Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
ab422c4d | 2 | Copyright (C) 2001-2013 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 | |
34809aa6 EZ |
58 | In Emacs Lisp, a coding system is represented by a Lisp symbol. On |
59 | the 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 | |
f10fe38f | 150 | Return true if the byte sequence conforms to XXX. |
df7492f9 KH |
151 | |
152 | Below is the template of these functions. */ | |
153 | ||
4ed46869 | 154 | #if 0 |
f10fe38f | 155 | static bool |
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; | |
f10fe38f | 161 | bool multibytep = coding->src_multibyte; |
d311d28c | 162 | ptrdiff_t 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; | |
f10fe38f | 215 | bool multibytep = coding->src_multibyte; |
df7492f9 KH |
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 | { |
f10fe38f | 263 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
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_; | |
d311d28c | 269 | ptrdiff_t produced_chars = 0; |
df7492f9 KH |
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 KH |
287 | #include <stdio.h> |
288 | ||
819e2da9 DC |
289 | #ifdef HAVE_WCHAR_H |
290 | #include <wchar.h> | |
291 | #endif /* HAVE_WCHAR_H */ | |
292 | ||
4ed46869 | 293 | #include "lisp.h" |
df7492f9 | 294 | #include "character.h" |
e5560ff7 | 295 | #include "buffer.h" |
4ed46869 KH |
296 | #include "charset.h" |
297 | #include "ccl.h" | |
df7492f9 | 298 | #include "composite.h" |
4ed46869 KH |
299 | #include "coding.h" |
300 | #include "window.h" | |
b8299c66 KL |
301 | #include "frame.h" |
302 | #include "termhooks.h" | |
4ed46869 | 303 | |
df7492f9 | 304 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 305 | |
955cbe7b PE |
306 | static Lisp_Object Qcoding_system, Qeol_type; |
307 | static Lisp_Object Qcoding_aliases; | |
84cc1ab6 PE |
308 | Lisp_Object Qunix, Qdos; |
309 | static Lisp_Object Qmac; | |
4ed46869 | 310 | Lisp_Object Qbuffer_file_coding_system; |
955cbe7b PE |
311 | static Lisp_Object Qpost_read_conversion, Qpre_write_conversion; |
312 | static Lisp_Object Qdefault_char; | |
27901516 | 313 | Lisp_Object Qno_conversion, Qundecided; |
955cbe7b PE |
314 | Lisp_Object Qcharset, Qutf_8; |
315 | static Lisp_Object Qiso_2022; | |
316 | static Lisp_Object Qutf_16, Qshift_jis, Qbig5; | |
317 | static Lisp_Object Qbig, Qlittle; | |
318 | static Lisp_Object Qcoding_system_history; | |
319 | static Lisp_Object Qvalid_codes; | |
320 | static Lisp_Object QCcategory, QCmnemonic, QCdefault_char; | |
321 | static Lisp_Object QCdecode_translation_table, QCencode_translation_table; | |
322 | static Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
323 | static Lisp_Object QCascii_compatible_p; | |
4ed46869 | 324 | |
387f6ba5 | 325 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 | 326 | Lisp_Object Qstart_process, Qopen_network_stream; |
955cbe7b | 327 | static Lisp_Object Qtarget_idx; |
4ed46869 | 328 | |
1af1a51a | 329 | static Lisp_Object Qinsufficient_source, Qinvalid_source, Qinterrupted; |
065e3595 | 330 | |
44e8490d KH |
331 | /* If a symbol has this property, evaluate the value to define the |
332 | symbol as a coding system. */ | |
333 | static Lisp_Object Qcoding_system_define_form; | |
334 | ||
fcbcfb64 KH |
335 | /* Format of end-of-line decided by system. This is Qunix on |
336 | Unix and Mac, Qdos on DOS/Windows. | |
337 | This has an effect only for external encoding (i.e. for output to | |
338 | file and process), not for in-buffer or Lisp string encoding. */ | |
339 | static Lisp_Object system_eol_type; | |
340 | ||
4ed46869 KH |
341 | #ifdef emacs |
342 | ||
4608c386 | 343 | Lisp_Object Qcoding_system_p, Qcoding_system_error; |
4ed46869 | 344 | |
d46c5b12 KH |
345 | /* Coding system emacs-mule and raw-text are for converting only |
346 | end-of-line format. */ | |
347 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 348 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 349 | |
53372c27 | 350 | #if defined (WINDOWSNT) || defined (CYGWIN) |
ba116008 DC |
351 | static Lisp_Object Qutf_16le; |
352 | #endif | |
353 | ||
4ed46869 KH |
354 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
355 | routines by the following three variables. */ | |
c4825358 KH |
356 | /* Coding system to be used to encode text for terminal display when |
357 | terminal coding system is nil. */ | |
358 | struct coding_system safe_terminal_coding; | |
359 | ||
4ed46869 KH |
360 | #endif /* emacs */ |
361 | ||
f967223b KH |
362 | Lisp_Object Qtranslation_table; |
363 | Lisp_Object Qtranslation_table_id; | |
955cbe7b PE |
364 | static Lisp_Object Qtranslation_table_for_decode; |
365 | static Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 | 366 | |
df7492f9 | 367 | /* Two special coding systems. */ |
74ab6df5 PE |
368 | static Lisp_Object Vsjis_coding_system; |
369 | static Lisp_Object Vbig5_coding_system; | |
df7492f9 | 370 | |
df7492f9 KH |
371 | /* ISO2022 section */ |
372 | ||
373 | #define CODING_ISO_INITIAL(coding, reg) \ | |
374 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
375 | coding_attr_iso_initial), \ | |
376 | reg))) | |
377 | ||
378 | ||
1b3b981b AS |
379 | #define CODING_ISO_REQUEST(coding, charset_id) \ |
380 | (((charset_id) <= (coding)->max_charset_id \ | |
381 | ? ((coding)->safe_charsets[charset_id] != 255 \ | |
382 | ? (coding)->safe_charsets[charset_id] \ | |
383 | : -1) \ | |
df7492f9 KH |
384 | : -1)) |
385 | ||
386 | ||
387 | #define CODING_ISO_FLAGS(coding) \ | |
388 | ((coding)->spec.iso_2022.flags) | |
389 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
390 | ((coding)->spec.iso_2022.current_designation[reg]) | |
391 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
392 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
393 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
394 | ((coding)->spec.iso_2022.single_shifting) | |
395 | #define CODING_ISO_BOL(coding) \ | |
396 | ((coding)->spec.iso_2022.bol) | |
397 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
398 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
e951386e KH |
399 | #define CODING_ISO_CMP_STATUS(coding) \ |
400 | (&(coding)->spec.iso_2022.cmp_status) | |
401 | #define CODING_ISO_EXTSEGMENT_LEN(coding) \ | |
402 | ((coding)->spec.iso_2022.ctext_extended_segment_len) | |
403 | #define CODING_ISO_EMBEDDED_UTF_8(coding) \ | |
404 | ((coding)->spec.iso_2022.embedded_utf_8) | |
df7492f9 KH |
405 | |
406 | /* Control characters of ISO2022. */ | |
407 | /* code */ /* function */ | |
df7492f9 KH |
408 | #define ISO_CODE_SO 0x0E /* shift-out */ |
409 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
410 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
411 | #define ISO_CODE_ESC 0x1B /* escape */ | |
412 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
413 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
414 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
415 | ||
416 | /* All code (1-byte) of ISO2022 is classified into one of the | |
417 | followings. */ | |
418 | enum iso_code_class_type | |
419 | { | |
420 | ISO_control_0, /* Control codes in the range | |
421 | 0x00..0x1F and 0x7F, except for the | |
422 | following 5 codes. */ | |
df7492f9 KH |
423 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
424 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
425 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
a0d7415f | 426 | ISO_escape, /* ISO_CODE_ESC (0x1B) */ |
df7492f9 KH |
427 | ISO_control_1, /* Control codes in the range |
428 | 0x80..0x9F, except for the | |
429 | following 3 codes. */ | |
430 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
431 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
432 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
433 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
434 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
435 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
436 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
437 | }; | |
05e6f5dc | 438 | |
df7492f9 KH |
439 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
440 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 441 | |
df7492f9 KH |
442 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
443 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
444 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 445 | |
df7492f9 KH |
446 | /* If set, reset graphic planes and registers at end-of-line to the |
447 | initial state. */ | |
448 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 449 | |
df7492f9 KH |
450 | /* If set, reset graphic planes and registers before any control |
451 | characters to the initial state. */ | |
452 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 453 | |
df7492f9 KH |
454 | /* If set, encode by 7-bit environment. */ |
455 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 456 | |
df7492f9 KH |
457 | /* If set, use locking-shift function. */ |
458 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 459 | |
df7492f9 KH |
460 | /* If set, use single-shift function. Overwrite |
461 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
462 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 463 | |
df7492f9 KH |
464 | /* If set, use designation escape sequence. */ |
465 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 466 | |
df7492f9 KH |
467 | /* If set, produce revision number sequence. */ |
468 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 469 | |
df7492f9 KH |
470 | /* If set, produce ISO6429's direction specifying sequence. */ |
471 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 472 | |
df7492f9 KH |
473 | /* If set, assume designation states are reset at beginning of line on |
474 | output. */ | |
475 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 476 | |
df7492f9 KH |
477 | /* If set, designation sequence should be placed at beginning of line |
478 | on output. */ | |
479 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 480 | |
ad1746f5 | 481 | /* If set, do not encode unsafe characters on output. */ |
df7492f9 | 482 | #define CODING_ISO_FLAG_SAFE 0x0800 |
aa72b389 | 483 | |
df7492f9 KH |
484 | /* If set, extra latin codes (128..159) are accepted as a valid code |
485 | on input. */ | |
486 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 487 | |
df7492f9 | 488 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 489 | |
5f58e762 | 490 | /* #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 */ |
aa72b389 | 491 | |
bf16eb23 | 492 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 493 | |
bf16eb23 | 494 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 495 | |
bf16eb23 | 496 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 497 | |
df7492f9 KH |
498 | /* A character to be produced on output if encoding of the original |
499 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
500 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 501 | |
a470d443 KH |
502 | /* UTF-8 section */ |
503 | #define CODING_UTF_8_BOM(coding) \ | |
504 | ((coding)->spec.utf_8_bom) | |
4ed46869 | 505 | |
df7492f9 KH |
506 | /* UTF-16 section */ |
507 | #define CODING_UTF_16_BOM(coding) \ | |
508 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 509 | |
df7492f9 KH |
510 | #define CODING_UTF_16_ENDIAN(coding) \ |
511 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 512 | |
df7492f9 KH |
513 | #define CODING_UTF_16_SURROGATE(coding) \ |
514 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 515 | |
4ed46869 | 516 | |
df7492f9 KH |
517 | /* CCL section */ |
518 | #define CODING_CCL_DECODER(coding) \ | |
519 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
520 | #define CODING_CCL_ENCODER(coding) \ | |
521 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
522 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 523 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 524 | |
5a936b46 | 525 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 526 | |
df7492f9 KH |
527 | enum coding_category |
528 | { | |
529 | coding_category_iso_7, | |
530 | coding_category_iso_7_tight, | |
531 | coding_category_iso_8_1, | |
532 | coding_category_iso_8_2, | |
533 | coding_category_iso_7_else, | |
534 | coding_category_iso_8_else, | |
a470d443 KH |
535 | coding_category_utf_8_auto, |
536 | coding_category_utf_8_nosig, | |
537 | coding_category_utf_8_sig, | |
df7492f9 KH |
538 | coding_category_utf_16_auto, |
539 | coding_category_utf_16_be, | |
540 | coding_category_utf_16_le, | |
541 | coding_category_utf_16_be_nosig, | |
542 | coding_category_utf_16_le_nosig, | |
543 | coding_category_charset, | |
544 | coding_category_sjis, | |
545 | coding_category_big5, | |
546 | coding_category_ccl, | |
547 | coding_category_emacs_mule, | |
548 | /* All above are targets of code detection. */ | |
549 | coding_category_raw_text, | |
550 | coding_category_undecided, | |
551 | coding_category_max | |
552 | }; | |
553 | ||
554 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
555 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
556 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
557 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
558 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
559 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
560 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
a470d443 KH |
561 | #define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto) |
562 | #define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig) | |
563 | #define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig) | |
b49a1807 | 564 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
565 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
566 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
567 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
568 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
569 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
570 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
571 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
572 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
573 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 574 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
575 | |
576 | /* This value is returned if detect_coding_mask () find nothing other | |
577 | than ASCII characters. */ | |
578 | #define CATEGORY_MASK_ANY \ | |
579 | (CATEGORY_MASK_ISO_7 \ | |
580 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
581 | | CATEGORY_MASK_ISO_8_1 \ | |
582 | | CATEGORY_MASK_ISO_8_2 \ | |
583 | | CATEGORY_MASK_ISO_7_ELSE \ | |
584 | | CATEGORY_MASK_ISO_8_ELSE \ | |
a470d443 KH |
585 | | CATEGORY_MASK_UTF_8_AUTO \ |
586 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
587 | | CATEGORY_MASK_UTF_8_SIG \ | |
2f3cbb32 | 588 | | CATEGORY_MASK_UTF_16_AUTO \ |
df7492f9 KH |
589 | | CATEGORY_MASK_UTF_16_BE \ |
590 | | CATEGORY_MASK_UTF_16_LE \ | |
591 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
592 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
593 | | CATEGORY_MASK_CHARSET \ | |
594 | | CATEGORY_MASK_SJIS \ | |
595 | | CATEGORY_MASK_BIG5 \ | |
596 | | CATEGORY_MASK_CCL \ | |
597 | | CATEGORY_MASK_EMACS_MULE) | |
598 | ||
599 | ||
600 | #define CATEGORY_MASK_ISO_7BIT \ | |
601 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
602 | ||
603 | #define CATEGORY_MASK_ISO_8BIT \ | |
604 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
605 | ||
606 | #define CATEGORY_MASK_ISO_ELSE \ | |
607 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
608 | ||
609 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
610 | (CATEGORY_MASK_ISO_7 \ | |
611 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
612 | | CATEGORY_MASK_ISO_7_ELSE \ | |
613 | | CATEGORY_MASK_ISO_8_ELSE) | |
614 | ||
615 | #define CATEGORY_MASK_ISO \ | |
616 | ( CATEGORY_MASK_ISO_7BIT \ | |
617 | | CATEGORY_MASK_ISO_8BIT \ | |
618 | | CATEGORY_MASK_ISO_ELSE) | |
619 | ||
620 | #define CATEGORY_MASK_UTF_16 \ | |
2f3cbb32 KH |
621 | (CATEGORY_MASK_UTF_16_AUTO \ |
622 | | CATEGORY_MASK_UTF_16_BE \ | |
df7492f9 KH |
623 | | CATEGORY_MASK_UTF_16_LE \ |
624 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
625 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
626 | ||
a470d443 KH |
627 | #define CATEGORY_MASK_UTF_8 \ |
628 | (CATEGORY_MASK_UTF_8_AUTO \ | |
629 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
630 | | CATEGORY_MASK_UTF_8_SIG) | |
df7492f9 | 631 | |
df7492f9 | 632 | /* Table of coding categories (Lisp symbols). This variable is for |
ad1746f5 | 633 | internal use only. */ |
df7492f9 KH |
634 | static Lisp_Object Vcoding_category_table; |
635 | ||
636 | /* Table of coding-categories ordered by priority. */ | |
637 | static enum coding_category coding_priorities[coding_category_max]; | |
638 | ||
639 | /* Nth element is a coding context for the coding system bound to the | |
640 | Nth coding category. */ | |
641 | static struct coding_system coding_categories[coding_category_max]; | |
642 | ||
df7492f9 KH |
643 | /*** Commonly used macros and functions ***/ |
644 | ||
645 | #ifndef min | |
646 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
647 | #endif | |
648 | #ifndef max | |
649 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
650 | #endif | |
4ed46869 | 651 | |
9c90cc06 PE |
652 | /* Encode a flag that can be nil, something else, or t as -1, 0, 1. */ |
653 | ||
654 | static int | |
655 | encode_inhibit_flag (Lisp_Object flag) | |
656 | { | |
657 | return NILP (flag) ? -1 : EQ (flag, Qt); | |
658 | } | |
659 | ||
660 | /* True if the value of ENCODED_FLAG says a flag should be treated as set. | |
661 | 1 means yes, -1 means no, 0 means ask the user variable VAR. */ | |
662 | ||
663 | static bool | |
664 | inhibit_flag (int encoded_flag, bool var) | |
665 | { | |
666 | return 0 < encoded_flag + var; | |
667 | } | |
668 | ||
24a73b0a KH |
669 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
670 | do { \ | |
671 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
672 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 673 | } while (0) |
4ed46869 | 674 | |
84575e67 PE |
675 | static void |
676 | CHECK_NATNUM_CAR (Lisp_Object x) | |
677 | { | |
678 | Lisp_Object tmp = XCAR (x); | |
679 | CHECK_NATNUM (tmp); | |
680 | XSETCAR (x, tmp); | |
681 | } | |
682 | ||
683 | static void | |
684 | CHECK_NATNUM_CDR (Lisp_Object x) | |
685 | { | |
686 | Lisp_Object tmp = XCDR (x); | |
687 | CHECK_NATNUM (tmp); | |
688 | XSETCDR (x, tmp); | |
689 | } | |
690 | ||
4ed46869 | 691 | |
df7492f9 KH |
692 | /* Safely get one byte from the source text pointed by SRC which ends |
693 | at SRC_END, and set C to that byte. If there are not enough bytes | |
f10fe38f PE |
694 | in the source, it jumps to 'no_more_source'. If MULTIBYTEP, |
695 | and a multibyte character is found at SRC, set C to the | |
065e3595 KH |
696 | negative value of the character code. The caller should declare |
697 | and set these variables appropriately in advance: | |
698 | src, src_end, multibytep */ | |
aa72b389 | 699 | |
065e3595 KH |
700 | #define ONE_MORE_BYTE(c) \ |
701 | do { \ | |
702 | if (src == src_end) \ | |
703 | { \ | |
704 | if (src_base < src) \ | |
705 | record_conversion_result \ | |
706 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
707 | goto no_more_source; \ | |
708 | } \ | |
709 | c = *src++; \ | |
710 | if (multibytep && (c & 0x80)) \ | |
711 | { \ | |
712 | if ((c & 0xFE) == 0xC0) \ | |
713 | c = ((c & 1) << 6) | *src++; \ | |
714 | else \ | |
715 | { \ | |
35befdaa KH |
716 | src--; \ |
717 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
718 | record_conversion_result \ |
719 | (coding, CODING_RESULT_INVALID_SRC); \ | |
720 | } \ | |
721 | } \ | |
722 | consumed_chars++; \ | |
aa72b389 KH |
723 | } while (0) |
724 | ||
f56a4450 | 725 | /* Safely get two bytes from the source text pointed by SRC which ends |
220eeac9 KH |
726 | at SRC_END, and set C1 and C2 to those bytes while skipping the |
727 | heading multibyte characters. If there are not enough bytes in the | |
f10fe38f | 728 | source, it jumps to 'no_more_source'. If MULTIBYTEP and |
220eeac9 KH |
729 | a multibyte character is found for C2, set C2 to the negative value |
730 | of the character code. The caller should declare and set these | |
731 | variables appropriately in advance: | |
f56a4450 KH |
732 | src, src_end, multibytep |
733 | It is intended that this macro is used in detect_coding_utf_16. */ | |
734 | ||
220eeac9 KH |
735 | #define TWO_MORE_BYTES(c1, c2) \ |
736 | do { \ | |
737 | do { \ | |
738 | if (src == src_end) \ | |
739 | goto no_more_source; \ | |
740 | c1 = *src++; \ | |
741 | if (multibytep && (c1 & 0x80)) \ | |
742 | { \ | |
743 | if ((c1 & 0xFE) == 0xC0) \ | |
744 | c1 = ((c1 & 1) << 6) | *src++; \ | |
745 | else \ | |
746 | { \ | |
747 | src += BYTES_BY_CHAR_HEAD (c1) - 1; \ | |
748 | c1 = -1; \ | |
749 | } \ | |
750 | } \ | |
751 | } while (c1 < 0); \ | |
752 | if (src == src_end) \ | |
753 | goto no_more_source; \ | |
754 | c2 = *src++; \ | |
755 | if (multibytep && (c2 & 0x80)) \ | |
756 | { \ | |
757 | if ((c2 & 0xFE) == 0xC0) \ | |
758 | c2 = ((c2 & 1) << 6) | *src++; \ | |
759 | else \ | |
760 | c2 = -1; \ | |
761 | } \ | |
f56a4450 KH |
762 | } while (0) |
763 | ||
aa72b389 | 764 | |
df7492f9 KH |
765 | /* Store a byte C in the place pointed by DST and increment DST to the |
766 | next free point, and increment PRODUCED_CHARS. The caller should | |
767 | assure that C is 0..127, and declare and set the variable `dst' | |
768 | appropriately in advance. | |
769 | */ | |
aa72b389 KH |
770 | |
771 | ||
df7492f9 KH |
772 | #define EMIT_ONE_ASCII_BYTE(c) \ |
773 | do { \ | |
774 | produced_chars++; \ | |
775 | *dst++ = (c); \ | |
b6871cc7 | 776 | } while (0) |
aa72b389 KH |
777 | |
778 | ||
ad1746f5 | 779 | /* Like EMIT_ONE_ASCII_BYTE but store two bytes; C1 and C2. */ |
aa72b389 | 780 | |
df7492f9 KH |
781 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
782 | do { \ | |
783 | produced_chars += 2; \ | |
784 | *dst++ = (c1), *dst++ = (c2); \ | |
785 | } while (0) | |
aa72b389 KH |
786 | |
787 | ||
df7492f9 | 788 | /* Store a byte C in the place pointed by DST and increment DST to the |
f10fe38f PE |
789 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP, |
790 | store in an appropriate multibyte form. The caller should | |
df7492f9 KH |
791 | declare and set the variables `dst' and `multibytep' appropriately |
792 | in advance. */ | |
793 | ||
794 | #define EMIT_ONE_BYTE(c) \ | |
795 | do { \ | |
796 | produced_chars++; \ | |
797 | if (multibytep) \ | |
798 | { \ | |
b25d760e | 799 | unsigned ch = (c); \ |
df7492f9 KH |
800 | if (ch >= 0x80) \ |
801 | ch = BYTE8_TO_CHAR (ch); \ | |
802 | CHAR_STRING_ADVANCE (ch, dst); \ | |
803 | } \ | |
804 | else \ | |
805 | *dst++ = (c); \ | |
aa72b389 | 806 | } while (0) |
aa72b389 | 807 | |
aa72b389 | 808 | |
df7492f9 | 809 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 810 | |
e19c3639 KH |
811 | #define EMIT_TWO_BYTES(c1, c2) \ |
812 | do { \ | |
813 | produced_chars += 2; \ | |
814 | if (multibytep) \ | |
815 | { \ | |
b25d760e | 816 | unsigned ch; \ |
e19c3639 KH |
817 | \ |
818 | ch = (c1); \ | |
819 | if (ch >= 0x80) \ | |
820 | ch = BYTE8_TO_CHAR (ch); \ | |
821 | CHAR_STRING_ADVANCE (ch, dst); \ | |
822 | ch = (c2); \ | |
823 | if (ch >= 0x80) \ | |
824 | ch = BYTE8_TO_CHAR (ch); \ | |
825 | CHAR_STRING_ADVANCE (ch, dst); \ | |
826 | } \ | |
827 | else \ | |
828 | { \ | |
829 | *dst++ = (c1); \ | |
830 | *dst++ = (c2); \ | |
831 | } \ | |
aa72b389 KH |
832 | } while (0) |
833 | ||
834 | ||
df7492f9 KH |
835 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
836 | do { \ | |
837 | EMIT_ONE_BYTE (c1); \ | |
838 | EMIT_TWO_BYTES (c2, c3); \ | |
839 | } while (0) | |
aa72b389 | 840 | |
aa72b389 | 841 | |
df7492f9 KH |
842 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
843 | do { \ | |
844 | EMIT_TWO_BYTES (c1, c2); \ | |
845 | EMIT_TWO_BYTES (c3, c4); \ | |
846 | } while (0) | |
aa72b389 | 847 | |
aa72b389 | 848 | |
065e3595 KH |
849 | static void |
850 | record_conversion_result (struct coding_system *coding, | |
851 | enum coding_result_code result) | |
852 | { | |
853 | coding->result = result; | |
854 | switch (result) | |
855 | { | |
856 | case CODING_RESULT_INSUFFICIENT_SRC: | |
857 | Vlast_code_conversion_error = Qinsufficient_source; | |
858 | break; | |
065e3595 KH |
859 | case CODING_RESULT_INVALID_SRC: |
860 | Vlast_code_conversion_error = Qinvalid_source; | |
861 | break; | |
862 | case CODING_RESULT_INTERRUPT: | |
863 | Vlast_code_conversion_error = Qinterrupted; | |
864 | break; | |
ebaf11b6 KH |
865 | case CODING_RESULT_INSUFFICIENT_DST: |
866 | /* Don't record this error in Vlast_code_conversion_error | |
867 | because it happens just temporarily and is resolved when the | |
868 | whole conversion is finished. */ | |
869 | break; | |
409ea3a1 AS |
870 | case CODING_RESULT_SUCCESS: |
871 | break; | |
35befdaa KH |
872 | default: |
873 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
874 | } |
875 | } | |
876 | ||
5eb05ea3 KH |
877 | /* These wrapper macros are used to preserve validity of pointers into |
878 | buffer text across calls to decode_char, encode_char, etc, which | |
879 | could cause relocation of buffers if it loads a charset map, | |
880 | because loading a charset map allocates large structures. */ | |
881 | ||
df7492f9 KH |
882 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
883 | do { \ | |
8f50130c | 884 | ptrdiff_t offset; \ |
5eb05ea3 | 885 | \ |
df7492f9 KH |
886 | charset_map_loaded = 0; \ |
887 | c = DECODE_CHAR (charset, code); \ | |
5eb05ea3 | 888 | if (charset_map_loaded \ |
c1892f11 | 889 | && (offset = coding_change_source (coding))) \ |
df7492f9 | 890 | { \ |
df7492f9 KH |
891 | src += offset; \ |
892 | src_base += offset; \ | |
893 | src_end += offset; \ | |
894 | } \ | |
aa72b389 KH |
895 | } while (0) |
896 | ||
5eb05ea3 KH |
897 | #define CODING_ENCODE_CHAR(coding, dst, dst_end, charset, c, code) \ |
898 | do { \ | |
8f50130c | 899 | ptrdiff_t offset; \ |
5eb05ea3 KH |
900 | \ |
901 | charset_map_loaded = 0; \ | |
902 | code = ENCODE_CHAR (charset, c); \ | |
903 | if (charset_map_loaded \ | |
c1892f11 | 904 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
905 | { \ |
906 | dst += offset; \ | |
907 | dst_end += offset; \ | |
908 | } \ | |
909 | } while (0) | |
910 | ||
911 | #define CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list, code_return, charset) \ | |
912 | do { \ | |
8f50130c | 913 | ptrdiff_t offset; \ |
5eb05ea3 KH |
914 | \ |
915 | charset_map_loaded = 0; \ | |
916 | charset = char_charset (c, charset_list, code_return); \ | |
917 | if (charset_map_loaded \ | |
c1892f11 | 918 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
919 | { \ |
920 | dst += offset; \ | |
921 | dst_end += offset; \ | |
922 | } \ | |
923 | } while (0) | |
924 | ||
925 | #define CODING_CHAR_CHARSET_P(coding, dst, dst_end, c, charset, result) \ | |
926 | do { \ | |
8f50130c | 927 | ptrdiff_t offset; \ |
5eb05ea3 KH |
928 | \ |
929 | charset_map_loaded = 0; \ | |
930 | result = CHAR_CHARSET_P (c, charset); \ | |
931 | if (charset_map_loaded \ | |
c1892f11 | 932 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
933 | { \ |
934 | dst += offset; \ | |
935 | dst_end += offset; \ | |
936 | } \ | |
937 | } while (0) | |
938 | ||
aa72b389 | 939 | |
119852e7 KH |
940 | /* If there are at least BYTES length of room at dst, allocate memory |
941 | for coding->destination and update dst and dst_end. We don't have | |
942 | to take care of coding->source which will be relocated. It is | |
943 | handled by calling coding_set_source in encode_coding. */ | |
944 | ||
df7492f9 KH |
945 | #define ASSURE_DESTINATION(bytes) \ |
946 | do { \ | |
947 | if (dst + (bytes) >= dst_end) \ | |
948 | { \ | |
d311d28c | 949 | ptrdiff_t more_bytes = charbuf_end - charbuf + (bytes); \ |
df7492f9 KH |
950 | \ |
951 | dst = alloc_destination (coding, more_bytes, dst); \ | |
952 | dst_end = coding->destination + coding->dst_bytes; \ | |
953 | } \ | |
954 | } while (0) | |
aa72b389 | 955 | |
aa72b389 | 956 | |
db274c7a | 957 | /* Store multibyte form of the character C in P, and advance P to the |
eedec3ee EZ |
958 | end of the multibyte form. This used to be like CHAR_STRING_ADVANCE |
959 | without ever calling MAYBE_UNIFY_CHAR, but nowadays we don't call | |
960 | MAYBE_UNIFY_CHAR in CHAR_STRING_ADVANCE. */ | |
db274c7a | 961 | |
eedec3ee | 962 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) CHAR_STRING_ADVANCE(c, p) |
db274c7a KH |
963 | |
964 | /* Return the character code of character whose multibyte form is at | |
eedec3ee EZ |
965 | P, and advance P to the end of the multibyte form. This used to be |
966 | like STRING_CHAR_ADVANCE without ever calling MAYBE_UNIFY_CHAR, but | |
967 | nowadays STRING_CHAR_ADVANCE doesn't call MAYBE_UNIFY_CHAR. */ | |
db274c7a | 968 | |
eedec3ee | 969 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) STRING_CHAR_ADVANCE(p) |
aa72b389 | 970 | |
c1892f11 | 971 | /* Set coding->source from coding->src_object. */ |
5eb05ea3 | 972 | |
c1892f11 | 973 | static void |
971de7fb | 974 | coding_set_source (struct coding_system *coding) |
aa72b389 | 975 | { |
df7492f9 KH |
976 | if (BUFFERP (coding->src_object)) |
977 | { | |
2cb26057 | 978 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 979 | |
df7492f9 | 980 | if (coding->src_pos < 0) |
2cb26057 | 981 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 982 | else |
2cb26057 | 983 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 984 | } |
df7492f9 | 985 | else if (STRINGP (coding->src_object)) |
aa72b389 | 986 | { |
8f924df7 | 987 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 988 | } |
df7492f9 | 989 | else |
f38b440c PE |
990 | { |
991 | /* Otherwise, the source is C string and is never relocated | |
992 | automatically. Thus we don't have to update anything. */ | |
993 | } | |
df7492f9 | 994 | } |
aa72b389 | 995 | |
5eb05ea3 | 996 | |
c1892f11 PE |
997 | /* Set coding->source from coding->src_object, and return how many |
998 | bytes coding->source was changed. */ | |
5eb05ea3 | 999 | |
8f50130c | 1000 | static ptrdiff_t |
c1892f11 | 1001 | coding_change_source (struct coding_system *coding) |
df7492f9 | 1002 | { |
c1892f11 PE |
1003 | const unsigned char *orig = coding->source; |
1004 | coding_set_source (coding); | |
1005 | return coding->source - orig; | |
1006 | } | |
1007 | ||
5eb05ea3 | 1008 | |
c1892f11 PE |
1009 | /* Set coding->destination from coding->dst_object. */ |
1010 | ||
1011 | static void | |
1012 | coding_set_destination (struct coding_system *coding) | |
1013 | { | |
df7492f9 | 1014 | if (BUFFERP (coding->dst_object)) |
aa72b389 | 1015 | { |
a0241d01 | 1016 | if (BUFFERP (coding->src_object) && coding->src_pos < 0) |
aa72b389 | 1017 | { |
13818c30 | 1018 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
1019 | coding->dst_bytes = (GAP_END_ADDR |
1020 | - (coding->src_bytes - coding->consumed) | |
1021 | - coding->destination); | |
aa72b389 | 1022 | } |
df7492f9 | 1023 | else |
28f67a95 KH |
1024 | { |
1025 | /* We are sure that coding->dst_pos_byte is before the gap | |
1026 | of the buffer. */ | |
1027 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 1028 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
1029 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
1030 | - coding->destination); | |
1031 | } | |
df7492f9 KH |
1032 | } |
1033 | else | |
f38b440c PE |
1034 | { |
1035 | /* Otherwise, the destination is C string and is never relocated | |
1036 | automatically. Thus we don't have to update anything. */ | |
1037 | } | |
c1892f11 PE |
1038 | } |
1039 | ||
1040 | ||
1041 | /* Set coding->destination from coding->dst_object, and return how | |
1042 | many bytes coding->destination was changed. */ | |
1043 | ||
1044 | static ptrdiff_t | |
1045 | coding_change_destination (struct coding_system *coding) | |
1046 | { | |
1047 | const unsigned char *orig = coding->destination; | |
1048 | coding_set_destination (coding); | |
5eb05ea3 | 1049 | return coding->destination - orig; |
df7492f9 KH |
1050 | } |
1051 | ||
1052 | ||
1053 | static void | |
d311d28c | 1054 | coding_alloc_by_realloc (struct coding_system *coding, ptrdiff_t bytes) |
df7492f9 | 1055 | { |
c9d624c6 | 1056 | if (STRING_BYTES_BOUND - coding->dst_bytes < bytes) |
d1f3d2af | 1057 | string_overflow (); |
38182d90 PE |
1058 | coding->destination = xrealloc (coding->destination, |
1059 | coding->dst_bytes + bytes); | |
df7492f9 KH |
1060 | coding->dst_bytes += bytes; |
1061 | } | |
1062 | ||
1063 | static void | |
cf84bb53 | 1064 | coding_alloc_by_making_gap (struct coding_system *coding, |
d311d28c | 1065 | ptrdiff_t gap_head_used, ptrdiff_t bytes) |
df7492f9 | 1066 | { |
db274c7a | 1067 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1068 | { |
db274c7a KH |
1069 | /* The gap may contain the produced data at the head and not-yet |
1070 | consumed data at the tail. To preserve those data, we at | |
1071 | first make the gap size to zero, then increase the gap | |
1072 | size. */ | |
d311d28c | 1073 | ptrdiff_t add = GAP_SIZE; |
db274c7a KH |
1074 | |
1075 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1076 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1077 | make_gap (bytes); |
1078 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1079 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1080 | } |
730fff51 | 1081 | else |
eefd7278 | 1082 | make_gap_1 (XBUFFER (coding->dst_object), bytes); |
df7492f9 | 1083 | } |
8f924df7 | 1084 | |
df7492f9 KH |
1085 | |
1086 | static unsigned char * | |
d311d28c | 1087 | alloc_destination (struct coding_system *coding, ptrdiff_t nbytes, |
cf84bb53 | 1088 | unsigned char *dst) |
df7492f9 | 1089 | { |
d311d28c | 1090 | ptrdiff_t offset = dst - coding->destination; |
df7492f9 KH |
1091 | |
1092 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1093 | { |
1094 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1095 | ||
1096 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1097 | } | |
aa72b389 | 1098 | else |
df7492f9 | 1099 | coding_alloc_by_realloc (coding, nbytes); |
df7492f9 KH |
1100 | coding_set_destination (coding); |
1101 | dst = coding->destination + offset; | |
1102 | return dst; | |
1103 | } | |
aa72b389 | 1104 | |
ff0dacd7 KH |
1105 | /** Macros for annotations. */ |
1106 | ||
ff0dacd7 KH |
1107 | /* An annotation data is stored in the array coding->charbuf in this |
1108 | format: | |
69a80ea3 | 1109 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1110 | LENGTH is the number of elements in the annotation. |
1111 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1112 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1113 | |
1114 | The format of the following elements depend on ANNOTATION_MASK. | |
1115 | ||
1116 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1117 | follows: | |
e951386e KH |
1118 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
1119 | ||
1120 | NBYTES is the number of bytes specified in the header part of | |
1121 | old-style emacs-mule encoding, or 0 for the other kind of | |
1122 | composition. | |
1123 | ||
ff0dacd7 | 1124 | METHOD is one of enum composition_method. |
e951386e | 1125 | |
ad1746f5 | 1126 | Optional COMPOSITION-COMPONENTS are characters and composition |
ff0dacd7 KH |
1127 | rules. |
1128 | ||
1129 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
e951386e KH |
1130 | follows. |
1131 | ||
1132 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | |
1133 | recover from an invalid annotation, and should be skipped by | |
1134 | produce_annotation. */ | |
1135 | ||
1136 | /* Maximum length of the header of annotation data. */ | |
1137 | #define MAX_ANNOTATION_LENGTH 5 | |
ff0dacd7 | 1138 | |
69a80ea3 | 1139 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1140 | do { \ |
1141 | *(buf)++ = -(len); \ | |
1142 | *(buf)++ = (mask); \ | |
69a80ea3 | 1143 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1144 | coding->annotated = 1; \ |
1145 | } while (0); | |
1146 | ||
e951386e | 1147 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
69a80ea3 | 1148 | do { \ |
e951386e KH |
1149 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
1150 | *buf++ = nbytes; \ | |
69a80ea3 | 1151 | *buf++ = method; \ |
ff0dacd7 KH |
1152 | } while (0) |
1153 | ||
1154 | ||
69a80ea3 KH |
1155 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1156 | do { \ | |
1157 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1158 | *buf++ = id; \ | |
ff0dacd7 KH |
1159 | } while (0) |
1160 | ||
e6d2f155 KH |
1161 | |
1162 | /* Bitmasks for coding->eol_seen. */ | |
1163 | ||
1164 | #define EOL_SEEN_NONE 0 | |
1165 | #define EOL_SEEN_LF 1 | |
1166 | #define EOL_SEEN_CR 2 | |
1167 | #define EOL_SEEN_CRLF 4 | |
1168 | ||
df7492f9 KH |
1169 | \f |
1170 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1171 | ||
1172 | ||
1173 | ||
1174 | \f | |
1175 | /*** 3. UTF-8 ***/ | |
1176 | ||
1177 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 1178 | Return true if a text is encoded in UTF-8. */ |
df7492f9 KH |
1179 | |
1180 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1181 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1182 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1183 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1184 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1185 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1186 | ||
a470d443 KH |
1187 | #define UTF_8_BOM_1 0xEF |
1188 | #define UTF_8_BOM_2 0xBB | |
1189 | #define UTF_8_BOM_3 0xBF | |
1190 | ||
e6d2f155 KH |
1191 | /* Unlike the other detect_coding_XXX, this function counts number of |
1192 | characters and check EOL format. */ | |
1193 | ||
f10fe38f | 1194 | static bool |
cf84bb53 JB |
1195 | detect_coding_utf_8 (struct coding_system *coding, |
1196 | struct coding_detection_info *detect_info) | |
df7492f9 | 1197 | { |
065e3595 | 1198 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1199 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 1200 | bool multibytep = coding->src_multibyte; |
d311d28c | 1201 | ptrdiff_t consumed_chars = 0; |
f10fe38f | 1202 | bool bom_found = 0; |
e6d2f155 KH |
1203 | int nchars = coding->head_ascii; |
1204 | int eol_seen = coding->eol_seen; | |
df7492f9 | 1205 | |
ff0dacd7 | 1206 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1207 | /* A coding system of this category is always ASCII compatible. */ |
e6d2f155 KH |
1208 | src += nchars; |
1209 | ||
1210 | if (src == coding->source /* BOM should be at the head. */ | |
1211 | && src + 3 < src_end /* BOM is 3-byte long. */ | |
1212 | && src[0] == UTF_8_BOM_1 | |
1213 | && src[1] == UTF_8_BOM_2 | |
1214 | && src[2] == UTF_8_BOM_3) | |
1215 | { | |
1216 | bom_found = 1; | |
1217 | src += 3; | |
1218 | nchars++; | |
1219 | } | |
df7492f9 KH |
1220 | |
1221 | while (1) | |
aa72b389 | 1222 | { |
df7492f9 | 1223 | int c, c1, c2, c3, c4; |
aa72b389 | 1224 | |
065e3595 | 1225 | src_base = src; |
df7492f9 | 1226 | ONE_MORE_BYTE (c); |
065e3595 | 1227 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
e6d2f155 KH |
1228 | { |
1229 | nchars++; | |
1230 | if (c == '\r') | |
1231 | { | |
1232 | if (src < src_end && *src == '\n') | |
1233 | { | |
1234 | eol_seen |= EOL_SEEN_CRLF; | |
1235 | src++; | |
1236 | nchars++; | |
1237 | } | |
1238 | else | |
1239 | eol_seen |= EOL_SEEN_CR; | |
1240 | } | |
1241 | else if (c == '\n') | |
1242 | eol_seen |= EOL_SEEN_LF; | |
1243 | continue; | |
1244 | } | |
df7492f9 | 1245 | ONE_MORE_BYTE (c1); |
065e3595 | 1246 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1247 | break; |
1248 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1249 | { |
e6d2f155 | 1250 | nchars++; |
df7492f9 | 1251 | continue; |
aa72b389 | 1252 | } |
df7492f9 | 1253 | ONE_MORE_BYTE (c2); |
065e3595 | 1254 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1255 | break; |
1256 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1257 | { |
e6d2f155 | 1258 | nchars++; |
df7492f9 | 1259 | continue; |
aa72b389 | 1260 | } |
df7492f9 | 1261 | ONE_MORE_BYTE (c3); |
065e3595 | 1262 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1263 | break; |
1264 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1265 | { |
e6d2f155 | 1266 | nchars++; |
df7492f9 KH |
1267 | continue; |
1268 | } | |
1269 | ONE_MORE_BYTE (c4); | |
065e3595 | 1270 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1271 | break; |
1272 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1273 | { | |
e6d2f155 | 1274 | nchars++; |
df7492f9 KH |
1275 | continue; |
1276 | } | |
1277 | break; | |
aa72b389 | 1278 | } |
ff0dacd7 | 1279 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1280 | return 0; |
aa72b389 | 1281 | |
df7492f9 | 1282 | no_more_source: |
065e3595 | 1283 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1284 | { |
ff0dacd7 | 1285 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1286 | return 0; |
aa72b389 | 1287 | } |
a470d443 KH |
1288 | if (bom_found) |
1289 | { | |
1290 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
e6d2f155 | 1291 | detect_info->found |= CATEGORY_MASK_UTF_8_AUTO | CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; |
a470d443 KH |
1292 | } |
1293 | else | |
1294 | { | |
1295 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
e6d2f155 KH |
1296 | if (nchars < src_end - coding->source) |
1297 | /* The found characters are less than source bytes, which | |
1298 | means that we found a valid non-ASCII characters. */ | |
1299 | detect_info->found |= CATEGORY_MASK_UTF_8_AUTO | CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1300 | } |
e6d2f155 | 1301 | coding->detected_utf8_chars = nchars; |
ff0dacd7 | 1302 | return 1; |
aa72b389 KH |
1303 | } |
1304 | ||
4ed46869 | 1305 | |
b73bfc1c | 1306 | static void |
971de7fb | 1307 | decode_coding_utf_8 (struct coding_system *coding) |
b73bfc1c | 1308 | { |
8f924df7 KH |
1309 | const unsigned char *src = coding->source + coding->consumed; |
1310 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1311 | const unsigned char *src_base; | |
69a80ea3 KH |
1312 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1313 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
d311d28c | 1314 | ptrdiff_t consumed_chars = 0, consumed_chars_base = 0; |
f10fe38f | 1315 | bool multibytep = coding->src_multibyte; |
a470d443 | 1316 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
f10fe38f PE |
1317 | bool eol_dos |
1318 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1319 | int byte_after_cr = -1; |
4ed46869 | 1320 | |
a470d443 KH |
1321 | if (bom != utf_without_bom) |
1322 | { | |
1323 | int c1, c2, c3; | |
1324 | ||
1325 | src_base = src; | |
1326 | ONE_MORE_BYTE (c1); | |
1327 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1328 | src = src_base; | |
1329 | else | |
1330 | { | |
159bd5a2 | 1331 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1332 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1333 | src = src_base; | |
1334 | else | |
1335 | { | |
159bd5a2 | 1336 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1337 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1338 | src = src_base; | |
1339 | else | |
1340 | { | |
1341 | if ((c1 != UTF_8_BOM_1) | |
1342 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1343 | src = src_base; | |
1344 | else | |
1345 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1346 | } | |
1347 | } | |
1348 | } | |
1349 | } | |
1350 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1351 | ||
df7492f9 | 1352 | while (1) |
b73bfc1c | 1353 | { |
df7492f9 | 1354 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1355 | |
df7492f9 KH |
1356 | src_base = src; |
1357 | consumed_chars_base = consumed_chars; | |
4af310db | 1358 | |
df7492f9 | 1359 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1360 | { |
1361 | if (byte_after_cr >= 0) | |
1362 | src_base--; | |
1363 | break; | |
1364 | } | |
df7492f9 | 1365 | |
119852e7 KH |
1366 | if (byte_after_cr >= 0) |
1367 | c1 = byte_after_cr, byte_after_cr = -1; | |
1368 | else | |
1369 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1370 | if (c1 < 0) |
1371 | { | |
1372 | c = - c1; | |
1373 | } | |
1a4990fb | 1374 | else if (UTF_8_1_OCTET_P (c1)) |
df7492f9 | 1375 | { |
2735d060 | 1376 | if (eol_dos && c1 == '\r') |
119852e7 | 1377 | ONE_MORE_BYTE (byte_after_cr); |
df7492f9 | 1378 | c = c1; |
4af310db | 1379 | } |
df7492f9 | 1380 | else |
4af310db | 1381 | { |
df7492f9 | 1382 | ONE_MORE_BYTE (c2); |
065e3595 | 1383 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1384 | goto invalid_code; |
1385 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1386 | { |
b0edb2c5 DL |
1387 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1388 | /* Reject overlong sequences here and below. Encoders | |
1389 | producing them are incorrect, they can be misleading, | |
1390 | and they mess up read/write invariance. */ | |
1391 | if (c < 128) | |
1392 | goto invalid_code; | |
4af310db | 1393 | } |
df7492f9 | 1394 | else |
aa72b389 | 1395 | { |
df7492f9 | 1396 | ONE_MORE_BYTE (c3); |
065e3595 | 1397 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1398 | goto invalid_code; |
1399 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1400 | { |
1401 | c = (((c1 & 0xF) << 12) | |
1402 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1403 | if (c < 0x800 |
1404 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1405 | goto invalid_code; |
1406 | } | |
df7492f9 KH |
1407 | else |
1408 | { | |
1409 | ONE_MORE_BYTE (c4); | |
065e3595 | 1410 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1411 | goto invalid_code; |
1412 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1413 | { |
df7492f9 KH |
1414 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1415 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1416 | if (c < 0x10000) |
1417 | goto invalid_code; | |
1418 | } | |
df7492f9 KH |
1419 | else |
1420 | { | |
1421 | ONE_MORE_BYTE (c5); | |
065e3595 | 1422 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1423 | goto invalid_code; |
1424 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1425 | { | |
1426 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1427 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1428 | | (c5 & 0x3F)); | |
b0edb2c5 | 1429 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1430 | goto invalid_code; |
1431 | } | |
1432 | else | |
1433 | goto invalid_code; | |
1434 | } | |
1435 | } | |
aa72b389 | 1436 | } |
b73bfc1c | 1437 | } |
df7492f9 KH |
1438 | |
1439 | *charbuf++ = c; | |
1440 | continue; | |
1441 | ||
1442 | invalid_code: | |
1443 | src = src_base; | |
1444 | consumed_chars = consumed_chars_base; | |
1445 | ONE_MORE_BYTE (c); | |
1446 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1447 | coding->errors++; | |
aa72b389 KH |
1448 | } |
1449 | ||
df7492f9 KH |
1450 | no_more_source: |
1451 | coding->consumed_char += consumed_chars_base; | |
1452 | coding->consumed = src_base - coding->source; | |
1453 | coding->charbuf_used = charbuf - coding->charbuf; | |
1454 | } | |
1455 | ||
1456 | ||
f10fe38f | 1457 | static bool |
971de7fb | 1458 | encode_coding_utf_8 (struct coding_system *coding) |
df7492f9 | 1459 | { |
f10fe38f | 1460 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
1461 | int *charbuf = coding->charbuf; |
1462 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1463 | unsigned char *dst = coding->destination + coding->produced; | |
1464 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c | 1465 | ptrdiff_t produced_chars = 0; |
df7492f9 KH |
1466 | int c; |
1467 | ||
a470d443 KH |
1468 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1469 | { | |
1470 | ASSURE_DESTINATION (3); | |
1471 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1472 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1473 | } | |
1474 | ||
df7492f9 | 1475 | if (multibytep) |
aa72b389 | 1476 | { |
df7492f9 KH |
1477 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1478 | ||
1479 | while (charbuf < charbuf_end) | |
b73bfc1c | 1480 | { |
df7492f9 | 1481 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1482 | |
df7492f9 KH |
1483 | ASSURE_DESTINATION (safe_room); |
1484 | c = *charbuf++; | |
28f67a95 KH |
1485 | if (CHAR_BYTE8_P (c)) |
1486 | { | |
1487 | c = CHAR_TO_BYTE8 (c); | |
1488 | EMIT_ONE_BYTE (c); | |
1489 | } | |
1490 | else | |
1491 | { | |
db274c7a | 1492 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1493 | for (p = str; p < pend; p++) |
1494 | EMIT_ONE_BYTE (*p); | |
1495 | } | |
b73bfc1c | 1496 | } |
aa72b389 | 1497 | } |
df7492f9 KH |
1498 | else |
1499 | { | |
1500 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1501 | ||
1502 | while (charbuf < charbuf_end) | |
b73bfc1c | 1503 | { |
df7492f9 KH |
1504 | ASSURE_DESTINATION (safe_room); |
1505 | c = *charbuf++; | |
f03caae0 KH |
1506 | if (CHAR_BYTE8_P (c)) |
1507 | *dst++ = CHAR_TO_BYTE8 (c); | |
1508 | else | |
db274c7a | 1509 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1510 | produced_chars++; |
4ed46869 KH |
1511 | } |
1512 | } | |
065e3595 | 1513 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1514 | coding->produced_char += produced_chars; |
1515 | coding->produced = dst - coding->destination; | |
1516 | return 0; | |
4ed46869 KH |
1517 | } |
1518 | ||
b73bfc1c | 1519 | |
df7492f9 | 1520 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f | 1521 | Return true if a text is encoded in one of UTF-16 based coding systems. */ |
aa72b389 | 1522 | |
df7492f9 KH |
1523 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1524 | (((val) & 0xFC00) == 0xD800) | |
1525 | ||
1526 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1527 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1528 | |
aa72b389 | 1529 | |
f10fe38f | 1530 | static bool |
cf84bb53 JB |
1531 | detect_coding_utf_16 (struct coding_system *coding, |
1532 | struct coding_detection_info *detect_info) | |
aa72b389 | 1533 | { |
ef1b0ba7 | 1534 | const unsigned char *src = coding->source; |
8f924df7 | 1535 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 1536 | bool multibytep = coding->src_multibyte; |
df7492f9 | 1537 | int c1, c2; |
aa72b389 | 1538 | |
ff0dacd7 | 1539 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1540 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1541 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1542 | { |
1543 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1544 | return 0; | |
1545 | } | |
24a73b0a | 1546 | |
f56a4450 | 1547 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1548 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1549 | { |
b49a1807 KH |
1550 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1551 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1552 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1553 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1554 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1555 | } |
df7492f9 | 1556 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1557 | { |
b49a1807 KH |
1558 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1559 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1560 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1561 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1562 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1563 | } | |
220eeac9 | 1564 | else if (c2 < 0) |
f56a4450 KH |
1565 | { |
1566 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1567 | return 0; | |
1568 | } | |
2f3cbb32 | 1569 | else |
24a73b0a | 1570 | { |
2f3cbb32 KH |
1571 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1572 | O is odd. If both are high, we assume binary data.*/ | |
1573 | unsigned char e[256], o[256]; | |
1574 | unsigned e_num = 1, o_num = 1; | |
1575 | ||
1576 | memset (e, 0, 256); | |
1577 | memset (o, 0, 256); | |
1578 | e[c1] = 1; | |
1579 | o[c2] = 1; | |
1580 | ||
cc13543e KH |
1581 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO |
1582 | |CATEGORY_MASK_UTF_16_BE | |
1583 | | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 | 1584 | |
7f1faf1c KH |
1585 | while ((detect_info->rejected & CATEGORY_MASK_UTF_16) |
1586 | != CATEGORY_MASK_UTF_16) | |
2f3cbb32 | 1587 | { |
f56a4450 | 1588 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1589 | if (c2 < 0) |
f56a4450 | 1590 | break; |
2f3cbb32 KH |
1591 | if (! e[c1]) |
1592 | { | |
1593 | e[c1] = 1; | |
1594 | e_num++; | |
cc13543e KH |
1595 | if (e_num >= 128) |
1596 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
2f3cbb32 KH |
1597 | } |
1598 | if (! o[c2]) | |
1599 | { | |
977b85f4 | 1600 | o[c2] = 1; |
2f3cbb32 | 1601 | o_num++; |
cc13543e KH |
1602 | if (o_num >= 128) |
1603 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
2f3cbb32 KH |
1604 | } |
1605 | } | |
2f3cbb32 | 1606 | return 0; |
ff0dacd7 | 1607 | } |
2f3cbb32 | 1608 | |
df7492f9 | 1609 | no_more_source: |
ff0dacd7 | 1610 | return 1; |
df7492f9 | 1611 | } |
aa72b389 | 1612 | |
df7492f9 | 1613 | static void |
971de7fb | 1614 | decode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1615 | { |
8f924df7 KH |
1616 | const unsigned char *src = coding->source + coding->consumed; |
1617 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1618 | const unsigned char *src_base; | |
69a80ea3 | 1619 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
1620 | /* We may produces at most 3 chars in one loop. */ |
1621 | int *charbuf_end = coding->charbuf + coding->charbuf_size - 2; | |
d311d28c | 1622 | ptrdiff_t consumed_chars = 0, consumed_chars_base = 0; |
f10fe38f | 1623 | bool multibytep = coding->src_multibyte; |
a470d443 | 1624 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1625 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1626 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
f10fe38f PE |
1627 | bool eol_dos |
1628 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1629 | int byte_after_cr1 = -1, byte_after_cr2 = -1; |
df7492f9 | 1630 | |
a470d443 | 1631 | if (bom == utf_with_bom) |
aa72b389 | 1632 | { |
df7492f9 | 1633 | int c, c1, c2; |
4af310db | 1634 | |
aa72b389 | 1635 | src_base = src; |
df7492f9 KH |
1636 | ONE_MORE_BYTE (c1); |
1637 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1638 | c = (c1 << 8) | c2; |
aa72b389 | 1639 | |
b49a1807 KH |
1640 | if (endian == utf_16_big_endian |
1641 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1642 | { |
b49a1807 KH |
1643 | /* The first two bytes are not BOM. Treat them as bytes |
1644 | for a normal character. */ | |
1645 | src = src_base; | |
1646 | coding->errors++; | |
aa72b389 | 1647 | } |
a470d443 | 1648 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1649 | } |
a470d443 | 1650 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1651 | { |
1652 | /* We have already tried to detect BOM and failed in | |
1653 | detect_coding. */ | |
a470d443 | 1654 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1655 | } |
aa72b389 | 1656 | |
df7492f9 KH |
1657 | while (1) |
1658 | { | |
1659 | int c, c1, c2; | |
1660 | ||
1661 | src_base = src; | |
1662 | consumed_chars_base = consumed_chars; | |
1663 | ||
df80c7f0 | 1664 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1665 | { |
1666 | if (byte_after_cr1 >= 0) | |
1667 | src_base -= 2; | |
1668 | break; | |
1669 | } | |
df7492f9 | 1670 | |
119852e7 KH |
1671 | if (byte_after_cr1 >= 0) |
1672 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1673 | else | |
1674 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1675 | if (c1 < 0) |
1676 | { | |
1677 | *charbuf++ = -c1; | |
1678 | continue; | |
1679 | } | |
119852e7 KH |
1680 | if (byte_after_cr2 >= 0) |
1681 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1682 | else | |
1683 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1684 | if (c2 < 0) |
1685 | { | |
1686 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1687 | *charbuf++ = -c2; | |
1688 | continue; | |
1689 | } | |
df7492f9 | 1690 | c = (endian == utf_16_big_endian |
e19c3639 | 1691 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1692 | |
df7492f9 | 1693 | if (surrogate) |
fd3ae0b9 | 1694 | { |
df7492f9 | 1695 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1696 | { |
df7492f9 KH |
1697 | if (endian == utf_16_big_endian) |
1698 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1699 | else | |
1700 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1701 | *charbuf++ = c1; | |
1702 | *charbuf++ = c2; | |
1703 | coding->errors++; | |
1704 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1705 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1706 | else |
df7492f9 | 1707 | *charbuf++ = c; |
fd3ae0b9 KH |
1708 | } |
1709 | else | |
df7492f9 KH |
1710 | { |
1711 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1712 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1713 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1714 | } |
fd3ae0b9 | 1715 | } |
aa72b389 | 1716 | else |
df7492f9 KH |
1717 | { |
1718 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1719 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1720 | else | |
119852e7 | 1721 | { |
2735d060 | 1722 | if (eol_dos && c == '\r') |
119852e7 KH |
1723 | { |
1724 | ONE_MORE_BYTE (byte_after_cr1); | |
1725 | ONE_MORE_BYTE (byte_after_cr2); | |
1726 | } | |
1727 | *charbuf++ = c; | |
1728 | } | |
8f924df7 | 1729 | } |
aa72b389 | 1730 | } |
df7492f9 KH |
1731 | |
1732 | no_more_source: | |
1733 | coding->consumed_char += consumed_chars_base; | |
1734 | coding->consumed = src_base - coding->source; | |
1735 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1736 | } |
b73bfc1c | 1737 | |
f10fe38f | 1738 | static bool |
971de7fb | 1739 | encode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1740 | { |
f10fe38f | 1741 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
1742 | int *charbuf = coding->charbuf; |
1743 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1744 | unsigned char *dst = coding->destination + coding->produced; | |
1745 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1746 | int safe_room = 8; | |
a470d443 | 1747 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
f10fe38f | 1748 | bool big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
d311d28c | 1749 | ptrdiff_t produced_chars = 0; |
df7492f9 | 1750 | int c; |
4ed46869 | 1751 | |
a470d443 | 1752 | if (bom != utf_without_bom) |
df7492f9 KH |
1753 | { |
1754 | ASSURE_DESTINATION (safe_room); | |
1755 | if (big_endian) | |
df7492f9 | 1756 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1757 | else |
1758 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1759 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1760 | } |
1761 | ||
1762 | while (charbuf < charbuf_end) | |
1763 | { | |
1764 | ASSURE_DESTINATION (safe_room); | |
1765 | c = *charbuf++; | |
60afa08d | 1766 | if (c > MAX_UNICODE_CHAR) |
e19c3639 | 1767 | c = coding->default_char; |
df7492f9 KH |
1768 | |
1769 | if (c < 0x10000) | |
1770 | { | |
1771 | if (big_endian) | |
1772 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1773 | else | |
1774 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1775 | } | |
1776 | else | |
1777 | { | |
1778 | int c1, c2; | |
1779 | ||
1780 | c -= 0x10000; | |
1781 | c1 = (c >> 10) + 0xD800; | |
1782 | c2 = (c & 0x3FF) + 0xDC00; | |
1783 | if (big_endian) | |
1784 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1785 | else | |
1786 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1787 | } | |
1788 | } | |
065e3595 | 1789 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1790 | coding->produced = dst - coding->destination; |
1791 | coding->produced_char += produced_chars; | |
1792 | return 0; | |
1793 | } | |
1794 | ||
1795 | \f | |
1796 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1797 | ||
1798 | /* Emacs' internal format for representation of multiple character | |
1799 | sets is a kind of multi-byte encoding, i.e. characters are | |
1800 | represented by variable-length sequences of one-byte codes. | |
1801 | ||
1802 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1803 | represented by one-byte sequences which are their ASCII codes, in | |
1804 | the range 0x00 through 0x7F. | |
1805 | ||
1806 | 8-bit characters of the range 0x80..0x9F are represented by | |
1807 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1808 | code + 0x20). | |
1809 | ||
1810 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1811 | one-byte sequences which are their 8-bit code. | |
1812 | ||
1813 | The other characters are represented by a sequence of `base | |
1814 | leading-code', optional `extended leading-code', and one or two | |
1815 | `position-code's. The length of the sequence is determined by the | |
1816 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1817 | whereas extended leading-code and position-code take the range 0xA0 | |
1818 | through 0xFF. See `charset.h' for more details about leading-code | |
1819 | and position-code. | |
1820 | ||
1821 | --- CODE RANGE of Emacs' internal format --- | |
1822 | character set range | |
1823 | ------------- ----- | |
1824 | ascii 0x00..0x7F | |
1825 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1826 | eight-bit-graphic 0xA0..0xBF | |
1827 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1828 | --------------------------------------------- | |
1829 | ||
1830 | As this is the internal character representation, the format is | |
1831 | usually not used externally (i.e. in a file or in a data sent to a | |
1832 | process). But, it is possible to have a text externally in this | |
1833 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1834 | ||
1835 | In that case, a sequence of one-byte codes has a slightly different | |
1836 | form. | |
1837 | ||
1838 | At first, all characters in eight-bit-control are represented by | |
1839 | one-byte sequences which are their 8-bit code. | |
1840 | ||
1841 | Next, character composition data are represented by the byte | |
1842 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1843 | where, | |
e951386e | 1844 | METHOD is 0xF2 plus one of composition method (enum |
df7492f9 KH |
1845 | composition_method), |
1846 | ||
1847 | BYTES is 0xA0 plus a byte length of this composition data, | |
1848 | ||
e951386e | 1849 | CHARS is 0xA0 plus a number of characters composed by this |
df7492f9 KH |
1850 | data, |
1851 | ||
ad1746f5 | 1852 | COMPONENTs are characters of multibyte form or composition |
df7492f9 KH |
1853 | rules encoded by two-byte of ASCII codes. |
1854 | ||
1855 | In addition, for backward compatibility, the following formats are | |
1856 | also recognized as composition data on decoding. | |
1857 | ||
1858 | 0x80 MSEQ ... | |
1859 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1860 | ||
1861 | Here, | |
1862 | MSEQ is a multibyte form but in these special format: | |
1863 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1864 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1865 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1866 | represents a composition rule. | |
1867 | */ | |
1868 | ||
1869 | char emacs_mule_bytes[256]; | |
1870 | ||
e951386e KH |
1871 | |
1872 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 1873 | Return true if a text is encoded in 'emacs-mule'. */ |
e951386e | 1874 | |
f10fe38f | 1875 | static bool |
cf84bb53 JB |
1876 | detect_coding_emacs_mule (struct coding_system *coding, |
1877 | struct coding_detection_info *detect_info) | |
e951386e KH |
1878 | { |
1879 | const unsigned char *src = coding->source, *src_base; | |
1880 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
f10fe38f | 1881 | bool multibytep = coding->src_multibyte; |
d311d28c | 1882 | ptrdiff_t consumed_chars = 0; |
e951386e KH |
1883 | int c; |
1884 | int found = 0; | |
1885 | ||
1886 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | |
1887 | /* A coding system of this category is always ASCII compatible. */ | |
1888 | src += coding->head_ascii; | |
1889 | ||
1890 | while (1) | |
1891 | { | |
1892 | src_base = src; | |
1893 | ONE_MORE_BYTE (c); | |
1894 | if (c < 0) | |
1895 | continue; | |
1896 | if (c == 0x80) | |
1897 | { | |
1898 | /* Perhaps the start of composite character. We simply skip | |
1899 | it because analyzing it is too heavy for detecting. But, | |
1900 | at least, we check that the composite character | |
1901 | constitutes of more than 4 bytes. */ | |
2735d060 | 1902 | const unsigned char *src_start; |
e951386e KH |
1903 | |
1904 | repeat: | |
2735d060 | 1905 | src_start = src; |
e951386e KH |
1906 | do |
1907 | { | |
1908 | ONE_MORE_BYTE (c); | |
1909 | } | |
1910 | while (c >= 0xA0); | |
1911 | ||
2735d060 | 1912 | if (src - src_start <= 4) |
e951386e KH |
1913 | break; |
1914 | found = CATEGORY_MASK_EMACS_MULE; | |
1915 | if (c == 0x80) | |
1916 | goto repeat; | |
1917 | } | |
1918 | ||
1919 | if (c < 0x80) | |
1920 | { | |
1921 | if (c < 0x20 | |
1922 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1923 | break; | |
1924 | } | |
1925 | else | |
1926 | { | |
396475b7 | 1927 | int more_bytes = emacs_mule_bytes[c] - 1; |
e951386e KH |
1928 | |
1929 | while (more_bytes > 0) | |
1930 | { | |
1931 | ONE_MORE_BYTE (c); | |
1932 | if (c < 0xA0) | |
1933 | { | |
1934 | src--; /* Unread the last byte. */ | |
1935 | break; | |
1936 | } | |
1937 | more_bytes--; | |
1938 | } | |
1939 | if (more_bytes != 0) | |
1940 | break; | |
1941 | found = CATEGORY_MASK_EMACS_MULE; | |
1942 | } | |
1943 | } | |
1944 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1945 | return 0; | |
1946 | ||
1947 | no_more_source: | |
1948 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | |
1949 | { | |
1950 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1951 | return 0; | |
1952 | } | |
1953 | detect_info->found |= found; | |
1954 | return 1; | |
1955 | } | |
1956 | ||
1957 | ||
1958 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | |
1959 | character. If CMP_STATUS indicates that we must expect MSEQ or | |
1960 | RULE described above, decode it and return the negative value of | |
685ebdc8 | 1961 | the decoded character or rule. If an invalid byte is found, return |
e951386e KH |
1962 | -1. If SRC is too short, return -2. */ |
1963 | ||
e2f1bab9 | 1964 | static int |
cf84bb53 JB |
1965 | emacs_mule_char (struct coding_system *coding, const unsigned char *src, |
1966 | int *nbytes, int *nchars, int *id, | |
1967 | struct composition_status *cmp_status) | |
df7492f9 | 1968 | { |
8f924df7 KH |
1969 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1970 | const unsigned char *src_base = src; | |
f10fe38f | 1971 | bool multibytep = coding->src_multibyte; |
2735d060 | 1972 | int charset_ID; |
df7492f9 KH |
1973 | unsigned code; |
1974 | int c; | |
1975 | int consumed_chars = 0; | |
f10fe38f | 1976 | bool mseq_found = 0; |
df7492f9 KH |
1977 | |
1978 | ONE_MORE_BYTE (c); | |
065e3595 | 1979 | if (c < 0) |
df7492f9 | 1980 | { |
065e3595 | 1981 | c = -c; |
2735d060 | 1982 | charset_ID = emacs_mule_charset[0]; |
065e3595 KH |
1983 | } |
1984 | else | |
1985 | { | |
4d41e8b7 KH |
1986 | if (c >= 0xA0) |
1987 | { | |
e951386e KH |
1988 | if (cmp_status->state != COMPOSING_NO |
1989 | && cmp_status->old_form) | |
4d41e8b7 | 1990 | { |
e951386e KH |
1991 | if (cmp_status->state == COMPOSING_CHAR) |
1992 | { | |
1993 | if (c == 0xA0) | |
1994 | { | |
1995 | ONE_MORE_BYTE (c); | |
1996 | c -= 0x80; | |
1997 | if (c < 0) | |
1998 | goto invalid_code; | |
1999 | } | |
2000 | else | |
2001 | c -= 0x20; | |
2002 | mseq_found = 1; | |
2003 | } | |
2004 | else | |
2005 | { | |
2006 | *nbytes = src - src_base; | |
2007 | *nchars = consumed_chars; | |
2008 | return -c; | |
2009 | } | |
4d41e8b7 KH |
2010 | } |
2011 | else | |
e951386e | 2012 | goto invalid_code; |
4d41e8b7 KH |
2013 | } |
2014 | ||
065e3595 | 2015 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 2016 | { |
065e3595 | 2017 | case 2: |
2735d060 | 2018 | if ((charset_ID = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
2019 | goto invalid_code; |
2020 | ONE_MORE_BYTE (c); | |
9ffd559c | 2021 | if (c < 0xA0) |
065e3595 | 2022 | goto invalid_code; |
df7492f9 | 2023 | code = c & 0x7F; |
065e3595 KH |
2024 | break; |
2025 | ||
2026 | case 3: | |
2027 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
2028 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
2029 | { | |
2030 | ONE_MORE_BYTE (c); | |
2735d060 | 2031 | if (c < 0xA0 || (charset_ID = emacs_mule_charset[c]) < 0) |
065e3595 KH |
2032 | goto invalid_code; |
2033 | ONE_MORE_BYTE (c); | |
9ffd559c | 2034 | if (c < 0xA0) |
065e3595 KH |
2035 | goto invalid_code; |
2036 | code = c & 0x7F; | |
2037 | } | |
2038 | else | |
2039 | { | |
2735d060 | 2040 | if ((charset_ID = emacs_mule_charset[c]) < 0) |
065e3595 KH |
2041 | goto invalid_code; |
2042 | ONE_MORE_BYTE (c); | |
9ffd559c | 2043 | if (c < 0xA0) |
065e3595 KH |
2044 | goto invalid_code; |
2045 | code = (c & 0x7F) << 8; | |
2046 | ONE_MORE_BYTE (c); | |
9ffd559c | 2047 | if (c < 0xA0) |
065e3595 KH |
2048 | goto invalid_code; |
2049 | code |= c & 0x7F; | |
2050 | } | |
2051 | break; | |
2052 | ||
2053 | case 4: | |
2054 | ONE_MORE_BYTE (c); | |
2735d060 | 2055 | if (c < 0 || (charset_ID = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
2056 | goto invalid_code; |
2057 | ONE_MORE_BYTE (c); | |
9ffd559c | 2058 | if (c < 0xA0) |
065e3595 | 2059 | goto invalid_code; |
781d7a48 | 2060 | code = (c & 0x7F) << 8; |
df7492f9 | 2061 | ONE_MORE_BYTE (c); |
9ffd559c | 2062 | if (c < 0xA0) |
065e3595 | 2063 | goto invalid_code; |
df7492f9 | 2064 | code |= c & 0x7F; |
065e3595 | 2065 | break; |
df7492f9 | 2066 | |
065e3595 KH |
2067 | case 1: |
2068 | code = c; | |
2735d060 | 2069 | charset_ID = ASCII_BYTE_P (code) ? charset_ascii : charset_eight_bit; |
065e3595 | 2070 | break; |
df7492f9 | 2071 | |
065e3595 | 2072 | default: |
1088b922 | 2073 | emacs_abort (); |
065e3595 | 2074 | } |
b84ae584 | 2075 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
2735d060 | 2076 | CHARSET_FROM_ID (charset_ID), code, c); |
065e3595 KH |
2077 | if (c < 0) |
2078 | goto invalid_code; | |
df7492f9 | 2079 | } |
df7492f9 KH |
2080 | *nbytes = src - src_base; |
2081 | *nchars = consumed_chars; | |
ff0dacd7 | 2082 | if (id) |
2735d060 | 2083 | *id = charset_ID; |
e951386e | 2084 | return (mseq_found ? -c : c); |
df7492f9 KH |
2085 | |
2086 | no_more_source: | |
2087 | return -2; | |
2088 | ||
2089 | invalid_code: | |
2090 | return -1; | |
2091 | } | |
2092 | ||
2093 | ||
e951386e | 2094 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
df7492f9 | 2095 | |
e951386e KH |
2096 | /* Handle these composition sequence ('|': the end of header elements, |
2097 | BYTES and CHARS >= 0xA0): | |
df7492f9 | 2098 | |
e951386e KH |
2099 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
2100 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... | |
2101 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... | |
df7492f9 | 2102 | |
e951386e | 2103 | and these old form: |
1a4990fb | 2104 | |
e951386e KH |
2105 | (4) relative composition: 0x80 | MSEQ ... MSEQ |
2106 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ | |
df7492f9 | 2107 | |
e951386e KH |
2108 | When the starter 0x80 and the following header elements are found, |
2109 | this annotation header is produced. | |
df7492f9 | 2110 | |
e951386e | 2111 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
df7492f9 | 2112 | |
e951386e KH |
2113 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
2114 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). | |
df7492f9 | 2115 | |
e951386e KH |
2116 | Then, upon reading the following elements, these codes are produced |
2117 | until the composition end is found: | |
df7492f9 | 2118 | |
e951386e KH |
2119 | (1) CHAR ... CHAR |
2120 | (2) ALT ... ALT CHAR ... CHAR | |
2121 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR | |
2122 | (4) CHAR ... CHAR | |
2123 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
4ed46869 | 2124 | |
e951386e KH |
2125 | When the composition end is found, LENGTH and NCHARS in the |
2126 | annotation header is updated as below: | |
b73bfc1c | 2127 | |
e951386e KH |
2128 | (1) LENGTH: unchanged, NCHARS: unchanged |
2129 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2130 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2131 | (4) LENGTH: unchanged, NCHARS: number of CHARs | |
2132 | (5) LENGTH: unchanged, NCHARS: number of CHARs | |
df7492f9 | 2133 | |
e951386e KH |
2134 | If an error is found while composing, the annotation header is |
2135 | changed to the original composition header (plus filler -1s) as | |
2136 | below: | |
2137 | ||
2138 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] | |
2139 | (5) [ 0x80 0xFF -1 -1- -1 ] | |
2140 | ||
2141 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
2142 | byte sequence as below: | |
2143 | o the original byte sequence is B: [ B -1 ] | |
2144 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
2145 | ||
2146 | Most of the routines are implemented by macros because many | |
2147 | variables and labels in the caller decode_coding_emacs_mule must be | |
2148 | accessible, and they are usually called just once (thus doesn't | |
2149 | increase the size of compiled object). */ | |
2150 | ||
2151 | /* Decode a composition rule represented by C as a component of | |
2152 | composition sequence of Emacs 20 style. Set RULE to the decoded | |
2153 | rule. */ | |
2154 | ||
2155 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ | |
df7492f9 | 2156 | do { \ |
e951386e KH |
2157 | int gref, nref; \ |
2158 | \ | |
4d41e8b7 | 2159 | c -= 0xA0; \ |
df7492f9 KH |
2160 | if (c < 0 || c >= 81) \ |
2161 | goto invalid_code; \ | |
df7492f9 | 2162 | gref = c / 9, nref = c % 9; \ |
e951386e KH |
2163 | if (gref == 4) gref = 10; \ |
2164 | if (nref == 4) nref = 10; \ | |
2165 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
df7492f9 KH |
2166 | } while (0) |
2167 | ||
2168 | ||
e951386e KH |
2169 | /* Decode a composition rule represented by C and the following byte |
2170 | at SRC as a component of composition sequence of Emacs 21 style. | |
2171 | Set RULE to the decoded rule. */ | |
781d7a48 | 2172 | |
e951386e | 2173 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
781d7a48 KH |
2174 | do { \ |
2175 | int gref, nref; \ | |
e951386e KH |
2176 | \ |
2177 | gref = c - 0x20; \ | |
2178 | if (gref < 0 || gref >= 81) \ | |
781d7a48 | 2179 | goto invalid_code; \ |
e951386e KH |
2180 | ONE_MORE_BYTE (c); \ |
2181 | nref = c - 0x20; \ | |
2182 | if (nref < 0 || nref >= 81) \ | |
781d7a48 | 2183 | goto invalid_code; \ |
e951386e | 2184 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
781d7a48 KH |
2185 | } while (0) |
2186 | ||
2187 | ||
e951386e KH |
2188 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
2189 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | |
2190 | byte length of this composition information, CHARS is the number of | |
2191 | characters composed by this composition. */ | |
2192 | ||
2193 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | |
aa72b389 | 2194 | do { \ |
781d7a48 | 2195 | enum composition_method method = c - 0xF2; \ |
df7492f9 | 2196 | int nbytes, nchars; \ |
e951386e | 2197 | \ |
df7492f9 | 2198 | ONE_MORE_BYTE (c); \ |
065e3595 KH |
2199 | if (c < 0) \ |
2200 | goto invalid_code; \ | |
df7492f9 | 2201 | nbytes = c - 0xA0; \ |
e951386e | 2202 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
df7492f9 KH |
2203 | goto invalid_code; \ |
2204 | ONE_MORE_BYTE (c); \ | |
2205 | nchars = c - 0xA0; \ | |
e951386e KH |
2206 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
2207 | goto invalid_code; \ | |
2208 | cmp_status->old_form = 0; \ | |
2209 | cmp_status->method = method; \ | |
2210 | if (method == COMPOSITION_RELATIVE) \ | |
2211 | cmp_status->state = COMPOSING_CHAR; \ | |
2212 | else \ | |
2213 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ | |
2214 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2215 | cmp_status->nchars = nchars; \ | |
2216 | cmp_status->ncomps = nbytes - 4; \ | |
2217 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ | |
aa72b389 | 2218 | } while (0) |
93dec019 | 2219 | |
aa72b389 | 2220 | |
e951386e KH |
2221 | /* Start of Emacs 20 style format for relative composition. */ |
2222 | ||
2223 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ | |
2224 | do { \ | |
2225 | cmp_status->old_form = 1; \ | |
2226 | cmp_status->method = COMPOSITION_RELATIVE; \ | |
2227 | cmp_status->state = COMPOSING_CHAR; \ | |
2228 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2229 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2230 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
2231 | } while (0) | |
2232 | ||
2233 | ||
2234 | /* Start of Emacs 20 style format for rule-base composition. */ | |
2235 | ||
2236 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | |
2237 | do { \ | |
2238 | cmp_status->old_form = 1; \ | |
2239 | cmp_status->method = COMPOSITION_WITH_RULE; \ | |
2240 | cmp_status->state = COMPOSING_CHAR; \ | |
2241 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2242 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2243 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
df7492f9 KH |
2244 | } while (0) |
2245 | ||
2246 | ||
e951386e KH |
2247 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ |
2248 | do { \ | |
2249 | const unsigned char *current_src = src; \ | |
2250 | \ | |
2251 | ONE_MORE_BYTE (c); \ | |
2252 | if (c < 0) \ | |
2253 | goto invalid_code; \ | |
2254 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | |
2255 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | |
2256 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | |
2257 | else if (c < 0xA0) \ | |
2258 | goto invalid_code; \ | |
2259 | else if (c < 0xC0) \ | |
2260 | { \ | |
2261 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | |
2262 | /* Re-read C as a composition component. */ \ | |
2263 | src = current_src; \ | |
2264 | } \ | |
2265 | else if (c == 0xFF) \ | |
2266 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | |
2267 | else \ | |
2268 | goto invalid_code; \ | |
2269 | } while (0) | |
2270 | ||
2271 | #define EMACS_MULE_COMPOSITION_END() \ | |
df7492f9 | 2272 | do { \ |
e951386e | 2273 | int idx = - cmp_status->length; \ |
4d41e8b7 | 2274 | \ |
e951386e KH |
2275 | if (cmp_status->old_form) \ |
2276 | charbuf[idx + 2] = cmp_status->nchars; \ | |
2277 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ | |
2278 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ | |
2279 | cmp_status->state = COMPOSING_NO; \ | |
2280 | } while (0) | |
2281 | ||
2282 | ||
2283 | static int | |
cf84bb53 JB |
2284 | emacs_mule_finish_composition (int *charbuf, |
2285 | struct composition_status *cmp_status) | |
e951386e KH |
2286 | { |
2287 | int idx = - cmp_status->length; | |
2288 | int new_chars; | |
2289 | ||
2290 | if (cmp_status->old_form && cmp_status->nchars > 0) | |
2291 | { | |
2292 | charbuf[idx + 2] = cmp_status->nchars; | |
2293 | new_chars = 0; | |
2294 | if (cmp_status->method == COMPOSITION_WITH_RULE | |
2295 | && cmp_status->state == COMPOSING_CHAR) | |
2296 | { | |
2297 | /* The last rule was invalid. */ | |
2298 | int rule = charbuf[-1] + 0xA0; | |
2299 | ||
2300 | charbuf[-2] = BYTE8_TO_CHAR (rule); | |
2301 | charbuf[-1] = -1; | |
2302 | new_chars = 1; | |
2303 | } | |
2304 | } | |
2305 | else | |
2306 | { | |
2307 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | |
2308 | ||
2309 | if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2310 | { | |
2311 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | |
2312 | charbuf[idx++] = -3; | |
2313 | charbuf[idx++] = 0; | |
2314 | new_chars = 1; | |
2315 | } | |
2316 | else | |
2317 | { | |
2318 | int nchars = charbuf[idx + 1] + 0xA0; | |
2319 | int nbytes = charbuf[idx + 2] + 0xA0; | |
2320 | ||
2321 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | |
2322 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | |
2323 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | |
2324 | charbuf[idx++] = -1; | |
2325 | new_chars = 4; | |
2326 | } | |
2327 | } | |
2328 | cmp_status->state = COMPOSING_NO; | |
2329 | return new_chars; | |
2330 | } | |
2331 | ||
2332 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | |
2333 | do { \ | |
2334 | if (cmp_status->state != COMPOSING_NO) \ | |
2335 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | |
df7492f9 KH |
2336 | } while (0) |
2337 | ||
aa72b389 KH |
2338 | |
2339 | static void | |
971de7fb | 2340 | decode_coding_emacs_mule (struct coding_system *coding) |
aa72b389 | 2341 | { |
8f924df7 KH |
2342 | const unsigned char *src = coding->source + coding->consumed; |
2343 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2344 | const unsigned char *src_base; | |
69a80ea3 | 2345 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
2346 | /* We may produce two annotations (charset and composition) in one |
2347 | loop and one more charset annotation at the end. */ | |
69a80ea3 | 2348 | int *charbuf_end |
15cbd324 EZ |
2349 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3) |
2350 | /* We can produce up to 2 characters in a loop. */ | |
2351 | - 1; | |
d311d28c | 2352 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 2353 | bool multibytep = coding->src_multibyte; |
d311d28c PE |
2354 | ptrdiff_t char_offset = coding->produced_char; |
2355 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 2356 | int last_id = charset_ascii; |
f10fe38f PE |
2357 | bool eol_dos |
2358 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 2359 | int byte_after_cr = -1; |
e951386e | 2360 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; |
aa72b389 | 2361 | |
e951386e KH |
2362 | if (cmp_status->state != COMPOSING_NO) |
2363 | { | |
2364 | int i; | |
2365 | ||
15cbd324 | 2366 | if (charbuf_end - charbuf < cmp_status->length) |
1088b922 | 2367 | emacs_abort (); |
e951386e KH |
2368 | for (i = 0; i < cmp_status->length; i++) |
2369 | *charbuf++ = cmp_status->carryover[i]; | |
2370 | coding->annotated = 1; | |
2371 | } | |
2372 | ||
aa72b389 KH |
2373 | while (1) |
2374 | { | |
ee05f961 | 2375 | int c, id IF_LINT (= 0); |
df7492f9 | 2376 | |
aa72b389 | 2377 | src_base = src; |
df7492f9 KH |
2378 | consumed_chars_base = consumed_chars; |
2379 | ||
2380 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2381 | { |
2382 | if (byte_after_cr >= 0) | |
2383 | src_base--; | |
2384 | break; | |
2385 | } | |
aa72b389 | 2386 | |
119852e7 KH |
2387 | if (byte_after_cr >= 0) |
2388 | c = byte_after_cr, byte_after_cr = -1; | |
2389 | else | |
2390 | ONE_MORE_BYTE (c); | |
e951386e KH |
2391 | |
2392 | if (c < 0 || c == 0x80) | |
065e3595 | 2393 | { |
e951386e KH |
2394 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
2395 | if (c < 0) | |
2396 | { | |
2397 | *charbuf++ = -c; | |
2398 | char_offset++; | |
2399 | } | |
2400 | else | |
2401 | DECODE_EMACS_MULE_COMPOSITION_START (); | |
2402 | continue; | |
065e3595 | 2403 | } |
e951386e KH |
2404 | |
2405 | if (c < 0x80) | |
aa72b389 | 2406 | { |
2735d060 | 2407 | if (eol_dos && c == '\r') |
119852e7 | 2408 | ONE_MORE_BYTE (byte_after_cr); |
e951386e KH |
2409 | id = charset_ascii; |
2410 | if (cmp_status->state != COMPOSING_NO) | |
2411 | { | |
2412 | if (cmp_status->old_form) | |
2413 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2414 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2415 | cmp_status->ncomps--; | |
2416 | } | |
2417 | } | |
2418 | else | |
2419 | { | |
ee05f961 | 2420 | int nchars IF_LINT (= 0), nbytes IF_LINT (= 0); |
75f80e63 EZ |
2421 | /* emacs_mule_char can load a charset map from a file, which |
2422 | allocates a large structure and might cause buffer text | |
2423 | to be relocated as result. Thus, we need to remember the | |
ad1746f5 | 2424 | original pointer to buffer text, and fix up all related |
75f80e63 EZ |
2425 | pointers after the call. */ |
2426 | const unsigned char *orig = coding->source; | |
d311d28c | 2427 | ptrdiff_t offset; |
e951386e KH |
2428 | |
2429 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, | |
2430 | cmp_status); | |
75f80e63 EZ |
2431 | offset = coding->source - orig; |
2432 | if (offset) | |
2433 | { | |
2434 | src += offset; | |
2435 | src_base += offset; | |
2436 | src_end += offset; | |
2437 | } | |
e951386e KH |
2438 | if (c < 0) |
2439 | { | |
2440 | if (c == -1) | |
2441 | goto invalid_code; | |
2442 | if (c == -2) | |
2443 | break; | |
2444 | } | |
2445 | src = src_base + nbytes; | |
2446 | consumed_chars = consumed_chars_base + nchars; | |
2447 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2448 | cmp_status->ncomps -= nchars; | |
2449 | } | |
2450 | ||
ad1746f5 | 2451 | /* Now if C >= 0, we found a normally encoded character, if C < |
e951386e KH |
2452 | 0, we found an old-style composition component character or |
2453 | rule. */ | |
2454 | ||
2455 | if (cmp_status->state == COMPOSING_NO) | |
2456 | { | |
2457 | if (last_id != id) | |
2458 | { | |
2459 | if (last_id != charset_ascii) | |
2460 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, | |
2461 | last_id); | |
2462 | last_id = id; | |
2463 | last_offset = char_offset; | |
2464 | } | |
df7492f9 KH |
2465 | *charbuf++ = c; |
2466 | char_offset++; | |
aa72b389 | 2467 | } |
e951386e | 2468 | else if (cmp_status->state == COMPOSING_CHAR) |
df7492f9 | 2469 | { |
e951386e KH |
2470 | if (cmp_status->old_form) |
2471 | { | |
2472 | if (c >= 0) | |
2473 | { | |
2474 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2475 | *charbuf++ = c; | |
2476 | char_offset++; | |
2477 | } | |
2478 | else | |
2479 | { | |
2480 | *charbuf++ = -c; | |
2481 | cmp_status->nchars++; | |
2482 | cmp_status->length++; | |
2483 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | |
2484 | EMACS_MULE_COMPOSITION_END (); | |
2485 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2486 | cmp_status->state = COMPOSING_RULE; | |
2487 | } | |
2488 | } | |
df7492f9 | 2489 | else |
e951386e KH |
2490 | { |
2491 | *charbuf++ = c; | |
2492 | cmp_status->length++; | |
2493 | cmp_status->nchars--; | |
2494 | if (cmp_status->nchars == 0) | |
2495 | EMACS_MULE_COMPOSITION_END (); | |
2496 | } | |
df7492f9 | 2497 | } |
e951386e | 2498 | else if (cmp_status->state == COMPOSING_RULE) |
df7492f9 | 2499 | { |
e951386e | 2500 | int rule; |
ff0dacd7 | 2501 | |
e951386e | 2502 | if (c >= 0) |
df7492f9 | 2503 | { |
e951386e KH |
2504 | EMACS_MULE_COMPOSITION_END (); |
2505 | *charbuf++ = c; | |
2506 | char_offset++; | |
df7492f9 | 2507 | } |
e951386e | 2508 | else |
ff0dacd7 | 2509 | { |
e951386e KH |
2510 | c = -c; |
2511 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | |
2512 | if (rule < 0) | |
2513 | goto invalid_code; | |
2514 | *charbuf++ = -2; | |
2515 | *charbuf++ = rule; | |
2516 | cmp_status->length += 2; | |
2517 | cmp_status->state = COMPOSING_CHAR; | |
ff0dacd7 | 2518 | } |
e951386e KH |
2519 | } |
2520 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | |
2521 | { | |
df7492f9 | 2522 | *charbuf++ = c; |
e951386e KH |
2523 | cmp_status->length++; |
2524 | if (cmp_status->ncomps == 0) | |
2525 | cmp_status->state = COMPOSING_CHAR; | |
2526 | else if (cmp_status->ncomps > 0) | |
2527 | { | |
2528 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | |
2529 | cmp_status->state = COMPOSING_COMPONENT_RULE; | |
2530 | } | |
2531 | else | |
2532 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 2533 | } |
e951386e KH |
2534 | else /* COMPOSING_COMPONENT_RULE */ |
2535 | { | |
2536 | int rule; | |
2537 | ||
2538 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | |
2539 | if (rule < 0) | |
2540 | goto invalid_code; | |
2541 | *charbuf++ = -2; | |
2542 | *charbuf++ = rule; | |
2543 | cmp_status->length += 2; | |
2544 | cmp_status->ncomps--; | |
2545 | if (cmp_status->ncomps > 0) | |
2546 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | |
2547 | else | |
2548 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2549 | } | |
2550 | continue; | |
2551 | ||
df7492f9 | 2552 | invalid_code: |
e951386e | 2553 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
df7492f9 KH |
2554 | src = src_base; |
2555 | consumed_chars = consumed_chars_base; | |
2556 | ONE_MORE_BYTE (c); | |
2557 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2558 | char_offset++; |
df7492f9 KH |
2559 | coding->errors++; |
2560 | } | |
2561 | ||
2562 | no_more_source: | |
e951386e KH |
2563 | if (cmp_status->state != COMPOSING_NO) |
2564 | { | |
2565 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
2566 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2567 | else | |
2568 | { | |
2569 | int i; | |
2570 | ||
2571 | charbuf -= cmp_status->length; | |
2572 | for (i = 0; i < cmp_status->length; i++) | |
2573 | cmp_status->carryover[i] = charbuf[i]; | |
2574 | } | |
2575 | } | |
ff0dacd7 | 2576 | if (last_id != charset_ascii) |
69a80ea3 | 2577 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2578 | coding->consumed_char += consumed_chars_base; |
2579 | coding->consumed = src_base - coding->source; | |
2580 | coding->charbuf_used = charbuf - coding->charbuf; | |
2581 | } | |
2582 | ||
2583 | ||
2584 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2585 | do { \ | |
2586 | if (id < 0xA0) \ | |
2587 | codes[0] = id, codes[1] = 0; \ | |
2588 | else if (id < 0xE0) \ | |
2589 | codes[0] = 0x9A, codes[1] = id; \ | |
2590 | else if (id < 0xF0) \ | |
2591 | codes[0] = 0x9B, codes[1] = id; \ | |
2592 | else if (id < 0xF5) \ | |
2593 | codes[0] = 0x9C, codes[1] = id; \ | |
2594 | else \ | |
2595 | codes[0] = 0x9D, codes[1] = id; \ | |
2596 | } while (0); | |
2597 | ||
aa72b389 | 2598 | |
f10fe38f | 2599 | static bool |
971de7fb | 2600 | encode_coding_emacs_mule (struct coding_system *coding) |
df7492f9 | 2601 | { |
f10fe38f | 2602 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
2603 | int *charbuf = coding->charbuf; |
2604 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2605 | unsigned char *dst = coding->destination + coding->produced; | |
2606 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2607 | int safe_room = 8; | |
d311d28c | 2608 | ptrdiff_t produced_chars = 0; |
24a73b0a | 2609 | Lisp_Object attrs, charset_list; |
df7492f9 | 2610 | int c; |
ff0dacd7 | 2611 | int preferred_charset_id = -1; |
df7492f9 | 2612 | |
24a73b0a | 2613 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2614 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2615 | { | |
4939150c PE |
2616 | charset_list = Vemacs_mule_charset_list; |
2617 | ASET (attrs, coding_attr_charset_list, charset_list); | |
eccb6815 | 2618 | } |
df7492f9 KH |
2619 | |
2620 | while (charbuf < charbuf_end) | |
2621 | { | |
2622 | ASSURE_DESTINATION (safe_room); | |
2623 | c = *charbuf++; | |
ff0dacd7 KH |
2624 | |
2625 | if (c < 0) | |
2626 | { | |
2627 | /* Handle an annotation. */ | |
2628 | switch (*charbuf) | |
2629 | { | |
2630 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2631 | /* Not yet implemented. */ | |
2632 | break; | |
2633 | case CODING_ANNOTATE_CHARSET_MASK: | |
2634 | preferred_charset_id = charbuf[3]; | |
2635 | if (preferred_charset_id >= 0 | |
2636 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2637 | charset_list))) | |
2638 | preferred_charset_id = -1; | |
2639 | break; | |
2640 | default: | |
1088b922 | 2641 | emacs_abort (); |
ff0dacd7 KH |
2642 | } |
2643 | charbuf += -c - 1; | |
2644 | continue; | |
2645 | } | |
2646 | ||
df7492f9 KH |
2647 | if (ASCII_CHAR_P (c)) |
2648 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2649 | else if (CHAR_BYTE8_P (c)) |
2650 | { | |
2651 | c = CHAR_TO_BYTE8 (c); | |
2652 | EMIT_ONE_BYTE (c); | |
2653 | } | |
df7492f9 | 2654 | else |
aa72b389 | 2655 | { |
df7492f9 KH |
2656 | struct charset *charset; |
2657 | unsigned code; | |
2658 | int dimension; | |
2659 | int emacs_mule_id; | |
2660 | unsigned char leading_codes[2]; | |
2661 | ||
ff0dacd7 KH |
2662 | if (preferred_charset_id >= 0) |
2663 | { | |
f10fe38f | 2664 | bool result; |
5eb05ea3 | 2665 | |
ff0dacd7 | 2666 | charset = CHARSET_FROM_ID (preferred_charset_id); |
5eb05ea3 KH |
2667 | CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result); |
2668 | if (result) | |
905ca9d2 KH |
2669 | code = ENCODE_CHAR (charset, c); |
2670 | else | |
5eb05ea3 KH |
2671 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2672 | &code, charset); | |
ff0dacd7 KH |
2673 | } |
2674 | else | |
5eb05ea3 KH |
2675 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2676 | &code, charset); | |
df7492f9 KH |
2677 | if (! charset) |
2678 | { | |
2679 | c = coding->default_char; | |
2680 | if (ASCII_CHAR_P (c)) | |
2681 | { | |
2682 | EMIT_ONE_ASCII_BYTE (c); | |
2683 | continue; | |
2684 | } | |
5eb05ea3 KH |
2685 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2686 | &code, charset); | |
df7492f9 KH |
2687 | } |
2688 | dimension = CHARSET_DIMENSION (charset); | |
2689 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2690 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2691 | EMIT_ONE_BYTE (leading_codes[0]); | |
2692 | if (leading_codes[1]) | |
2693 | EMIT_ONE_BYTE (leading_codes[1]); | |
2694 | if (dimension == 1) | |
1fa663f9 | 2695 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2696 | else |
df7492f9 | 2697 | { |
1fa663f9 | 2698 | code |= 0x8080; |
df7492f9 KH |
2699 | EMIT_ONE_BYTE (code >> 8); |
2700 | EMIT_ONE_BYTE (code & 0xFF); | |
2701 | } | |
aa72b389 | 2702 | } |
aa72b389 | 2703 | } |
065e3595 | 2704 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2705 | coding->produced_char += produced_chars; |
2706 | coding->produced = dst - coding->destination; | |
2707 | return 0; | |
aa72b389 | 2708 | } |
b73bfc1c | 2709 | |
4ed46869 | 2710 | \f |
df7492f9 | 2711 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2712 | |
2713 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2714 | Since the intention of this note is to help understand the |
5a936b46 | 2715 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2716 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2717 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2718 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2719 | |
2720 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2721 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2722 | is encoded using bytes less than 128. This may make the encoded |
2723 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2724 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2725 | Significant Bit). |
b73bfc1c | 2726 | |
cfb43547 DL |
2727 | There are two kinds of character sets: control character sets and |
2728 | graphic character sets. The former contain control characters such | |
4ed46869 | 2729 | as `newline' and `escape' to provide control functions (control |
39787efd | 2730 | functions are also provided by escape sequences). The latter |
cfb43547 | 2731 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2732 | two control character sets and many graphic character sets. |
2733 | ||
2734 | Graphic character sets are classified into one of the following | |
39787efd KH |
2735 | four classes, according to the number of bytes (DIMENSION) and |
2736 | number of characters in one dimension (CHARS) of the set: | |
2737 | - DIMENSION1_CHARS94 | |
2738 | - DIMENSION1_CHARS96 | |
2739 | - DIMENSION2_CHARS94 | |
2740 | - DIMENSION2_CHARS96 | |
2741 | ||
2742 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2743 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2744 | hereafter). The <F> of each character set is decided by ECMA(*) |
2745 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2746 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2747 | |
2748 | Note (*): ECMA = European Computer Manufacturers Association | |
2749 | ||
cfb43547 | 2750 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2751 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2752 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2753 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2754 | o DIMENSION2_CHARS96 -- none for the moment | |
2755 | ||
39787efd | 2756 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2757 | C0 [0x00..0x1F] -- control character plane 0 |
2758 | GL [0x20..0x7F] -- graphic character plane 0 | |
2759 | C1 [0x80..0x9F] -- control character plane 1 | |
2760 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2761 | ||
2762 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2763 | C1 by an escape sequence. The most common case is that: |
2764 | - ISO646's control character set is designated/invoked to C0, and | |
2765 | - ISO6429's control character set is designated/invoked to C1, | |
2766 | and usually these designations/invocations are omitted in encoded | |
2767 | text. In a 7-bit environment, only C0 can be used, and a control | |
2768 | character for C1 is encoded by an appropriate escape sequence to | |
2769 | fit into the environment. All control characters for C1 are | |
2770 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2771 | |
2772 | A graphic character set is at first designated to one of four | |
2773 | graphic registers (G0 through G3), then these graphic registers are | |
2774 | invoked to GL or GR. These designations and invocations can be | |
2775 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2776 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2777 | these invocations and designations are omitted in encoded text. | |
2778 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2779 | |
39787efd KH |
2780 | When a graphic character set of CHARS94 is invoked to GL, codes |
2781 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2782 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2783 | be used. | |
4ed46869 KH |
2784 | |
2785 | There are two ways of invocation: locking-shift and single-shift. | |
2786 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2787 | invocation, whereas with single-shift, the invocation affects the |
2788 | following character only and doesn't affect the locking-shift | |
2789 | state. Invocations are done by the following control characters or | |
2790 | escape sequences: | |
4ed46869 KH |
2791 | |
2792 | ---------------------------------------------------------------------- | |
39787efd | 2793 | abbrev function cntrl escape seq description |
4ed46869 | 2794 | ---------------------------------------------------------------------- |
39787efd KH |
2795 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2796 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2797 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2798 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2799 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2800 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2801 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2802 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2803 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2804 | ---------------------------------------------------------------------- |
39787efd KH |
2805 | (*) These are not used by any known coding system. |
2806 | ||
2807 | Control characters for these functions are defined by macros | |
2808 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2809 | |
39787efd | 2810 | Designations are done by the following escape sequences: |
4ed46869 KH |
2811 | ---------------------------------------------------------------------- |
2812 | escape sequence description | |
2813 | ---------------------------------------------------------------------- | |
2814 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2815 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2816 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2817 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2818 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2819 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2820 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2821 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2822 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2823 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2824 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2825 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2826 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2827 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2828 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2829 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2830 | ---------------------------------------------------------------------- | |
2831 | ||
2832 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2833 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2834 | |
2835 | Note (*): Although these designations are not allowed in ISO2022, | |
2836 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2837 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2838 | 7-bit environment, non-locking-shift, and non-single-shift. |
2839 | ||
2840 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2841 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2842 | |
cfb43547 | 2843 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2844 | same multilingual text in ISO2022. Actually, there exist many |
2845 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2846 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2847 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2848 | localized platforms), and all of these are variants of ISO2022. |
2849 | ||
2850 | In addition to the above, Emacs handles two more kinds of escape | |
2851 | sequences: ISO6429's direction specification and Emacs' private | |
2852 | sequence for specifying character composition. | |
2853 | ||
39787efd | 2854 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2855 | o CSI ']' -- end of the current direction |
2856 | o CSI '0' ']' -- end of the current direction | |
2857 | o CSI '1' ']' -- start of left-to-right text | |
2858 | o CSI '2' ']' -- start of right-to-left text | |
2859 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2860 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2861 | ||
2862 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2863 | o ESC '0' -- start relative composition |
2864 | o ESC '1' -- end composition | |
2865 | o ESC '2' -- start rule-base composition (*) | |
2866 | o ESC '3' -- start relative composition with alternate chars (**) | |
2867 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2868 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2869 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2870 | |
5a936b46 DL |
2871 | (*) This form is used only in Emacs 20.7 and older versions, |
2872 | but newer versions can safely decode it. | |
cfb43547 | 2873 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2874 | and older versions can't decode it. |
ec6d2bb8 | 2875 | |
cfb43547 | 2876 | Here's a list of example usages of these composition escape |
b73bfc1c | 2877 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2878 | |
b73bfc1c | 2879 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2880 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2881 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2882 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2883 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2884 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2885 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2886 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 | 2887 | |
74ab6df5 | 2888 | static enum iso_code_class_type iso_code_class[256]; |
4ed46869 | 2889 | |
df7492f9 KH |
2890 | #define SAFE_CHARSET_P(coding, id) \ |
2891 | ((id) <= (coding)->max_charset_id \ | |
1b3b981b | 2892 | && (coding)->safe_charsets[id] != 255) |
df7492f9 | 2893 | |
df7492f9 | 2894 | static void |
971de7fb | 2895 | setup_iso_safe_charsets (Lisp_Object attrs) |
df7492f9 KH |
2896 | { |
2897 | Lisp_Object charset_list, safe_charsets; | |
2898 | Lisp_Object request; | |
2899 | Lisp_Object reg_usage; | |
2900 | Lisp_Object tail; | |
d311d28c | 2901 | EMACS_INT reg94, reg96; |
df7492f9 KH |
2902 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); |
2903 | int max_charset_id; | |
2904 | ||
2905 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2906 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2907 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2908 | { | |
4939150c PE |
2909 | charset_list = Viso_2022_charset_list; |
2910 | ASET (attrs, coding_attr_charset_list, charset_list); | |
df7492f9 KH |
2911 | ASET (attrs, coding_attr_safe_charsets, Qnil); |
2912 | } | |
2913 | ||
2914 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2915 | return; | |
2916 | ||
2917 | max_charset_id = 0; | |
2918 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2919 | { | |
2920 | int id = XINT (XCAR (tail)); | |
2921 | if (max_charset_id < id) | |
2922 | max_charset_id = id; | |
2923 | } | |
d46c5b12 | 2924 | |
1b3b981b AS |
2925 | safe_charsets = make_uninit_string (max_charset_id + 1); |
2926 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
2927 | request = AREF (attrs, coding_attr_iso_request); |
2928 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2929 | reg94 = XINT (XCAR (reg_usage)); | |
2930 | reg96 = XINT (XCDR (reg_usage)); | |
2931 | ||
2932 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2933 | { | |
2934 | Lisp_Object id; | |
2935 | Lisp_Object reg; | |
2936 | struct charset *charset; | |
2937 | ||
2938 | id = XCAR (tail); | |
2939 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2940 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2941 | if (! NILP (reg)) |
8f924df7 | 2942 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2943 | else if (charset->iso_chars_96) |
2944 | { | |
2945 | if (reg96 < 4) | |
8f924df7 | 2946 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2947 | } |
2948 | else | |
2949 | { | |
2950 | if (reg94 < 4) | |
8f924df7 | 2951 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2952 | } |
2953 | } | |
2954 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2955 | } | |
d46c5b12 | 2956 | |
b6871cc7 | 2957 | |
4ed46869 | 2958 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f PE |
2959 | Return true if a text is encoded in one of ISO-2022 based coding |
2960 | systems. */ | |
4ed46869 | 2961 | |
f10fe38f | 2962 | static bool |
cf84bb53 JB |
2963 | detect_coding_iso_2022 (struct coding_system *coding, |
2964 | struct coding_detection_info *detect_info) | |
4ed46869 | 2965 | { |
8f924df7 KH |
2966 | const unsigned char *src = coding->source, *src_base = src; |
2967 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
f10fe38f PE |
2968 | bool multibytep = coding->src_multibyte; |
2969 | bool single_shifting = 0; | |
0e48bb22 | 2970 | int id; |
df7492f9 | 2971 | int c, c1; |
d311d28c | 2972 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 2973 | int i; |
ff0dacd7 KH |
2974 | int rejected = 0; |
2975 | int found = 0; | |
cee53ed4 | 2976 | int composition_count = -1; |
ff0dacd7 KH |
2977 | |
2978 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2979 | |
2980 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2981 | { | |
2982 | struct coding_system *this = &(coding_categories[i]); | |
2983 | Lisp_Object attrs, val; | |
2984 | ||
c6b278e7 KH |
2985 | if (this->id < 0) |
2986 | continue; | |
df7492f9 KH |
2987 | attrs = CODING_ID_ATTRS (this->id); |
2988 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
1b3b981b | 2989 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list)) |
df7492f9 KH |
2990 | setup_iso_safe_charsets (attrs); |
2991 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 2992 | this->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 2993 | this->safe_charsets = SDATA (val); |
df7492f9 KH |
2994 | } |
2995 | ||
2996 | /* A coding system of this category is always ASCII compatible. */ | |
2997 | src += coding->head_ascii; | |
3f003981 | 2998 | |
ff0dacd7 | 2999 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 3000 | { |
065e3595 | 3001 | src_base = src; |
df7492f9 | 3002 | ONE_MORE_BYTE (c); |
4ed46869 KH |
3003 | switch (c) |
3004 | { | |
3005 | case ISO_CODE_ESC: | |
74383408 KH |
3006 | if (inhibit_iso_escape_detection) |
3007 | break; | |
f46869e4 | 3008 | single_shifting = 0; |
df7492f9 | 3009 | ONE_MORE_BYTE (c); |
0e48bb22 | 3010 | if (c == 'N' || c == 'O') |
d46c5b12 | 3011 | { |
ae9ff118 | 3012 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
3013 | single_shifting = 1; |
3014 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
4ed46869 | 3015 | } |
cee53ed4 KH |
3016 | else if (c == '1') |
3017 | { | |
3018 | /* End of composition. */ | |
3019 | if (composition_count < 0 | |
3020 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
3021 | /* Invalid */ | |
3022 | break; | |
3023 | composition_count = -1; | |
3024 | found |= CATEGORY_MASK_ISO; | |
3025 | } | |
ec6d2bb8 KH |
3026 | else if (c >= '0' && c <= '4') |
3027 | { | |
3028 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 3029 | composition_count = 0; |
ec6d2bb8 | 3030 | } |
bf9cdd4e | 3031 | else |
df7492f9 | 3032 | { |
0e48bb22 AS |
3033 | if (c >= '(' && c <= '/') |
3034 | { | |
3035 | /* Designation sequence for a charset of dimension 1. */ | |
3036 | ONE_MORE_BYTE (c1); | |
3037 | if (c1 < ' ' || c1 >= 0x80 | |
3038 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) | |
3039 | /* Invalid designation sequence. Just ignore. */ | |
3040 | break; | |
3041 | } | |
3042 | else if (c == '$') | |
3043 | { | |
3044 | /* Designation sequence for a charset of dimension 2. */ | |
3045 | ONE_MORE_BYTE (c); | |
3046 | if (c >= '@' && c <= 'B') | |
3047 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
3048 | id = iso_charset_table[1][0][c]; | |
3049 | else if (c >= '(' && c <= '/') | |
3050 | { | |
3051 | ONE_MORE_BYTE (c1); | |
3052 | if (c1 < ' ' || c1 >= 0x80 | |
3053 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) | |
3054 | /* Invalid designation sequence. Just ignore. */ | |
3055 | break; | |
3056 | } | |
3057 | else | |
3058 | /* Invalid designation sequence. Just ignore it. */ | |
3059 | break; | |
3060 | } | |
3061 | else | |
3062 | { | |
3063 | /* Invalid escape sequence. Just ignore it. */ | |
3064 | break; | |
3065 | } | |
d46c5b12 | 3066 | |
0e48bb22 AS |
3067 | /* We found a valid designation sequence for CHARSET. */ |
3068 | rejected |= CATEGORY_MASK_ISO_8BIT; | |
3069 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], | |
3070 | id)) | |
3071 | found |= CATEGORY_MASK_ISO_7; | |
3072 | else | |
3073 | rejected |= CATEGORY_MASK_ISO_7; | |
3074 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], | |
3075 | id)) | |
3076 | found |= CATEGORY_MASK_ISO_7_TIGHT; | |
3077 | else | |
3078 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; | |
3079 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], | |
3080 | id)) | |
3081 | found |= CATEGORY_MASK_ISO_7_ELSE; | |
3082 | else | |
3083 | rejected |= CATEGORY_MASK_ISO_7_ELSE; | |
3084 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], | |
3085 | id)) | |
3086 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3087 | else | |
3088 | rejected |= CATEGORY_MASK_ISO_8_ELSE; | |
3089 | } | |
4ed46869 KH |
3090 | break; |
3091 | ||
4ed46869 | 3092 | case ISO_CODE_SO: |
d46c5b12 | 3093 | case ISO_CODE_SI: |
ff0dacd7 | 3094 | /* Locking shift out/in. */ |
74383408 KH |
3095 | if (inhibit_iso_escape_detection) |
3096 | break; | |
f46869e4 | 3097 | single_shifting = 0; |
ff0dacd7 | 3098 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
3099 | break; |
3100 | ||
4ed46869 | 3101 | case ISO_CODE_CSI: |
ff0dacd7 | 3102 | /* Control sequence introducer. */ |
f46869e4 | 3103 | single_shifting = 0; |
ff0dacd7 KH |
3104 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3105 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3106 | goto check_extra_latin; | |
3107 | ||
4ed46869 KH |
3108 | case ISO_CODE_SS2: |
3109 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
3110 | /* Single shift. */ |
3111 | if (inhibit_iso_escape_detection) | |
3112 | break; | |
75e2a253 | 3113 | single_shifting = 0; |
ff0dacd7 KH |
3114 | rejected |= CATEGORY_MASK_ISO_7BIT; |
3115 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3116 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
0e48bb22 AS |
3117 | { |
3118 | found |= CATEGORY_MASK_ISO_8_1; | |
3119 | single_shifting = 1; | |
3120 | } | |
ff0dacd7 KH |
3121 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
3122 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
0e48bb22 AS |
3123 | { |
3124 | found |= CATEGORY_MASK_ISO_8_2; | |
3125 | single_shifting = 1; | |
3126 | } | |
75e2a253 KH |
3127 | if (single_shifting) |
3128 | break; | |
ba14c607 | 3129 | goto check_extra_latin; |
4ed46869 KH |
3130 | |
3131 | default: | |
065e3595 KH |
3132 | if (c < 0) |
3133 | continue; | |
4ed46869 | 3134 | if (c < 0x80) |
f46869e4 | 3135 | { |
cee53ed4 KH |
3136 | if (composition_count >= 0) |
3137 | composition_count++; | |
f46869e4 KH |
3138 | single_shifting = 0; |
3139 | break; | |
3140 | } | |
ff0dacd7 | 3141 | if (c >= 0xA0) |
c4825358 | 3142 | { |
ff0dacd7 KH |
3143 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3144 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 3145 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
3146 | 0xA0..0FF. If the byte length is even, we include |
3147 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
3148 | only when we are not single shifting. */ | |
3149 | if (! single_shifting | |
3150 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 3151 | { |
2735d060 | 3152 | int len = 1; |
b73bfc1c KH |
3153 | while (src < src_end) |
3154 | { | |
d12bd917 | 3155 | src_base = src; |
df7492f9 | 3156 | ONE_MORE_BYTE (c); |
b73bfc1c | 3157 | if (c < 0xA0) |
d12bd917 KH |
3158 | { |
3159 | src = src_base; | |
3160 | break; | |
3161 | } | |
2735d060 | 3162 | len++; |
b73bfc1c KH |
3163 | } |
3164 | ||
2735d060 | 3165 | if (len & 1 && src < src_end) |
cee53ed4 KH |
3166 | { |
3167 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3168 | if (composition_count >= 0) | |
2735d060 | 3169 | composition_count += len; |
cee53ed4 | 3170 | } |
f46869e4 | 3171 | else |
cee53ed4 KH |
3172 | { |
3173 | found |= CATEGORY_MASK_ISO_8_2; | |
3174 | if (composition_count >= 0) | |
2735d060 | 3175 | composition_count += len / 2; |
cee53ed4 | 3176 | } |
f46869e4 | 3177 | } |
ff0dacd7 | 3178 | break; |
4ed46869 | 3179 | } |
ba14c607 AS |
3180 | check_extra_latin: |
3181 | if (! VECTORP (Vlatin_extra_code_table) | |
3182 | || NILP (AREF (Vlatin_extra_code_table, c))) | |
3183 | { | |
3184 | rejected = CATEGORY_MASK_ISO; | |
3185 | break; | |
3186 | } | |
3187 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3188 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3189 | found |= CATEGORY_MASK_ISO_8_1; | |
3190 | else | |
3191 | rejected |= CATEGORY_MASK_ISO_8_1; | |
3192 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3193 | break; | |
4ed46869 KH |
3194 | } |
3195 | } | |
ff0dacd7 KH |
3196 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3197 | return 0; | |
4ed46869 | 3198 | |
df7492f9 | 3199 | no_more_source: |
ff0dacd7 KH |
3200 | detect_info->rejected |= rejected; |
3201 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3202 | return 1; |
4ed46869 | 3203 | } |
ec6d2bb8 | 3204 | |
4ed46869 | 3205 | |
134b9549 KH |
3206 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3207 | escape sequence should be kept. */ | |
df7492f9 KH |
3208 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3209 | do { \ | |
3210 | int id, prev; \ | |
3211 | \ | |
3212 | if (final < '0' || final >= 128 \ | |
3213 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3214 | || !SAFE_CHARSET_P (coding, id)) \ | |
3215 | { \ | |
3216 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3217 | chars_96 = -1; \ |
3218 | break; \ | |
df7492f9 KH |
3219 | } \ |
3220 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3221 | if (id == charset_jisx0201_roman) \ |
3222 | { \ | |
3223 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3224 | id = charset_ascii; \ | |
3225 | } \ | |
3226 | else if (id == charset_jisx0208_1978) \ | |
3227 | { \ | |
3228 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3229 | id = charset_jisx0208; \ | |
3230 | } \ | |
df7492f9 KH |
3231 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3232 | /* If there was an invalid designation to REG previously, and this \ | |
3233 | designation is ASCII to REG, we should keep this designation \ | |
3234 | sequence. */ \ | |
3235 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3236 | chars_96 = -1; \ |
4ed46869 KH |
3237 | } while (0) |
3238 | ||
d46c5b12 | 3239 | |
e951386e KH |
3240 | /* Handle these composition sequence (ALT: alternate char): |
3241 | ||
3242 | (1) relative composition: ESC 0 CHAR ... ESC 1 | |
3243 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
3244 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | |
3245 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | |
3246 | ||
3247 | When the start sequence (ESC 0/2/3/4) is found, this annotation | |
3248 | header is produced. | |
3249 | ||
3250 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | |
3251 | ||
3252 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | |
3253 | produced until the end sequence (ESC 1) is found: | |
3254 | ||
3255 | (1) CHAR ... CHAR | |
3256 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
3257 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | |
3258 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | |
3259 | ||
3260 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | |
3261 | annotation header is updated as below: | |
3262 | ||
3263 | (1) LENGTH: unchanged, NCHARS: number of CHARs | |
3264 | (2) LENGTH: unchanged, NCHARS: number of CHARs | |
3265 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | |
3266 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | |
3267 | ||
3268 | If an error is found while composing, the annotation header is | |
3269 | changed to: | |
3270 | ||
3271 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | |
3272 | ||
3273 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
3274 | byte sequence as below: | |
3275 | o the original byte sequence is B: [ B -1 ] | |
3276 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
3277 | and the sequence [ -1 -1 ] is changed to the original byte | |
3278 | sequence: | |
3279 | [ ESC '0' ] | |
3280 | */ | |
3281 | ||
3282 | /* Decode a composition rule C1 and maybe one more byte from the | |
66ebf983 | 3283 | source, and set RULE to the encoded composition rule. If the rule |
d5efd1d1 | 3284 | is invalid, goto invalid_code. */ |
e951386e | 3285 | |
66ebf983 | 3286 | #define DECODE_COMPOSITION_RULE(rule) \ |
e951386e KH |
3287 | do { \ |
3288 | rule = c1 - 32; \ | |
3289 | if (rule < 0) \ | |
d5efd1d1 | 3290 | goto invalid_code; \ |
e951386e KH |
3291 | if (rule < 81) /* old format (before ver.21) */ \ |
3292 | { \ | |
3293 | int gref = (rule) / 9; \ | |
3294 | int nref = (rule) % 9; \ | |
3295 | if (gref == 4) gref = 10; \ | |
3296 | if (nref == 4) nref = 10; \ | |
3297 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
e951386e KH |
3298 | } \ |
3299 | else /* new format (after ver.21) */ \ | |
3300 | { \ | |
2735d060 | 3301 | int b; \ |
e951386e | 3302 | \ |
2735d060 | 3303 | ONE_MORE_BYTE (b); \ |
d5efd1d1 PE |
3304 | if (! COMPOSITION_ENCODE_RULE_VALID (rule - 81, b - 32)) \ |
3305 | goto invalid_code; \ | |
2735d060 | 3306 | rule = COMPOSITION_ENCODE_RULE (rule - 81, b - 32); \ |
d5efd1d1 | 3307 | rule += 0x100; /* Distinguish it from the old format. */ \ |
e951386e KH |
3308 | } \ |
3309 | } while (0) | |
3310 | ||
3311 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
df7492f9 | 3312 | do { \ |
e951386e KH |
3313 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
3314 | \ | |
3315 | if (rule < 0x100) /* old format */ \ | |
df7492f9 | 3316 | { \ |
e951386e KH |
3317 | if (gref == 10) gref = 4; \ |
3318 | if (nref == 10) nref = 4; \ | |
3319 | charbuf[idx] = 32 + gref * 9 + nref; \ | |
3320 | charbuf[idx + 1] = -1; \ | |
3321 | new_chars++; \ | |
df7492f9 | 3322 | } \ |
e951386e | 3323 | else /* new format */ \ |
df7492f9 | 3324 | { \ |
e951386e KH |
3325 | charbuf[idx] = 32 + 81 + gref; \ |
3326 | charbuf[idx + 1] = 32 + nref; \ | |
3327 | new_chars += 2; \ | |
df7492f9 KH |
3328 | } \ |
3329 | } while (0) | |
3330 | ||
e951386e KH |
3331 | /* Finish the current composition as invalid. */ |
3332 | ||
e951386e | 3333 | static int |
971de7fb | 3334 | finish_composition (int *charbuf, struct composition_status *cmp_status) |
e951386e KH |
3335 | { |
3336 | int idx = - cmp_status->length; | |
3337 | int new_chars; | |
3338 | ||
3339 | /* Recover the original ESC sequence */ | |
3340 | charbuf[idx++] = ISO_CODE_ESC; | |
3341 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | |
3342 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | |
3343 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | |
3344 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | |
3345 | : '4'); | |
3346 | charbuf[idx++] = -2; | |
3347 | charbuf[idx++] = 0; | |
3348 | charbuf[idx++] = -1; | |
3349 | new_chars = cmp_status->nchars; | |
3350 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | |
3351 | for (; idx < 0; idx++) | |
3352 | { | |
3353 | int elt = charbuf[idx]; | |
3354 | ||
3355 | if (elt == -2) | |
3356 | { | |
3357 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | |
3358 | idx++; | |
3359 | } | |
3360 | else if (elt == -1) | |
3361 | { | |
3362 | charbuf[idx++] = ISO_CODE_ESC; | |
3363 | charbuf[idx] = '0'; | |
3364 | new_chars += 2; | |
3365 | } | |
3366 | } | |
3367 | cmp_status->state = COMPOSING_NO; | |
3368 | return new_chars; | |
3369 | } | |
3370 | ||
ad1746f5 | 3371 | /* If characters are under composition, finish the composition. */ |
e951386e KH |
3372 | #define MAYBE_FINISH_COMPOSITION() \ |
3373 | do { \ | |
3374 | if (cmp_status->state != COMPOSING_NO) \ | |
3375 | char_offset += finish_composition (charbuf, cmp_status); \ | |
3376 | } while (0) | |
d46c5b12 | 3377 | |
aa72b389 | 3378 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
e951386e | 3379 | |
aa72b389 KH |
3380 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
3381 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3382 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3383 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
ec6d2bb8 | 3384 | |
e951386e KH |
3385 | Produce this annotation sequence now: |
3386 | ||
3387 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] | |
3388 | */ | |
3389 | ||
3390 | #define DECODE_COMPOSITION_START(c1) \ | |
3391 | do { \ | |
3392 | if (c1 == '0' \ | |
3393 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ | |
3394 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ | |
3395 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ | |
3396 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ | |
3397 | { \ | |
3398 | *charbuf++ = -1; \ | |
3399 | *charbuf++= -1; \ | |
3400 | cmp_status->state = COMPOSING_CHAR; \ | |
3401 | cmp_status->length += 2; \ | |
3402 | } \ | |
3403 | else \ | |
3404 | { \ | |
3405 | MAYBE_FINISH_COMPOSITION (); \ | |
3406 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3407 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3408 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3409 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3410 | cmp_status->state \ | |
3411 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ | |
3412 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
3413 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
3414 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
3415 | coding->annotated = 1; \ | |
3416 | } \ | |
ec6d2bb8 KH |
3417 | } while (0) |
3418 | ||
ec6d2bb8 | 3419 | |
e951386e | 3420 | /* Handle composition end sequence ESC 1. */ |
df7492f9 KH |
3421 | |
3422 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3423 | do { \ |
e951386e KH |
3424 | if (cmp_status->nchars == 0 \ |
3425 | || ((cmp_status->state == COMPOSING_CHAR) \ | |
3426 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ | |
ec6d2bb8 | 3427 | { \ |
e951386e KH |
3428 | MAYBE_FINISH_COMPOSITION (); \ |
3429 | goto invalid_code; \ | |
ec6d2bb8 | 3430 | } \ |
e951386e KH |
3431 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
3432 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ | |
3433 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
3434 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ | |
3435 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ | |
3436 | char_offset += cmp_status->nchars; \ | |
3437 | cmp_status->state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3438 | } while (0) |
3439 | ||
e951386e | 3440 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ |
df7492f9 | 3441 | |
e951386e KH |
3442 | #define STORE_COMPOSITION_RULE(rule) \ |
3443 | do { \ | |
3444 | *charbuf++ = -2; \ | |
3445 | *charbuf++ = rule; \ | |
3446 | cmp_status->length += 2; \ | |
3447 | cmp_status->state--; \ | |
3448 | } while (0) | |
ec6d2bb8 | 3449 | |
e951386e KH |
3450 | /* Store a composed char or a component char C in charbuf, and update |
3451 | cmp_status. */ | |
3452 | ||
3453 | #define STORE_COMPOSITION_CHAR(c) \ | |
ec6d2bb8 | 3454 | do { \ |
e951386e KH |
3455 | *charbuf++ = (c); \ |
3456 | cmp_status->length++; \ | |
3457 | if (cmp_status->state == COMPOSING_CHAR) \ | |
3458 | cmp_status->nchars++; \ | |
df7492f9 | 3459 | else \ |
e951386e KH |
3460 | cmp_status->ncomps++; \ |
3461 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | |
3462 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | |
3463 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | |
3464 | cmp_status->state++; \ | |
ec6d2bb8 | 3465 | } while (0) |
88993dfd | 3466 | |
d46c5b12 | 3467 | |
4ed46869 KH |
3468 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3469 | ||
b73bfc1c | 3470 | static void |
971de7fb | 3471 | decode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 3472 | { |
8f924df7 KH |
3473 | const unsigned char *src = coding->source + coding->consumed; |
3474 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3475 | const unsigned char *src_base; | |
69a80ea3 | 3476 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
3477 | /* We may produce two annotations (charset and composition) in one |
3478 | loop and one more charset annotation at the end. */ | |
ff0dacd7 | 3479 | int *charbuf_end |
df80c7f0 | 3480 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
d311d28c | 3481 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 3482 | bool multibytep = coding->src_multibyte; |
4ed46869 | 3483 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3484 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3485 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3486 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3487 | struct charset *charset; |
3488 | int c; | |
e951386e | 3489 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
66ebf983 | 3490 | Lisp_Object attrs = CODING_ID_ATTRS (coding->id); |
d311d28c PE |
3491 | ptrdiff_t char_offset = coding->produced_char; |
3492 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 3493 | int last_id = charset_ascii; |
f10fe38f PE |
3494 | bool eol_dos |
3495 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 3496 | int byte_after_cr = -1; |
e951386e | 3497 | int i; |
df7492f9 | 3498 | |
df7492f9 | 3499 | setup_iso_safe_charsets (attrs); |
1b3b981b | 3500 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
b73bfc1c | 3501 | |
e951386e KH |
3502 | if (cmp_status->state != COMPOSING_NO) |
3503 | { | |
15cbd324 | 3504 | if (charbuf_end - charbuf < cmp_status->length) |
1088b922 | 3505 | emacs_abort (); |
e951386e KH |
3506 | for (i = 0; i < cmp_status->length; i++) |
3507 | *charbuf++ = cmp_status->carryover[i]; | |
3508 | coding->annotated = 1; | |
3509 | } | |
3510 | ||
b73bfc1c | 3511 | while (1) |
4ed46869 | 3512 | { |
cf299835 | 3513 | int c1, c2, c3; |
b73bfc1c KH |
3514 | |
3515 | src_base = src; | |
df7492f9 KH |
3516 | consumed_chars_base = consumed_chars; |
3517 | ||
3518 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3519 | { |
3520 | if (byte_after_cr >= 0) | |
3521 | src_base--; | |
3522 | break; | |
3523 | } | |
df7492f9 | 3524 | |
119852e7 KH |
3525 | if (byte_after_cr >= 0) |
3526 | c1 = byte_after_cr, byte_after_cr = -1; | |
3527 | else | |
3528 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3529 | if (c1 < 0) |
3530 | goto invalid_code; | |
4ed46869 | 3531 | |
e951386e | 3532 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
4ed46869 | 3533 | { |
e951386e KH |
3534 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
3535 | char_offset++; | |
3536 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | |
3537 | continue; | |
3538 | } | |
3539 | ||
3540 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | |
3541 | { | |
3542 | if (c1 == ISO_CODE_ESC) | |
ec6d2bb8 | 3543 | { |
e951386e KH |
3544 | if (src + 1 >= src_end) |
3545 | goto no_more_source; | |
3546 | *charbuf++ = ISO_CODE_ESC; | |
3547 | char_offset++; | |
3548 | if (src[0] == '%' && src[1] == '@') | |
df7492f9 | 3549 | { |
e951386e KH |
3550 | src += 2; |
3551 | consumed_chars += 2; | |
3552 | char_offset += 2; | |
3553 | /* We are sure charbuf can contain two more chars. */ | |
3554 | *charbuf++ = '%'; | |
3555 | *charbuf++ = '@'; | |
3556 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
df7492f9 | 3557 | } |
4ed46869 | 3558 | } |
e951386e KH |
3559 | else |
3560 | { | |
3561 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
3562 | char_offset++; | |
3563 | } | |
3564 | continue; | |
3565 | } | |
3566 | ||
3567 | if ((cmp_status->state == COMPOSING_RULE | |
3568 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | |
3569 | && c1 != ISO_CODE_ESC) | |
3570 | { | |
66ebf983 | 3571 | int rule; |
e951386e | 3572 | |
66ebf983 | 3573 | DECODE_COMPOSITION_RULE (rule); |
e951386e KH |
3574 | STORE_COMPOSITION_RULE (rule); |
3575 | continue; | |
3576 | } | |
3577 | ||
3578 | /* We produce at most one character. */ | |
3579 | switch (iso_code_class [c1]) | |
3580 | { | |
3581 | case ISO_0x20_or_0x7F: | |
df7492f9 KH |
3582 | if (charset_id_0 < 0 |
3583 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3584 | /* This is SPACE or DEL. */ |
3585 | charset = CHARSET_FROM_ID (charset_ascii); | |
3586 | else | |
3587 | charset = CHARSET_FROM_ID (charset_id_0); | |
3588 | break; | |
4ed46869 KH |
3589 | |
3590 | case ISO_graphic_plane_0: | |
134b9549 KH |
3591 | if (charset_id_0 < 0) |
3592 | charset = CHARSET_FROM_ID (charset_ascii); | |
3593 | else | |
3594 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3595 | break; |
3596 | ||
3597 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3598 | if (charset_id_1 < 0 |
3599 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3600 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3601 | goto invalid_code; | |
4ed46869 KH |
3602 | /* This is a graphic character, we fall down ... */ |
3603 | ||
3604 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3605 | if (charset_id_1 < 0) |
3606 | goto invalid_code; | |
3607 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3608 | break; |
3609 | ||
df7492f9 | 3610 | case ISO_control_0: |
2735d060 | 3611 | if (eol_dos && c1 == '\r') |
119852e7 | 3612 | ONE_MORE_BYTE (byte_after_cr); |
df7492f9 KH |
3613 | MAYBE_FINISH_COMPOSITION (); |
3614 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3615 | break; |
3616 | ||
df7492f9 | 3617 | case ISO_control_1: |
df7492f9 KH |
3618 | goto invalid_code; |
3619 | ||
4ed46869 | 3620 | case ISO_shift_out: |
df7492f9 KH |
3621 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3622 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3623 | goto invalid_code; | |
3624 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3625 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3626 | continue; |
4ed46869 KH |
3627 | |
3628 | case ISO_shift_in: | |
df7492f9 KH |
3629 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3630 | goto invalid_code; | |
3631 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3632 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3633 | continue; |
4ed46869 KH |
3634 | |
3635 | case ISO_single_shift_2_7: | |
a63dba42 KH |
3636 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)) |
3637 | goto invalid_code; | |
4ed46869 | 3638 | case ISO_single_shift_2: |
df7492f9 KH |
3639 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3640 | goto invalid_code; | |
4ed46869 KH |
3641 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3642 | c1 = 'N'; | |
3643 | goto label_escape_sequence; | |
3644 | ||
3645 | case ISO_single_shift_3: | |
df7492f9 KH |
3646 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3647 | goto invalid_code; | |
4ed46869 KH |
3648 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3649 | c1 = 'O'; | |
3650 | goto label_escape_sequence; | |
3651 | ||
3652 | case ISO_control_sequence_introducer: | |
3653 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3654 | c1 = '['; | |
3655 | goto label_escape_sequence; | |
3656 | ||
3657 | case ISO_escape: | |
3658 | ONE_MORE_BYTE (c1); | |
3659 | label_escape_sequence: | |
df7492f9 | 3660 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3661 | designation, direction specification, and character |
3662 | composition specification. */ | |
3663 | switch (c1) | |
3664 | { | |
3665 | case '&': /* revision of following character set */ | |
3666 | ONE_MORE_BYTE (c1); | |
3667 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3668 | goto invalid_code; |
4ed46869 KH |
3669 | ONE_MORE_BYTE (c1); |
3670 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3671 | goto invalid_code; |
4ed46869 KH |
3672 | ONE_MORE_BYTE (c1); |
3673 | goto label_escape_sequence; | |
3674 | ||
3675 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3676 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3677 | goto invalid_code; | |
134b9549 KH |
3678 | { |
3679 | int reg, chars96; | |
3680 | ||
3681 | ONE_MORE_BYTE (c1); | |
3682 | if (c1 >= '@' && c1 <= 'B') | |
3683 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3684 | or JISX0208.1980 */ |
134b9549 KH |
3685 | reg = 0, chars96 = 0; |
3686 | } | |
3687 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3688 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3689 | reg = c1 - 0x28, chars96 = 0; | |
3690 | ONE_MORE_BYTE (c1); | |
3691 | } | |
3692 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3693 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3694 | reg = c1 - 0x2C, chars96 = 1; | |
3695 | ONE_MORE_BYTE (c1); | |
3696 | } | |
3697 | else | |
3698 | goto invalid_code; | |
3699 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3700 | /* We must update these variables now. */ | |
3701 | if (reg == 0) | |
3702 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3703 | else if (reg == 1) | |
3704 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3705 | if (chars96 < 0) | |
3706 | goto invalid_code; | |
3707 | } | |
b73bfc1c | 3708 | continue; |
4ed46869 KH |
3709 | |
3710 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3711 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3712 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3713 | goto invalid_code; | |
3714 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3715 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3716 | continue; |
4ed46869 KH |
3717 | |
3718 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3719 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3720 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3721 | goto invalid_code; | |
3722 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3723 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3724 | continue; |
4ed46869 KH |
3725 | |
3726 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3727 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3728 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3729 | goto invalid_code; | |
134b9549 KH |
3730 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3731 | if (charset_id_2 < 0) | |
3732 | charset = CHARSET_FROM_ID (charset_ascii); | |
3733 | else | |
3734 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3735 | ONE_MORE_BYTE (c1); |
e7046a18 | 3736 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3737 | goto invalid_code; |
4ed46869 KH |
3738 | break; |
3739 | ||
3740 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3741 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3742 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3743 | goto invalid_code; | |
134b9549 KH |
3744 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3745 | if (charset_id_3 < 0) | |
3746 | charset = CHARSET_FROM_ID (charset_ascii); | |
3747 | else | |
3748 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3749 | ONE_MORE_BYTE (c1); |
e7046a18 | 3750 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3751 | goto invalid_code; |
4ed46869 KH |
3752 | break; |
3753 | ||
ec6d2bb8 | 3754 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3755 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3756 | goto invalid_code; | |
e951386e KH |
3757 | if (last_id != charset_ascii) |
3758 | { | |
3759 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | |
3760 | last_id = charset_ascii; | |
3761 | last_offset = char_offset; | |
3762 | } | |
ec6d2bb8 | 3763 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3764 | continue; |
4ed46869 | 3765 | |
ec6d2bb8 | 3766 | case '1': /* end composition */ |
e951386e | 3767 | if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3768 | goto invalid_code; |
3769 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3770 | continue; |
4ed46869 KH |
3771 | |
3772 | case '[': /* specification of direction */ | |
de59072a | 3773 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)) |
df7492f9 | 3774 | goto invalid_code; |
4ed46869 | 3775 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3776 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
ad1746f5 | 3777 | left-to-right, and nonzero means right-to-left. */ |
4ed46869 KH |
3778 | ONE_MORE_BYTE (c1); |
3779 | switch (c1) | |
3780 | { | |
3781 | case ']': /* end of the current direction */ | |
d46c5b12 | 3782 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3783 | |
3784 | case '0': /* end of the current direction */ | |
3785 | case '1': /* start of left-to-right direction */ | |
3786 | ONE_MORE_BYTE (c1); | |
3787 | if (c1 == ']') | |
d46c5b12 | 3788 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3789 | else |
df7492f9 | 3790 | goto invalid_code; |
4ed46869 KH |
3791 | break; |
3792 | ||
3793 | case '2': /* start of right-to-left direction */ | |
3794 | ONE_MORE_BYTE (c1); | |
3795 | if (c1 == ']') | |
d46c5b12 | 3796 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3797 | else |
df7492f9 | 3798 | goto invalid_code; |
4ed46869 KH |
3799 | break; |
3800 | ||
3801 | default: | |
df7492f9 | 3802 | goto invalid_code; |
4ed46869 | 3803 | } |
b73bfc1c | 3804 | continue; |
4ed46869 | 3805 | |
103e0180 | 3806 | case '%': |
103e0180 KH |
3807 | ONE_MORE_BYTE (c1); |
3808 | if (c1 == '/') | |
3809 | { | |
3810 | /* CTEXT extended segment: | |
3811 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3812 | We keep these bytes as is for the moment. | |
3813 | They may be decoded by post-read-conversion. */ | |
3814 | int dim, M, L; | |
4776e638 | 3815 | int size; |
8f924df7 | 3816 | |
103e0180 | 3817 | ONE_MORE_BYTE (dim); |
7a84eee5 | 3818 | if (dim < '0' || dim > '4') |
e951386e | 3819 | goto invalid_code; |
103e0180 | 3820 | ONE_MORE_BYTE (M); |
e951386e KH |
3821 | if (M < 128) |
3822 | goto invalid_code; | |
103e0180 | 3823 | ONE_MORE_BYTE (L); |
e951386e KH |
3824 | if (L < 128) |
3825 | goto invalid_code; | |
103e0180 | 3826 | size = ((M - 128) * 128) + (L - 128); |
e951386e | 3827 | if (charbuf + 6 > charbuf_end) |
4776e638 KH |
3828 | goto break_loop; |
3829 | *charbuf++ = ISO_CODE_ESC; | |
3830 | *charbuf++ = '%'; | |
3831 | *charbuf++ = '/'; | |
3832 | *charbuf++ = dim; | |
3833 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3834 | *charbuf++ = BYTE8_TO_CHAR (L); | |
e951386e | 3835 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
103e0180 KH |
3836 | } |
3837 | else if (c1 == 'G') | |
3838 | { | |
103e0180 KH |
3839 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3840 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3841 | We keep these bytes as is for the moment. | |
3842 | They may be decoded by post-read-conversion. */ | |
e951386e | 3843 | if (charbuf + 3 > charbuf_end) |
4776e638 | 3844 | goto break_loop; |
e951386e KH |
3845 | *charbuf++ = ISO_CODE_ESC; |
3846 | *charbuf++ = '%'; | |
3847 | *charbuf++ = 'G'; | |
3848 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; | |
103e0180 KH |
3849 | } |
3850 | else | |
4776e638 | 3851 | goto invalid_code; |
103e0180 | 3852 | continue; |
4776e638 | 3853 | break; |
103e0180 | 3854 | |
4ed46869 | 3855 | default: |
df7492f9 KH |
3856 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3857 | goto invalid_code; | |
134b9549 KH |
3858 | { |
3859 | int reg, chars96; | |
3860 | ||
3861 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3862 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3863 | reg = c1 - 0x28, chars96 = 0; | |
3864 | ONE_MORE_BYTE (c1); | |
3865 | } | |
3866 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3867 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3868 | reg = c1 - 0x2C, chars96 = 1; | |
3869 | ONE_MORE_BYTE (c1); | |
3870 | } | |
3871 | else | |
3872 | goto invalid_code; | |
3873 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3874 | /* We must update these variables now. */ | |
3875 | if (reg == 0) | |
3876 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3877 | else if (reg == 1) | |
3878 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3879 | if (chars96 < 0) | |
3880 | goto invalid_code; | |
3881 | } | |
b73bfc1c | 3882 | continue; |
4ed46869 | 3883 | } |
413bb2db PE |
3884 | break; |
3885 | ||
3886 | default: | |
1088b922 | 3887 | emacs_abort (); |
b73bfc1c | 3888 | } |
4ed46869 | 3889 | |
e951386e KH |
3890 | if (cmp_status->state == COMPOSING_NO |
3891 | && charset->id != charset_ascii | |
ff0dacd7 KH |
3892 | && last_id != charset->id) |
3893 | { | |
3894 | if (last_id != charset_ascii) | |
69a80ea3 | 3895 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3896 | last_id = charset->id; |
3897 | last_offset = char_offset; | |
3898 | } | |
3899 | ||
b73bfc1c | 3900 | /* Now we know CHARSET and 1st position code C1 of a character. |
cf299835 KH |
3901 | Produce a decoded character while getting 2nd and 3rd |
3902 | position codes C2, C3 if necessary. */ | |
df7492f9 | 3903 | if (CHARSET_DIMENSION (charset) > 1) |
b73bfc1c KH |
3904 | { |
3905 | ONE_MORE_BYTE (c2); | |
cf299835 KH |
3906 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0) |
3907 | || ((c1 & 0x80) != (c2 & 0x80))) | |
b73bfc1c | 3908 | /* C2 is not in a valid range. */ |
df7492f9 | 3909 | goto invalid_code; |
cf299835 KH |
3910 | if (CHARSET_DIMENSION (charset) == 2) |
3911 | c1 = (c1 << 8) | c2; | |
3912 | else | |
df7492f9 | 3913 | { |
cf299835 KH |
3914 | ONE_MORE_BYTE (c3); |
3915 | if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0) | |
3916 | || ((c1 & 0x80) != (c3 & 0x80))) | |
3917 | /* C3 is not in a valid range. */ | |
df7492f9 | 3918 | goto invalid_code; |
cf299835 | 3919 | c1 = (c1 << 16) | (c2 << 8) | c2; |
df7492f9 KH |
3920 | } |
3921 | } | |
cf299835 | 3922 | c1 &= 0x7F7F7F; |
df7492f9 KH |
3923 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); |
3924 | if (c < 0) | |
3925 | { | |
3926 | MAYBE_FINISH_COMPOSITION (); | |
3927 | for (; src_base < src; src_base++, char_offset++) | |
3928 | { | |
3929 | if (ASCII_BYTE_P (*src_base)) | |
3930 | *charbuf++ = *src_base; | |
3931 | else | |
3932 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3933 | } | |
3934 | } | |
e951386e | 3935 | else if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3936 | { |
3937 | *charbuf++ = c; | |
3938 | char_offset++; | |
4ed46869 | 3939 | } |
e951386e KH |
3940 | else if ((cmp_status->state == COMPOSING_CHAR |
3941 | ? cmp_status->nchars | |
3942 | : cmp_status->ncomps) | |
3943 | >= MAX_COMPOSITION_COMPONENTS) | |
781d7a48 | 3944 | { |
e951386e KH |
3945 | /* Too long composition. */ |
3946 | MAYBE_FINISH_COMPOSITION (); | |
3947 | *charbuf++ = c; | |
3948 | char_offset++; | |
4ed46869 | 3949 | } |
e951386e KH |
3950 | else |
3951 | STORE_COMPOSITION_CHAR (c); | |
4ed46869 KH |
3952 | continue; |
3953 | ||
df7492f9 KH |
3954 | invalid_code: |
3955 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3956 | src = src_base; |
df7492f9 KH |
3957 | consumed_chars = consumed_chars_base; |
3958 | ONE_MORE_BYTE (c); | |
065e3595 | 3959 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3960 | char_offset++; |
df7492f9 | 3961 | coding->errors++; |
ec509856 KH |
3962 | /* Reset the invocation and designation status to the safest |
3963 | one; i.e. designate ASCII to the graphic register 0, and | |
3964 | invoke that register to the graphic plane 0. This typically | |
3965 | helps the case that an designation sequence for ASCII "ESC ( | |
3966 | B" is somehow broken (e.g. broken by a newline). */ | |
3967 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3968 | CODING_ISO_DESIGNATION (coding, 0) = charset_ascii; | |
3969 | charset_id_0 = charset_ascii; | |
4776e638 KH |
3970 | continue; |
3971 | ||
3972 | break_loop: | |
3973 | break; | |
4ed46869 | 3974 | } |
fb88bf2d | 3975 | |
df7492f9 | 3976 | no_more_source: |
e951386e KH |
3977 | if (cmp_status->state != COMPOSING_NO) |
3978 | { | |
3979 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
3980 | MAYBE_FINISH_COMPOSITION (); | |
3981 | else | |
3982 | { | |
3983 | charbuf -= cmp_status->length; | |
3984 | for (i = 0; i < cmp_status->length; i++) | |
3985 | cmp_status->carryover[i] = charbuf[i]; | |
3986 | } | |
3987 | } | |
3988 | else if (last_id != charset_ascii) | |
69a80ea3 | 3989 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3990 | coding->consumed_char += consumed_chars_base; |
3991 | coding->consumed = src_base - coding->source; | |
3992 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3993 | } |
3994 | ||
b73bfc1c | 3995 | |
f4dee582 | 3996 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3997 | |
3998 | /* | |
f4dee582 | 3999 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 4000 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 4001 | variant has the following specifications: |
df7492f9 | 4002 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
4003 | 2. Allows short-form designation? |
4004 | 3. ASCII should be designated to G0 before control characters? | |
4005 | 4. ASCII should be designated to G0 at end of line? | |
4006 | 5. 7-bit environment or 8-bit environment? | |
4007 | 6. Use locking-shift? | |
4008 | 7. Use Single-shift? | |
4009 | And the following two are only for Japanese: | |
4010 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
4011 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
4012 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
4013 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 4014 | details. |
4ed46869 KH |
4015 | */ |
4016 | ||
4017 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
4018 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
4019 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
4020 | designation sequence of short-form. */ | |
4ed46869 KH |
4021 | |
4022 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
4023 | do { \ | |
df7492f9 | 4024 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
675e2c69 DN |
4025 | const char *intermediate_char_94 = "()*+"; \ |
4026 | const char *intermediate_char_96 = ",-./"; \ | |
df7492f9 | 4027 | int revision = -1; \ |
df7492f9 KH |
4028 | \ |
4029 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 4030 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
4031 | \ |
4032 | if (revision >= 0) \ | |
70c22245 | 4033 | { \ |
df7492f9 KH |
4034 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
4035 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 4036 | } \ |
df7492f9 | 4037 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
4038 | if (CHARSET_DIMENSION (charset) == 1) \ |
4039 | { \ | |
2735d060 | 4040 | int b; \ |
df7492f9 | 4041 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
2735d060 | 4042 | b = intermediate_char_94[reg]; \ |
4ed46869 | 4043 | else \ |
2735d060 PE |
4044 | b = intermediate_char_96[reg]; \ |
4045 | EMIT_ONE_ASCII_BYTE (b); \ | |
4ed46869 KH |
4046 | } \ |
4047 | else \ | |
4048 | { \ | |
df7492f9 KH |
4049 | EMIT_ONE_ASCII_BYTE ('$'); \ |
4050 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 4051 | { \ |
df7492f9 | 4052 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
4053 | || reg != 0 \ |
4054 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 4055 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
4056 | } \ |
4057 | else \ | |
df7492f9 | 4058 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 4059 | } \ |
df7492f9 KH |
4060 | EMIT_ONE_ASCII_BYTE (final_char); \ |
4061 | \ | |
4062 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
4063 | } while (0) |
4064 | ||
df7492f9 | 4065 | |
4ed46869 KH |
4066 | /* The following two macros produce codes (control character or escape |
4067 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
4068 | single-shift-3). */ | |
4069 | ||
df7492f9 KH |
4070 | #define ENCODE_SINGLE_SHIFT_2 \ |
4071 | do { \ | |
4072 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4073 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
4074 | else \ | |
4075 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
4076 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4077 | } while (0) |
4078 | ||
df7492f9 KH |
4079 | |
4080 | #define ENCODE_SINGLE_SHIFT_3 \ | |
4081 | do { \ | |
4082 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4083 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
4084 | else \ | |
4085 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
4086 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4087 | } while (0) |
4088 | ||
df7492f9 | 4089 | |
4ed46869 KH |
4090 | /* The following four macros produce codes (control character or |
4091 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
4092 | shift-out, locking-shift-2, and locking-shift-3). */ | |
4093 | ||
df7492f9 KH |
4094 | #define ENCODE_SHIFT_IN \ |
4095 | do { \ | |
4096 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
4097 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
4098 | } while (0) |
4099 | ||
df7492f9 KH |
4100 | |
4101 | #define ENCODE_SHIFT_OUT \ | |
4102 | do { \ | |
4103 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
4104 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
4105 | } while (0) |
4106 | ||
df7492f9 KH |
4107 | |
4108 | #define ENCODE_LOCKING_SHIFT_2 \ | |
4109 | do { \ | |
4110 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4111 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
4112 | } while (0) |
4113 | ||
df7492f9 KH |
4114 | |
4115 | #define ENCODE_LOCKING_SHIFT_3 \ | |
4116 | do { \ | |
4117 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4118 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
4119 | } while (0) |
4120 | ||
df7492f9 | 4121 | |
f4dee582 RS |
4122 | /* Produce codes for a DIMENSION1 character whose character set is |
4123 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
4124 | sequences are also produced in advance if necessary. */ |
4125 | ||
6e85d753 KH |
4126 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
4127 | do { \ | |
df7492f9 | 4128 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4129 | \ |
4130 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
4131 | && id == charset_ascii) \ | |
4132 | { \ | |
4133 | id = charset_jisx0201_roman; \ | |
4134 | charset = CHARSET_FROM_ID (id); \ | |
4135 | } \ | |
4136 | \ | |
df7492f9 | 4137 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4138 | { \ |
df7492f9 KH |
4139 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4140 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 4141 | else \ |
df7492f9 KH |
4142 | EMIT_ONE_BYTE (c1 | 0x80); \ |
4143 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4144 | break; \ |
4145 | } \ | |
df7492f9 | 4146 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4147 | { \ |
df7492f9 | 4148 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
4149 | break; \ |
4150 | } \ | |
df7492f9 | 4151 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4152 | { \ |
df7492f9 | 4153 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
4154 | break; \ |
4155 | } \ | |
6e85d753 KH |
4156 | else \ |
4157 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4158 | must invoke it, or, at first, designate it to some graphic \ | |
4159 | register. Then repeat the loop to actually produce the \ | |
4160 | character. */ \ | |
df7492f9 KH |
4161 | dst = encode_invocation_designation (charset, coding, dst, \ |
4162 | &produced_chars); \ | |
4ed46869 KH |
4163 | } while (1) |
4164 | ||
df7492f9 | 4165 | |
f4dee582 RS |
4166 | /* Produce codes for a DIMENSION2 character whose character set is |
4167 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
4168 | invocation codes are also produced in advance if necessary. */ |
4169 | ||
6e85d753 KH |
4170 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
4171 | do { \ | |
df7492f9 | 4172 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4173 | \ |
4174 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
4175 | && id == charset_jisx0208) \ | |
4176 | { \ | |
4177 | id = charset_jisx0208_1978; \ | |
4178 | charset = CHARSET_FROM_ID (id); \ | |
4179 | } \ | |
4180 | \ | |
df7492f9 | 4181 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4182 | { \ |
df7492f9 KH |
4183 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4184 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 4185 | else \ |
df7492f9 KH |
4186 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
4187 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4188 | break; \ |
4189 | } \ | |
df7492f9 | 4190 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4191 | { \ |
df7492f9 | 4192 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
4193 | break; \ |
4194 | } \ | |
df7492f9 | 4195 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4196 | { \ |
df7492f9 | 4197 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
4198 | break; \ |
4199 | } \ | |
6e85d753 KH |
4200 | else \ |
4201 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4202 | must invoke it, or, at first, designate it to some graphic \ | |
4203 | register. Then repeat the loop to actually produce the \ | |
4204 | character. */ \ | |
df7492f9 KH |
4205 | dst = encode_invocation_designation (charset, coding, dst, \ |
4206 | &produced_chars); \ | |
4ed46869 KH |
4207 | } while (1) |
4208 | ||
05e6f5dc | 4209 | |
df7492f9 KH |
4210 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
4211 | do { \ | |
8f50130c | 4212 | unsigned code; \ |
5eb05ea3 | 4213 | CODING_ENCODE_CHAR (coding, dst, dst_end, (charset), (c), code); \ |
df7492f9 KH |
4214 | \ |
4215 | if (CHARSET_DIMENSION (charset) == 1) \ | |
4216 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
4217 | else \ | |
4218 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 4219 | } while (0) |
bdd9fb48 | 4220 | |
05e6f5dc | 4221 | |
4ed46869 | 4222 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 4223 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
4224 | Return new DST. */ |
4225 | ||
e2f1bab9 | 4226 | static unsigned char * |
cf84bb53 JB |
4227 | encode_invocation_designation (struct charset *charset, |
4228 | struct coding_system *coding, | |
d311d28c | 4229 | unsigned char *dst, ptrdiff_t *p_nchars) |
4ed46869 | 4230 | { |
f10fe38f | 4231 | bool multibytep = coding->dst_multibyte; |
d311d28c | 4232 | ptrdiff_t produced_chars = *p_nchars; |
4ed46869 | 4233 | int reg; /* graphic register number */ |
df7492f9 | 4234 | int id = CHARSET_ID (charset); |
4ed46869 KH |
4235 | |
4236 | /* At first, check designations. */ | |
4237 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 4238 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
4239 | break; |
4240 | ||
4241 | if (reg >= 4) | |
4242 | { | |
4243 | /* CHARSET is not yet designated to any graphic registers. */ | |
4244 | /* At first check the requested designation. */ | |
df7492f9 KH |
4245 | reg = CODING_ISO_REQUEST (coding, id); |
4246 | if (reg < 0) | |
1ba9e4ab KH |
4247 | /* Since CHARSET requests no special designation, designate it |
4248 | to graphic register 0. */ | |
4ed46869 KH |
4249 | reg = 0; |
4250 | ||
4251 | ENCODE_DESIGNATION (charset, reg, coding); | |
4252 | } | |
4253 | ||
df7492f9 KH |
4254 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
4255 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
4256 | { |
4257 | /* Since the graphic register REG is not invoked to any graphic | |
4258 | planes, invoke it to graphic plane 0. */ | |
4259 | switch (reg) | |
4260 | { | |
4261 | case 0: /* graphic register 0 */ | |
4262 | ENCODE_SHIFT_IN; | |
4263 | break; | |
4264 | ||
4265 | case 1: /* graphic register 1 */ | |
4266 | ENCODE_SHIFT_OUT; | |
4267 | break; | |
4268 | ||
4269 | case 2: /* graphic register 2 */ | |
df7492f9 | 4270 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4271 | ENCODE_SINGLE_SHIFT_2; |
4272 | else | |
4273 | ENCODE_LOCKING_SHIFT_2; | |
4274 | break; | |
4275 | ||
4276 | case 3: /* graphic register 3 */ | |
df7492f9 | 4277 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4278 | ENCODE_SINGLE_SHIFT_3; |
4279 | else | |
4280 | ENCODE_LOCKING_SHIFT_3; | |
4281 | break; | |
4282 | } | |
4283 | } | |
b73bfc1c | 4284 | |
df7492f9 | 4285 | *p_nchars = produced_chars; |
4ed46869 KH |
4286 | return dst; |
4287 | } | |
4288 | ||
4ed46869 KH |
4289 | |
4290 | /* Produce codes for designation and invocation to reset the graphic | |
4291 | planes and registers to initial state. */ | |
df7492f9 KH |
4292 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4293 | do { \ | |
4294 | int reg; \ | |
4295 | struct charset *charset; \ | |
4296 | \ | |
4297 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4298 | ENCODE_SHIFT_IN; \ | |
4299 | for (reg = 0; reg < 4; reg++) \ | |
4300 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4301 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4302 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4303 | { \ | |
4304 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4305 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4306 | } \ | |
4ed46869 KH |
4307 | } while (0) |
4308 | ||
df7492f9 | 4309 | |
bdd9fb48 | 4310 | /* Produce designation sequences of charsets in the line started from |
5eb05ea3 KH |
4311 | CHARBUF to a place pointed by DST, and return the number of |
4312 | produced bytes. DST should not directly point a buffer text area | |
4313 | which may be relocated by char_charset call. | |
bdd9fb48 KH |
4314 | |
4315 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4316 | find all the necessary designations. */ |
4317 | ||
6e6c82a4 | 4318 | static ptrdiff_t |
5eb05ea3 KH |
4319 | encode_designation_at_bol (struct coding_system *coding, |
4320 | int *charbuf, int *charbuf_end, | |
461c2ab9 | 4321 | unsigned char *dst) |
e0e989f6 | 4322 | { |
75a3b399 | 4323 | unsigned char *orig = dst; |
df7492f9 | 4324 | struct charset *charset; |
bdd9fb48 KH |
4325 | /* Table of charsets to be designated to each graphic register. */ |
4326 | int r[4]; | |
df7492f9 | 4327 | int c, found = 0, reg; |
d311d28c | 4328 | ptrdiff_t produced_chars = 0; |
f10fe38f | 4329 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4330 | Lisp_Object attrs; |
4331 | Lisp_Object charset_list; | |
4332 | ||
4333 | attrs = CODING_ID_ATTRS (coding->id); | |
4334 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4335 | if (EQ (charset_list, Qiso_2022)) | |
4336 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4337 | |
4338 | for (reg = 0; reg < 4; reg++) | |
4339 | r[reg] = -1; | |
4340 | ||
5eb05ea3 | 4341 | while (charbuf < charbuf_end && found < 4) |
e0e989f6 | 4342 | { |
df7492f9 KH |
4343 | int id; |
4344 | ||
4345 | c = *charbuf++; | |
b73bfc1c KH |
4346 | if (c == '\n') |
4347 | break; | |
df7492f9 KH |
4348 | charset = char_charset (c, charset_list, NULL); |
4349 | id = CHARSET_ID (charset); | |
4350 | reg = CODING_ISO_REQUEST (coding, id); | |
4351 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4352 | { |
4353 | found++; | |
df7492f9 | 4354 | r[reg] = id; |
bdd9fb48 | 4355 | } |
bdd9fb48 KH |
4356 | } |
4357 | ||
4358 | if (found) | |
4359 | { | |
4360 | for (reg = 0; reg < 4; reg++) | |
4361 | if (r[reg] >= 0 | |
df7492f9 KH |
4362 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4363 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4364 | } |
b73bfc1c | 4365 | |
5eb05ea3 | 4366 | return dst - orig; |
e0e989f6 KH |
4367 | } |
4368 | ||
4ed46869 KH |
4369 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4370 | ||
f10fe38f | 4371 | static bool |
971de7fb | 4372 | encode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 4373 | { |
f10fe38f | 4374 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4375 | int *charbuf = coding->charbuf; |
4376 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4377 | unsigned char *dst = coding->destination + coding->produced; | |
4378 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4379 | int safe_room = 16; | |
f10fe38f | 4380 | bool bol_designation |
df7492f9 KH |
4381 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL |
4382 | && CODING_ISO_BOL (coding)); | |
d311d28c | 4383 | ptrdiff_t produced_chars = 0; |
df7492f9 | 4384 | Lisp_Object attrs, eol_type, charset_list; |
f10fe38f | 4385 | bool ascii_compatible; |
b73bfc1c | 4386 | int c; |
ff0dacd7 | 4387 | int preferred_charset_id = -1; |
05e6f5dc | 4388 | |
24a73b0a | 4389 | CODING_GET_INFO (coding, attrs, charset_list); |
0a9564cb | 4390 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
24a73b0a KH |
4391 | if (VECTORP (eol_type)) |
4392 | eol_type = Qunix; | |
4393 | ||
004068e4 | 4394 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4395 | /* Charset list may have been changed. */ |
287c57d7 | 4396 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
1b3b981b | 4397 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
0eecad43 | 4398 | |
a552b35a KH |
4399 | ascii_compatible |
4400 | = (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)) | |
4401 | && ! (CODING_ISO_FLAGS (coding) & (CODING_ISO_FLAG_DESIGNATION | |
4402 | | CODING_ISO_FLAG_LOCKING_SHIFT))); | |
bdd9fb48 | 4403 | |
df7492f9 | 4404 | while (charbuf < charbuf_end) |
4ed46869 | 4405 | { |
df7492f9 | 4406 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4407 | |
df7492f9 | 4408 | if (bol_designation) |
b73bfc1c | 4409 | { |
bdd9fb48 | 4410 | /* We have to produce designation sequences if any now. */ |
5eb05ea3 KH |
4411 | unsigned char desig_buf[16]; |
4412 | int nbytes; | |
8f50130c | 4413 | ptrdiff_t offset; |
5eb05ea3 KH |
4414 | |
4415 | charset_map_loaded = 0; | |
4416 | nbytes = encode_designation_at_bol (coding, charbuf, charbuf_end, | |
4417 | desig_buf); | |
4418 | if (charset_map_loaded | |
c1892f11 | 4419 | && (offset = coding_change_destination (coding))) |
5eb05ea3 KH |
4420 | { |
4421 | dst += offset; | |
4422 | dst_end += offset; | |
4423 | } | |
4424 | memcpy (dst, desig_buf, nbytes); | |
4425 | dst += nbytes; | |
df7492f9 | 4426 | /* We are sure that designation sequences are all ASCII bytes. */ |
5eb05ea3 KH |
4427 | produced_chars += nbytes; |
4428 | bol_designation = 0; | |
4429 | ASSURE_DESTINATION (safe_room); | |
e0e989f6 KH |
4430 | } |
4431 | ||
df7492f9 | 4432 | c = *charbuf++; |
ec6d2bb8 | 4433 | |
ff0dacd7 KH |
4434 | if (c < 0) |
4435 | { | |
4436 | /* Handle an annotation. */ | |
4437 | switch (*charbuf) | |
ec6d2bb8 | 4438 | { |
ff0dacd7 KH |
4439 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4440 | /* Not yet implemented. */ | |
4441 | break; | |
4442 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4443 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4444 | if (preferred_charset_id >= 0 |
4445 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4446 | charset_list))) | |
4447 | preferred_charset_id = -1; | |
4448 | break; | |
4449 | default: | |
1088b922 | 4450 | emacs_abort (); |
4ed46869 | 4451 | } |
ff0dacd7 KH |
4452 | charbuf += -c - 1; |
4453 | continue; | |
4ed46869 | 4454 | } |
ec6d2bb8 | 4455 | |
b73bfc1c KH |
4456 | /* Now encode the character C. */ |
4457 | if (c < 0x20 || c == 0x7F) | |
4458 | { | |
df7492f9 KH |
4459 | if (c == '\n' |
4460 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4461 | { |
df7492f9 KH |
4462 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4463 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4464 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4465 | { |
df7492f9 KH |
4466 | int i; |
4467 | ||
4468 | for (i = 0; i < 4; i++) | |
4469 | CODING_ISO_DESIGNATION (coding, i) | |
4470 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4471 | } |
f10fe38f PE |
4472 | bol_designation = ((CODING_ISO_FLAGS (coding) |
4473 | & CODING_ISO_FLAG_DESIGNATE_AT_BOL) | |
4474 | != 0); | |
19a8d9e0 | 4475 | } |
df7492f9 KH |
4476 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4477 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4478 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4479 | } |
df7492f9 | 4480 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4481 | { |
df7492f9 KH |
4482 | if (ascii_compatible) |
4483 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4484 | else |
19a8d9e0 | 4485 | { |
bf16eb23 KH |
4486 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4487 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4488 | } |
4ed46869 | 4489 | } |
16eafb5d | 4490 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4491 | { |
16eafb5d KH |
4492 | c = CHAR_TO_BYTE8 (c); |
4493 | EMIT_ONE_BYTE (c); | |
88993dfd | 4494 | } |
b73bfc1c | 4495 | else |
df7492f9 | 4496 | { |
ff0dacd7 | 4497 | struct charset *charset; |
b73bfc1c | 4498 | |
ff0dacd7 KH |
4499 | if (preferred_charset_id >= 0) |
4500 | { | |
f10fe38f | 4501 | bool result; |
5eb05ea3 | 4502 | |
ff0dacd7 | 4503 | charset = CHARSET_FROM_ID (preferred_charset_id); |
5eb05ea3 KH |
4504 | CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result); |
4505 | if (! result) | |
4506 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4507 | NULL, charset); | |
ff0dacd7 KH |
4508 | } |
4509 | else | |
5eb05ea3 KH |
4510 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
4511 | NULL, charset); | |
df7492f9 KH |
4512 | if (!charset) |
4513 | { | |
41cbe562 KH |
4514 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4515 | { | |
4516 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4517 | charset = CHARSET_FROM_ID (charset_ascii); | |
4518 | } | |
4519 | else | |
4520 | { | |
4521 | c = coding->default_char; | |
5eb05ea3 KH |
4522 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4523 | charset_list, NULL, charset); | |
41cbe562 | 4524 | } |
df7492f9 KH |
4525 | } |
4526 | ENCODE_ISO_CHARACTER (charset, c); | |
4527 | } | |
84fbb8a0 | 4528 | } |
b73bfc1c | 4529 | |
df7492f9 KH |
4530 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4531 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4532 | { | |
4533 | ASSURE_DESTINATION (safe_room); | |
4534 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4535 | } | |
065e3595 | 4536 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4537 | CODING_ISO_BOL (coding) = bol_designation; |
4538 | coding->produced_char += produced_chars; | |
4539 | coding->produced = dst - coding->destination; | |
4540 | return 0; | |
4ed46869 KH |
4541 | } |
4542 | ||
4543 | \f | |
df7492f9 | 4544 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4545 | |
df7492f9 | 4546 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4547 | quite widely. So, for the moment, Emacs supports them in the bare |
4548 | C code. But, in the future, they may be supported only by CCL. */ | |
4549 | ||
4550 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4551 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4552 | as is. A character of charset katakana-jisx0201 is encoded by | |
4553 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4554 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4555 | so that it fit in the range below. |
4ed46869 KH |
4556 | |
4557 | --- CODE RANGE of SJIS --- | |
4558 | (character set) (range) | |
4559 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4560 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4561 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4562 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4563 | ------------------------------- |
4564 | ||
4565 | */ | |
4566 | ||
4567 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4568 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4569 | character set and is encoded in two-byte. |
4ed46869 KH |
4570 | |
4571 | --- CODE RANGE of BIG5 --- | |
4572 | (character set) (range) | |
4573 | ASCII 0x00 .. 0x7F | |
4574 | Big5 (1st byte) 0xA1 .. 0xFE | |
4575 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4576 | -------------------------- | |
4577 | ||
df7492f9 | 4578 | */ |
4ed46869 KH |
4579 | |
4580 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 4581 | Return true if a text is encoded in SJIS. */ |
4ed46869 | 4582 | |
f10fe38f | 4583 | static bool |
cf84bb53 JB |
4584 | detect_coding_sjis (struct coding_system *coding, |
4585 | struct coding_detection_info *detect_info) | |
4ed46869 | 4586 | { |
065e3595 | 4587 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4588 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 4589 | bool multibytep = coding->src_multibyte; |
d311d28c | 4590 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 4591 | int found = 0; |
b73bfc1c | 4592 | int c; |
f07190ca KH |
4593 | Lisp_Object attrs, charset_list; |
4594 | int max_first_byte_of_2_byte_code; | |
4595 | ||
4596 | CODING_GET_INFO (coding, attrs, charset_list); | |
4597 | max_first_byte_of_2_byte_code | |
4598 | = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF); | |
df7492f9 | 4599 | |
ff0dacd7 | 4600 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4601 | /* A coding system of this category is always ASCII compatible. */ |
4602 | src += coding->head_ascii; | |
4ed46869 | 4603 | |
b73bfc1c | 4604 | while (1) |
4ed46869 | 4605 | { |
065e3595 | 4606 | src_base = src; |
df7492f9 | 4607 | ONE_MORE_BYTE (c); |
682169fe KH |
4608 | if (c < 0x80) |
4609 | continue; | |
f07190ca KH |
4610 | if ((c >= 0x81 && c <= 0x9F) |
4611 | || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code)) | |
4ed46869 | 4612 | { |
df7492f9 | 4613 | ONE_MORE_BYTE (c); |
682169fe | 4614 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4615 | break; |
ff0dacd7 | 4616 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4617 | } |
df7492f9 | 4618 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4619 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4620 | else |
4621 | break; | |
4ed46869 | 4622 | } |
ff0dacd7 | 4623 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4624 | return 0; |
4625 | ||
4626 | no_more_source: | |
065e3595 | 4627 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4628 | { |
ff0dacd7 | 4629 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 4630 | return 0; |
4ed46869 | 4631 | } |
ff0dacd7 KH |
4632 | detect_info->found |= found; |
4633 | return 1; | |
4ed46869 KH |
4634 | } |
4635 | ||
4636 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 4637 | Return true if a text is encoded in BIG5. */ |
4ed46869 | 4638 | |
f10fe38f | 4639 | static bool |
cf84bb53 JB |
4640 | detect_coding_big5 (struct coding_system *coding, |
4641 | struct coding_detection_info *detect_info) | |
4ed46869 | 4642 | { |
065e3595 | 4643 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4644 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 4645 | bool multibytep = coding->src_multibyte; |
d311d28c | 4646 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 4647 | int found = 0; |
b73bfc1c | 4648 | int c; |
fa42c37f | 4649 | |
ff0dacd7 | 4650 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4651 | /* A coding system of this category is always ASCII compatible. */ |
4652 | src += coding->head_ascii; | |
fa42c37f | 4653 | |
b73bfc1c | 4654 | while (1) |
fa42c37f | 4655 | { |
065e3595 | 4656 | src_base = src; |
df7492f9 KH |
4657 | ONE_MORE_BYTE (c); |
4658 | if (c < 0x80) | |
fa42c37f | 4659 | continue; |
df7492f9 | 4660 | if (c >= 0xA1) |
fa42c37f | 4661 | { |
df7492f9 KH |
4662 | ONE_MORE_BYTE (c); |
4663 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4664 | return 0; |
ff0dacd7 | 4665 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4666 | } |
df7492f9 KH |
4667 | else |
4668 | break; | |
fa42c37f | 4669 | } |
ff0dacd7 | 4670 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4671 | return 0; |
fa42c37f | 4672 | |
df7492f9 | 4673 | no_more_source: |
065e3595 | 4674 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4675 | { |
ff0dacd7 | 4676 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4677 | return 0; |
4678 | } | |
ff0dacd7 KH |
4679 | detect_info->found |= found; |
4680 | return 1; | |
fa42c37f KH |
4681 | } |
4682 | ||
f10fe38f | 4683 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
fa42c37f | 4684 | |
b73bfc1c | 4685 | static void |
971de7fb | 4686 | decode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4687 | { |
8f924df7 KH |
4688 | const unsigned char *src = coding->source + coding->consumed; |
4689 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4690 | const unsigned char *src_base; | |
69a80ea3 | 4691 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4692 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4693 | the end. */ |
69a80ea3 | 4694 | int *charbuf_end |
df80c7f0 | 4695 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 4696 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 4697 | bool multibytep = coding->src_multibyte; |
df7492f9 | 4698 | struct charset *charset_roman, *charset_kanji, *charset_kana; |
57a47f8a | 4699 | struct charset *charset_kanji2; |
24a73b0a | 4700 | Lisp_Object attrs, charset_list, val; |
d311d28c PE |
4701 | ptrdiff_t char_offset = coding->produced_char; |
4702 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 4703 | int last_id = charset_ascii; |
f10fe38f PE |
4704 | bool eol_dos |
4705 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4706 | int byte_after_cr = -1; |
a5d301df | 4707 | |
24a73b0a | 4708 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4709 | |
4710 | val = charset_list; | |
4711 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4712 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4713 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4714 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4715 | |
b73bfc1c | 4716 | while (1) |
4ed46869 | 4717 | { |
df7492f9 | 4718 | int c, c1; |
24a73b0a | 4719 | struct charset *charset; |
fa42c37f | 4720 | |
b73bfc1c | 4721 | src_base = src; |
df7492f9 | 4722 | consumed_chars_base = consumed_chars; |
fa42c37f | 4723 | |
df7492f9 | 4724 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4725 | { |
4726 | if (byte_after_cr >= 0) | |
4727 | src_base--; | |
4728 | break; | |
4729 | } | |
df7492f9 | 4730 | |
119852e7 KH |
4731 | if (byte_after_cr >= 0) |
4732 | c = byte_after_cr, byte_after_cr = -1; | |
4733 | else | |
4734 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4735 | if (c < 0) |
4736 | goto invalid_code; | |
24a73b0a | 4737 | if (c < 0x80) |
119852e7 | 4738 | { |
2735d060 | 4739 | if (eol_dos && c == '\r') |
119852e7 KH |
4740 | ONE_MORE_BYTE (byte_after_cr); |
4741 | charset = charset_roman; | |
4742 | } | |
57a47f8a | 4743 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4744 | goto invalid_code; |
57a47f8a KH |
4745 | else if (c >= 0xA1 && c <= 0xDF) |
4746 | { | |
4747 | /* SJIS -> JISX0201-Kana */ | |
4748 | c &= 0x7F; | |
4749 | charset = charset_kana; | |
4750 | } | |
4751 | else if (c <= 0xEF) | |
df7492f9 | 4752 | { |
57a47f8a KH |
4753 | /* SJIS -> JISX0208 */ |
4754 | ONE_MORE_BYTE (c1); | |
4755 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4756 | goto invalid_code; |
57a47f8a KH |
4757 | c = (c << 8) | c1; |
4758 | SJIS_TO_JIS (c); | |
4759 | charset = charset_kanji; | |
4760 | } | |
4761 | else if (c <= 0xFC && charset_kanji2) | |
4762 | { | |
c6876370 | 4763 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4764 | ONE_MORE_BYTE (c1); |
4765 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4766 | goto invalid_code; |
57a47f8a KH |
4767 | c = (c << 8) | c1; |
4768 | SJIS_TO_JIS2 (c); | |
4769 | charset = charset_kanji2; | |
df7492f9 | 4770 | } |
57a47f8a KH |
4771 | else |
4772 | goto invalid_code; | |
24a73b0a KH |
4773 | if (charset->id != charset_ascii |
4774 | && last_id != charset->id) | |
4775 | { | |
4776 | if (last_id != charset_ascii) | |
69a80ea3 | 4777 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4778 | last_id = charset->id; |
4779 | last_offset = char_offset; | |
4780 | } | |
4781 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4782 | *charbuf++ = c; |
ff0dacd7 | 4783 | char_offset++; |
df7492f9 | 4784 | continue; |
b73bfc1c | 4785 | |
df7492f9 KH |
4786 | invalid_code: |
4787 | src = src_base; | |
4788 | consumed_chars = consumed_chars_base; | |
4789 | ONE_MORE_BYTE (c); | |
065e3595 | 4790 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4791 | char_offset++; |
df7492f9 KH |
4792 | coding->errors++; |
4793 | } | |
fa42c37f | 4794 | |
df7492f9 | 4795 | no_more_source: |
ff0dacd7 | 4796 | if (last_id != charset_ascii) |
69a80ea3 | 4797 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4798 | coding->consumed_char += consumed_chars_base; |
4799 | coding->consumed = src_base - coding->source; | |
4800 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4801 | } |
4802 | ||
b73bfc1c | 4803 | static void |
971de7fb | 4804 | decode_coding_big5 (struct coding_system *coding) |
4ed46869 | 4805 | { |
8f924df7 KH |
4806 | const unsigned char *src = coding->source + coding->consumed; |
4807 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4808 | const unsigned char *src_base; | |
69a80ea3 | 4809 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4810 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4811 | the end. */ |
69a80ea3 | 4812 | int *charbuf_end |
df80c7f0 | 4813 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 4814 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 4815 | bool multibytep = coding->src_multibyte; |
df7492f9 | 4816 | struct charset *charset_roman, *charset_big5; |
24a73b0a | 4817 | Lisp_Object attrs, charset_list, val; |
d311d28c PE |
4818 | ptrdiff_t char_offset = coding->produced_char; |
4819 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 4820 | int last_id = charset_ascii; |
f10fe38f PE |
4821 | bool eol_dos |
4822 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4823 | int byte_after_cr = -1; |
df7492f9 | 4824 | |
24a73b0a | 4825 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4826 | val = charset_list; |
4827 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4828 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4829 | |
b73bfc1c | 4830 | while (1) |
4ed46869 | 4831 | { |
df7492f9 | 4832 | int c, c1; |
24a73b0a | 4833 | struct charset *charset; |
b73bfc1c KH |
4834 | |
4835 | src_base = src; | |
df7492f9 KH |
4836 | consumed_chars_base = consumed_chars; |
4837 | ||
4838 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4839 | { |
4840 | if (byte_after_cr >= 0) | |
4841 | src_base--; | |
4842 | break; | |
4843 | } | |
df7492f9 | 4844 | |
119852e7 | 4845 | if (byte_after_cr >= 0) |
14daee73 | 4846 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4847 | else |
4848 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4849 | |
065e3595 KH |
4850 | if (c < 0) |
4851 | goto invalid_code; | |
24a73b0a | 4852 | if (c < 0x80) |
119852e7 | 4853 | { |
2735d060 | 4854 | if (eol_dos && c == '\r') |
119852e7 KH |
4855 | ONE_MORE_BYTE (byte_after_cr); |
4856 | charset = charset_roman; | |
4857 | } | |
24a73b0a | 4858 | else |
4ed46869 | 4859 | { |
24a73b0a KH |
4860 | /* BIG5 -> Big5 */ |
4861 | if (c < 0xA1 || c > 0xFE) | |
4862 | goto invalid_code; | |
4863 | ONE_MORE_BYTE (c1); | |
4864 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4865 | goto invalid_code; | |
4866 | c = c << 8 | c1; | |
4867 | charset = charset_big5; | |
4ed46869 | 4868 | } |
24a73b0a KH |
4869 | if (charset->id != charset_ascii |
4870 | && last_id != charset->id) | |
df7492f9 | 4871 | { |
24a73b0a | 4872 | if (last_id != charset_ascii) |
69a80ea3 | 4873 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4874 | last_id = charset->id; |
4875 | last_offset = char_offset; | |
4ed46869 | 4876 | } |
24a73b0a | 4877 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4878 | *charbuf++ = c; |
ff0dacd7 | 4879 | char_offset++; |
fb88bf2d KH |
4880 | continue; |
4881 | ||
df7492f9 | 4882 | invalid_code: |
4ed46869 | 4883 | src = src_base; |
df7492f9 KH |
4884 | consumed_chars = consumed_chars_base; |
4885 | ONE_MORE_BYTE (c); | |
065e3595 | 4886 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4887 | char_offset++; |
df7492f9 | 4888 | coding->errors++; |
fb88bf2d | 4889 | } |
d46c5b12 | 4890 | |
df7492f9 | 4891 | no_more_source: |
ff0dacd7 | 4892 | if (last_id != charset_ascii) |
69a80ea3 | 4893 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4894 | coding->consumed_char += consumed_chars_base; |
4895 | coding->consumed = src_base - coding->source; | |
4896 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4897 | } |
4898 | ||
4899 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4900 | This function can encode charsets `ascii', `katakana-jisx0201', |
4901 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4902 | are sure that all these charsets are registered as official charset | |
4ed46869 | 4903 | (i.e. do not have extended leading-codes). Characters of other |
f10fe38f | 4904 | charsets are produced without any encoding. */ |
4ed46869 | 4905 | |
f10fe38f | 4906 | static bool |
971de7fb | 4907 | encode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4908 | { |
f10fe38f | 4909 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4910 | int *charbuf = coding->charbuf; |
4911 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4912 | unsigned char *dst = coding->destination + coding->produced; | |
4913 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4914 | int safe_room = 4; | |
d311d28c | 4915 | ptrdiff_t produced_chars = 0; |
24a73b0a | 4916 | Lisp_Object attrs, charset_list, val; |
f10fe38f | 4917 | bool ascii_compatible; |
66ebf983 | 4918 | struct charset *charset_kanji, *charset_kana; |
57a47f8a | 4919 | struct charset *charset_kanji2; |
df7492f9 | 4920 | int c; |
a5d301df | 4921 | |
24a73b0a | 4922 | CODING_GET_INFO (coding, attrs, charset_list); |
66ebf983 | 4923 | val = XCDR (charset_list); |
df7492f9 | 4924 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4925 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4926 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4927 | |
df7492f9 | 4928 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4929 | |
df7492f9 KH |
4930 | while (charbuf < charbuf_end) |
4931 | { | |
4932 | ASSURE_DESTINATION (safe_room); | |
4933 | c = *charbuf++; | |
b73bfc1c | 4934 | /* Now encode the character C. */ |
df7492f9 KH |
4935 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4936 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4937 | else if (CHAR_BYTE8_P (c)) |
4938 | { | |
4939 | c = CHAR_TO_BYTE8 (c); | |
4940 | EMIT_ONE_BYTE (c); | |
4941 | } | |
df7492f9 | 4942 | else |
b73bfc1c | 4943 | { |
df7492f9 | 4944 | unsigned code; |
5eb05ea3 KH |
4945 | struct charset *charset; |
4946 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4947 | &code, charset); | |
df7492f9 KH |
4948 | |
4949 | if (!charset) | |
4ed46869 | 4950 | { |
41cbe562 | 4951 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4952 | { |
41cbe562 KH |
4953 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4954 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4955 | } |
41cbe562 | 4956 | else |
b73bfc1c | 4957 | { |
41cbe562 | 4958 | c = coding->default_char; |
5eb05ea3 KH |
4959 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4960 | charset_list, &code, charset); | |
b73bfc1c | 4961 | } |
b73bfc1c | 4962 | } |
df7492f9 | 4963 | if (code == CHARSET_INVALID_CODE (charset)) |
1088b922 | 4964 | emacs_abort (); |
df7492f9 KH |
4965 | if (charset == charset_kanji) |
4966 | { | |
4967 | int c1, c2; | |
4968 | JIS_TO_SJIS (code); | |
4969 | c1 = code >> 8, c2 = code & 0xFF; | |
4970 | EMIT_TWO_BYTES (c1, c2); | |
4971 | } | |
4972 | else if (charset == charset_kana) | |
4973 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4974 | else if (charset_kanji2 && charset == charset_kanji2) |
4975 | { | |
4976 | int c1, c2; | |
4977 | ||
4978 | c1 = code >> 8; | |
f07190ca KH |
4979 | if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25) |
4980 | || c1 == 0x28 | |
57a47f8a KH |
4981 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) |
4982 | { | |
4983 | JIS_TO_SJIS2 (code); | |
4984 | c1 = code >> 8, c2 = code & 0xFF; | |
4985 | EMIT_TWO_BYTES (c1, c2); | |
4986 | } | |
4987 | else | |
4988 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4989 | } | |
df7492f9 KH |
4990 | else |
4991 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4992 | } | |
4993 | } | |
065e3595 | 4994 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4995 | coding->produced_char += produced_chars; |
4996 | coding->produced = dst - coding->destination; | |
4997 | return 0; | |
4998 | } | |
4999 | ||
f10fe38f | 5000 | static bool |
971de7fb | 5001 | encode_coding_big5 (struct coding_system *coding) |
df7492f9 | 5002 | { |
f10fe38f | 5003 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5004 | int *charbuf = coding->charbuf; |
5005 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5006 | unsigned char *dst = coding->destination + coding->produced; | |
5007 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5008 | int safe_room = 4; | |
d311d28c | 5009 | ptrdiff_t produced_chars = 0; |
24a73b0a | 5010 | Lisp_Object attrs, charset_list, val; |
f10fe38f | 5011 | bool ascii_compatible; |
66ebf983 | 5012 | struct charset *charset_big5; |
df7492f9 KH |
5013 | int c; |
5014 | ||
24a73b0a | 5015 | CODING_GET_INFO (coding, attrs, charset_list); |
66ebf983 | 5016 | val = XCDR (charset_list); |
df7492f9 KH |
5017 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); |
5018 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
5019 | ||
5020 | while (charbuf < charbuf_end) | |
5021 | { | |
5022 | ASSURE_DESTINATION (safe_room); | |
5023 | c = *charbuf++; | |
5024 | /* Now encode the character C. */ | |
5025 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
5026 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
5027 | else if (CHAR_BYTE8_P (c)) |
5028 | { | |
5029 | c = CHAR_TO_BYTE8 (c); | |
5030 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
5031 | } |
5032 | else | |
5033 | { | |
df7492f9 | 5034 | unsigned code; |
5eb05ea3 KH |
5035 | struct charset *charset; |
5036 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
5037 | &code, charset); | |
df7492f9 KH |
5038 | |
5039 | if (! charset) | |
b73bfc1c | 5040 | { |
41cbe562 | 5041 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 5042 | { |
41cbe562 KH |
5043 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
5044 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 5045 | } |
41cbe562 | 5046 | else |
0eecad43 | 5047 | { |
41cbe562 | 5048 | c = coding->default_char; |
5eb05ea3 KH |
5049 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
5050 | charset_list, &code, charset); | |
0eecad43 | 5051 | } |
4ed46869 | 5052 | } |
df7492f9 | 5053 | if (code == CHARSET_INVALID_CODE (charset)) |
1088b922 | 5054 | emacs_abort (); |
df7492f9 | 5055 | if (charset == charset_big5) |
b73bfc1c | 5056 | { |
df7492f9 KH |
5057 | int c1, c2; |
5058 | ||
5059 | c1 = code >> 8, c2 = code & 0xFF; | |
5060 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 5061 | } |
df7492f9 KH |
5062 | else |
5063 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 5064 | } |
4ed46869 | 5065 | } |
065e3595 | 5066 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5067 | coding->produced_char += produced_chars; |
5068 | coding->produced = dst - coding->destination; | |
5069 | return 0; | |
4ed46869 KH |
5070 | } |
5071 | ||
5072 | \f | |
df7492f9 | 5073 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
5074 | |
5075 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f PE |
5076 | Return true if a text is encoded in a coding system of which |
5077 | encoder/decoder are written in CCL program. */ | |
1397dc18 | 5078 | |
f10fe38f | 5079 | static bool |
cf84bb53 JB |
5080 | detect_coding_ccl (struct coding_system *coding, |
5081 | struct coding_detection_info *detect_info) | |
1397dc18 | 5082 | { |
065e3595 | 5083 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5084 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 5085 | bool multibytep = coding->src_multibyte; |
d311d28c | 5086 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 5087 | int found = 0; |
0e219d54 | 5088 | unsigned char *valids; |
d311d28c | 5089 | ptrdiff_t head_ascii = coding->head_ascii; |
df7492f9 KH |
5090 | Lisp_Object attrs; |
5091 | ||
ff0dacd7 KH |
5092 | detect_info->checked |= CATEGORY_MASK_CCL; |
5093 | ||
df7492f9 | 5094 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 5095 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
5096 | attrs = CODING_ID_ATTRS (coding->id); |
5097 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
5098 | src += head_ascii; | |
1397dc18 | 5099 | |
b73bfc1c | 5100 | while (1) |
1397dc18 | 5101 | { |
df7492f9 | 5102 | int c; |
065e3595 KH |
5103 | |
5104 | src_base = src; | |
df7492f9 | 5105 | ONE_MORE_BYTE (c); |
065e3595 | 5106 | if (c < 0 || ! valids[c]) |
df7492f9 | 5107 | break; |
ff0dacd7 KH |
5108 | if ((valids[c] > 1)) |
5109 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 5110 | } |
ff0dacd7 | 5111 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
5112 | return 0; |
5113 | ||
5114 | no_more_source: | |
ff0dacd7 KH |
5115 | detect_info->found |= found; |
5116 | return 1; | |
df7492f9 KH |
5117 | } |
5118 | ||
5119 | static void | |
971de7fb | 5120 | decode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5121 | { |
7c78e542 | 5122 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 5123 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
5124 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5125 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
d311d28c | 5126 | ptrdiff_t consumed_chars = 0; |
f10fe38f | 5127 | bool multibytep = coding->src_multibyte; |
d0396581 | 5128 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 | 5129 | int source_charbuf[1024]; |
fbdc1721 | 5130 | int source_byteidx[1025]; |
24a73b0a | 5131 | Lisp_Object attrs, charset_list; |
df7492f9 | 5132 | |
24a73b0a | 5133 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5134 | |
d0396581 | 5135 | while (1) |
df7492f9 | 5136 | { |
7c78e542 | 5137 | const unsigned char *p = src; |
95402d5f | 5138 | ptrdiff_t offset; |
df7492f9 KH |
5139 | int i = 0; |
5140 | ||
5141 | if (multibytep) | |
fbdc1721 KH |
5142 | { |
5143 | while (i < 1024 && p < src_end) | |
5144 | { | |
5145 | source_byteidx[i] = p - src; | |
5146 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
5147 | } | |
5148 | source_byteidx[i] = p - src; | |
5149 | } | |
df7492f9 KH |
5150 | else |
5151 | while (i < 1024 && p < src_end) | |
5152 | source_charbuf[i++] = *p++; | |
8f924df7 | 5153 | |
df7492f9 | 5154 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
d0396581 | 5155 | ccl->last_block = 1; |
95402d5f KH |
5156 | /* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */ |
5157 | charset_map_loaded = 0; | |
d0396581 KH |
5158 | ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf, |
5159 | charset_list); | |
95402d5f KH |
5160 | if (charset_map_loaded |
5161 | && (offset = coding_change_source (coding))) | |
5162 | { | |
5163 | p += offset; | |
5164 | src += offset; | |
5165 | src_end += offset; | |
5166 | } | |
d0396581 | 5167 | charbuf += ccl->produced; |
fbdc1721 | 5168 | if (multibytep) |
d0396581 | 5169 | src += source_byteidx[ccl->consumed]; |
df7492f9 | 5170 | else |
d0396581 KH |
5171 | src += ccl->consumed; |
5172 | consumed_chars += ccl->consumed; | |
5173 | if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC) | |
df7492f9 KH |
5174 | break; |
5175 | } | |
5176 | ||
d0396581 | 5177 | switch (ccl->status) |
df7492f9 KH |
5178 | { |
5179 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5180 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5181 | break; |
5182 | case CCL_STAT_SUSPEND_BY_DST: | |
d0396581 | 5183 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5184 | break; |
5185 | case CCL_STAT_QUIT: | |
5186 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5187 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5188 | break; |
5189 | default: | |
065e3595 | 5190 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5191 | break; |
5192 | } | |
5193 | coding->consumed_char += consumed_chars; | |
5194 | coding->consumed = src - coding->source; | |
5195 | coding->charbuf_used = charbuf - coding->charbuf; | |
5196 | } | |
5197 | ||
f10fe38f | 5198 | static bool |
971de7fb | 5199 | encode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5200 | { |
fb608df3 | 5201 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
f10fe38f | 5202 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5203 | int *charbuf = coding->charbuf; |
5204 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5205 | unsigned char *dst = coding->destination + coding->produced; | |
5206 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 | 5207 | int destination_charbuf[1024]; |
d311d28c | 5208 | ptrdiff_t produced_chars = 0; |
a53e2e89 | 5209 | int i; |
24a73b0a | 5210 | Lisp_Object attrs, charset_list; |
df7492f9 | 5211 | |
24a73b0a | 5212 | CODING_GET_INFO (coding, attrs, charset_list); |
fb608df3 KH |
5213 | if (coding->consumed_char == coding->src_chars |
5214 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
5215 | ccl->last_block = 1; | |
df7492f9 | 5216 | |
76470ad1 | 5217 | do |
df7492f9 | 5218 | { |
95402d5f KH |
5219 | ptrdiff_t offset; |
5220 | ||
5221 | /* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */ | |
5222 | charset_map_loaded = 0; | |
fb608df3 | 5223 | ccl_driver (ccl, charbuf, destination_charbuf, |
8cffd3e7 | 5224 | charbuf_end - charbuf, 1024, charset_list); |
95402d5f KH |
5225 | if (charset_map_loaded |
5226 | && (offset = coding_change_destination (coding))) | |
5227 | dst += offset; | |
df7492f9 | 5228 | if (multibytep) |
8cffd3e7 | 5229 | { |
fb608df3 KH |
5230 | ASSURE_DESTINATION (ccl->produced * 2); |
5231 | for (i = 0; i < ccl->produced; i++) | |
8cffd3e7 KH |
5232 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); |
5233 | } | |
df7492f9 KH |
5234 | else |
5235 | { | |
fb608df3 KH |
5236 | ASSURE_DESTINATION (ccl->produced); |
5237 | for (i = 0; i < ccl->produced; i++) | |
df7492f9 | 5238 | *dst++ = destination_charbuf[i] & 0xFF; |
fb608df3 | 5239 | produced_chars += ccl->produced; |
df7492f9 | 5240 | } |
fb608df3 KH |
5241 | charbuf += ccl->consumed; |
5242 | if (ccl->status == CCL_STAT_QUIT | |
5243 | || ccl->status == CCL_STAT_INVALID_CMD) | |
8cffd3e7 | 5244 | break; |
df7492f9 | 5245 | } |
76470ad1 | 5246 | while (charbuf < charbuf_end); |
df7492f9 | 5247 | |
fb608df3 | 5248 | switch (ccl->status) |
df7492f9 KH |
5249 | { |
5250 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5251 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5252 | break; |
5253 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 5254 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5255 | break; |
5256 | case CCL_STAT_QUIT: | |
5257 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5258 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5259 | break; |
5260 | default: | |
065e3595 | 5261 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5262 | break; |
1397dc18 | 5263 | } |
df7492f9 KH |
5264 | |
5265 | coding->produced_char += produced_chars; | |
5266 | coding->produced = dst - coding->destination; | |
5267 | return 0; | |
1397dc18 KH |
5268 | } |
5269 | ||
5270 | \f | |
df7492f9 | 5271 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 5272 | |
b73bfc1c | 5273 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 5274 | |
b73bfc1c | 5275 | static void |
971de7fb | 5276 | decode_coding_raw_text (struct coding_system *coding) |
4ed46869 | 5277 | { |
f10fe38f PE |
5278 | bool eol_dos |
5279 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5280 | |
df7492f9 | 5281 | coding->chars_at_source = 1; |
119852e7 KH |
5282 | coding->consumed_char = coding->src_chars; |
5283 | coding->consumed = coding->src_bytes; | |
2735d060 | 5284 | if (eol_dos && coding->source[coding->src_bytes - 1] == '\r') |
119852e7 KH |
5285 | { |
5286 | coding->consumed_char--; | |
5287 | coding->consumed--; | |
5288 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
5289 | } | |
5290 | else | |
5291 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 5292 | } |
4ed46869 | 5293 | |
f10fe38f | 5294 | static bool |
971de7fb | 5295 | encode_coding_raw_text (struct coding_system *coding) |
df7492f9 | 5296 | { |
f10fe38f | 5297 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5298 | int *charbuf = coding->charbuf; |
5299 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5300 | unsigned char *dst = coding->destination + coding->produced; | |
5301 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c | 5302 | ptrdiff_t produced_chars = 0; |
b73bfc1c KH |
5303 | int c; |
5304 | ||
df7492f9 | 5305 | if (multibytep) |
b73bfc1c | 5306 | { |
df7492f9 | 5307 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5308 | |
df7492f9 KH |
5309 | if (coding->src_multibyte) |
5310 | while (charbuf < charbuf_end) | |
5311 | { | |
5312 | ASSURE_DESTINATION (safe_room); | |
5313 | c = *charbuf++; | |
5314 | if (ASCII_CHAR_P (c)) | |
5315 | EMIT_ONE_ASCII_BYTE (c); | |
5316 | else if (CHAR_BYTE8_P (c)) | |
5317 | { | |
5318 | c = CHAR_TO_BYTE8 (c); | |
5319 | EMIT_ONE_BYTE (c); | |
5320 | } | |
5321 | else | |
5322 | { | |
5323 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5324 | |
df7492f9 | 5325 | CHAR_STRING_ADVANCE (c, p1); |
8abc3f12 | 5326 | do |
9d123124 KH |
5327 | { |
5328 | EMIT_ONE_BYTE (*p0); | |
5329 | p0++; | |
5330 | } | |
8abc3f12 | 5331 | while (p0 < p1); |
df7492f9 KH |
5332 | } |
5333 | } | |
b73bfc1c | 5334 | else |
df7492f9 KH |
5335 | while (charbuf < charbuf_end) |
5336 | { | |
5337 | ASSURE_DESTINATION (safe_room); | |
5338 | c = *charbuf++; | |
5339 | EMIT_ONE_BYTE (c); | |
5340 | } | |
5341 | } | |
5342 | else | |
4ed46869 | 5343 | { |
df7492f9 | 5344 | if (coding->src_multibyte) |
d46c5b12 | 5345 | { |
df7492f9 KH |
5346 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5347 | ||
5348 | while (charbuf < charbuf_end) | |
d46c5b12 | 5349 | { |
df7492f9 KH |
5350 | ASSURE_DESTINATION (safe_room); |
5351 | c = *charbuf++; | |
5352 | if (ASCII_CHAR_P (c)) | |
5353 | *dst++ = c; | |
5354 | else if (CHAR_BYTE8_P (c)) | |
5355 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5356 | else |
df7492f9 | 5357 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5358 | } |
5359 | } | |
df7492f9 KH |
5360 | else |
5361 | { | |
5362 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5363 | while (charbuf < charbuf_end && dst < dst_end) | |
5364 | *dst++ = *charbuf++; | |
8f924df7 | 5365 | } |
319a3947 | 5366 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5367 | } |
065e3595 | 5368 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5369 | coding->produced_char += produced_chars; |
df7492f9 KH |
5370 | coding->produced = dst - coding->destination; |
5371 | return 0; | |
4ed46869 KH |
5372 | } |
5373 | ||
ff0dacd7 | 5374 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f | 5375 | Return true if a text is encoded in a charset-based coding system. */ |
ff0dacd7 | 5376 | |
f10fe38f | 5377 | static bool |
cf84bb53 JB |
5378 | detect_coding_charset (struct coding_system *coding, |
5379 | struct coding_detection_info *detect_info) | |
1397dc18 | 5380 | { |
065e3595 | 5381 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5382 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 5383 | bool multibytep = coding->src_multibyte; |
d311d28c | 5384 | ptrdiff_t consumed_chars = 0; |
07295713 | 5385 | Lisp_Object attrs, valids, name; |
584948ac | 5386 | int found = 0; |
d311d28c | 5387 | ptrdiff_t head_ascii = coding->head_ascii; |
f10fe38f | 5388 | bool check_latin_extra = 0; |
1397dc18 | 5389 | |
ff0dacd7 KH |
5390 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5391 | ||
df7492f9 KH |
5392 | coding = &coding_categories[coding_category_charset]; |
5393 | attrs = CODING_ID_ATTRS (coding->id); | |
5394 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 | 5395 | name = CODING_ID_NAME (coding->id); |
51b59d79 | 5396 | if (strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5397 | "iso-8859-", sizeof ("iso-8859-") - 1) == 0 |
51b59d79 | 5398 | || strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5399 | "iso-latin-", sizeof ("iso-latin-") - 1) == 0) |
07295713 | 5400 | check_latin_extra = 1; |
237aabf4 | 5401 | |
df7492f9 | 5402 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5403 | src += head_ascii; |
1397dc18 | 5404 | |
b73bfc1c | 5405 | while (1) |
1397dc18 | 5406 | { |
df7492f9 | 5407 | int c; |
716b3fa0 KH |
5408 | Lisp_Object val; |
5409 | struct charset *charset; | |
5410 | int dim, idx; | |
1397dc18 | 5411 | |
065e3595 | 5412 | src_base = src; |
df7492f9 | 5413 | ONE_MORE_BYTE (c); |
065e3595 KH |
5414 | if (c < 0) |
5415 | continue; | |
716b3fa0 KH |
5416 | val = AREF (valids, c); |
5417 | if (NILP (val)) | |
df7492f9 | 5418 | break; |
584948ac | 5419 | if (c >= 0x80) |
07295713 KH |
5420 | { |
5421 | if (c < 0xA0 | |
237aabf4 JR |
5422 | && check_latin_extra |
5423 | && (!VECTORP (Vlatin_extra_code_table) | |
28be1ada | 5424 | || NILP (AREF (Vlatin_extra_code_table, c)))) |
07295713 KH |
5425 | break; |
5426 | found = CATEGORY_MASK_CHARSET; | |
5427 | } | |
716b3fa0 KH |
5428 | if (INTEGERP (val)) |
5429 | { | |
5430 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5431 | dim = CHARSET_DIMENSION (charset); | |
5432 | for (idx = 1; idx < dim; idx++) | |
5433 | { | |
5434 | if (src == src_end) | |
5435 | goto too_short; | |
5436 | ONE_MORE_BYTE (c); | |
2f9442b8 PE |
5437 | if (c < charset->code_space[(dim - 1 - idx) * 4] |
5438 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
716b3fa0 KH |
5439 | break; |
5440 | } | |
5441 | if (idx < dim) | |
5442 | break; | |
5443 | } | |
5444 | else | |
5445 | { | |
5446 | idx = 1; | |
5447 | for (; CONSP (val); val = XCDR (val)) | |
5448 | { | |
5449 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5450 | dim = CHARSET_DIMENSION (charset); | |
5451 | while (idx < dim) | |
5452 | { | |
5453 | if (src == src_end) | |
5454 | goto too_short; | |
5455 | ONE_MORE_BYTE (c); | |
5456 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5457 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5458 | break; | |
5459 | idx++; | |
5460 | } | |
5461 | if (idx == dim) | |
5462 | { | |
5463 | val = Qnil; | |
5464 | break; | |
5465 | } | |
5466 | } | |
5467 | if (CONSP (val)) | |
5468 | break; | |
5469 | } | |
df7492f9 | 5470 | } |
716b3fa0 | 5471 | too_short: |
ff0dacd7 | 5472 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5473 | return 0; |
4ed46869 | 5474 | |
df7492f9 | 5475 | no_more_source: |
ff0dacd7 KH |
5476 | detect_info->found |= found; |
5477 | return 1; | |
df7492f9 | 5478 | } |
b73bfc1c | 5479 | |
b73bfc1c | 5480 | static void |
971de7fb | 5481 | decode_coding_charset (struct coding_system *coding) |
4ed46869 | 5482 | { |
8f924df7 KH |
5483 | const unsigned char *src = coding->source + coding->consumed; |
5484 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5485 | const unsigned char *src_base; | |
69a80ea3 | 5486 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 5487 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 5488 | the end. */ |
69a80ea3 | 5489 | int *charbuf_end |
df80c7f0 | 5490 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 5491 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 5492 | bool multibytep = coding->src_multibyte; |
66ebf983 PE |
5493 | Lisp_Object attrs = CODING_ID_ATTRS (coding->id); |
5494 | Lisp_Object valids; | |
d311d28c PE |
5495 | ptrdiff_t char_offset = coding->produced_char; |
5496 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 5497 | int last_id = charset_ascii; |
f10fe38f PE |
5498 | bool eol_dos |
5499 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5500 | int byte_after_cr = -1; |
df7492f9 | 5501 | |
4eb6d3f1 | 5502 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5503 | |
df7492f9 | 5504 | while (1) |
4ed46869 | 5505 | { |
4eb6d3f1 | 5506 | int c; |
24a73b0a KH |
5507 | Lisp_Object val; |
5508 | struct charset *charset; | |
5509 | int dim; | |
5510 | int len = 1; | |
5511 | unsigned code; | |
df7492f9 KH |
5512 | |
5513 | src_base = src; | |
5514 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5515 | |
df7492f9 | 5516 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5517 | { |
5518 | if (byte_after_cr >= 0) | |
5519 | src_base--; | |
5520 | break; | |
5521 | } | |
df7492f9 | 5522 | |
119852e7 KH |
5523 | if (byte_after_cr >= 0) |
5524 | { | |
5525 | c = byte_after_cr; | |
5526 | byte_after_cr = -1; | |
5527 | } | |
5528 | else | |
5529 | { | |
5530 | ONE_MORE_BYTE (c); | |
2735d060 | 5531 | if (eol_dos && c == '\r') |
119852e7 KH |
5532 | ONE_MORE_BYTE (byte_after_cr); |
5533 | } | |
065e3595 KH |
5534 | if (c < 0) |
5535 | goto invalid_code; | |
24a73b0a KH |
5536 | code = c; |
5537 | ||
5538 | val = AREF (valids, c); | |
1b17adfd | 5539 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5540 | goto invalid_code; |
5541 | if (INTEGERP (val)) | |
d46c5b12 | 5542 | { |
24a73b0a KH |
5543 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5544 | dim = CHARSET_DIMENSION (charset); | |
5545 | while (len < dim) | |
b73bfc1c | 5546 | { |
24a73b0a KH |
5547 | ONE_MORE_BYTE (c); |
5548 | code = (code << 8) | c; | |
5549 | len++; | |
b73bfc1c | 5550 | } |
24a73b0a KH |
5551 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5552 | charset, code, c); | |
d46c5b12 | 5553 | } |
df7492f9 | 5554 | else |
d46c5b12 | 5555 | { |
24a73b0a KH |
5556 | /* VAL is a list of charset IDs. It is assured that the |
5557 | list is sorted by charset dimensions (smaller one | |
5558 | comes first). */ | |
5559 | while (CONSP (val)) | |
4eb6d3f1 | 5560 | { |
24a73b0a | 5561 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5562 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5563 | while (len < dim) |
4eb6d3f1 | 5564 | { |
acb2a965 KH |
5565 | ONE_MORE_BYTE (c); |
5566 | code = (code << 8) | c; | |
f9d71dcd | 5567 | len++; |
4eb6d3f1 | 5568 | } |
24a73b0a KH |
5569 | CODING_DECODE_CHAR (coding, src, src_base, |
5570 | src_end, charset, code, c); | |
5571 | if (c >= 0) | |
5572 | break; | |
5573 | val = XCDR (val); | |
ff0dacd7 | 5574 | } |
d46c5b12 | 5575 | } |
24a73b0a KH |
5576 | if (c < 0) |
5577 | goto invalid_code; | |
5578 | if (charset->id != charset_ascii | |
5579 | && last_id != charset->id) | |
5580 | { | |
5581 | if (last_id != charset_ascii) | |
69a80ea3 | 5582 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5583 | last_id = charset->id; |
5584 | last_offset = char_offset; | |
5585 | } | |
5586 | ||
df7492f9 | 5587 | *charbuf++ = c; |
ff0dacd7 | 5588 | char_offset++; |
df7492f9 KH |
5589 | continue; |
5590 | ||
5591 | invalid_code: | |
5592 | src = src_base; | |
5593 | consumed_chars = consumed_chars_base; | |
5594 | ONE_MORE_BYTE (c); | |
065e3595 | 5595 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5596 | char_offset++; |
df7492f9 | 5597 | coding->errors++; |
4ed46869 KH |
5598 | } |
5599 | ||
df7492f9 | 5600 | no_more_source: |
ff0dacd7 | 5601 | if (last_id != charset_ascii) |
69a80ea3 | 5602 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5603 | coding->consumed_char += consumed_chars_base; |
5604 | coding->consumed = src_base - coding->source; | |
5605 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5606 | } |
5607 | ||
f10fe38f | 5608 | static bool |
971de7fb | 5609 | encode_coding_charset (struct coding_system *coding) |
4ed46869 | 5610 | { |
f10fe38f | 5611 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5612 | int *charbuf = coding->charbuf; |
5613 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5614 | unsigned char *dst = coding->destination + coding->produced; | |
5615 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5616 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
d311d28c | 5617 | ptrdiff_t produced_chars = 0; |
24a73b0a | 5618 | Lisp_Object attrs, charset_list; |
f10fe38f | 5619 | bool ascii_compatible; |
b73bfc1c | 5620 | int c; |
b73bfc1c | 5621 | |
24a73b0a | 5622 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5623 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5624 | |
df7492f9 | 5625 | while (charbuf < charbuf_end) |
4ed46869 | 5626 | { |
4eb6d3f1 | 5627 | struct charset *charset; |
df7492f9 | 5628 | unsigned code; |
8f924df7 | 5629 | |
df7492f9 KH |
5630 | ASSURE_DESTINATION (safe_room); |
5631 | c = *charbuf++; | |
5632 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5633 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5634 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5635 | { |
16eafb5d KH |
5636 | c = CHAR_TO_BYTE8 (c); |
5637 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5638 | } |
d46c5b12 | 5639 | else |
b73bfc1c | 5640 | { |
5eb05ea3 KH |
5641 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
5642 | &code, charset); | |
5643 | ||
4eb6d3f1 KH |
5644 | if (charset) |
5645 | { | |
5646 | if (CHARSET_DIMENSION (charset) == 1) | |
5647 | EMIT_ONE_BYTE (code); | |
5648 | else if (CHARSET_DIMENSION (charset) == 2) | |
5649 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5650 | else if (CHARSET_DIMENSION (charset) == 3) | |
5651 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5652 | else | |
5653 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5654 | (code >> 8) & 0xFF, code & 0xFF); | |
5655 | } | |
5656 | else | |
41cbe562 KH |
5657 | { |
5658 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5659 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5660 | else | |
5661 | c = coding->default_char; | |
5662 | EMIT_ONE_BYTE (c); | |
5663 | } | |
4ed46869 | 5664 | } |
4ed46869 KH |
5665 | } |
5666 | ||
065e3595 | 5667 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5668 | coding->produced_char += produced_chars; |
5669 | coding->produced = dst - coding->destination; | |
5670 | return 0; | |
4ed46869 KH |
5671 | } |
5672 | ||
5673 | \f | |
1397dc18 | 5674 | /*** 7. C library functions ***/ |
4ed46869 | 5675 | |
df7492f9 KH |
5676 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5677 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5678 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5679 | |
ec6d2bb8 | 5680 | void |
971de7fb | 5681 | setup_coding_system (Lisp_Object coding_system, struct coding_system *coding) |
4ed46869 | 5682 | { |
df7492f9 KH |
5683 | Lisp_Object attrs; |
5684 | Lisp_Object eol_type; | |
5685 | Lisp_Object coding_type; | |
4608c386 | 5686 | Lisp_Object val; |
4ed46869 | 5687 | |
df7492f9 | 5688 | if (NILP (coding_system)) |
ae6f73fa | 5689 | coding_system = Qundecided; |
c07c8e12 | 5690 | |
df7492f9 | 5691 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5692 | |
df7492f9 | 5693 | attrs = CODING_ID_ATTRS (coding->id); |
0a9564cb | 5694 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
1f5dbf34 | 5695 | |
df7492f9 | 5696 | coding->mode = 0; |
4a015c45 KH |
5697 | if (VECTORP (eol_type)) |
5698 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5699 | | CODING_REQUIRE_DETECTION_MASK); | |
5700 | else if (! EQ (eol_type, Qunix)) | |
5701 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5702 | | CODING_REQUIRE_ENCODING_MASK); | |
5703 | else | |
5704 | coding->common_flags = 0; | |
5e5c78be KH |
5705 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5706 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5707 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5708 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5709 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5710 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5711 | |
df7492f9 | 5712 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 | 5713 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5714 | coding->safe_charsets = SDATA (val); |
df7492f9 | 5715 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
624bda09 | 5716 | coding->carryover_bytes = 0; |
4608c386 | 5717 | |
df7492f9 KH |
5718 | coding_type = CODING_ATTR_TYPE (attrs); |
5719 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5720 | { |
df7492f9 KH |
5721 | coding->detector = NULL; |
5722 | coding->decoder = decode_coding_raw_text; | |
5723 | coding->encoder = encode_coding_raw_text; | |
5724 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
c3a7b3f4 | 5725 | coding->spec.undecided.inhibit_nbd |
9c90cc06 PE |
5726 | = (encode_inhibit_flag |
5727 | (AREF (attrs, coding_attr_undecided_inhibit_null_byte_detection))); | |
c3a7b3f4 | 5728 | coding->spec.undecided.inhibit_ied |
9c90cc06 PE |
5729 | = (encode_inhibit_flag |
5730 | (AREF (attrs, coding_attr_undecided_inhibit_iso_escape_detection))); | |
c3a7b3f4 KH |
5731 | coding->spec.undecided.prefer_utf_8 |
5732 | = ! NILP (AREF (attrs, coding_attr_undecided_prefer_utf_8)); | |
d46c5b12 | 5733 | } |
df7492f9 | 5734 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5735 | { |
df7492f9 KH |
5736 | int i; |
5737 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5738 | ||
5739 | /* Invoke graphic register 0 to plane 0. */ | |
5740 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5741 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5742 | CODING_ISO_INVOCATION (coding, 1) | |
5743 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5744 | /* Setup the initial status of designation. */ | |
5745 | for (i = 0; i < 4; i++) | |
5746 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5747 | /* Not single shifting initially. */ | |
5748 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5749 | /* Beginning of buffer should also be regarded as bol. */ | |
5750 | CODING_ISO_BOL (coding) = 1; | |
5751 | coding->detector = detect_coding_iso_2022; | |
5752 | coding->decoder = decode_coding_iso_2022; | |
5753 | coding->encoder = encode_coding_iso_2022; | |
5754 | if (flags & CODING_ISO_FLAG_SAFE) | |
5755 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5756 | coding->common_flags |
df7492f9 KH |
5757 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5758 | | CODING_REQUIRE_FLUSHING_MASK); | |
5759 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5760 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5761 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5762 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5763 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5764 | { | |
5765 | setup_iso_safe_charsets (attrs); | |
5766 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 5767 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5768 | coding->safe_charsets = SDATA (val); |
df7492f9 KH |
5769 | } |
5770 | CODING_ISO_FLAGS (coding) = flags; | |
e951386e KH |
5771 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; |
5772 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | |
5773 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | |
5774 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
d46c5b12 | 5775 | } |
df7492f9 | 5776 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5777 | { |
df7492f9 KH |
5778 | coding->detector = detect_coding_charset; |
5779 | coding->decoder = decode_coding_charset; | |
5780 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5781 | coding->common_flags |
df7492f9 | 5782 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5783 | } |
df7492f9 | 5784 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5785 | { |
a470d443 KH |
5786 | val = AREF (attrs, coding_attr_utf_bom); |
5787 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5788 | : EQ (val, Qt) ? utf_with_bom | |
5789 | : utf_without_bom); | |
df7492f9 KH |
5790 | coding->detector = detect_coding_utf_8; |
5791 | coding->decoder = decode_coding_utf_8; | |
5792 | coding->encoder = encode_coding_utf_8; | |
5793 | coding->common_flags | |
5794 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5795 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5796 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5797 | } |
5798 | else if (EQ (coding_type, Qutf_16)) | |
5799 | { | |
a470d443 KH |
5800 | val = AREF (attrs, coding_attr_utf_bom); |
5801 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5802 | : EQ (val, Qt) ? utf_with_bom | |
5803 | : utf_without_bom); | |
df7492f9 | 5804 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5805 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5806 | : utf_16_little_endian); |
e19c3639 | 5807 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5808 | coding->detector = detect_coding_utf_16; |
5809 | coding->decoder = decode_coding_utf_16; | |
5810 | coding->encoder = encode_coding_utf_16; | |
5811 | coding->common_flags | |
5812 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5813 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5814 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5815 | } |
df7492f9 | 5816 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5817 | { |
df7492f9 KH |
5818 | coding->detector = detect_coding_ccl; |
5819 | coding->decoder = decode_coding_ccl; | |
5820 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5821 | coding->common_flags |
df7492f9 KH |
5822 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5823 | | CODING_REQUIRE_FLUSHING_MASK); | |
5824 | } | |
5825 | else if (EQ (coding_type, Qemacs_mule)) | |
5826 | { | |
5827 | coding->detector = detect_coding_emacs_mule; | |
5828 | coding->decoder = decode_coding_emacs_mule; | |
5829 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5830 | coding->common_flags |
df7492f9 KH |
5831 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5832 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5833 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5834 | { | |
5835 | Lisp_Object tail, safe_charsets; | |
5836 | int max_charset_id = 0; | |
5837 | ||
5838 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5839 | tail = XCDR (tail)) | |
5840 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5841 | max_charset_id = XFASTINT (XCAR (tail)); | |
1b3b981b AS |
5842 | safe_charsets = make_uninit_string (max_charset_id + 1); |
5843 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
5844 | for (tail = Vemacs_mule_charset_list; CONSP (tail); |
5845 | tail = XCDR (tail)) | |
8f924df7 | 5846 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5847 | coding->max_charset_id = max_charset_id; |
1b3b981b | 5848 | coding->safe_charsets = SDATA (safe_charsets); |
df7492f9 | 5849 | } |
e951386e KH |
5850 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; |
5851 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | |
df7492f9 KH |
5852 | } |
5853 | else if (EQ (coding_type, Qshift_jis)) | |
5854 | { | |
5855 | coding->detector = detect_coding_sjis; | |
5856 | coding->decoder = decode_coding_sjis; | |
5857 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5858 | coding->common_flags |
df7492f9 KH |
5859 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5860 | } | |
5861 | else if (EQ (coding_type, Qbig5)) | |
5862 | { | |
5863 | coding->detector = detect_coding_big5; | |
5864 | coding->decoder = decode_coding_big5; | |
5865 | coding->encoder = encode_coding_big5; | |
c952af22 | 5866 | coding->common_flags |
df7492f9 KH |
5867 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5868 | } | |
5869 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5870 | { |
df7492f9 KH |
5871 | coding->detector = NULL; |
5872 | coding->decoder = decode_coding_raw_text; | |
5873 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5874 | if (! EQ (eol_type, Qunix)) |
5875 | { | |
5876 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5877 | if (! VECTORP (eol_type)) | |
5878 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5879 | } | |
5880 | ||
4ed46869 | 5881 | } |
4ed46869 | 5882 | |
df7492f9 | 5883 | return; |
4ed46869 KH |
5884 | } |
5885 | ||
0ff61e78 KH |
5886 | /* Return a list of charsets supported by CODING. */ |
5887 | ||
5888 | Lisp_Object | |
971de7fb | 5889 | coding_charset_list (struct coding_system *coding) |
0ff61e78 | 5890 | { |
35befdaa | 5891 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5892 | |
5893 | CODING_GET_INFO (coding, attrs, charset_list); | |
5894 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5895 | { | |
5896 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5897 | ||
5898 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5899 | charset_list = Viso_2022_charset_list; | |
5900 | } | |
5901 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5902 | { | |
5903 | charset_list = Vemacs_mule_charset_list; | |
5904 | } | |
5905 | return charset_list; | |
5906 | } | |
5907 | ||
5908 | ||
e9f91ece KH |
5909 | /* Return a list of charsets supported by CODING-SYSTEM. */ |
5910 | ||
5911 | Lisp_Object | |
971de7fb | 5912 | coding_system_charset_list (Lisp_Object coding_system) |
e9f91ece | 5913 | { |
d3411f89 | 5914 | ptrdiff_t id; |
e9f91ece KH |
5915 | Lisp_Object attrs, charset_list; |
5916 | ||
5917 | CHECK_CODING_SYSTEM_GET_ID (coding_system, id); | |
5918 | attrs = CODING_ID_ATTRS (id); | |
5919 | ||
5920 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5921 | { | |
5922 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5923 | ||
5924 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5925 | charset_list = Viso_2022_charset_list; | |
5926 | else | |
5927 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5928 | } | |
5929 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5930 | { | |
5931 | charset_list = Vemacs_mule_charset_list; | |
5932 | } | |
5933 | else | |
5934 | { | |
5935 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5936 | } | |
5937 | return charset_list; | |
5938 | } | |
5939 | ||
5940 | ||
df7492f9 KH |
5941 | /* Return raw-text or one of its subsidiaries that has the same |
5942 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5943 | |
df7492f9 | 5944 | Lisp_Object |
971de7fb | 5945 | raw_text_coding_system (Lisp_Object coding_system) |
ec6d2bb8 | 5946 | { |
0be8721c | 5947 | Lisp_Object spec, attrs; |
df7492f9 | 5948 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5949 | |
d3e4cb56 KH |
5950 | if (NILP (coding_system)) |
5951 | return Qraw_text; | |
df7492f9 KH |
5952 | spec = CODING_SYSTEM_SPEC (coding_system); |
5953 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5954 | |
df7492f9 KH |
5955 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5956 | return coding_system; | |
ec6d2bb8 | 5957 | |
df7492f9 KH |
5958 | eol_type = AREF (spec, 2); |
5959 | if (VECTORP (eol_type)) | |
5960 | return Qraw_text; | |
5961 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5962 | raw_text_eol_type = AREF (spec, 2); | |
5963 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5964 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5965 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5966 | } |
5967 | ||
54f78171 | 5968 | |
1911a33b KH |
5969 | /* If CODING_SYSTEM doesn't specify end-of-line format, return one of |
5970 | the subsidiary that has the same eol-spec as PARENT (if it is not | |
5971 | nil and specifies end-of-line format) or the system's setting | |
fcbcfb64 | 5972 | (system_eol_type). */ |
df7492f9 KH |
5973 | |
5974 | Lisp_Object | |
971de7fb | 5975 | coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent) |
54f78171 | 5976 | { |
3e139625 | 5977 | Lisp_Object spec, eol_type; |
54f78171 | 5978 | |
d3e4cb56 KH |
5979 | if (NILP (coding_system)) |
5980 | coding_system = Qraw_text; | |
df7492f9 | 5981 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5982 | eol_type = AREF (spec, 2); |
fcbcfb64 | 5983 | if (VECTORP (eol_type)) |
df7492f9 | 5984 | { |
df7492f9 KH |
5985 | Lisp_Object parent_eol_type; |
5986 | ||
fcbcfb64 KH |
5987 | if (! NILP (parent)) |
5988 | { | |
5989 | Lisp_Object parent_spec; | |
5990 | ||
4a015c45 | 5991 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 | 5992 | parent_eol_type = AREF (parent_spec, 2); |
1911a33b | 5993 | if (VECTORP (parent_eol_type)) |
4628bef1 | 5994 | parent_eol_type = system_eol_type; |
fcbcfb64 KH |
5995 | } |
5996 | else | |
5997 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
5998 | if (EQ (parent_eol_type, Qunix)) |
5999 | coding_system = AREF (eol_type, 0); | |
6000 | else if (EQ (parent_eol_type, Qdos)) | |
6001 | coding_system = AREF (eol_type, 1); | |
6002 | else if (EQ (parent_eol_type, Qmac)) | |
6003 | coding_system = AREF (eol_type, 2); | |
54f78171 | 6004 | } |
df7492f9 | 6005 | return coding_system; |
54f78171 KH |
6006 | } |
6007 | ||
fcaf8878 KH |
6008 | |
6009 | /* Check if text-conversion and eol-conversion of CODING_SYSTEM are | |
6010 | decided for writing to a process. If not, complement them, and | |
6011 | return a new coding system. */ | |
6012 | ||
6013 | Lisp_Object | |
4628bef1 | 6014 | complement_process_encoding_system (Lisp_Object coding_system) |
fcaf8878 | 6015 | { |
5886ec9c KH |
6016 | Lisp_Object coding_base = Qnil, eol_base = Qnil; |
6017 | Lisp_Object spec, attrs; | |
93d50df8 | 6018 | int i; |
fcaf8878 | 6019 | |
93d50df8 | 6020 | for (i = 0; i < 3; i++) |
fcaf8878 | 6021 | { |
93d50df8 KH |
6022 | if (i == 1) |
6023 | coding_system = CDR_SAFE (Vdefault_process_coding_system); | |
6024 | else if (i == 2) | |
6025 | coding_system = preferred_coding_system (); | |
6026 | spec = CODING_SYSTEM_SPEC (coding_system); | |
6027 | if (NILP (spec)) | |
6028 | continue; | |
6029 | attrs = AREF (spec, 0); | |
6030 | if (NILP (coding_base) && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
6031 | coding_base = CODING_ATTR_BASE_NAME (attrs); | |
6032 | if (NILP (eol_base) && ! VECTORP (AREF (spec, 2))) | |
6033 | eol_base = coding_system; | |
6034 | if (! NILP (coding_base) && ! NILP (eol_base)) | |
6035 | break; | |
fcaf8878 | 6036 | } |
fcaf8878 | 6037 | |
93d50df8 KH |
6038 | if (i > 0) |
6039 | /* The original CODING_SYSTEM didn't specify text-conversion or | |
6040 | eol-conversion. Be sure that we return a fully complemented | |
6041 | coding system. */ | |
6042 | coding_system = coding_inherit_eol_type (coding_base, eol_base); | |
6043 | return coding_system; | |
fcaf8878 KH |
6044 | } |
6045 | ||
6046 | ||
4ed46869 KH |
6047 | /* Emacs has a mechanism to automatically detect a coding system if it |
6048 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
6049 | it's impossible to distinguish some coding systems accurately | |
6050 | because they use the same range of codes. So, at first, coding | |
6051 | systems are categorized into 7, those are: | |
6052 | ||
0ef69138 | 6053 | o coding-category-emacs-mule |
4ed46869 KH |
6054 | |
6055 | The category for a coding system which has the same code range | |
6056 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 6057 | symbol) `emacs-mule' by default. |
4ed46869 KH |
6058 | |
6059 | o coding-category-sjis | |
6060 | ||
6061 | The category for a coding system which has the same code range | |
6062 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 6063 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
6064 | |
6065 | o coding-category-iso-7 | |
6066 | ||
6067 | The category for a coding system which has the same code range | |
7717c392 | 6068 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
6069 | shift and single shift functions. This can encode/decode all |
6070 | charsets. Assigned the coding-system (Lisp symbol) | |
6071 | `iso-2022-7bit' by default. | |
6072 | ||
6073 | o coding-category-iso-7-tight | |
6074 | ||
6075 | Same as coding-category-iso-7 except that this can | |
6076 | encode/decode only the specified charsets. | |
4ed46869 KH |
6077 | |
6078 | o coding-category-iso-8-1 | |
6079 | ||
6080 | The category for a coding system which has the same code range | |
6081 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6082 | for DIMENSION1 charset. This doesn't use any locking shift |
6083 | and single shift functions. Assigned the coding-system (Lisp | |
6084 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
6085 | |
6086 | o coding-category-iso-8-2 | |
6087 | ||
6088 | The category for a coding system which has the same code range | |
6089 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6090 | for DIMENSION2 charset. This doesn't use any locking shift |
6091 | and single shift functions. Assigned the coding-system (Lisp | |
6092 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 6093 | |
7717c392 | 6094 | o coding-category-iso-7-else |
4ed46869 KH |
6095 | |
6096 | The category for a coding system which has the same code range | |
ad1746f5 | 6097 | as ISO2022 of 7-bit environment but uses locking shift or |
7717c392 KH |
6098 | single shift functions. Assigned the coding-system (Lisp |
6099 | symbol) `iso-2022-7bit-lock' by default. | |
6100 | ||
6101 | o coding-category-iso-8-else | |
6102 | ||
6103 | The category for a coding system which has the same code range | |
ad1746f5 | 6104 | as ISO2022 of 8-bit environment but uses locking shift or |
7717c392 KH |
6105 | single shift functions. Assigned the coding-system (Lisp |
6106 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
6107 | |
6108 | o coding-category-big5 | |
6109 | ||
6110 | The category for a coding system which has the same code range | |
6111 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6112 | `cn-big5' by default. |
4ed46869 | 6113 | |
fa42c37f KH |
6114 | o coding-category-utf-8 |
6115 | ||
6116 | The category for a coding system which has the same code range | |
6e76ae91 | 6117 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
6118 | symbol) `utf-8' by default. |
6119 | ||
6120 | o coding-category-utf-16-be | |
6121 | ||
6122 | The category for a coding system in which a text has an | |
6123 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
6124 | endian at the head. Assigned the coding-system (Lisp symbol) | |
6125 | `utf-16-be' by default. | |
6126 | ||
6127 | o coding-category-utf-16-le | |
6128 | ||
6129 | The category for a coding system in which a text has an | |
6130 | Unicode signature (cf. Unicode Standard) in the order of | |
6131 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
6132 | symbol) `utf-16-le' by default. | |
6133 | ||
1397dc18 KH |
6134 | o coding-category-ccl |
6135 | ||
6136 | The category for a coding system of which encoder/decoder is | |
6137 | written in CCL programs. The default value is nil, i.e., no | |
6138 | coding system is assigned. | |
6139 | ||
4ed46869 KH |
6140 | o coding-category-binary |
6141 | ||
6142 | The category for a coding system not categorized in any of the | |
6143 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6144 | `no-conversion' by default. |
4ed46869 KH |
6145 | |
6146 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 6147 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
6148 | What Emacs does actually is to detect a category of coding system. |
6149 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 6150 | decide only one possible category, it selects a category of the |
4ed46869 KH |
6151 | highest priority. Priorities of categories are also specified by a |
6152 | user in a Lisp variable `coding-category-list'. | |
6153 | ||
6154 | */ | |
6155 | ||
251e9147 KH |
6156 | static Lisp_Object adjust_coding_eol_type (struct coding_system *coding, |
6157 | int eol_seen); | |
8a44e6d1 KH |
6158 | |
6159 | ||
251e9147 | 6160 | /* Return the number of ASCII characters at the head of the source. |
e6d2f155 KH |
6161 | By side effects, set coding->head_ascii and update |
6162 | coding->eol_seen. The value of coding->eol_seen is "logical or" of | |
6163 | EOL_SEEN_LF, EOL_SEEN_CR, and EOL_SEEN_CRLF, but the value is | |
6164 | reliable only when all the source bytes are ASCII. */ | |
8a44e6d1 | 6165 | |
251e9147 KH |
6166 | static int |
6167 | check_ascii (struct coding_system *coding) | |
8a44e6d1 KH |
6168 | { |
6169 | const unsigned char *src, *end; | |
6170 | Lisp_Object eol_type = CODING_ID_EOL_TYPE (coding->id); | |
e6d2f155 | 6171 | int eol_seen = coding->eol_seen; |
8a44e6d1 | 6172 | |
8a44e6d1 KH |
6173 | coding_set_source (coding); |
6174 | src = coding->source; | |
6175 | end = src + coding->src_bytes; | |
6176 | ||
251e9147 | 6177 | if (inhibit_eol_conversion |
e6d2f155 | 6178 | || SYMBOLP (eol_type)) |
8a44e6d1 KH |
6179 | { |
6180 | /* We don't have to check EOL format. */ | |
e6d2f155 | 6181 | while (src < end && !( *src & 0x80)) |
251e9147 | 6182 | { |
e6d2f155 KH |
6183 | if (*src++ == '\n') |
6184 | eol_seen |= EOL_SEEN_LF; | |
251e9147 | 6185 | } |
8a44e6d1 KH |
6186 | } |
6187 | else | |
6188 | { | |
251e9147 | 6189 | end--; /* We look ahead one byte for "CR LF". */ |
8a44e6d1 KH |
6190 | while (src < end) |
6191 | { | |
6192 | int c = *src; | |
6193 | ||
6194 | if (c & 0x80) | |
6195 | break; | |
6196 | src++; | |
251e9147 KH |
6197 | if (c == '\r') |
6198 | { | |
6199 | if (*src == '\n') | |
6200 | { | |
6201 | eol_seen |= EOL_SEEN_CRLF; | |
6202 | src++; | |
6203 | } | |
6204 | else | |
6205 | eol_seen |= EOL_SEEN_CR; | |
6206 | } | |
6207 | else if (c == '\n') | |
6208 | eol_seen |= EOL_SEEN_LF; | |
6209 | } | |
6210 | if (src == end) | |
6211 | { | |
6212 | int c = *src; | |
6213 | ||
6214 | /* All bytes but the last one C are ASCII. */ | |
6215 | if (! (c & 0x80)) | |
6216 | { | |
6217 | if (c == '\r') | |
6218 | eol_seen |= EOL_SEEN_CR; | |
6219 | else if (c == '\n') | |
6220 | eol_seen |= EOL_SEEN_LF; | |
6221 | src++; | |
6222 | } | |
6223 | } | |
6224 | } | |
6225 | coding->head_ascii = src - coding->source; | |
6226 | coding->eol_seen = eol_seen; | |
6227 | return (coding->head_ascii); | |
6228 | } | |
6229 | ||
6230 | ||
8ead3901 | 6231 | /* Return the number of characters at the source if all the bytes are |
251e9147 KH |
6232 | valid UTF-8 (of Unicode range). Otherwise, return -1. By side |
6233 | effects, update coding->eol_seen. The value of coding->eol_seen is | |
6234 | "logical or" of EOL_SEEN_LF, EOL_SEEN_CR, and EOL_SEEN_CRLF, but | |
6235 | the value is reliable only when all the source bytes are valid | |
6236 | UTF-8. */ | |
6237 | ||
6238 | static int | |
6239 | check_utf_8 (struct coding_system *coding) | |
6240 | { | |
6241 | const unsigned char *src, *end; | |
e6d2f155 | 6242 | int eol_seen; |
251e9147 KH |
6243 | int nchars = coding->head_ascii; |
6244 | ||
6245 | if (coding->head_ascii < 0) | |
6246 | check_ascii (coding); | |
6247 | else | |
6248 | coding_set_source (coding); | |
6249 | src = coding->source + coding->head_ascii; | |
6250 | /* We look ahead one byte for CR LF. */ | |
6251 | end = coding->source + coding->src_bytes - 1; | |
e6d2f155 | 6252 | eol_seen = coding->eol_seen; |
251e9147 KH |
6253 | while (src < end) |
6254 | { | |
6255 | int c = *src; | |
6256 | ||
6257 | if (UTF_8_1_OCTET_P (*src)) | |
6258 | { | |
6259 | src++; | |
8a44e6d1 KH |
6260 | if (c < 0x20) |
6261 | { | |
6262 | if (c == '\r') | |
6263 | { | |
6264 | if (*src == '\n') | |
6265 | { | |
6266 | eol_seen |= EOL_SEEN_CRLF; | |
6267 | src++; | |
251e9147 | 6268 | nchars++; |
8a44e6d1 KH |
6269 | } |
6270 | else | |
6271 | eol_seen |= EOL_SEEN_CR; | |
6272 | } | |
6273 | else if (c == '\n') | |
6274 | eol_seen |= EOL_SEEN_LF; | |
6275 | } | |
6276 | } | |
251e9147 | 6277 | else if (UTF_8_2_OCTET_LEADING_P (c)) |
8a44e6d1 | 6278 | { |
251e9147 KH |
6279 | if (c < 0xC2 /* overlong sequence */ |
6280 | || src + 1 >= end | |
6281 | || ! UTF_8_EXTRA_OCTET_P (src[1])) | |
6282 | return -1; | |
6283 | src += 2; | |
8a44e6d1 | 6284 | } |
251e9147 KH |
6285 | else if (UTF_8_3_OCTET_LEADING_P (c)) |
6286 | { | |
6287 | if (src + 2 >= end | |
6288 | || ! (UTF_8_EXTRA_OCTET_P (src[1]) | |
6289 | && UTF_8_EXTRA_OCTET_P (src[2]))) | |
6290 | return -1; | |
6291 | c = (((c & 0xF) << 12) | |
6292 | | ((src[1] & 0x3F) << 6) | (src[2] & 0x3F)); | |
6293 | if (c < 0x800 /* overlong sequence */ | |
6294 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
6295 | return -1; | |
6296 | src += 3; | |
6297 | } | |
6298 | else if (UTF_8_4_OCTET_LEADING_P (c)) | |
6299 | { | |
6300 | if (src + 3 >= end | |
6301 | || ! (UTF_8_EXTRA_OCTET_P (src[1]) | |
6302 | && UTF_8_EXTRA_OCTET_P (src[2]) | |
6303 | && UTF_8_EXTRA_OCTET_P (src[3]))) | |
6304 | return -1; | |
6305 | c = (((c & 0x7) << 18) | ((src[1] & 0x3F) << 12) | |
6306 | | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F)); | |
6307 | if (c < 0x10000 /* overlong sequence */ | |
6308 | || c >= 0x110000) /* non-Unicode character */ | |
6309 | return -1; | |
6310 | src += 4; | |
6311 | } | |
6312 | else | |
6313 | return -1; | |
6314 | nchars++; | |
6315 | } | |
6316 | ||
6317 | if (src == end) | |
6318 | { | |
6319 | if (! UTF_8_1_OCTET_P (*src)) | |
6320 | return -1; | |
6321 | nchars++; | |
6322 | if (*src == '\r') | |
6323 | eol_seen |= EOL_SEEN_CR; | |
6324 | else if (*src == '\n') | |
6325 | eol_seen |= EOL_SEEN_LF; | |
8a44e6d1 | 6326 | } |
8a44e6d1 | 6327 | coding->eol_seen = eol_seen; |
251e9147 | 6328 | return nchars; |
8a44e6d1 KH |
6329 | } |
6330 | ||
6331 | ||
ff0dacd7 KH |
6332 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
6333 | SOURCE is encoded. If CATEGORY is one of | |
6334 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
6335 | two-byte, else they are encoded by one-byte. | |
6336 | ||
6337 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 6338 | |
bc4bc72a | 6339 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
6340 | |
6341 | static int | |
d311d28c | 6342 | detect_eol (const unsigned char *source, ptrdiff_t src_bytes, |
cf84bb53 | 6343 | enum coding_category category) |
4ed46869 | 6344 | { |
f6cbaf43 | 6345 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 6346 | unsigned char c; |
df7492f9 KH |
6347 | int total = 0; |
6348 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 6349 | |
89528eb3 | 6350 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 6351 | { |
f10fe38f PE |
6352 | bool msb = category == (coding_category_utf_16_le |
6353 | | coding_category_utf_16_le_nosig); | |
6354 | bool lsb = !msb; | |
fa42c37f | 6355 | |
df7492f9 | 6356 | while (src + 1 < src_end) |
fa42c37f | 6357 | { |
df7492f9 KH |
6358 | c = src[lsb]; |
6359 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 6360 | { |
df7492f9 KH |
6361 | int this_eol; |
6362 | ||
6363 | if (c == '\n') | |
6364 | this_eol = EOL_SEEN_LF; | |
6365 | else if (src + 3 >= src_end | |
6366 | || src[msb + 2] != 0 | |
6367 | || src[lsb + 2] != '\n') | |
6368 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 6369 | else |
75f4f1ac EZ |
6370 | { |
6371 | this_eol = EOL_SEEN_CRLF; | |
6372 | src += 2; | |
6373 | } | |
df7492f9 KH |
6374 | |
6375 | if (eol_seen == EOL_SEEN_NONE) | |
6376 | /* This is the first end-of-line. */ | |
6377 | eol_seen = this_eol; | |
6378 | else if (eol_seen != this_eol) | |
fa42c37f | 6379 | { |
75f4f1ac EZ |
6380 | /* The found type is different from what found before. |
6381 | Allow for stray ^M characters in DOS EOL files. */ | |
ef1b0ba7 SM |
6382 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) |
6383 | || (eol_seen == EOL_SEEN_CRLF | |
6384 | && this_eol == EOL_SEEN_CR)) | |
75f4f1ac EZ |
6385 | eol_seen = EOL_SEEN_CRLF; |
6386 | else | |
6387 | { | |
6388 | eol_seen = EOL_SEEN_LF; | |
6389 | break; | |
6390 | } | |
fa42c37f | 6391 | } |
df7492f9 KH |
6392 | if (++total == MAX_EOL_CHECK_COUNT) |
6393 | break; | |
fa42c37f | 6394 | } |
df7492f9 | 6395 | src += 2; |
fa42c37f | 6396 | } |
bcf26d6a | 6397 | } |
d46c5b12 | 6398 | else |
ef1b0ba7 SM |
6399 | while (src < src_end) |
6400 | { | |
6401 | c = *src++; | |
6402 | if (c == '\n' || c == '\r') | |
6403 | { | |
6404 | int this_eol; | |
d46c5b12 | 6405 | |
ef1b0ba7 SM |
6406 | if (c == '\n') |
6407 | this_eol = EOL_SEEN_LF; | |
6408 | else if (src >= src_end || *src != '\n') | |
6409 | this_eol = EOL_SEEN_CR; | |
6410 | else | |
6411 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 6412 | |
ef1b0ba7 SM |
6413 | if (eol_seen == EOL_SEEN_NONE) |
6414 | /* This is the first end-of-line. */ | |
6415 | eol_seen = this_eol; | |
6416 | else if (eol_seen != this_eol) | |
6417 | { | |
6418 | /* The found type is different from what found before. | |
6419 | Allow for stray ^M characters in DOS EOL files. */ | |
6420 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) | |
6421 | || (eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR)) | |
6422 | eol_seen = EOL_SEEN_CRLF; | |
6423 | else | |
6424 | { | |
6425 | eol_seen = EOL_SEEN_LF; | |
6426 | break; | |
6427 | } | |
6428 | } | |
6429 | if (++total == MAX_EOL_CHECK_COUNT) | |
6430 | break; | |
6431 | } | |
6432 | } | |
df7492f9 | 6433 | return eol_seen; |
73be902c KH |
6434 | } |
6435 | ||
df7492f9 | 6436 | |
24a73b0a | 6437 | static Lisp_Object |
971de7fb | 6438 | adjust_coding_eol_type (struct coding_system *coding, int eol_seen) |
73be902c | 6439 | { |
0be8721c | 6440 | Lisp_Object eol_type; |
8f924df7 | 6441 | |
df7492f9 | 6442 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
251e9147 KH |
6443 | if (! VECTORP (eol_type)) |
6444 | /* Already adjusted. */ | |
6445 | return eol_type; | |
df7492f9 | 6446 | if (eol_seen & EOL_SEEN_LF) |
24a73b0a KH |
6447 | { |
6448 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6449 | eol_type = Qunix; | |
6450 | } | |
6f197c07 | 6451 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
6452 | { |
6453 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
6454 | eol_type = Qdos; | |
6455 | } | |
6f197c07 | 6456 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
6457 | { |
6458 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
6459 | eol_type = Qmac; | |
6460 | } | |
6461 | return eol_type; | |
d46c5b12 | 6462 | } |
4ed46869 | 6463 | |
df7492f9 KH |
6464 | /* Detect how a text specified in CODING is encoded. If a coding |
6465 | system is detected, update fields of CODING by the detected coding | |
6466 | system. */ | |
0a28aafb | 6467 | |
74ab6df5 | 6468 | static void |
971de7fb | 6469 | detect_coding (struct coding_system *coding) |
d46c5b12 | 6470 | { |
8f924df7 | 6471 | const unsigned char *src, *src_end; |
f10fe38f | 6472 | unsigned int saved_mode = coding->mode; |
e6d2f155 KH |
6473 | Lisp_Object found = Qnil; |
6474 | Lisp_Object eol_type = CODING_ID_EOL_TYPE (coding->id); | |
d46c5b12 | 6475 | |
df7492f9 KH |
6476 | coding->consumed = coding->consumed_char = 0; |
6477 | coding->produced = coding->produced_char = 0; | |
6478 | coding_set_source (coding); | |
1c3478b0 | 6479 | |
df7492f9 | 6480 | src_end = coding->source + coding->src_bytes; |
1c3478b0 | 6481 | |
e6d2f155 | 6482 | coding->eol_seen = EOL_SEEN_NONE; |
df7492f9 KH |
6483 | /* If we have not yet decided the text encoding type, detect it |
6484 | now. */ | |
6485 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 6486 | { |
df7492f9 | 6487 | int c, i; |
6cb21a4f | 6488 | struct coding_detection_info detect_info; |
f10fe38f | 6489 | bool null_byte_found = 0, eight_bit_found = 0; |
9c90cc06 PE |
6490 | bool inhibit_nbd = inhibit_flag (coding->spec.undecided.inhibit_nbd, |
6491 | inhibit_null_byte_detection); | |
6492 | bool inhibit_ied = inhibit_flag (coding->spec.undecided.inhibit_ied, | |
6493 | inhibit_iso_escape_detection); | |
6494 | bool prefer_utf_8 = coding->spec.undecided.prefer_utf_8; | |
df7492f9 | 6495 | |
8a44e6d1 | 6496 | coding->head_ascii = 0; |
6cb21a4f | 6497 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 6498 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 6499 | { |
df7492f9 | 6500 | c = *src; |
6cb21a4f | 6501 | if (c & 0x80) |
6cb21a4f | 6502 | { |
2f3cbb32 | 6503 | eight_bit_found = 1; |
2f3cbb32 KH |
6504 | if (null_byte_found) |
6505 | break; | |
6506 | } | |
6507 | else if (c < 0x20) | |
6508 | { | |
6509 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
c3a7b3f4 | 6510 | && ! inhibit_ied |
2f3cbb32 | 6511 | && ! detect_info.checked) |
6cb21a4f | 6512 | { |
2f3cbb32 KH |
6513 | if (detect_coding_iso_2022 (coding, &detect_info)) |
6514 | { | |
6515 | /* We have scanned the whole data. */ | |
6516 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
6517 | { |
6518 | /* We didn't find an 8-bit code. We may | |
6519 | have found a null-byte, but it's very | |
ce5b453a | 6520 | rare that a binary file conforms to |
c0e16b14 KH |
6521 | ISO-2022. */ |
6522 | src = src_end; | |
6523 | coding->head_ascii = src - coding->source; | |
6524 | } | |
6525 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
6526 | break; |
6527 | } | |
6528 | } | |
c3a7b3f4 | 6529 | else if (! c && !inhibit_nbd) |
2f3cbb32 KH |
6530 | { |
6531 | null_byte_found = 1; | |
6532 | if (eight_bit_found) | |
6533 | break; | |
6cb21a4f | 6534 | } |
8a44e6d1 KH |
6535 | else if (! disable_ascii_optimization |
6536 | && ! inhibit_eol_conversion) | |
6537 | { | |
6538 | if (c == '\r') | |
6539 | { | |
6540 | if (src < src_end && src[1] == '\n') | |
6541 | { | |
6542 | coding->eol_seen |= EOL_SEEN_CRLF; | |
6543 | src++; | |
251e9147 KH |
6544 | if (! eight_bit_found) |
6545 | coding->head_ascii++; | |
8a44e6d1 KH |
6546 | } |
6547 | else | |
6548 | coding->eol_seen |= EOL_SEEN_CR; | |
6549 | } | |
6550 | else if (c == '\n') | |
6551 | { | |
6552 | coding->eol_seen |= EOL_SEEN_LF; | |
6553 | } | |
6554 | } | |
6555 | ||
c006c0c8 KH |
6556 | if (! eight_bit_found) |
6557 | coding->head_ascii++; | |
6cb21a4f | 6558 | } |
c006c0c8 | 6559 | else if (! eight_bit_found) |
c0e16b14 | 6560 | coding->head_ascii++; |
d46c5b12 | 6561 | } |
df7492f9 | 6562 | |
2f3cbb32 KH |
6563 | if (null_byte_found || eight_bit_found |
6564 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 6565 | || detect_info.found) |
d46c5b12 | 6566 | { |
ff0dacd7 KH |
6567 | enum coding_category category; |
6568 | struct coding_system *this; | |
df7492f9 | 6569 | |
6cb21a4f KH |
6570 | if (coding->head_ascii == coding->src_bytes) |
6571 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
6572 | for (i = 0; i < coding_category_raw_text; i++) | |
6573 | { | |
6574 | category = coding_priorities[i]; | |
6575 | this = coding_categories + category; | |
6576 | if (detect_info.found & (1 << category)) | |
24a73b0a | 6577 | break; |
6cb21a4f KH |
6578 | } |
6579 | else | |
2f3cbb32 KH |
6580 | { |
6581 | if (null_byte_found) | |
ff0dacd7 | 6582 | { |
2f3cbb32 KH |
6583 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
6584 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 6585 | } |
c3a7b3f4 KH |
6586 | else if (prefer_utf_8 |
6587 | && detect_coding_utf_8 (coding, &detect_info)) | |
6588 | { | |
6589 | detect_info.checked |= ~CATEGORY_MASK_UTF_8; | |
6590 | detect_info.rejected |= ~CATEGORY_MASK_UTF_8; | |
6591 | } | |
2f3cbb32 KH |
6592 | for (i = 0; i < coding_category_raw_text; i++) |
6593 | { | |
6594 | category = coding_priorities[i]; | |
6595 | this = coding_categories + category; | |
0ba06a77 KH |
6596 | /* Some of this->detector (e.g. detect_coding_sjis) |
6597 | require this information. */ | |
6598 | coding->id = this->id; | |
2f3cbb32 KH |
6599 | if (this->id < 0) |
6600 | { | |
6601 | /* No coding system of this category is defined. */ | |
6602 | detect_info.rejected |= (1 << category); | |
6603 | } | |
6604 | else if (category >= coding_category_raw_text) | |
6605 | continue; | |
6606 | else if (detect_info.checked & (1 << category)) | |
6607 | { | |
6608 | if (detect_info.found & (1 << category)) | |
6609 | break; | |
6610 | } | |
6611 | else if ((*(this->detector)) (coding, &detect_info) | |
6612 | && detect_info.found & (1 << category)) | |
e6d2f155 | 6613 | break; |
2f3cbb32 | 6614 | } |
2f3cbb32 | 6615 | } |
c0e16b14 KH |
6616 | |
6617 | if (i < coding_category_raw_text) | |
e6d2f155 KH |
6618 | { |
6619 | if (category == coding_category_utf_8_auto) | |
6620 | { | |
6621 | Lisp_Object coding_systems; | |
6622 | ||
6623 | coding_systems = AREF (CODING_ID_ATTRS (this->id), | |
6624 | coding_attr_utf_bom); | |
6625 | if (CONSP (coding_systems)) | |
6626 | { | |
6627 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6628 | found = XCAR (coding_systems); | |
6629 | else | |
6630 | found = XCDR (coding_systems); | |
6631 | } | |
6632 | else | |
6633 | found = CODING_ID_NAME (this->id); | |
6634 | } | |
6635 | else if (category == coding_category_utf_16_auto) | |
6636 | { | |
6637 | Lisp_Object coding_systems; | |
6638 | ||
6639 | coding_systems = AREF (CODING_ID_ATTRS (this->id), | |
6640 | coding_attr_utf_bom); | |
6641 | if (CONSP (coding_systems)) | |
6642 | { | |
6643 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6644 | found = XCAR (coding_systems); | |
6645 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
6646 | found = XCDR (coding_systems); | |
6647 | } | |
6648 | else | |
6649 | found = CODING_ID_NAME (this->id); | |
6650 | } | |
6651 | else | |
6652 | found = CODING_ID_NAME (this->id); | |
6653 | } | |
c0e16b14 | 6654 | else if (null_byte_found) |
e6d2f155 | 6655 | found = Qno_conversion; |
c0e16b14 KH |
6656 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) |
6657 | == CATEGORY_MASK_ANY) | |
e6d2f155 | 6658 | found = Qraw_text; |
c0e16b14 KH |
6659 | else if (detect_info.rejected) |
6660 | for (i = 0; i < coding_category_raw_text; i++) | |
6661 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6662 | { | |
6663 | this = coding_categories + coding_priorities[i]; | |
e6d2f155 | 6664 | found = CODING_ID_NAME (this->id); |
c0e16b14 KH |
6665 | break; |
6666 | } | |
d46c5b12 | 6667 | } |
b73bfc1c | 6668 | } |
a470d443 KH |
6669 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6670 | == coding_category_utf_8_auto) | |
6671 | { | |
6672 | Lisp_Object coding_systems; | |
6673 | struct coding_detection_info detect_info; | |
6674 | ||
6675 | coding_systems | |
6676 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6677 | detect_info.found = detect_info.rejected = 0; | |
251e9147 | 6678 | if (check_ascii (coding) == coding->src_bytes) |
c230dd7d | 6679 | { |
e6d2f155 KH |
6680 | if (CONSP (coding_systems)) |
6681 | found = XCDR (coding_systems); | |
c230dd7d | 6682 | } |
8a44e6d1 | 6683 | else |
a470d443 | 6684 | { |
8a44e6d1 KH |
6685 | if (CONSP (coding_systems) |
6686 | && detect_coding_utf_8 (coding, &detect_info)) | |
6687 | { | |
6688 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
e6d2f155 | 6689 | found = XCAR (coding_systems); |
8a44e6d1 | 6690 | else |
e6d2f155 | 6691 | found = XCDR (coding_systems); |
8a44e6d1 | 6692 | } |
a470d443 KH |
6693 | } |
6694 | } | |
24a73b0a KH |
6695 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6696 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6697 | { |
6698 | Lisp_Object coding_systems; | |
6699 | struct coding_detection_info detect_info; | |
6700 | ||
6701 | coding_systems | |
a470d443 | 6702 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6703 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6704 | coding->head_ascii = 0; |
b49a1807 | 6705 | if (CONSP (coding_systems) |
24a73b0a | 6706 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6707 | { |
6708 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
e6d2f155 | 6709 | found = XCAR (coding_systems); |
24a73b0a | 6710 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
e6d2f155 | 6711 | found = XCDR (coding_systems); |
b49a1807 KH |
6712 | } |
6713 | } | |
e6d2f155 KH |
6714 | |
6715 | if (! NILP (found)) | |
6716 | { | |
6717 | int specified_eol = (VECTORP (eol_type) ? EOL_SEEN_NONE | |
6718 | : EQ (eol_type, Qdos) ? EOL_SEEN_CRLF | |
6719 | : EQ (eol_type, Qmac) ? EOL_SEEN_CR | |
6720 | : EOL_SEEN_LF); | |
6721 | ||
6722 | setup_coding_system (found, coding); | |
6723 | if (specified_eol != EOL_SEEN_NONE) | |
6724 | adjust_coding_eol_type (coding, specified_eol); | |
6725 | } | |
6726 | ||
73cce38d | 6727 | coding->mode = saved_mode; |
4ed46869 | 6728 | } |
4ed46869 | 6729 | |
d46c5b12 | 6730 | |
aaaf0b1e | 6731 | static void |
971de7fb | 6732 | decode_eol (struct coding_system *coding) |
aaaf0b1e | 6733 | { |
24a73b0a KH |
6734 | Lisp_Object eol_type; |
6735 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6736 | |
24a73b0a | 6737 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
0a9564cb | 6738 | if (EQ (eol_type, Qunix) || inhibit_eol_conversion) |
24a73b0a KH |
6739 | return; |
6740 | ||
6741 | if (NILP (coding->dst_object)) | |
6742 | pbeg = coding->destination; | |
6743 | else | |
6744 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6745 | pend = pbeg + coding->produced; | |
6746 | ||
6747 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6748 | { |
df7492f9 | 6749 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6750 | |
24a73b0a | 6751 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6752 | { |
df7492f9 KH |
6753 | if (*p == '\n') |
6754 | eol_seen |= EOL_SEEN_LF; | |
6755 | else if (*p == '\r') | |
aaaf0b1e | 6756 | { |
df7492f9 | 6757 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6758 | { |
df7492f9 KH |
6759 | eol_seen |= EOL_SEEN_CRLF; |
6760 | p++; | |
aaaf0b1e | 6761 | } |
aaaf0b1e | 6762 | else |
df7492f9 | 6763 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6764 | } |
aaaf0b1e | 6765 | } |
75f4f1ac EZ |
6766 | /* Handle DOS-style EOLs in a file with stray ^M characters. */ |
6767 | if ((eol_seen & EOL_SEEN_CRLF) != 0 | |
6768 | && (eol_seen & EOL_SEEN_CR) != 0 | |
6769 | && (eol_seen & EOL_SEEN_LF) == 0) | |
6770 | eol_seen = EOL_SEEN_CRLF; | |
6771 | else if (eol_seen != EOL_SEEN_NONE | |
24a73b0a KH |
6772 | && eol_seen != EOL_SEEN_LF |
6773 | && eol_seen != EOL_SEEN_CRLF | |
6774 | && eol_seen != EOL_SEEN_CR) | |
6775 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6776 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6777 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6778 | } |
d46c5b12 | 6779 | |
24a73b0a | 6780 | if (EQ (eol_type, Qmac)) |
27901516 | 6781 | { |
24a73b0a | 6782 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6783 | if (*p == '\r') |
6784 | *p = '\n'; | |
4ed46869 | 6785 | } |
24a73b0a | 6786 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6787 | { |
d311d28c | 6788 | ptrdiff_t n = 0; |
b73bfc1c | 6789 | |
24a73b0a KH |
6790 | if (NILP (coding->dst_object)) |
6791 | { | |
4347441b KH |
6792 | /* Start deleting '\r' from the tail to minimize the memory |
6793 | movement. */ | |
24a73b0a KH |
6794 | for (p = pend - 2; p >= pbeg; p--) |
6795 | if (*p == '\r') | |
6796 | { | |
72af86bd | 6797 | memmove (p, p + 1, pend-- - p - 1); |
24a73b0a KH |
6798 | n++; |
6799 | } | |
6800 | } | |
6801 | else | |
6802 | { | |
d311d28c PE |
6803 | ptrdiff_t pos_byte = coding->dst_pos_byte; |
6804 | ptrdiff_t pos = coding->dst_pos; | |
6805 | ptrdiff_t pos_end = pos + coding->produced_char - 1; | |
4347441b KH |
6806 | |
6807 | while (pos < pos_end) | |
6808 | { | |
6809 | p = BYTE_POS_ADDR (pos_byte); | |
6810 | if (*p == '\r' && p[1] == '\n') | |
6811 | { | |
6812 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6813 | n++; | |
6814 | pos_end--; | |
6815 | } | |
6816 | pos++; | |
69b8522d KH |
6817 | if (coding->dst_multibyte) |
6818 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6819 | else | |
6820 | pos_byte++; | |
4347441b | 6821 | } |
24a73b0a KH |
6822 | } |
6823 | coding->produced -= n; | |
6824 | coding->produced_char -= n; | |
aaaf0b1e | 6825 | } |
4ed46869 KH |
6826 | } |
6827 | ||
7d64c6ad | 6828 | |
a6f87d34 | 6829 | /* Return a translation table (or list of them) from coding system |
f10fe38f PE |
6830 | attribute vector ATTRS for encoding (if ENCODEP) or decoding (if |
6831 | not ENCODEP). */ | |
7d64c6ad | 6832 | |
e6a54062 | 6833 | static Lisp_Object |
f10fe38f | 6834 | get_translation_table (Lisp_Object attrs, bool encodep, int *max_lookup) |
7d64c6ad KH |
6835 | { |
6836 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6837 | Lisp_Object val; |
7d64c6ad | 6838 | |
4bed5909 CY |
6839 | if (NILP (Venable_character_translation)) |
6840 | { | |
6841 | if (max_lookup) | |
6842 | *max_lookup = 0; | |
6843 | return Qnil; | |
6844 | } | |
7d64c6ad KH |
6845 | if (encodep) |
6846 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6847 | standard = Vstandard_translation_table_for_encode; | |
6848 | else | |
6849 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6850 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6851 | if (NILP (translation_table)) |
09ee6fdd KH |
6852 | translation_table = standard; |
6853 | else | |
a6f87d34 | 6854 | { |
09ee6fdd KH |
6855 | if (SYMBOLP (translation_table)) |
6856 | translation_table = Fget (translation_table, Qtranslation_table); | |
6857 | else if (CONSP (translation_table)) | |
6858 | { | |
6859 | translation_table = Fcopy_sequence (translation_table); | |
6860 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6861 | if (SYMBOLP (XCAR (val))) | |
6862 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6863 | } | |
6864 | if (CHAR_TABLE_P (standard)) | |
6865 | { | |
6866 | if (CONSP (translation_table)) | |
6867 | translation_table = nconc2 (translation_table, | |
6868 | Fcons (standard, Qnil)); | |
6869 | else | |
6870 | translation_table = Fcons (translation_table, | |
6871 | Fcons (standard, Qnil)); | |
6872 | } | |
a6f87d34 | 6873 | } |
2170c8f0 KH |
6874 | |
6875 | if (max_lookup) | |
09ee6fdd | 6876 | { |
2170c8f0 KH |
6877 | *max_lookup = 1; |
6878 | if (CHAR_TABLE_P (translation_table) | |
6879 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6880 | { | |
6881 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6882 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6883 | *max_lookup = XFASTINT (val); | |
6884 | } | |
6885 | else if (CONSP (translation_table)) | |
6886 | { | |
2735d060 | 6887 | Lisp_Object tail; |
09ee6fdd | 6888 | |
2170c8f0 KH |
6889 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6890 | if (CHAR_TABLE_P (XCAR (tail)) | |
6891 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6892 | { | |
2735d060 PE |
6893 | Lisp_Object tailval = XCHAR_TABLE (XCAR (tail))->extras[1]; |
6894 | if (NATNUMP (tailval) && *max_lookup < XFASTINT (tailval)) | |
6895 | *max_lookup = XFASTINT (tailval); | |
2170c8f0 KH |
6896 | } |
6897 | } | |
a6f87d34 | 6898 | } |
7d64c6ad KH |
6899 | return translation_table; |
6900 | } | |
6901 | ||
09ee6fdd KH |
6902 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6903 | do { \ | |
6904 | trans = Qnil; \ | |
6905 | if (CHAR_TABLE_P (table)) \ | |
6906 | { \ | |
6907 | trans = CHAR_TABLE_REF (table, c); \ | |
6908 | if (CHARACTERP (trans)) \ | |
6909 | c = XFASTINT (trans), trans = Qnil; \ | |
6910 | } \ | |
6911 | else if (CONSP (table)) \ | |
6912 | { \ | |
6913 | Lisp_Object tail; \ | |
6914 | \ | |
6915 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6916 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6917 | { \ | |
6918 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6919 | if (CHARACTERP (trans)) \ | |
6920 | c = XFASTINT (trans), trans = Qnil; \ | |
6921 | else if (! NILP (trans)) \ | |
6922 | break; \ | |
6923 | } \ | |
6924 | } \ | |
e6a54062 KH |
6925 | } while (0) |
6926 | ||
7d64c6ad | 6927 | |
e951386e KH |
6928 | /* Return a translation of character(s) at BUF according to TRANS. |
6929 | TRANS is TO-CHAR or ((FROM . TO) ...) where | |
6930 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | |
6931 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | |
6932 | translation is found, and Qnil if not found.. | |
6933 | If BUF is too short to lookup characters in FROM, return Qt. */ | |
6934 | ||
69a80ea3 | 6935 | static Lisp_Object |
971de7fb | 6936 | get_translation (Lisp_Object trans, int *buf, int *buf_end) |
69a80ea3 | 6937 | { |
e951386e KH |
6938 | |
6939 | if (INTEGERP (trans)) | |
6940 | return trans; | |
6941 | for (; CONSP (trans); trans = XCDR (trans)) | |
69a80ea3 | 6942 | { |
e951386e KH |
6943 | Lisp_Object val = XCAR (trans); |
6944 | Lisp_Object from = XCAR (val); | |
2c6a9faa PE |
6945 | ptrdiff_t len = ASIZE (from); |
6946 | ptrdiff_t i; | |
69a80ea3 | 6947 | |
e951386e | 6948 | for (i = 0; i < len; i++) |
69a80ea3 | 6949 | { |
e951386e KH |
6950 | if (buf + i == buf_end) |
6951 | return Qt; | |
6952 | if (XINT (AREF (from, i)) != buf[i]) | |
6953 | break; | |
69a80ea3 | 6954 | } |
e951386e KH |
6955 | if (i == len) |
6956 | return val; | |
69a80ea3 | 6957 | } |
e951386e | 6958 | return Qnil; |
69a80ea3 KH |
6959 | } |
6960 | ||
6961 | ||
d46c5b12 | 6962 | static int |
cf84bb53 | 6963 | produce_chars (struct coding_system *coding, Lisp_Object translation_table, |
f10fe38f | 6964 | bool last_block) |
4ed46869 | 6965 | { |
df7492f9 KH |
6966 | unsigned char *dst = coding->destination + coding->produced; |
6967 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c PE |
6968 | ptrdiff_t produced; |
6969 | ptrdiff_t produced_chars = 0; | |
69a80ea3 | 6970 | int carryover = 0; |
4ed46869 | 6971 | |
df7492f9 | 6972 | if (! coding->chars_at_source) |
4ed46869 | 6973 | { |
119852e7 | 6974 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6975 | int *buf = coding->charbuf; |
6976 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6977 | |
db274c7a KH |
6978 | if (EQ (coding->src_object, coding->dst_object)) |
6979 | { | |
6980 | coding_set_source (coding); | |
6981 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6982 | } | |
4ed46869 | 6983 | |
df7492f9 | 6984 | while (buf < buf_end) |
4ed46869 | 6985 | { |
27bb1ca4 PE |
6986 | int c = *buf; |
6987 | ptrdiff_t i; | |
bc4bc72a | 6988 | |
df7492f9 KH |
6989 | if (c >= 0) |
6990 | { | |
d311d28c | 6991 | ptrdiff_t from_nchars = 1, to_nchars = 1; |
69a80ea3 KH |
6992 | Lisp_Object trans = Qnil; |
6993 | ||
09ee6fdd | 6994 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6995 | if (! NILP (trans)) |
69a80ea3 | 6996 | { |
e951386e KH |
6997 | trans = get_translation (trans, buf, buf_end); |
6998 | if (INTEGERP (trans)) | |
6999 | c = XINT (trans); | |
7000 | else if (CONSP (trans)) | |
7001 | { | |
7002 | from_nchars = ASIZE (XCAR (trans)); | |
7003 | trans = XCDR (trans); | |
7004 | if (INTEGERP (trans)) | |
7005 | c = XINT (trans); | |
7006 | else | |
7007 | { | |
7008 | to_nchars = ASIZE (trans); | |
7009 | c = XINT (AREF (trans, 0)); | |
7010 | } | |
7011 | } | |
7012 | else if (EQ (trans, Qt) && ! last_block) | |
69a80ea3 | 7013 | break; |
69a80ea3 KH |
7014 | } |
7015 | ||
5d009b3a | 7016 | if ((dst_end - dst) / MAX_MULTIBYTE_LENGTH < to_nchars) |
69a80ea3 | 7017 | { |
5d009b3a PE |
7018 | if (((min (PTRDIFF_MAX, SIZE_MAX) - (buf_end - buf)) |
7019 | / MAX_MULTIBYTE_LENGTH) | |
7020 | < to_nchars) | |
7021 | memory_full (SIZE_MAX); | |
69a80ea3 KH |
7022 | dst = alloc_destination (coding, |
7023 | buf_end - buf | |
7024 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
7025 | dst); | |
db274c7a KH |
7026 | if (EQ (coding->src_object, coding->dst_object)) |
7027 | { | |
7028 | coding_set_source (coding); | |
e951386e KH |
7029 | dst_end = (((unsigned char *) coding->source) |
7030 | + coding->consumed); | |
db274c7a KH |
7031 | } |
7032 | else | |
7033 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
7034 | } |
7035 | ||
433f7f87 | 7036 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 7037 | { |
433f7f87 KH |
7038 | if (i > 0) |
7039 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
7040 | if (coding->dst_multibyte |
7041 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 7042 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
7043 | else |
7044 | *dst++ = CHAR_TO_BYTE8 (c); | |
7045 | } | |
7046 | produced_chars += to_nchars; | |
e951386e | 7047 | buf += from_nchars; |
d46c5b12 | 7048 | } |
df7492f9 | 7049 | else |
69a80ea3 KH |
7050 | /* This is an annotation datum. (-C) is the length. */ |
7051 | buf += -c; | |
4ed46869 | 7052 | } |
69a80ea3 | 7053 | carryover = buf_end - buf; |
4ed46869 | 7054 | } |
fa42c37f | 7055 | else |
fa42c37f | 7056 | { |
119852e7 | 7057 | /* Source characters are at coding->source. */ |
8f924df7 | 7058 | const unsigned char *src = coding->source; |
119852e7 | 7059 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 7060 | |
db274c7a KH |
7061 | if (EQ (coding->dst_object, coding->src_object)) |
7062 | dst_end = (unsigned char *) src; | |
df7492f9 | 7063 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 7064 | { |
df7492f9 | 7065 | if (coding->src_multibyte) |
fa42c37f | 7066 | { |
f10fe38f | 7067 | bool multibytep = 1; |
d311d28c | 7068 | ptrdiff_t consumed_chars = 0; |
d46c5b12 | 7069 | |
df7492f9 KH |
7070 | while (1) |
7071 | { | |
8f924df7 | 7072 | const unsigned char *src_base = src; |
df7492f9 | 7073 | int c; |
b73bfc1c | 7074 | |
df7492f9 | 7075 | ONE_MORE_BYTE (c); |
119852e7 | 7076 | if (dst == dst_end) |
df7492f9 | 7077 | { |
119852e7 KH |
7078 | if (EQ (coding->src_object, coding->dst_object)) |
7079 | dst_end = (unsigned char *) src; | |
7080 | if (dst == dst_end) | |
df7492f9 | 7081 | { |
d311d28c | 7082 | ptrdiff_t offset = src - coding->source; |
119852e7 KH |
7083 | |
7084 | dst = alloc_destination (coding, src_end - src + 1, | |
7085 | dst); | |
7086 | dst_end = coding->destination + coding->dst_bytes; | |
7087 | coding_set_source (coding); | |
7088 | src = coding->source + offset; | |
5c1ca13d | 7089 | src_end = coding->source + coding->consumed; |
db274c7a KH |
7090 | if (EQ (coding->src_object, coding->dst_object)) |
7091 | dst_end = (unsigned char *) src; | |
df7492f9 | 7092 | } |
df7492f9 KH |
7093 | } |
7094 | *dst++ = c; | |
7095 | produced_chars++; | |
7096 | } | |
7097 | no_more_source: | |
7098 | ; | |
fa42c37f KH |
7099 | } |
7100 | else | |
df7492f9 KH |
7101 | while (src < src_end) |
7102 | { | |
f10fe38f | 7103 | bool multibytep = 1; |
df7492f9 | 7104 | int c = *src++; |
b73bfc1c | 7105 | |
df7492f9 KH |
7106 | if (dst >= dst_end - 1) |
7107 | { | |
2c78b7e1 | 7108 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 7109 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
7110 | if (dst >= dst_end - 1) |
7111 | { | |
d311d28c PE |
7112 | ptrdiff_t offset = src - coding->source; |
7113 | ptrdiff_t more_bytes; | |
119852e7 | 7114 | |
db274c7a KH |
7115 | if (EQ (coding->src_object, coding->dst_object)) |
7116 | more_bytes = ((src_end - src) / 2) + 2; | |
7117 | else | |
7118 | more_bytes = src_end - src + 2; | |
7119 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
7120 | dst_end = coding->destination + coding->dst_bytes; |
7121 | coding_set_source (coding); | |
119852e7 | 7122 | src = coding->source + offset; |
5c1ca13d | 7123 | src_end = coding->source + coding->consumed; |
db274c7a KH |
7124 | if (EQ (coding->src_object, coding->dst_object)) |
7125 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 7126 | } |
df7492f9 KH |
7127 | } |
7128 | EMIT_ONE_BYTE (c); | |
7129 | } | |
d46c5b12 | 7130 | } |
df7492f9 KH |
7131 | else |
7132 | { | |
7133 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 7134 | { |
d311d28c | 7135 | ptrdiff_t require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 7136 | |
df7492f9 | 7137 | if (require > 0) |
fa42c37f | 7138 | { |
d311d28c | 7139 | ptrdiff_t offset = src - coding->source; |
df7492f9 KH |
7140 | |
7141 | dst = alloc_destination (coding, require, dst); | |
7142 | coding_set_source (coding); | |
7143 | src = coding->source + offset; | |
5c1ca13d | 7144 | src_end = coding->source + coding->consumed; |
fa42c37f KH |
7145 | } |
7146 | } | |
119852e7 | 7147 | produced_chars = coding->consumed_char; |
df7492f9 | 7148 | while (src < src_end) |
14daee73 | 7149 | *dst++ = *src++; |
fa42c37f KH |
7150 | } |
7151 | } | |
7152 | ||
df7492f9 | 7153 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 7154 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
8a44e6d1 | 7155 | insert_from_gap (produced_chars, produced, 0); |
df7492f9 KH |
7156 | coding->produced += produced; |
7157 | coding->produced_char += produced_chars; | |
69a80ea3 | 7158 | return carryover; |
fa42c37f KH |
7159 | } |
7160 | ||
ff0dacd7 KH |
7161 | /* Compose text in CODING->object according to the annotation data at |
7162 | CHARBUF. CHARBUF is an array: | |
e951386e | 7163 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
df7492f9 | 7164 | */ |
4ed46869 | 7165 | |
b0ab8123 | 7166 | static void |
d311d28c | 7167 | produce_composition (struct coding_system *coding, int *charbuf, ptrdiff_t pos) |
4ed46869 | 7168 | { |
df7492f9 | 7169 | int len; |
d311d28c | 7170 | ptrdiff_t to; |
df7492f9 | 7171 | enum composition_method method; |
df7492f9 | 7172 | Lisp_Object components; |
fa42c37f | 7173 | |
e951386e | 7174 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
69a80ea3 | 7175 | to = pos + charbuf[2]; |
e951386e | 7176 | method = (enum composition_method) (charbuf[4]); |
d46c5b12 | 7177 | |
df7492f9 KH |
7178 | if (method == COMPOSITION_RELATIVE) |
7179 | components = Qnil; | |
e951386e | 7180 | else |
d46c5b12 | 7181 | { |
df7492f9 | 7182 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
e951386e | 7183 | int i, j; |
b73bfc1c | 7184 | |
e951386e KH |
7185 | if (method == COMPOSITION_WITH_RULE) |
7186 | len = charbuf[2] * 3 - 2; | |
7187 | charbuf += MAX_ANNOTATION_LENGTH; | |
7188 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | |
7189 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | |
9ffd559c | 7190 | { |
e951386e KH |
7191 | if (charbuf[i] >= 0) |
7192 | args[j] = make_number (charbuf[i]); | |
7193 | else | |
7194 | { | |
7195 | i++; | |
7196 | args[j] = make_number (charbuf[i] % 0x100); | |
7197 | } | |
9ffd559c | 7198 | } |
e951386e | 7199 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
d46c5b12 | 7200 | } |
69a80ea3 | 7201 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
7202 | } |
7203 | ||
d46c5b12 | 7204 | |
ff0dacd7 KH |
7205 | /* Put `charset' property on text in CODING->object according to |
7206 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 7207 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 7208 | */ |
d46c5b12 | 7209 | |
b0ab8123 | 7210 | static void |
d311d28c | 7211 | produce_charset (struct coding_system *coding, int *charbuf, ptrdiff_t pos) |
d46c5b12 | 7212 | { |
d311d28c | 7213 | ptrdiff_t from = pos - charbuf[2]; |
69a80ea3 | 7214 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); |
b73bfc1c | 7215 | |
69a80ea3 | 7216 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
7217 | Qcharset, CHARSET_NAME (charset), |
7218 | coding->dst_object); | |
d46c5b12 KH |
7219 | } |
7220 | ||
d46c5b12 | 7221 | |
df7492f9 KH |
7222 | #define CHARBUF_SIZE 0x4000 |
7223 | ||
7224 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
7225 | do { \ | |
1af1a51a DA |
7226 | coding->charbuf = SAFE_ALLOCA (CHARBUF_SIZE * sizeof (int)); \ |
7227 | coding->charbuf_size = CHARBUF_SIZE; \ | |
df7492f9 | 7228 | } while (0) |
4ed46869 | 7229 | |
d46c5b12 KH |
7230 | |
7231 | static void | |
d311d28c | 7232 | produce_annotation (struct coding_system *coding, ptrdiff_t pos) |
d46c5b12 | 7233 | { |
df7492f9 KH |
7234 | int *charbuf = coding->charbuf; |
7235 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 7236 | |
ff0dacd7 KH |
7237 | if (NILP (coding->dst_object)) |
7238 | return; | |
d46c5b12 | 7239 | |
df7492f9 | 7240 | while (charbuf < charbuf_end) |
a84f1519 | 7241 | { |
df7492f9 | 7242 | if (*charbuf >= 0) |
e951386e | 7243 | pos++, charbuf++; |
d46c5b12 | 7244 | else |
d46c5b12 | 7245 | { |
df7492f9 | 7246 | int len = -*charbuf; |
e951386e KH |
7247 | |
7248 | if (len > 2) | |
7249 | switch (charbuf[1]) | |
7250 | { | |
7251 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
7252 | produce_composition (coding, charbuf, pos); | |
7253 | break; | |
7254 | case CODING_ANNOTATE_CHARSET_MASK: | |
7255 | produce_charset (coding, charbuf, pos); | |
7256 | break; | |
7257 | } | |
df7492f9 | 7258 | charbuf += len; |
d46c5b12 | 7259 | } |
a84f1519 | 7260 | } |
d46c5b12 KH |
7261 | } |
7262 | ||
df7492f9 KH |
7263 | /* Decode the data at CODING->src_object into CODING->dst_object. |
7264 | CODING->src_object is a buffer, a string, or nil. | |
7265 | CODING->dst_object is a buffer. | |
d46c5b12 | 7266 | |
df7492f9 KH |
7267 | If CODING->src_object is a buffer, it must be the current buffer. |
7268 | In this case, if CODING->src_pos is positive, it is a position of | |
7269 | the source text in the buffer, otherwise, the source text is in the | |
7270 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
7271 | the text from GPT (which must be the same as PT). If this is the | |
7272 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7273 | negative. | |
d46c5b12 | 7274 | |
b6828792 | 7275 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 7276 | that string. |
d46c5b12 | 7277 | |
df7492f9 KH |
7278 | If CODING->src_object is nil, CODING->source must already point to |
7279 | the non-relocatable memory area. In this case, CODING->src_pos is | |
7280 | an offset from CODING->source. | |
73be902c | 7281 | |
df7492f9 KH |
7282 | The decoded data is inserted at the current point of the buffer |
7283 | CODING->dst_object. | |
7284 | */ | |
d46c5b12 | 7285 | |
f10fe38f | 7286 | static void |
971de7fb | 7287 | decode_coding (struct coding_system *coding) |
d46c5b12 | 7288 | { |
df7492f9 | 7289 | Lisp_Object attrs; |
24a73b0a | 7290 | Lisp_Object undo_list; |
7d64c6ad | 7291 | Lisp_Object translation_table; |
d0396581 | 7292 | struct ccl_spec cclspec; |
69a80ea3 KH |
7293 | int carryover; |
7294 | int i; | |
d46c5b12 | 7295 | |
1af1a51a DA |
7296 | USE_SAFE_ALLOCA; |
7297 | ||
df7492f9 KH |
7298 | if (BUFFERP (coding->src_object) |
7299 | && coding->src_pos > 0 | |
7300 | && coding->src_pos < GPT | |
7301 | && coding->src_pos + coding->src_chars > GPT) | |
7302 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 7303 | |
24a73b0a | 7304 | undo_list = Qt; |
df7492f9 | 7305 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 7306 | { |
a3d794a1 | 7307 | set_buffer_internal (XBUFFER (coding->dst_object)); |
df7492f9 KH |
7308 | if (GPT != PT) |
7309 | move_gap_both (PT, PT_BYTE); | |
f48b82fd GR |
7310 | |
7311 | /* We must disable undo_list in order to record the whole insert | |
7312 | transaction via record_insert at the end. But doing so also | |
7313 | disables the recording of the first change to the undo_list. | |
7314 | Therefore we check for first change here and record it via | |
7315 | record_first_change if needed. */ | |
7316 | if (MODIFF <= SAVE_MODIFF) | |
7317 | record_first_change (); | |
7318 | ||
4b4deea2 | 7319 | undo_list = BVAR (current_buffer, undo_list); |
39eb03f1 | 7320 | bset_undo_list (current_buffer, Qt); |
1c3478b0 KH |
7321 | } |
7322 | ||
df7492f9 KH |
7323 | coding->consumed = coding->consumed_char = 0; |
7324 | coding->produced = coding->produced_char = 0; | |
7325 | coding->chars_at_source = 0; | |
065e3595 | 7326 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 7327 | coding->errors = 0; |
1c3478b0 | 7328 | |
df7492f9 KH |
7329 | ALLOC_CONVERSION_WORK_AREA (coding); |
7330 | ||
7331 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 7332 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 7333 | |
69a80ea3 | 7334 | carryover = 0; |
d0396581 KH |
7335 | if (coding->decoder == decode_coding_ccl) |
7336 | { | |
7337 | coding->spec.ccl = &cclspec; | |
7338 | setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding)); | |
7339 | } | |
df7492f9 | 7340 | do |
b73bfc1c | 7341 | { |
d311d28c | 7342 | ptrdiff_t pos = coding->dst_pos + coding->produced_char; |
69a80ea3 | 7343 | |
df7492f9 KH |
7344 | coding_set_source (coding); |
7345 | coding->annotated = 0; | |
69a80ea3 | 7346 | coding->charbuf_used = carryover; |
df7492f9 | 7347 | (*(coding->decoder)) (coding); |
df7492f9 | 7348 | coding_set_destination (coding); |
69a80ea3 | 7349 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 7350 | if (coding->annotated) |
69a80ea3 KH |
7351 | produce_annotation (coding, pos); |
7352 | for (i = 0; i < carryover; i++) | |
7353 | coding->charbuf[i] | |
7354 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 7355 | } |
d0396581 KH |
7356 | while (coding->result == CODING_RESULT_INSUFFICIENT_DST |
7357 | || (coding->consumed < coding->src_bytes | |
7358 | && (coding->result == CODING_RESULT_SUCCESS | |
7359 | || coding->result == CODING_RESULT_INVALID_SRC))); | |
d46c5b12 | 7360 | |
69a80ea3 KH |
7361 | if (carryover > 0) |
7362 | { | |
7363 | coding_set_destination (coding); | |
7364 | coding->charbuf_used = carryover; | |
7365 | produce_chars (coding, translation_table, 1); | |
7366 | } | |
7367 | ||
df7492f9 KH |
7368 | coding->carryover_bytes = 0; |
7369 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 7370 | { |
df7492f9 | 7371 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 7372 | const unsigned char *src; |
df7492f9 KH |
7373 | |
7374 | coding_set_source (coding); | |
7375 | coding_set_destination (coding); | |
7376 | src = coding->source + coding->consumed; | |
7377 | ||
7378 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 7379 | { |
df7492f9 KH |
7380 | /* Flush out unprocessed data as binary chars. We are sure |
7381 | that the number of data is less than the size of | |
7382 | coding->charbuf. */ | |
065e3595 | 7383 | coding->charbuf_used = 0; |
b2dab6c8 JR |
7384 | coding->chars_at_source = 0; |
7385 | ||
df7492f9 | 7386 | while (nbytes-- > 0) |
1c3478b0 | 7387 | { |
df7492f9 | 7388 | int c = *src++; |
98725083 | 7389 | |
1c91457d KH |
7390 | if (c & 0x80) |
7391 | c = BYTE8_TO_CHAR (c); | |
7392 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 7393 | } |
f6cbaf43 | 7394 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 7395 | } |
d46c5b12 | 7396 | else |
df7492f9 KH |
7397 | { |
7398 | /* Record unprocessed bytes in coding->carryover. We are | |
7399 | sure that the number of data is less than the size of | |
7400 | coding->carryover. */ | |
7401 | unsigned char *p = coding->carryover; | |
7402 | ||
f289d375 KH |
7403 | if (nbytes > sizeof coding->carryover) |
7404 | nbytes = sizeof coding->carryover; | |
df7492f9 KH |
7405 | coding->carryover_bytes = nbytes; |
7406 | while (nbytes-- > 0) | |
7407 | *p++ = *src++; | |
1c3478b0 | 7408 | } |
df7492f9 | 7409 | coding->consumed = coding->src_bytes; |
b73bfc1c | 7410 | } |
69f76525 | 7411 | |
0a9564cb EZ |
7412 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix) |
7413 | && !inhibit_eol_conversion) | |
4347441b | 7414 | decode_eol (coding); |
24a73b0a KH |
7415 | if (BUFFERP (coding->dst_object)) |
7416 | { | |
39eb03f1 | 7417 | bset_undo_list (current_buffer, undo_list); |
24a73b0a KH |
7418 | record_insert (coding->dst_pos, coding->produced_char); |
7419 | } | |
1af1a51a DA |
7420 | |
7421 | SAFE_FREE (); | |
4ed46869 KH |
7422 | } |
7423 | ||
aaaf0b1e | 7424 | |
e1c23804 | 7425 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
7426 | ending before LIMIT of CODING->src_object (buffer or string), store |
7427 | the data in BUF, set *STOP to a starting position of the next | |
7428 | composition (if any) or to LIMIT, and return the address of the | |
7429 | next element of BUF. | |
7430 | ||
7431 | If such an annotation is not found, set *STOP to a starting | |
7432 | position of a composition after POS (if any) or to LIMIT, and | |
7433 | return BUF. */ | |
7434 | ||
b0ab8123 | 7435 | static int * |
d311d28c | 7436 | handle_composition_annotation (ptrdiff_t pos, ptrdiff_t limit, |
cf84bb53 | 7437 | struct coding_system *coding, int *buf, |
d311d28c | 7438 | ptrdiff_t *stop) |
aaaf0b1e | 7439 | { |
d311d28c | 7440 | ptrdiff_t start, end; |
ff0dacd7 | 7441 | Lisp_Object prop; |
aaaf0b1e | 7442 | |
ff0dacd7 KH |
7443 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
7444 | || end > limit) | |
7445 | *stop = limit; | |
7446 | else if (start > pos) | |
7447 | *stop = start; | |
7448 | else | |
aaaf0b1e | 7449 | { |
ff0dacd7 | 7450 | if (start == pos) |
aaaf0b1e | 7451 | { |
ff0dacd7 KH |
7452 | /* We found a composition. Store the corresponding |
7453 | annotation data in BUF. */ | |
7454 | int *head = buf; | |
7455 | enum composition_method method = COMPOSITION_METHOD (prop); | |
7456 | int nchars = COMPOSITION_LENGTH (prop); | |
7457 | ||
e951386e | 7458 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
ff0dacd7 | 7459 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 7460 | { |
ff0dacd7 | 7461 | Lisp_Object components; |
2c6a9faa | 7462 | ptrdiff_t i, len, i_byte; |
ff0dacd7 KH |
7463 | |
7464 | components = COMPOSITION_COMPONENTS (prop); | |
7465 | if (VECTORP (components)) | |
aaaf0b1e | 7466 | { |
77b37c05 | 7467 | len = ASIZE (components); |
ff0dacd7 KH |
7468 | for (i = 0; i < len; i++) |
7469 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 7470 | } |
ff0dacd7 | 7471 | else if (STRINGP (components)) |
aaaf0b1e | 7472 | { |
8f924df7 | 7473 | len = SCHARS (components); |
ff0dacd7 KH |
7474 | i = i_byte = 0; |
7475 | while (i < len) | |
7476 | { | |
7477 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
7478 | buf++; | |
7479 | } | |
7480 | } | |
7481 | else if (INTEGERP (components)) | |
7482 | { | |
7483 | len = 1; | |
7484 | *buf++ = XINT (components); | |
7485 | } | |
7486 | else if (CONSP (components)) | |
7487 | { | |
7488 | for (len = 0; CONSP (components); | |
7489 | len++, components = XCDR (components)) | |
7490 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 7491 | } |
aaaf0b1e | 7492 | else |
1088b922 | 7493 | emacs_abort (); |
ff0dacd7 | 7494 | *head -= len; |
aaaf0b1e | 7495 | } |
aaaf0b1e | 7496 | } |
ff0dacd7 KH |
7497 | |
7498 | if (find_composition (end, limit, &start, &end, &prop, | |
7499 | coding->src_object) | |
7500 | && end <= limit) | |
7501 | *stop = start; | |
7502 | else | |
7503 | *stop = limit; | |
aaaf0b1e | 7504 | } |
ff0dacd7 KH |
7505 | return buf; |
7506 | } | |
7507 | ||
7508 | ||
e1c23804 | 7509 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
7510 | CODING->src_object (buffer of string), store the data in BUF, set |
7511 | *STOP to the position where the value of `charset' property changes | |
7512 | (limiting by LIMIT), and return the address of the next element of | |
7513 | BUF. | |
7514 | ||
7515 | If the property value is nil, set *STOP to the position where the | |
7516 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
7517 | ||
b0ab8123 | 7518 | static int * |
d311d28c | 7519 | handle_charset_annotation (ptrdiff_t pos, ptrdiff_t limit, |
cf84bb53 | 7520 | struct coding_system *coding, int *buf, |
d311d28c | 7521 | ptrdiff_t *stop) |
ff0dacd7 KH |
7522 | { |
7523 | Lisp_Object val, next; | |
7524 | int id; | |
7525 | ||
7526 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
7527 | if (! NILP (val) && CHARSETP (val)) | |
7528 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
7529 | else | |
7530 | id = -1; | |
69a80ea3 | 7531 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
7532 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
7533 | coding->src_object, | |
7534 | make_number (limit)); | |
7535 | *stop = XINT (next); | |
7536 | return buf; | |
7537 | } | |
7538 | ||
7539 | ||
df7492f9 | 7540 | static void |
cf84bb53 JB |
7541 | consume_chars (struct coding_system *coding, Lisp_Object translation_table, |
7542 | int max_lookup) | |
df7492f9 KH |
7543 | { |
7544 | int *buf = coding->charbuf; | |
ff0dacd7 | 7545 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 7546 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 7547 | const unsigned char *src_end = coding->source + coding->src_bytes; |
d311d28c PE |
7548 | ptrdiff_t pos = coding->src_pos + coding->consumed_char; |
7549 | ptrdiff_t end_pos = coding->src_pos + coding->src_chars; | |
f10fe38f | 7550 | bool multibytep = coding->src_multibyte; |
df7492f9 KH |
7551 | Lisp_Object eol_type; |
7552 | int c; | |
d311d28c | 7553 | ptrdiff_t stop, stop_composition, stop_charset; |
09ee6fdd | 7554 | int *lookup_buf = NULL; |
433f7f87 KH |
7555 | |
7556 | if (! NILP (translation_table)) | |
09ee6fdd | 7557 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 7558 | |
0a9564cb | 7559 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
df7492f9 KH |
7560 | if (VECTORP (eol_type)) |
7561 | eol_type = Qunix; | |
88993dfd | 7562 | |
df7492f9 KH |
7563 | /* Note: composition handling is not yet implemented. */ |
7564 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 7565 | |
0b5670c9 KH |
7566 | if (NILP (coding->src_object)) |
7567 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 7568 | else |
0b5670c9 KH |
7569 | { |
7570 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
7571 | stop = stop_composition = pos; | |
7572 | else | |
7573 | stop = stop_composition = end_pos; | |
7574 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
7575 | stop = stop_charset = pos; | |
7576 | else | |
7577 | stop_charset = end_pos; | |
7578 | } | |
ec6d2bb8 | 7579 | |
24a73b0a | 7580 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 7581 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 7582 | while (buf < buf_end) |
aaaf0b1e | 7583 | { |
433f7f87 KH |
7584 | Lisp_Object trans; |
7585 | ||
df7492f9 | 7586 | if (pos == stop) |
ec6d2bb8 | 7587 | { |
df7492f9 KH |
7588 | if (pos == end_pos) |
7589 | break; | |
ff0dacd7 KH |
7590 | if (pos == stop_composition) |
7591 | buf = handle_composition_annotation (pos, end_pos, coding, | |
7592 | buf, &stop_composition); | |
7593 | if (pos == stop_charset) | |
7594 | buf = handle_charset_annotation (pos, end_pos, coding, | |
7595 | buf, &stop_charset); | |
7596 | stop = (stop_composition < stop_charset | |
7597 | ? stop_composition : stop_charset); | |
df7492f9 KH |
7598 | } |
7599 | ||
7600 | if (! multibytep) | |
4776e638 | 7601 | { |
d311d28c | 7602 | int bytes; |
aaaf0b1e | 7603 | |
4d1e6632 KH |
7604 | if (coding->encoder == encode_coding_raw_text |
7605 | || coding->encoder == encode_coding_ccl) | |
ea29edf2 KH |
7606 | c = *src++, pos++; |
7607 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 7608 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 7609 | else |
f03caae0 | 7610 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 7611 | } |
df7492f9 | 7612 | else |
db274c7a | 7613 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
7614 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
7615 | c = '\n'; | |
7616 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 7617 | { |
df7492f9 | 7618 | if (c == '\n') |
aaaf0b1e | 7619 | { |
df7492f9 KH |
7620 | if (EQ (eol_type, Qdos)) |
7621 | *buf++ = '\r'; | |
7622 | else | |
7623 | c = '\r'; | |
aaaf0b1e KH |
7624 | } |
7625 | } | |
433f7f87 | 7626 | |
e6a54062 | 7627 | trans = Qnil; |
09ee6fdd | 7628 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 7629 | if (NILP (trans)) |
433f7f87 KH |
7630 | *buf++ = c; |
7631 | else | |
7632 | { | |
2c6a9faa | 7633 | ptrdiff_t from_nchars = 1, to_nchars = 1; |
433f7f87 KH |
7634 | int *lookup_buf_end; |
7635 | const unsigned char *p = src; | |
7636 | int i; | |
7637 | ||
7638 | lookup_buf[0] = c; | |
7639 | for (i = 1; i < max_lookup && p < src_end; i++) | |
7640 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
7641 | lookup_buf_end = lookup_buf + i; | |
e951386e KH |
7642 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
7643 | if (INTEGERP (trans)) | |
7644 | c = XINT (trans); | |
7645 | else if (CONSP (trans)) | |
7646 | { | |
7647 | from_nchars = ASIZE (XCAR (trans)); | |
7648 | trans = XCDR (trans); | |
7649 | if (INTEGERP (trans)) | |
7650 | c = XINT (trans); | |
7651 | else | |
7652 | { | |
7653 | to_nchars = ASIZE (trans); | |
2c6a9faa | 7654 | if (buf_end - buf < to_nchars) |
e951386e KH |
7655 | break; |
7656 | c = XINT (AREF (trans, 0)); | |
7657 | } | |
7658 | } | |
7659 | else | |
433f7f87 | 7660 | break; |
e951386e | 7661 | *buf++ = c; |
433f7f87 KH |
7662 | for (i = 1; i < to_nchars; i++) |
7663 | *buf++ = XINT (AREF (trans, i)); | |
7664 | for (i = 1; i < from_nchars; i++, pos++) | |
7665 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7666 | } | |
aaaf0b1e | 7667 | } |
ec6d2bb8 | 7668 | |
df7492f9 KH |
7669 | coding->consumed = src - coding->source; |
7670 | coding->consumed_char = pos - coding->src_pos; | |
7671 | coding->charbuf_used = buf - coding->charbuf; | |
7672 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7673 | } |
7674 | ||
4ed46869 | 7675 | |
df7492f9 KH |
7676 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7677 | CODING->src_object is a buffer or a string. | |
7678 | CODING->dst_object is a buffer or nil. | |
7679 | ||
7680 | If CODING->src_object is a buffer, it must be the current buffer. | |
7681 | In this case, if CODING->src_pos is positive, it is a position of | |
7682 | the source text in the buffer, otherwise. the source text is in the | |
7683 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7684 | the text from GPT (which must be the same as PT). If this is the | |
7685 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7686 | negative and CODING should not have `pre-write-conversion'. | |
7687 | ||
7688 | If CODING->src_object is a string, CODING should not have | |
7689 | `pre-write-conversion'. | |
7690 | ||
7691 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7692 | the current point of that buffer. | |
7693 | ||
7694 | If CODING->dst_object is nil, the encoded data is placed at the | |
7695 | memory area specified by CODING->destination. */ | |
7696 | ||
f10fe38f | 7697 | static void |
971de7fb | 7698 | encode_coding (struct coding_system *coding) |
4ed46869 | 7699 | { |
df7492f9 | 7700 | Lisp_Object attrs; |
7d64c6ad | 7701 | Lisp_Object translation_table; |
09ee6fdd | 7702 | int max_lookup; |
fb608df3 | 7703 | struct ccl_spec cclspec; |
9861e777 | 7704 | |
1af1a51a DA |
7705 | USE_SAFE_ALLOCA; |
7706 | ||
df7492f9 | 7707 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7708 | if (coding->encoder == encode_coding_raw_text) |
7709 | translation_table = Qnil, max_lookup = 0; | |
7710 | else | |
7711 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7712 | |
df7492f9 | 7713 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7714 | { |
df7492f9 KH |
7715 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7716 | coding->dst_multibyte | |
4b4deea2 | 7717 | = ! NILP (BVAR (current_buffer, enable_multibyte_characters)); |
8844fa83 | 7718 | } |
4ed46869 | 7719 | |
b73bfc1c | 7720 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7721 | coding->produced = coding->produced_char = 0; |
065e3595 | 7722 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7723 | coding->errors = 0; |
b73bfc1c | 7724 | |
df7492f9 | 7725 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7726 | |
fb608df3 KH |
7727 | if (coding->encoder == encode_coding_ccl) |
7728 | { | |
7729 | coding->spec.ccl = &cclspec; | |
7730 | setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding)); | |
7731 | } | |
df7492f9 KH |
7732 | do { |
7733 | coding_set_source (coding); | |
09ee6fdd | 7734 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7735 | coding_set_destination (coding); |
7736 | (*(coding->encoder)) (coding); | |
7737 | } while (coding->consumed_char < coding->src_chars); | |
7738 | ||
284201e4 | 7739 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
8a44e6d1 | 7740 | insert_from_gap (coding->produced_char, coding->produced, 0); |
1af1a51a DA |
7741 | |
7742 | SAFE_FREE (); | |
ec6d2bb8 KH |
7743 | } |
7744 | ||
fb88bf2d | 7745 | |
24a73b0a KH |
7746 | /* Name (or base name) of work buffer for code conversion. */ |
7747 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7748 | |
24a73b0a KH |
7749 | /* A working buffer used by the top level conversion. Once it is |
7750 | created, it is never destroyed. It has the name | |
7751 | Vcode_conversion_workbuf_name. The other working buffers are | |
7752 | destroyed after the use is finished, and their names are modified | |
7753 | versions of Vcode_conversion_workbuf_name. */ | |
7754 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7755 | |
f10fe38f PE |
7756 | /* True iff Vcode_conversion_reused_workbuf is already in use. */ |
7757 | static bool reused_workbuf_in_use; | |
4ed46869 | 7758 | |
24a73b0a | 7759 | |
ad1746f5 | 7760 | /* Return a working buffer of code conversion. MULTIBYTE specifies the |
24a73b0a | 7761 | multibyteness of returning buffer. */ |
b73bfc1c | 7762 | |
f6cbaf43 | 7763 | static Lisp_Object |
f10fe38f | 7764 | make_conversion_work_buffer (bool multibyte) |
df7492f9 | 7765 | { |
24a73b0a KH |
7766 | Lisp_Object name, workbuf; |
7767 | struct buffer *current; | |
4ed46869 | 7768 | |
f10fe38f | 7769 | if (reused_workbuf_in_use) |
065e3595 KH |
7770 | { |
7771 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7772 | workbuf = Fget_buffer_create (name); | |
7773 | } | |
df7492f9 | 7774 | else |
065e3595 | 7775 | { |
f10fe38f | 7776 | reused_workbuf_in_use = 1; |
159bd5a2 | 7777 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7778 | Vcode_conversion_reused_workbuf |
7779 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7780 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7781 | } |
24a73b0a KH |
7782 | current = current_buffer; |
7783 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7784 | /* We can't allow modification hooks to run in the work buffer. For |
7785 | instance, directory_files_internal assumes that file decoding | |
7786 | doesn't compile new regexps. */ | |
7787 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7788 | Ferase_buffer (); |
39eb03f1 PE |
7789 | bset_undo_list (current_buffer, Qt); |
7790 | bset_enable_multibyte_characters (current_buffer, multibyte ? Qt : Qnil); | |
df7492f9 | 7791 | set_buffer_internal (current); |
24a73b0a | 7792 | return workbuf; |
df7492f9 | 7793 | } |
d46c5b12 | 7794 | |
24a73b0a | 7795 | |
4776e638 | 7796 | static Lisp_Object |
971de7fb | 7797 | code_conversion_restore (Lisp_Object arg) |
4776e638 | 7798 | { |
24a73b0a | 7799 | Lisp_Object current, workbuf; |
948bdcf3 | 7800 | struct gcpro gcpro1; |
24a73b0a | 7801 | |
948bdcf3 | 7802 | GCPRO1 (arg); |
24a73b0a KH |
7803 | current = XCAR (arg); |
7804 | workbuf = XCDR (arg); | |
7805 | if (! NILP (workbuf)) | |
7806 | { | |
7807 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7808 | reused_workbuf_in_use = 0; | |
d17337e5 | 7809 | else |
24a73b0a KH |
7810 | Fkill_buffer (workbuf); |
7811 | } | |
7812 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7813 | UNGCPRO; |
4776e638 KH |
7814 | return Qnil; |
7815 | } | |
b73bfc1c | 7816 | |
24a73b0a | 7817 | Lisp_Object |
f10fe38f | 7818 | code_conversion_save (bool with_work_buf, bool multibyte) |
df7492f9 | 7819 | { |
24a73b0a | 7820 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7821 | |
4776e638 | 7822 | if (with_work_buf) |
24a73b0a KH |
7823 | workbuf = make_conversion_work_buffer (multibyte); |
7824 | record_unwind_protect (code_conversion_restore, | |
7825 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7826 | return workbuf; |
df7492f9 | 7827 | } |
d46c5b12 | 7828 | |
f10fe38f | 7829 | void |
cf84bb53 | 7830 | decode_coding_gap (struct coding_system *coding, |
d311d28c | 7831 | ptrdiff_t chars, ptrdiff_t bytes) |
df7492f9 | 7832 | { |
d311d28c | 7833 | ptrdiff_t count = SPECPDL_INDEX (); |
5e5c78be | 7834 | Lisp_Object attrs; |
fb88bf2d | 7835 | |
24a73b0a | 7836 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7837 | coding->src_chars = chars; |
7838 | coding->src_bytes = bytes; | |
7839 | coding->src_pos = -chars; | |
7840 | coding->src_pos_byte = -bytes; | |
7841 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7842 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7843 | coding->dst_pos = PT; |
7844 | coding->dst_pos_byte = PT_BYTE; | |
4b4deea2 | 7845 | coding->dst_multibyte = ! NILP (BVAR (current_buffer, enable_multibyte_characters)); |
4ed46869 | 7846 | |
e6d2f155 KH |
7847 | coding->head_ascii = -1; |
7848 | coding->detected_utf8_chars = -1; | |
7849 | coding->eol_seen = EOL_SEEN_NONE; | |
df7492f9 KH |
7850 | if (CODING_REQUIRE_DETECTION (coding)) |
7851 | detect_coding (coding); | |
c230dd7d | 7852 | attrs = CODING_ID_ATTRS (coding->id); |
251e9147 KH |
7853 | if (! disable_ascii_optimization |
7854 | && ! coding->src_multibyte | |
7855 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)) | |
7856 | && NILP (CODING_ATTR_POST_READ (attrs)) | |
7857 | && NILP (get_translation_table (attrs, 0, NULL))) | |
7858 | { | |
7859 | chars = coding->head_ascii; | |
7860 | if (chars < 0) | |
7861 | chars = check_ascii (coding); | |
7862 | if (chars != bytes) | |
7863 | { | |
e6d2f155 | 7864 | /* There exists a non-ASCII byte. */ |
251e9147 | 7865 | if (EQ (CODING_ATTR_TYPE (attrs), Qutf_8)) |
e6d2f155 KH |
7866 | { |
7867 | if (coding->detected_utf8_chars >= 0) | |
7868 | chars = coding->detected_utf8_chars; | |
7869 | else | |
7870 | chars = check_utf_8 (coding); | |
7871 | if (CODING_UTF_8_BOM (coding) != utf_without_bom | |
7872 | && coding->head_ascii == 0 | |
7873 | && coding->source[0] == UTF_8_BOM_1 | |
7874 | && coding->source[1] == UTF_8_BOM_2 | |
7875 | && coding->source[2] == UTF_8_BOM_3) | |
7876 | { | |
7877 | chars--; | |
7878 | bytes -= 3; | |
7879 | coding->src_bytes -= 3; | |
7880 | } | |
7881 | } | |
251e9147 KH |
7882 | else |
7883 | chars = -1; | |
7884 | } | |
7885 | if (chars >= 0) | |
c230dd7d | 7886 | { |
e6d2f155 | 7887 | Lisp_Object eol_type; |
251e9147 | 7888 | |
e6d2f155 KH |
7889 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
7890 | if (VECTORP (eol_type)) | |
7891 | { | |
7892 | if (coding->eol_seen != EOL_SEEN_NONE) | |
7893 | eol_type = adjust_coding_eol_type (coding, coding->eol_seen); | |
7894 | } | |
7895 | if (EQ (eol_type, Qmac)) | |
8a44e6d1 KH |
7896 | { |
7897 | unsigned char *src_end = GAP_END_ADDR; | |
cded56c1 | 7898 | unsigned char *src = src_end - coding->src_bytes; |
c230dd7d | 7899 | |
8a44e6d1 KH |
7900 | while (src < src_end) |
7901 | { | |
7902 | if (*src++ == '\r') | |
7903 | src[-1] = '\n'; | |
7904 | } | |
7905 | } | |
e6d2f155 | 7906 | else if (EQ (eol_type, Qdos)) |
c230dd7d | 7907 | { |
8a44e6d1 KH |
7908 | unsigned char *src = GAP_END_ADDR; |
7909 | unsigned char *src_beg = src - coding->src_bytes; | |
7910 | unsigned char *dst = src; | |
251e9147 | 7911 | ptrdiff_t diff; |
8a44e6d1 KH |
7912 | |
7913 | while (src_beg < src) | |
7914 | { | |
7915 | *--dst = *--src; | |
9e63b4a5 | 7916 | if (*src == '\n' && src > src_beg && src[-1] == '\r') |
8a44e6d1 KH |
7917 | src--; |
7918 | } | |
251e9147 KH |
7919 | diff = dst - src; |
7920 | bytes -= diff; | |
7921 | chars -= diff; | |
c230dd7d | 7922 | } |
251e9147 KH |
7923 | coding->produced = bytes; |
7924 | coding->produced_char = chars; | |
7925 | insert_from_gap (chars, bytes, 1); | |
c230dd7d KH |
7926 | return; |
7927 | } | |
7928 | } | |
c230dd7d | 7929 | code_conversion_save (0, 0); |
8f924df7 | 7930 | |
9286b333 | 7931 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7932 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7933 | decode_coding (coding); |
287c57d7 | 7934 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7935 | |
5e5c78be | 7936 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
b73bfc1c | 7937 | { |
d311d28c | 7938 | ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
5e5c78be KH |
7939 | Lisp_Object val; |
7940 | ||
7941 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7942 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7943 | make_number (coding->produced_char)); | |
5e5c78be KH |
7944 | CHECK_NATNUM (val); |
7945 | coding->produced_char += Z - prev_Z; | |
7946 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7947 | } |
4ed46869 | 7948 | |
df7492f9 | 7949 | unbind_to (count, Qnil); |
b73bfc1c | 7950 | } |
52d41803 | 7951 | |
d46c5b12 | 7952 | |
df7492f9 KH |
7953 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7954 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7955 | |
df7492f9 | 7956 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7957 | |
df7492f9 KH |
7958 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7959 | are positions in the buffer. | |
b73bfc1c | 7960 | |
df7492f9 KH |
7961 | If it is a string, the text is at the beginning of the string. |
7962 | FROM and TO are indices to the string. | |
4ed46869 | 7963 | |
df7492f9 KH |
7964 | If it is nil, the text is at coding->source. FROM and TO are |
7965 | indices to coding->source. | |
bb10be8b | 7966 | |
df7492f9 | 7967 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7968 | |
df7492f9 KH |
7969 | If it is a buffer, the decoded text is inserted at point of the |
7970 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7971 | is deleted. | |
4ed46869 | 7972 | |
df7492f9 KH |
7973 | If it is Qt, a string is made from the decoded text, and |
7974 | set in CODING->dst_object. | |
d46c5b12 | 7975 | |
df7492f9 | 7976 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7977 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7978 | CODING->destination by xmalloc. If the decoded text is longer than |
7979 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7980 | */ | |
d46c5b12 | 7981 | |
df7492f9 | 7982 | void |
cf84bb53 JB |
7983 | decode_coding_object (struct coding_system *coding, |
7984 | Lisp_Object src_object, | |
d311d28c PE |
7985 | ptrdiff_t from, ptrdiff_t from_byte, |
7986 | ptrdiff_t to, ptrdiff_t to_byte, | |
cf84bb53 | 7987 | Lisp_Object dst_object) |
d46c5b12 | 7988 | { |
d311d28c | 7989 | ptrdiff_t count = SPECPDL_INDEX (); |
c4a63b12 | 7990 | unsigned char *destination IF_LINT (= NULL); |
d311d28c PE |
7991 | ptrdiff_t dst_bytes IF_LINT (= 0); |
7992 | ptrdiff_t chars = to - from; | |
7993 | ptrdiff_t bytes = to_byte - from_byte; | |
df7492f9 | 7994 | Lisp_Object attrs; |
f10fe38f PE |
7995 | ptrdiff_t saved_pt = -1, saved_pt_byte IF_LINT (= 0); |
7996 | bool need_marker_adjustment = 0; | |
b3bfad50 | 7997 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7998 | |
b3bfad50 | 7999 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 8000 | |
df7492f9 | 8001 | if (NILP (dst_object)) |
d46c5b12 | 8002 | { |
df7492f9 KH |
8003 | destination = coding->destination; |
8004 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 8005 | } |
93dec019 | 8006 | |
df7492f9 KH |
8007 | coding->src_object = src_object; |
8008 | coding->src_chars = chars; | |
8009 | coding->src_bytes = bytes; | |
8010 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 8011 | |
df7492f9 | 8012 | if (STRINGP (src_object)) |
d46c5b12 | 8013 | { |
df7492f9 KH |
8014 | coding->src_pos = from; |
8015 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 8016 | } |
df7492f9 | 8017 | else if (BUFFERP (src_object)) |
88993dfd | 8018 | { |
df7492f9 KH |
8019 | set_buffer_internal (XBUFFER (src_object)); |
8020 | if (from != GPT) | |
8021 | move_gap_both (from, from_byte); | |
8022 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 8023 | { |
64cedb0c KH |
8024 | struct Lisp_Marker *tail; |
8025 | ||
8026 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
8027 | { | |
8028 | tail->need_adjustment | |
8029 | = tail->charpos == (tail->insertion_type ? from : to); | |
8030 | need_marker_adjustment |= tail->need_adjustment; | |
8031 | } | |
4776e638 | 8032 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 8033 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 8034 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
8035 | del_range_both (from, from_byte, to, to_byte, 1); |
8036 | coding->src_pos = -chars; | |
8037 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 8038 | } |
df7492f9 | 8039 | else |
fb88bf2d | 8040 | { |
df7492f9 KH |
8041 | coding->src_pos = from; |
8042 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 8043 | } |
88993dfd KH |
8044 | } |
8045 | ||
df7492f9 KH |
8046 | if (CODING_REQUIRE_DETECTION (coding)) |
8047 | detect_coding (coding); | |
8048 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 8049 | |
2cb26057 KH |
8050 | if (EQ (dst_object, Qt) |
8051 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
8052 | && NILP (dst_object))) | |
b73bfc1c | 8053 | { |
a1567c45 SM |
8054 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
8055 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
8056 | coding->dst_pos = BEG; |
8057 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 8058 | } |
df7492f9 | 8059 | else if (BUFFERP (dst_object)) |
d46c5b12 | 8060 | { |
24a73b0a | 8061 | code_conversion_save (0, 0); |
df7492f9 KH |
8062 | coding->dst_object = dst_object; |
8063 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
8064 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
8065 | coding->dst_multibyte | |
4b4deea2 | 8066 | = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters)); |
d46c5b12 KH |
8067 | } |
8068 | else | |
8069 | { | |
24a73b0a | 8070 | code_conversion_save (0, 0); |
df7492f9 | 8071 | coding->dst_object = Qnil; |
0154725e SM |
8072 | /* Most callers presume this will return a multibyte result, and they |
8073 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
8074 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 8075 | coding->dst_multibyte = 1; |
d46c5b12 KH |
8076 | } |
8077 | ||
df7492f9 | 8078 | decode_coding (coding); |
fa46990e | 8079 | |
df7492f9 KH |
8080 | if (BUFFERP (coding->dst_object)) |
8081 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 8082 | |
df7492f9 | 8083 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 8084 | { |
b3bfad50 | 8085 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d311d28c | 8086 | ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 8087 | Lisp_Object val; |
d46c5b12 | 8088 | |
c0cc7f7f | 8089 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
8090 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
8091 | old_deactivate_mark); | |
d4850d67 KH |
8092 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
8093 | make_number (coding->produced_char)); | |
df7492f9 KH |
8094 | UNGCPRO; |
8095 | CHECK_NATNUM (val); | |
8096 | coding->produced_char += Z - prev_Z; | |
8097 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 8098 | } |
de79a6a5 | 8099 | |
df7492f9 | 8100 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 8101 | { |
df7492f9 KH |
8102 | coding->dst_object = Fbuffer_string (); |
8103 | } | |
8104 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
8105 | { | |
8106 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
8107 | if (dst_bytes < coding->produced) | |
8108 | { | |
1af1a51a | 8109 | eassert (coding->produced > 0); |
b3bfad50 | 8110 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
8111 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) |
8112 | move_gap_both (BEGV, BEGV_BYTE); | |
72af86bd | 8113 | memcpy (destination, BEGV_ADDR, coding->produced); |
df7492f9 | 8114 | coding->destination = destination; |
d46c5b12 | 8115 | } |
ec6d2bb8 | 8116 | } |
b73bfc1c | 8117 | |
4776e638 KH |
8118 | if (saved_pt >= 0) |
8119 | { | |
8120 | /* This is the case of: | |
8121 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
8122 | As we have moved PT while replacing the original buffer | |
8123 | contents, we must recover it now. */ | |
8124 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 8125 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
8126 | if (saved_pt < from) |
8127 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
8128 | else if (saved_pt < from + chars) | |
8129 | TEMP_SET_PT_BOTH (from, from_byte); | |
4b4deea2 | 8130 | else if (! NILP (BVAR (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
8131 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
8132 | saved_pt_byte + (coding->produced - bytes)); | |
8133 | else | |
8134 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
8135 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
8136 | |
8137 | if (need_marker_adjustment) | |
8138 | { | |
8139 | struct Lisp_Marker *tail; | |
8140 | ||
8141 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
8142 | if (tail->need_adjustment) | |
8143 | { | |
8144 | tail->need_adjustment = 0; | |
8145 | if (tail->insertion_type) | |
8146 | { | |
8147 | tail->bytepos = from_byte; | |
8148 | tail->charpos = from; | |
8149 | } | |
8150 | else | |
8151 | { | |
8152 | tail->bytepos = from_byte + coding->produced; | |
8153 | tail->charpos | |
4b4deea2 | 8154 | = (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
8155 | ? tail->bytepos : from + coding->produced_char); |
8156 | } | |
8157 | } | |
8158 | } | |
d46c5b12 | 8159 | } |
4776e638 | 8160 | |
b3bfad50 | 8161 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 8162 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
8163 | } |
8164 | ||
d46c5b12 | 8165 | |
df7492f9 | 8166 | void |
cf84bb53 JB |
8167 | encode_coding_object (struct coding_system *coding, |
8168 | Lisp_Object src_object, | |
d311d28c PE |
8169 | ptrdiff_t from, ptrdiff_t from_byte, |
8170 | ptrdiff_t to, ptrdiff_t to_byte, | |
cf84bb53 | 8171 | Lisp_Object dst_object) |
d46c5b12 | 8172 | { |
d311d28c PE |
8173 | ptrdiff_t count = SPECPDL_INDEX (); |
8174 | ptrdiff_t chars = to - from; | |
8175 | ptrdiff_t bytes = to_byte - from_byte; | |
df7492f9 | 8176 | Lisp_Object attrs; |
f10fe38f PE |
8177 | ptrdiff_t saved_pt = -1, saved_pt_byte IF_LINT (= 0); |
8178 | bool need_marker_adjustment = 0; | |
8179 | bool kill_src_buffer = 0; | |
b3bfad50 | 8180 | Lisp_Object old_deactivate_mark; |
df7492f9 | 8181 | |
b3bfad50 | 8182 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
8183 | |
8184 | coding->src_object = src_object; | |
8185 | coding->src_chars = chars; | |
8186 | coding->src_bytes = bytes; | |
8187 | coding->src_multibyte = chars < bytes; | |
8188 | ||
8189 | attrs = CODING_ID_ATTRS (coding->id); | |
8190 | ||
64cedb0c KH |
8191 | if (EQ (src_object, dst_object)) |
8192 | { | |
8193 | struct Lisp_Marker *tail; | |
8194 | ||
8195 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
8196 | { | |
8197 | tail->need_adjustment | |
8198 | = tail->charpos == (tail->insertion_type ? from : to); | |
8199 | need_marker_adjustment |= tail->need_adjustment; | |
8200 | } | |
8201 | } | |
8202 | ||
df7492f9 | 8203 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 8204 | { |
24a73b0a | 8205 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
8206 | set_buffer_internal (XBUFFER (coding->src_object)); |
8207 | if (STRINGP (src_object)) | |
8208 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
8209 | else if (BUFFERP (src_object)) | |
8210 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
8211 | else | |
b68864e5 | 8212 | insert_1_both ((char *) coding->source + from, chars, bytes, 0, 0, 0); |
d46c5b12 | 8213 | |
df7492f9 KH |
8214 | if (EQ (src_object, dst_object)) |
8215 | { | |
8216 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 8217 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
8218 | del_range_both (from, from_byte, to, to_byte, 1); |
8219 | set_buffer_internal (XBUFFER (coding->src_object)); | |
8220 | } | |
8221 | ||
d4850d67 | 8222 | { |
b3bfad50 | 8223 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 8224 | |
b3bfad50 KH |
8225 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
8226 | old_deactivate_mark); | |
6cd7a139 DA |
8227 | safe_call2 (CODING_ATTR_PRE_WRITE (attrs), |
8228 | make_number (BEG), make_number (Z)); | |
b3bfad50 | 8229 | UNGCPRO; |
d4850d67 | 8230 | } |
c02d943b KH |
8231 | if (XBUFFER (coding->src_object) != current_buffer) |
8232 | kill_src_buffer = 1; | |
ac87bbef | 8233 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
8234 | if (BEG != GPT) |
8235 | move_gap_both (BEG, BEG_BYTE); | |
8236 | coding->src_chars = Z - BEG; | |
8237 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
8238 | coding->src_pos = BEG; | |
8239 | coding->src_pos_byte = BEG_BYTE; | |
8240 | coding->src_multibyte = Z < Z_BYTE; | |
8241 | } | |
8242 | else if (STRINGP (src_object)) | |
d46c5b12 | 8243 | { |
24a73b0a | 8244 | code_conversion_save (0, 0); |
df7492f9 KH |
8245 | coding->src_pos = from; |
8246 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 8247 | } |
df7492f9 | 8248 | else if (BUFFERP (src_object)) |
b73bfc1c | 8249 | { |
24a73b0a | 8250 | code_conversion_save (0, 0); |
df7492f9 | 8251 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 8252 | if (EQ (src_object, dst_object)) |
d46c5b12 | 8253 | { |
4776e638 | 8254 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
8255 | coding->src_object = del_range_1 (from, to, 1, 1); |
8256 | coding->src_pos = 0; | |
8257 | coding->src_pos_byte = 0; | |
d46c5b12 | 8258 | } |
df7492f9 | 8259 | else |
d46c5b12 | 8260 | { |
ff0dacd7 KH |
8261 | if (from < GPT && to >= GPT) |
8262 | move_gap_both (from, from_byte); | |
df7492f9 KH |
8263 | coding->src_pos = from; |
8264 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 8265 | } |
d46c5b12 | 8266 | } |
4776e638 | 8267 | else |
24a73b0a | 8268 | code_conversion_save (0, 0); |
d46c5b12 | 8269 | |
df7492f9 | 8270 | if (BUFFERP (dst_object)) |
88993dfd | 8271 | { |
df7492f9 | 8272 | coding->dst_object = dst_object; |
28f67a95 KH |
8273 | if (EQ (src_object, dst_object)) |
8274 | { | |
8275 | coding->dst_pos = from; | |
8276 | coding->dst_pos_byte = from_byte; | |
8277 | } | |
8278 | else | |
8279 | { | |
319a3947 KH |
8280 | struct buffer *current = current_buffer; |
8281 | ||
8282 | set_buffer_temp (XBUFFER (dst_object)); | |
8283 | coding->dst_pos = PT; | |
8284 | coding->dst_pos_byte = PT_BYTE; | |
8285 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
8286 | set_buffer_temp (current); | |
28f67a95 | 8287 | } |
df7492f9 | 8288 | coding->dst_multibyte |
4b4deea2 | 8289 | = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters)); |
88993dfd | 8290 | } |
df7492f9 | 8291 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 8292 | { |
5d009b3a | 8293 | ptrdiff_t dst_bytes = max (1, coding->src_chars); |
df7492f9 | 8294 | coding->dst_object = Qnil; |
23f86fce | 8295 | coding->destination = xmalloc (dst_bytes); |
5d009b3a | 8296 | coding->dst_bytes = dst_bytes; |
df7492f9 | 8297 | coding->dst_multibyte = 0; |
d46c5b12 KH |
8298 | } |
8299 | else | |
8300 | { | |
df7492f9 KH |
8301 | coding->dst_object = Qnil; |
8302 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
8303 | } |
8304 | ||
df7492f9 | 8305 | encode_coding (coding); |
d46c5b12 | 8306 | |
df7492f9 | 8307 | if (EQ (dst_object, Qt)) |
d46c5b12 | 8308 | { |
df7492f9 KH |
8309 | if (BUFFERP (coding->dst_object)) |
8310 | coding->dst_object = Fbuffer_string (); | |
8311 | else | |
d46c5b12 | 8312 | { |
df7492f9 KH |
8313 | coding->dst_object |
8314 | = make_unibyte_string ((char *) coding->destination, | |
8315 | coding->produced); | |
8316 | xfree (coding->destination); | |
d46c5b12 | 8317 | } |
4ed46869 | 8318 | } |
d46c5b12 | 8319 | |
4776e638 KH |
8320 | if (saved_pt >= 0) |
8321 | { | |
8322 | /* This is the case of: | |
8323 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
8324 | As we have moved PT while replacing the original buffer | |
8325 | contents, we must recover it now. */ | |
8326 | set_buffer_internal (XBUFFER (src_object)); | |
8327 | if (saved_pt < from) | |
8328 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
8329 | else if (saved_pt < from + chars) | |
8330 | TEMP_SET_PT_BOTH (from, from_byte); | |
4b4deea2 | 8331 | else if (! NILP (BVAR (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
8332 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
8333 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 8334 | else |
4776e638 KH |
8335 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
8336 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
8337 | |
8338 | if (need_marker_adjustment) | |
8339 | { | |
8340 | struct Lisp_Marker *tail; | |
8341 | ||
8342 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
8343 | if (tail->need_adjustment) | |
8344 | { | |
8345 | tail->need_adjustment = 0; | |
8346 | if (tail->insertion_type) | |
8347 | { | |
8348 | tail->bytepos = from_byte; | |
8349 | tail->charpos = from; | |
8350 | } | |
8351 | else | |
8352 | { | |
8353 | tail->bytepos = from_byte + coding->produced; | |
8354 | tail->charpos | |
4b4deea2 | 8355 | = (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
8356 | ? tail->bytepos : from + coding->produced_char); |
8357 | } | |
8358 | } | |
8359 | } | |
4776e638 KH |
8360 | } |
8361 | ||
c02d943b KH |
8362 | if (kill_src_buffer) |
8363 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
8364 | |
8365 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 8366 | unbind_to (count, Qnil); |
b73bfc1c KH |
8367 | } |
8368 | ||
df7492f9 | 8369 | |
b73bfc1c | 8370 | Lisp_Object |
971de7fb | 8371 | preferred_coding_system (void) |
b73bfc1c | 8372 | { |
df7492f9 | 8373 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 8374 | |
df7492f9 | 8375 | return CODING_ID_NAME (id); |
4ed46869 KH |
8376 | } |
8377 | ||
7f590b0c | 8378 | #if defined (WINDOWSNT) || defined (CYGWIN) |
ba116008 DC |
8379 | |
8380 | Lisp_Object | |
8381 | from_unicode (Lisp_Object str) | |
8382 | { | |
8383 | CHECK_STRING (str); | |
8384 | if (!STRING_MULTIBYTE (str) && | |
8385 | SBYTES (str) & 1) | |
8386 | { | |
8387 | str = Fsubstring (str, make_number (0), make_number (-1)); | |
8388 | } | |
8389 | ||
8390 | return code_convert_string_norecord (str, Qutf_16le, 0); | |
8391 | } | |
8392 | ||
819e2da9 DC |
8393 | Lisp_Object |
8394 | from_unicode_buffer (const wchar_t* wstr) | |
8395 | { | |
8396 | return from_unicode ( | |
8397 | make_unibyte_string ( | |
8398 | (char*) wstr, | |
8399 | /* we get one of the two final 0 bytes for free. */ | |
8400 | 1 + sizeof (wchar_t) * wcslen (wstr))); | |
8401 | } | |
8402 | ||
ba116008 DC |
8403 | wchar_t * |
8404 | to_unicode (Lisp_Object str, Lisp_Object *buf) | |
8405 | { | |
8406 | *buf = code_convert_string_norecord (str, Qutf_16le, 1); | |
bc989a58 | 8407 | /* We need to make another copy (in addition to the one made by |
ba116008 DC |
8408 | code_convert_string_norecord) to ensure that the final string is |
8409 | _doubly_ zero terminated --- that is, that the string is | |
8410 | terminated by two zero bytes and one utf-16le null character. | |
8411 | Because strings are already terminated with a single zero byte, | |
8412 | we just add one additional zero. */ | |
8413 | str = make_uninit_string (SBYTES (*buf) + 1); | |
8414 | memcpy (SDATA (str), SDATA (*buf), SBYTES (*buf)); | |
8415 | SDATA (str) [SBYTES (*buf)] = '\0'; | |
8416 | *buf = str; | |
8417 | return WCSDATA (*buf); | |
8418 | } | |
7f590b0c DC |
8419 | |
8420 | #endif /* WINDOWSNT || CYGWIN */ | |
ba116008 | 8421 | |
4ed46869 KH |
8422 | \f |
8423 | #ifdef emacs | |
1397dc18 | 8424 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 8425 | |
a7ca3326 | 8426 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 8427 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 8428 | See the documentation of `define-coding-system' for information |
48b0f3ae | 8429 | about coding-system objects. */) |
5842a27b | 8430 | (Lisp_Object object) |
4ed46869 | 8431 | { |
d4a1d553 JB |
8432 | if (NILP (object) |
8433 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 8434 | return Qt; |
d4a1d553 JB |
8435 | if (! SYMBOLP (object) |
8436 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
8437 | return Qnil; |
8438 | return Qt; | |
4ed46869 KH |
8439 | } |
8440 | ||
a7ca3326 | 8441 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
9d991de8 | 8442 | Sread_non_nil_coding_system, 1, 1, 0, |
48b0f3ae | 8443 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
5842a27b | 8444 | (Lisp_Object prompt) |
4ed46869 | 8445 | { |
e0e989f6 | 8446 | Lisp_Object val; |
9d991de8 RS |
8447 | do |
8448 | { | |
4608c386 KH |
8449 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
8450 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 8451 | } |
8f924df7 | 8452 | while (SCHARS (val) == 0); |
e0e989f6 | 8453 | return (Fintern (val, Qnil)); |
4ed46869 KH |
8454 | } |
8455 | ||
a7ca3326 | 8456 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 8457 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
8458 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
8459 | Ignores case when completing coding systems (all Emacs coding systems | |
8460 | are lower-case). */) | |
5842a27b | 8461 | (Lisp_Object prompt, Lisp_Object default_coding_system) |
4ed46869 | 8462 | { |
f44d27ce | 8463 | Lisp_Object val; |
d311d28c | 8464 | ptrdiff_t count = SPECPDL_INDEX (); |
c7183fb8 | 8465 | |
9b787f3e | 8466 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 8467 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 8468 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 8469 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
8470 | Qt, Qnil, Qcoding_system_history, |
8471 | default_coding_system, Qnil); | |
c7183fb8 | 8472 | unbind_to (count, Qnil); |
8f924df7 | 8473 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
8474 | } |
8475 | ||
a7ca3326 | 8476 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, |
4ed46869 | 8477 | 1, 1, 0, |
48b0f3ae | 8478 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
8479 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
8480 | It is valid if it is nil or a symbol defined as a coding system by the | |
8481 | function `define-coding-system'. */) | |
5842a27b | 8482 | (Lisp_Object coding_system) |
4ed46869 | 8483 | { |
44e8490d KH |
8484 | Lisp_Object define_form; |
8485 | ||
8486 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
8487 | if (! NILP (define_form)) | |
8488 | { | |
8489 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
8490 | safe_eval (define_form); | |
8491 | } | |
4ed46869 KH |
8492 | if (!NILP (Fcoding_system_p (coding_system))) |
8493 | return coding_system; | |
fcad4ec4 | 8494 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 8495 | } |
df7492f9 | 8496 | |
3a73fa5d | 8497 | \f |
89528eb3 | 8498 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
f10fe38f | 8499 | HIGHEST, return the coding system of the highest |
ad1746f5 | 8500 | priority among the detected coding systems. Otherwise return a |
89528eb3 | 8501 | list of detected coding systems sorted by their priorities. If |
f10fe38f | 8502 | MULTIBYTEP, it is assumed that the bytes are in correct |
89528eb3 KH |
8503 | multibyte form but contains only ASCII and eight-bit chars. |
8504 | Otherwise, the bytes are raw bytes. | |
8505 | ||
8506 | CODING-SYSTEM controls the detection as below: | |
8507 | ||
8508 | If it is nil, detect both text-format and eol-format. If the | |
8509 | text-format part of CODING-SYSTEM is already specified | |
8510 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
8511 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
8512 | detect only text-format. */ | |
8513 | ||
d46c5b12 | 8514 | Lisp_Object |
cf84bb53 | 8515 | detect_coding_system (const unsigned char *src, |
d311d28c | 8516 | ptrdiff_t src_chars, ptrdiff_t src_bytes, |
f10fe38f | 8517 | bool highest, bool multibytep, |
cf84bb53 | 8518 | Lisp_Object coding_system) |
4ed46869 | 8519 | { |
8f924df7 | 8520 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 8521 | Lisp_Object attrs, eol_type; |
4533845d | 8522 | Lisp_Object val = Qnil; |
df7492f9 | 8523 | struct coding_system coding; |
d3411f89 | 8524 | ptrdiff_t id; |
ff0dacd7 | 8525 | struct coding_detection_info detect_info; |
24a73b0a | 8526 | enum coding_category base_category; |
f10fe38f | 8527 | bool null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 8528 | |
df7492f9 KH |
8529 | if (NILP (coding_system)) |
8530 | coding_system = Qundecided; | |
8531 | setup_coding_system (coding_system, &coding); | |
8532 | attrs = CODING_ID_ATTRS (coding.id); | |
8533 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 8534 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 8535 | |
df7492f9 | 8536 | coding.source = src; |
24a73b0a | 8537 | coding.src_chars = src_chars; |
df7492f9 KH |
8538 | coding.src_bytes = src_bytes; |
8539 | coding.src_multibyte = multibytep; | |
8540 | coding.consumed = 0; | |
89528eb3 | 8541 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 8542 | coding.head_ascii = 0; |
d46c5b12 | 8543 | |
ff0dacd7 | 8544 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 8545 | |
89528eb3 | 8546 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
8547 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
8548 | if (base_category == coding_category_undecided) | |
4ed46869 | 8549 | { |
c4a63b12 PE |
8550 | enum coding_category category IF_LINT (= 0); |
8551 | struct coding_system *this IF_LINT (= NULL); | |
ff0dacd7 | 8552 | int c, i; |
9c90cc06 PE |
8553 | bool inhibit_nbd = inhibit_flag (coding.spec.undecided.inhibit_nbd, |
8554 | inhibit_null_byte_detection); | |
8555 | bool inhibit_ied = inhibit_flag (coding.spec.undecided.inhibit_ied, | |
8556 | inhibit_iso_escape_detection); | |
8557 | bool prefer_utf_8 = coding.spec.undecided.prefer_utf_8; | |
88993dfd | 8558 | |
24a73b0a | 8559 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 8560 | for (; src < src_end; src++) |
4ed46869 | 8561 | { |
df7492f9 | 8562 | c = *src; |
6cb21a4f | 8563 | if (c & 0x80) |
6cb21a4f | 8564 | { |
2f3cbb32 | 8565 | eight_bit_found = 1; |
2f3cbb32 KH |
8566 | if (null_byte_found) |
8567 | break; | |
8568 | } | |
c0e16b14 | 8569 | else if (c < 0x20) |
2f3cbb32 KH |
8570 | { |
8571 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
c3a7b3f4 | 8572 | && ! inhibit_ied |
2f3cbb32 | 8573 | && ! detect_info.checked) |
6cb21a4f | 8574 | { |
2f3cbb32 KH |
8575 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
8576 | { | |
8577 | /* We have scanned the whole data. */ | |
8578 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
8579 | { |
8580 | /* We didn't find an 8-bit code. We may | |
8581 | have found a null-byte, but it's very | |
8582 | rare that a binary file confirm to | |
8583 | ISO-2022. */ | |
8584 | src = src_end; | |
8585 | coding.head_ascii = src - coding.source; | |
8586 | } | |
8587 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
8588 | break; |
8589 | } | |
8590 | } | |
c3a7b3f4 | 8591 | else if (! c && !inhibit_nbd) |
2f3cbb32 KH |
8592 | { |
8593 | null_byte_found = 1; | |
8594 | if (eight_bit_found) | |
8595 | break; | |
6cb21a4f | 8596 | } |
c006c0c8 KH |
8597 | if (! eight_bit_found) |
8598 | coding.head_ascii++; | |
6cb21a4f | 8599 | } |
c006c0c8 | 8600 | else if (! eight_bit_found) |
c0e16b14 | 8601 | coding.head_ascii++; |
4ed46869 | 8602 | } |
88993dfd | 8603 | |
2f3cbb32 KH |
8604 | if (null_byte_found || eight_bit_found |
8605 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
8606 | || detect_info.found) |
8607 | { | |
2f3cbb32 | 8608 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
8609 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
8610 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 8611 | { |
6cb21a4f | 8612 | category = coding_priorities[i]; |
c7266f4a | 8613 | this = coding_categories + category; |
6cb21a4f | 8614 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
8615 | break; |
8616 | } | |
6cb21a4f | 8617 | else |
2f3cbb32 KH |
8618 | { |
8619 | if (null_byte_found) | |
8620 | { | |
8621 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
8622 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
8623 | } | |
c3a7b3f4 KH |
8624 | else if (prefer_utf_8 |
8625 | && detect_coding_utf_8 (&coding, &detect_info)) | |
8626 | { | |
8627 | detect_info.checked |= ~CATEGORY_MASK_UTF_8; | |
8628 | detect_info.rejected |= ~CATEGORY_MASK_UTF_8; | |
8629 | } | |
2f3cbb32 KH |
8630 | for (i = 0; i < coding_category_raw_text; i++) |
8631 | { | |
8632 | category = coding_priorities[i]; | |
8633 | this = coding_categories + category; | |
6cb21a4f | 8634 | |
2f3cbb32 KH |
8635 | if (this->id < 0) |
8636 | { | |
8637 | /* No coding system of this category is defined. */ | |
8638 | detect_info.rejected |= (1 << category); | |
8639 | } | |
8640 | else if (category >= coding_category_raw_text) | |
8641 | continue; | |
8642 | else if (detect_info.checked & (1 << category)) | |
8643 | { | |
8644 | if (highest | |
8645 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 8646 | break; |
2f3cbb32 KH |
8647 | } |
8648 | else if ((*(this->detector)) (&coding, &detect_info) | |
8649 | && highest | |
8650 | && (detect_info.found & (1 << category))) | |
8651 | { | |
8652 | if (category == coding_category_utf_16_auto) | |
8653 | { | |
8654 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8655 | category = coding_category_utf_16_le; | |
8656 | else | |
8657 | category = coding_category_utf_16_be; | |
8658 | } | |
8659 | break; | |
8660 | } | |
8661 | } | |
8662 | } | |
6cb21a4f | 8663 | } |
ec6d2bb8 | 8664 | |
4cddb209 KH |
8665 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
8666 | || null_byte_found) | |
ec6d2bb8 | 8667 | { |
ff0dacd7 | 8668 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 8669 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
8670 | val = Fcons (make_number (id), Qnil); |
8671 | } | |
ff0dacd7 | 8672 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 8673 | { |
ff0dacd7 | 8674 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
8675 | id = coding_categories[coding_category_undecided].id; |
8676 | val = Fcons (make_number (id), Qnil); | |
8677 | } | |
8678 | else if (highest) | |
8679 | { | |
ff0dacd7 | 8680 | if (detect_info.found) |
ec6d2bb8 | 8681 | { |
ff0dacd7 KH |
8682 | detect_info.found = 1 << category; |
8683 | val = Fcons (make_number (this->id), Qnil); | |
8684 | } | |
8685 | else | |
8686 | for (i = 0; i < coding_category_raw_text; i++) | |
8687 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
8688 | { | |
8689 | detect_info.found = 1 << coding_priorities[i]; | |
8690 | id = coding_categories[coding_priorities[i]].id; | |
8691 | val = Fcons (make_number (id), Qnil); | |
8692 | break; | |
8693 | } | |
8694 | } | |
89528eb3 KH |
8695 | else |
8696 | { | |
ff0dacd7 KH |
8697 | int mask = detect_info.rejected | detect_info.found; |
8698 | int found = 0; | |
ec6d2bb8 | 8699 | |
89528eb3 | 8700 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
8701 | { |
8702 | category = coding_priorities[i]; | |
8703 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 8704 | { |
ff0dacd7 KH |
8705 | found |= 1 << category; |
8706 | id = coding_categories[category].id; | |
c7266f4a KH |
8707 | if (id >= 0) |
8708 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
8709 | } |
8710 | } | |
8711 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
8712 | { | |
8713 | category = coding_priorities[i]; | |
8714 | if (detect_info.found & (1 << category)) | |
8715 | { | |
8716 | id = coding_categories[category].id; | |
8717 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 8718 | } |
ec6d2bb8 | 8719 | } |
ff0dacd7 | 8720 | detect_info.found |= found; |
ec6d2bb8 | 8721 | } |
ec6d2bb8 | 8722 | } |
a470d443 KH |
8723 | else if (base_category == coding_category_utf_8_auto) |
8724 | { | |
8725 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
8726 | { | |
8727 | struct coding_system *this; | |
8728 | ||
8729 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
8730 | this = coding_categories + coding_category_utf_8_sig; | |
8731 | else | |
8732 | this = coding_categories + coding_category_utf_8_nosig; | |
8733 | val = Fcons (make_number (this->id), Qnil); | |
8734 | } | |
8735 | } | |
24a73b0a KH |
8736 | else if (base_category == coding_category_utf_16_auto) |
8737 | { | |
8738 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
8739 | { | |
24a73b0a KH |
8740 | struct coding_system *this; |
8741 | ||
8742 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8743 | this = coding_categories + coding_category_utf_16_le; | |
8744 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
8745 | this = coding_categories + coding_category_utf_16_be; | |
8746 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
8747 | this = coding_categories + coding_category_utf_16_be_nosig; | |
8748 | else | |
8749 | this = coding_categories + coding_category_utf_16_le_nosig; | |
8750 | val = Fcons (make_number (this->id), Qnil); | |
8751 | } | |
8752 | } | |
df7492f9 KH |
8753 | else |
8754 | { | |
ff0dacd7 | 8755 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 8756 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8757 | } |
df7492f9 | 8758 | |
89528eb3 | 8759 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8760 | { |
4533845d | 8761 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8762 | Lisp_Object tail; |
8763 | ||
89528eb3 KH |
8764 | if (VECTORP (eol_type)) |
8765 | { | |
ff0dacd7 | 8766 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8767 | { |
8768 | if (null_byte_found) | |
8769 | normal_eol = EOL_SEEN_LF; | |
8770 | else | |
8771 | normal_eol = detect_eol (coding.source, src_bytes, | |
8772 | coding_category_raw_text); | |
8773 | } | |
ff0dacd7 KH |
8774 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8775 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8776 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8777 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8778 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8779 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8780 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8781 | coding_category_utf_16_le); | |
8782 | } | |
8783 | else | |
8784 | { | |
8785 | if (EQ (eol_type, Qunix)) | |
8786 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8787 | else if (EQ (eol_type, Qdos)) | |
8788 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8789 | else | |
8790 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8791 | } | |
8792 | ||
df7492f9 KH |
8793 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8794 | { | |
89528eb3 | 8795 | enum coding_category category; |
df7492f9 | 8796 | int this_eol; |
89528eb3 KH |
8797 | |
8798 | id = XINT (XCAR (tail)); | |
8799 | attrs = CODING_ID_ATTRS (id); | |
8800 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8801 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8802 | if (VECTORP (eol_type)) |
8803 | { | |
89528eb3 KH |
8804 | if (category == coding_category_utf_16_be |
8805 | || category == coding_category_utf_16_be_nosig) | |
8806 | this_eol = utf_16_be_eol; | |
8807 | else if (category == coding_category_utf_16_le | |
8808 | || category == coding_category_utf_16_le_nosig) | |
8809 | this_eol = utf_16_le_eol; | |
df7492f9 | 8810 | else |
89528eb3 KH |
8811 | this_eol = normal_eol; |
8812 | ||
df7492f9 KH |
8813 | if (this_eol == EOL_SEEN_LF) |
8814 | XSETCAR (tail, AREF (eol_type, 0)); | |
8815 | else if (this_eol == EOL_SEEN_CRLF) | |
8816 | XSETCAR (tail, AREF (eol_type, 1)); | |
8817 | else if (this_eol == EOL_SEEN_CR) | |
8818 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8819 | else |
8820 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8821 | } |
89528eb3 KH |
8822 | else |
8823 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8824 | } |
8825 | } | |
ec6d2bb8 | 8826 | |
4533845d | 8827 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8828 | } |
8829 | ||
ec6d2bb8 | 8830 | |
d46c5b12 KH |
8831 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8832 | 2, 3, 0, | |
48b0f3ae PJ |
8833 | doc: /* Detect coding system of the text in the region between START and END. |
8834 | Return a list of possible coding systems ordered by priority. | |
b811c52b KH |
8835 | The coding systems to try and their priorities follows what |
8836 | the function `coding-system-priority-list' (which see) returns. | |
ec6d2bb8 | 8837 | |
12e0131a | 8838 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8839 | characters as ESC), it returns a list of single element `undecided' |
8840 | or its subsidiary coding system according to a detected end-of-line | |
8841 | format. | |
ec6d2bb8 | 8842 | |
48b0f3ae PJ |
8843 | If optional argument HIGHEST is non-nil, return the coding system of |
8844 | highest priority. */) | |
5842a27b | 8845 | (Lisp_Object start, Lisp_Object end, Lisp_Object highest) |
d46c5b12 | 8846 | { |
d311d28c PE |
8847 | ptrdiff_t from, to; |
8848 | ptrdiff_t from_byte, to_byte; | |
ec6d2bb8 | 8849 | |
d46c5b12 KH |
8850 | validate_region (&start, &end); |
8851 | from = XINT (start), to = XINT (end); | |
8852 | from_byte = CHAR_TO_BYTE (from); | |
8853 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8854 | |
d46c5b12 KH |
8855 | if (from < GPT && to >= GPT) |
8856 | move_gap_both (to, to_byte); | |
c210f766 | 8857 | |
d46c5b12 | 8858 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8859 | to - from, to_byte - from_byte, |
0a28aafb | 8860 | !NILP (highest), |
4b4deea2 | 8861 | !NILP (BVAR (current_buffer |
5d8ea120 | 8862 | , enable_multibyte_characters)), |
df7492f9 | 8863 | Qnil); |
ec6d2bb8 KH |
8864 | } |
8865 | ||
d46c5b12 KH |
8866 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8867 | 1, 2, 0, | |
48b0f3ae PJ |
8868 | doc: /* Detect coding system of the text in STRING. |
8869 | Return a list of possible coding systems ordered by priority. | |
67ceab9d KH |
8870 | The coding systems to try and their priorities follows what |
8871 | the function `coding-system-priority-list' (which see) returns. | |
fb88bf2d | 8872 | |
12e0131a | 8873 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8874 | characters as ESC), it returns a list of single element `undecided' |
8875 | or its subsidiary coding system according to a detected end-of-line | |
8876 | format. | |
d46c5b12 | 8877 | |
48b0f3ae PJ |
8878 | If optional argument HIGHEST is non-nil, return the coding system of |
8879 | highest priority. */) | |
5842a27b | 8880 | (Lisp_Object string, Lisp_Object highest) |
d46c5b12 | 8881 | { |
b7826503 | 8882 | CHECK_STRING (string); |
b73bfc1c | 8883 | |
24a73b0a KH |
8884 | return detect_coding_system (SDATA (string), |
8885 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8886 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8887 | Qnil); |
4ed46869 | 8888 | } |
4ed46869 | 8889 | |
b73bfc1c | 8890 | |
b0ab8123 | 8891 | static bool |
971de7fb | 8892 | char_encodable_p (int c, Lisp_Object attrs) |
05e6f5dc | 8893 | { |
df7492f9 | 8894 | Lisp_Object tail; |
df7492f9 | 8895 | struct charset *charset; |
7d64c6ad | 8896 | Lisp_Object translation_table; |
d46c5b12 | 8897 | |
7d64c6ad | 8898 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8899 | if (! NILP (translation_table)) |
7d64c6ad | 8900 | c = translate_char (translation_table, c); |
df7492f9 KH |
8901 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8902 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8903 | { |
df7492f9 KH |
8904 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8905 | if (CHAR_CHARSET_P (c, charset)) | |
8906 | break; | |
e133c8fa | 8907 | } |
df7492f9 | 8908 | return (! NILP (tail)); |
05e6f5dc | 8909 | } |
83fa074f | 8910 | |
fb88bf2d | 8911 | |
df7492f9 KH |
8912 | /* Return a list of coding systems that safely encode the text between |
8913 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8914 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8915 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8916 | unibyte, return t. */ |
e077cc80 | 8917 | |
df7492f9 KH |
8918 | DEFUN ("find-coding-systems-region-internal", |
8919 | Ffind_coding_systems_region_internal, | |
8920 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8921 | doc: /* Internal use only. */) | |
5842a27b | 8922 | (Lisp_Object start, Lisp_Object end, Lisp_Object exclude) |
df7492f9 KH |
8923 | { |
8924 | Lisp_Object coding_attrs_list, safe_codings; | |
d311d28c | 8925 | ptrdiff_t start_byte, end_byte; |
7c78e542 | 8926 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8927 | int c; |
0e727afa | 8928 | Lisp_Object tail, elt, work_table; |
d46c5b12 | 8929 | |
df7492f9 KH |
8930 | if (STRINGP (start)) |
8931 | { | |
8932 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8933 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8934 | return Qt; |
8935 | start_byte = 0; | |
8f924df7 | 8936 | end_byte = SBYTES (start); |
df7492f9 KH |
8937 | } |
8938 | else | |
d46c5b12 | 8939 | { |
df7492f9 KH |
8940 | CHECK_NUMBER_COERCE_MARKER (start); |
8941 | CHECK_NUMBER_COERCE_MARKER (end); | |
8942 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8943 | args_out_of_range (start, end); | |
4b4deea2 | 8944 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8945 | return Qt; |
8946 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8947 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8948 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8949 | return Qt; | |
d46c5b12 | 8950 | |
e1c23804 | 8951 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8952 | { |
e1c23804 DL |
8953 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8954 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8955 | else |
e1c23804 | 8956 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8957 | } |
8958 | } | |
8959 | ||
df7492f9 KH |
8960 | coding_attrs_list = Qnil; |
8961 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8962 | if (NILP (exclude) | |
8963 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8964 | { | |
8965 | Lisp_Object attrs; | |
d46c5b12 | 8966 | |
df7492f9 | 8967 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
c3a7b3f4 | 8968 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs))) |
7d64c6ad KH |
8969 | { |
8970 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8971 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8972 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8973 | } | |
df7492f9 | 8974 | } |
d46c5b12 | 8975 | |
df7492f9 | 8976 | if (STRINGP (start)) |
8f924df7 | 8977 | p = pbeg = SDATA (start); |
df7492f9 KH |
8978 | else |
8979 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8980 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8981 | |
df7492f9 KH |
8982 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8983 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8984 | |
0e727afa | 8985 | work_table = Fmake_char_table (Qnil, Qnil); |
05e6f5dc | 8986 | while (p < pend) |
72d1a715 | 8987 | { |
df7492f9 KH |
8988 | if (ASCII_BYTE_P (*p)) |
8989 | p++; | |
72d1a715 RS |
8990 | else |
8991 | { | |
df7492f9 | 8992 | c = STRING_CHAR_ADVANCE (p); |
0e727afa YM |
8993 | if (!NILP (char_table_ref (work_table, c))) |
8994 | /* This character was already checked. Ignore it. */ | |
8995 | continue; | |
12410ef1 | 8996 | |
df7492f9 KH |
8997 | charset_map_loaded = 0; |
8998 | for (tail = coding_attrs_list; CONSP (tail);) | |
8999 | { | |
9000 | elt = XCAR (tail); | |
9001 | if (NILP (elt)) | |
9002 | tail = XCDR (tail); | |
9003 | else if (char_encodable_p (c, elt)) | |
9004 | tail = XCDR (tail); | |
9005 | else if (CONSP (XCDR (tail))) | |
9006 | { | |
9007 | XSETCAR (tail, XCAR (XCDR (tail))); | |
9008 | XSETCDR (tail, XCDR (XCDR (tail))); | |
9009 | } | |
9010 | else | |
9011 | { | |
9012 | XSETCAR (tail, Qnil); | |
9013 | tail = XCDR (tail); | |
9014 | } | |
9015 | } | |
9016 | if (charset_map_loaded) | |
9017 | { | |
d311d28c | 9018 | ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg; |
05e6f5dc | 9019 | |
df7492f9 | 9020 | if (STRINGP (start)) |
8f924df7 | 9021 | pbeg = SDATA (start); |
df7492f9 KH |
9022 | else |
9023 | pbeg = BYTE_POS_ADDR (start_byte); | |
9024 | p = pbeg + p_offset; | |
9025 | pend = pbeg + pend_offset; | |
9026 | } | |
0e727afa | 9027 | char_table_set (work_table, c, Qt); |
df7492f9 | 9028 | } |
ec6d2bb8 | 9029 | } |
fb88bf2d | 9030 | |
988b3759 | 9031 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
9032 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
9033 | if (! NILP (XCAR (tail))) | |
9034 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 9035 | |
05e6f5dc KH |
9036 | return safe_codings; |
9037 | } | |
4956c225 | 9038 | |
d46c5b12 | 9039 | |
8f924df7 KH |
9040 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
9041 | Sunencodable_char_position, 3, 5, 0, | |
9042 | doc: /* | |
9043 | Return position of first un-encodable character in a region. | |
d4a1d553 | 9044 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 9045 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 9046 | |
8f924df7 KH |
9047 | If optional 4th argument COUNT is non-nil, it specifies at most how |
9048 | many un-encodable characters to search. In this case, the value is a | |
9049 | list of positions. | |
d46c5b12 | 9050 | |
8f924df7 KH |
9051 | If optional 5th argument STRING is non-nil, it is a string to search |
9052 | for un-encodable characters. In that case, START and END are indexes | |
9053 | to the string. */) | |
5842a27b | 9054 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object count, Lisp_Object string) |
8f924df7 | 9055 | { |
d311d28c | 9056 | EMACS_INT n; |
8f924df7 | 9057 | struct coding_system coding; |
7d64c6ad | 9058 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 | 9059 | Lisp_Object positions; |
d311d28c | 9060 | ptrdiff_t from, to; |
8f924df7 | 9061 | const unsigned char *p, *stop, *pend; |
f10fe38f | 9062 | bool ascii_compatible; |
fb88bf2d | 9063 | |
8f924df7 KH |
9064 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
9065 | attrs = CODING_ID_ATTRS (coding.id); | |
9066 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
9067 | return Qnil; | |
9068 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
9069 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 9070 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 9071 | |
8f924df7 KH |
9072 | if (NILP (string)) |
9073 | { | |
9074 | validate_region (&start, &end); | |
9075 | from = XINT (start); | |
9076 | to = XINT (end); | |
4b4deea2 | 9077 | if (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
8f924df7 KH |
9078 | || (ascii_compatible |
9079 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
9080 | return Qnil; | |
9081 | p = CHAR_POS_ADDR (from); | |
9082 | pend = CHAR_POS_ADDR (to); | |
9083 | if (from < GPT && to >= GPT) | |
9084 | stop = GPT_ADDR; | |
9085 | else | |
9086 | stop = pend; | |
9087 | } | |
9088 | else | |
9089 | { | |
9090 | CHECK_STRING (string); | |
9091 | CHECK_NATNUM (start); | |
9092 | CHECK_NATNUM (end); | |
d311d28c PE |
9093 | if (! (XINT (start) <= XINT (end) && XINT (end) <= SCHARS (string))) |
9094 | args_out_of_range_3 (string, start, end); | |
8f924df7 KH |
9095 | from = XINT (start); |
9096 | to = XINT (end); | |
8f924df7 KH |
9097 | if (! STRING_MULTIBYTE (string)) |
9098 | return Qnil; | |
9099 | p = SDATA (string) + string_char_to_byte (string, from); | |
9100 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
9101 | if (ascii_compatible && (to - from) == (pend - p)) | |
9102 | return Qnil; | |
9103 | } | |
f2558efd | 9104 | |
8f924df7 KH |
9105 | if (NILP (count)) |
9106 | n = 1; | |
9107 | else | |
b73bfc1c | 9108 | { |
8f924df7 KH |
9109 | CHECK_NATNUM (count); |
9110 | n = XINT (count); | |
b73bfc1c KH |
9111 | } |
9112 | ||
8f924df7 | 9113 | positions = Qnil; |
3633e3aa | 9114 | charset_map_loaded = 0; |
8f924df7 | 9115 | while (1) |
d46c5b12 | 9116 | { |
8f924df7 | 9117 | int c; |
ec6d2bb8 | 9118 | |
8f924df7 KH |
9119 | if (ascii_compatible) |
9120 | while (p < stop && ASCII_BYTE_P (*p)) | |
9121 | p++, from++; | |
9122 | if (p >= stop) | |
0e79d667 | 9123 | { |
8f924df7 KH |
9124 | if (p >= pend) |
9125 | break; | |
9126 | stop = pend; | |
9127 | p = GAP_END_ADDR; | |
0e79d667 | 9128 | } |
ec6d2bb8 | 9129 | |
8f924df7 KH |
9130 | c = STRING_CHAR_ADVANCE (p); |
9131 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
9132 | && ! char_charset (translate_char (translation_table, c), |
9133 | charset_list, NULL)) | |
ec6d2bb8 | 9134 | { |
8f924df7 KH |
9135 | positions = Fcons (make_number (from), positions); |
9136 | n--; | |
9137 | if (n == 0) | |
9138 | break; | |
ec6d2bb8 KH |
9139 | } |
9140 | ||
8f924df7 | 9141 | from++; |
3633e3aa KH |
9142 | if (charset_map_loaded && NILP (string)) |
9143 | { | |
9144 | p = CHAR_POS_ADDR (from); | |
9145 | pend = CHAR_POS_ADDR (to); | |
9146 | if (from < GPT && to >= GPT) | |
9147 | stop = GPT_ADDR; | |
9148 | else | |
9149 | stop = pend; | |
9150 | charset_map_loaded = 0; | |
9151 | } | |
8f924df7 | 9152 | } |
d46c5b12 | 9153 | |
8f924df7 KH |
9154 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
9155 | } | |
d46c5b12 | 9156 | |
d46c5b12 | 9157 | |
df7492f9 KH |
9158 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
9159 | Scheck_coding_systems_region, 3, 3, 0, | |
9160 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 9161 | |
df7492f9 KH |
9162 | START and END are buffer positions specifying the region. |
9163 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 9164 | |
df7492f9 | 9165 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 9166 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
9167 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
9168 | characters are found. | |
93dec019 | 9169 | |
df7492f9 KH |
9170 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
9171 | value is nil. | |
93dec019 | 9172 | |
df7492f9 KH |
9173 | START may be a string. In that case, check if the string is |
9174 | encodable, and the value contains indices to the string instead of | |
5704f39a KH |
9175 | buffer positions. END is ignored. |
9176 | ||
4c1958f4 | 9177 | If the current buffer (or START if it is a string) is unibyte, the value |
5704f39a | 9178 | is nil. */) |
5842a27b | 9179 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system_list) |
05e6f5dc | 9180 | { |
df7492f9 | 9181 | Lisp_Object list; |
d311d28c PE |
9182 | ptrdiff_t start_byte, end_byte; |
9183 | ptrdiff_t pos; | |
7c78e542 | 9184 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 9185 | int c; |
7d64c6ad | 9186 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 9187 | |
05e6f5dc KH |
9188 | if (STRINGP (start)) |
9189 | { | |
df7492f9 | 9190 | if (!STRING_MULTIBYTE (start) |
4c1958f4 | 9191 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
9192 | return Qnil; |
9193 | start_byte = 0; | |
8f924df7 | 9194 | end_byte = SBYTES (start); |
df7492f9 | 9195 | pos = 0; |
d46c5b12 | 9196 | } |
05e6f5dc | 9197 | else |
b73bfc1c | 9198 | { |
b7826503 PJ |
9199 | CHECK_NUMBER_COERCE_MARKER (start); |
9200 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
9201 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
9202 | args_out_of_range (start, end); | |
4b4deea2 | 9203 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
9204 | return Qnil; |
9205 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
9206 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
9207 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
5704f39a | 9208 | return Qnil; |
df7492f9 | 9209 | |
e1c23804 | 9210 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 9211 | { |
e1c23804 DL |
9212 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
9213 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 9214 | else |
e1c23804 | 9215 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 9216 | } |
e1c23804 | 9217 | pos = XINT (start); |
b73bfc1c | 9218 | } |
7553d0e1 | 9219 | |
df7492f9 KH |
9220 | list = Qnil; |
9221 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 9222 | { |
df7492f9 | 9223 | elt = XCAR (tail); |
7d64c6ad | 9224 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
9225 | ASET (attrs, coding_attr_trans_tbl, |
9226 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 9227 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
9228 | } |
9229 | ||
df7492f9 | 9230 | if (STRINGP (start)) |
8f924df7 | 9231 | p = pbeg = SDATA (start); |
72d1a715 | 9232 | else |
df7492f9 KH |
9233 | p = pbeg = BYTE_POS_ADDR (start_byte); |
9234 | pend = p + (end_byte - start_byte); | |
4ed46869 | 9235 | |
df7492f9 KH |
9236 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
9237 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 9238 | |
df7492f9 | 9239 | while (p < pend) |
d46c5b12 | 9240 | { |
df7492f9 KH |
9241 | if (ASCII_BYTE_P (*p)) |
9242 | p++; | |
e133c8fa | 9243 | else |
05e6f5dc | 9244 | { |
df7492f9 KH |
9245 | c = STRING_CHAR_ADVANCE (p); |
9246 | ||
9247 | charset_map_loaded = 0; | |
9248 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
9249 | { | |
9250 | elt = XCDR (XCAR (tail)); | |
9251 | if (! char_encodable_p (c, XCAR (elt))) | |
9252 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
9253 | } | |
9254 | if (charset_map_loaded) | |
9255 | { | |
d311d28c | 9256 | ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg; |
df7492f9 KH |
9257 | |
9258 | if (STRINGP (start)) | |
8f924df7 | 9259 | pbeg = SDATA (start); |
df7492f9 KH |
9260 | else |
9261 | pbeg = BYTE_POS_ADDR (start_byte); | |
9262 | p = pbeg + p_offset; | |
9263 | pend = pbeg + pend_offset; | |
9264 | } | |
05e6f5dc | 9265 | } |
df7492f9 | 9266 | pos++; |
d46c5b12 | 9267 | } |
4ed46869 | 9268 | |
df7492f9 KH |
9269 | tail = list; |
9270 | list = Qnil; | |
9271 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 9272 | { |
df7492f9 KH |
9273 | elt = XCAR (tail); |
9274 | if (CONSP (XCDR (XCDR (elt)))) | |
9275 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
9276 | list); | |
ec6d2bb8 | 9277 | } |
2b4f9037 | 9278 | |
df7492f9 | 9279 | return list; |
d46c5b12 KH |
9280 | } |
9281 | ||
3fd9494b | 9282 | |
74ab6df5 | 9283 | static Lisp_Object |
cf84bb53 JB |
9284 | code_convert_region (Lisp_Object start, Lisp_Object end, |
9285 | Lisp_Object coding_system, Lisp_Object dst_object, | |
f10fe38f | 9286 | bool encodep, bool norecord) |
4ed46869 | 9287 | { |
3a73fa5d | 9288 | struct coding_system coding; |
d311d28c | 9289 | ptrdiff_t from, from_byte, to, to_byte; |
df7492f9 | 9290 | Lisp_Object src_object; |
4ed46869 | 9291 | |
df7492f9 KH |
9292 | if (NILP (coding_system)) |
9293 | coding_system = Qno_conversion; | |
9294 | else | |
9295 | CHECK_CODING_SYSTEM (coding_system); | |
9296 | src_object = Fcurrent_buffer (); | |
9297 | if (NILP (dst_object)) | |
9298 | dst_object = src_object; | |
9299 | else if (! EQ (dst_object, Qt)) | |
9300 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 9301 | |
d46c5b12 KH |
9302 | validate_region (&start, &end); |
9303 | from = XFASTINT (start); | |
df7492f9 | 9304 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 9305 | to = XFASTINT (end); |
df7492f9 | 9306 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 9307 | |
df7492f9 KH |
9308 | setup_coding_system (coding_system, &coding); |
9309 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 9310 | |
df7492f9 KH |
9311 | if (encodep) |
9312 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
9313 | dst_object); | |
9314 | else | |
9315 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
9316 | dst_object); | |
9317 | if (! norecord) | |
9318 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 9319 | |
df7492f9 KH |
9320 | return (BUFFERP (dst_object) |
9321 | ? make_number (coding.produced_char) | |
9322 | : coding.dst_object); | |
4031e2bf | 9323 | } |
78108bcd | 9324 | |
4ed46869 | 9325 | |
4031e2bf | 9326 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 9327 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 9328 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
9329 | When called from a program, takes four arguments: |
9330 | START, END, CODING-SYSTEM, and DESTINATION. | |
9331 | START and END are buffer positions. | |
8844fa83 | 9332 | |
df7492f9 | 9333 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 9334 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
9335 | If buffer, the decoded text is inserted in that buffer after point (point |
9336 | does not move). | |
446dcd75 | 9337 | In those cases, the length of the decoded text is returned. |
319a3947 | 9338 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 9339 | |
48b0f3ae PJ |
9340 | This function sets `last-coding-system-used' to the precise coding system |
9341 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 9342 | not fully specified.) */) |
5842a27b | 9343 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
4031e2bf | 9344 | { |
df7492f9 | 9345 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 9346 | } |
8844fa83 | 9347 | |
3a73fa5d | 9348 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
9349 | 3, 4, "r\nzCoding system: ", |
9350 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
9351 | When called from a program, takes four arguments: |
9352 | START, END, CODING-SYSTEM and DESTINATION. | |
9353 | START and END are buffer positions. | |
d46c5b12 | 9354 | |
df7492f9 KH |
9355 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
9356 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
9357 | If buffer, the encoded text is inserted in that buffer after point (point |
9358 | does not move). | |
446dcd75 | 9359 | In those cases, the length of the encoded text is returned. |
319a3947 | 9360 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 9361 | |
48b0f3ae PJ |
9362 | This function sets `last-coding-system-used' to the precise coding system |
9363 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 9364 | not fully specified.) */) |
5842a27b | 9365 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
3a73fa5d | 9366 | { |
df7492f9 | 9367 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
9368 | } |
9369 | ||
9370 | Lisp_Object | |
6f704c76 | 9371 | code_convert_string (Lisp_Object string, Lisp_Object coding_system, |
f10fe38f PE |
9372 | Lisp_Object dst_object, bool encodep, bool nocopy, |
9373 | bool norecord) | |
b73bfc1c | 9374 | { |
4031e2bf | 9375 | struct coding_system coding; |
d311d28c | 9376 | ptrdiff_t chars, bytes; |
ec6d2bb8 | 9377 | |
b7826503 | 9378 | CHECK_STRING (string); |
d46c5b12 | 9379 | if (NILP (coding_system)) |
4956c225 | 9380 | { |
df7492f9 KH |
9381 | if (! norecord) |
9382 | Vlast_coding_system_used = Qno_conversion; | |
9383 | if (NILP (dst_object)) | |
9384 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 9385 | } |
b73bfc1c | 9386 | |
df7492f9 KH |
9387 | if (NILP (coding_system)) |
9388 | coding_system = Qno_conversion; | |
9389 | else | |
9390 | CHECK_CODING_SYSTEM (coding_system); | |
9391 | if (NILP (dst_object)) | |
9392 | dst_object = Qt; | |
9393 | else if (! EQ (dst_object, Qt)) | |
9394 | CHECK_BUFFER (dst_object); | |
73be902c | 9395 | |
df7492f9 | 9396 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 9397 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
9398 | chars = SCHARS (string); |
9399 | bytes = SBYTES (string); | |
df7492f9 KH |
9400 | if (encodep) |
9401 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9402 | else | |
9403 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
9404 | if (! norecord) | |
9405 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 9406 | |
df7492f9 KH |
9407 | return (BUFFERP (dst_object) |
9408 | ? make_number (coding.produced_char) | |
9409 | : coding.dst_object); | |
4ed46869 | 9410 | } |
73be902c | 9411 | |
b73bfc1c | 9412 | |
ecec61c1 | 9413 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 9414 | Do not set Vlast_coding_system_used. |
4ed46869 | 9415 | |
ec6d2bb8 KH |
9416 | This function is called only from macros DECODE_FILE and |
9417 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 9418 | |
ecec61c1 | 9419 | Lisp_Object |
cf84bb53 | 9420 | code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system, |
f10fe38f | 9421 | bool encodep) |
4ed46869 | 9422 | { |
0be8721c | 9423 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
9424 | } |
9425 | ||
4ed46869 | 9426 | |
a7ca3326 | 9427 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
df7492f9 KH |
9428 | 2, 4, 0, |
9429 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
9430 | ||
9431 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
9432 | if the decoding operation is trivial. | |
ecec61c1 | 9433 | |
d4a1d553 | 9434 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
9435 | inserted in that buffer after point (point does not move). In this |
9436 | case, the return value is the length of the decoded text. | |
ecec61c1 | 9437 | |
df7492f9 KH |
9438 | This function sets `last-coding-system-used' to the precise coding system |
9439 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 9440 | not fully specified.) */) |
5842a27b | 9441 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9442 | { |
df7492f9 KH |
9443 | return code_convert_string (string, coding_system, buffer, |
9444 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
9445 | } |
9446 | ||
df7492f9 KH |
9447 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
9448 | 2, 4, 0, | |
9449 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
9450 | ||
9451 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
9452 | itself if the encoding operation is trivial. | |
9453 | ||
d4a1d553 | 9454 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
9455 | inserted in that buffer after point (point does not move). In this |
9456 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
9457 | |
9458 | This function sets `last-coding-system-used' to the precise coding system | |
9459 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
9460 | not fully specified.) */) | |
5842a27b | 9461 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9462 | { |
df7492f9 | 9463 | return code_convert_string (string, coding_system, buffer, |
4550efdf | 9464 | 1, ! NILP (nocopy), 0); |
4ed46869 | 9465 | } |
df7492f9 | 9466 | |
3a73fa5d | 9467 | \f |
4ed46869 | 9468 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
9469 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
9470 | Return the corresponding character. */) | |
5842a27b | 9471 | (Lisp_Object code) |
4ed46869 | 9472 | { |
df7492f9 KH |
9473 | Lisp_Object spec, attrs, val; |
9474 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
5fdb398c PE |
9475 | EMACS_INT ch; |
9476 | int c; | |
4ed46869 | 9477 | |
df7492f9 | 9478 | CHECK_NATNUM (code); |
5fdb398c | 9479 | ch = XFASTINT (code); |
df7492f9 KH |
9480 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); |
9481 | attrs = AREF (spec, 0); | |
4ed46869 | 9482 | |
5fdb398c | 9483 | if (ASCII_BYTE_P (ch) |
df7492f9 KH |
9484 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
9485 | return code; | |
4ed46869 | 9486 | |
df7492f9 KH |
9487 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9488 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
9489 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
9490 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 9491 | |
5fdb398c PE |
9492 | if (ch <= 0x7F) |
9493 | { | |
9494 | c = ch; | |
9495 | charset = charset_roman; | |
9496 | } | |
9497 | else if (ch >= 0xA0 && ch < 0xDF) | |
55ab7be3 | 9498 | { |
5fdb398c | 9499 | c = ch - 0x80; |
df7492f9 | 9500 | charset = charset_kana; |
4ed46869 | 9501 | } |
55ab7be3 | 9502 | else |
4ed46869 | 9503 | { |
5fdb398c PE |
9504 | EMACS_INT c1 = ch >> 8; |
9505 | int c2 = ch & 0xFF; | |
df7492f9 | 9506 | |
2735d060 PE |
9507 | if (c1 < 0x81 || (c1 > 0x9F && c1 < 0xE0) || c1 > 0xEF |
9508 | || c2 < 0x40 || c2 == 0x7F || c2 > 0xFC) | |
c2982e87 | 9509 | error ("Invalid code: %"pI"d", ch); |
5fdb398c | 9510 | c = ch; |
df7492f9 KH |
9511 | SJIS_TO_JIS (c); |
9512 | charset = charset_kanji; | |
4ed46869 | 9513 | } |
df7492f9 KH |
9514 | c = DECODE_CHAR (charset, c); |
9515 | if (c < 0) | |
c2982e87 | 9516 | error ("Invalid code: %"pI"d", ch); |
df7492f9 | 9517 | return make_number (c); |
93dec019 | 9518 | } |
4ed46869 | 9519 | |
48b0f3ae | 9520 | |
4ed46869 | 9521 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 9522 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae | 9523 | Return the corresponding code in SJIS. */) |
5842a27b | 9524 | (Lisp_Object ch) |
4ed46869 | 9525 | { |
df7492f9 KH |
9526 | Lisp_Object spec, attrs, charset_list; |
9527 | int c; | |
9528 | struct charset *charset; | |
9529 | unsigned code; | |
48b0f3ae | 9530 | |
df7492f9 KH |
9531 | CHECK_CHARACTER (ch); |
9532 | c = XFASTINT (ch); | |
9533 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9534 | attrs = AREF (spec, 0); | |
9535 | ||
9536 | if (ASCII_CHAR_P (c) | |
9537 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9538 | return ch; | |
9539 | ||
9540 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9541 | charset = char_charset (c, charset_list, &code); | |
9542 | if (code == CHARSET_INVALID_CODE (charset)) | |
e6c3da20 | 9543 | error ("Can't encode by shift_jis encoding: %c", c); |
df7492f9 KH |
9544 | JIS_TO_SJIS (code); |
9545 | ||
9546 | return make_number (code); | |
4ed46869 KH |
9547 | } |
9548 | ||
9549 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
9550 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
9551 | Return the corresponding character. */) | |
5842a27b | 9552 | (Lisp_Object code) |
d46c5b12 | 9553 | { |
df7492f9 KH |
9554 | Lisp_Object spec, attrs, val; |
9555 | struct charset *charset_roman, *charset_big5, *charset; | |
5fdb398c | 9556 | EMACS_INT ch; |
df7492f9 | 9557 | int c; |
6289dd10 | 9558 | |
df7492f9 | 9559 | CHECK_NATNUM (code); |
5fdb398c | 9560 | ch = XFASTINT (code); |
df7492f9 KH |
9561 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); |
9562 | attrs = AREF (spec, 0); | |
4ed46869 | 9563 | |
5fdb398c | 9564 | if (ASCII_BYTE_P (ch) |
df7492f9 KH |
9565 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
9566 | return code; | |
6289dd10 | 9567 | |
df7492f9 KH |
9568 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9569 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
9570 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 9571 | |
5fdb398c PE |
9572 | if (ch <= 0x7F) |
9573 | { | |
9574 | c = ch; | |
9575 | charset = charset_roman; | |
9576 | } | |
c28a9453 KH |
9577 | else |
9578 | { | |
5fdb398c PE |
9579 | EMACS_INT b1 = ch >> 8; |
9580 | int b2 = ch & 0x7F; | |
df7492f9 KH |
9581 | if (b1 < 0xA1 || b1 > 0xFE |
9582 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
c2982e87 | 9583 | error ("Invalid code: %"pI"d", ch); |
5fdb398c | 9584 | c = ch; |
df7492f9 | 9585 | charset = charset_big5; |
c28a9453 | 9586 | } |
5fdb398c | 9587 | c = DECODE_CHAR (charset, c); |
df7492f9 | 9588 | if (c < 0) |
c2982e87 | 9589 | error ("Invalid code: %"pI"d", ch); |
df7492f9 | 9590 | return make_number (c); |
d46c5b12 | 9591 | } |
6289dd10 | 9592 | |
4ed46869 | 9593 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 9594 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae | 9595 | Return the corresponding character code in Big5. */) |
5842a27b | 9596 | (Lisp_Object ch) |
4ed46869 | 9597 | { |
df7492f9 KH |
9598 | Lisp_Object spec, attrs, charset_list; |
9599 | struct charset *charset; | |
9600 | int c; | |
9601 | unsigned code; | |
9602 | ||
9603 | CHECK_CHARACTER (ch); | |
9604 | c = XFASTINT (ch); | |
9605 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9606 | attrs = AREF (spec, 0); | |
9607 | if (ASCII_CHAR_P (c) | |
9608 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9609 | return ch; | |
9610 | ||
9611 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9612 | charset = char_charset (c, charset_list, &code); | |
9613 | if (code == CHARSET_INVALID_CODE (charset)) | |
e6c3da20 | 9614 | error ("Can't encode by Big5 encoding: %c", c); |
df7492f9 KH |
9615 | |
9616 | return make_number (code); | |
4ed46869 | 9617 | } |
48b0f3ae | 9618 | |
3a73fa5d | 9619 | \f |
002fdb44 | 9620 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 9621 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9622 | doc: /* Internal use only. */) |
5842a27b | 9623 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9624 | { |
b18fad6d KH |
9625 | struct terminal *term = get_terminal (terminal, 1); |
9626 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term); | |
b7826503 | 9627 | CHECK_SYMBOL (coding_system); |
b8299c66 | 9628 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 9629 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 9630 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
ad1746f5 | 9631 | /* Character composition should be disabled. */ |
c73bd236 | 9632 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
9633 | terminal_coding->src_multibyte = 1; |
9634 | terminal_coding->dst_multibyte = 0; | |
3f22b86f PE |
9635 | tset_charset_list |
9636 | (term, (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK | |
9637 | ? coding_charset_list (terminal_coding) | |
9638 | : Fcons (make_number (charset_ascii), Qnil))); | |
4ed46869 KH |
9639 | return Qnil; |
9640 | } | |
9641 | ||
c4825358 KH |
9642 | DEFUN ("set-safe-terminal-coding-system-internal", |
9643 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 9644 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 9645 | doc: /* Internal use only. */) |
5842a27b | 9646 | (Lisp_Object coding_system) |
d46c5b12 | 9647 | { |
b7826503 | 9648 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
9649 | setup_coding_system (Fcheck_coding_system (coding_system), |
9650 | &safe_terminal_coding); | |
ad1746f5 | 9651 | /* Character composition should be disabled. */ |
df7492f9 | 9652 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b73bfc1c KH |
9653 | safe_terminal_coding.src_multibyte = 1; |
9654 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
9655 | return Qnil; |
9656 | } | |
4ed46869 | 9657 | |
002fdb44 | 9658 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 9659 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff | 9660 | doc: /* Return coding system specified for terminal output on the given terminal. |
708e05dc | 9661 | TERMINAL may be a terminal object, a frame, or nil for the selected |
6ed8eeff | 9662 | frame's terminal device. */) |
5842a27b | 9663 | (Lisp_Object terminal) |
4ed46869 | 9664 | { |
985773c9 MB |
9665 | struct coding_system *terminal_coding |
9666 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
9667 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 9668 | |
6d5eb5b0 | 9669 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 9670 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
9671 | } |
9672 | ||
002fdb44 | 9673 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 9674 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9675 | doc: /* Internal use only. */) |
5842a27b | 9676 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9677 | { |
6ed8eeff | 9678 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 9679 | CHECK_SYMBOL (coding_system); |
624bda09 KH |
9680 | if (NILP (coding_system)) |
9681 | coding_system = Qno_conversion; | |
9682 | else | |
9683 | Fcheck_coding_system (coding_system); | |
9684 | setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t)); | |
ad1746f5 | 9685 | /* Character composition should be disabled. */ |
c73bd236 MB |
9686 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
9687 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
9688 | return Qnil; |
9689 | } | |
9690 | ||
9691 | DEFUN ("keyboard-coding-system", | |
985773c9 | 9692 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 9693 | doc: /* Return coding system specified for decoding keyboard input. */) |
5842a27b | 9694 | (Lisp_Object terminal) |
4ed46869 | 9695 | { |
985773c9 MB |
9696 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
9697 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
9698 | } |
9699 | ||
4ed46869 | 9700 | \f |
a7ca3326 | 9701 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
a5d301df | 9702 | Sfind_operation_coding_system, 1, MANY, 0, |
48b0f3ae PJ |
9703 | doc: /* Choose a coding system for an operation based on the target name. |
9704 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
9705 | DECODING-SYSTEM is the coding system to use for decoding | |
9706 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
9707 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 9708 | |
48b0f3ae PJ |
9709 | The first argument OPERATION specifies an I/O primitive: |
9710 | For file I/O, `insert-file-contents' or `write-region'. | |
9711 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
9712 | For network I/O, `open-network-stream'. | |
05e6f5dc | 9713 | |
48b0f3ae PJ |
9714 | The remaining arguments should be the same arguments that were passed |
9715 | to the primitive. Depending on which primitive, one of those arguments | |
9716 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
9717 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 9718 | |
48b0f3ae | 9719 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 9720 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 9721 | For process I/O, TARGET is a process name. |
d4a1d553 | 9722 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 9723 | |
d4a1d553 | 9724 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
9725 | `file-coding-system-alist', `process-coding-system-alist', |
9726 | or `network-coding-system-alist' depending on OPERATION. | |
9727 | They may specify a coding system, a cons of coding systems, | |
9728 | or a function symbol to call. | |
9729 | In the last case, we call the function with one argument, | |
9730 | which is a list of all the arguments given to this function. | |
1011c487 MB |
9731 | If the function can't decide a coding system, it can return |
9732 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 9733 | |
b883cdb2 MB |
9734 | If OPERATION is `insert-file-contents', the argument corresponding to |
9735 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
9736 | file name to look up, and BUFFER is a buffer that contains the file's | |
9737 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
9738 | function to call for FILENAME, that function should examine the | |
9739 | contents of BUFFER instead of reading the file. | |
9740 | ||
d918f936 | 9741 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
f66c7cf8 | 9742 | (ptrdiff_t nargs, Lisp_Object *args) |
6b89e3aa | 9743 | { |
4ed46869 KH |
9744 | Lisp_Object operation, target_idx, target, val; |
9745 | register Lisp_Object chain; | |
177c0ea7 | 9746 | |
4ed46869 KH |
9747 | if (nargs < 2) |
9748 | error ("Too few arguments"); | |
9749 | operation = args[0]; | |
9750 | if (!SYMBOLP (operation) | |
d311d28c | 9751 | || (target_idx = Fget (operation, Qtarget_idx), !NATNUMP (target_idx))) |
3ed051d4 | 9752 | error ("Invalid first argument"); |
7b09a37a | 9753 | if (nargs <= 1 + XFASTINT (target_idx)) |
94dcfacf | 9754 | error ("Too few arguments for operation `%s'", |
8f924df7 | 9755 | SDATA (SYMBOL_NAME (operation))); |
c5101a77 | 9756 | target = args[XFASTINT (target_idx) + 1]; |
4ed46869 | 9757 | if (!(STRINGP (target) |
091a0ff0 KH |
9758 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
9759 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 9760 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
94dcfacf EZ |
9761 | error ("Invalid argument %"pI"d of operation `%s'", |
9762 | XFASTINT (target_idx) + 1, SDATA (SYMBOL_NAME (operation))); | |
091a0ff0 KH |
9763 | if (CONSP (target)) |
9764 | target = XCAR (target); | |
4ed46869 | 9765 | |
2e34157c RS |
9766 | chain = ((EQ (operation, Qinsert_file_contents) |
9767 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9768 | ? Vfile_coding_system_alist |
2e34157c | 9769 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9770 | ? Vnetwork_coding_system_alist |
9771 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9772 | if (NILP (chain)) |
9773 | return Qnil; | |
9774 | ||
03699b14 | 9775 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9776 | { |
f44d27ce | 9777 | Lisp_Object elt; |
6b89e3aa | 9778 | |
df7492f9 | 9779 | elt = XCAR (chain); |
4ed46869 KH |
9780 | if (CONSP (elt) |
9781 | && ((STRINGP (target) | |
03699b14 KR |
9782 | && STRINGP (XCAR (elt)) |
9783 | && fast_string_match (XCAR (elt), target) >= 0) | |
9784 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9785 | { |
03699b14 | 9786 | val = XCDR (elt); |
b19fd4c5 KH |
9787 | /* Here, if VAL is both a valid coding system and a valid |
9788 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9789 | if (CONSP (val)) |
9790 | return val; | |
9791 | if (! SYMBOLP (val)) | |
9792 | return Qnil; | |
9793 | if (! NILP (Fcoding_system_p (val))) | |
9794 | return Fcons (val, val); | |
b19fd4c5 | 9795 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9796 | { |
e2b97060 MB |
9797 | /* We use call1 rather than safe_call1 |
9798 | so as to get bug reports about functions called here | |
9799 | which don't handle the current interface. */ | |
9800 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9801 | if (CONSP (val)) |
9802 | return val; | |
9803 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9804 | return Fcons (val, val); | |
6b89e3aa | 9805 | } |
02ba4723 | 9806 | return Qnil; |
6b89e3aa KH |
9807 | } |
9808 | } | |
4ed46869 | 9809 | return Qnil; |
6b89e3aa KH |
9810 | } |
9811 | ||
df7492f9 | 9812 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9813 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9814 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9815 | If multiple coding systems belong to the same category, |
a3181084 DL |
9816 | all but the first one are ignored. |
9817 | ||
d4a1d553 | 9818 | usage: (set-coding-system-priority &rest coding-systems) */) |
f66c7cf8 | 9819 | (ptrdiff_t nargs, Lisp_Object *args) |
df7492f9 | 9820 | { |
f66c7cf8 | 9821 | ptrdiff_t i, j; |
f10fe38f | 9822 | bool changed[coding_category_max]; |
df7492f9 KH |
9823 | enum coding_category priorities[coding_category_max]; |
9824 | ||
72af86bd | 9825 | memset (changed, 0, sizeof changed); |
6b89e3aa | 9826 | |
df7492f9 | 9827 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9828 | { |
df7492f9 KH |
9829 | enum coding_category category; |
9830 | Lisp_Object spec, attrs; | |
6b89e3aa | 9831 | |
df7492f9 KH |
9832 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9833 | attrs = AREF (spec, 0); | |
9834 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9835 | if (changed[category]) | |
9836 | /* Ignore this coding system because a coding system of the | |
9837 | same category already had a higher priority. */ | |
9838 | continue; | |
9839 | changed[category] = 1; | |
9840 | priorities[j++] = category; | |
9841 | if (coding_categories[category].id >= 0 | |
9842 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9843 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9844 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9845 | } |
6b89e3aa | 9846 | |
df7492f9 KH |
9847 | /* Now we have decided top J priorities. Reflect the order of the |
9848 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9849 | |
df7492f9 | 9850 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9851 | { |
df7492f9 KH |
9852 | while (j < coding_category_max |
9853 | && changed[coding_priorities[j]]) | |
9854 | j++; | |
9855 | if (j == coding_category_max) | |
1088b922 | 9856 | emacs_abort (); |
df7492f9 KH |
9857 | priorities[i] = coding_priorities[j]; |
9858 | } | |
6b89e3aa | 9859 | |
72af86bd | 9860 | memcpy (coding_priorities, priorities, sizeof priorities); |
177c0ea7 | 9861 | |
ff563fce KH |
9862 | /* Update `coding-category-list'. */ |
9863 | Vcoding_category_list = Qnil; | |
c5101a77 | 9864 | for (i = coding_category_max; i-- > 0; ) |
ff563fce KH |
9865 | Vcoding_category_list |
9866 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9867 | Vcoding_category_list); | |
6b89e3aa | 9868 | |
df7492f9 | 9869 | return Qnil; |
6b89e3aa KH |
9870 | } |
9871 | ||
df7492f9 KH |
9872 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9873 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 | 9874 | doc: /* Return a list of coding systems ordered by their priorities. |
b811c52b KH |
9875 | The list contains a subset of coding systems; i.e. coding systems |
9876 | assigned to each coding category (see `coding-category-list'). | |
9877 | ||
da7db224 | 9878 | HIGHESTP non-nil means just return the highest priority one. */) |
5842a27b | 9879 | (Lisp_Object highestp) |
d46c5b12 KH |
9880 | { |
9881 | int i; | |
df7492f9 | 9882 | Lisp_Object val; |
6b89e3aa | 9883 | |
df7492f9 | 9884 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9885 | { |
df7492f9 KH |
9886 | enum coding_category category = coding_priorities[i]; |
9887 | int id = coding_categories[category].id; | |
9888 | Lisp_Object attrs; | |
068a9dbd | 9889 | |
df7492f9 KH |
9890 | if (id < 0) |
9891 | continue; | |
9892 | attrs = CODING_ID_ATTRS (id); | |
9893 | if (! NILP (highestp)) | |
9894 | return CODING_ATTR_BASE_NAME (attrs); | |
9895 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9896 | } | |
9897 | return Fnreverse (val); | |
9898 | } | |
068a9dbd | 9899 | |
91433552 | 9900 | static const char *const suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9901 | |
9902 | static Lisp_Object | |
971de7fb | 9903 | make_subsidiaries (Lisp_Object base) |
068a9dbd | 9904 | { |
df7492f9 | 9905 | Lisp_Object subsidiaries; |
1bfdaf10 | 9906 | ptrdiff_t base_name_len = SBYTES (SYMBOL_NAME (base)); |
38182d90 | 9907 | char *buf = alloca (base_name_len + 6); |
df7492f9 | 9908 | int i; |
068a9dbd | 9909 | |
72af86bd | 9910 | memcpy (buf, SDATA (SYMBOL_NAME (base)), base_name_len); |
25721f5b | 9911 | subsidiaries = make_uninit_vector (3); |
df7492f9 | 9912 | for (i = 0; i < 3; i++) |
068a9dbd | 9913 | { |
1bfdaf10 | 9914 | strcpy (buf + base_name_len, suffixes[i]); |
df7492f9 | 9915 | ASET (subsidiaries, i, intern (buf)); |
068a9dbd | 9916 | } |
df7492f9 | 9917 | return subsidiaries; |
068a9dbd KH |
9918 | } |
9919 | ||
9920 | ||
df7492f9 KH |
9921 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9922 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9923 | doc: /* For internal use only. |
9924 | usage: (define-coding-system-internal ...) */) | |
f66c7cf8 | 9925 | (ptrdiff_t nargs, Lisp_Object *args) |
068a9dbd | 9926 | { |
df7492f9 KH |
9927 | Lisp_Object name; |
9928 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9929 | Lisp_Object attrs; /* Vector of attributes. */ | |
9930 | Lisp_Object eol_type; | |
9931 | Lisp_Object aliases; | |
9932 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9933 | enum coding_category category; | |
9934 | Lisp_Object tail, val; | |
9935 | int max_charset_id = 0; | |
9936 | int i; | |
068a9dbd | 9937 | |
df7492f9 KH |
9938 | if (nargs < coding_arg_max) |
9939 | goto short_args; | |
068a9dbd | 9940 | |
df7492f9 | 9941 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9942 | |
df7492f9 KH |
9943 | name = args[coding_arg_name]; |
9944 | CHECK_SYMBOL (name); | |
4939150c | 9945 | ASET (attrs, coding_attr_base_name, name); |
068a9dbd | 9946 | |
df7492f9 KH |
9947 | val = args[coding_arg_mnemonic]; |
9948 | if (! STRINGP (val)) | |
9949 | CHECK_CHARACTER (val); | |
4939150c | 9950 | ASET (attrs, coding_attr_mnemonic, val); |
068a9dbd | 9951 | |
df7492f9 KH |
9952 | coding_type = args[coding_arg_coding_type]; |
9953 | CHECK_SYMBOL (coding_type); | |
4939150c | 9954 | ASET (attrs, coding_attr_type, coding_type); |
068a9dbd | 9955 | |
df7492f9 KH |
9956 | charset_list = args[coding_arg_charset_list]; |
9957 | if (SYMBOLP (charset_list)) | |
9958 | { | |
9959 | if (EQ (charset_list, Qiso_2022)) | |
9960 | { | |
9961 | if (! EQ (coding_type, Qiso_2022)) | |
9962 | error ("Invalid charset-list"); | |
9963 | charset_list = Viso_2022_charset_list; | |
9964 | } | |
9965 | else if (EQ (charset_list, Qemacs_mule)) | |
9966 | { | |
9967 | if (! EQ (coding_type, Qemacs_mule)) | |
9968 | error ("Invalid charset-list"); | |
9969 | charset_list = Vemacs_mule_charset_list; | |
9970 | } | |
9971 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
d311d28c PE |
9972 | { |
9973 | if (! RANGED_INTEGERP (0, XCAR (tail), INT_MAX - 1)) | |
9974 | error ("Invalid charset-list"); | |
9975 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9976 | max_charset_id = XFASTINT (XCAR (tail)); | |
9977 | } | |
df7492f9 | 9978 | } |
068a9dbd KH |
9979 | else |
9980 | { | |
df7492f9 | 9981 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9982 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9983 | { |
df7492f9 KH |
9984 | struct charset *charset; |
9985 | ||
985773c9 | 9986 | val = XCAR (tail); |
df7492f9 KH |
9987 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9988 | if (EQ (coding_type, Qiso_2022) | |
9989 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9990 | : EQ (coding_type, Qemacs_mule) | |
9991 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9992 | : 0) | |
9993 | error ("Can't handle charset `%s'", | |
8f924df7 | 9994 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9995 | |
8f924df7 | 9996 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9997 | if (max_charset_id < charset->id) |
9998 | max_charset_id = charset->id; | |
068a9dbd KH |
9999 | } |
10000 | } | |
4939150c | 10001 | ASET (attrs, coding_attr_charset_list, charset_list); |
068a9dbd | 10002 | |
1b3b981b AS |
10003 | safe_charsets = make_uninit_string (max_charset_id + 1); |
10004 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 | 10005 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8f924df7 | 10006 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
4939150c | 10007 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); |
068a9dbd | 10008 | |
4939150c | 10009 | ASET (attrs, coding_attr_ascii_compat, args[coding_arg_ascii_compatible_p]); |
3a73fa5d | 10010 | |
df7492f9 | 10011 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 10012 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 10013 | CHECK_SYMBOL (val); |
4939150c | 10014 | ASET (attrs, coding_attr_decode_tbl, val); |
3a73fa5d | 10015 | |
df7492f9 | 10016 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 10017 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 10018 | CHECK_SYMBOL (val); |
4939150c | 10019 | ASET (attrs, coding_attr_encode_tbl, val); |
d46c5b12 | 10020 | |
df7492f9 KH |
10021 | val = args[coding_arg_post_read_conversion]; |
10022 | CHECK_SYMBOL (val); | |
4939150c | 10023 | ASET (attrs, coding_attr_post_read, val); |
d46c5b12 | 10024 | |
df7492f9 KH |
10025 | val = args[coding_arg_pre_write_conversion]; |
10026 | CHECK_SYMBOL (val); | |
4939150c | 10027 | ASET (attrs, coding_attr_pre_write, val); |
3a73fa5d | 10028 | |
df7492f9 KH |
10029 | val = args[coding_arg_default_char]; |
10030 | if (NILP (val)) | |
4939150c | 10031 | ASET (attrs, coding_attr_default_char, make_number (' ')); |
df7492f9 KH |
10032 | else |
10033 | { | |
8f924df7 | 10034 | CHECK_CHARACTER (val); |
4939150c | 10035 | ASET (attrs, coding_attr_default_char, val); |
df7492f9 | 10036 | } |
4031e2bf | 10037 | |
8f924df7 | 10038 | val = args[coding_arg_for_unibyte]; |
4939150c | 10039 | ASET (attrs, coding_attr_for_unibyte, NILP (val) ? Qnil : Qt); |
3a73fa5d | 10040 | |
df7492f9 KH |
10041 | val = args[coding_arg_plist]; |
10042 | CHECK_LIST (val); | |
4939150c | 10043 | ASET (attrs, coding_attr_plist, val); |
3a73fa5d | 10044 | |
df7492f9 KH |
10045 | if (EQ (coding_type, Qcharset)) |
10046 | { | |
c7c66a95 KH |
10047 | /* Generate a lisp vector of 256 elements. Each element is nil, |
10048 | integer, or a list of charset IDs. | |
3a73fa5d | 10049 | |
c7c66a95 KH |
10050 | If Nth element is nil, the byte code N is invalid in this |
10051 | coding system. | |
4ed46869 | 10052 | |
c7c66a95 KH |
10053 | If Nth element is a number NUM, N is the first byte of a |
10054 | charset whose ID is NUM. | |
4ed46869 | 10055 | |
c7c66a95 KH |
10056 | If Nth element is a list of charset IDs, N is the first byte |
10057 | of one of them. The list is sorted by dimensions of the | |
ad1746f5 | 10058 | charsets. A charset of smaller dimension comes first. */ |
df7492f9 | 10059 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 10060 | |
5c99c2e6 | 10061 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 10062 | { |
c7c66a95 KH |
10063 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
10064 | int dim = CHARSET_DIMENSION (charset); | |
10065 | int idx = (dim - 1) * 4; | |
4ed46869 | 10066 | |
5c99c2e6 | 10067 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 10068 | ASET (attrs, coding_attr_ascii_compat, Qt); |
4031e2bf | 10069 | |
15d143f7 KH |
10070 | for (i = charset->code_space[idx]; |
10071 | i <= charset->code_space[idx + 1]; i++) | |
10072 | { | |
c7c66a95 KH |
10073 | Lisp_Object tmp, tmp2; |
10074 | int dim2; | |
ec6d2bb8 | 10075 | |
c7c66a95 KH |
10076 | tmp = AREF (val, i); |
10077 | if (NILP (tmp)) | |
10078 | tmp = XCAR (tail); | |
10079 | else if (NUMBERP (tmp)) | |
10080 | { | |
10081 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
10082 | if (dim < dim2) | |
c7c66a95 | 10083 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
10084 | else |
10085 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 10086 | } |
15d143f7 | 10087 | else |
c7c66a95 KH |
10088 | { |
10089 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
10090 | { | |
10091 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
10092 | if (dim < dim2) | |
10093 | break; | |
10094 | } | |
10095 | if (NILP (tmp2)) | |
10096 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
10097 | else | |
10098 | { | |
10099 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
10100 | XSETCAR (tmp2, XCAR (tail)); | |
10101 | } | |
10102 | } | |
10103 | ASET (val, i, tmp); | |
15d143f7 | 10104 | } |
df7492f9 KH |
10105 | } |
10106 | ASET (attrs, coding_attr_charset_valids, val); | |
10107 | category = coding_category_charset; | |
10108 | } | |
10109 | else if (EQ (coding_type, Qccl)) | |
10110 | { | |
10111 | Lisp_Object valids; | |
ecec61c1 | 10112 | |
df7492f9 KH |
10113 | if (nargs < coding_arg_ccl_max) |
10114 | goto short_args; | |
ecec61c1 | 10115 | |
df7492f9 KH |
10116 | val = args[coding_arg_ccl_decoder]; |
10117 | CHECK_CCL_PROGRAM (val); | |
10118 | if (VECTORP (val)) | |
10119 | val = Fcopy_sequence (val); | |
10120 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 10121 | |
df7492f9 KH |
10122 | val = args[coding_arg_ccl_encoder]; |
10123 | CHECK_CCL_PROGRAM (val); | |
10124 | if (VECTORP (val)) | |
10125 | val = Fcopy_sequence (val); | |
10126 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 10127 | |
df7492f9 KH |
10128 | val = args[coding_arg_ccl_valids]; |
10129 | valids = Fmake_string (make_number (256), make_number (0)); | |
7d7bbefd | 10130 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 10131 | { |
8dcbea82 | 10132 | int from, to; |
ecec61c1 | 10133 | |
34348bd4 | 10134 | val = XCAR (tail); |
df7492f9 | 10135 | if (INTEGERP (val)) |
8dcbea82 | 10136 | { |
d311d28c | 10137 | if (! (0 <= XINT (val) && XINT (val) <= 255)) |
8dcbea82 | 10138 | args_out_of_range_3 (val, make_number (0), make_number (255)); |
d311d28c | 10139 | from = to = XINT (val); |
8dcbea82 | 10140 | } |
df7492f9 KH |
10141 | else |
10142 | { | |
df7492f9 | 10143 | CHECK_CONS (val); |
8f924df7 | 10144 | CHECK_NATNUM_CAR (val); |
d311d28c PE |
10145 | CHECK_NUMBER_CDR (val); |
10146 | if (XINT (XCAR (val)) > 255) | |
8dcbea82 KH |
10147 | args_out_of_range_3 (XCAR (val), |
10148 | make_number (0), make_number (255)); | |
d311d28c PE |
10149 | from = XINT (XCAR (val)); |
10150 | if (! (from <= XINT (XCDR (val)) && XINT (XCDR (val)) <= 255)) | |
8dcbea82 KH |
10151 | args_out_of_range_3 (XCDR (val), |
10152 | XCAR (val), make_number (255)); | |
d311d28c | 10153 | to = XINT (XCDR (val)); |
df7492f9 | 10154 | } |
8dcbea82 | 10155 | for (i = from; i <= to; i++) |
8f924df7 | 10156 | SSET (valids, i, 1); |
df7492f9 KH |
10157 | } |
10158 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 10159 | |
df7492f9 | 10160 | category = coding_category_ccl; |
55ab7be3 | 10161 | } |
df7492f9 | 10162 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 10163 | { |
df7492f9 | 10164 | Lisp_Object bom, endian; |
4ed46869 | 10165 | |
4939150c | 10166 | ASET (attrs, coding_attr_ascii_compat, Qnil); |
4ed46869 | 10167 | |
df7492f9 KH |
10168 | if (nargs < coding_arg_utf16_max) |
10169 | goto short_args; | |
4ed46869 | 10170 | |
df7492f9 KH |
10171 | bom = args[coding_arg_utf16_bom]; |
10172 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
10173 | { | |
10174 | CHECK_CONS (bom); | |
8f924df7 KH |
10175 | val = XCAR (bom); |
10176 | CHECK_CODING_SYSTEM (val); | |
10177 | val = XCDR (bom); | |
10178 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 10179 | } |
a470d443 | 10180 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
10181 | |
10182 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
10183 | CHECK_SYMBOL (endian); |
10184 | if (NILP (endian)) | |
10185 | endian = Qbig; | |
10186 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 10187 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
10188 | ASET (attrs, coding_attr_utf_16_endian, endian); |
10189 | ||
10190 | category = (CONSP (bom) | |
10191 | ? coding_category_utf_16_auto | |
10192 | : NILP (bom) | |
b49a1807 | 10193 | ? (EQ (endian, Qbig) |
df7492f9 KH |
10194 | ? coding_category_utf_16_be_nosig |
10195 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 10196 | : (EQ (endian, Qbig) |
df7492f9 KH |
10197 | ? coding_category_utf_16_be |
10198 | : coding_category_utf_16_le)); | |
10199 | } | |
10200 | else if (EQ (coding_type, Qiso_2022)) | |
10201 | { | |
10202 | Lisp_Object initial, reg_usage, request, flags; | |
1397dc18 | 10203 | |
df7492f9 KH |
10204 | if (nargs < coding_arg_iso2022_max) |
10205 | goto short_args; | |
10206 | ||
10207 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
10208 | CHECK_VECTOR (initial); | |
10209 | for (i = 0; i < 4; i++) | |
10210 | { | |
9a9d91d9 | 10211 | val = AREF (initial, i); |
df7492f9 KH |
10212 | if (! NILP (val)) |
10213 | { | |
584948ac KH |
10214 | struct charset *charset; |
10215 | ||
10216 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
10217 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
10218 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
4939150c | 10219 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
10220 | } |
10221 | else | |
10222 | ASET (initial, i, make_number (-1)); | |
10223 | } | |
10224 | ||
10225 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
10226 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
10227 | CHECK_NUMBER_CAR (reg_usage); |
10228 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
10229 | |
10230 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
7d7bbefd | 10231 | for (tail = request; CONSP (tail); tail = XCDR (tail)) |
1397dc18 | 10232 | { |
df7492f9 | 10233 | int id; |
2735d060 | 10234 | Lisp_Object tmp1; |
df7492f9 | 10235 | |
34348bd4 | 10236 | val = XCAR (tail); |
df7492f9 | 10237 | CHECK_CONS (val); |
2735d060 PE |
10238 | tmp1 = XCAR (val); |
10239 | CHECK_CHARSET_GET_ID (tmp1, id); | |
8f924df7 | 10240 | CHECK_NATNUM_CDR (val); |
df7492f9 | 10241 | if (XINT (XCDR (val)) >= 4) |
c2982e87 | 10242 | error ("Invalid graphic register number: %"pI"d", XINT (XCDR (val))); |
8f924df7 | 10243 | XSETCAR (val, make_number (id)); |
1397dc18 | 10244 | } |
4ed46869 | 10245 | |
df7492f9 KH |
10246 | flags = args[coding_arg_iso2022_flags]; |
10247 | CHECK_NATNUM (flags); | |
d311d28c | 10248 | i = XINT (flags) & INT_MAX; |
df7492f9 | 10249 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) |
d311d28c PE |
10250 | i |= CODING_ISO_FLAG_FULL_SUPPORT; |
10251 | flags = make_number (i); | |
df7492f9 KH |
10252 | |
10253 | ASET (attrs, coding_attr_iso_initial, initial); | |
10254 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
10255 | ASET (attrs, coding_attr_iso_request, request); | |
10256 | ASET (attrs, coding_attr_iso_flags, flags); | |
10257 | setup_iso_safe_charsets (attrs); | |
10258 | ||
10259 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
10260 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
10261 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
10262 | ? coding_category_iso_7_else | |
10263 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
10264 | ? coding_category_iso_7 | |
10265 | : coding_category_iso_7_tight); | |
10266 | else | |
10267 | { | |
10268 | int id = XINT (AREF (initial, 1)); | |
10269 | ||
c6fb6e98 | 10270 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
10271 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
10272 | || id < 0) | |
10273 | ? coding_category_iso_8_else | |
10274 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
10275 | ? coding_category_iso_8_1 | |
10276 | : coding_category_iso_8_2); | |
10277 | } | |
0ce7886f KH |
10278 | if (category != coding_category_iso_8_1 |
10279 | && category != coding_category_iso_8_2) | |
4939150c | 10280 | ASET (attrs, coding_attr_ascii_compat, Qnil); |
df7492f9 KH |
10281 | } |
10282 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 10283 | { |
df7492f9 KH |
10284 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
10285 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
4939150c | 10286 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 | 10287 | category = coding_category_emacs_mule; |
c28a9453 | 10288 | } |
df7492f9 | 10289 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 10290 | { |
df7492f9 KH |
10291 | |
10292 | struct charset *charset; | |
10293 | ||
7d64c6ad | 10294 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 10295 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 10296 | error ("There should be three or four charsets"); |
df7492f9 KH |
10297 | |
10298 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10299 | if (CHARSET_DIMENSION (charset) != 1) | |
10300 | error ("Dimension of charset %s is not one", | |
8f924df7 | 10301 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac | 10302 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 10303 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
10304 | |
10305 | charset_list = XCDR (charset_list); | |
10306 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10307 | if (CHARSET_DIMENSION (charset) != 1) | |
10308 | error ("Dimension of charset %s is not one", | |
8f924df7 | 10309 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
10310 | |
10311 | charset_list = XCDR (charset_list); | |
10312 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10313 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
10314 | error ("Dimension of charset %s is not two", |
10315 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
10316 | ||
10317 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
10318 | if (! NILP (charset_list)) |
10319 | { | |
10320 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10321 | if (CHARSET_DIMENSION (charset) != 2) | |
10322 | error ("Dimension of charset %s is not two", | |
10323 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
10324 | } | |
df7492f9 KH |
10325 | |
10326 | category = coding_category_sjis; | |
10327 | Vsjis_coding_system = name; | |
c28a9453 | 10328 | } |
df7492f9 KH |
10329 | else if (EQ (coding_type, Qbig5)) |
10330 | { | |
10331 | struct charset *charset; | |
4ed46869 | 10332 | |
df7492f9 KH |
10333 | if (XINT (Flength (charset_list)) != 2) |
10334 | error ("There should be just two charsets"); | |
10335 | ||
10336 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10337 | if (CHARSET_DIMENSION (charset) != 1) | |
10338 | error ("Dimension of charset %s is not one", | |
8f924df7 | 10339 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac | 10340 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 10341 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
10342 | |
10343 | charset_list = XCDR (charset_list); | |
10344 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
10345 | if (CHARSET_DIMENSION (charset) != 2) | |
10346 | error ("Dimension of charset %s is not two", | |
8f924df7 | 10347 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 10348 | |
df7492f9 KH |
10349 | category = coding_category_big5; |
10350 | Vbig5_coding_system = name; | |
10351 | } | |
10352 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 10353 | { |
584948ac | 10354 | category = coding_category_raw_text; |
4939150c | 10355 | ASET (attrs, coding_attr_ascii_compat, Qt); |
c28a9453 | 10356 | } |
df7492f9 | 10357 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 10358 | { |
a470d443 KH |
10359 | Lisp_Object bom; |
10360 | ||
a470d443 KH |
10361 | if (nargs < coding_arg_utf8_max) |
10362 | goto short_args; | |
10363 | ||
10364 | bom = args[coding_arg_utf8_bom]; | |
10365 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
10366 | { | |
10367 | CHECK_CONS (bom); | |
10368 | val = XCAR (bom); | |
10369 | CHECK_CODING_SYSTEM (val); | |
10370 | val = XCDR (bom); | |
10371 | CHECK_CODING_SYSTEM (val); | |
10372 | } | |
10373 | ASET (attrs, coding_attr_utf_bom, bom); | |
0e5317f7 | 10374 | if (NILP (bom)) |
4939150c | 10375 | ASET (attrs, coding_attr_ascii_compat, Qt); |
a470d443 KH |
10376 | |
10377 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
10378 | : NILP (bom) ? coding_category_utf_8_nosig | |
10379 | : coding_category_utf_8_sig); | |
4ed46869 | 10380 | } |
df7492f9 | 10381 | else if (EQ (coding_type, Qundecided)) |
c3a7b3f4 KH |
10382 | { |
10383 | if (nargs < coding_arg_undecided_max) | |
10384 | goto short_args; | |
10385 | ASET (attrs, coding_attr_undecided_inhibit_null_byte_detection, | |
10386 | args[coding_arg_undecided_inhibit_null_byte_detection]); | |
10387 | ASET (attrs, coding_attr_undecided_inhibit_iso_escape_detection, | |
10388 | args[coding_arg_undecided_inhibit_iso_escape_detection]); | |
10389 | ASET (attrs, coding_attr_undecided_prefer_utf_8, | |
10390 | args[coding_arg_undecided_prefer_utf_8]); | |
10391 | category = coding_category_undecided; | |
10392 | } | |
4ed46869 | 10393 | else |
df7492f9 | 10394 | error ("Invalid coding system type: %s", |
8f924df7 | 10395 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 10396 | |
4939150c PE |
10397 | ASET (attrs, coding_attr_category, make_number (category)); |
10398 | ASET (attrs, coding_attr_plist, | |
10399 | Fcons (QCcategory, | |
10400 | Fcons (AREF (Vcoding_category_table, category), | |
10401 | CODING_ATTR_PLIST (attrs)))); | |
10402 | ASET (attrs, coding_attr_plist, | |
10403 | Fcons (QCascii_compatible_p, | |
10404 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), | |
10405 | CODING_ATTR_PLIST (attrs)))); | |
c4825358 | 10406 | |
df7492f9 KH |
10407 | eol_type = args[coding_arg_eol_type]; |
10408 | if (! NILP (eol_type) | |
10409 | && ! EQ (eol_type, Qunix) | |
10410 | && ! EQ (eol_type, Qdos) | |
10411 | && ! EQ (eol_type, Qmac)) | |
10412 | error ("Invalid eol-type"); | |
4ed46869 | 10413 | |
df7492f9 | 10414 | aliases = Fcons (name, Qnil); |
4ed46869 | 10415 | |
df7492f9 KH |
10416 | if (NILP (eol_type)) |
10417 | { | |
10418 | eol_type = make_subsidiaries (name); | |
10419 | for (i = 0; i < 3; i++) | |
1397dc18 | 10420 | { |
df7492f9 KH |
10421 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
10422 | ||
10423 | this_name = AREF (eol_type, i); | |
10424 | this_aliases = Fcons (this_name, Qnil); | |
10425 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
25721f5b DA |
10426 | this_spec = make_uninit_vector (3); |
10427 | ASET (this_spec, 0, attrs); | |
df7492f9 KH |
10428 | ASET (this_spec, 1, this_aliases); |
10429 | ASET (this_spec, 2, this_eol_type); | |
10430 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
10431 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
10432 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
10433 | if (NILP (val)) | |
10434 | Vcoding_system_alist | |
10435 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
10436 | Vcoding_system_alist); | |
1397dc18 | 10437 | } |
d46c5b12 | 10438 | } |
4ed46869 | 10439 | |
25721f5b DA |
10440 | spec_vec = make_uninit_vector (3); |
10441 | ASET (spec_vec, 0, attrs); | |
df7492f9 KH |
10442 | ASET (spec_vec, 1, aliases); |
10443 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 10444 | |
df7492f9 KH |
10445 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
10446 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
10447 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
10448 | if (NILP (val)) | |
10449 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
10450 | Vcoding_system_alist); | |
48b0f3ae | 10451 | |
df7492f9 KH |
10452 | { |
10453 | int id = coding_categories[category].id; | |
48b0f3ae | 10454 | |
df7492f9 KH |
10455 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
10456 | setup_coding_system (name, &coding_categories[category]); | |
10457 | } | |
48b0f3ae | 10458 | |
d46c5b12 | 10459 | return Qnil; |
48b0f3ae | 10460 | |
df7492f9 KH |
10461 | short_args: |
10462 | return Fsignal (Qwrong_number_of_arguments, | |
10463 | Fcons (intern ("define-coding-system-internal"), | |
10464 | make_number (nargs))); | |
d46c5b12 | 10465 | } |
4ed46869 | 10466 | |
d6925f38 | 10467 | |
a6f87d34 KH |
10468 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
10469 | 3, 3, 0, | |
10470 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
5842a27b | 10471 | (Lisp_Object coding_system, Lisp_Object prop, Lisp_Object val) |
a6f87d34 | 10472 | { |
3dbe7859 | 10473 | Lisp_Object spec, attrs; |
a6f87d34 KH |
10474 | |
10475 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10476 | attrs = AREF (spec, 0); | |
10477 | if (EQ (prop, QCmnemonic)) | |
10478 | { | |
10479 | if (! STRINGP (val)) | |
10480 | CHECK_CHARACTER (val); | |
4939150c | 10481 | ASET (attrs, coding_attr_mnemonic, val); |
a6f87d34 | 10482 | } |
2133e2d1 | 10483 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
10484 | { |
10485 | if (NILP (val)) | |
10486 | val = make_number (' '); | |
10487 | else | |
10488 | CHECK_CHARACTER (val); | |
4939150c | 10489 | ASET (attrs, coding_attr_default_char, val); |
a6f87d34 KH |
10490 | } |
10491 | else if (EQ (prop, QCdecode_translation_table)) | |
10492 | { | |
10493 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10494 | CHECK_SYMBOL (val); | |
4939150c | 10495 | ASET (attrs, coding_attr_decode_tbl, val); |
a6f87d34 KH |
10496 | } |
10497 | else if (EQ (prop, QCencode_translation_table)) | |
10498 | { | |
10499 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10500 | CHECK_SYMBOL (val); | |
4939150c | 10501 | ASET (attrs, coding_attr_encode_tbl, val); |
a6f87d34 KH |
10502 | } |
10503 | else if (EQ (prop, QCpost_read_conversion)) | |
10504 | { | |
10505 | CHECK_SYMBOL (val); | |
4939150c | 10506 | ASET (attrs, coding_attr_post_read, val); |
a6f87d34 KH |
10507 | } |
10508 | else if (EQ (prop, QCpre_write_conversion)) | |
10509 | { | |
10510 | CHECK_SYMBOL (val); | |
4939150c | 10511 | ASET (attrs, coding_attr_pre_write, val); |
a6f87d34 | 10512 | } |
35befdaa KH |
10513 | else if (EQ (prop, QCascii_compatible_p)) |
10514 | { | |
4939150c | 10515 | ASET (attrs, coding_attr_ascii_compat, val); |
35befdaa | 10516 | } |
a6f87d34 | 10517 | |
4939150c PE |
10518 | ASET (attrs, coding_attr_plist, |
10519 | Fplist_put (CODING_ATTR_PLIST (attrs), prop, val)); | |
a6f87d34 KH |
10520 | return val; |
10521 | } | |
10522 | ||
10523 | ||
df7492f9 KH |
10524 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
10525 | Sdefine_coding_system_alias, 2, 2, 0, | |
10526 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
5842a27b | 10527 | (Lisp_Object alias, Lisp_Object coding_system) |
66cfb530 | 10528 | { |
583f71ca | 10529 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 10530 | |
df7492f9 KH |
10531 | CHECK_SYMBOL (alias); |
10532 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10533 | aliases = AREF (spec, 1); | |
d4a1d553 | 10534 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
10535 | element is a base coding system. Append ALIAS at the tail of the |
10536 | list. */ | |
df7492f9 KH |
10537 | while (!NILP (XCDR (aliases))) |
10538 | aliases = XCDR (aliases); | |
8f924df7 | 10539 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 10540 | |
df7492f9 KH |
10541 | eol_type = AREF (spec, 2); |
10542 | if (VECTORP (eol_type)) | |
4ed46869 | 10543 | { |
df7492f9 KH |
10544 | Lisp_Object subsidiaries; |
10545 | int i; | |
4ed46869 | 10546 | |
df7492f9 KH |
10547 | subsidiaries = make_subsidiaries (alias); |
10548 | for (i = 0; i < 3; i++) | |
10549 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
10550 | AREF (eol_type, i)); | |
4ed46869 | 10551 | } |
df7492f9 KH |
10552 | |
10553 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 10554 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
10555 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
10556 | if (NILP (val)) | |
10557 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
10558 | Vcoding_system_alist); | |
66cfb530 | 10559 | |
4ed46869 KH |
10560 | return Qnil; |
10561 | } | |
10562 | ||
a7ca3326 | 10563 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
df7492f9 KH |
10564 | 1, 1, 0, |
10565 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 10566 | Any alias or subsidiary coding system is not a base coding system. */) |
5842a27b | 10567 | (Lisp_Object coding_system) |
d46c5b12 | 10568 | { |
df7492f9 | 10569 | Lisp_Object spec, attrs; |
d46c5b12 | 10570 | |
df7492f9 KH |
10571 | if (NILP (coding_system)) |
10572 | return (Qno_conversion); | |
10573 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10574 | attrs = AREF (spec, 0); | |
10575 | return CODING_ATTR_BASE_NAME (attrs); | |
10576 | } | |
1397dc18 | 10577 | |
df7492f9 KH |
10578 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
10579 | 1, 1, 0, | |
10580 | doc: "Return the property list of CODING-SYSTEM.") | |
5842a27b | 10581 | (Lisp_Object coding_system) |
df7492f9 KH |
10582 | { |
10583 | Lisp_Object spec, attrs; | |
1397dc18 | 10584 | |
df7492f9 KH |
10585 | if (NILP (coding_system)) |
10586 | coding_system = Qno_conversion; | |
10587 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10588 | attrs = AREF (spec, 0); | |
10589 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
10590 | } |
10591 | ||
df7492f9 KH |
10592 | |
10593 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
10594 | 1, 1, 0, | |
da7db224 | 10595 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
5842a27b | 10596 | (Lisp_Object coding_system) |
66cfb530 | 10597 | { |
df7492f9 | 10598 | Lisp_Object spec; |
84d60297 | 10599 | |
df7492f9 KH |
10600 | if (NILP (coding_system)) |
10601 | coding_system = Qno_conversion; | |
10602 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 10603 | return AREF (spec, 1); |
df7492f9 | 10604 | } |
66cfb530 | 10605 | |
a7ca3326 | 10606 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
df7492f9 KH |
10607 | Scoding_system_eol_type, 1, 1, 0, |
10608 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 10609 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 10610 | |
df7492f9 KH |
10611 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
10612 | and CR respectively. | |
66cfb530 | 10613 | |
df7492f9 KH |
10614 | A vector value indicates that a format of end-of-line should be |
10615 | detected automatically. Nth element of the vector is the subsidiary | |
10616 | coding system whose eol-type is N. */) | |
5842a27b | 10617 | (Lisp_Object coding_system) |
6b89e3aa | 10618 | { |
df7492f9 KH |
10619 | Lisp_Object spec, eol_type; |
10620 | int n; | |
6b89e3aa | 10621 | |
df7492f9 KH |
10622 | if (NILP (coding_system)) |
10623 | coding_system = Qno_conversion; | |
10624 | if (! CODING_SYSTEM_P (coding_system)) | |
10625 | return Qnil; | |
10626 | spec = CODING_SYSTEM_SPEC (coding_system); | |
10627 | eol_type = AREF (spec, 2); | |
10628 | if (VECTORP (eol_type)) | |
10629 | return Fcopy_sequence (eol_type); | |
10630 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
10631 | return make_number (n); | |
6b89e3aa KH |
10632 | } |
10633 | ||
4ed46869 KH |
10634 | #endif /* emacs */ |
10635 | ||
10636 | \f | |
1397dc18 | 10637 | /*** 9. Post-amble ***/ |
4ed46869 | 10638 | |
dfcf069d | 10639 | void |
971de7fb | 10640 | init_coding_once (void) |
4ed46869 KH |
10641 | { |
10642 | int i; | |
10643 | ||
df7492f9 KH |
10644 | for (i = 0; i < coding_category_max; i++) |
10645 | { | |
10646 | coding_categories[i].id = -1; | |
10647 | coding_priorities[i] = i; | |
10648 | } | |
4ed46869 KH |
10649 | |
10650 | /* ISO2022 specific initialize routine. */ | |
10651 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 10652 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
10653 | for (i = 0x21; i < 0x7F; i++) |
10654 | iso_code_class[i] = ISO_graphic_plane_0; | |
10655 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 10656 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
10657 | for (i = 0xA1; i < 0xFF; i++) |
10658 | iso_code_class[i] = ISO_graphic_plane_1; | |
10659 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
10660 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
10661 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
10662 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
10663 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
10664 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
10665 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
10666 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
10667 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
10668 | ||
df7492f9 KH |
10669 | for (i = 0; i < 256; i++) |
10670 | { | |
10671 | emacs_mule_bytes[i] = 1; | |
10672 | } | |
7c78e542 KH |
10673 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
10674 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
10675 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
10676 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
10677 | } |
10678 | ||
10679 | #ifdef emacs | |
10680 | ||
dfcf069d | 10681 | void |
971de7fb | 10682 | syms_of_coding (void) |
e0e989f6 | 10683 | { |
df7492f9 | 10684 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
10685 | { |
10686 | Lisp_Object args[2]; | |
10687 | args[0] = QCtest; | |
10688 | args[1] = Qeq; | |
10689 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
10690 | } | |
df7492f9 KH |
10691 | |
10692 | staticpro (&Vsjis_coding_system); | |
10693 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 10694 | |
df7492f9 KH |
10695 | staticpro (&Vbig5_coding_system); |
10696 | Vbig5_coding_system = Qnil; | |
10697 | ||
24a73b0a KH |
10698 | staticpro (&Vcode_conversion_reused_workbuf); |
10699 | Vcode_conversion_reused_workbuf = Qnil; | |
10700 | ||
10701 | staticpro (&Vcode_conversion_workbuf_name); | |
2a0213a6 | 10702 | Vcode_conversion_workbuf_name = build_pure_c_string (" *code-conversion-work*"); |
e0e989f6 | 10703 | |
24a73b0a | 10704 | reused_workbuf_in_use = 0; |
df7492f9 KH |
10705 | |
10706 | DEFSYM (Qcharset, "charset"); | |
10707 | DEFSYM (Qtarget_idx, "target-idx"); | |
10708 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
10709 | Fset (Qcoding_system_history, Qnil); |
10710 | ||
9ce27fde | 10711 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 10712 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 10713 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
10714 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
10715 | ||
df7492f9 | 10716 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 10717 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
10718 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
10719 | ||
df7492f9 | 10720 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 10721 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10722 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
10723 | ||
df7492f9 | 10724 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 10725 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10726 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
10727 | ||
df7492f9 | 10728 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 10729 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
10730 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
10731 | ||
df7492f9 KH |
10732 | DEFSYM (Qcoding_system, "coding-system"); |
10733 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 10734 | |
df7492f9 KH |
10735 | DEFSYM (Qeol_type, "eol-type"); |
10736 | DEFSYM (Qunix, "unix"); | |
10737 | DEFSYM (Qdos, "dos"); | |
4b298d5a | 10738 | DEFSYM (Qmac, "mac"); |
4ed46869 | 10739 | |
df7492f9 KH |
10740 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
10741 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
10742 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
10743 | DEFSYM (Qdefault_char, "default-char"); | |
10744 | DEFSYM (Qundecided, "undecided"); | |
10745 | DEFSYM (Qno_conversion, "no-conversion"); | |
10746 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 10747 | |
df7492f9 | 10748 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 10749 | |
df7492f9 | 10750 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 10751 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 10752 | |
7f590b0c | 10753 | #if defined (WINDOWSNT) || defined (CYGWIN) |
ba116008 DC |
10754 | /* No, not utf-16-le: that one has a BOM. */ |
10755 | DEFSYM (Qutf_16le, "utf-16le"); | |
10756 | #endif | |
10757 | ||
df7492f9 | 10758 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
10759 | DEFSYM (Qbig, "big"); |
10760 | DEFSYM (Qlittle, "little"); | |
27901516 | 10761 | |
df7492f9 KH |
10762 | DEFSYM (Qshift_jis, "shift-jis"); |
10763 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 10764 | |
df7492f9 | 10765 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 10766 | |
df7492f9 | 10767 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 | 10768 | Fput (Qcoding_system_error, Qerror_conditions, |
3438fe21 | 10769 | listn (CONSTYPE_PURE, 2, Qcoding_system_error, Qerror)); |
4ed46869 | 10770 | Fput (Qcoding_system_error, Qerror_message, |
2a0213a6 | 10771 | build_pure_c_string ("Invalid coding system")); |
4ed46869 | 10772 | |
05e6f5dc KH |
10773 | /* Intern this now in case it isn't already done. |
10774 | Setting this variable twice is harmless. | |
10775 | But don't staticpro it here--that is done in alloc.c. */ | |
d67b4f80 | 10776 | Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots"); |
70c22245 | 10777 | |
df7492f9 | 10778 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 10779 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
10780 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
10781 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10782 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10783 | |
df7492f9 | 10784 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10785 | |
df7492f9 | 10786 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10787 | |
01378f49 | 10788 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10789 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10790 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10791 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10792 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10793 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10794 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10795 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10796 | |
df7492f9 KH |
10797 | Vcoding_category_table |
10798 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10799 | staticpro (&Vcoding_category_table); | |
10800 | /* Followings are target of code detection. */ | |
10801 | ASET (Vcoding_category_table, coding_category_iso_7, | |
d67b4f80 | 10802 | intern_c_string ("coding-category-iso-7")); |
df7492f9 | 10803 | ASET (Vcoding_category_table, coding_category_iso_7_tight, |
d67b4f80 | 10804 | intern_c_string ("coding-category-iso-7-tight")); |
df7492f9 | 10805 | ASET (Vcoding_category_table, coding_category_iso_8_1, |
d67b4f80 | 10806 | intern_c_string ("coding-category-iso-8-1")); |
df7492f9 | 10807 | ASET (Vcoding_category_table, coding_category_iso_8_2, |
d67b4f80 | 10808 | intern_c_string ("coding-category-iso-8-2")); |
df7492f9 | 10809 | ASET (Vcoding_category_table, coding_category_iso_7_else, |
d67b4f80 | 10810 | intern_c_string ("coding-category-iso-7-else")); |
df7492f9 | 10811 | ASET (Vcoding_category_table, coding_category_iso_8_else, |
d67b4f80 | 10812 | intern_c_string ("coding-category-iso-8-else")); |
a470d443 | 10813 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
d67b4f80 | 10814 | intern_c_string ("coding-category-utf-8-auto")); |
a470d443 | 10815 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, |
d67b4f80 | 10816 | intern_c_string ("coding-category-utf-8")); |
a470d443 | 10817 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
d67b4f80 | 10818 | intern_c_string ("coding-category-utf-8-sig")); |
df7492f9 | 10819 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
d67b4f80 | 10820 | intern_c_string ("coding-category-utf-16-be")); |
ff563fce | 10821 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
d67b4f80 | 10822 | intern_c_string ("coding-category-utf-16-auto")); |
df7492f9 | 10823 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
d67b4f80 | 10824 | intern_c_string ("coding-category-utf-16-le")); |
df7492f9 | 10825 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, |
d67b4f80 | 10826 | intern_c_string ("coding-category-utf-16-be-nosig")); |
df7492f9 | 10827 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, |
d67b4f80 | 10828 | intern_c_string ("coding-category-utf-16-le-nosig")); |
df7492f9 | 10829 | ASET (Vcoding_category_table, coding_category_charset, |
d67b4f80 | 10830 | intern_c_string ("coding-category-charset")); |
df7492f9 | 10831 | ASET (Vcoding_category_table, coding_category_sjis, |
d67b4f80 | 10832 | intern_c_string ("coding-category-sjis")); |
df7492f9 | 10833 | ASET (Vcoding_category_table, coding_category_big5, |
d67b4f80 | 10834 | intern_c_string ("coding-category-big5")); |
df7492f9 | 10835 | ASET (Vcoding_category_table, coding_category_ccl, |
d67b4f80 | 10836 | intern_c_string ("coding-category-ccl")); |
df7492f9 | 10837 | ASET (Vcoding_category_table, coding_category_emacs_mule, |
d67b4f80 | 10838 | intern_c_string ("coding-category-emacs-mule")); |
df7492f9 KH |
10839 | /* Followings are NOT target of code detection. */ |
10840 | ASET (Vcoding_category_table, coding_category_raw_text, | |
d67b4f80 | 10841 | intern_c_string ("coding-category-raw-text")); |
df7492f9 | 10842 | ASET (Vcoding_category_table, coding_category_undecided, |
d67b4f80 | 10843 | intern_c_string ("coding-category-undecided")); |
ecf488bc | 10844 | |
065e3595 | 10845 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
065e3595 KH |
10846 | DEFSYM (Qinvalid_source, "invalid-source"); |
10847 | DEFSYM (Qinterrupted, "interrupted"); | |
44e8490d | 10848 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10849 | |
4ed46869 KH |
10850 | defsubr (&Scoding_system_p); |
10851 | defsubr (&Sread_coding_system); | |
10852 | defsubr (&Sread_non_nil_coding_system); | |
10853 | defsubr (&Scheck_coding_system); | |
10854 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10855 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10856 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10857 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10858 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10859 | defsubr (&Sdecode_coding_region); |
10860 | defsubr (&Sencode_coding_region); | |
10861 | defsubr (&Sdecode_coding_string); | |
10862 | defsubr (&Sencode_coding_string); | |
10863 | defsubr (&Sdecode_sjis_char); | |
10864 | defsubr (&Sencode_sjis_char); | |
10865 | defsubr (&Sdecode_big5_char); | |
10866 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10867 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10868 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10869 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10870 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10871 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10872 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10873 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10874 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10875 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10876 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10877 | defsubr (&Scoding_system_base); |
10878 | defsubr (&Scoding_system_plist); | |
10879 | defsubr (&Scoding_system_aliases); | |
10880 | defsubr (&Scoding_system_eol_type); | |
10881 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10882 | |
29208e82 | 10883 | DEFVAR_LISP ("coding-system-list", Vcoding_system_list, |
48b0f3ae PJ |
10884 | doc: /* List of coding systems. |
10885 | ||
10886 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10887 | updated by the functions `define-coding-system' and |
48b0f3ae | 10888 | `define-coding-system-alias'. */); |
4608c386 KH |
10889 | Vcoding_system_list = Qnil; |
10890 | ||
29208e82 | 10891 | DEFVAR_LISP ("coding-system-alist", Vcoding_system_alist, |
48b0f3ae PJ |
10892 | doc: /* Alist of coding system names. |
10893 | Each element is one element list of coding system name. | |
446dcd75 | 10894 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10895 | |
10896 | Do not alter the value of this variable manually. This variable should be | |
10897 | updated by the functions `make-coding-system' and | |
10898 | `define-coding-system-alias'. */); | |
4608c386 KH |
10899 | Vcoding_system_alist = Qnil; |
10900 | ||
29208e82 | 10901 | DEFVAR_LISP ("coding-category-list", Vcoding_category_list, |
48b0f3ae PJ |
10902 | doc: /* List of coding-categories (symbols) ordered by priority. |
10903 | ||
10904 | On detecting a coding system, Emacs tries code detection algorithms | |
10905 | associated with each coding-category one by one in this order. When | |
10906 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10907 | system bound to the corresponding coding-category is selected. |
10908 | ||
448e17d6 | 10909 | Don't modify this variable directly, but use `set-coding-system-priority'. */); |
4ed46869 KH |
10910 | { |
10911 | int i; | |
10912 | ||
10913 | Vcoding_category_list = Qnil; | |
df7492f9 | 10914 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10915 | Vcoding_category_list |
28be1ada | 10916 | = Fcons (AREF (Vcoding_category_table, i), |
d46c5b12 | 10917 | Vcoding_category_list); |
4ed46869 KH |
10918 | } |
10919 | ||
29208e82 | 10920 | DEFVAR_LISP ("coding-system-for-read", Vcoding_system_for_read, |
48b0f3ae PJ |
10921 | doc: /* Specify the coding system for read operations. |
10922 | It is useful to bind this variable with `let', but do not set it globally. | |
10923 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10924 | If not, an appropriate element is used from one of the coding system alists. |
10925 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10926 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10927 | Vcoding_system_for_read = Qnil; |
10928 | ||
29208e82 | 10929 | DEFVAR_LISP ("coding-system-for-write", Vcoding_system_for_write, |
48b0f3ae PJ |
10930 | doc: /* Specify the coding system for write operations. |
10931 | Programs bind this variable with `let', but you should not set it globally. | |
10932 | If the value is a coding system, it is used for encoding of output, | |
10933 | when writing it to a file and when sending it to a file or subprocess. | |
10934 | ||
10935 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10936 | is used from one of the coding system alists. |
10937 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10938 | `process-coding-system-alist', and `network-coding-system-alist'. |
10939 | For output to files, if the above procedure does not specify a coding system, | |
10940 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10941 | Vcoding_system_for_write = Qnil; |
10942 | ||
29208e82 | 10943 | DEFVAR_LISP ("last-coding-system-used", Vlast_coding_system_used, |
df7492f9 KH |
10944 | doc: /* |
10945 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10946 | Vlast_coding_system_used = Qnil; |
10947 | ||
29208e82 | 10948 | DEFVAR_LISP ("last-code-conversion-error", Vlast_code_conversion_error, |
065e3595 KH |
10949 | doc: /* |
10950 | Error status of the last code conversion. | |
10951 | ||
10952 | When an error was detected in the last code conversion, this variable | |
10953 | is set to one of the following symbols. | |
10954 | `insufficient-source' | |
10955 | `inconsistent-eol' | |
10956 | `invalid-source' | |
10957 | `interrupted' | |
10958 | `insufficient-memory' | |
10959 | When no error was detected, the value doesn't change. So, to check | |
10960 | the error status of a code conversion by this variable, you must | |
10961 | explicitly set this variable to nil before performing code | |
10962 | conversion. */); | |
10963 | Vlast_code_conversion_error = Qnil; | |
10964 | ||
29208e82 | 10965 | DEFVAR_BOOL ("inhibit-eol-conversion", inhibit_eol_conversion, |
df7492f9 KH |
10966 | doc: /* |
10967 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10968 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10969 | such conversion. */); | |
9ce27fde KH |
10970 | inhibit_eol_conversion = 0; |
10971 | ||
29208e82 | 10972 | DEFVAR_BOOL ("inherit-process-coding-system", inherit_process_coding_system, |
df7492f9 KH |
10973 | doc: /* |
10974 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10975 | Bind it to t if the process output is to be treated as if it were a file |
10976 | read from some filesystem. */); | |
ed29121d EZ |
10977 | inherit_process_coding_system = 0; |
10978 | ||
29208e82 | 10979 | DEFVAR_LISP ("file-coding-system-alist", Vfile_coding_system_alist, |
df7492f9 KH |
10980 | doc: /* |
10981 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10982 | The format is ((PATTERN . VAL) ...), |
10983 | where PATTERN is a regular expression matching a file name, | |
10984 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10985 | If VAL is a coding system, it is used for both decoding and encoding | |
10986 | the file contents. | |
10987 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10988 | and the cdr part is used for encoding. | |
10989 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10990 | or a cons of coding systems which are used as above. The function is |
10991 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10992 | `find-operation-coding-system' was called. If the function can't decide |
10993 | a coding system, it can return `undecided' so that the normal | |
10994 | code-detection is performed. | |
48b0f3ae PJ |
10995 | |
10996 | See also the function `find-operation-coding-system' | |
10997 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10998 | Vfile_coding_system_alist = Qnil; |
10999 | ||
29208e82 | 11000 | DEFVAR_LISP ("process-coding-system-alist", Vprocess_coding_system_alist, |
df7492f9 KH |
11001 | doc: /* |
11002 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
11003 | The format is ((PATTERN . VAL) ...), |
11004 | where PATTERN is a regular expression matching a program name, | |
11005 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
11006 | If VAL is a coding system, it is used for both decoding what received | |
11007 | from the program and encoding what sent to the program. | |
11008 | If VAL is a cons of coding systems, the car part is used for decoding, | |
11009 | and the cdr part is used for encoding. | |
11010 | If VAL is a function symbol, the function must return a coding system | |
11011 | or a cons of coding systems which are used as above. | |
11012 | ||
11013 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
11014 | Vprocess_coding_system_alist = Qnil; |
11015 | ||
29208e82 | 11016 | DEFVAR_LISP ("network-coding-system-alist", Vnetwork_coding_system_alist, |
df7492f9 KH |
11017 | doc: /* |
11018 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
11019 | The format is ((PATTERN . VAL) ...), |
11020 | where PATTERN is a regular expression matching a network service name | |
11021 | or is a port number to connect to, | |
11022 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
11023 | If VAL is a coding system, it is used for both decoding what received | |
11024 | from the network stream and encoding what sent to the network stream. | |
11025 | If VAL is a cons of coding systems, the car part is used for decoding, | |
11026 | and the cdr part is used for encoding. | |
11027 | If VAL is a function symbol, the function must return a coding system | |
11028 | or a cons of coding systems which are used as above. | |
11029 | ||
11030 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 11031 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 11032 | |
29208e82 | 11033 | DEFVAR_LISP ("locale-coding-system", Vlocale_coding_system, |
75205970 RS |
11034 | doc: /* Coding system to use with system messages. |
11035 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
11036 | Vlocale_coding_system = Qnil; |
11037 | ||
005f0d35 | 11038 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
29208e82 | 11039 | DEFVAR_LISP ("eol-mnemonic-unix", eol_mnemonic_unix, |
df7492f9 KH |
11040 | doc: /* |
11041 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
2a0213a6 | 11042 | eol_mnemonic_unix = build_pure_c_string (":"); |
4ed46869 | 11043 | |
29208e82 | 11044 | DEFVAR_LISP ("eol-mnemonic-dos", eol_mnemonic_dos, |
df7492f9 KH |
11045 | doc: /* |
11046 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
2a0213a6 | 11047 | eol_mnemonic_dos = build_pure_c_string ("\\"); |
4ed46869 | 11048 | |
29208e82 | 11049 | DEFVAR_LISP ("eol-mnemonic-mac", eol_mnemonic_mac, |
df7492f9 KH |
11050 | doc: /* |
11051 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
2a0213a6 | 11052 | eol_mnemonic_mac = build_pure_c_string ("/"); |
4ed46869 | 11053 | |
29208e82 | 11054 | DEFVAR_LISP ("eol-mnemonic-undecided", eol_mnemonic_undecided, |
df7492f9 KH |
11055 | doc: /* |
11056 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
2a0213a6 | 11057 | eol_mnemonic_undecided = build_pure_c_string (":"); |
4ed46869 | 11058 | |
29208e82 | 11059 | DEFVAR_LISP ("enable-character-translation", Venable_character_translation, |
df7492f9 KH |
11060 | doc: /* |
11061 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 11062 | Venable_character_translation = Qt; |
bdd9fb48 | 11063 | |
f967223b | 11064 | DEFVAR_LISP ("standard-translation-table-for-decode", |
29208e82 | 11065 | Vstandard_translation_table_for_decode, |
48b0f3ae | 11066 | doc: /* Table for translating characters while decoding. */); |
f967223b | 11067 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 11068 | |
f967223b | 11069 | DEFVAR_LISP ("standard-translation-table-for-encode", |
29208e82 | 11070 | Vstandard_translation_table_for_encode, |
48b0f3ae | 11071 | doc: /* Table for translating characters while encoding. */); |
f967223b | 11072 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 11073 | |
29208e82 | 11074 | DEFVAR_LISP ("charset-revision-table", Vcharset_revision_table, |
48b0f3ae PJ |
11075 | doc: /* Alist of charsets vs revision numbers. |
11076 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
11077 | designate it with the escape sequence identifying revision (cdr part |
11078 | of the element). */); | |
11079 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
11080 | |
11081 | DEFVAR_LISP ("default-process-coding-system", | |
29208e82 | 11082 | Vdefault_process_coding_system, |
48b0f3ae PJ |
11083 | doc: /* Cons of coding systems used for process I/O by default. |
11084 | The car part is used for decoding a process output, | |
11085 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 11086 | Vdefault_process_coding_system = Qnil; |
c4825358 | 11087 | |
29208e82 | 11088 | DEFVAR_LISP ("latin-extra-code-table", Vlatin_extra_code_table, |
df7492f9 KH |
11089 | doc: /* |
11090 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
11091 | This is a vector of length 256. |
11092 | If Nth element is non-nil, the existence of code N in a file | |
11093 | \(or output of subprocess) doesn't prevent it to be detected as | |
11094 | a coding system of ISO 2022 variant which has a flag | |
11095 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
11096 | or reading output of a subprocess. | |
446dcd75 | 11097 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 11098 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
11099 | |
11100 | DEFVAR_LISP ("select-safe-coding-system-function", | |
29208e82 | 11101 | Vselect_safe_coding_system_function, |
df7492f9 KH |
11102 | doc: /* |
11103 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
11104 | |
11105 | If set, this function is called to force a user to select a proper | |
11106 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
11107 | coding system used in each operation can't encode the text. The |
11108 | function should take care that the buffer is not modified while | |
11109 | the coding system is being selected. | |
48b0f3ae PJ |
11110 | |
11111 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
11112 | Vselect_safe_coding_system_function = Qnil; |
11113 | ||
5d5bf4d8 | 11114 | DEFVAR_BOOL ("coding-system-require-warning", |
29208e82 | 11115 | coding_system_require_warning, |
5d5bf4d8 | 11116 | doc: /* Internal use only. |
6b89e3aa KH |
11117 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
11118 | called even if `coding-system-for-write' is non-nil. The command | |
11119 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
11120 | coding_system_require_warning = 0; |
11121 | ||
11122 | ||
22ab2303 | 11123 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
29208e82 | 11124 | inhibit_iso_escape_detection, |
df7492f9 | 11125 | doc: /* |
97b1b294 | 11126 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 11127 | |
97b1b294 EZ |
11128 | When Emacs reads text, it tries to detect how the text is encoded. |
11129 | This code detection is sensitive to escape sequences. If Emacs sees | |
11130 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
11131 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
11132 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
11133 | |
11134 | However, there may be a case that you want to read escape sequences in | |
11135 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
11136 | Then the code detection will ignore any escape sequences, and no text is |
11137 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
11138 | escape sequences become visible in a buffer. |
11139 | ||
11140 | The default value is nil, and it is strongly recommended not to change | |
11141 | it. That is because many Emacs Lisp source files that contain | |
11142 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
11143 | in Emacs's distribution, and they won't be decoded correctly on | |
11144 | reading if you suppress escape sequence detection. | |
11145 | ||
11146 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 11147 | to explicitly specify some coding system that doesn't use ISO-2022 |
65e7ca35 | 11148 | escape sequence (e.g., `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 11149 | inhibit_iso_escape_detection = 0; |
002fdb44 | 11150 | |
97b1b294 | 11151 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
29208e82 | 11152 | inhibit_null_byte_detection, |
97b1b294 EZ |
11153 | doc: /* If non-nil, Emacs ignores null bytes on code detection. |
11154 | By default, Emacs treats it as binary data, and does not attempt to | |
11155 | decode it. The effect is as if you specified `no-conversion' for | |
11156 | reading that text. | |
11157 | ||
11158 | Set this to non-nil when a regular text happens to include null bytes. | |
11159 | Examples are Index nodes of Info files and null-byte delimited output | |
11160 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
11161 | decode text as usual. */); | |
11162 | inhibit_null_byte_detection = 0; | |
11163 | ||
8a44e6d1 KH |
11164 | DEFVAR_BOOL ("disable-ascii-optimization", disable_ascii_optimization, |
11165 | doc: /* If non-nil, Emacs does not optimize code decoder for ASCII files. | |
11166 | Internal use only. Removed after the experimental optimizer gets stable. */); | |
8bc369d4 | 11167 | disable_ascii_optimization = 0; |
8a44e6d1 | 11168 | |
29208e82 | 11169 | DEFVAR_LISP ("translation-table-for-input", Vtranslation_table_for_input, |
15c8f9d1 | 11170 | doc: /* Char table for translating self-inserting characters. |
446dcd75 | 11171 | This is applied to the result of input methods, not their input. |
8434d0b8 EZ |
11172 | See also `keyboard-translate-table'. |
11173 | ||
11174 | Use of this variable for character code unification was rendered | |
11175 | obsolete in Emacs 23.1 and later, since Unicode is now the basis of | |
11176 | internal character representation. */); | |
002fdb44 | 11177 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 11178 | |
2c78b7e1 | 11179 | { |
c3a7b3f4 | 11180 | Lisp_Object args[coding_arg_undecided_max]; |
8f924df7 | 11181 | Lisp_Object plist[16]; |
2c78b7e1 KH |
11182 | int i; |
11183 | ||
c3a7b3f4 | 11184 | for (i = 0; i < coding_arg_undecided_max; i++) |
2c78b7e1 KH |
11185 | args[i] = Qnil; |
11186 | ||
d67b4f80 | 11187 | plist[0] = intern_c_string (":name"); |
2c78b7e1 | 11188 | plist[1] = args[coding_arg_name] = Qno_conversion; |
d67b4f80 | 11189 | plist[2] = intern_c_string (":mnemonic"); |
2c78b7e1 | 11190 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); |
d67b4f80 | 11191 | plist[4] = intern_c_string (":coding-type"); |
2c78b7e1 | 11192 | plist[5] = args[coding_arg_coding_type] = Qraw_text; |
d67b4f80 | 11193 | plist[6] = intern_c_string (":ascii-compatible-p"); |
2c78b7e1 | 11194 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; |
d67b4f80 | 11195 | plist[8] = intern_c_string (":default-char"); |
2c78b7e1 | 11196 | plist[9] = args[coding_arg_default_char] = make_number (0); |
d67b4f80 | 11197 | plist[10] = intern_c_string (":for-unibyte"); |
8f924df7 | 11198 | plist[11] = args[coding_arg_for_unibyte] = Qt; |
d67b4f80 | 11199 | plist[12] = intern_c_string (":docstring"); |
2a0213a6 | 11200 | plist[13] = build_pure_c_string ("Do no conversion.\n\ |
2c78b7e1 KH |
11201 | \n\ |
11202 | When you visit a file with this coding, the file is read into a\n\ | |
11203 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
11204 | character."); | |
d67b4f80 | 11205 | plist[14] = intern_c_string (":eol-type"); |
8f924df7 KH |
11206 | plist[15] = args[coding_arg_eol_type] = Qunix; |
11207 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 11208 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
11209 | |
11210 | plist[1] = args[coding_arg_name] = Qundecided; | |
11211 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
11212 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
11213 | /* This is already set. | |
35befdaa | 11214 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
d67b4f80 | 11215 | plist[8] = intern_c_string (":charset-list"); |
ae6f73fa KH |
11216 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); |
11217 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
2a0213a6 | 11218 | plist[13] = build_pure_c_string ("No conversion on encoding, automatic conversion on decoding."); |
ae6f73fa KH |
11219 | plist[15] = args[coding_arg_eol_type] = Qnil; |
11220 | args[coding_arg_plist] = Flist (16, plist); | |
c3a7b3f4 | 11221 | Fdefine_coding_system_internal (coding_arg_undecided_max, args); |
2c78b7e1 KH |
11222 | } |
11223 | ||
2c78b7e1 | 11224 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
11225 | |
11226 | { | |
11227 | int i; | |
11228 | ||
11229 | for (i = 0; i < coding_category_max; i++) | |
11230 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
11231 | } | |
1a4990fb | 11232 | #if defined (DOS_NT) |
fcbcfb64 KH |
11233 | system_eol_type = Qdos; |
11234 | #else | |
11235 | system_eol_type = Qunix; | |
11236 | #endif | |
11237 | staticpro (&system_eol_type); | |
4ed46869 KH |
11238 | } |
11239 | ||
68c45bf0 | 11240 | char * |
971de7fb | 11241 | emacs_strerror (int error_number) |
68c45bf0 PE |
11242 | { |
11243 | char *str; | |
11244 | ||
ca9c0567 | 11245 | synchronize_system_messages_locale (); |
68c45bf0 PE |
11246 | str = strerror (error_number); |
11247 | ||
11248 | if (! NILP (Vlocale_coding_system)) | |
11249 | { | |
11250 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
11251 | Vlocale_coding_system, | |
11252 | 0); | |
51b59d79 | 11253 | str = SSDATA (dec); |
68c45bf0 PE |
11254 | } |
11255 | ||
11256 | return str; | |
11257 | } | |
11258 | ||
4ed46869 | 11259 | #endif /* emacs */ |