QCascii_compatible_p)) |
10099 | { | |
10100 | CODING_ATTR_ASCII_COMPAT (attrs) = val; | |
10101 | } | |
a6f87d34 KH |
10102 | |
10103 | CODING_ATTR_PLIST (attrs) | |
10104 | = Fplist_put (CODING_ATTR_PLIST (attrs), prop, val); | |
10105 | return val; | |
10106 | } | |
10107 | ||
10108 | ||
df7492f9 KH |
10109 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
10110 | Sdefine_coding_system_alias, 2, 2, 0, | |
10111 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
5842a27b | 10112 | (Lisp_Object alias, Lisp_Object coding_system) |
66cfb530 | 10113 | { |
583f71ca | 10114 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 10115 | |
df7492f9 KH |
10116 | CHECK_SYMBOL (alias); |
10117 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10118 | aliases = AREF (spec, 1); | |
d4a1d553 | 10119 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
10120 | element is a base coding system. Append ALIAS at the tail of the |
10121 | list. */ | |
df7492f9 KH |
10122 | while (!NILP (XCDR (aliases))) |
10123 | aliases = XCDR (aliases); | |
8f924df7 | 10124 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 10125 | |
df7492f9 KH |
10126 | eol_type = AREF (spec, 2); |
10127 | if (VECTORP (eol_type)) | |
4ed46869 | 10128 | { |
df7492f9 KH |
10129 | Lisp_Object subsidiaries; |
10130 | int i; | |
4ed46869 | 10131 | |
df7492f9 KH |
10132 | subsidiaries = make_subsidiaries (alias); |
10133 | for (i = 0; i < 3; i++) | |
10134 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
10135 | AREF (eol_type, i)); | |
4ed46869 | 10136 | } |
df7492f9 KH |
10137 | |
10138 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 10139 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
10140 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
10141 | if (NILP (val)) | |
10142 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
10143 | Vcoding_system_alist); | |
66cfb530 | 10144 | |
4ed46869 KH |
10145 | return Qnil; |
10146 | } | |
10147 | ||
df7492f9 KH |
10148 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
10149 | 1, 1, 0, | |
10150 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 10151 | Any alias or subsidiary coding system is not a base coding system. */) |
5842a27b | 10152 | (Lisp_Object coding_system) |
d46c5b12 | 10153 | { |
df7492f9 | 10154 | Lisp_Object spec, attrs; |
d46c5b12 | 10155 | |
df7492f9 KH |
10156 | if (NILP (coding_system)) |
10157 | return (Qno_conversion); | |
10158 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10159 | attrs = AREF (spec, 0); | |
10160 | return CODING_ATTR_BASE_NAME (attrs); | |
10161 | } | |
1397dc18 | 10162 | |
df7492f9 KH |
10163 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
10164 | 1, 1, 0, | |
10165 | doc: "Return the property list of CODING-SYSTEM.") | |
5842a27b | 10166 | (Lisp_Object coding_system) |
df7492f9 KH |
10167 | { |
10168 | Lisp_Object spec, attrs; | |
1397dc18 | 10169 | |
df7492f9 KH |
10170 | if (NILP (coding_system)) |
10171 | coding_system = Qno_conversion; | |
10172 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10173 | attrs = AREF (spec, 0); | |
10174 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
10175 | } |
10176 | ||
df7492f9 KH |
10177 | |
10178 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
10179 | 1, 1, 0, | |
da7db224 | 10180 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
5842a27b | 10181 | (Lisp_Object coding_system) |
66cfb530 | 10182 | { |
df7492f9 | 10183 | Lisp_Object spec; |
84d60297 | 10184 | |
df7492f9 KH |
10185 | if (NILP (coding_system)) |
10186 | coding_system = Qno_conversion; | |
10187 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 10188 | return AREF (spec, 1); |
df7492f9 | 10189 | } |
66cfb530 | 10190 | |
df7492f9 KH |
10191 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
10192 | Scoding_system_eol_type, 1, 1, 0, | |
10193 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 10194 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 10195 | |
df7492f9 KH |
10196 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
10197 | and CR respectively. | |
66cfb530 | 10198 | |
df7492f9 KH |
10199 | A vector value indicates that a format of end-of-line should be |
10200 | detected automatically. Nth element of the vector is the subsidiary | |
10201 | coding system whose eol-type is N. */) | |
5842a27b | 10202 | (Lisp_Object coding_system) |
6b89e3aa | 10203 | { |
df7492f9 KH |
10204 | Lisp_Object spec, eol_type; |
10205 | int n; | |
6b89e3aa | 10206 | |
df7492f9 KH |
10207 | if (NILP (coding_system)) |
10208 | coding_system = Qno_conversion; | |
10209 | if (! CODING_SYSTEM_P (coding_system)) | |
10210 | return Qnil; | |
10211 | spec = CODING_SYSTEM_SPEC (coding_system); | |
10212 | eol_type = AREF (spec, 2); | |
10213 | if (VECTORP (eol_type)) | |
10214 | return Fcopy_sequence (eol_type); | |
10215 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
10216 | return make_number (n); | |
6b89e3aa KH |
10217 | } |
10218 | ||
4ed46869 KH |
10219 | #endif /* emacs */ |
10220 | ||
10221 | \f | |
1397dc18 | 10222 | /*** 9. Post-amble ***/ |
4ed46869 | 10223 | |
dfcf069d | 10224 | void |
971de7fb | 10225 | init_coding_once (void) |
4ed46869 KH |
10226 | { |
10227 | int i; | |
10228 | ||
df7492f9 KH |
10229 | for (i = 0; i < coding_category_max; i++) |
10230 | { | |
10231 | coding_categories[i].id = -1; | |
10232 | coding_priorities[i] = i; | |
10233 | } | |
4ed46869 KH |
10234 | |
10235 | /* ISO2022 specific initialize routine. */ | |
10236 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 10237 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
10238 | for (i = 0x21; i < 0x7F; i++) |
10239 | iso_code_class[i] = ISO_graphic_plane_0; | |
10240 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 10241 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
10242 | for (i = 0xA1; i < 0xFF; i++) |
10243 | iso_code_class[i] = ISO_graphic_plane_1; | |
10244 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
10245 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
10246 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
10247 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
10248 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
10249 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
10250 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
10251 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
10252 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
10253 | ||
df7492f9 KH |
10254 | for (i = 0; i < 256; i++) |
10255 | { | |
10256 | emacs_mule_bytes[i] = 1; | |
10257 | } | |
7c78e542 KH |
10258 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
10259 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
10260 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
10261 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
10262 | } |
10263 | ||
10264 | #ifdef emacs | |
10265 | ||
dfcf069d | 10266 | void |
971de7fb | 10267 | syms_of_coding (void) |
e0e989f6 | 10268 | { |
df7492f9 | 10269 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
10270 | { |
10271 | Lisp_Object args[2]; | |
10272 | args[0] = QCtest; | |
10273 | args[1] = Qeq; | |
10274 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
10275 | } | |
df7492f9 KH |
10276 | |
10277 | staticpro (&Vsjis_coding_system); | |
10278 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 10279 | |
df7492f9 KH |
10280 | staticpro (&Vbig5_coding_system); |
10281 | Vbig5_coding_system = Qnil; | |
10282 | ||
24a73b0a KH |
10283 | staticpro (&Vcode_conversion_reused_workbuf); |
10284 | Vcode_conversion_reused_workbuf = Qnil; | |
10285 | ||
10286 | staticpro (&Vcode_conversion_workbuf_name); | |
d67b4f80 | 10287 | Vcode_conversion_workbuf_name = make_pure_c_string (" *code-conversion-work*"); |
e0e989f6 | 10288 | |
24a73b0a | 10289 | reused_workbuf_in_use = 0; |
df7492f9 KH |
10290 | |
10291 | DEFSYM (Qcharset, "charset"); | |
10292 | DEFSYM (Qtarget_idx, "target-idx"); | |
10293 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
10294 | Fset (Qcoding_system_history, Qnil); |
10295 | ||
9ce27fde | 10296 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 10297 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 10298 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
10299 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
10300 | ||
df7492f9 | 10301 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 10302 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
10303 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
10304 | ||
df7492f9 | 10305 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 10306 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10307 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
10308 | ||
df7492f9 | 10309 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 10310 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10311 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
10312 | ||
df7492f9 | 10313 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 10314 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
10315 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
10316 | ||
df7492f9 KH |
10317 | DEFSYM (Qcoding_system, "coding-system"); |
10318 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 10319 | |
df7492f9 KH |
10320 | DEFSYM (Qeol_type, "eol-type"); |
10321 | DEFSYM (Qunix, "unix"); | |
10322 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 10323 | |
df7492f9 KH |
10324 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
10325 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
10326 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
10327 | DEFSYM (Qdefault_char, "default-char"); | |
10328 | DEFSYM (Qundecided, "undecided"); | |
10329 | DEFSYM (Qno_conversion, "no-conversion"); | |
10330 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 10331 | |
df7492f9 | 10332 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 10333 | |
df7492f9 | 10334 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 10335 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 10336 | |
df7492f9 | 10337 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
10338 | DEFSYM (Qbig, "big"); |
10339 | DEFSYM (Qlittle, "little"); | |
27901516 | 10340 | |
df7492f9 KH |
10341 | DEFSYM (Qshift_jis, "shift-jis"); |
10342 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 10343 | |
df7492f9 | 10344 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 10345 | |
df7492f9 | 10346 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 | 10347 | Fput (Qcoding_system_error, Qerror_conditions, |
d67b4f80 | 10348 | pure_cons (Qcoding_system_error, pure_cons (Qerror, Qnil))); |
4ed46869 | 10349 | Fput (Qcoding_system_error, Qerror_message, |
d67b4f80 | 10350 | make_pure_c_string ("Invalid coding system")); |
4ed46869 | 10351 | |
05e6f5dc KH |
10352 | /* Intern this now in case it isn't already done. |
10353 | Setting this variable twice is harmless. | |
10354 | But don't staticpro it here--that is done in alloc.c. */ | |
d67b4f80 | 10355 | Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots"); |
70c22245 | 10356 | |
df7492f9 | 10357 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 10358 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
10359 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
10360 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10361 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10362 | |
df7492f9 | 10363 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10364 | |
df7492f9 | 10365 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10366 | |
01378f49 | 10367 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10368 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10369 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10370 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10371 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10372 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10373 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10374 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10375 | |
df7492f9 KH |
10376 | Vcoding_category_table |
10377 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10378 | staticpro (&Vcoding_category_table); | |
10379 | /* Followings are target of code detection. */ | |
10380 | ASET (Vcoding_category_table, coding_category_iso_7, | |
d67b4f80 | 10381 | intern_c_string ("coding-category-iso-7")); |
df7492f9 | 10382 | ASET (Vcoding_category_table, coding_category_iso_7_tight, |
d67b4f80 | 10383 | intern_c_string ("coding-category-iso-7-tight")); |
df7492f9 | 10384 | ASET (Vcoding_category_table, coding_category_iso_8_1, |
d67b4f80 | 10385 | intern_c_string ("coding-category-iso-8-1")); |
df7492f9 | 10386 | ASET (Vcoding_category_table, coding_category_iso_8_2, |
d67b4f80 | 10387 | intern_c_string ("coding-category-iso-8-2")); |
df7492f9 | 10388 | ASET (Vcoding_category_table, coding_category_iso_7_else, |
d67b4f80 | 10389 | intern_c_string ("coding-category-iso-7-else")); |
df7492f9 | 10390 | ASET (Vcoding_category_table, coding_category_iso_8_else, |
d67b4f80 | 10391 | intern_c_string ("coding-category-iso-8-else")); |
a470d443 | 10392 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
d67b4f80 | 10393 | intern_c_string ("coding-category-utf-8-auto")); |
a470d443 | 10394 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, |
d67b4f80 | 10395 | intern_c_string ("coding-category-utf-8")); |
a470d443 | 10396 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
d67b4f80 | 10397 | intern_c_string ("coding-category-utf-8-sig")); |
df7492f9 | 10398 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
d67b4f80 | 10399 | intern_c_string ("coding-category-utf-16-be")); |
ff563fce | 10400 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
d67b4f80 | 10401 | intern_c_string ("coding-category-utf-16-auto")); |
df7492f9 | 10402 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
d67b4f80 | 10403 | intern_c_string ("coding-category-utf-16-le")); |
df7492f9 | 10404 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, |
d67b4f80 | 10405 | intern_c_string ("coding-category-utf-16-be-nosig")); |
df7492f9 | 10406 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, |
d67b4f80 | 10407 | intern_c_string ("coding-category-utf-16-le-nosig")); |
df7492f9 | 10408 | ASET (Vcoding_category_table, coding_category_charset, |
d67b4f80 | 10409 | intern_c_string ("coding-category-charset")); |
df7492f9 | 10410 | ASET (Vcoding_category_table, coding_category_sjis, |
d67b4f80 | 10411 | intern_c_string ("coding-category-sjis")); |
df7492f9 | 10412 | ASET (Vcoding_category_table, coding_category_big5, |
d67b4f80 | 10413 | intern_c_string ("coding-category-big5")); |
df7492f9 | 10414 | ASET (Vcoding_category_table, coding_category_ccl, |
d67b4f80 | 10415 | intern_c_string ("coding-category-ccl")); |
df7492f9 | 10416 | ASET (Vcoding_category_table, coding_category_emacs_mule, |
d67b4f80 | 10417 | intern_c_string ("coding-category-emacs-mule")); |
df7492f9 KH |
10418 | /* Followings are NOT target of code detection. */ |
10419 | ASET (Vcoding_category_table, coding_category_raw_text, | |
d67b4f80 | 10420 | intern_c_string ("coding-category-raw-text")); |
df7492f9 | 10421 | ASET (Vcoding_category_table, coding_category_undecided, |
d67b4f80 | 10422 | intern_c_string ("coding-category-undecided")); |
ecf488bc | 10423 | |
065e3595 KH |
10424 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
10425 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
10426 | DEFSYM (Qinvalid_source, "invalid-source"); | |
10427 | DEFSYM (Qinterrupted, "interrupted"); | |
10428 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 10429 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10430 | |
4ed46869 KH |
10431 | defsubr (&Scoding_system_p); |
10432 | defsubr (&Sread_coding_system); | |
10433 | defsubr (&Sread_non_nil_coding_system); | |
10434 | defsubr (&Scheck_coding_system); | |
10435 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10436 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10437 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10438 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10439 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10440 | defsubr (&Sdecode_coding_region); |
10441 | defsubr (&Sencode_coding_region); | |
10442 | defsubr (&Sdecode_coding_string); | |
10443 | defsubr (&Sencode_coding_string); | |
10444 | defsubr (&Sdecode_sjis_char); | |
10445 | defsubr (&Sencode_sjis_char); | |
10446 | defsubr (&Sdecode_big5_char); | |
10447 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10448 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10449 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10450 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10451 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10452 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10453 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10454 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10455 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10456 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10457 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10458 | defsubr (&Scoding_system_base); |
10459 | defsubr (&Scoding_system_plist); | |
10460 | defsubr (&Scoding_system_aliases); | |
10461 | defsubr (&Scoding_system_eol_type); | |
10462 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10463 | |
29208e82 | 10464 | DEFVAR_LISP ("coding-system-list", Vcoding_system_list, |
48b0f3ae PJ |
10465 | doc: /* List of coding systems. |
10466 | ||
10467 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10468 | updated by the functions `define-coding-system' and |
48b0f3ae | 10469 | `define-coding-system-alias'. */); |
4608c386 KH |
10470 | Vcoding_system_list = Qnil; |
10471 | ||
29208e82 | 10472 | DEFVAR_LISP ("coding-system-alist", Vcoding_system_alist, |
48b0f3ae PJ |
10473 | doc: /* Alist of coding system names. |
10474 | Each element is one element list of coding system name. | |
446dcd75 | 10475 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10476 | |
10477 | Do not alter the value of this variable manually. This variable should be | |
10478 | updated by the functions `make-coding-system' and | |
10479 | `define-coding-system-alias'. */); | |
4608c386 KH |
10480 | Vcoding_system_alist = Qnil; |
10481 | ||
29208e82 | 10482 | DEFVAR_LISP ("coding-category-list", Vcoding_category_list, |
48b0f3ae PJ |
10483 | doc: /* List of coding-categories (symbols) ordered by priority. |
10484 | ||
10485 | On detecting a coding system, Emacs tries code detection algorithms | |
10486 | associated with each coding-category one by one in this order. When | |
10487 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10488 | system bound to the corresponding coding-category is selected. |
10489 | ||
448e17d6 | 10490 | Don't modify this variable directly, but use `set-coding-system-priority'. */); |
4ed46869 KH |
10491 | { |
10492 | int i; | |
10493 | ||
10494 | Vcoding_category_list = Qnil; | |
df7492f9 | 10495 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10496 | Vcoding_category_list |
d46c5b12 KH |
10497 | = Fcons (XVECTOR (Vcoding_category_table)->contents[i], |
10498 | Vcoding_category_list); | |
4ed46869 KH |
10499 | } |
10500 | ||
29208e82 | 10501 | DEFVAR_LISP ("coding-system-for-read", Vcoding_system_for_read, |
48b0f3ae PJ |
10502 | doc: /* Specify the coding system for read operations. |
10503 | It is useful to bind this variable with `let', but do not set it globally. | |
10504 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10505 | If not, an appropriate element is used from one of the coding system alists. |
10506 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10507 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10508 | Vcoding_system_for_read = Qnil; |
10509 | ||
29208e82 | 10510 | DEFVAR_LISP ("coding-system-for-write", Vcoding_system_for_write, |
48b0f3ae PJ |
10511 | doc: /* Specify the coding system for write operations. |
10512 | Programs bind this variable with `let', but you should not set it globally. | |
10513 | If the value is a coding system, it is used for encoding of output, | |
10514 | when writing it to a file and when sending it to a file or subprocess. | |
10515 | ||
10516 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10517 | is used from one of the coding system alists. |
10518 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10519 | `process-coding-system-alist', and `network-coding-system-alist'. |
10520 | For output to files, if the above procedure does not specify a coding system, | |
10521 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10522 | Vcoding_system_for_write = Qnil; |
10523 | ||
29208e82 | 10524 | DEFVAR_LISP ("last-coding-system-used", Vlast_coding_system_used, |
df7492f9 KH |
10525 | doc: /* |
10526 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10527 | Vlast_coding_system_used = Qnil; |
10528 | ||
29208e82 | 10529 | DEFVAR_LISP ("last-code-conversion-error", Vlast_code_conversion_error, |
065e3595 KH |
10530 | doc: /* |
10531 | Error status of the last code conversion. | |
10532 | ||
10533 | When an error was detected in the last code conversion, this variable | |
10534 | is set to one of the following symbols. | |
10535 | `insufficient-source' | |
10536 | `inconsistent-eol' | |
10537 | `invalid-source' | |
10538 | `interrupted' | |
10539 | `insufficient-memory' | |
10540 | When no error was detected, the value doesn't change. So, to check | |
10541 | the error status of a code conversion by this variable, you must | |
10542 | explicitly set this variable to nil before performing code | |
10543 | conversion. */); | |
10544 | Vlast_code_conversion_error = Qnil; | |
10545 | ||
29208e82 | 10546 | DEFVAR_BOOL ("inhibit-eol-conversion", inhibit_eol_conversion, |
df7492f9 KH |
10547 | doc: /* |
10548 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10549 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10550 | such conversion. */); | |
9ce27fde KH |
10551 | inhibit_eol_conversion = 0; |
10552 | ||
29208e82 | 10553 | DEFVAR_BOOL ("inherit-process-coding-system", inherit_process_coding_system, |
df7492f9 KH |
10554 | doc: /* |
10555 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10556 | Bind it to t if the process output is to be treated as if it were a file |
10557 | read from some filesystem. */); | |
ed29121d EZ |
10558 | inherit_process_coding_system = 0; |
10559 | ||
29208e82 | 10560 | DEFVAR_LISP ("file-coding-system-alist", Vfile_coding_system_alist, |
df7492f9 KH |
10561 | doc: /* |
10562 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10563 | The format is ((PATTERN . VAL) ...), |
10564 | where PATTERN is a regular expression matching a file name, | |
10565 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10566 | If VAL is a coding system, it is used for both decoding and encoding | |
10567 | the file contents. | |
10568 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10569 | and the cdr part is used for encoding. | |
10570 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10571 | or a cons of coding systems which are used as above. The function is |
10572 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10573 | `find-operation-coding-system' was called. If the function can't decide |
10574 | a coding system, it can return `undecided' so that the normal | |
10575 | code-detection is performed. | |
48b0f3ae PJ |
10576 | |
10577 | See also the function `find-operation-coding-system' | |
10578 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10579 | Vfile_coding_system_alist = Qnil; |
10580 | ||
29208e82 | 10581 | DEFVAR_LISP ("process-coding-system-alist", Vprocess_coding_system_alist, |
df7492f9 KH |
10582 | doc: /* |
10583 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
10584 | The format is ((PATTERN . VAL) ...), |
10585 | where PATTERN is a regular expression matching a program name, | |
10586 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10587 | If VAL is a coding system, it is used for both decoding what received | |
10588 | from the program and encoding what sent to the program. | |
10589 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10590 | and the cdr part is used for encoding. | |
10591 | If VAL is a function symbol, the function must return a coding system | |
10592 | or a cons of coding systems which are used as above. | |
10593 | ||
10594 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
10595 | Vprocess_coding_system_alist = Qnil; |
10596 | ||
29208e82 | 10597 | DEFVAR_LISP ("network-coding-system-alist", Vnetwork_coding_system_alist, |
df7492f9 KH |
10598 | doc: /* |
10599 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
10600 | The format is ((PATTERN . VAL) ...), |
10601 | where PATTERN is a regular expression matching a network service name | |
10602 | or is a port number to connect to, | |
10603 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10604 | If VAL is a coding system, it is used for both decoding what received | |
10605 | from the network stream and encoding what sent to the network stream. | |
10606 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10607 | and the cdr part is used for encoding. | |
10608 | If VAL is a function symbol, the function must return a coding system | |
10609 | or a cons of coding systems which are used as above. | |
10610 | ||
10611 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 10612 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 10613 | |
29208e82 | 10614 | DEFVAR_LISP ("locale-coding-system", Vlocale_coding_system, |
75205970 RS |
10615 | doc: /* Coding system to use with system messages. |
10616 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
10617 | Vlocale_coding_system = Qnil; |
10618 | ||
005f0d35 | 10619 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
29208e82 | 10620 | DEFVAR_LISP ("eol-mnemonic-unix", eol_mnemonic_unix, |
df7492f9 KH |
10621 | doc: /* |
10622 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
d67b4f80 | 10623 | eol_mnemonic_unix = make_pure_c_string (":"); |
4ed46869 | 10624 | |
29208e82 | 10625 | DEFVAR_LISP ("eol-mnemonic-dos", eol_mnemonic_dos, |
df7492f9 KH |
10626 | doc: /* |
10627 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
d67b4f80 | 10628 | eol_mnemonic_dos = make_pure_c_string ("\\"); |
4ed46869 | 10629 | |
29208e82 | 10630 | DEFVAR_LISP ("eol-mnemonic-mac", eol_mnemonic_mac, |
df7492f9 KH |
10631 | doc: /* |
10632 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
d67b4f80 | 10633 | eol_mnemonic_mac = make_pure_c_string ("/"); |
4ed46869 | 10634 | |
29208e82 | 10635 | DEFVAR_LISP ("eol-mnemonic-undecided", eol_mnemonic_undecided, |
df7492f9 KH |
10636 | doc: /* |
10637 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
d67b4f80 | 10638 | eol_mnemonic_undecided = make_pure_c_string (":"); |
4ed46869 | 10639 | |
29208e82 | 10640 | DEFVAR_LISP ("enable-character-translation", Venable_character_translation, |
df7492f9 KH |
10641 | doc: /* |
10642 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 10643 | Venable_character_translation = Qt; |
bdd9fb48 | 10644 | |
f967223b | 10645 | DEFVAR_LISP ("standard-translation-table-for-decode", |
29208e82 | 10646 | Vstandard_translation_table_for_decode, |
48b0f3ae | 10647 | doc: /* Table for translating characters while decoding. */); |
f967223b | 10648 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 10649 | |
f967223b | 10650 | DEFVAR_LISP ("standard-translation-table-for-encode", |
29208e82 | 10651 | Vstandard_translation_table_for_encode, |
48b0f3ae | 10652 | doc: /* Table for translating characters while encoding. */); |
f967223b | 10653 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 10654 | |
29208e82 | 10655 | DEFVAR_LISP ("charset-revision-table", Vcharset_revision_table, |
48b0f3ae PJ |
10656 | doc: /* Alist of charsets vs revision numbers. |
10657 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
10658 | designate it with the escape sequence identifying revision (cdr part |
10659 | of the element). */); | |
10660 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
10661 | |
10662 | DEFVAR_LISP ("default-process-coding-system", | |
29208e82 | 10663 | Vdefault_process_coding_system, |
48b0f3ae PJ |
10664 | doc: /* Cons of coding systems used for process I/O by default. |
10665 | The car part is used for decoding a process output, | |
10666 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 10667 | Vdefault_process_coding_system = Qnil; |
c4825358 | 10668 | |
29208e82 | 10669 | DEFVAR_LISP ("latin-extra-code-table", Vlatin_extra_code_table, |
df7492f9 KH |
10670 | doc: /* |
10671 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
10672 | This is a vector of length 256. |
10673 | If Nth element is non-nil, the existence of code N in a file | |
10674 | \(or output of subprocess) doesn't prevent it to be detected as | |
10675 | a coding system of ISO 2022 variant which has a flag | |
10676 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
10677 | or reading output of a subprocess. | |
446dcd75 | 10678 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 10679 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
10680 | |
10681 | DEFVAR_LISP ("select-safe-coding-system-function", | |
29208e82 | 10682 | Vselect_safe_coding_system_function, |
df7492f9 KH |
10683 | doc: /* |
10684 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
10685 | |
10686 | If set, this function is called to force a user to select a proper | |
10687 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
10688 | coding system used in each operation can't encode the text. The |
10689 | function should take care that the buffer is not modified while | |
10690 | the coding system is being selected. | |
48b0f3ae PJ |
10691 | |
10692 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
10693 | Vselect_safe_coding_system_function = Qnil; |
10694 | ||
5d5bf4d8 | 10695 | DEFVAR_BOOL ("coding-system-require-warning", |
29208e82 | 10696 | coding_system_require_warning, |
5d5bf4d8 | 10697 | doc: /* Internal use only. |
6b89e3aa KH |
10698 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
10699 | called even if `coding-system-for-write' is non-nil. The command | |
10700 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
10701 | coding_system_require_warning = 0; |
10702 | ||
10703 | ||
22ab2303 | 10704 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
29208e82 | 10705 | inhibit_iso_escape_detection, |
df7492f9 | 10706 | doc: /* |
97b1b294 | 10707 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 10708 | |
97b1b294 EZ |
10709 | When Emacs reads text, it tries to detect how the text is encoded. |
10710 | This code detection is sensitive to escape sequences. If Emacs sees | |
10711 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
10712 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
10713 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
10714 | |
10715 | However, there may be a case that you want to read escape sequences in | |
10716 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
10717 | Then the code detection will ignore any escape sequences, and no text is |
10718 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
10719 | escape sequences become visible in a buffer. |
10720 | ||
10721 | The default value is nil, and it is strongly recommended not to change | |
10722 | it. That is because many Emacs Lisp source files that contain | |
10723 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
10724 | in Emacs's distribution, and they won't be decoded correctly on | |
10725 | reading if you suppress escape sequence detection. | |
10726 | ||
10727 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 10728 | to explicitly specify some coding system that doesn't use ISO-2022 |
48b0f3ae | 10729 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 10730 | inhibit_iso_escape_detection = 0; |
002fdb44 | 10731 | |
97b1b294 | 10732 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
29208e82 | 10733 | inhibit_null_byte_detection, |
97b1b294 EZ |
10734 | doc: /* If non-nil, Emacs ignores null bytes on code detection. |
10735 | By default, Emacs treats it as binary data, and does not attempt to | |
10736 | decode it. The effect is as if you specified `no-conversion' for | |
10737 | reading that text. | |
10738 | ||
10739 | Set this to non-nil when a regular text happens to include null bytes. | |
10740 | Examples are Index nodes of Info files and null-byte delimited output | |
10741 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
10742 | decode text as usual. */); | |
10743 | inhibit_null_byte_detection = 0; | |
10744 | ||
29208e82 | 10745 | DEFVAR_LISP ("translation-table-for-input", Vtranslation_table_for_input, |
15c8f9d1 | 10746 | doc: /* Char table for translating self-inserting characters. |
446dcd75 | 10747 | This is applied to the result of input methods, not their input. |
8434d0b8 EZ |
10748 | See also `keyboard-translate-table'. |
10749 | ||
10750 | Use of this variable for character code unification was rendered | |
10751 | obsolete in Emacs 23.1 and later, since Unicode is now the basis of | |
10752 | internal character representation. */); | |
002fdb44 | 10753 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 10754 | |
2c78b7e1 KH |
10755 | { |
10756 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 10757 | Lisp_Object plist[16]; |
2c78b7e1 KH |
10758 | int i; |
10759 | ||
10760 | for (i = 0; i < coding_arg_max; i++) | |
10761 | args[i] = Qnil; | |
10762 | ||
d67b4f80 | 10763 | plist[0] = intern_c_string (":name"); |
2c78b7e1 | 10764 | plist[1] = args[coding_arg_name] = Qno_conversion; |
d67b4f80 | 10765 | plist[2] = intern_c_string (":mnemonic"); |
2c78b7e1 | 10766 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); |
d67b4f80 | 10767 | plist[4] = intern_c_string (":coding-type"); |
2c78b7e1 | 10768 | plist[5] = args[coding_arg_coding_type] = Qraw_text; |
d67b4f80 | 10769 | plist[6] = intern_c_string (":ascii-compatible-p"); |
2c78b7e1 | 10770 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; |
d67b4f80 | 10771 | plist[8] = intern_c_string (":default-char"); |
2c78b7e1 | 10772 | plist[9] = args[coding_arg_default_char] = make_number (0); |
d67b4f80 | 10773 | plist[10] = intern_c_string (":for-unibyte"); |
8f924df7 | 10774 | plist[11] = args[coding_arg_for_unibyte] = Qt; |
d67b4f80 DN |
10775 | plist[12] = intern_c_string (":docstring"); |
10776 | plist[13] = make_pure_c_string ("Do no conversion.\n\ | |
2c78b7e1 KH |
10777 | \n\ |
10778 | When you visit a file with this coding, the file is read into a\n\ | |
10779 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
10780 | character."); | |
d67b4f80 | 10781 | plist[14] = intern_c_string (":eol-type"); |
8f924df7 KH |
10782 | plist[15] = args[coding_arg_eol_type] = Qunix; |
10783 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 10784 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
10785 | |
10786 | plist[1] = args[coding_arg_name] = Qundecided; | |
10787 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
10788 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
10789 | /* This is already set. | |
35befdaa | 10790 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
d67b4f80 | 10791 | plist[8] = intern_c_string (":charset-list"); |
ae6f73fa KH |
10792 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); |
10793 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
d67b4f80 | 10794 | plist[13] = make_pure_c_string ("No conversion on encoding, automatic conversion on decoding."); |
ae6f73fa KH |
10795 | plist[15] = args[coding_arg_eol_type] = Qnil; |
10796 | args[coding_arg_plist] = Flist (16, plist); | |
10797 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
10798 | } |
10799 | ||
2c78b7e1 | 10800 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
10801 | |
10802 | { | |
10803 | int i; | |
10804 | ||
10805 | for (i = 0; i < coding_category_max; i++) | |
10806 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
10807 | } | |
1a4990fb | 10808 | #if defined (DOS_NT) |
fcbcfb64 KH |
10809 | system_eol_type = Qdos; |
10810 | #else | |
10811 | system_eol_type = Qunix; | |
10812 | #endif | |
10813 | staticpro (&system_eol_type); | |
4ed46869 KH |
10814 | } |
10815 | ||
68c45bf0 | 10816 | char * |
971de7fb | 10817 | emacs_strerror (int error_number) |
68c45bf0 PE |
10818 | { |
10819 | char *str; | |
10820 | ||
ca9c0567 | 10821 | synchronize_system_messages_locale (); |
68c45bf0 PE |
10822 | str = strerror (error_number); |
10823 | ||
10824 | if (! NILP (Vlocale_coding_system)) | |
10825 | { | |
10826 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
10827 | Vlocale_coding_system, | |
10828 | 0); | |
51b59d79 | 10829 | str = SSDATA (dec); |
68c45bf0 PE |
10830 | } |
10831 | ||
10832 | return str; | |
10833 | } | |
10834 | ||
4ed46869 | 10835 | #endif /* emacs */ |