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 | ||
4ed46869 | 289 | #include "lisp.h" |
df7492f9 | 290 | #include "character.h" |
e5560ff7 | 291 | #include "buffer.h" |
4ed46869 KH |
292 | #include "charset.h" |
293 | #include "ccl.h" | |
df7492f9 | 294 | #include "composite.h" |
4ed46869 KH |
295 | #include "coding.h" |
296 | #include "window.h" | |
b8299c66 KL |
297 | #include "frame.h" |
298 | #include "termhooks.h" | |
4ed46869 | 299 | |
df7492f9 | 300 | Lisp_Object Vcoding_system_hash_table; |
4ed46869 | 301 | |
955cbe7b PE |
302 | static Lisp_Object Qcoding_system, Qeol_type; |
303 | static Lisp_Object Qcoding_aliases; | |
84cc1ab6 PE |
304 | Lisp_Object Qunix, Qdos; |
305 | static Lisp_Object Qmac; | |
4ed46869 | 306 | Lisp_Object Qbuffer_file_coding_system; |
955cbe7b PE |
307 | static Lisp_Object Qpost_read_conversion, Qpre_write_conversion; |
308 | static Lisp_Object Qdefault_char; | |
27901516 | 309 | Lisp_Object Qno_conversion, Qundecided; |
955cbe7b PE |
310 | Lisp_Object Qcharset, Qutf_8; |
311 | static Lisp_Object Qiso_2022; | |
312 | static Lisp_Object Qutf_16, Qshift_jis, Qbig5; | |
313 | static Lisp_Object Qbig, Qlittle; | |
314 | static Lisp_Object Qcoding_system_history; | |
315 | static Lisp_Object Qvalid_codes; | |
316 | static Lisp_Object QCcategory, QCmnemonic, QCdefault_char; | |
317 | static Lisp_Object QCdecode_translation_table, QCencode_translation_table; | |
318 | static Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
319 | static Lisp_Object QCascii_compatible_p; | |
4ed46869 | 320 | |
387f6ba5 | 321 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 | 322 | Lisp_Object Qstart_process, Qopen_network_stream; |
955cbe7b | 323 | static Lisp_Object Qtarget_idx; |
4ed46869 | 324 | |
955cbe7b PE |
325 | static Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
326 | static Lisp_Object Qinterrupted, Qinsufficient_memory; | |
065e3595 | 327 | |
44e8490d KH |
328 | /* If a symbol has this property, evaluate the value to define the |
329 | symbol as a coding system. */ | |
330 | static Lisp_Object Qcoding_system_define_form; | |
331 | ||
fcbcfb64 KH |
332 | /* Format of end-of-line decided by system. This is Qunix on |
333 | Unix and Mac, Qdos on DOS/Windows. | |
334 | This has an effect only for external encoding (i.e. for output to | |
335 | file and process), not for in-buffer or Lisp string encoding. */ | |
336 | static Lisp_Object system_eol_type; | |
337 | ||
4ed46869 KH |
338 | #ifdef emacs |
339 | ||
4608c386 | 340 | Lisp_Object Qcoding_system_p, Qcoding_system_error; |
4ed46869 | 341 | |
d46c5b12 KH |
342 | /* Coding system emacs-mule and raw-text are for converting only |
343 | end-of-line format. */ | |
344 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 345 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 346 | |
53372c27 | 347 | #if defined (WINDOWSNT) || defined (CYGWIN) |
ba116008 DC |
348 | static Lisp_Object Qutf_16le; |
349 | #endif | |
350 | ||
4ed46869 KH |
351 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
352 | routines by the following three variables. */ | |
c4825358 KH |
353 | /* Coding system to be used to encode text for terminal display when |
354 | terminal coding system is nil. */ | |
355 | struct coding_system safe_terminal_coding; | |
356 | ||
4ed46869 KH |
357 | #endif /* emacs */ |
358 | ||
f967223b KH |
359 | Lisp_Object Qtranslation_table; |
360 | Lisp_Object Qtranslation_table_id; | |
955cbe7b PE |
361 | static Lisp_Object Qtranslation_table_for_decode; |
362 | static Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 | 363 | |
df7492f9 | 364 | /* Two special coding systems. */ |
74ab6df5 PE |
365 | static Lisp_Object Vsjis_coding_system; |
366 | static Lisp_Object Vbig5_coding_system; | |
df7492f9 | 367 | |
df7492f9 KH |
368 | /* ISO2022 section */ |
369 | ||
370 | #define CODING_ISO_INITIAL(coding, reg) \ | |
371 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
372 | coding_attr_iso_initial), \ | |
373 | reg))) | |
374 | ||
375 | ||
1b3b981b AS |
376 | #define CODING_ISO_REQUEST(coding, charset_id) \ |
377 | (((charset_id) <= (coding)->max_charset_id \ | |
378 | ? ((coding)->safe_charsets[charset_id] != 255 \ | |
379 | ? (coding)->safe_charsets[charset_id] \ | |
380 | : -1) \ | |
df7492f9 KH |
381 | : -1)) |
382 | ||
383 | ||
384 | #define CODING_ISO_FLAGS(coding) \ | |
385 | ((coding)->spec.iso_2022.flags) | |
386 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
387 | ((coding)->spec.iso_2022.current_designation[reg]) | |
388 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
389 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
390 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
391 | ((coding)->spec.iso_2022.single_shifting) | |
392 | #define CODING_ISO_BOL(coding) \ | |
393 | ((coding)->spec.iso_2022.bol) | |
394 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
395 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
e951386e KH |
396 | #define CODING_ISO_CMP_STATUS(coding) \ |
397 | (&(coding)->spec.iso_2022.cmp_status) | |
398 | #define CODING_ISO_EXTSEGMENT_LEN(coding) \ | |
399 | ((coding)->spec.iso_2022.ctext_extended_segment_len) | |
400 | #define CODING_ISO_EMBEDDED_UTF_8(coding) \ | |
401 | ((coding)->spec.iso_2022.embedded_utf_8) | |
df7492f9 KH |
402 | |
403 | /* Control characters of ISO2022. */ | |
404 | /* code */ /* function */ | |
df7492f9 KH |
405 | #define ISO_CODE_SO 0x0E /* shift-out */ |
406 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
407 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
408 | #define ISO_CODE_ESC 0x1B /* escape */ | |
409 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
410 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
411 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
412 | ||
413 | /* All code (1-byte) of ISO2022 is classified into one of the | |
414 | followings. */ | |
415 | enum iso_code_class_type | |
416 | { | |
417 | ISO_control_0, /* Control codes in the range | |
418 | 0x00..0x1F and 0x7F, except for the | |
419 | following 5 codes. */ | |
df7492f9 KH |
420 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
421 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
422 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
a0d7415f | 423 | ISO_escape, /* ISO_CODE_ESC (0x1B) */ |
df7492f9 KH |
424 | ISO_control_1, /* Control codes in the range |
425 | 0x80..0x9F, except for the | |
426 | following 3 codes. */ | |
427 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
428 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
429 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
430 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
431 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
432 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
433 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
434 | }; | |
05e6f5dc | 435 | |
df7492f9 KH |
436 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
437 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 438 | |
df7492f9 KH |
439 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
440 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
441 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 442 | |
df7492f9 KH |
443 | /* If set, reset graphic planes and registers at end-of-line to the |
444 | initial state. */ | |
445 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 446 | |
df7492f9 KH |
447 | /* If set, reset graphic planes and registers before any control |
448 | characters to the initial state. */ | |
449 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 450 | |
df7492f9 KH |
451 | /* If set, encode by 7-bit environment. */ |
452 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 453 | |
df7492f9 KH |
454 | /* If set, use locking-shift function. */ |
455 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 456 | |
df7492f9 KH |
457 | /* If set, use single-shift function. Overwrite |
458 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
459 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 460 | |
df7492f9 KH |
461 | /* If set, use designation escape sequence. */ |
462 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 463 | |
df7492f9 KH |
464 | /* If set, produce revision number sequence. */ |
465 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 466 | |
df7492f9 KH |
467 | /* If set, produce ISO6429's direction specifying sequence. */ |
468 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 469 | |
df7492f9 KH |
470 | /* If set, assume designation states are reset at beginning of line on |
471 | output. */ | |
472 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 473 | |
df7492f9 KH |
474 | /* If set, designation sequence should be placed at beginning of line |
475 | on output. */ | |
476 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 477 | |
ad1746f5 | 478 | /* If set, do not encode unsafe characters on output. */ |
df7492f9 | 479 | #define CODING_ISO_FLAG_SAFE 0x0800 |
aa72b389 | 480 | |
df7492f9 KH |
481 | /* If set, extra latin codes (128..159) are accepted as a valid code |
482 | on input. */ | |
483 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 484 | |
df7492f9 | 485 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 486 | |
5f58e762 | 487 | /* #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 */ |
aa72b389 | 488 | |
bf16eb23 | 489 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 490 | |
bf16eb23 | 491 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 492 | |
bf16eb23 | 493 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 494 | |
df7492f9 KH |
495 | /* A character to be produced on output if encoding of the original |
496 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
497 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 498 | |
a470d443 KH |
499 | /* UTF-8 section */ |
500 | #define CODING_UTF_8_BOM(coding) \ | |
501 | ((coding)->spec.utf_8_bom) | |
4ed46869 | 502 | |
df7492f9 KH |
503 | /* UTF-16 section */ |
504 | #define CODING_UTF_16_BOM(coding) \ | |
505 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 506 | |
df7492f9 KH |
507 | #define CODING_UTF_16_ENDIAN(coding) \ |
508 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 509 | |
df7492f9 KH |
510 | #define CODING_UTF_16_SURROGATE(coding) \ |
511 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 512 | |
4ed46869 | 513 | |
df7492f9 KH |
514 | /* CCL section */ |
515 | #define CODING_CCL_DECODER(coding) \ | |
516 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
517 | #define CODING_CCL_ENCODER(coding) \ | |
518 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
519 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 520 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 521 | |
5a936b46 | 522 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 523 | |
df7492f9 KH |
524 | enum coding_category |
525 | { | |
526 | coding_category_iso_7, | |
527 | coding_category_iso_7_tight, | |
528 | coding_category_iso_8_1, | |
529 | coding_category_iso_8_2, | |
530 | coding_category_iso_7_else, | |
531 | coding_category_iso_8_else, | |
a470d443 KH |
532 | coding_category_utf_8_auto, |
533 | coding_category_utf_8_nosig, | |
534 | coding_category_utf_8_sig, | |
df7492f9 KH |
535 | coding_category_utf_16_auto, |
536 | coding_category_utf_16_be, | |
537 | coding_category_utf_16_le, | |
538 | coding_category_utf_16_be_nosig, | |
539 | coding_category_utf_16_le_nosig, | |
540 | coding_category_charset, | |
541 | coding_category_sjis, | |
542 | coding_category_big5, | |
543 | coding_category_ccl, | |
544 | coding_category_emacs_mule, | |
545 | /* All above are targets of code detection. */ | |
546 | coding_category_raw_text, | |
547 | coding_category_undecided, | |
548 | coding_category_max | |
549 | }; | |
550 | ||
551 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
552 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
553 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
554 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
555 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
556 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
557 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
a470d443 KH |
558 | #define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto) |
559 | #define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig) | |
560 | #define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig) | |
b49a1807 | 561 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
562 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
563 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
564 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
565 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
566 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
567 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
568 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
569 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
570 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 571 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
572 | |
573 | /* This value is returned if detect_coding_mask () find nothing other | |
574 | than ASCII characters. */ | |
575 | #define CATEGORY_MASK_ANY \ | |
576 | (CATEGORY_MASK_ISO_7 \ | |
577 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
578 | | CATEGORY_MASK_ISO_8_1 \ | |
579 | | CATEGORY_MASK_ISO_8_2 \ | |
580 | | CATEGORY_MASK_ISO_7_ELSE \ | |
581 | | CATEGORY_MASK_ISO_8_ELSE \ | |
a470d443 KH |
582 | | CATEGORY_MASK_UTF_8_AUTO \ |
583 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
584 | | CATEGORY_MASK_UTF_8_SIG \ | |
2f3cbb32 | 585 | | CATEGORY_MASK_UTF_16_AUTO \ |
df7492f9 KH |
586 | | CATEGORY_MASK_UTF_16_BE \ |
587 | | CATEGORY_MASK_UTF_16_LE \ | |
588 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
589 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
590 | | CATEGORY_MASK_CHARSET \ | |
591 | | CATEGORY_MASK_SJIS \ | |
592 | | CATEGORY_MASK_BIG5 \ | |
593 | | CATEGORY_MASK_CCL \ | |
594 | | CATEGORY_MASK_EMACS_MULE) | |
595 | ||
596 | ||
597 | #define CATEGORY_MASK_ISO_7BIT \ | |
598 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
599 | ||
600 | #define CATEGORY_MASK_ISO_8BIT \ | |
601 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
602 | ||
603 | #define CATEGORY_MASK_ISO_ELSE \ | |
604 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
605 | ||
606 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
607 | (CATEGORY_MASK_ISO_7 \ | |
608 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
609 | | CATEGORY_MASK_ISO_7_ELSE \ | |
610 | | CATEGORY_MASK_ISO_8_ELSE) | |
611 | ||
612 | #define CATEGORY_MASK_ISO \ | |
613 | ( CATEGORY_MASK_ISO_7BIT \ | |
614 | | CATEGORY_MASK_ISO_8BIT \ | |
615 | | CATEGORY_MASK_ISO_ELSE) | |
616 | ||
617 | #define CATEGORY_MASK_UTF_16 \ | |
2f3cbb32 KH |
618 | (CATEGORY_MASK_UTF_16_AUTO \ |
619 | | CATEGORY_MASK_UTF_16_BE \ | |
df7492f9 KH |
620 | | CATEGORY_MASK_UTF_16_LE \ |
621 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
622 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
623 | ||
a470d443 KH |
624 | #define CATEGORY_MASK_UTF_8 \ |
625 | (CATEGORY_MASK_UTF_8_AUTO \ | |
626 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
627 | | CATEGORY_MASK_UTF_8_SIG) | |
df7492f9 | 628 | |
df7492f9 | 629 | /* Table of coding categories (Lisp symbols). This variable is for |
ad1746f5 | 630 | internal use only. */ |
df7492f9 KH |
631 | static Lisp_Object Vcoding_category_table; |
632 | ||
633 | /* Table of coding-categories ordered by priority. */ | |
634 | static enum coding_category coding_priorities[coding_category_max]; | |
635 | ||
636 | /* Nth element is a coding context for the coding system bound to the | |
637 | Nth coding category. */ | |
638 | static struct coding_system coding_categories[coding_category_max]; | |
639 | ||
df7492f9 KH |
640 | /*** Commonly used macros and functions ***/ |
641 | ||
642 | #ifndef min | |
643 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
644 | #endif | |
645 | #ifndef max | |
646 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
647 | #endif | |
4ed46869 | 648 | |
24a73b0a KH |
649 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
650 | do { \ | |
651 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
652 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 653 | } while (0) |
4ed46869 | 654 | |
4ed46869 | 655 | |
df7492f9 KH |
656 | /* Safely get one byte from the source text pointed by SRC which ends |
657 | at SRC_END, and set C to that byte. If there are not enough bytes | |
f10fe38f PE |
658 | in the source, it jumps to 'no_more_source'. If MULTIBYTEP, |
659 | and a multibyte character is found at SRC, set C to the | |
065e3595 KH |
660 | negative value of the character code. The caller should declare |
661 | and set these variables appropriately in advance: | |
662 | src, src_end, multibytep */ | |
aa72b389 | 663 | |
065e3595 KH |
664 | #define ONE_MORE_BYTE(c) \ |
665 | do { \ | |
666 | if (src == src_end) \ | |
667 | { \ | |
668 | if (src_base < src) \ | |
669 | record_conversion_result \ | |
670 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
671 | goto no_more_source; \ | |
672 | } \ | |
673 | c = *src++; \ | |
674 | if (multibytep && (c & 0x80)) \ | |
675 | { \ | |
676 | if ((c & 0xFE) == 0xC0) \ | |
677 | c = ((c & 1) << 6) | *src++; \ | |
678 | else \ | |
679 | { \ | |
35befdaa KH |
680 | src--; \ |
681 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
682 | record_conversion_result \ |
683 | (coding, CODING_RESULT_INVALID_SRC); \ | |
684 | } \ | |
685 | } \ | |
686 | consumed_chars++; \ | |
aa72b389 KH |
687 | } while (0) |
688 | ||
f56a4450 | 689 | /* Safely get two bytes from the source text pointed by SRC which ends |
220eeac9 KH |
690 | at SRC_END, and set C1 and C2 to those bytes while skipping the |
691 | heading multibyte characters. If there are not enough bytes in the | |
f10fe38f | 692 | source, it jumps to 'no_more_source'. If MULTIBYTEP and |
220eeac9 KH |
693 | a multibyte character is found for C2, set C2 to the negative value |
694 | of the character code. The caller should declare and set these | |
695 | variables appropriately in advance: | |
f56a4450 KH |
696 | src, src_end, multibytep |
697 | It is intended that this macro is used in detect_coding_utf_16. */ | |
698 | ||
220eeac9 KH |
699 | #define TWO_MORE_BYTES(c1, c2) \ |
700 | do { \ | |
701 | do { \ | |
702 | if (src == src_end) \ | |
703 | goto no_more_source; \ | |
704 | c1 = *src++; \ | |
705 | if (multibytep && (c1 & 0x80)) \ | |
706 | { \ | |
707 | if ((c1 & 0xFE) == 0xC0) \ | |
708 | c1 = ((c1 & 1) << 6) | *src++; \ | |
709 | else \ | |
710 | { \ | |
711 | src += BYTES_BY_CHAR_HEAD (c1) - 1; \ | |
712 | c1 = -1; \ | |
713 | } \ | |
714 | } \ | |
715 | } while (c1 < 0); \ | |
716 | if (src == src_end) \ | |
717 | goto no_more_source; \ | |
718 | c2 = *src++; \ | |
719 | if (multibytep && (c2 & 0x80)) \ | |
720 | { \ | |
721 | if ((c2 & 0xFE) == 0xC0) \ | |
722 | c2 = ((c2 & 1) << 6) | *src++; \ | |
723 | else \ | |
724 | c2 = -1; \ | |
725 | } \ | |
f56a4450 KH |
726 | } while (0) |
727 | ||
aa72b389 | 728 | |
df7492f9 KH |
729 | /* Store a byte C in the place pointed by DST and increment DST to the |
730 | next free point, and increment PRODUCED_CHARS. The caller should | |
731 | assure that C is 0..127, and declare and set the variable `dst' | |
732 | appropriately in advance. | |
733 | */ | |
aa72b389 KH |
734 | |
735 | ||
df7492f9 KH |
736 | #define EMIT_ONE_ASCII_BYTE(c) \ |
737 | do { \ | |
738 | produced_chars++; \ | |
739 | *dst++ = (c); \ | |
b6871cc7 | 740 | } while (0) |
aa72b389 KH |
741 | |
742 | ||
ad1746f5 | 743 | /* Like EMIT_ONE_ASCII_BYTE but store two bytes; C1 and C2. */ |
aa72b389 | 744 | |
df7492f9 KH |
745 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
746 | do { \ | |
747 | produced_chars += 2; \ | |
748 | *dst++ = (c1), *dst++ = (c2); \ | |
749 | } while (0) | |
aa72b389 KH |
750 | |
751 | ||
df7492f9 | 752 | /* Store a byte C in the place pointed by DST and increment DST to the |
f10fe38f PE |
753 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP, |
754 | store in an appropriate multibyte form. The caller should | |
df7492f9 KH |
755 | declare and set the variables `dst' and `multibytep' appropriately |
756 | in advance. */ | |
757 | ||
758 | #define EMIT_ONE_BYTE(c) \ | |
759 | do { \ | |
760 | produced_chars++; \ | |
761 | if (multibytep) \ | |
762 | { \ | |
b25d760e | 763 | unsigned ch = (c); \ |
df7492f9 KH |
764 | if (ch >= 0x80) \ |
765 | ch = BYTE8_TO_CHAR (ch); \ | |
766 | CHAR_STRING_ADVANCE (ch, dst); \ | |
767 | } \ | |
768 | else \ | |
769 | *dst++ = (c); \ | |
aa72b389 | 770 | } while (0) |
aa72b389 | 771 | |
aa72b389 | 772 | |
df7492f9 | 773 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 774 | |
e19c3639 KH |
775 | #define EMIT_TWO_BYTES(c1, c2) \ |
776 | do { \ | |
777 | produced_chars += 2; \ | |
778 | if (multibytep) \ | |
779 | { \ | |
b25d760e | 780 | unsigned ch; \ |
e19c3639 KH |
781 | \ |
782 | ch = (c1); \ | |
783 | if (ch >= 0x80) \ | |
784 | ch = BYTE8_TO_CHAR (ch); \ | |
785 | CHAR_STRING_ADVANCE (ch, dst); \ | |
786 | ch = (c2); \ | |
787 | if (ch >= 0x80) \ | |
788 | ch = BYTE8_TO_CHAR (ch); \ | |
789 | CHAR_STRING_ADVANCE (ch, dst); \ | |
790 | } \ | |
791 | else \ | |
792 | { \ | |
793 | *dst++ = (c1); \ | |
794 | *dst++ = (c2); \ | |
795 | } \ | |
aa72b389 KH |
796 | } while (0) |
797 | ||
798 | ||
df7492f9 KH |
799 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
800 | do { \ | |
801 | EMIT_ONE_BYTE (c1); \ | |
802 | EMIT_TWO_BYTES (c2, c3); \ | |
803 | } while (0) | |
aa72b389 | 804 | |
aa72b389 | 805 | |
df7492f9 KH |
806 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
807 | do { \ | |
808 | EMIT_TWO_BYTES (c1, c2); \ | |
809 | EMIT_TWO_BYTES (c3, c4); \ | |
810 | } while (0) | |
aa72b389 | 811 | |
aa72b389 | 812 | |
065e3595 KH |
813 | static void |
814 | record_conversion_result (struct coding_system *coding, | |
815 | enum coding_result_code result) | |
816 | { | |
817 | coding->result = result; | |
818 | switch (result) | |
819 | { | |
820 | case CODING_RESULT_INSUFFICIENT_SRC: | |
821 | Vlast_code_conversion_error = Qinsufficient_source; | |
822 | break; | |
823 | case CODING_RESULT_INCONSISTENT_EOL: | |
824 | Vlast_code_conversion_error = Qinconsistent_eol; | |
825 | break; | |
826 | case CODING_RESULT_INVALID_SRC: | |
827 | Vlast_code_conversion_error = Qinvalid_source; | |
828 | break; | |
829 | case CODING_RESULT_INTERRUPT: | |
830 | Vlast_code_conversion_error = Qinterrupted; | |
831 | break; | |
832 | case CODING_RESULT_INSUFFICIENT_MEM: | |
833 | Vlast_code_conversion_error = Qinsufficient_memory; | |
834 | break; | |
ebaf11b6 KH |
835 | case CODING_RESULT_INSUFFICIENT_DST: |
836 | /* Don't record this error in Vlast_code_conversion_error | |
837 | because it happens just temporarily and is resolved when the | |
838 | whole conversion is finished. */ | |
839 | break; | |
409ea3a1 AS |
840 | case CODING_RESULT_SUCCESS: |
841 | break; | |
35befdaa KH |
842 | default: |
843 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
844 | } |
845 | } | |
846 | ||
5eb05ea3 KH |
847 | /* These wrapper macros are used to preserve validity of pointers into |
848 | buffer text across calls to decode_char, encode_char, etc, which | |
849 | could cause relocation of buffers if it loads a charset map, | |
850 | because loading a charset map allocates large structures. */ | |
851 | ||
df7492f9 KH |
852 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
853 | do { \ | |
8f50130c | 854 | ptrdiff_t offset; \ |
5eb05ea3 | 855 | \ |
df7492f9 KH |
856 | charset_map_loaded = 0; \ |
857 | c = DECODE_CHAR (charset, code); \ | |
5eb05ea3 | 858 | if (charset_map_loaded \ |
c1892f11 | 859 | && (offset = coding_change_source (coding))) \ |
df7492f9 | 860 | { \ |
df7492f9 KH |
861 | src += offset; \ |
862 | src_base += offset; \ | |
863 | src_end += offset; \ | |
864 | } \ | |
aa72b389 KH |
865 | } while (0) |
866 | ||
5eb05ea3 KH |
867 | #define CODING_ENCODE_CHAR(coding, dst, dst_end, charset, c, code) \ |
868 | do { \ | |
8f50130c | 869 | ptrdiff_t offset; \ |
5eb05ea3 KH |
870 | \ |
871 | charset_map_loaded = 0; \ | |
872 | code = ENCODE_CHAR (charset, c); \ | |
873 | if (charset_map_loaded \ | |
c1892f11 | 874 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
875 | { \ |
876 | dst += offset; \ | |
877 | dst_end += offset; \ | |
878 | } \ | |
879 | } while (0) | |
880 | ||
881 | #define CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list, code_return, charset) \ | |
882 | do { \ | |
8f50130c | 883 | ptrdiff_t offset; \ |
5eb05ea3 KH |
884 | \ |
885 | charset_map_loaded = 0; \ | |
886 | charset = char_charset (c, charset_list, code_return); \ | |
887 | if (charset_map_loaded \ | |
c1892f11 | 888 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
889 | { \ |
890 | dst += offset; \ | |
891 | dst_end += offset; \ | |
892 | } \ | |
893 | } while (0) | |
894 | ||
895 | #define CODING_CHAR_CHARSET_P(coding, dst, dst_end, c, charset, result) \ | |
896 | do { \ | |
8f50130c | 897 | ptrdiff_t offset; \ |
5eb05ea3 KH |
898 | \ |
899 | charset_map_loaded = 0; \ | |
900 | result = CHAR_CHARSET_P (c, charset); \ | |
901 | if (charset_map_loaded \ | |
c1892f11 | 902 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
903 | { \ |
904 | dst += offset; \ | |
905 | dst_end += offset; \ | |
906 | } \ | |
907 | } while (0) | |
908 | ||
aa72b389 | 909 | |
119852e7 KH |
910 | /* If there are at least BYTES length of room at dst, allocate memory |
911 | for coding->destination and update dst and dst_end. We don't have | |
912 | to take care of coding->source which will be relocated. It is | |
913 | handled by calling coding_set_source in encode_coding. */ | |
914 | ||
df7492f9 KH |
915 | #define ASSURE_DESTINATION(bytes) \ |
916 | do { \ | |
917 | if (dst + (bytes) >= dst_end) \ | |
918 | { \ | |
d311d28c | 919 | ptrdiff_t more_bytes = charbuf_end - charbuf + (bytes); \ |
df7492f9 KH |
920 | \ |
921 | dst = alloc_destination (coding, more_bytes, dst); \ | |
922 | dst_end = coding->destination + coding->dst_bytes; \ | |
923 | } \ | |
924 | } while (0) | |
aa72b389 | 925 | |
aa72b389 | 926 | |
db274c7a | 927 | /* Store multibyte form of the character C in P, and advance P to the |
eedec3ee EZ |
928 | end of the multibyte form. This used to be like CHAR_STRING_ADVANCE |
929 | without ever calling MAYBE_UNIFY_CHAR, but nowadays we don't call | |
930 | MAYBE_UNIFY_CHAR in CHAR_STRING_ADVANCE. */ | |
db274c7a | 931 | |
eedec3ee | 932 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) CHAR_STRING_ADVANCE(c, p) |
db274c7a KH |
933 | |
934 | /* Return the character code of character whose multibyte form is at | |
eedec3ee EZ |
935 | P, and advance P to the end of the multibyte form. This used to be |
936 | like STRING_CHAR_ADVANCE without ever calling MAYBE_UNIFY_CHAR, but | |
937 | nowadays STRING_CHAR_ADVANCE doesn't call MAYBE_UNIFY_CHAR. */ | |
db274c7a | 938 | |
eedec3ee | 939 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) STRING_CHAR_ADVANCE(p) |
aa72b389 | 940 | |
c1892f11 | 941 | /* Set coding->source from coding->src_object. */ |
5eb05ea3 | 942 | |
c1892f11 | 943 | static void |
971de7fb | 944 | coding_set_source (struct coding_system *coding) |
aa72b389 | 945 | { |
df7492f9 KH |
946 | if (BUFFERP (coding->src_object)) |
947 | { | |
2cb26057 | 948 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 949 | |
df7492f9 | 950 | if (coding->src_pos < 0) |
2cb26057 | 951 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 952 | else |
2cb26057 | 953 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 954 | } |
df7492f9 | 955 | else if (STRINGP (coding->src_object)) |
aa72b389 | 956 | { |
8f924df7 | 957 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 958 | } |
df7492f9 | 959 | else |
f38b440c PE |
960 | { |
961 | /* Otherwise, the source is C string and is never relocated | |
962 | automatically. Thus we don't have to update anything. */ | |
963 | } | |
df7492f9 | 964 | } |
aa72b389 | 965 | |
5eb05ea3 | 966 | |
c1892f11 PE |
967 | /* Set coding->source from coding->src_object, and return how many |
968 | bytes coding->source was changed. */ | |
5eb05ea3 | 969 | |
8f50130c | 970 | static ptrdiff_t |
c1892f11 | 971 | coding_change_source (struct coding_system *coding) |
df7492f9 | 972 | { |
c1892f11 PE |
973 | const unsigned char *orig = coding->source; |
974 | coding_set_source (coding); | |
975 | return coding->source - orig; | |
976 | } | |
977 | ||
5eb05ea3 | 978 | |
c1892f11 PE |
979 | /* Set coding->destination from coding->dst_object. */ |
980 | ||
981 | static void | |
982 | coding_set_destination (struct coding_system *coding) | |
983 | { | |
df7492f9 | 984 | if (BUFFERP (coding->dst_object)) |
aa72b389 | 985 | { |
a0241d01 | 986 | if (BUFFERP (coding->src_object) && coding->src_pos < 0) |
aa72b389 | 987 | { |
13818c30 | 988 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
989 | coding->dst_bytes = (GAP_END_ADDR |
990 | - (coding->src_bytes - coding->consumed) | |
991 | - coding->destination); | |
aa72b389 | 992 | } |
df7492f9 | 993 | else |
28f67a95 KH |
994 | { |
995 | /* We are sure that coding->dst_pos_byte is before the gap | |
996 | of the buffer. */ | |
997 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 998 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
999 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
1000 | - coding->destination); | |
1001 | } | |
df7492f9 KH |
1002 | } |
1003 | else | |
f38b440c PE |
1004 | { |
1005 | /* Otherwise, the destination is C string and is never relocated | |
1006 | automatically. Thus we don't have to update anything. */ | |
1007 | } | |
c1892f11 PE |
1008 | } |
1009 | ||
1010 | ||
1011 | /* Set coding->destination from coding->dst_object, and return how | |
1012 | many bytes coding->destination was changed. */ | |
1013 | ||
1014 | static ptrdiff_t | |
1015 | coding_change_destination (struct coding_system *coding) | |
1016 | { | |
1017 | const unsigned char *orig = coding->destination; | |
1018 | coding_set_destination (coding); | |
5eb05ea3 | 1019 | return coding->destination - orig; |
df7492f9 KH |
1020 | } |
1021 | ||
1022 | ||
1023 | static void | |
d311d28c | 1024 | coding_alloc_by_realloc (struct coding_system *coding, ptrdiff_t bytes) |
df7492f9 | 1025 | { |
c9d624c6 | 1026 | if (STRING_BYTES_BOUND - coding->dst_bytes < bytes) |
d1f3d2af | 1027 | string_overflow (); |
38182d90 PE |
1028 | coding->destination = xrealloc (coding->destination, |
1029 | coding->dst_bytes + bytes); | |
df7492f9 KH |
1030 | coding->dst_bytes += bytes; |
1031 | } | |
1032 | ||
1033 | static void | |
cf84bb53 | 1034 | coding_alloc_by_making_gap (struct coding_system *coding, |
d311d28c | 1035 | ptrdiff_t gap_head_used, ptrdiff_t bytes) |
df7492f9 | 1036 | { |
db274c7a | 1037 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1038 | { |
db274c7a KH |
1039 | /* The gap may contain the produced data at the head and not-yet |
1040 | consumed data at the tail. To preserve those data, we at | |
1041 | first make the gap size to zero, then increase the gap | |
1042 | size. */ | |
d311d28c | 1043 | ptrdiff_t add = GAP_SIZE; |
db274c7a KH |
1044 | |
1045 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1046 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1047 | make_gap (bytes); |
1048 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1049 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1050 | } |
730fff51 | 1051 | else |
eefd7278 | 1052 | make_gap_1 (XBUFFER (coding->dst_object), bytes); |
df7492f9 | 1053 | } |
8f924df7 | 1054 | |
df7492f9 KH |
1055 | |
1056 | static unsigned char * | |
d311d28c | 1057 | alloc_destination (struct coding_system *coding, ptrdiff_t nbytes, |
cf84bb53 | 1058 | unsigned char *dst) |
df7492f9 | 1059 | { |
d311d28c | 1060 | ptrdiff_t offset = dst - coding->destination; |
df7492f9 KH |
1061 | |
1062 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1063 | { |
1064 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1065 | ||
1066 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1067 | } | |
aa72b389 | 1068 | else |
df7492f9 | 1069 | coding_alloc_by_realloc (coding, nbytes); |
df7492f9 KH |
1070 | coding_set_destination (coding); |
1071 | dst = coding->destination + offset; | |
1072 | return dst; | |
1073 | } | |
aa72b389 | 1074 | |
ff0dacd7 KH |
1075 | /** Macros for annotations. */ |
1076 | ||
ff0dacd7 KH |
1077 | /* An annotation data is stored in the array coding->charbuf in this |
1078 | format: | |
69a80ea3 | 1079 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1080 | LENGTH is the number of elements in the annotation. |
1081 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1082 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1083 | |
1084 | The format of the following elements depend on ANNOTATION_MASK. | |
1085 | ||
1086 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1087 | follows: | |
e951386e KH |
1088 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
1089 | ||
1090 | NBYTES is the number of bytes specified in the header part of | |
1091 | old-style emacs-mule encoding, or 0 for the other kind of | |
1092 | composition. | |
1093 | ||
ff0dacd7 | 1094 | METHOD is one of enum composition_method. |
e951386e | 1095 | |
ad1746f5 | 1096 | Optional COMPOSITION-COMPONENTS are characters and composition |
ff0dacd7 KH |
1097 | rules. |
1098 | ||
1099 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
e951386e KH |
1100 | follows. |
1101 | ||
1102 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | |
1103 | recover from an invalid annotation, and should be skipped by | |
1104 | produce_annotation. */ | |
1105 | ||
1106 | /* Maximum length of the header of annotation data. */ | |
1107 | #define MAX_ANNOTATION_LENGTH 5 | |
ff0dacd7 | 1108 | |
69a80ea3 | 1109 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1110 | do { \ |
1111 | *(buf)++ = -(len); \ | |
1112 | *(buf)++ = (mask); \ | |
69a80ea3 | 1113 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1114 | coding->annotated = 1; \ |
1115 | } while (0); | |
1116 | ||
e951386e | 1117 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
69a80ea3 | 1118 | do { \ |
e951386e KH |
1119 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
1120 | *buf++ = nbytes; \ | |
69a80ea3 | 1121 | *buf++ = method; \ |
ff0dacd7 KH |
1122 | } while (0) |
1123 | ||
1124 | ||
69a80ea3 KH |
1125 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1126 | do { \ | |
1127 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1128 | *buf++ = id; \ | |
ff0dacd7 KH |
1129 | } while (0) |
1130 | ||
df7492f9 KH |
1131 | \f |
1132 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1133 | ||
1134 | ||
1135 | ||
1136 | \f | |
1137 | /*** 3. UTF-8 ***/ | |
1138 | ||
1139 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 1140 | Return true if a text is encoded in UTF-8. */ |
df7492f9 KH |
1141 | |
1142 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1143 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1144 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1145 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1146 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1147 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1148 | ||
a470d443 KH |
1149 | #define UTF_8_BOM_1 0xEF |
1150 | #define UTF_8_BOM_2 0xBB | |
1151 | #define UTF_8_BOM_3 0xBF | |
1152 | ||
f10fe38f | 1153 | static bool |
cf84bb53 JB |
1154 | detect_coding_utf_8 (struct coding_system *coding, |
1155 | struct coding_detection_info *detect_info) | |
df7492f9 | 1156 | { |
065e3595 | 1157 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1158 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 1159 | bool multibytep = coding->src_multibyte; |
d311d28c | 1160 | ptrdiff_t consumed_chars = 0; |
f10fe38f PE |
1161 | bool bom_found = 0; |
1162 | bool found = 0; | |
df7492f9 | 1163 | |
ff0dacd7 | 1164 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1165 | /* A coding system of this category is always ASCII compatible. */ |
1166 | src += coding->head_ascii; | |
1167 | ||
1168 | while (1) | |
aa72b389 | 1169 | { |
df7492f9 | 1170 | int c, c1, c2, c3, c4; |
aa72b389 | 1171 | |
065e3595 | 1172 | src_base = src; |
df7492f9 | 1173 | ONE_MORE_BYTE (c); |
065e3595 | 1174 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1175 | continue; |
1176 | ONE_MORE_BYTE (c1); | |
065e3595 | 1177 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1178 | break; |
1179 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1180 | { |
a470d443 | 1181 | found = 1; |
df7492f9 | 1182 | continue; |
aa72b389 | 1183 | } |
df7492f9 | 1184 | ONE_MORE_BYTE (c2); |
065e3595 | 1185 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1186 | break; |
1187 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1188 | { |
a470d443 KH |
1189 | found = 1; |
1190 | if (src_base == coding->source | |
1191 | && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3) | |
1192 | bom_found = 1; | |
df7492f9 | 1193 | continue; |
aa72b389 | 1194 | } |
df7492f9 | 1195 | ONE_MORE_BYTE (c3); |
065e3595 | 1196 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1197 | break; |
1198 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1199 | { |
a470d443 | 1200 | found = 1; |
df7492f9 KH |
1201 | continue; |
1202 | } | |
1203 | ONE_MORE_BYTE (c4); | |
065e3595 | 1204 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1205 | break; |
1206 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1207 | { | |
a470d443 | 1208 | found = 1; |
df7492f9 KH |
1209 | continue; |
1210 | } | |
1211 | break; | |
aa72b389 | 1212 | } |
ff0dacd7 | 1213 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1214 | return 0; |
aa72b389 | 1215 | |
df7492f9 | 1216 | no_more_source: |
065e3595 | 1217 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1218 | { |
ff0dacd7 | 1219 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1220 | return 0; |
aa72b389 | 1221 | } |
a470d443 KH |
1222 | if (bom_found) |
1223 | { | |
1224 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
1225 | detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; | |
1226 | } | |
1227 | else | |
1228 | { | |
1229 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
0e17387a KH |
1230 | if (found) |
1231 | detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1232 | } |
ff0dacd7 | 1233 | return 1; |
aa72b389 KH |
1234 | } |
1235 | ||
4ed46869 | 1236 | |
b73bfc1c | 1237 | static void |
971de7fb | 1238 | decode_coding_utf_8 (struct coding_system *coding) |
b73bfc1c | 1239 | { |
8f924df7 KH |
1240 | const unsigned char *src = coding->source + coding->consumed; |
1241 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1242 | const unsigned char *src_base; | |
69a80ea3 KH |
1243 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1244 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
d311d28c | 1245 | ptrdiff_t consumed_chars = 0, consumed_chars_base = 0; |
f10fe38f | 1246 | bool multibytep = coding->src_multibyte; |
a470d443 | 1247 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
f10fe38f PE |
1248 | bool eol_dos |
1249 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1250 | int byte_after_cr = -1; |
4ed46869 | 1251 | |
a470d443 KH |
1252 | if (bom != utf_without_bom) |
1253 | { | |
1254 | int c1, c2, c3; | |
1255 | ||
1256 | src_base = src; | |
1257 | ONE_MORE_BYTE (c1); | |
1258 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1259 | src = src_base; | |
1260 | else | |
1261 | { | |
159bd5a2 | 1262 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1263 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1264 | src = src_base; | |
1265 | else | |
1266 | { | |
159bd5a2 | 1267 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1268 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1269 | src = src_base; | |
1270 | else | |
1271 | { | |
1272 | if ((c1 != UTF_8_BOM_1) | |
1273 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1274 | src = src_base; | |
1275 | else | |
1276 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1277 | } | |
1278 | } | |
1279 | } | |
1280 | } | |
1281 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1282 | ||
df7492f9 | 1283 | while (1) |
b73bfc1c | 1284 | { |
df7492f9 | 1285 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1286 | |
df7492f9 KH |
1287 | src_base = src; |
1288 | consumed_chars_base = consumed_chars; | |
4af310db | 1289 | |
df7492f9 | 1290 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1291 | { |
1292 | if (byte_after_cr >= 0) | |
1293 | src_base--; | |
1294 | break; | |
1295 | } | |
df7492f9 | 1296 | |
119852e7 KH |
1297 | if (byte_after_cr >= 0) |
1298 | c1 = byte_after_cr, byte_after_cr = -1; | |
1299 | else | |
1300 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1301 | if (c1 < 0) |
1302 | { | |
1303 | c = - c1; | |
1304 | } | |
1a4990fb | 1305 | else if (UTF_8_1_OCTET_P (c1)) |
df7492f9 | 1306 | { |
2735d060 | 1307 | if (eol_dos && c1 == '\r') |
119852e7 | 1308 | ONE_MORE_BYTE (byte_after_cr); |
df7492f9 | 1309 | c = c1; |
4af310db | 1310 | } |
df7492f9 | 1311 | else |
4af310db | 1312 | { |
df7492f9 | 1313 | ONE_MORE_BYTE (c2); |
065e3595 | 1314 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1315 | goto invalid_code; |
1316 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1317 | { |
b0edb2c5 DL |
1318 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1319 | /* Reject overlong sequences here and below. Encoders | |
1320 | producing them are incorrect, they can be misleading, | |
1321 | and they mess up read/write invariance. */ | |
1322 | if (c < 128) | |
1323 | goto invalid_code; | |
4af310db | 1324 | } |
df7492f9 | 1325 | else |
aa72b389 | 1326 | { |
df7492f9 | 1327 | ONE_MORE_BYTE (c3); |
065e3595 | 1328 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1329 | goto invalid_code; |
1330 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1331 | { |
1332 | c = (((c1 & 0xF) << 12) | |
1333 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1334 | if (c < 0x800 |
1335 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1336 | goto invalid_code; |
1337 | } | |
df7492f9 KH |
1338 | else |
1339 | { | |
1340 | ONE_MORE_BYTE (c4); | |
065e3595 | 1341 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1342 | goto invalid_code; |
1343 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1344 | { |
df7492f9 KH |
1345 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1346 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1347 | if (c < 0x10000) |
1348 | goto invalid_code; | |
1349 | } | |
df7492f9 KH |
1350 | else |
1351 | { | |
1352 | ONE_MORE_BYTE (c5); | |
065e3595 | 1353 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1354 | goto invalid_code; |
1355 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1356 | { | |
1357 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1358 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1359 | | (c5 & 0x3F)); | |
b0edb2c5 | 1360 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1361 | goto invalid_code; |
1362 | } | |
1363 | else | |
1364 | goto invalid_code; | |
1365 | } | |
1366 | } | |
aa72b389 | 1367 | } |
b73bfc1c | 1368 | } |
df7492f9 KH |
1369 | |
1370 | *charbuf++ = c; | |
1371 | continue; | |
1372 | ||
1373 | invalid_code: | |
1374 | src = src_base; | |
1375 | consumed_chars = consumed_chars_base; | |
1376 | ONE_MORE_BYTE (c); | |
1377 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1378 | coding->errors++; | |
aa72b389 KH |
1379 | } |
1380 | ||
df7492f9 KH |
1381 | no_more_source: |
1382 | coding->consumed_char += consumed_chars_base; | |
1383 | coding->consumed = src_base - coding->source; | |
1384 | coding->charbuf_used = charbuf - coding->charbuf; | |
1385 | } | |
1386 | ||
1387 | ||
f10fe38f | 1388 | static bool |
971de7fb | 1389 | encode_coding_utf_8 (struct coding_system *coding) |
df7492f9 | 1390 | { |
f10fe38f | 1391 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
1392 | int *charbuf = coding->charbuf; |
1393 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1394 | unsigned char *dst = coding->destination + coding->produced; | |
1395 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c | 1396 | ptrdiff_t produced_chars = 0; |
df7492f9 KH |
1397 | int c; |
1398 | ||
a470d443 KH |
1399 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1400 | { | |
1401 | ASSURE_DESTINATION (3); | |
1402 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1403 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1404 | } | |
1405 | ||
df7492f9 | 1406 | if (multibytep) |
aa72b389 | 1407 | { |
df7492f9 KH |
1408 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1409 | ||
1410 | while (charbuf < charbuf_end) | |
b73bfc1c | 1411 | { |
df7492f9 | 1412 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1413 | |
df7492f9 KH |
1414 | ASSURE_DESTINATION (safe_room); |
1415 | c = *charbuf++; | |
28f67a95 KH |
1416 | if (CHAR_BYTE8_P (c)) |
1417 | { | |
1418 | c = CHAR_TO_BYTE8 (c); | |
1419 | EMIT_ONE_BYTE (c); | |
1420 | } | |
1421 | else | |
1422 | { | |
db274c7a | 1423 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1424 | for (p = str; p < pend; p++) |
1425 | EMIT_ONE_BYTE (*p); | |
1426 | } | |
b73bfc1c | 1427 | } |
aa72b389 | 1428 | } |
df7492f9 KH |
1429 | else |
1430 | { | |
1431 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1432 | ||
1433 | while (charbuf < charbuf_end) | |
b73bfc1c | 1434 | { |
df7492f9 KH |
1435 | ASSURE_DESTINATION (safe_room); |
1436 | c = *charbuf++; | |
f03caae0 KH |
1437 | if (CHAR_BYTE8_P (c)) |
1438 | *dst++ = CHAR_TO_BYTE8 (c); | |
1439 | else | |
db274c7a | 1440 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1441 | produced_chars++; |
4ed46869 KH |
1442 | } |
1443 | } | |
065e3595 | 1444 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1445 | coding->produced_char += produced_chars; |
1446 | coding->produced = dst - coding->destination; | |
1447 | return 0; | |
4ed46869 KH |
1448 | } |
1449 | ||
b73bfc1c | 1450 | |
df7492f9 | 1451 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f | 1452 | Return true if a text is encoded in one of UTF-16 based coding systems. */ |
aa72b389 | 1453 | |
df7492f9 KH |
1454 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1455 | (((val) & 0xFC00) == 0xD800) | |
1456 | ||
1457 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1458 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1459 | |
aa72b389 | 1460 | |
f10fe38f | 1461 | static bool |
cf84bb53 JB |
1462 | detect_coding_utf_16 (struct coding_system *coding, |
1463 | struct coding_detection_info *detect_info) | |
aa72b389 | 1464 | { |
ef1b0ba7 | 1465 | const unsigned char *src = coding->source; |
8f924df7 | 1466 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 1467 | bool multibytep = coding->src_multibyte; |
df7492f9 | 1468 | int c1, c2; |
aa72b389 | 1469 | |
ff0dacd7 | 1470 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1471 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1472 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1473 | { |
1474 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1475 | return 0; | |
1476 | } | |
24a73b0a | 1477 | |
f56a4450 | 1478 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1479 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1480 | { |
b49a1807 KH |
1481 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1482 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1483 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1484 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1485 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1486 | } |
df7492f9 | 1487 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1488 | { |
b49a1807 KH |
1489 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1490 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1491 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1492 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1493 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1494 | } | |
220eeac9 | 1495 | else if (c2 < 0) |
f56a4450 KH |
1496 | { |
1497 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1498 | return 0; | |
1499 | } | |
2f3cbb32 | 1500 | else |
24a73b0a | 1501 | { |
2f3cbb32 KH |
1502 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1503 | O is odd. If both are high, we assume binary data.*/ | |
1504 | unsigned char e[256], o[256]; | |
1505 | unsigned e_num = 1, o_num = 1; | |
1506 | ||
1507 | memset (e, 0, 256); | |
1508 | memset (o, 0, 256); | |
1509 | e[c1] = 1; | |
1510 | o[c2] = 1; | |
1511 | ||
cc13543e KH |
1512 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO |
1513 | |CATEGORY_MASK_UTF_16_BE | |
1514 | | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 | 1515 | |
7f1faf1c KH |
1516 | while ((detect_info->rejected & CATEGORY_MASK_UTF_16) |
1517 | != CATEGORY_MASK_UTF_16) | |
2f3cbb32 | 1518 | { |
f56a4450 | 1519 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1520 | if (c2 < 0) |
f56a4450 | 1521 | break; |
2f3cbb32 KH |
1522 | if (! e[c1]) |
1523 | { | |
1524 | e[c1] = 1; | |
1525 | e_num++; | |
cc13543e KH |
1526 | if (e_num >= 128) |
1527 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
2f3cbb32 KH |
1528 | } |
1529 | if (! o[c2]) | |
1530 | { | |
977b85f4 | 1531 | o[c2] = 1; |
2f3cbb32 | 1532 | o_num++; |
cc13543e KH |
1533 | if (o_num >= 128) |
1534 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
2f3cbb32 KH |
1535 | } |
1536 | } | |
2f3cbb32 | 1537 | return 0; |
ff0dacd7 | 1538 | } |
2f3cbb32 | 1539 | |
df7492f9 | 1540 | no_more_source: |
ff0dacd7 | 1541 | return 1; |
df7492f9 | 1542 | } |
aa72b389 | 1543 | |
df7492f9 | 1544 | static void |
971de7fb | 1545 | decode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1546 | { |
8f924df7 KH |
1547 | const unsigned char *src = coding->source + coding->consumed; |
1548 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1549 | const unsigned char *src_base; | |
69a80ea3 | 1550 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
1551 | /* We may produces at most 3 chars in one loop. */ |
1552 | int *charbuf_end = coding->charbuf + coding->charbuf_size - 2; | |
d311d28c | 1553 | ptrdiff_t consumed_chars = 0, consumed_chars_base = 0; |
f10fe38f | 1554 | bool multibytep = coding->src_multibyte; |
a470d443 | 1555 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1556 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1557 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
f10fe38f PE |
1558 | bool eol_dos |
1559 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1560 | int byte_after_cr1 = -1, byte_after_cr2 = -1; |
df7492f9 | 1561 | |
a470d443 | 1562 | if (bom == utf_with_bom) |
aa72b389 | 1563 | { |
df7492f9 | 1564 | int c, c1, c2; |
4af310db | 1565 | |
aa72b389 | 1566 | src_base = src; |
df7492f9 KH |
1567 | ONE_MORE_BYTE (c1); |
1568 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1569 | c = (c1 << 8) | c2; |
aa72b389 | 1570 | |
b49a1807 KH |
1571 | if (endian == utf_16_big_endian |
1572 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1573 | { |
b49a1807 KH |
1574 | /* The first two bytes are not BOM. Treat them as bytes |
1575 | for a normal character. */ | |
1576 | src = src_base; | |
1577 | coding->errors++; | |
aa72b389 | 1578 | } |
a470d443 | 1579 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1580 | } |
a470d443 | 1581 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1582 | { |
1583 | /* We have already tried to detect BOM and failed in | |
1584 | detect_coding. */ | |
a470d443 | 1585 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1586 | } |
aa72b389 | 1587 | |
df7492f9 KH |
1588 | while (1) |
1589 | { | |
1590 | int c, c1, c2; | |
1591 | ||
1592 | src_base = src; | |
1593 | consumed_chars_base = consumed_chars; | |
1594 | ||
df80c7f0 | 1595 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1596 | { |
1597 | if (byte_after_cr1 >= 0) | |
1598 | src_base -= 2; | |
1599 | break; | |
1600 | } | |
df7492f9 | 1601 | |
119852e7 KH |
1602 | if (byte_after_cr1 >= 0) |
1603 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1604 | else | |
1605 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1606 | if (c1 < 0) |
1607 | { | |
1608 | *charbuf++ = -c1; | |
1609 | continue; | |
1610 | } | |
119852e7 KH |
1611 | if (byte_after_cr2 >= 0) |
1612 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1613 | else | |
1614 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1615 | if (c2 < 0) |
1616 | { | |
1617 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1618 | *charbuf++ = -c2; | |
1619 | continue; | |
1620 | } | |
df7492f9 | 1621 | c = (endian == utf_16_big_endian |
e19c3639 | 1622 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1623 | |
df7492f9 | 1624 | if (surrogate) |
fd3ae0b9 | 1625 | { |
df7492f9 | 1626 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1627 | { |
df7492f9 KH |
1628 | if (endian == utf_16_big_endian) |
1629 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1630 | else | |
1631 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1632 | *charbuf++ = c1; | |
1633 | *charbuf++ = c2; | |
1634 | coding->errors++; | |
1635 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1636 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1637 | else |
df7492f9 | 1638 | *charbuf++ = c; |
fd3ae0b9 KH |
1639 | } |
1640 | else | |
df7492f9 KH |
1641 | { |
1642 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1643 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1644 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1645 | } |
fd3ae0b9 | 1646 | } |
aa72b389 | 1647 | else |
df7492f9 KH |
1648 | { |
1649 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1650 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1651 | else | |
119852e7 | 1652 | { |
2735d060 | 1653 | if (eol_dos && c == '\r') |
119852e7 KH |
1654 | { |
1655 | ONE_MORE_BYTE (byte_after_cr1); | |
1656 | ONE_MORE_BYTE (byte_after_cr2); | |
1657 | } | |
1658 | *charbuf++ = c; | |
1659 | } | |
8f924df7 | 1660 | } |
aa72b389 | 1661 | } |
df7492f9 KH |
1662 | |
1663 | no_more_source: | |
1664 | coding->consumed_char += consumed_chars_base; | |
1665 | coding->consumed = src_base - coding->source; | |
1666 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1667 | } |
b73bfc1c | 1668 | |
f10fe38f | 1669 | static bool |
971de7fb | 1670 | encode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1671 | { |
f10fe38f | 1672 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
1673 | int *charbuf = coding->charbuf; |
1674 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1675 | unsigned char *dst = coding->destination + coding->produced; | |
1676 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1677 | int safe_room = 8; | |
a470d443 | 1678 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
f10fe38f | 1679 | bool big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
d311d28c | 1680 | ptrdiff_t produced_chars = 0; |
df7492f9 | 1681 | int c; |
4ed46869 | 1682 | |
a470d443 | 1683 | if (bom != utf_without_bom) |
df7492f9 KH |
1684 | { |
1685 | ASSURE_DESTINATION (safe_room); | |
1686 | if (big_endian) | |
df7492f9 | 1687 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1688 | else |
1689 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1690 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1691 | } |
1692 | ||
1693 | while (charbuf < charbuf_end) | |
1694 | { | |
1695 | ASSURE_DESTINATION (safe_room); | |
1696 | c = *charbuf++; | |
60afa08d | 1697 | if (c > MAX_UNICODE_CHAR) |
e19c3639 | 1698 | c = coding->default_char; |
df7492f9 KH |
1699 | |
1700 | if (c < 0x10000) | |
1701 | { | |
1702 | if (big_endian) | |
1703 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1704 | else | |
1705 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1706 | } | |
1707 | else | |
1708 | { | |
1709 | int c1, c2; | |
1710 | ||
1711 | c -= 0x10000; | |
1712 | c1 = (c >> 10) + 0xD800; | |
1713 | c2 = (c & 0x3FF) + 0xDC00; | |
1714 | if (big_endian) | |
1715 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1716 | else | |
1717 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1718 | } | |
1719 | } | |
065e3595 | 1720 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1721 | coding->produced = dst - coding->destination; |
1722 | coding->produced_char += produced_chars; | |
1723 | return 0; | |
1724 | } | |
1725 | ||
1726 | \f | |
1727 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1728 | ||
1729 | /* Emacs' internal format for representation of multiple character | |
1730 | sets is a kind of multi-byte encoding, i.e. characters are | |
1731 | represented by variable-length sequences of one-byte codes. | |
1732 | ||
1733 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1734 | represented by one-byte sequences which are their ASCII codes, in | |
1735 | the range 0x00 through 0x7F. | |
1736 | ||
1737 | 8-bit characters of the range 0x80..0x9F are represented by | |
1738 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1739 | code + 0x20). | |
1740 | ||
1741 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1742 | one-byte sequences which are their 8-bit code. | |
1743 | ||
1744 | The other characters are represented by a sequence of `base | |
1745 | leading-code', optional `extended leading-code', and one or two | |
1746 | `position-code's. The length of the sequence is determined by the | |
1747 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1748 | whereas extended leading-code and position-code take the range 0xA0 | |
1749 | through 0xFF. See `charset.h' for more details about leading-code | |
1750 | and position-code. | |
1751 | ||
1752 | --- CODE RANGE of Emacs' internal format --- | |
1753 | character set range | |
1754 | ------------- ----- | |
1755 | ascii 0x00..0x7F | |
1756 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1757 | eight-bit-graphic 0xA0..0xBF | |
1758 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1759 | --------------------------------------------- | |
1760 | ||
1761 | As this is the internal character representation, the format is | |
1762 | usually not used externally (i.e. in a file or in a data sent to a | |
1763 | process). But, it is possible to have a text externally in this | |
1764 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1765 | ||
1766 | In that case, a sequence of one-byte codes has a slightly different | |
1767 | form. | |
1768 | ||
1769 | At first, all characters in eight-bit-control are represented by | |
1770 | one-byte sequences which are their 8-bit code. | |
1771 | ||
1772 | Next, character composition data are represented by the byte | |
1773 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1774 | where, | |
e951386e | 1775 | METHOD is 0xF2 plus one of composition method (enum |
df7492f9 KH |
1776 | composition_method), |
1777 | ||
1778 | BYTES is 0xA0 plus a byte length of this composition data, | |
1779 | ||
e951386e | 1780 | CHARS is 0xA0 plus a number of characters composed by this |
df7492f9 KH |
1781 | data, |
1782 | ||
ad1746f5 | 1783 | COMPONENTs are characters of multibyte form or composition |
df7492f9 KH |
1784 | rules encoded by two-byte of ASCII codes. |
1785 | ||
1786 | In addition, for backward compatibility, the following formats are | |
1787 | also recognized as composition data on decoding. | |
1788 | ||
1789 | 0x80 MSEQ ... | |
1790 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1791 | ||
1792 | Here, | |
1793 | MSEQ is a multibyte form but in these special format: | |
1794 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1795 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1796 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1797 | represents a composition rule. | |
1798 | */ | |
1799 | ||
1800 | char emacs_mule_bytes[256]; | |
1801 | ||
e951386e KH |
1802 | |
1803 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 1804 | Return true if a text is encoded in 'emacs-mule'. */ |
e951386e | 1805 | |
f10fe38f | 1806 | static bool |
cf84bb53 JB |
1807 | detect_coding_emacs_mule (struct coding_system *coding, |
1808 | struct coding_detection_info *detect_info) | |
e951386e KH |
1809 | { |
1810 | const unsigned char *src = coding->source, *src_base; | |
1811 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
f10fe38f | 1812 | bool multibytep = coding->src_multibyte; |
d311d28c | 1813 | ptrdiff_t consumed_chars = 0; |
e951386e KH |
1814 | int c; |
1815 | int found = 0; | |
1816 | ||
1817 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | |
1818 | /* A coding system of this category is always ASCII compatible. */ | |
1819 | src += coding->head_ascii; | |
1820 | ||
1821 | while (1) | |
1822 | { | |
1823 | src_base = src; | |
1824 | ONE_MORE_BYTE (c); | |
1825 | if (c < 0) | |
1826 | continue; | |
1827 | if (c == 0x80) | |
1828 | { | |
1829 | /* Perhaps the start of composite character. We simply skip | |
1830 | it because analyzing it is too heavy for detecting. But, | |
1831 | at least, we check that the composite character | |
1832 | constitutes of more than 4 bytes. */ | |
2735d060 | 1833 | const unsigned char *src_start; |
e951386e KH |
1834 | |
1835 | repeat: | |
2735d060 | 1836 | src_start = src; |
e951386e KH |
1837 | do |
1838 | { | |
1839 | ONE_MORE_BYTE (c); | |
1840 | } | |
1841 | while (c >= 0xA0); | |
1842 | ||
2735d060 | 1843 | if (src - src_start <= 4) |
e951386e KH |
1844 | break; |
1845 | found = CATEGORY_MASK_EMACS_MULE; | |
1846 | if (c == 0x80) | |
1847 | goto repeat; | |
1848 | } | |
1849 | ||
1850 | if (c < 0x80) | |
1851 | { | |
1852 | if (c < 0x20 | |
1853 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1854 | break; | |
1855 | } | |
1856 | else | |
1857 | { | |
396475b7 | 1858 | int more_bytes = emacs_mule_bytes[c] - 1; |
e951386e KH |
1859 | |
1860 | while (more_bytes > 0) | |
1861 | { | |
1862 | ONE_MORE_BYTE (c); | |
1863 | if (c < 0xA0) | |
1864 | { | |
1865 | src--; /* Unread the last byte. */ | |
1866 | break; | |
1867 | } | |
1868 | more_bytes--; | |
1869 | } | |
1870 | if (more_bytes != 0) | |
1871 | break; | |
1872 | found = CATEGORY_MASK_EMACS_MULE; | |
1873 | } | |
1874 | } | |
1875 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1876 | return 0; | |
1877 | ||
1878 | no_more_source: | |
1879 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | |
1880 | { | |
1881 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1882 | return 0; | |
1883 | } | |
1884 | detect_info->found |= found; | |
1885 | return 1; | |
1886 | } | |
1887 | ||
1888 | ||
1889 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | |
1890 | character. If CMP_STATUS indicates that we must expect MSEQ or | |
1891 | RULE described above, decode it and return the negative value of | |
685ebdc8 | 1892 | the decoded character or rule. If an invalid byte is found, return |
e951386e KH |
1893 | -1. If SRC is too short, return -2. */ |
1894 | ||
e2f1bab9 | 1895 | static int |
cf84bb53 JB |
1896 | emacs_mule_char (struct coding_system *coding, const unsigned char *src, |
1897 | int *nbytes, int *nchars, int *id, | |
1898 | struct composition_status *cmp_status) | |
df7492f9 | 1899 | { |
8f924df7 KH |
1900 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1901 | const unsigned char *src_base = src; | |
f10fe38f | 1902 | bool multibytep = coding->src_multibyte; |
2735d060 | 1903 | int charset_ID; |
df7492f9 KH |
1904 | unsigned code; |
1905 | int c; | |
1906 | int consumed_chars = 0; | |
f10fe38f | 1907 | bool mseq_found = 0; |
df7492f9 KH |
1908 | |
1909 | ONE_MORE_BYTE (c); | |
065e3595 | 1910 | if (c < 0) |
df7492f9 | 1911 | { |
065e3595 | 1912 | c = -c; |
2735d060 | 1913 | charset_ID = emacs_mule_charset[0]; |
065e3595 KH |
1914 | } |
1915 | else | |
1916 | { | |
4d41e8b7 KH |
1917 | if (c >= 0xA0) |
1918 | { | |
e951386e KH |
1919 | if (cmp_status->state != COMPOSING_NO |
1920 | && cmp_status->old_form) | |
4d41e8b7 | 1921 | { |
e951386e KH |
1922 | if (cmp_status->state == COMPOSING_CHAR) |
1923 | { | |
1924 | if (c == 0xA0) | |
1925 | { | |
1926 | ONE_MORE_BYTE (c); | |
1927 | c -= 0x80; | |
1928 | if (c < 0) | |
1929 | goto invalid_code; | |
1930 | } | |
1931 | else | |
1932 | c -= 0x20; | |
1933 | mseq_found = 1; | |
1934 | } | |
1935 | else | |
1936 | { | |
1937 | *nbytes = src - src_base; | |
1938 | *nchars = consumed_chars; | |
1939 | return -c; | |
1940 | } | |
4d41e8b7 KH |
1941 | } |
1942 | else | |
e951386e | 1943 | goto invalid_code; |
4d41e8b7 KH |
1944 | } |
1945 | ||
065e3595 | 1946 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 1947 | { |
065e3595 | 1948 | case 2: |
2735d060 | 1949 | if ((charset_ID = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
1950 | goto invalid_code; |
1951 | ONE_MORE_BYTE (c); | |
9ffd559c | 1952 | if (c < 0xA0) |
065e3595 | 1953 | goto invalid_code; |
df7492f9 | 1954 | code = c & 0x7F; |
065e3595 KH |
1955 | break; |
1956 | ||
1957 | case 3: | |
1958 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
1959 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
1960 | { | |
1961 | ONE_MORE_BYTE (c); | |
2735d060 | 1962 | if (c < 0xA0 || (charset_ID = emacs_mule_charset[c]) < 0) |
065e3595 KH |
1963 | goto invalid_code; |
1964 | ONE_MORE_BYTE (c); | |
9ffd559c | 1965 | if (c < 0xA0) |
065e3595 KH |
1966 | goto invalid_code; |
1967 | code = c & 0x7F; | |
1968 | } | |
1969 | else | |
1970 | { | |
2735d060 | 1971 | if ((charset_ID = emacs_mule_charset[c]) < 0) |
065e3595 KH |
1972 | goto invalid_code; |
1973 | ONE_MORE_BYTE (c); | |
9ffd559c | 1974 | if (c < 0xA0) |
065e3595 KH |
1975 | goto invalid_code; |
1976 | code = (c & 0x7F) << 8; | |
1977 | ONE_MORE_BYTE (c); | |
9ffd559c | 1978 | if (c < 0xA0) |
065e3595 KH |
1979 | goto invalid_code; |
1980 | code |= c & 0x7F; | |
1981 | } | |
1982 | break; | |
1983 | ||
1984 | case 4: | |
1985 | ONE_MORE_BYTE (c); | |
2735d060 | 1986 | if (c < 0 || (charset_ID = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
1987 | goto invalid_code; |
1988 | ONE_MORE_BYTE (c); | |
9ffd559c | 1989 | if (c < 0xA0) |
065e3595 | 1990 | goto invalid_code; |
781d7a48 | 1991 | code = (c & 0x7F) << 8; |
df7492f9 | 1992 | ONE_MORE_BYTE (c); |
9ffd559c | 1993 | if (c < 0xA0) |
065e3595 | 1994 | goto invalid_code; |
df7492f9 | 1995 | code |= c & 0x7F; |
065e3595 | 1996 | break; |
df7492f9 | 1997 | |
065e3595 KH |
1998 | case 1: |
1999 | code = c; | |
2735d060 | 2000 | charset_ID = ASCII_BYTE_P (code) ? charset_ascii : charset_eight_bit; |
065e3595 | 2001 | break; |
df7492f9 | 2002 | |
065e3595 | 2003 | default: |
1088b922 | 2004 | emacs_abort (); |
065e3595 | 2005 | } |
b84ae584 | 2006 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
2735d060 | 2007 | CHARSET_FROM_ID (charset_ID), code, c); |
065e3595 KH |
2008 | if (c < 0) |
2009 | goto invalid_code; | |
df7492f9 | 2010 | } |
df7492f9 KH |
2011 | *nbytes = src - src_base; |
2012 | *nchars = consumed_chars; | |
ff0dacd7 | 2013 | if (id) |
2735d060 | 2014 | *id = charset_ID; |
e951386e | 2015 | return (mseq_found ? -c : c); |
df7492f9 KH |
2016 | |
2017 | no_more_source: | |
2018 | return -2; | |
2019 | ||
2020 | invalid_code: | |
2021 | return -1; | |
2022 | } | |
2023 | ||
2024 | ||
e951386e | 2025 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
df7492f9 | 2026 | |
e951386e KH |
2027 | /* Handle these composition sequence ('|': the end of header elements, |
2028 | BYTES and CHARS >= 0xA0): | |
df7492f9 | 2029 | |
e951386e KH |
2030 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
2031 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... | |
2032 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... | |
df7492f9 | 2033 | |
e951386e | 2034 | and these old form: |
1a4990fb | 2035 | |
e951386e KH |
2036 | (4) relative composition: 0x80 | MSEQ ... MSEQ |
2037 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ | |
df7492f9 | 2038 | |
e951386e KH |
2039 | When the starter 0x80 and the following header elements are found, |
2040 | this annotation header is produced. | |
df7492f9 | 2041 | |
e951386e | 2042 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
df7492f9 | 2043 | |
e951386e KH |
2044 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
2045 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). | |
df7492f9 | 2046 | |
e951386e KH |
2047 | Then, upon reading the following elements, these codes are produced |
2048 | until the composition end is found: | |
df7492f9 | 2049 | |
e951386e KH |
2050 | (1) CHAR ... CHAR |
2051 | (2) ALT ... ALT CHAR ... CHAR | |
2052 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR | |
2053 | (4) CHAR ... CHAR | |
2054 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
4ed46869 | 2055 | |
e951386e KH |
2056 | When the composition end is found, LENGTH and NCHARS in the |
2057 | annotation header is updated as below: | |
b73bfc1c | 2058 | |
e951386e KH |
2059 | (1) LENGTH: unchanged, NCHARS: unchanged |
2060 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2061 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2062 | (4) LENGTH: unchanged, NCHARS: number of CHARs | |
2063 | (5) LENGTH: unchanged, NCHARS: number of CHARs | |
df7492f9 | 2064 | |
e951386e KH |
2065 | If an error is found while composing, the annotation header is |
2066 | changed to the original composition header (plus filler -1s) as | |
2067 | below: | |
2068 | ||
2069 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] | |
2070 | (5) [ 0x80 0xFF -1 -1- -1 ] | |
2071 | ||
2072 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
2073 | byte sequence as below: | |
2074 | o the original byte sequence is B: [ B -1 ] | |
2075 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
2076 | ||
2077 | Most of the routines are implemented by macros because many | |
2078 | variables and labels in the caller decode_coding_emacs_mule must be | |
2079 | accessible, and they are usually called just once (thus doesn't | |
2080 | increase the size of compiled object). */ | |
2081 | ||
2082 | /* Decode a composition rule represented by C as a component of | |
2083 | composition sequence of Emacs 20 style. Set RULE to the decoded | |
2084 | rule. */ | |
2085 | ||
2086 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ | |
df7492f9 | 2087 | do { \ |
e951386e KH |
2088 | int gref, nref; \ |
2089 | \ | |
4d41e8b7 | 2090 | c -= 0xA0; \ |
df7492f9 KH |
2091 | if (c < 0 || c >= 81) \ |
2092 | goto invalid_code; \ | |
df7492f9 | 2093 | gref = c / 9, nref = c % 9; \ |
e951386e KH |
2094 | if (gref == 4) gref = 10; \ |
2095 | if (nref == 4) nref = 10; \ | |
2096 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
df7492f9 KH |
2097 | } while (0) |
2098 | ||
2099 | ||
e951386e KH |
2100 | /* Decode a composition rule represented by C and the following byte |
2101 | at SRC as a component of composition sequence of Emacs 21 style. | |
2102 | Set RULE to the decoded rule. */ | |
781d7a48 | 2103 | |
e951386e | 2104 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
781d7a48 KH |
2105 | do { \ |
2106 | int gref, nref; \ | |
e951386e KH |
2107 | \ |
2108 | gref = c - 0x20; \ | |
2109 | if (gref < 0 || gref >= 81) \ | |
781d7a48 | 2110 | goto invalid_code; \ |
e951386e KH |
2111 | ONE_MORE_BYTE (c); \ |
2112 | nref = c - 0x20; \ | |
2113 | if (nref < 0 || nref >= 81) \ | |
781d7a48 | 2114 | goto invalid_code; \ |
e951386e | 2115 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
781d7a48 KH |
2116 | } while (0) |
2117 | ||
2118 | ||
e951386e KH |
2119 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
2120 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | |
2121 | byte length of this composition information, CHARS is the number of | |
2122 | characters composed by this composition. */ | |
2123 | ||
2124 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | |
aa72b389 | 2125 | do { \ |
781d7a48 | 2126 | enum composition_method method = c - 0xF2; \ |
df7492f9 | 2127 | int nbytes, nchars; \ |
e951386e | 2128 | \ |
df7492f9 | 2129 | ONE_MORE_BYTE (c); \ |
065e3595 KH |
2130 | if (c < 0) \ |
2131 | goto invalid_code; \ | |
df7492f9 | 2132 | nbytes = c - 0xA0; \ |
e951386e | 2133 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
df7492f9 KH |
2134 | goto invalid_code; \ |
2135 | ONE_MORE_BYTE (c); \ | |
2136 | nchars = c - 0xA0; \ | |
e951386e KH |
2137 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
2138 | goto invalid_code; \ | |
2139 | cmp_status->old_form = 0; \ | |
2140 | cmp_status->method = method; \ | |
2141 | if (method == COMPOSITION_RELATIVE) \ | |
2142 | cmp_status->state = COMPOSING_CHAR; \ | |
2143 | else \ | |
2144 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ | |
2145 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2146 | cmp_status->nchars = nchars; \ | |
2147 | cmp_status->ncomps = nbytes - 4; \ | |
2148 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ | |
aa72b389 | 2149 | } while (0) |
93dec019 | 2150 | |
aa72b389 | 2151 | |
e951386e KH |
2152 | /* Start of Emacs 20 style format for relative composition. */ |
2153 | ||
2154 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ | |
2155 | do { \ | |
2156 | cmp_status->old_form = 1; \ | |
2157 | cmp_status->method = COMPOSITION_RELATIVE; \ | |
2158 | cmp_status->state = COMPOSING_CHAR; \ | |
2159 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2160 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2161 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
2162 | } while (0) | |
2163 | ||
2164 | ||
2165 | /* Start of Emacs 20 style format for rule-base composition. */ | |
2166 | ||
2167 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | |
2168 | do { \ | |
2169 | cmp_status->old_form = 1; \ | |
2170 | cmp_status->method = COMPOSITION_WITH_RULE; \ | |
2171 | cmp_status->state = COMPOSING_CHAR; \ | |
2172 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2173 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2174 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
df7492f9 KH |
2175 | } while (0) |
2176 | ||
2177 | ||
e951386e KH |
2178 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ |
2179 | do { \ | |
2180 | const unsigned char *current_src = src; \ | |
2181 | \ | |
2182 | ONE_MORE_BYTE (c); \ | |
2183 | if (c < 0) \ | |
2184 | goto invalid_code; \ | |
2185 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | |
2186 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | |
2187 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | |
2188 | else if (c < 0xA0) \ | |
2189 | goto invalid_code; \ | |
2190 | else if (c < 0xC0) \ | |
2191 | { \ | |
2192 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | |
2193 | /* Re-read C as a composition component. */ \ | |
2194 | src = current_src; \ | |
2195 | } \ | |
2196 | else if (c == 0xFF) \ | |
2197 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | |
2198 | else \ | |
2199 | goto invalid_code; \ | |
2200 | } while (0) | |
2201 | ||
2202 | #define EMACS_MULE_COMPOSITION_END() \ | |
df7492f9 | 2203 | do { \ |
e951386e | 2204 | int idx = - cmp_status->length; \ |
4d41e8b7 | 2205 | \ |
e951386e KH |
2206 | if (cmp_status->old_form) \ |
2207 | charbuf[idx + 2] = cmp_status->nchars; \ | |
2208 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ | |
2209 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ | |
2210 | cmp_status->state = COMPOSING_NO; \ | |
2211 | } while (0) | |
2212 | ||
2213 | ||
2214 | static int | |
cf84bb53 JB |
2215 | emacs_mule_finish_composition (int *charbuf, |
2216 | struct composition_status *cmp_status) | |
e951386e KH |
2217 | { |
2218 | int idx = - cmp_status->length; | |
2219 | int new_chars; | |
2220 | ||
2221 | if (cmp_status->old_form && cmp_status->nchars > 0) | |
2222 | { | |
2223 | charbuf[idx + 2] = cmp_status->nchars; | |
2224 | new_chars = 0; | |
2225 | if (cmp_status->method == COMPOSITION_WITH_RULE | |
2226 | && cmp_status->state == COMPOSING_CHAR) | |
2227 | { | |
2228 | /* The last rule was invalid. */ | |
2229 | int rule = charbuf[-1] + 0xA0; | |
2230 | ||
2231 | charbuf[-2] = BYTE8_TO_CHAR (rule); | |
2232 | charbuf[-1] = -1; | |
2233 | new_chars = 1; | |
2234 | } | |
2235 | } | |
2236 | else | |
2237 | { | |
2238 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | |
2239 | ||
2240 | if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2241 | { | |
2242 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | |
2243 | charbuf[idx++] = -3; | |
2244 | charbuf[idx++] = 0; | |
2245 | new_chars = 1; | |
2246 | } | |
2247 | else | |
2248 | { | |
2249 | int nchars = charbuf[idx + 1] + 0xA0; | |
2250 | int nbytes = charbuf[idx + 2] + 0xA0; | |
2251 | ||
2252 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | |
2253 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | |
2254 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | |
2255 | charbuf[idx++] = -1; | |
2256 | new_chars = 4; | |
2257 | } | |
2258 | } | |
2259 | cmp_status->state = COMPOSING_NO; | |
2260 | return new_chars; | |
2261 | } | |
2262 | ||
2263 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | |
2264 | do { \ | |
2265 | if (cmp_status->state != COMPOSING_NO) \ | |
2266 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | |
df7492f9 KH |
2267 | } while (0) |
2268 | ||
aa72b389 KH |
2269 | |
2270 | static void | |
971de7fb | 2271 | decode_coding_emacs_mule (struct coding_system *coding) |
aa72b389 | 2272 | { |
8f924df7 KH |
2273 | const unsigned char *src = coding->source + coding->consumed; |
2274 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2275 | const unsigned char *src_base; | |
69a80ea3 | 2276 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
2277 | /* We may produce two annotations (charset and composition) in one |
2278 | loop and one more charset annotation at the end. */ | |
69a80ea3 | 2279 | int *charbuf_end |
15cbd324 EZ |
2280 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3) |
2281 | /* We can produce up to 2 characters in a loop. */ | |
2282 | - 1; | |
d311d28c | 2283 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 2284 | bool multibytep = coding->src_multibyte; |
d311d28c PE |
2285 | ptrdiff_t char_offset = coding->produced_char; |
2286 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 2287 | int last_id = charset_ascii; |
f10fe38f PE |
2288 | bool eol_dos |
2289 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 2290 | int byte_after_cr = -1; |
e951386e | 2291 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; |
aa72b389 | 2292 | |
e951386e KH |
2293 | if (cmp_status->state != COMPOSING_NO) |
2294 | { | |
2295 | int i; | |
2296 | ||
15cbd324 | 2297 | if (charbuf_end - charbuf < cmp_status->length) |
1088b922 | 2298 | emacs_abort (); |
e951386e KH |
2299 | for (i = 0; i < cmp_status->length; i++) |
2300 | *charbuf++ = cmp_status->carryover[i]; | |
2301 | coding->annotated = 1; | |
2302 | } | |
2303 | ||
aa72b389 KH |
2304 | while (1) |
2305 | { | |
ee05f961 | 2306 | int c, id IF_LINT (= 0); |
df7492f9 | 2307 | |
aa72b389 | 2308 | src_base = src; |
df7492f9 KH |
2309 | consumed_chars_base = consumed_chars; |
2310 | ||
2311 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2312 | { |
2313 | if (byte_after_cr >= 0) | |
2314 | src_base--; | |
2315 | break; | |
2316 | } | |
aa72b389 | 2317 | |
119852e7 KH |
2318 | if (byte_after_cr >= 0) |
2319 | c = byte_after_cr, byte_after_cr = -1; | |
2320 | else | |
2321 | ONE_MORE_BYTE (c); | |
e951386e KH |
2322 | |
2323 | if (c < 0 || c == 0x80) | |
065e3595 | 2324 | { |
e951386e KH |
2325 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
2326 | if (c < 0) | |
2327 | { | |
2328 | *charbuf++ = -c; | |
2329 | char_offset++; | |
2330 | } | |
2331 | else | |
2332 | DECODE_EMACS_MULE_COMPOSITION_START (); | |
2333 | continue; | |
065e3595 | 2334 | } |
e951386e KH |
2335 | |
2336 | if (c < 0x80) | |
aa72b389 | 2337 | { |
2735d060 | 2338 | if (eol_dos && c == '\r') |
119852e7 | 2339 | ONE_MORE_BYTE (byte_after_cr); |
e951386e KH |
2340 | id = charset_ascii; |
2341 | if (cmp_status->state != COMPOSING_NO) | |
2342 | { | |
2343 | if (cmp_status->old_form) | |
2344 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2345 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2346 | cmp_status->ncomps--; | |
2347 | } | |
2348 | } | |
2349 | else | |
2350 | { | |
ee05f961 | 2351 | int nchars IF_LINT (= 0), nbytes IF_LINT (= 0); |
75f80e63 EZ |
2352 | /* emacs_mule_char can load a charset map from a file, which |
2353 | allocates a large structure and might cause buffer text | |
2354 | to be relocated as result. Thus, we need to remember the | |
ad1746f5 | 2355 | original pointer to buffer text, and fix up all related |
75f80e63 EZ |
2356 | pointers after the call. */ |
2357 | const unsigned char *orig = coding->source; | |
d311d28c | 2358 | ptrdiff_t offset; |
e951386e KH |
2359 | |
2360 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, | |
2361 | cmp_status); | |
75f80e63 EZ |
2362 | offset = coding->source - orig; |
2363 | if (offset) | |
2364 | { | |
2365 | src += offset; | |
2366 | src_base += offset; | |
2367 | src_end += offset; | |
2368 | } | |
e951386e KH |
2369 | if (c < 0) |
2370 | { | |
2371 | if (c == -1) | |
2372 | goto invalid_code; | |
2373 | if (c == -2) | |
2374 | break; | |
2375 | } | |
2376 | src = src_base + nbytes; | |
2377 | consumed_chars = consumed_chars_base + nchars; | |
2378 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2379 | cmp_status->ncomps -= nchars; | |
2380 | } | |
2381 | ||
ad1746f5 | 2382 | /* Now if C >= 0, we found a normally encoded character, if C < |
e951386e KH |
2383 | 0, we found an old-style composition component character or |
2384 | rule. */ | |
2385 | ||
2386 | if (cmp_status->state == COMPOSING_NO) | |
2387 | { | |
2388 | if (last_id != id) | |
2389 | { | |
2390 | if (last_id != charset_ascii) | |
2391 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, | |
2392 | last_id); | |
2393 | last_id = id; | |
2394 | last_offset = char_offset; | |
2395 | } | |
df7492f9 KH |
2396 | *charbuf++ = c; |
2397 | char_offset++; | |
aa72b389 | 2398 | } |
e951386e | 2399 | else if (cmp_status->state == COMPOSING_CHAR) |
df7492f9 | 2400 | { |
e951386e KH |
2401 | if (cmp_status->old_form) |
2402 | { | |
2403 | if (c >= 0) | |
2404 | { | |
2405 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2406 | *charbuf++ = c; | |
2407 | char_offset++; | |
2408 | } | |
2409 | else | |
2410 | { | |
2411 | *charbuf++ = -c; | |
2412 | cmp_status->nchars++; | |
2413 | cmp_status->length++; | |
2414 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | |
2415 | EMACS_MULE_COMPOSITION_END (); | |
2416 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2417 | cmp_status->state = COMPOSING_RULE; | |
2418 | } | |
2419 | } | |
df7492f9 | 2420 | else |
e951386e KH |
2421 | { |
2422 | *charbuf++ = c; | |
2423 | cmp_status->length++; | |
2424 | cmp_status->nchars--; | |
2425 | if (cmp_status->nchars == 0) | |
2426 | EMACS_MULE_COMPOSITION_END (); | |
2427 | } | |
df7492f9 | 2428 | } |
e951386e | 2429 | else if (cmp_status->state == COMPOSING_RULE) |
df7492f9 | 2430 | { |
e951386e | 2431 | int rule; |
ff0dacd7 | 2432 | |
e951386e | 2433 | if (c >= 0) |
df7492f9 | 2434 | { |
e951386e KH |
2435 | EMACS_MULE_COMPOSITION_END (); |
2436 | *charbuf++ = c; | |
2437 | char_offset++; | |
df7492f9 | 2438 | } |
e951386e | 2439 | else |
ff0dacd7 | 2440 | { |
e951386e KH |
2441 | c = -c; |
2442 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | |
2443 | if (rule < 0) | |
2444 | goto invalid_code; | |
2445 | *charbuf++ = -2; | |
2446 | *charbuf++ = rule; | |
2447 | cmp_status->length += 2; | |
2448 | cmp_status->state = COMPOSING_CHAR; | |
ff0dacd7 | 2449 | } |
e951386e KH |
2450 | } |
2451 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | |
2452 | { | |
df7492f9 | 2453 | *charbuf++ = c; |
e951386e KH |
2454 | cmp_status->length++; |
2455 | if (cmp_status->ncomps == 0) | |
2456 | cmp_status->state = COMPOSING_CHAR; | |
2457 | else if (cmp_status->ncomps > 0) | |
2458 | { | |
2459 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | |
2460 | cmp_status->state = COMPOSING_COMPONENT_RULE; | |
2461 | } | |
2462 | else | |
2463 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 2464 | } |
e951386e KH |
2465 | else /* COMPOSING_COMPONENT_RULE */ |
2466 | { | |
2467 | int rule; | |
2468 | ||
2469 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | |
2470 | if (rule < 0) | |
2471 | goto invalid_code; | |
2472 | *charbuf++ = -2; | |
2473 | *charbuf++ = rule; | |
2474 | cmp_status->length += 2; | |
2475 | cmp_status->ncomps--; | |
2476 | if (cmp_status->ncomps > 0) | |
2477 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | |
2478 | else | |
2479 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2480 | } | |
2481 | continue; | |
2482 | ||
df7492f9 | 2483 | invalid_code: |
e951386e | 2484 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
df7492f9 KH |
2485 | src = src_base; |
2486 | consumed_chars = consumed_chars_base; | |
2487 | ONE_MORE_BYTE (c); | |
2488 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2489 | char_offset++; |
df7492f9 KH |
2490 | coding->errors++; |
2491 | } | |
2492 | ||
2493 | no_more_source: | |
e951386e KH |
2494 | if (cmp_status->state != COMPOSING_NO) |
2495 | { | |
2496 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
2497 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2498 | else | |
2499 | { | |
2500 | int i; | |
2501 | ||
2502 | charbuf -= cmp_status->length; | |
2503 | for (i = 0; i < cmp_status->length; i++) | |
2504 | cmp_status->carryover[i] = charbuf[i]; | |
2505 | } | |
2506 | } | |
ff0dacd7 | 2507 | if (last_id != charset_ascii) |
69a80ea3 | 2508 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2509 | coding->consumed_char += consumed_chars_base; |
2510 | coding->consumed = src_base - coding->source; | |
2511 | coding->charbuf_used = charbuf - coding->charbuf; | |
2512 | } | |
2513 | ||
2514 | ||
2515 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2516 | do { \ | |
2517 | if (id < 0xA0) \ | |
2518 | codes[0] = id, codes[1] = 0; \ | |
2519 | else if (id < 0xE0) \ | |
2520 | codes[0] = 0x9A, codes[1] = id; \ | |
2521 | else if (id < 0xF0) \ | |
2522 | codes[0] = 0x9B, codes[1] = id; \ | |
2523 | else if (id < 0xF5) \ | |
2524 | codes[0] = 0x9C, codes[1] = id; \ | |
2525 | else \ | |
2526 | codes[0] = 0x9D, codes[1] = id; \ | |
2527 | } while (0); | |
2528 | ||
aa72b389 | 2529 | |
f10fe38f | 2530 | static bool |
971de7fb | 2531 | encode_coding_emacs_mule (struct coding_system *coding) |
df7492f9 | 2532 | { |
f10fe38f | 2533 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
2534 | int *charbuf = coding->charbuf; |
2535 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2536 | unsigned char *dst = coding->destination + coding->produced; | |
2537 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2538 | int safe_room = 8; | |
d311d28c | 2539 | ptrdiff_t produced_chars = 0; |
24a73b0a | 2540 | Lisp_Object attrs, charset_list; |
df7492f9 | 2541 | int c; |
ff0dacd7 | 2542 | int preferred_charset_id = -1; |
df7492f9 | 2543 | |
24a73b0a | 2544 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2545 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2546 | { | |
4939150c PE |
2547 | charset_list = Vemacs_mule_charset_list; |
2548 | ASET (attrs, coding_attr_charset_list, charset_list); | |
eccb6815 | 2549 | } |
df7492f9 KH |
2550 | |
2551 | while (charbuf < charbuf_end) | |
2552 | { | |
2553 | ASSURE_DESTINATION (safe_room); | |
2554 | c = *charbuf++; | |
ff0dacd7 KH |
2555 | |
2556 | if (c < 0) | |
2557 | { | |
2558 | /* Handle an annotation. */ | |
2559 | switch (*charbuf) | |
2560 | { | |
2561 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2562 | /* Not yet implemented. */ | |
2563 | break; | |
2564 | case CODING_ANNOTATE_CHARSET_MASK: | |
2565 | preferred_charset_id = charbuf[3]; | |
2566 | if (preferred_charset_id >= 0 | |
2567 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2568 | charset_list))) | |
2569 | preferred_charset_id = -1; | |
2570 | break; | |
2571 | default: | |
1088b922 | 2572 | emacs_abort (); |
ff0dacd7 KH |
2573 | } |
2574 | charbuf += -c - 1; | |
2575 | continue; | |
2576 | } | |
2577 | ||
df7492f9 KH |
2578 | if (ASCII_CHAR_P (c)) |
2579 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2580 | else if (CHAR_BYTE8_P (c)) |
2581 | { | |
2582 | c = CHAR_TO_BYTE8 (c); | |
2583 | EMIT_ONE_BYTE (c); | |
2584 | } | |
df7492f9 | 2585 | else |
aa72b389 | 2586 | { |
df7492f9 KH |
2587 | struct charset *charset; |
2588 | unsigned code; | |
2589 | int dimension; | |
2590 | int emacs_mule_id; | |
2591 | unsigned char leading_codes[2]; | |
2592 | ||
ff0dacd7 KH |
2593 | if (preferred_charset_id >= 0) |
2594 | { | |
f10fe38f | 2595 | bool result; |
5eb05ea3 | 2596 | |
ff0dacd7 | 2597 | charset = CHARSET_FROM_ID (preferred_charset_id); |
5eb05ea3 KH |
2598 | CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result); |
2599 | if (result) | |
905ca9d2 KH |
2600 | code = ENCODE_CHAR (charset, c); |
2601 | else | |
5eb05ea3 KH |
2602 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2603 | &code, charset); | |
ff0dacd7 KH |
2604 | } |
2605 | else | |
5eb05ea3 KH |
2606 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2607 | &code, charset); | |
df7492f9 KH |
2608 | if (! charset) |
2609 | { | |
2610 | c = coding->default_char; | |
2611 | if (ASCII_CHAR_P (c)) | |
2612 | { | |
2613 | EMIT_ONE_ASCII_BYTE (c); | |
2614 | continue; | |
2615 | } | |
5eb05ea3 KH |
2616 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2617 | &code, charset); | |
df7492f9 KH |
2618 | } |
2619 | dimension = CHARSET_DIMENSION (charset); | |
2620 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2621 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2622 | EMIT_ONE_BYTE (leading_codes[0]); | |
2623 | if (leading_codes[1]) | |
2624 | EMIT_ONE_BYTE (leading_codes[1]); | |
2625 | if (dimension == 1) | |
1fa663f9 | 2626 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2627 | else |
df7492f9 | 2628 | { |
1fa663f9 | 2629 | code |= 0x8080; |
df7492f9 KH |
2630 | EMIT_ONE_BYTE (code >> 8); |
2631 | EMIT_ONE_BYTE (code & 0xFF); | |
2632 | } | |
aa72b389 | 2633 | } |
aa72b389 | 2634 | } |
065e3595 | 2635 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2636 | coding->produced_char += produced_chars; |
2637 | coding->produced = dst - coding->destination; | |
2638 | return 0; | |
aa72b389 | 2639 | } |
b73bfc1c | 2640 | |
4ed46869 | 2641 | \f |
df7492f9 | 2642 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2643 | |
2644 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2645 | Since the intention of this note is to help understand the |
5a936b46 | 2646 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2647 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2648 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2649 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2650 | |
2651 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2652 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2653 | is encoded using bytes less than 128. This may make the encoded |
2654 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2655 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2656 | Significant Bit). |
b73bfc1c | 2657 | |
cfb43547 DL |
2658 | There are two kinds of character sets: control character sets and |
2659 | graphic character sets. The former contain control characters such | |
4ed46869 | 2660 | as `newline' and `escape' to provide control functions (control |
39787efd | 2661 | functions are also provided by escape sequences). The latter |
cfb43547 | 2662 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2663 | two control character sets and many graphic character sets. |
2664 | ||
2665 | Graphic character sets are classified into one of the following | |
39787efd KH |
2666 | four classes, according to the number of bytes (DIMENSION) and |
2667 | number of characters in one dimension (CHARS) of the set: | |
2668 | - DIMENSION1_CHARS94 | |
2669 | - DIMENSION1_CHARS96 | |
2670 | - DIMENSION2_CHARS94 | |
2671 | - DIMENSION2_CHARS96 | |
2672 | ||
2673 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2674 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2675 | hereafter). The <F> of each character set is decided by ECMA(*) |
2676 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2677 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2678 | |
2679 | Note (*): ECMA = European Computer Manufacturers Association | |
2680 | ||
cfb43547 | 2681 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2682 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2683 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2684 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2685 | o DIMENSION2_CHARS96 -- none for the moment | |
2686 | ||
39787efd | 2687 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2688 | C0 [0x00..0x1F] -- control character plane 0 |
2689 | GL [0x20..0x7F] -- graphic character plane 0 | |
2690 | C1 [0x80..0x9F] -- control character plane 1 | |
2691 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2692 | ||
2693 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2694 | C1 by an escape sequence. The most common case is that: |
2695 | - ISO646's control character set is designated/invoked to C0, and | |
2696 | - ISO6429's control character set is designated/invoked to C1, | |
2697 | and usually these designations/invocations are omitted in encoded | |
2698 | text. In a 7-bit environment, only C0 can be used, and a control | |
2699 | character for C1 is encoded by an appropriate escape sequence to | |
2700 | fit into the environment. All control characters for C1 are | |
2701 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2702 | |
2703 | A graphic character set is at first designated to one of four | |
2704 | graphic registers (G0 through G3), then these graphic registers are | |
2705 | invoked to GL or GR. These designations and invocations can be | |
2706 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2707 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2708 | these invocations and designations are omitted in encoded text. | |
2709 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2710 | |
39787efd KH |
2711 | When a graphic character set of CHARS94 is invoked to GL, codes |
2712 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2713 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2714 | be used. | |
4ed46869 KH |
2715 | |
2716 | There are two ways of invocation: locking-shift and single-shift. | |
2717 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2718 | invocation, whereas with single-shift, the invocation affects the |
2719 | following character only and doesn't affect the locking-shift | |
2720 | state. Invocations are done by the following control characters or | |
2721 | escape sequences: | |
4ed46869 KH |
2722 | |
2723 | ---------------------------------------------------------------------- | |
39787efd | 2724 | abbrev function cntrl escape seq description |
4ed46869 | 2725 | ---------------------------------------------------------------------- |
39787efd KH |
2726 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2727 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2728 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2729 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2730 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2731 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2732 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2733 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2734 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2735 | ---------------------------------------------------------------------- |
39787efd KH |
2736 | (*) These are not used by any known coding system. |
2737 | ||
2738 | Control characters for these functions are defined by macros | |
2739 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2740 | |
39787efd | 2741 | Designations are done by the following escape sequences: |
4ed46869 KH |
2742 | ---------------------------------------------------------------------- |
2743 | escape sequence description | |
2744 | ---------------------------------------------------------------------- | |
2745 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2746 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2747 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2748 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2749 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2750 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2751 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2752 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2753 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2754 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2755 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2756 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2757 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2758 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2759 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2760 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2761 | ---------------------------------------------------------------------- | |
2762 | ||
2763 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2764 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2765 | |
2766 | Note (*): Although these designations are not allowed in ISO2022, | |
2767 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2768 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2769 | 7-bit environment, non-locking-shift, and non-single-shift. |
2770 | ||
2771 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2772 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2773 | |
cfb43547 | 2774 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2775 | same multilingual text in ISO2022. Actually, there exist many |
2776 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2777 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2778 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2779 | localized platforms), and all of these are variants of ISO2022. |
2780 | ||
2781 | In addition to the above, Emacs handles two more kinds of escape | |
2782 | sequences: ISO6429's direction specification and Emacs' private | |
2783 | sequence for specifying character composition. | |
2784 | ||
39787efd | 2785 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2786 | o CSI ']' -- end of the current direction |
2787 | o CSI '0' ']' -- end of the current direction | |
2788 | o CSI '1' ']' -- start of left-to-right text | |
2789 | o CSI '2' ']' -- start of right-to-left text | |
2790 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2791 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2792 | ||
2793 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2794 | o ESC '0' -- start relative composition |
2795 | o ESC '1' -- end composition | |
2796 | o ESC '2' -- start rule-base composition (*) | |
2797 | o ESC '3' -- start relative composition with alternate chars (**) | |
2798 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2799 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2800 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2801 | |
5a936b46 DL |
2802 | (*) This form is used only in Emacs 20.7 and older versions, |
2803 | but newer versions can safely decode it. | |
cfb43547 | 2804 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2805 | and older versions can't decode it. |
ec6d2bb8 | 2806 | |
cfb43547 | 2807 | Here's a list of example usages of these composition escape |
b73bfc1c | 2808 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2809 | |
b73bfc1c | 2810 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2811 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2812 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2813 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2814 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2815 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2816 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2817 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 | 2818 | |
74ab6df5 | 2819 | static enum iso_code_class_type iso_code_class[256]; |
4ed46869 | 2820 | |
df7492f9 KH |
2821 | #define SAFE_CHARSET_P(coding, id) \ |
2822 | ((id) <= (coding)->max_charset_id \ | |
1b3b981b | 2823 | && (coding)->safe_charsets[id] != 255) |
df7492f9 | 2824 | |
df7492f9 | 2825 | static void |
971de7fb | 2826 | setup_iso_safe_charsets (Lisp_Object attrs) |
df7492f9 KH |
2827 | { |
2828 | Lisp_Object charset_list, safe_charsets; | |
2829 | Lisp_Object request; | |
2830 | Lisp_Object reg_usage; | |
2831 | Lisp_Object tail; | |
d311d28c | 2832 | EMACS_INT reg94, reg96; |
df7492f9 KH |
2833 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); |
2834 | int max_charset_id; | |
2835 | ||
2836 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2837 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2838 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2839 | { | |
4939150c PE |
2840 | charset_list = Viso_2022_charset_list; |
2841 | ASET (attrs, coding_attr_charset_list, charset_list); | |
df7492f9 KH |
2842 | ASET (attrs, coding_attr_safe_charsets, Qnil); |
2843 | } | |
2844 | ||
2845 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2846 | return; | |
2847 | ||
2848 | max_charset_id = 0; | |
2849 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2850 | { | |
2851 | int id = XINT (XCAR (tail)); | |
2852 | if (max_charset_id < id) | |
2853 | max_charset_id = id; | |
2854 | } | |
d46c5b12 | 2855 | |
1b3b981b AS |
2856 | safe_charsets = make_uninit_string (max_charset_id + 1); |
2857 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
2858 | request = AREF (attrs, coding_attr_iso_request); |
2859 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2860 | reg94 = XINT (XCAR (reg_usage)); | |
2861 | reg96 = XINT (XCDR (reg_usage)); | |
2862 | ||
2863 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2864 | { | |
2865 | Lisp_Object id; | |
2866 | Lisp_Object reg; | |
2867 | struct charset *charset; | |
2868 | ||
2869 | id = XCAR (tail); | |
2870 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2871 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2872 | if (! NILP (reg)) |
8f924df7 | 2873 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2874 | else if (charset->iso_chars_96) |
2875 | { | |
2876 | if (reg96 < 4) | |
8f924df7 | 2877 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2878 | } |
2879 | else | |
2880 | { | |
2881 | if (reg94 < 4) | |
8f924df7 | 2882 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2883 | } |
2884 | } | |
2885 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2886 | } | |
d46c5b12 | 2887 | |
b6871cc7 | 2888 | |
4ed46869 | 2889 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f PE |
2890 | Return true if a text is encoded in one of ISO-2022 based coding |
2891 | systems. */ | |
4ed46869 | 2892 | |
f10fe38f | 2893 | static bool |
cf84bb53 JB |
2894 | detect_coding_iso_2022 (struct coding_system *coding, |
2895 | struct coding_detection_info *detect_info) | |
4ed46869 | 2896 | { |
8f924df7 KH |
2897 | const unsigned char *src = coding->source, *src_base = src; |
2898 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
f10fe38f PE |
2899 | bool multibytep = coding->src_multibyte; |
2900 | bool single_shifting = 0; | |
0e48bb22 | 2901 | int id; |
df7492f9 | 2902 | int c, c1; |
d311d28c | 2903 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 2904 | int i; |
ff0dacd7 KH |
2905 | int rejected = 0; |
2906 | int found = 0; | |
cee53ed4 | 2907 | int composition_count = -1; |
ff0dacd7 KH |
2908 | |
2909 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2910 | |
2911 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2912 | { | |
2913 | struct coding_system *this = &(coding_categories[i]); | |
2914 | Lisp_Object attrs, val; | |
2915 | ||
c6b278e7 KH |
2916 | if (this->id < 0) |
2917 | continue; | |
df7492f9 KH |
2918 | attrs = CODING_ID_ATTRS (this->id); |
2919 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
1b3b981b | 2920 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list)) |
df7492f9 KH |
2921 | setup_iso_safe_charsets (attrs); |
2922 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 2923 | this->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 2924 | this->safe_charsets = SDATA (val); |
df7492f9 KH |
2925 | } |
2926 | ||
2927 | /* A coding system of this category is always ASCII compatible. */ | |
2928 | src += coding->head_ascii; | |
3f003981 | 2929 | |
ff0dacd7 | 2930 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2931 | { |
065e3595 | 2932 | src_base = src; |
df7492f9 | 2933 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2934 | switch (c) |
2935 | { | |
2936 | case ISO_CODE_ESC: | |
74383408 KH |
2937 | if (inhibit_iso_escape_detection) |
2938 | break; | |
f46869e4 | 2939 | single_shifting = 0; |
df7492f9 | 2940 | ONE_MORE_BYTE (c); |
0e48bb22 | 2941 | if (c == 'N' || c == 'O') |
d46c5b12 | 2942 | { |
ae9ff118 | 2943 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2944 | single_shifting = 1; |
2945 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
4ed46869 | 2946 | } |
cee53ed4 KH |
2947 | else if (c == '1') |
2948 | { | |
2949 | /* End of composition. */ | |
2950 | if (composition_count < 0 | |
2951 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
2952 | /* Invalid */ | |
2953 | break; | |
2954 | composition_count = -1; | |
2955 | found |= CATEGORY_MASK_ISO; | |
2956 | } | |
ec6d2bb8 KH |
2957 | else if (c >= '0' && c <= '4') |
2958 | { | |
2959 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 2960 | composition_count = 0; |
ec6d2bb8 | 2961 | } |
bf9cdd4e | 2962 | else |
df7492f9 | 2963 | { |
0e48bb22 AS |
2964 | if (c >= '(' && c <= '/') |
2965 | { | |
2966 | /* Designation sequence for a charset of dimension 1. */ | |
2967 | ONE_MORE_BYTE (c1); | |
2968 | if (c1 < ' ' || c1 >= 0x80 | |
2969 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) | |
2970 | /* Invalid designation sequence. Just ignore. */ | |
2971 | break; | |
2972 | } | |
2973 | else if (c == '$') | |
2974 | { | |
2975 | /* Designation sequence for a charset of dimension 2. */ | |
2976 | ONE_MORE_BYTE (c); | |
2977 | if (c >= '@' && c <= 'B') | |
2978 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
2979 | id = iso_charset_table[1][0][c]; | |
2980 | else if (c >= '(' && c <= '/') | |
2981 | { | |
2982 | ONE_MORE_BYTE (c1); | |
2983 | if (c1 < ' ' || c1 >= 0x80 | |
2984 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) | |
2985 | /* Invalid designation sequence. Just ignore. */ | |
2986 | break; | |
2987 | } | |
2988 | else | |
2989 | /* Invalid designation sequence. Just ignore it. */ | |
2990 | break; | |
2991 | } | |
2992 | else | |
2993 | { | |
2994 | /* Invalid escape sequence. Just ignore it. */ | |
2995 | break; | |
2996 | } | |
d46c5b12 | 2997 | |
0e48bb22 AS |
2998 | /* We found a valid designation sequence for CHARSET. */ |
2999 | rejected |= CATEGORY_MASK_ISO_8BIT; | |
3000 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], | |
3001 | id)) | |
3002 | found |= CATEGORY_MASK_ISO_7; | |
3003 | else | |
3004 | rejected |= CATEGORY_MASK_ISO_7; | |
3005 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], | |
3006 | id)) | |
3007 | found |= CATEGORY_MASK_ISO_7_TIGHT; | |
3008 | else | |
3009 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; | |
3010 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], | |
3011 | id)) | |
3012 | found |= CATEGORY_MASK_ISO_7_ELSE; | |
3013 | else | |
3014 | rejected |= CATEGORY_MASK_ISO_7_ELSE; | |
3015 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], | |
3016 | id)) | |
3017 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3018 | else | |
3019 | rejected |= CATEGORY_MASK_ISO_8_ELSE; | |
3020 | } | |
4ed46869 KH |
3021 | break; |
3022 | ||
4ed46869 | 3023 | case ISO_CODE_SO: |
d46c5b12 | 3024 | case ISO_CODE_SI: |
ff0dacd7 | 3025 | /* Locking shift out/in. */ |
74383408 KH |
3026 | if (inhibit_iso_escape_detection) |
3027 | break; | |
f46869e4 | 3028 | single_shifting = 0; |
ff0dacd7 | 3029 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
3030 | break; |
3031 | ||
4ed46869 | 3032 | case ISO_CODE_CSI: |
ff0dacd7 | 3033 | /* Control sequence introducer. */ |
f46869e4 | 3034 | single_shifting = 0; |
ff0dacd7 KH |
3035 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3036 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3037 | goto check_extra_latin; | |
3038 | ||
4ed46869 KH |
3039 | case ISO_CODE_SS2: |
3040 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
3041 | /* Single shift. */ |
3042 | if (inhibit_iso_escape_detection) | |
3043 | break; | |
75e2a253 | 3044 | single_shifting = 0; |
ff0dacd7 KH |
3045 | rejected |= CATEGORY_MASK_ISO_7BIT; |
3046 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3047 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
0e48bb22 AS |
3048 | { |
3049 | found |= CATEGORY_MASK_ISO_8_1; | |
3050 | single_shifting = 1; | |
3051 | } | |
ff0dacd7 KH |
3052 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
3053 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
0e48bb22 AS |
3054 | { |
3055 | found |= CATEGORY_MASK_ISO_8_2; | |
3056 | single_shifting = 1; | |
3057 | } | |
75e2a253 KH |
3058 | if (single_shifting) |
3059 | break; | |
ba14c607 | 3060 | goto check_extra_latin; |
4ed46869 KH |
3061 | |
3062 | default: | |
065e3595 KH |
3063 | if (c < 0) |
3064 | continue; | |
4ed46869 | 3065 | if (c < 0x80) |
f46869e4 | 3066 | { |
cee53ed4 KH |
3067 | if (composition_count >= 0) |
3068 | composition_count++; | |
f46869e4 KH |
3069 | single_shifting = 0; |
3070 | break; | |
3071 | } | |
ff0dacd7 | 3072 | if (c >= 0xA0) |
c4825358 | 3073 | { |
ff0dacd7 KH |
3074 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3075 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 3076 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
3077 | 0xA0..0FF. If the byte length is even, we include |
3078 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
3079 | only when we are not single shifting. */ | |
3080 | if (! single_shifting | |
3081 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 3082 | { |
2735d060 | 3083 | int len = 1; |
b73bfc1c KH |
3084 | while (src < src_end) |
3085 | { | |
d12bd917 | 3086 | src_base = src; |
df7492f9 | 3087 | ONE_MORE_BYTE (c); |
b73bfc1c | 3088 | if (c < 0xA0) |
d12bd917 KH |
3089 | { |
3090 | src = src_base; | |
3091 | break; | |
3092 | } | |
2735d060 | 3093 | len++; |
b73bfc1c KH |
3094 | } |
3095 | ||
2735d060 | 3096 | if (len & 1 && src < src_end) |
cee53ed4 KH |
3097 | { |
3098 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3099 | if (composition_count >= 0) | |
2735d060 | 3100 | composition_count += len; |
cee53ed4 | 3101 | } |
f46869e4 | 3102 | else |
cee53ed4 KH |
3103 | { |
3104 | found |= CATEGORY_MASK_ISO_8_2; | |
3105 | if (composition_count >= 0) | |
2735d060 | 3106 | composition_count += len / 2; |
cee53ed4 | 3107 | } |
f46869e4 | 3108 | } |
ff0dacd7 | 3109 | break; |
4ed46869 | 3110 | } |
ba14c607 AS |
3111 | check_extra_latin: |
3112 | if (! VECTORP (Vlatin_extra_code_table) | |
3113 | || NILP (AREF (Vlatin_extra_code_table, c))) | |
3114 | { | |
3115 | rejected = CATEGORY_MASK_ISO; | |
3116 | break; | |
3117 | } | |
3118 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3119 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3120 | found |= CATEGORY_MASK_ISO_8_1; | |
3121 | else | |
3122 | rejected |= CATEGORY_MASK_ISO_8_1; | |
3123 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3124 | break; | |
4ed46869 KH |
3125 | } |
3126 | } | |
ff0dacd7 KH |
3127 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3128 | return 0; | |
4ed46869 | 3129 | |
df7492f9 | 3130 | no_more_source: |
ff0dacd7 KH |
3131 | detect_info->rejected |= rejected; |
3132 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3133 | return 1; |
4ed46869 | 3134 | } |
ec6d2bb8 | 3135 | |
4ed46869 | 3136 | |
134b9549 KH |
3137 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3138 | escape sequence should be kept. */ | |
df7492f9 KH |
3139 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3140 | do { \ | |
3141 | int id, prev; \ | |
3142 | \ | |
3143 | if (final < '0' || final >= 128 \ | |
3144 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3145 | || !SAFE_CHARSET_P (coding, id)) \ | |
3146 | { \ | |
3147 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3148 | chars_96 = -1; \ |
3149 | break; \ | |
df7492f9 KH |
3150 | } \ |
3151 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3152 | if (id == charset_jisx0201_roman) \ |
3153 | { \ | |
3154 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3155 | id = charset_ascii; \ | |
3156 | } \ | |
3157 | else if (id == charset_jisx0208_1978) \ | |
3158 | { \ | |
3159 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3160 | id = charset_jisx0208; \ | |
3161 | } \ | |
df7492f9 KH |
3162 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3163 | /* If there was an invalid designation to REG previously, and this \ | |
3164 | designation is ASCII to REG, we should keep this designation \ | |
3165 | sequence. */ \ | |
3166 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3167 | chars_96 = -1; \ |
4ed46869 KH |
3168 | } while (0) |
3169 | ||
d46c5b12 | 3170 | |
e951386e KH |
3171 | /* Handle these composition sequence (ALT: alternate char): |
3172 | ||
3173 | (1) relative composition: ESC 0 CHAR ... ESC 1 | |
3174 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
3175 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | |
3176 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | |
3177 | ||
3178 | When the start sequence (ESC 0/2/3/4) is found, this annotation | |
3179 | header is produced. | |
3180 | ||
3181 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | |
3182 | ||
3183 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | |
3184 | produced until the end sequence (ESC 1) is found: | |
3185 | ||
3186 | (1) CHAR ... CHAR | |
3187 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
3188 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | |
3189 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | |
3190 | ||
3191 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | |
3192 | annotation header is updated as below: | |
3193 | ||
3194 | (1) LENGTH: unchanged, NCHARS: number of CHARs | |
3195 | (2) LENGTH: unchanged, NCHARS: number of CHARs | |
3196 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | |
3197 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | |
3198 | ||
3199 | If an error is found while composing, the annotation header is | |
3200 | changed to: | |
3201 | ||
3202 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | |
3203 | ||
3204 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
3205 | byte sequence as below: | |
3206 | o the original byte sequence is B: [ B -1 ] | |
3207 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
3208 | and the sequence [ -1 -1 ] is changed to the original byte | |
3209 | sequence: | |
3210 | [ ESC '0' ] | |
3211 | */ | |
3212 | ||
3213 | /* Decode a composition rule C1 and maybe one more byte from the | |
66ebf983 | 3214 | source, and set RULE to the encoded composition rule. If the rule |
d5efd1d1 | 3215 | is invalid, goto invalid_code. */ |
e951386e | 3216 | |
66ebf983 | 3217 | #define DECODE_COMPOSITION_RULE(rule) \ |
e951386e KH |
3218 | do { \ |
3219 | rule = c1 - 32; \ | |
3220 | if (rule < 0) \ | |
d5efd1d1 | 3221 | goto invalid_code; \ |
e951386e KH |
3222 | if (rule < 81) /* old format (before ver.21) */ \ |
3223 | { \ | |
3224 | int gref = (rule) / 9; \ | |
3225 | int nref = (rule) % 9; \ | |
3226 | if (gref == 4) gref = 10; \ | |
3227 | if (nref == 4) nref = 10; \ | |
3228 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
e951386e KH |
3229 | } \ |
3230 | else /* new format (after ver.21) */ \ | |
3231 | { \ | |
2735d060 | 3232 | int b; \ |
e951386e | 3233 | \ |
2735d060 | 3234 | ONE_MORE_BYTE (b); \ |
d5efd1d1 PE |
3235 | if (! COMPOSITION_ENCODE_RULE_VALID (rule - 81, b - 32)) \ |
3236 | goto invalid_code; \ | |
2735d060 | 3237 | rule = COMPOSITION_ENCODE_RULE (rule - 81, b - 32); \ |
d5efd1d1 | 3238 | rule += 0x100; /* Distinguish it from the old format. */ \ |
e951386e KH |
3239 | } \ |
3240 | } while (0) | |
3241 | ||
3242 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
df7492f9 | 3243 | do { \ |
e951386e KH |
3244 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
3245 | \ | |
3246 | if (rule < 0x100) /* old format */ \ | |
df7492f9 | 3247 | { \ |
e951386e KH |
3248 | if (gref == 10) gref = 4; \ |
3249 | if (nref == 10) nref = 4; \ | |
3250 | charbuf[idx] = 32 + gref * 9 + nref; \ | |
3251 | charbuf[idx + 1] = -1; \ | |
3252 | new_chars++; \ | |
df7492f9 | 3253 | } \ |
e951386e | 3254 | else /* new format */ \ |
df7492f9 | 3255 | { \ |
e951386e KH |
3256 | charbuf[idx] = 32 + 81 + gref; \ |
3257 | charbuf[idx + 1] = 32 + nref; \ | |
3258 | new_chars += 2; \ | |
df7492f9 KH |
3259 | } \ |
3260 | } while (0) | |
3261 | ||
e951386e KH |
3262 | /* Finish the current composition as invalid. */ |
3263 | ||
e951386e | 3264 | static int |
971de7fb | 3265 | finish_composition (int *charbuf, struct composition_status *cmp_status) |
e951386e KH |
3266 | { |
3267 | int idx = - cmp_status->length; | |
3268 | int new_chars; | |
3269 | ||
3270 | /* Recover the original ESC sequence */ | |
3271 | charbuf[idx++] = ISO_CODE_ESC; | |
3272 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | |
3273 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | |
3274 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | |
3275 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | |
3276 | : '4'); | |
3277 | charbuf[idx++] = -2; | |
3278 | charbuf[idx++] = 0; | |
3279 | charbuf[idx++] = -1; | |
3280 | new_chars = cmp_status->nchars; | |
3281 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | |
3282 | for (; idx < 0; idx++) | |
3283 | { | |
3284 | int elt = charbuf[idx]; | |
3285 | ||
3286 | if (elt == -2) | |
3287 | { | |
3288 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | |
3289 | idx++; | |
3290 | } | |
3291 | else if (elt == -1) | |
3292 | { | |
3293 | charbuf[idx++] = ISO_CODE_ESC; | |
3294 | charbuf[idx] = '0'; | |
3295 | new_chars += 2; | |
3296 | } | |
3297 | } | |
3298 | cmp_status->state = COMPOSING_NO; | |
3299 | return new_chars; | |
3300 | } | |
3301 | ||
ad1746f5 | 3302 | /* If characters are under composition, finish the composition. */ |
e951386e KH |
3303 | #define MAYBE_FINISH_COMPOSITION() \ |
3304 | do { \ | |
3305 | if (cmp_status->state != COMPOSING_NO) \ | |
3306 | char_offset += finish_composition (charbuf, cmp_status); \ | |
3307 | } while (0) | |
d46c5b12 | 3308 | |
aa72b389 | 3309 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
e951386e | 3310 | |
aa72b389 KH |
3311 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
3312 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3313 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3314 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
ec6d2bb8 | 3315 | |
e951386e KH |
3316 | Produce this annotation sequence now: |
3317 | ||
3318 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] | |
3319 | */ | |
3320 | ||
3321 | #define DECODE_COMPOSITION_START(c1) \ | |
3322 | do { \ | |
3323 | if (c1 == '0' \ | |
3324 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ | |
3325 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ | |
3326 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ | |
3327 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ | |
3328 | { \ | |
3329 | *charbuf++ = -1; \ | |
3330 | *charbuf++= -1; \ | |
3331 | cmp_status->state = COMPOSING_CHAR; \ | |
3332 | cmp_status->length += 2; \ | |
3333 | } \ | |
3334 | else \ | |
3335 | { \ | |
3336 | MAYBE_FINISH_COMPOSITION (); \ | |
3337 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3338 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3339 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3340 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3341 | cmp_status->state \ | |
3342 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ | |
3343 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
3344 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
3345 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
3346 | coding->annotated = 1; \ | |
3347 | } \ | |
ec6d2bb8 KH |
3348 | } while (0) |
3349 | ||
ec6d2bb8 | 3350 | |
e951386e | 3351 | /* Handle composition end sequence ESC 1. */ |
df7492f9 KH |
3352 | |
3353 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3354 | do { \ |
e951386e KH |
3355 | if (cmp_status->nchars == 0 \ |
3356 | || ((cmp_status->state == COMPOSING_CHAR) \ | |
3357 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ | |
ec6d2bb8 | 3358 | { \ |
e951386e KH |
3359 | MAYBE_FINISH_COMPOSITION (); \ |
3360 | goto invalid_code; \ | |
ec6d2bb8 | 3361 | } \ |
e951386e KH |
3362 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
3363 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ | |
3364 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
3365 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ | |
3366 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ | |
3367 | char_offset += cmp_status->nchars; \ | |
3368 | cmp_status->state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3369 | } while (0) |
3370 | ||
e951386e | 3371 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ |
df7492f9 | 3372 | |
e951386e KH |
3373 | #define STORE_COMPOSITION_RULE(rule) \ |
3374 | do { \ | |
3375 | *charbuf++ = -2; \ | |
3376 | *charbuf++ = rule; \ | |
3377 | cmp_status->length += 2; \ | |
3378 | cmp_status->state--; \ | |
3379 | } while (0) | |
ec6d2bb8 | 3380 | |
e951386e KH |
3381 | /* Store a composed char or a component char C in charbuf, and update |
3382 | cmp_status. */ | |
3383 | ||
3384 | #define STORE_COMPOSITION_CHAR(c) \ | |
ec6d2bb8 | 3385 | do { \ |
e951386e KH |
3386 | *charbuf++ = (c); \ |
3387 | cmp_status->length++; \ | |
3388 | if (cmp_status->state == COMPOSING_CHAR) \ | |
3389 | cmp_status->nchars++; \ | |
df7492f9 | 3390 | else \ |
e951386e KH |
3391 | cmp_status->ncomps++; \ |
3392 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | |
3393 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | |
3394 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | |
3395 | cmp_status->state++; \ | |
ec6d2bb8 | 3396 | } while (0) |
88993dfd | 3397 | |
d46c5b12 | 3398 | |
4ed46869 KH |
3399 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3400 | ||
b73bfc1c | 3401 | static void |
971de7fb | 3402 | decode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 3403 | { |
8f924df7 KH |
3404 | const unsigned char *src = coding->source + coding->consumed; |
3405 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3406 | const unsigned char *src_base; | |
69a80ea3 | 3407 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
3408 | /* We may produce two annotations (charset and composition) in one |
3409 | loop and one more charset annotation at the end. */ | |
ff0dacd7 | 3410 | int *charbuf_end |
df80c7f0 | 3411 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
d311d28c | 3412 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 3413 | bool multibytep = coding->src_multibyte; |
4ed46869 | 3414 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3415 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3416 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3417 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3418 | struct charset *charset; |
3419 | int c; | |
e951386e | 3420 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
66ebf983 | 3421 | Lisp_Object attrs = CODING_ID_ATTRS (coding->id); |
d311d28c PE |
3422 | ptrdiff_t char_offset = coding->produced_char; |
3423 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 3424 | int last_id = charset_ascii; |
f10fe38f PE |
3425 | bool eol_dos |
3426 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 3427 | int byte_after_cr = -1; |
e951386e | 3428 | int i; |
df7492f9 | 3429 | |
df7492f9 | 3430 | setup_iso_safe_charsets (attrs); |
1b3b981b | 3431 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
b73bfc1c | 3432 | |
e951386e KH |
3433 | if (cmp_status->state != COMPOSING_NO) |
3434 | { | |
15cbd324 | 3435 | if (charbuf_end - charbuf < cmp_status->length) |
1088b922 | 3436 | emacs_abort (); |
e951386e KH |
3437 | for (i = 0; i < cmp_status->length; i++) |
3438 | *charbuf++ = cmp_status->carryover[i]; | |
3439 | coding->annotated = 1; | |
3440 | } | |
3441 | ||
b73bfc1c | 3442 | while (1) |
4ed46869 | 3443 | { |
cf299835 | 3444 | int c1, c2, c3; |
b73bfc1c KH |
3445 | |
3446 | src_base = src; | |
df7492f9 KH |
3447 | consumed_chars_base = consumed_chars; |
3448 | ||
3449 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3450 | { |
3451 | if (byte_after_cr >= 0) | |
3452 | src_base--; | |
3453 | break; | |
3454 | } | |
df7492f9 | 3455 | |
119852e7 KH |
3456 | if (byte_after_cr >= 0) |
3457 | c1 = byte_after_cr, byte_after_cr = -1; | |
3458 | else | |
3459 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3460 | if (c1 < 0) |
3461 | goto invalid_code; | |
4ed46869 | 3462 | |
e951386e | 3463 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
4ed46869 | 3464 | { |
e951386e KH |
3465 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
3466 | char_offset++; | |
3467 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | |
3468 | continue; | |
3469 | } | |
3470 | ||
3471 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | |
3472 | { | |
3473 | if (c1 == ISO_CODE_ESC) | |
ec6d2bb8 | 3474 | { |
e951386e KH |
3475 | if (src + 1 >= src_end) |
3476 | goto no_more_source; | |
3477 | *charbuf++ = ISO_CODE_ESC; | |
3478 | char_offset++; | |
3479 | if (src[0] == '%' && src[1] == '@') | |
df7492f9 | 3480 | { |
e951386e KH |
3481 | src += 2; |
3482 | consumed_chars += 2; | |
3483 | char_offset += 2; | |
3484 | /* We are sure charbuf can contain two more chars. */ | |
3485 | *charbuf++ = '%'; | |
3486 | *charbuf++ = '@'; | |
3487 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
df7492f9 | 3488 | } |
4ed46869 | 3489 | } |
e951386e KH |
3490 | else |
3491 | { | |
3492 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
3493 | char_offset++; | |
3494 | } | |
3495 | continue; | |
3496 | } | |
3497 | ||
3498 | if ((cmp_status->state == COMPOSING_RULE | |
3499 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | |
3500 | && c1 != ISO_CODE_ESC) | |
3501 | { | |
66ebf983 | 3502 | int rule; |
e951386e | 3503 | |
66ebf983 | 3504 | DECODE_COMPOSITION_RULE (rule); |
e951386e KH |
3505 | STORE_COMPOSITION_RULE (rule); |
3506 | continue; | |
3507 | } | |
3508 | ||
3509 | /* We produce at most one character. */ | |
3510 | switch (iso_code_class [c1]) | |
3511 | { | |
3512 | case ISO_0x20_or_0x7F: | |
df7492f9 KH |
3513 | if (charset_id_0 < 0 |
3514 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3515 | /* This is SPACE or DEL. */ |
3516 | charset = CHARSET_FROM_ID (charset_ascii); | |
3517 | else | |
3518 | charset = CHARSET_FROM_ID (charset_id_0); | |
3519 | break; | |
4ed46869 KH |
3520 | |
3521 | case ISO_graphic_plane_0: | |
134b9549 KH |
3522 | if (charset_id_0 < 0) |
3523 | charset = CHARSET_FROM_ID (charset_ascii); | |
3524 | else | |
3525 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3526 | break; |
3527 | ||
3528 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3529 | if (charset_id_1 < 0 |
3530 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3531 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3532 | goto invalid_code; | |
4ed46869 KH |
3533 | /* This is a graphic character, we fall down ... */ |
3534 | ||
3535 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3536 | if (charset_id_1 < 0) |
3537 | goto invalid_code; | |
3538 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3539 | break; |
3540 | ||
df7492f9 | 3541 | case ISO_control_0: |
2735d060 | 3542 | if (eol_dos && c1 == '\r') |
119852e7 | 3543 | ONE_MORE_BYTE (byte_after_cr); |
df7492f9 KH |
3544 | MAYBE_FINISH_COMPOSITION (); |
3545 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3546 | break; |
3547 | ||
df7492f9 | 3548 | case ISO_control_1: |
df7492f9 KH |
3549 | goto invalid_code; |
3550 | ||
4ed46869 | 3551 | case ISO_shift_out: |
df7492f9 KH |
3552 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3553 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3554 | goto invalid_code; | |
3555 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3556 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3557 | continue; |
4ed46869 KH |
3558 | |
3559 | case ISO_shift_in: | |
df7492f9 KH |
3560 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3561 | goto invalid_code; | |
3562 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3563 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3564 | continue; |
4ed46869 KH |
3565 | |
3566 | case ISO_single_shift_2_7: | |
a63dba42 KH |
3567 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)) |
3568 | goto invalid_code; | |
4ed46869 | 3569 | case ISO_single_shift_2: |
df7492f9 KH |
3570 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3571 | goto invalid_code; | |
4ed46869 KH |
3572 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3573 | c1 = 'N'; | |
3574 | goto label_escape_sequence; | |
3575 | ||
3576 | case ISO_single_shift_3: | |
df7492f9 KH |
3577 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3578 | goto invalid_code; | |
4ed46869 KH |
3579 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3580 | c1 = 'O'; | |
3581 | goto label_escape_sequence; | |
3582 | ||
3583 | case ISO_control_sequence_introducer: | |
3584 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3585 | c1 = '['; | |
3586 | goto label_escape_sequence; | |
3587 | ||
3588 | case ISO_escape: | |
3589 | ONE_MORE_BYTE (c1); | |
3590 | label_escape_sequence: | |
df7492f9 | 3591 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3592 | designation, direction specification, and character |
3593 | composition specification. */ | |
3594 | switch (c1) | |
3595 | { | |
3596 | case '&': /* revision of following character set */ | |
3597 | ONE_MORE_BYTE (c1); | |
3598 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3599 | goto invalid_code; |
4ed46869 KH |
3600 | ONE_MORE_BYTE (c1); |
3601 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3602 | goto invalid_code; |
4ed46869 KH |
3603 | ONE_MORE_BYTE (c1); |
3604 | goto label_escape_sequence; | |
3605 | ||
3606 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3607 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3608 | goto invalid_code; | |
134b9549 KH |
3609 | { |
3610 | int reg, chars96; | |
3611 | ||
3612 | ONE_MORE_BYTE (c1); | |
3613 | if (c1 >= '@' && c1 <= 'B') | |
3614 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3615 | or JISX0208.1980 */ |
134b9549 KH |
3616 | reg = 0, chars96 = 0; |
3617 | } | |
3618 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3619 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3620 | reg = c1 - 0x28, chars96 = 0; | |
3621 | ONE_MORE_BYTE (c1); | |
3622 | } | |
3623 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3624 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3625 | reg = c1 - 0x2C, chars96 = 1; | |
3626 | ONE_MORE_BYTE (c1); | |
3627 | } | |
3628 | else | |
3629 | goto invalid_code; | |
3630 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3631 | /* We must update these variables now. */ | |
3632 | if (reg == 0) | |
3633 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3634 | else if (reg == 1) | |
3635 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3636 | if (chars96 < 0) | |
3637 | goto invalid_code; | |
3638 | } | |
b73bfc1c | 3639 | continue; |
4ed46869 KH |
3640 | |
3641 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3642 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3643 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3644 | goto invalid_code; | |
3645 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3646 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3647 | continue; |
4ed46869 KH |
3648 | |
3649 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3650 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3651 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3652 | goto invalid_code; | |
3653 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3654 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3655 | continue; |
4ed46869 KH |
3656 | |
3657 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3658 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3659 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3660 | goto invalid_code; | |
134b9549 KH |
3661 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3662 | if (charset_id_2 < 0) | |
3663 | charset = CHARSET_FROM_ID (charset_ascii); | |
3664 | else | |
3665 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3666 | ONE_MORE_BYTE (c1); |
e7046a18 | 3667 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3668 | goto invalid_code; |
4ed46869 KH |
3669 | break; |
3670 | ||
3671 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3672 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3673 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3674 | goto invalid_code; | |
134b9549 KH |
3675 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3676 | if (charset_id_3 < 0) | |
3677 | charset = CHARSET_FROM_ID (charset_ascii); | |
3678 | else | |
3679 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3680 | ONE_MORE_BYTE (c1); |
e7046a18 | 3681 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3682 | goto invalid_code; |
4ed46869 KH |
3683 | break; |
3684 | ||
ec6d2bb8 | 3685 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3686 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3687 | goto invalid_code; | |
e951386e KH |
3688 | if (last_id != charset_ascii) |
3689 | { | |
3690 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | |
3691 | last_id = charset_ascii; | |
3692 | last_offset = char_offset; | |
3693 | } | |
ec6d2bb8 | 3694 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3695 | continue; |
4ed46869 | 3696 | |
ec6d2bb8 | 3697 | case '1': /* end composition */ |
e951386e | 3698 | if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3699 | goto invalid_code; |
3700 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3701 | continue; |
4ed46869 KH |
3702 | |
3703 | case '[': /* specification of direction */ | |
de59072a | 3704 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)) |
df7492f9 | 3705 | goto invalid_code; |
4ed46869 | 3706 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3707 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
ad1746f5 | 3708 | left-to-right, and nonzero means right-to-left. */ |
4ed46869 KH |
3709 | ONE_MORE_BYTE (c1); |
3710 | switch (c1) | |
3711 | { | |
3712 | case ']': /* end of the current direction */ | |
d46c5b12 | 3713 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3714 | |
3715 | case '0': /* end of the current direction */ | |
3716 | case '1': /* start of left-to-right direction */ | |
3717 | ONE_MORE_BYTE (c1); | |
3718 | if (c1 == ']') | |
d46c5b12 | 3719 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3720 | else |
df7492f9 | 3721 | goto invalid_code; |
4ed46869 KH |
3722 | break; |
3723 | ||
3724 | case '2': /* start of right-to-left direction */ | |
3725 | ONE_MORE_BYTE (c1); | |
3726 | if (c1 == ']') | |
d46c5b12 | 3727 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3728 | else |
df7492f9 | 3729 | goto invalid_code; |
4ed46869 KH |
3730 | break; |
3731 | ||
3732 | default: | |
df7492f9 | 3733 | goto invalid_code; |
4ed46869 | 3734 | } |
b73bfc1c | 3735 | continue; |
4ed46869 | 3736 | |
103e0180 | 3737 | case '%': |
103e0180 KH |
3738 | ONE_MORE_BYTE (c1); |
3739 | if (c1 == '/') | |
3740 | { | |
3741 | /* CTEXT extended segment: | |
3742 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3743 | We keep these bytes as is for the moment. | |
3744 | They may be decoded by post-read-conversion. */ | |
3745 | int dim, M, L; | |
4776e638 | 3746 | int size; |
8f924df7 | 3747 | |
103e0180 | 3748 | ONE_MORE_BYTE (dim); |
7a84eee5 | 3749 | if (dim < '0' || dim > '4') |
e951386e | 3750 | goto invalid_code; |
103e0180 | 3751 | ONE_MORE_BYTE (M); |
e951386e KH |
3752 | if (M < 128) |
3753 | goto invalid_code; | |
103e0180 | 3754 | ONE_MORE_BYTE (L); |
e951386e KH |
3755 | if (L < 128) |
3756 | goto invalid_code; | |
103e0180 | 3757 | size = ((M - 128) * 128) + (L - 128); |
e951386e | 3758 | if (charbuf + 6 > charbuf_end) |
4776e638 KH |
3759 | goto break_loop; |
3760 | *charbuf++ = ISO_CODE_ESC; | |
3761 | *charbuf++ = '%'; | |
3762 | *charbuf++ = '/'; | |
3763 | *charbuf++ = dim; | |
3764 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3765 | *charbuf++ = BYTE8_TO_CHAR (L); | |
e951386e | 3766 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
103e0180 KH |
3767 | } |
3768 | else if (c1 == 'G') | |
3769 | { | |
103e0180 KH |
3770 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3771 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3772 | We keep these bytes as is for the moment. | |
3773 | They may be decoded by post-read-conversion. */ | |
e951386e | 3774 | if (charbuf + 3 > charbuf_end) |
4776e638 | 3775 | goto break_loop; |
e951386e KH |
3776 | *charbuf++ = ISO_CODE_ESC; |
3777 | *charbuf++ = '%'; | |
3778 | *charbuf++ = 'G'; | |
3779 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; | |
103e0180 KH |
3780 | } |
3781 | else | |
4776e638 | 3782 | goto invalid_code; |
103e0180 | 3783 | continue; |
4776e638 | 3784 | break; |
103e0180 | 3785 | |
4ed46869 | 3786 | default: |
df7492f9 KH |
3787 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3788 | goto invalid_code; | |
134b9549 KH |
3789 | { |
3790 | int reg, chars96; | |
3791 | ||
3792 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3793 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3794 | reg = c1 - 0x28, chars96 = 0; | |
3795 | ONE_MORE_BYTE (c1); | |
3796 | } | |
3797 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3798 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3799 | reg = c1 - 0x2C, chars96 = 1; | |
3800 | ONE_MORE_BYTE (c1); | |
3801 | } | |
3802 | else | |
3803 | goto invalid_code; | |
3804 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3805 | /* We must update these variables now. */ | |
3806 | if (reg == 0) | |
3807 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3808 | else if (reg == 1) | |
3809 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3810 | if (chars96 < 0) | |
3811 | goto invalid_code; | |
3812 | } | |
b73bfc1c | 3813 | continue; |
4ed46869 | 3814 | } |
413bb2db PE |
3815 | break; |
3816 | ||
3817 | default: | |
1088b922 | 3818 | emacs_abort (); |
b73bfc1c | 3819 | } |
4ed46869 | 3820 | |
e951386e KH |
3821 | if (cmp_status->state == COMPOSING_NO |
3822 | && charset->id != charset_ascii | |
ff0dacd7 KH |
3823 | && last_id != charset->id) |
3824 | { | |
3825 | if (last_id != charset_ascii) | |
69a80ea3 | 3826 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3827 | last_id = charset->id; |
3828 | last_offset = char_offset; | |
3829 | } | |
3830 | ||
b73bfc1c | 3831 | /* Now we know CHARSET and 1st position code C1 of a character. |
cf299835 KH |
3832 | Produce a decoded character while getting 2nd and 3rd |
3833 | position codes C2, C3 if necessary. */ | |
df7492f9 | 3834 | if (CHARSET_DIMENSION (charset) > 1) |
b73bfc1c KH |
3835 | { |
3836 | ONE_MORE_BYTE (c2); | |
cf299835 KH |
3837 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0) |
3838 | || ((c1 & 0x80) != (c2 & 0x80))) | |
b73bfc1c | 3839 | /* C2 is not in a valid range. */ |
df7492f9 | 3840 | goto invalid_code; |
cf299835 KH |
3841 | if (CHARSET_DIMENSION (charset) == 2) |
3842 | c1 = (c1 << 8) | c2; | |
3843 | else | |
df7492f9 | 3844 | { |
cf299835 KH |
3845 | ONE_MORE_BYTE (c3); |
3846 | if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0) | |
3847 | || ((c1 & 0x80) != (c3 & 0x80))) | |
3848 | /* C3 is not in a valid range. */ | |
df7492f9 | 3849 | goto invalid_code; |
cf299835 | 3850 | c1 = (c1 << 16) | (c2 << 8) | c2; |
df7492f9 KH |
3851 | } |
3852 | } | |
cf299835 | 3853 | c1 &= 0x7F7F7F; |
df7492f9 KH |
3854 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); |
3855 | if (c < 0) | |
3856 | { | |
3857 | MAYBE_FINISH_COMPOSITION (); | |
3858 | for (; src_base < src; src_base++, char_offset++) | |
3859 | { | |
3860 | if (ASCII_BYTE_P (*src_base)) | |
3861 | *charbuf++ = *src_base; | |
3862 | else | |
3863 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3864 | } | |
3865 | } | |
e951386e | 3866 | else if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3867 | { |
3868 | *charbuf++ = c; | |
3869 | char_offset++; | |
4ed46869 | 3870 | } |
e951386e KH |
3871 | else if ((cmp_status->state == COMPOSING_CHAR |
3872 | ? cmp_status->nchars | |
3873 | : cmp_status->ncomps) | |
3874 | >= MAX_COMPOSITION_COMPONENTS) | |
781d7a48 | 3875 | { |
e951386e KH |
3876 | /* Too long composition. */ |
3877 | MAYBE_FINISH_COMPOSITION (); | |
3878 | *charbuf++ = c; | |
3879 | char_offset++; | |
4ed46869 | 3880 | } |
e951386e KH |
3881 | else |
3882 | STORE_COMPOSITION_CHAR (c); | |
4ed46869 KH |
3883 | continue; |
3884 | ||
df7492f9 KH |
3885 | invalid_code: |
3886 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3887 | src = src_base; |
df7492f9 KH |
3888 | consumed_chars = consumed_chars_base; |
3889 | ONE_MORE_BYTE (c); | |
065e3595 | 3890 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3891 | char_offset++; |
df7492f9 | 3892 | coding->errors++; |
4776e638 KH |
3893 | continue; |
3894 | ||
3895 | break_loop: | |
3896 | break; | |
4ed46869 | 3897 | } |
fb88bf2d | 3898 | |
df7492f9 | 3899 | no_more_source: |
e951386e KH |
3900 | if (cmp_status->state != COMPOSING_NO) |
3901 | { | |
3902 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
3903 | MAYBE_FINISH_COMPOSITION (); | |
3904 | else | |
3905 | { | |
3906 | charbuf -= cmp_status->length; | |
3907 | for (i = 0; i < cmp_status->length; i++) | |
3908 | cmp_status->carryover[i] = charbuf[i]; | |
3909 | } | |
3910 | } | |
3911 | else if (last_id != charset_ascii) | |
69a80ea3 | 3912 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3913 | coding->consumed_char += consumed_chars_base; |
3914 | coding->consumed = src_base - coding->source; | |
3915 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3916 | } |
3917 | ||
b73bfc1c | 3918 | |
f4dee582 | 3919 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3920 | |
3921 | /* | |
f4dee582 | 3922 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3923 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3924 | variant has the following specifications: |
df7492f9 | 3925 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3926 | 2. Allows short-form designation? |
3927 | 3. ASCII should be designated to G0 before control characters? | |
3928 | 4. ASCII should be designated to G0 at end of line? | |
3929 | 5. 7-bit environment or 8-bit environment? | |
3930 | 6. Use locking-shift? | |
3931 | 7. Use Single-shift? | |
3932 | And the following two are only for Japanese: | |
3933 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3934 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3935 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3936 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3937 | details. |
4ed46869 KH |
3938 | */ |
3939 | ||
3940 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3941 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3942 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3943 | designation sequence of short-form. */ | |
4ed46869 KH |
3944 | |
3945 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3946 | do { \ | |
df7492f9 | 3947 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
675e2c69 DN |
3948 | const char *intermediate_char_94 = "()*+"; \ |
3949 | const char *intermediate_char_96 = ",-./"; \ | |
df7492f9 | 3950 | int revision = -1; \ |
df7492f9 KH |
3951 | \ |
3952 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3953 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3954 | \ |
3955 | if (revision >= 0) \ | |
70c22245 | 3956 | { \ |
df7492f9 KH |
3957 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3958 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3959 | } \ |
df7492f9 | 3960 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3961 | if (CHARSET_DIMENSION (charset) == 1) \ |
3962 | { \ | |
2735d060 | 3963 | int b; \ |
df7492f9 | 3964 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
2735d060 | 3965 | b = intermediate_char_94[reg]; \ |
4ed46869 | 3966 | else \ |
2735d060 PE |
3967 | b = intermediate_char_96[reg]; \ |
3968 | EMIT_ONE_ASCII_BYTE (b); \ | |
4ed46869 KH |
3969 | } \ |
3970 | else \ | |
3971 | { \ | |
df7492f9 KH |
3972 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3973 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3974 | { \ |
df7492f9 | 3975 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3976 | || reg != 0 \ |
3977 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3978 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3979 | } \ |
3980 | else \ | |
df7492f9 | 3981 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3982 | } \ |
df7492f9 KH |
3983 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3984 | \ | |
3985 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3986 | } while (0) |
3987 | ||
df7492f9 | 3988 | |
4ed46869 KH |
3989 | /* The following two macros produce codes (control character or escape |
3990 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3991 | single-shift-3). */ | |
3992 | ||
df7492f9 KH |
3993 | #define ENCODE_SINGLE_SHIFT_2 \ |
3994 | do { \ | |
3995 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3996 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3997 | else \ | |
3998 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
3999 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4000 | } while (0) |
4001 | ||
df7492f9 KH |
4002 | |
4003 | #define ENCODE_SINGLE_SHIFT_3 \ | |
4004 | do { \ | |
4005 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4006 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
4007 | else \ | |
4008 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
4009 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4010 | } while (0) |
4011 | ||
df7492f9 | 4012 | |
4ed46869 KH |
4013 | /* The following four macros produce codes (control character or |
4014 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
4015 | shift-out, locking-shift-2, and locking-shift-3). */ | |
4016 | ||
df7492f9 KH |
4017 | #define ENCODE_SHIFT_IN \ |
4018 | do { \ | |
4019 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
4020 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
4021 | } while (0) |
4022 | ||
df7492f9 KH |
4023 | |
4024 | #define ENCODE_SHIFT_OUT \ | |
4025 | do { \ | |
4026 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
4027 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
4028 | } while (0) |
4029 | ||
df7492f9 KH |
4030 | |
4031 | #define ENCODE_LOCKING_SHIFT_2 \ | |
4032 | do { \ | |
4033 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4034 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
4035 | } while (0) |
4036 | ||
df7492f9 KH |
4037 | |
4038 | #define ENCODE_LOCKING_SHIFT_3 \ | |
4039 | do { \ | |
4040 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4041 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
4042 | } while (0) |
4043 | ||
df7492f9 | 4044 | |
f4dee582 RS |
4045 | /* Produce codes for a DIMENSION1 character whose character set is |
4046 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
4047 | sequences are also produced in advance if necessary. */ |
4048 | ||
6e85d753 KH |
4049 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
4050 | do { \ | |
df7492f9 | 4051 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4052 | \ |
4053 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
4054 | && id == charset_ascii) \ | |
4055 | { \ | |
4056 | id = charset_jisx0201_roman; \ | |
4057 | charset = CHARSET_FROM_ID (id); \ | |
4058 | } \ | |
4059 | \ | |
df7492f9 | 4060 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4061 | { \ |
df7492f9 KH |
4062 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4063 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 4064 | else \ |
df7492f9 KH |
4065 | EMIT_ONE_BYTE (c1 | 0x80); \ |
4066 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4067 | break; \ |
4068 | } \ | |
df7492f9 | 4069 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4070 | { \ |
df7492f9 | 4071 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
4072 | break; \ |
4073 | } \ | |
df7492f9 | 4074 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4075 | { \ |
df7492f9 | 4076 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
4077 | break; \ |
4078 | } \ | |
6e85d753 KH |
4079 | else \ |
4080 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4081 | must invoke it, or, at first, designate it to some graphic \ | |
4082 | register. Then repeat the loop to actually produce the \ | |
4083 | character. */ \ | |
df7492f9 KH |
4084 | dst = encode_invocation_designation (charset, coding, dst, \ |
4085 | &produced_chars); \ | |
4ed46869 KH |
4086 | } while (1) |
4087 | ||
df7492f9 | 4088 | |
f4dee582 RS |
4089 | /* Produce codes for a DIMENSION2 character whose character set is |
4090 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
4091 | invocation codes are also produced in advance if necessary. */ |
4092 | ||
6e85d753 KH |
4093 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
4094 | do { \ | |
df7492f9 | 4095 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4096 | \ |
4097 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
4098 | && id == charset_jisx0208) \ | |
4099 | { \ | |
4100 | id = charset_jisx0208_1978; \ | |
4101 | charset = CHARSET_FROM_ID (id); \ | |
4102 | } \ | |
4103 | \ | |
df7492f9 | 4104 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4105 | { \ |
df7492f9 KH |
4106 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4107 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 4108 | else \ |
df7492f9 KH |
4109 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
4110 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4111 | break; \ |
4112 | } \ | |
df7492f9 | 4113 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4114 | { \ |
df7492f9 | 4115 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
4116 | break; \ |
4117 | } \ | |
df7492f9 | 4118 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4119 | { \ |
df7492f9 | 4120 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
4121 | break; \ |
4122 | } \ | |
6e85d753 KH |
4123 | else \ |
4124 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4125 | must invoke it, or, at first, designate it to some graphic \ | |
4126 | register. Then repeat the loop to actually produce the \ | |
4127 | character. */ \ | |
df7492f9 KH |
4128 | dst = encode_invocation_designation (charset, coding, dst, \ |
4129 | &produced_chars); \ | |
4ed46869 KH |
4130 | } while (1) |
4131 | ||
05e6f5dc | 4132 | |
df7492f9 KH |
4133 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
4134 | do { \ | |
8f50130c | 4135 | unsigned code; \ |
5eb05ea3 | 4136 | CODING_ENCODE_CHAR (coding, dst, dst_end, (charset), (c), code); \ |
df7492f9 KH |
4137 | \ |
4138 | if (CHARSET_DIMENSION (charset) == 1) \ | |
4139 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
4140 | else \ | |
4141 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 4142 | } while (0) |
bdd9fb48 | 4143 | |
05e6f5dc | 4144 | |
4ed46869 | 4145 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 4146 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
4147 | Return new DST. */ |
4148 | ||
e2f1bab9 | 4149 | static unsigned char * |
cf84bb53 JB |
4150 | encode_invocation_designation (struct charset *charset, |
4151 | struct coding_system *coding, | |
d311d28c | 4152 | unsigned char *dst, ptrdiff_t *p_nchars) |
4ed46869 | 4153 | { |
f10fe38f | 4154 | bool multibytep = coding->dst_multibyte; |
d311d28c | 4155 | ptrdiff_t produced_chars = *p_nchars; |
4ed46869 | 4156 | int reg; /* graphic register number */ |
df7492f9 | 4157 | int id = CHARSET_ID (charset); |
4ed46869 KH |
4158 | |
4159 | /* At first, check designations. */ | |
4160 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 4161 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
4162 | break; |
4163 | ||
4164 | if (reg >= 4) | |
4165 | { | |
4166 | /* CHARSET is not yet designated to any graphic registers. */ | |
4167 | /* At first check the requested designation. */ | |
df7492f9 KH |
4168 | reg = CODING_ISO_REQUEST (coding, id); |
4169 | if (reg < 0) | |
1ba9e4ab KH |
4170 | /* Since CHARSET requests no special designation, designate it |
4171 | to graphic register 0. */ | |
4ed46869 KH |
4172 | reg = 0; |
4173 | ||
4174 | ENCODE_DESIGNATION (charset, reg, coding); | |
4175 | } | |
4176 | ||
df7492f9 KH |
4177 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
4178 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
4179 | { |
4180 | /* Since the graphic register REG is not invoked to any graphic | |
4181 | planes, invoke it to graphic plane 0. */ | |
4182 | switch (reg) | |
4183 | { | |
4184 | case 0: /* graphic register 0 */ | |
4185 | ENCODE_SHIFT_IN; | |
4186 | break; | |
4187 | ||
4188 | case 1: /* graphic register 1 */ | |
4189 | ENCODE_SHIFT_OUT; | |
4190 | break; | |
4191 | ||
4192 | case 2: /* graphic register 2 */ | |
df7492f9 | 4193 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4194 | ENCODE_SINGLE_SHIFT_2; |
4195 | else | |
4196 | ENCODE_LOCKING_SHIFT_2; | |
4197 | break; | |
4198 | ||
4199 | case 3: /* graphic register 3 */ | |
df7492f9 | 4200 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4201 | ENCODE_SINGLE_SHIFT_3; |
4202 | else | |
4203 | ENCODE_LOCKING_SHIFT_3; | |
4204 | break; | |
4205 | } | |
4206 | } | |
b73bfc1c | 4207 | |
df7492f9 | 4208 | *p_nchars = produced_chars; |
4ed46869 KH |
4209 | return dst; |
4210 | } | |
4211 | ||
4ed46869 KH |
4212 | |
4213 | /* Produce codes for designation and invocation to reset the graphic | |
4214 | planes and registers to initial state. */ | |
df7492f9 KH |
4215 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4216 | do { \ | |
4217 | int reg; \ | |
4218 | struct charset *charset; \ | |
4219 | \ | |
4220 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4221 | ENCODE_SHIFT_IN; \ | |
4222 | for (reg = 0; reg < 4; reg++) \ | |
4223 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4224 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4225 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4226 | { \ | |
4227 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4228 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4229 | } \ | |
4ed46869 KH |
4230 | } while (0) |
4231 | ||
df7492f9 | 4232 | |
bdd9fb48 | 4233 | /* Produce designation sequences of charsets in the line started from |
5eb05ea3 KH |
4234 | CHARBUF to a place pointed by DST, and return the number of |
4235 | produced bytes. DST should not directly point a buffer text area | |
4236 | which may be relocated by char_charset call. | |
bdd9fb48 KH |
4237 | |
4238 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4239 | find all the necessary designations. */ |
4240 | ||
6e6c82a4 | 4241 | static ptrdiff_t |
5eb05ea3 KH |
4242 | encode_designation_at_bol (struct coding_system *coding, |
4243 | int *charbuf, int *charbuf_end, | |
461c2ab9 | 4244 | unsigned char *dst) |
e0e989f6 | 4245 | { |
75a3b399 | 4246 | unsigned char *orig = dst; |
df7492f9 | 4247 | struct charset *charset; |
bdd9fb48 KH |
4248 | /* Table of charsets to be designated to each graphic register. */ |
4249 | int r[4]; | |
df7492f9 | 4250 | int c, found = 0, reg; |
d311d28c | 4251 | ptrdiff_t produced_chars = 0; |
f10fe38f | 4252 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4253 | Lisp_Object attrs; |
4254 | Lisp_Object charset_list; | |
4255 | ||
4256 | attrs = CODING_ID_ATTRS (coding->id); | |
4257 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4258 | if (EQ (charset_list, Qiso_2022)) | |
4259 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4260 | |
4261 | for (reg = 0; reg < 4; reg++) | |
4262 | r[reg] = -1; | |
4263 | ||
5eb05ea3 | 4264 | while (charbuf < charbuf_end && found < 4) |
e0e989f6 | 4265 | { |
df7492f9 KH |
4266 | int id; |
4267 | ||
4268 | c = *charbuf++; | |
b73bfc1c KH |
4269 | if (c == '\n') |
4270 | break; | |
df7492f9 KH |
4271 | charset = char_charset (c, charset_list, NULL); |
4272 | id = CHARSET_ID (charset); | |
4273 | reg = CODING_ISO_REQUEST (coding, id); | |
4274 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4275 | { |
4276 | found++; | |
df7492f9 | 4277 | r[reg] = id; |
bdd9fb48 | 4278 | } |
bdd9fb48 KH |
4279 | } |
4280 | ||
4281 | if (found) | |
4282 | { | |
4283 | for (reg = 0; reg < 4; reg++) | |
4284 | if (r[reg] >= 0 | |
df7492f9 KH |
4285 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4286 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4287 | } |
b73bfc1c | 4288 | |
5eb05ea3 | 4289 | return dst - orig; |
e0e989f6 KH |
4290 | } |
4291 | ||
4ed46869 KH |
4292 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4293 | ||
f10fe38f | 4294 | static bool |
971de7fb | 4295 | encode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 4296 | { |
f10fe38f | 4297 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4298 | int *charbuf = coding->charbuf; |
4299 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4300 | unsigned char *dst = coding->destination + coding->produced; | |
4301 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4302 | int safe_room = 16; | |
f10fe38f | 4303 | bool bol_designation |
df7492f9 KH |
4304 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL |
4305 | && CODING_ISO_BOL (coding)); | |
d311d28c | 4306 | ptrdiff_t produced_chars = 0; |
df7492f9 | 4307 | Lisp_Object attrs, eol_type, charset_list; |
f10fe38f | 4308 | bool ascii_compatible; |
b73bfc1c | 4309 | int c; |
ff0dacd7 | 4310 | int preferred_charset_id = -1; |
05e6f5dc | 4311 | |
24a73b0a | 4312 | CODING_GET_INFO (coding, attrs, charset_list); |
0a9564cb | 4313 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
24a73b0a KH |
4314 | if (VECTORP (eol_type)) |
4315 | eol_type = Qunix; | |
4316 | ||
004068e4 | 4317 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4318 | /* Charset list may have been changed. */ |
287c57d7 | 4319 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
1b3b981b | 4320 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
0eecad43 | 4321 | |
a552b35a KH |
4322 | ascii_compatible |
4323 | = (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)) | |
4324 | && ! (CODING_ISO_FLAGS (coding) & (CODING_ISO_FLAG_DESIGNATION | |
4325 | | CODING_ISO_FLAG_LOCKING_SHIFT))); | |
bdd9fb48 | 4326 | |
df7492f9 | 4327 | while (charbuf < charbuf_end) |
4ed46869 | 4328 | { |
df7492f9 | 4329 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4330 | |
df7492f9 | 4331 | if (bol_designation) |
b73bfc1c | 4332 | { |
bdd9fb48 | 4333 | /* We have to produce designation sequences if any now. */ |
5eb05ea3 KH |
4334 | unsigned char desig_buf[16]; |
4335 | int nbytes; | |
8f50130c | 4336 | ptrdiff_t offset; |
5eb05ea3 KH |
4337 | |
4338 | charset_map_loaded = 0; | |
4339 | nbytes = encode_designation_at_bol (coding, charbuf, charbuf_end, | |
4340 | desig_buf); | |
4341 | if (charset_map_loaded | |
c1892f11 | 4342 | && (offset = coding_change_destination (coding))) |
5eb05ea3 KH |
4343 | { |
4344 | dst += offset; | |
4345 | dst_end += offset; | |
4346 | } | |
4347 | memcpy (dst, desig_buf, nbytes); | |
4348 | dst += nbytes; | |
df7492f9 | 4349 | /* We are sure that designation sequences are all ASCII bytes. */ |
5eb05ea3 KH |
4350 | produced_chars += nbytes; |
4351 | bol_designation = 0; | |
4352 | ASSURE_DESTINATION (safe_room); | |
e0e989f6 KH |
4353 | } |
4354 | ||
df7492f9 | 4355 | c = *charbuf++; |
ec6d2bb8 | 4356 | |
ff0dacd7 KH |
4357 | if (c < 0) |
4358 | { | |
4359 | /* Handle an annotation. */ | |
4360 | switch (*charbuf) | |
ec6d2bb8 | 4361 | { |
ff0dacd7 KH |
4362 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4363 | /* Not yet implemented. */ | |
4364 | break; | |
4365 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4366 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4367 | if (preferred_charset_id >= 0 |
4368 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4369 | charset_list))) | |
4370 | preferred_charset_id = -1; | |
4371 | break; | |
4372 | default: | |
1088b922 | 4373 | emacs_abort (); |
4ed46869 | 4374 | } |
ff0dacd7 KH |
4375 | charbuf += -c - 1; |
4376 | continue; | |
4ed46869 | 4377 | } |
ec6d2bb8 | 4378 | |
b73bfc1c KH |
4379 | /* Now encode the character C. */ |
4380 | if (c < 0x20 || c == 0x7F) | |
4381 | { | |
df7492f9 KH |
4382 | if (c == '\n' |
4383 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4384 | { |
df7492f9 KH |
4385 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4386 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4387 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4388 | { |
df7492f9 KH |
4389 | int i; |
4390 | ||
4391 | for (i = 0; i < 4; i++) | |
4392 | CODING_ISO_DESIGNATION (coding, i) | |
4393 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4394 | } |
f10fe38f PE |
4395 | bol_designation = ((CODING_ISO_FLAGS (coding) |
4396 | & CODING_ISO_FLAG_DESIGNATE_AT_BOL) | |
4397 | != 0); | |
19a8d9e0 | 4398 | } |
df7492f9 KH |
4399 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4400 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4401 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4402 | } |
df7492f9 | 4403 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4404 | { |
df7492f9 KH |
4405 | if (ascii_compatible) |
4406 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4407 | else |
19a8d9e0 | 4408 | { |
bf16eb23 KH |
4409 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4410 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4411 | } |
4ed46869 | 4412 | } |
16eafb5d | 4413 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4414 | { |
16eafb5d KH |
4415 | c = CHAR_TO_BYTE8 (c); |
4416 | EMIT_ONE_BYTE (c); | |
88993dfd | 4417 | } |
b73bfc1c | 4418 | else |
df7492f9 | 4419 | { |
ff0dacd7 | 4420 | struct charset *charset; |
b73bfc1c | 4421 | |
ff0dacd7 KH |
4422 | if (preferred_charset_id >= 0) |
4423 | { | |
f10fe38f | 4424 | bool result; |
5eb05ea3 | 4425 | |
ff0dacd7 | 4426 | charset = CHARSET_FROM_ID (preferred_charset_id); |
5eb05ea3 KH |
4427 | CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result); |
4428 | if (! result) | |
4429 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4430 | NULL, charset); | |
ff0dacd7 KH |
4431 | } |
4432 | else | |
5eb05ea3 KH |
4433 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
4434 | NULL, charset); | |
df7492f9 KH |
4435 | if (!charset) |
4436 | { | |
41cbe562 KH |
4437 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4438 | { | |
4439 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4440 | charset = CHARSET_FROM_ID (charset_ascii); | |
4441 | } | |
4442 | else | |
4443 | { | |
4444 | c = coding->default_char; | |
5eb05ea3 KH |
4445 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4446 | charset_list, NULL, charset); | |
41cbe562 | 4447 | } |
df7492f9 KH |
4448 | } |
4449 | ENCODE_ISO_CHARACTER (charset, c); | |
4450 | } | |
84fbb8a0 | 4451 | } |
b73bfc1c | 4452 | |
df7492f9 KH |
4453 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4454 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4455 | { | |
4456 | ASSURE_DESTINATION (safe_room); | |
4457 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4458 | } | |
065e3595 | 4459 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4460 | CODING_ISO_BOL (coding) = bol_designation; |
4461 | coding->produced_char += produced_chars; | |
4462 | coding->produced = dst - coding->destination; | |
4463 | return 0; | |
4ed46869 KH |
4464 | } |
4465 | ||
4466 | \f | |
df7492f9 | 4467 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4468 | |
df7492f9 | 4469 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4470 | quite widely. So, for the moment, Emacs supports them in the bare |
4471 | C code. But, in the future, they may be supported only by CCL. */ | |
4472 | ||
4473 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4474 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4475 | as is. A character of charset katakana-jisx0201 is encoded by | |
4476 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4477 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4478 | so that it fit in the range below. |
4ed46869 KH |
4479 | |
4480 | --- CODE RANGE of SJIS --- | |
4481 | (character set) (range) | |
4482 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4483 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4484 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4485 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4486 | ------------------------------- |
4487 | ||
4488 | */ | |
4489 | ||
4490 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4491 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4492 | character set and is encoded in two-byte. |
4ed46869 KH |
4493 | |
4494 | --- CODE RANGE of BIG5 --- | |
4495 | (character set) (range) | |
4496 | ASCII 0x00 .. 0x7F | |
4497 | Big5 (1st byte) 0xA1 .. 0xFE | |
4498 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4499 | -------------------------- | |
4500 | ||
df7492f9 | 4501 | */ |
4ed46869 KH |
4502 | |
4503 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 4504 | Return true if a text is encoded in SJIS. */ |
4ed46869 | 4505 | |
f10fe38f | 4506 | static bool |
cf84bb53 JB |
4507 | detect_coding_sjis (struct coding_system *coding, |
4508 | struct coding_detection_info *detect_info) | |
4ed46869 | 4509 | { |
065e3595 | 4510 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4511 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 4512 | bool multibytep = coding->src_multibyte; |
d311d28c | 4513 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 4514 | int found = 0; |
b73bfc1c | 4515 | int c; |
f07190ca KH |
4516 | Lisp_Object attrs, charset_list; |
4517 | int max_first_byte_of_2_byte_code; | |
4518 | ||
4519 | CODING_GET_INFO (coding, attrs, charset_list); | |
4520 | max_first_byte_of_2_byte_code | |
4521 | = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF); | |
df7492f9 | 4522 | |
ff0dacd7 | 4523 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4524 | /* A coding system of this category is always ASCII compatible. */ |
4525 | src += coding->head_ascii; | |
4ed46869 | 4526 | |
b73bfc1c | 4527 | while (1) |
4ed46869 | 4528 | { |
065e3595 | 4529 | src_base = src; |
df7492f9 | 4530 | ONE_MORE_BYTE (c); |
682169fe KH |
4531 | if (c < 0x80) |
4532 | continue; | |
f07190ca KH |
4533 | if ((c >= 0x81 && c <= 0x9F) |
4534 | || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code)) | |
4ed46869 | 4535 | { |
df7492f9 | 4536 | ONE_MORE_BYTE (c); |
682169fe | 4537 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4538 | break; |
ff0dacd7 | 4539 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4540 | } |
df7492f9 | 4541 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4542 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4543 | else |
4544 | break; | |
4ed46869 | 4545 | } |
ff0dacd7 | 4546 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4547 | return 0; |
4548 | ||
4549 | no_more_source: | |
065e3595 | 4550 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4551 | { |
ff0dacd7 | 4552 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 4553 | return 0; |
4ed46869 | 4554 | } |
ff0dacd7 KH |
4555 | detect_info->found |= found; |
4556 | return 1; | |
4ed46869 KH |
4557 | } |
4558 | ||
4559 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 4560 | Return true if a text is encoded in BIG5. */ |
4ed46869 | 4561 | |
f10fe38f | 4562 | static bool |
cf84bb53 JB |
4563 | detect_coding_big5 (struct coding_system *coding, |
4564 | struct coding_detection_info *detect_info) | |
4ed46869 | 4565 | { |
065e3595 | 4566 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4567 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 4568 | bool multibytep = coding->src_multibyte; |
d311d28c | 4569 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 4570 | int found = 0; |
b73bfc1c | 4571 | int c; |
fa42c37f | 4572 | |
ff0dacd7 | 4573 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4574 | /* A coding system of this category is always ASCII compatible. */ |
4575 | src += coding->head_ascii; | |
fa42c37f | 4576 | |
b73bfc1c | 4577 | while (1) |
fa42c37f | 4578 | { |
065e3595 | 4579 | src_base = src; |
df7492f9 KH |
4580 | ONE_MORE_BYTE (c); |
4581 | if (c < 0x80) | |
fa42c37f | 4582 | continue; |
df7492f9 | 4583 | if (c >= 0xA1) |
fa42c37f | 4584 | { |
df7492f9 KH |
4585 | ONE_MORE_BYTE (c); |
4586 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4587 | return 0; |
ff0dacd7 | 4588 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4589 | } |
df7492f9 KH |
4590 | else |
4591 | break; | |
fa42c37f | 4592 | } |
ff0dacd7 | 4593 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4594 | return 0; |
fa42c37f | 4595 | |
df7492f9 | 4596 | no_more_source: |
065e3595 | 4597 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4598 | { |
ff0dacd7 | 4599 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4600 | return 0; |
4601 | } | |
ff0dacd7 KH |
4602 | detect_info->found |= found; |
4603 | return 1; | |
fa42c37f KH |
4604 | } |
4605 | ||
f10fe38f | 4606 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
fa42c37f | 4607 | |
b73bfc1c | 4608 | static void |
971de7fb | 4609 | decode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4610 | { |
8f924df7 KH |
4611 | const unsigned char *src = coding->source + coding->consumed; |
4612 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4613 | const unsigned char *src_base; | |
69a80ea3 | 4614 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4615 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4616 | the end. */ |
69a80ea3 | 4617 | int *charbuf_end |
df80c7f0 | 4618 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 4619 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 4620 | bool multibytep = coding->src_multibyte; |
df7492f9 | 4621 | struct charset *charset_roman, *charset_kanji, *charset_kana; |
57a47f8a | 4622 | struct charset *charset_kanji2; |
24a73b0a | 4623 | Lisp_Object attrs, charset_list, val; |
d311d28c PE |
4624 | ptrdiff_t char_offset = coding->produced_char; |
4625 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 4626 | int last_id = charset_ascii; |
f10fe38f PE |
4627 | bool eol_dos |
4628 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4629 | int byte_after_cr = -1; |
a5d301df | 4630 | |
24a73b0a | 4631 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4632 | |
4633 | val = charset_list; | |
4634 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4635 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4636 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4637 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4638 | |
b73bfc1c | 4639 | while (1) |
4ed46869 | 4640 | { |
df7492f9 | 4641 | int c, c1; |
24a73b0a | 4642 | struct charset *charset; |
fa42c37f | 4643 | |
b73bfc1c | 4644 | src_base = src; |
df7492f9 | 4645 | consumed_chars_base = consumed_chars; |
fa42c37f | 4646 | |
df7492f9 | 4647 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4648 | { |
4649 | if (byte_after_cr >= 0) | |
4650 | src_base--; | |
4651 | break; | |
4652 | } | |
df7492f9 | 4653 | |
119852e7 KH |
4654 | if (byte_after_cr >= 0) |
4655 | c = byte_after_cr, byte_after_cr = -1; | |
4656 | else | |
4657 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4658 | if (c < 0) |
4659 | goto invalid_code; | |
24a73b0a | 4660 | if (c < 0x80) |
119852e7 | 4661 | { |
2735d060 | 4662 | if (eol_dos && c == '\r') |
119852e7 KH |
4663 | ONE_MORE_BYTE (byte_after_cr); |
4664 | charset = charset_roman; | |
4665 | } | |
57a47f8a | 4666 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4667 | goto invalid_code; |
57a47f8a KH |
4668 | else if (c >= 0xA1 && c <= 0xDF) |
4669 | { | |
4670 | /* SJIS -> JISX0201-Kana */ | |
4671 | c &= 0x7F; | |
4672 | charset = charset_kana; | |
4673 | } | |
4674 | else if (c <= 0xEF) | |
df7492f9 | 4675 | { |
57a47f8a KH |
4676 | /* SJIS -> JISX0208 */ |
4677 | ONE_MORE_BYTE (c1); | |
4678 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4679 | goto invalid_code; |
57a47f8a KH |
4680 | c = (c << 8) | c1; |
4681 | SJIS_TO_JIS (c); | |
4682 | charset = charset_kanji; | |
4683 | } | |
4684 | else if (c <= 0xFC && charset_kanji2) | |
4685 | { | |
c6876370 | 4686 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4687 | ONE_MORE_BYTE (c1); |
4688 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4689 | goto invalid_code; |
57a47f8a KH |
4690 | c = (c << 8) | c1; |
4691 | SJIS_TO_JIS2 (c); | |
4692 | charset = charset_kanji2; | |
df7492f9 | 4693 | } |
57a47f8a KH |
4694 | else |
4695 | goto invalid_code; | |
24a73b0a KH |
4696 | if (charset->id != charset_ascii |
4697 | && last_id != charset->id) | |
4698 | { | |
4699 | if (last_id != charset_ascii) | |
69a80ea3 | 4700 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4701 | last_id = charset->id; |
4702 | last_offset = char_offset; | |
4703 | } | |
4704 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4705 | *charbuf++ = c; |
ff0dacd7 | 4706 | char_offset++; |
df7492f9 | 4707 | continue; |
b73bfc1c | 4708 | |
df7492f9 KH |
4709 | invalid_code: |
4710 | src = src_base; | |
4711 | consumed_chars = consumed_chars_base; | |
4712 | ONE_MORE_BYTE (c); | |
065e3595 | 4713 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4714 | char_offset++; |
df7492f9 KH |
4715 | coding->errors++; |
4716 | } | |
fa42c37f | 4717 | |
df7492f9 | 4718 | no_more_source: |
ff0dacd7 | 4719 | if (last_id != charset_ascii) |
69a80ea3 | 4720 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4721 | coding->consumed_char += consumed_chars_base; |
4722 | coding->consumed = src_base - coding->source; | |
4723 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4724 | } |
4725 | ||
b73bfc1c | 4726 | static void |
971de7fb | 4727 | decode_coding_big5 (struct coding_system *coding) |
4ed46869 | 4728 | { |
8f924df7 KH |
4729 | const unsigned char *src = coding->source + coding->consumed; |
4730 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4731 | const unsigned char *src_base; | |
69a80ea3 | 4732 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4733 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4734 | the end. */ |
69a80ea3 | 4735 | int *charbuf_end |
df80c7f0 | 4736 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 4737 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 4738 | bool multibytep = coding->src_multibyte; |
df7492f9 | 4739 | struct charset *charset_roman, *charset_big5; |
24a73b0a | 4740 | Lisp_Object attrs, charset_list, val; |
d311d28c PE |
4741 | ptrdiff_t char_offset = coding->produced_char; |
4742 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 4743 | int last_id = charset_ascii; |
f10fe38f PE |
4744 | bool eol_dos |
4745 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4746 | int byte_after_cr = -1; |
df7492f9 | 4747 | |
24a73b0a | 4748 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4749 | val = charset_list; |
4750 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4751 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4752 | |
b73bfc1c | 4753 | while (1) |
4ed46869 | 4754 | { |
df7492f9 | 4755 | int c, c1; |
24a73b0a | 4756 | struct charset *charset; |
b73bfc1c KH |
4757 | |
4758 | src_base = src; | |
df7492f9 KH |
4759 | consumed_chars_base = consumed_chars; |
4760 | ||
4761 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4762 | { |
4763 | if (byte_after_cr >= 0) | |
4764 | src_base--; | |
4765 | break; | |
4766 | } | |
df7492f9 | 4767 | |
119852e7 | 4768 | if (byte_after_cr >= 0) |
14daee73 | 4769 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4770 | else |
4771 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4772 | |
065e3595 KH |
4773 | if (c < 0) |
4774 | goto invalid_code; | |
24a73b0a | 4775 | if (c < 0x80) |
119852e7 | 4776 | { |
2735d060 | 4777 | if (eol_dos && c == '\r') |
119852e7 KH |
4778 | ONE_MORE_BYTE (byte_after_cr); |
4779 | charset = charset_roman; | |
4780 | } | |
24a73b0a | 4781 | else |
4ed46869 | 4782 | { |
24a73b0a KH |
4783 | /* BIG5 -> Big5 */ |
4784 | if (c < 0xA1 || c > 0xFE) | |
4785 | goto invalid_code; | |
4786 | ONE_MORE_BYTE (c1); | |
4787 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4788 | goto invalid_code; | |
4789 | c = c << 8 | c1; | |
4790 | charset = charset_big5; | |
4ed46869 | 4791 | } |
24a73b0a KH |
4792 | if (charset->id != charset_ascii |
4793 | && last_id != charset->id) | |
df7492f9 | 4794 | { |
24a73b0a | 4795 | if (last_id != charset_ascii) |
69a80ea3 | 4796 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4797 | last_id = charset->id; |
4798 | last_offset = char_offset; | |
4ed46869 | 4799 | } |
24a73b0a | 4800 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4801 | *charbuf++ = c; |
ff0dacd7 | 4802 | char_offset++; |
fb88bf2d KH |
4803 | continue; |
4804 | ||
df7492f9 | 4805 | invalid_code: |
4ed46869 | 4806 | src = src_base; |
df7492f9 KH |
4807 | consumed_chars = consumed_chars_base; |
4808 | ONE_MORE_BYTE (c); | |
065e3595 | 4809 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4810 | char_offset++; |
df7492f9 | 4811 | coding->errors++; |
fb88bf2d | 4812 | } |
d46c5b12 | 4813 | |
df7492f9 | 4814 | no_more_source: |
ff0dacd7 | 4815 | if (last_id != charset_ascii) |
69a80ea3 | 4816 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4817 | coding->consumed_char += consumed_chars_base; |
4818 | coding->consumed = src_base - coding->source; | |
4819 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4820 | } |
4821 | ||
4822 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4823 | This function can encode charsets `ascii', `katakana-jisx0201', |
4824 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4825 | are sure that all these charsets are registered as official charset | |
4ed46869 | 4826 | (i.e. do not have extended leading-codes). Characters of other |
f10fe38f | 4827 | charsets are produced without any encoding. */ |
4ed46869 | 4828 | |
f10fe38f | 4829 | static bool |
971de7fb | 4830 | encode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4831 | { |
f10fe38f | 4832 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4833 | int *charbuf = coding->charbuf; |
4834 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4835 | unsigned char *dst = coding->destination + coding->produced; | |
4836 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4837 | int safe_room = 4; | |
d311d28c | 4838 | ptrdiff_t produced_chars = 0; |
24a73b0a | 4839 | Lisp_Object attrs, charset_list, val; |
f10fe38f | 4840 | bool ascii_compatible; |
66ebf983 | 4841 | struct charset *charset_kanji, *charset_kana; |
57a47f8a | 4842 | struct charset *charset_kanji2; |
df7492f9 | 4843 | int c; |
a5d301df | 4844 | |
24a73b0a | 4845 | CODING_GET_INFO (coding, attrs, charset_list); |
66ebf983 | 4846 | val = XCDR (charset_list); |
df7492f9 | 4847 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4848 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4849 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4850 | |
df7492f9 | 4851 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4852 | |
df7492f9 KH |
4853 | while (charbuf < charbuf_end) |
4854 | { | |
4855 | ASSURE_DESTINATION (safe_room); | |
4856 | c = *charbuf++; | |
b73bfc1c | 4857 | /* Now encode the character C. */ |
df7492f9 KH |
4858 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4859 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4860 | else if (CHAR_BYTE8_P (c)) |
4861 | { | |
4862 | c = CHAR_TO_BYTE8 (c); | |
4863 | EMIT_ONE_BYTE (c); | |
4864 | } | |
df7492f9 | 4865 | else |
b73bfc1c | 4866 | { |
df7492f9 | 4867 | unsigned code; |
5eb05ea3 KH |
4868 | struct charset *charset; |
4869 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4870 | &code, charset); | |
df7492f9 KH |
4871 | |
4872 | if (!charset) | |
4ed46869 | 4873 | { |
41cbe562 | 4874 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4875 | { |
41cbe562 KH |
4876 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4877 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4878 | } |
41cbe562 | 4879 | else |
b73bfc1c | 4880 | { |
41cbe562 | 4881 | c = coding->default_char; |
5eb05ea3 KH |
4882 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4883 | charset_list, &code, charset); | |
b73bfc1c | 4884 | } |
b73bfc1c | 4885 | } |
df7492f9 | 4886 | if (code == CHARSET_INVALID_CODE (charset)) |
1088b922 | 4887 | emacs_abort (); |
df7492f9 KH |
4888 | if (charset == charset_kanji) |
4889 | { | |
4890 | int c1, c2; | |
4891 | JIS_TO_SJIS (code); | |
4892 | c1 = code >> 8, c2 = code & 0xFF; | |
4893 | EMIT_TWO_BYTES (c1, c2); | |
4894 | } | |
4895 | else if (charset == charset_kana) | |
4896 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4897 | else if (charset_kanji2 && charset == charset_kanji2) |
4898 | { | |
4899 | int c1, c2; | |
4900 | ||
4901 | c1 = code >> 8; | |
f07190ca KH |
4902 | if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25) |
4903 | || c1 == 0x28 | |
57a47f8a KH |
4904 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) |
4905 | { | |
4906 | JIS_TO_SJIS2 (code); | |
4907 | c1 = code >> 8, c2 = code & 0xFF; | |
4908 | EMIT_TWO_BYTES (c1, c2); | |
4909 | } | |
4910 | else | |
4911 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4912 | } | |
df7492f9 KH |
4913 | else |
4914 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4915 | } | |
4916 | } | |
065e3595 | 4917 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4918 | coding->produced_char += produced_chars; |
4919 | coding->produced = dst - coding->destination; | |
4920 | return 0; | |
4921 | } | |
4922 | ||
f10fe38f | 4923 | static bool |
971de7fb | 4924 | encode_coding_big5 (struct coding_system *coding) |
df7492f9 | 4925 | { |
f10fe38f | 4926 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4927 | int *charbuf = coding->charbuf; |
4928 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4929 | unsigned char *dst = coding->destination + coding->produced; | |
4930 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4931 | int safe_room = 4; | |
d311d28c | 4932 | ptrdiff_t produced_chars = 0; |
24a73b0a | 4933 | Lisp_Object attrs, charset_list, val; |
f10fe38f | 4934 | bool ascii_compatible; |
66ebf983 | 4935 | struct charset *charset_big5; |
df7492f9 KH |
4936 | int c; |
4937 | ||
24a73b0a | 4938 | CODING_GET_INFO (coding, attrs, charset_list); |
66ebf983 | 4939 | val = XCDR (charset_list); |
df7492f9 KH |
4940 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); |
4941 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4942 | ||
4943 | while (charbuf < charbuf_end) | |
4944 | { | |
4945 | ASSURE_DESTINATION (safe_room); | |
4946 | c = *charbuf++; | |
4947 | /* Now encode the character C. */ | |
4948 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4949 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4950 | else if (CHAR_BYTE8_P (c)) |
4951 | { | |
4952 | c = CHAR_TO_BYTE8 (c); | |
4953 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4954 | } |
4955 | else | |
4956 | { | |
df7492f9 | 4957 | unsigned code; |
5eb05ea3 KH |
4958 | struct charset *charset; |
4959 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4960 | &code, charset); | |
df7492f9 KH |
4961 | |
4962 | if (! charset) | |
b73bfc1c | 4963 | { |
41cbe562 | 4964 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4965 | { |
41cbe562 KH |
4966 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4967 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4968 | } |
41cbe562 | 4969 | else |
0eecad43 | 4970 | { |
41cbe562 | 4971 | c = coding->default_char; |
5eb05ea3 KH |
4972 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4973 | charset_list, &code, charset); | |
0eecad43 | 4974 | } |
4ed46869 | 4975 | } |
df7492f9 | 4976 | if (code == CHARSET_INVALID_CODE (charset)) |
1088b922 | 4977 | emacs_abort (); |
df7492f9 | 4978 | if (charset == charset_big5) |
b73bfc1c | 4979 | { |
df7492f9 KH |
4980 | int c1, c2; |
4981 | ||
4982 | c1 = code >> 8, c2 = code & 0xFF; | |
4983 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4984 | } |
df7492f9 KH |
4985 | else |
4986 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4987 | } |
4ed46869 | 4988 | } |
065e3595 | 4989 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4990 | coding->produced_char += produced_chars; |
4991 | coding->produced = dst - coding->destination; | |
4992 | return 0; | |
4ed46869 KH |
4993 | } |
4994 | ||
4995 | \f | |
df7492f9 | 4996 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4997 | |
4998 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f PE |
4999 | Return true if a text is encoded in a coding system of which |
5000 | encoder/decoder are written in CCL program. */ | |
1397dc18 | 5001 | |
f10fe38f | 5002 | static bool |
cf84bb53 JB |
5003 | detect_coding_ccl (struct coding_system *coding, |
5004 | struct coding_detection_info *detect_info) | |
1397dc18 | 5005 | { |
065e3595 | 5006 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5007 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 5008 | bool multibytep = coding->src_multibyte; |
d311d28c | 5009 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 5010 | int found = 0; |
0e219d54 | 5011 | unsigned char *valids; |
d311d28c | 5012 | ptrdiff_t head_ascii = coding->head_ascii; |
df7492f9 KH |
5013 | Lisp_Object attrs; |
5014 | ||
ff0dacd7 KH |
5015 | detect_info->checked |= CATEGORY_MASK_CCL; |
5016 | ||
df7492f9 | 5017 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 5018 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
5019 | attrs = CODING_ID_ATTRS (coding->id); |
5020 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
5021 | src += head_ascii; | |
1397dc18 | 5022 | |
b73bfc1c | 5023 | while (1) |
1397dc18 | 5024 | { |
df7492f9 | 5025 | int c; |
065e3595 KH |
5026 | |
5027 | src_base = src; | |
df7492f9 | 5028 | ONE_MORE_BYTE (c); |
065e3595 | 5029 | if (c < 0 || ! valids[c]) |
df7492f9 | 5030 | break; |
ff0dacd7 KH |
5031 | if ((valids[c] > 1)) |
5032 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 5033 | } |
ff0dacd7 | 5034 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
5035 | return 0; |
5036 | ||
5037 | no_more_source: | |
ff0dacd7 KH |
5038 | detect_info->found |= found; |
5039 | return 1; | |
df7492f9 KH |
5040 | } |
5041 | ||
5042 | static void | |
971de7fb | 5043 | decode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5044 | { |
7c78e542 | 5045 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 5046 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
5047 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5048 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
d311d28c | 5049 | ptrdiff_t consumed_chars = 0; |
f10fe38f | 5050 | bool multibytep = coding->src_multibyte; |
d0396581 | 5051 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 | 5052 | int source_charbuf[1024]; |
fbdc1721 | 5053 | int source_byteidx[1025]; |
24a73b0a | 5054 | Lisp_Object attrs, charset_list; |
df7492f9 | 5055 | |
24a73b0a | 5056 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5057 | |
d0396581 | 5058 | while (1) |
df7492f9 | 5059 | { |
7c78e542 | 5060 | const unsigned char *p = src; |
95402d5f | 5061 | ptrdiff_t offset; |
df7492f9 KH |
5062 | int i = 0; |
5063 | ||
5064 | if (multibytep) | |
fbdc1721 KH |
5065 | { |
5066 | while (i < 1024 && p < src_end) | |
5067 | { | |
5068 | source_byteidx[i] = p - src; | |
5069 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
5070 | } | |
5071 | source_byteidx[i] = p - src; | |
5072 | } | |
df7492f9 KH |
5073 | else |
5074 | while (i < 1024 && p < src_end) | |
5075 | source_charbuf[i++] = *p++; | |
8f924df7 | 5076 | |
df7492f9 | 5077 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
d0396581 | 5078 | ccl->last_block = 1; |
95402d5f KH |
5079 | /* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */ |
5080 | charset_map_loaded = 0; | |
d0396581 KH |
5081 | ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf, |
5082 | charset_list); | |
95402d5f KH |
5083 | if (charset_map_loaded |
5084 | && (offset = coding_change_source (coding))) | |
5085 | { | |
5086 | p += offset; | |
5087 | src += offset; | |
5088 | src_end += offset; | |
5089 | } | |
d0396581 | 5090 | charbuf += ccl->produced; |
fbdc1721 | 5091 | if (multibytep) |
d0396581 | 5092 | src += source_byteidx[ccl->consumed]; |
df7492f9 | 5093 | else |
d0396581 KH |
5094 | src += ccl->consumed; |
5095 | consumed_chars += ccl->consumed; | |
5096 | if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC) | |
df7492f9 KH |
5097 | break; |
5098 | } | |
5099 | ||
d0396581 | 5100 | switch (ccl->status) |
df7492f9 KH |
5101 | { |
5102 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5103 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5104 | break; |
5105 | case CCL_STAT_SUSPEND_BY_DST: | |
d0396581 | 5106 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5107 | break; |
5108 | case CCL_STAT_QUIT: | |
5109 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5110 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5111 | break; |
5112 | default: | |
065e3595 | 5113 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5114 | break; |
5115 | } | |
5116 | coding->consumed_char += consumed_chars; | |
5117 | coding->consumed = src - coding->source; | |
5118 | coding->charbuf_used = charbuf - coding->charbuf; | |
5119 | } | |
5120 | ||
f10fe38f | 5121 | static bool |
971de7fb | 5122 | encode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5123 | { |
fb608df3 | 5124 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
f10fe38f | 5125 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5126 | int *charbuf = coding->charbuf; |
5127 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5128 | unsigned char *dst = coding->destination + coding->produced; | |
5129 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 | 5130 | int destination_charbuf[1024]; |
d311d28c | 5131 | ptrdiff_t produced_chars = 0; |
a53e2e89 | 5132 | int i; |
24a73b0a | 5133 | Lisp_Object attrs, charset_list; |
df7492f9 | 5134 | |
24a73b0a | 5135 | CODING_GET_INFO (coding, attrs, charset_list); |
fb608df3 KH |
5136 | if (coding->consumed_char == coding->src_chars |
5137 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
5138 | ccl->last_block = 1; | |
df7492f9 | 5139 | |
76470ad1 | 5140 | do |
df7492f9 | 5141 | { |
95402d5f KH |
5142 | ptrdiff_t offset; |
5143 | ||
5144 | /* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */ | |
5145 | charset_map_loaded = 0; | |
fb608df3 | 5146 | ccl_driver (ccl, charbuf, destination_charbuf, |
8cffd3e7 | 5147 | charbuf_end - charbuf, 1024, charset_list); |
95402d5f KH |
5148 | if (charset_map_loaded |
5149 | && (offset = coding_change_destination (coding))) | |
5150 | dst += offset; | |
df7492f9 | 5151 | if (multibytep) |
8cffd3e7 | 5152 | { |
fb608df3 KH |
5153 | ASSURE_DESTINATION (ccl->produced * 2); |
5154 | for (i = 0; i < ccl->produced; i++) | |
8cffd3e7 KH |
5155 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); |
5156 | } | |
df7492f9 KH |
5157 | else |
5158 | { | |
fb608df3 KH |
5159 | ASSURE_DESTINATION (ccl->produced); |
5160 | for (i = 0; i < ccl->produced; i++) | |
df7492f9 | 5161 | *dst++ = destination_charbuf[i] & 0xFF; |
fb608df3 | 5162 | produced_chars += ccl->produced; |
df7492f9 | 5163 | } |
fb608df3 KH |
5164 | charbuf += ccl->consumed; |
5165 | if (ccl->status == CCL_STAT_QUIT | |
5166 | || ccl->status == CCL_STAT_INVALID_CMD) | |
8cffd3e7 | 5167 | break; |
df7492f9 | 5168 | } |
76470ad1 | 5169 | while (charbuf < charbuf_end); |
df7492f9 | 5170 | |
fb608df3 | 5171 | switch (ccl->status) |
df7492f9 KH |
5172 | { |
5173 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5174 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5175 | break; |
5176 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 5177 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5178 | break; |
5179 | case CCL_STAT_QUIT: | |
5180 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5181 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5182 | break; |
5183 | default: | |
065e3595 | 5184 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5185 | break; |
1397dc18 | 5186 | } |
df7492f9 KH |
5187 | |
5188 | coding->produced_char += produced_chars; | |
5189 | coding->produced = dst - coding->destination; | |
5190 | return 0; | |
1397dc18 KH |
5191 | } |
5192 | ||
5193 | \f | |
df7492f9 | 5194 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 5195 | |
b73bfc1c | 5196 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 5197 | |
b73bfc1c | 5198 | static void |
971de7fb | 5199 | decode_coding_raw_text (struct coding_system *coding) |
4ed46869 | 5200 | { |
f10fe38f PE |
5201 | bool eol_dos |
5202 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5203 | |
df7492f9 | 5204 | coding->chars_at_source = 1; |
119852e7 KH |
5205 | coding->consumed_char = coding->src_chars; |
5206 | coding->consumed = coding->src_bytes; | |
2735d060 | 5207 | if (eol_dos && coding->source[coding->src_bytes - 1] == '\r') |
119852e7 KH |
5208 | { |
5209 | coding->consumed_char--; | |
5210 | coding->consumed--; | |
5211 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
5212 | } | |
5213 | else | |
5214 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 5215 | } |
4ed46869 | 5216 | |
f10fe38f | 5217 | static bool |
971de7fb | 5218 | encode_coding_raw_text (struct coding_system *coding) |
df7492f9 | 5219 | { |
f10fe38f | 5220 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5221 | int *charbuf = coding->charbuf; |
5222 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5223 | unsigned char *dst = coding->destination + coding->produced; | |
5224 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c | 5225 | ptrdiff_t produced_chars = 0; |
b73bfc1c KH |
5226 | int c; |
5227 | ||
df7492f9 | 5228 | if (multibytep) |
b73bfc1c | 5229 | { |
df7492f9 | 5230 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5231 | |
df7492f9 KH |
5232 | if (coding->src_multibyte) |
5233 | while (charbuf < charbuf_end) | |
5234 | { | |
5235 | ASSURE_DESTINATION (safe_room); | |
5236 | c = *charbuf++; | |
5237 | if (ASCII_CHAR_P (c)) | |
5238 | EMIT_ONE_ASCII_BYTE (c); | |
5239 | else if (CHAR_BYTE8_P (c)) | |
5240 | { | |
5241 | c = CHAR_TO_BYTE8 (c); | |
5242 | EMIT_ONE_BYTE (c); | |
5243 | } | |
5244 | else | |
5245 | { | |
5246 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5247 | |
df7492f9 | 5248 | CHAR_STRING_ADVANCE (c, p1); |
8abc3f12 | 5249 | do |
9d123124 KH |
5250 | { |
5251 | EMIT_ONE_BYTE (*p0); | |
5252 | p0++; | |
5253 | } | |
8abc3f12 | 5254 | while (p0 < p1); |
df7492f9 KH |
5255 | } |
5256 | } | |
b73bfc1c | 5257 | else |
df7492f9 KH |
5258 | while (charbuf < charbuf_end) |
5259 | { | |
5260 | ASSURE_DESTINATION (safe_room); | |
5261 | c = *charbuf++; | |
5262 | EMIT_ONE_BYTE (c); | |
5263 | } | |
5264 | } | |
5265 | else | |
4ed46869 | 5266 | { |
df7492f9 | 5267 | if (coding->src_multibyte) |
d46c5b12 | 5268 | { |
df7492f9 KH |
5269 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5270 | ||
5271 | while (charbuf < charbuf_end) | |
d46c5b12 | 5272 | { |
df7492f9 KH |
5273 | ASSURE_DESTINATION (safe_room); |
5274 | c = *charbuf++; | |
5275 | if (ASCII_CHAR_P (c)) | |
5276 | *dst++ = c; | |
5277 | else if (CHAR_BYTE8_P (c)) | |
5278 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5279 | else |
df7492f9 | 5280 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5281 | } |
5282 | } | |
df7492f9 KH |
5283 | else |
5284 | { | |
5285 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5286 | while (charbuf < charbuf_end && dst < dst_end) | |
5287 | *dst++ = *charbuf++; | |
8f924df7 | 5288 | } |
319a3947 | 5289 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5290 | } |
065e3595 | 5291 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5292 | coding->produced_char += produced_chars; |
df7492f9 KH |
5293 | coding->produced = dst - coding->destination; |
5294 | return 0; | |
4ed46869 KH |
5295 | } |
5296 | ||
ff0dacd7 | 5297 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f | 5298 | Return true if a text is encoded in a charset-based coding system. */ |
ff0dacd7 | 5299 | |
f10fe38f | 5300 | static bool |
cf84bb53 JB |
5301 | detect_coding_charset (struct coding_system *coding, |
5302 | struct coding_detection_info *detect_info) | |
1397dc18 | 5303 | { |
065e3595 | 5304 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5305 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 5306 | bool multibytep = coding->src_multibyte; |
d311d28c | 5307 | ptrdiff_t consumed_chars = 0; |
07295713 | 5308 | Lisp_Object attrs, valids, name; |
584948ac | 5309 | int found = 0; |
d311d28c | 5310 | ptrdiff_t head_ascii = coding->head_ascii; |
f10fe38f | 5311 | bool check_latin_extra = 0; |
1397dc18 | 5312 | |
ff0dacd7 KH |
5313 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5314 | ||
df7492f9 KH |
5315 | coding = &coding_categories[coding_category_charset]; |
5316 | attrs = CODING_ID_ATTRS (coding->id); | |
5317 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 | 5318 | name = CODING_ID_NAME (coding->id); |
51b59d79 | 5319 | if (strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5320 | "iso-8859-", sizeof ("iso-8859-") - 1) == 0 |
51b59d79 | 5321 | || strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5322 | "iso-latin-", sizeof ("iso-latin-") - 1) == 0) |
07295713 | 5323 | check_latin_extra = 1; |
237aabf4 | 5324 | |
df7492f9 | 5325 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5326 | src += head_ascii; |
1397dc18 | 5327 | |
b73bfc1c | 5328 | while (1) |
1397dc18 | 5329 | { |
df7492f9 | 5330 | int c; |
716b3fa0 KH |
5331 | Lisp_Object val; |
5332 | struct charset *charset; | |
5333 | int dim, idx; | |
1397dc18 | 5334 | |
065e3595 | 5335 | src_base = src; |
df7492f9 | 5336 | ONE_MORE_BYTE (c); |
065e3595 KH |
5337 | if (c < 0) |
5338 | continue; | |
716b3fa0 KH |
5339 | val = AREF (valids, c); |
5340 | if (NILP (val)) | |
df7492f9 | 5341 | break; |
584948ac | 5342 | if (c >= 0x80) |
07295713 KH |
5343 | { |
5344 | if (c < 0xA0 | |
237aabf4 JR |
5345 | && check_latin_extra |
5346 | && (!VECTORP (Vlatin_extra_code_table) | |
28be1ada | 5347 | || NILP (AREF (Vlatin_extra_code_table, c)))) |
07295713 KH |
5348 | break; |
5349 | found = CATEGORY_MASK_CHARSET; | |
5350 | } | |
716b3fa0 KH |
5351 | if (INTEGERP (val)) |
5352 | { | |
5353 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5354 | dim = CHARSET_DIMENSION (charset); | |
5355 | for (idx = 1; idx < dim; idx++) | |
5356 | { | |
5357 | if (src == src_end) | |
5358 | goto too_short; | |
5359 | ONE_MORE_BYTE (c); | |
2f9442b8 PE |
5360 | if (c < charset->code_space[(dim - 1 - idx) * 4] |
5361 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
716b3fa0 KH |
5362 | break; |
5363 | } | |
5364 | if (idx < dim) | |
5365 | break; | |
5366 | } | |
5367 | else | |
5368 | { | |
5369 | idx = 1; | |
5370 | for (; CONSP (val); val = XCDR (val)) | |
5371 | { | |
5372 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5373 | dim = CHARSET_DIMENSION (charset); | |
5374 | while (idx < dim) | |
5375 | { | |
5376 | if (src == src_end) | |
5377 | goto too_short; | |
5378 | ONE_MORE_BYTE (c); | |
5379 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5380 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5381 | break; | |
5382 | idx++; | |
5383 | } | |
5384 | if (idx == dim) | |
5385 | { | |
5386 | val = Qnil; | |
5387 | break; | |
5388 | } | |
5389 | } | |
5390 | if (CONSP (val)) | |
5391 | break; | |
5392 | } | |
df7492f9 | 5393 | } |
716b3fa0 | 5394 | too_short: |
ff0dacd7 | 5395 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5396 | return 0; |
4ed46869 | 5397 | |
df7492f9 | 5398 | no_more_source: |
ff0dacd7 KH |
5399 | detect_info->found |= found; |
5400 | return 1; | |
df7492f9 | 5401 | } |
b73bfc1c | 5402 | |
b73bfc1c | 5403 | static void |
971de7fb | 5404 | decode_coding_charset (struct coding_system *coding) |
4ed46869 | 5405 | { |
8f924df7 KH |
5406 | const unsigned char *src = coding->source + coding->consumed; |
5407 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5408 | const unsigned char *src_base; | |
69a80ea3 | 5409 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 5410 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 5411 | the end. */ |
69a80ea3 | 5412 | int *charbuf_end |
df80c7f0 | 5413 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 5414 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 5415 | bool multibytep = coding->src_multibyte; |
66ebf983 PE |
5416 | Lisp_Object attrs = CODING_ID_ATTRS (coding->id); |
5417 | Lisp_Object valids; | |
d311d28c PE |
5418 | ptrdiff_t char_offset = coding->produced_char; |
5419 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 5420 | int last_id = charset_ascii; |
f10fe38f PE |
5421 | bool eol_dos |
5422 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5423 | int byte_after_cr = -1; |
df7492f9 | 5424 | |
4eb6d3f1 | 5425 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5426 | |
df7492f9 | 5427 | while (1) |
4ed46869 | 5428 | { |
4eb6d3f1 | 5429 | int c; |
24a73b0a KH |
5430 | Lisp_Object val; |
5431 | struct charset *charset; | |
5432 | int dim; | |
5433 | int len = 1; | |
5434 | unsigned code; | |
df7492f9 KH |
5435 | |
5436 | src_base = src; | |
5437 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5438 | |
df7492f9 | 5439 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5440 | { |
5441 | if (byte_after_cr >= 0) | |
5442 | src_base--; | |
5443 | break; | |
5444 | } | |
df7492f9 | 5445 | |
119852e7 KH |
5446 | if (byte_after_cr >= 0) |
5447 | { | |
5448 | c = byte_after_cr; | |
5449 | byte_after_cr = -1; | |
5450 | } | |
5451 | else | |
5452 | { | |
5453 | ONE_MORE_BYTE (c); | |
2735d060 | 5454 | if (eol_dos && c == '\r') |
119852e7 KH |
5455 | ONE_MORE_BYTE (byte_after_cr); |
5456 | } | |
065e3595 KH |
5457 | if (c < 0) |
5458 | goto invalid_code; | |
24a73b0a KH |
5459 | code = c; |
5460 | ||
5461 | val = AREF (valids, c); | |
1b17adfd | 5462 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5463 | goto invalid_code; |
5464 | if (INTEGERP (val)) | |
d46c5b12 | 5465 | { |
24a73b0a KH |
5466 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5467 | dim = CHARSET_DIMENSION (charset); | |
5468 | while (len < dim) | |
b73bfc1c | 5469 | { |
24a73b0a KH |
5470 | ONE_MORE_BYTE (c); |
5471 | code = (code << 8) | c; | |
5472 | len++; | |
b73bfc1c | 5473 | } |
24a73b0a KH |
5474 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5475 | charset, code, c); | |
d46c5b12 | 5476 | } |
df7492f9 | 5477 | else |
d46c5b12 | 5478 | { |
24a73b0a KH |
5479 | /* VAL is a list of charset IDs. It is assured that the |
5480 | list is sorted by charset dimensions (smaller one | |
5481 | comes first). */ | |
5482 | while (CONSP (val)) | |
4eb6d3f1 | 5483 | { |
24a73b0a | 5484 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5485 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5486 | while (len < dim) |
4eb6d3f1 | 5487 | { |
acb2a965 KH |
5488 | ONE_MORE_BYTE (c); |
5489 | code = (code << 8) | c; | |
f9d71dcd | 5490 | len++; |
4eb6d3f1 | 5491 | } |
24a73b0a KH |
5492 | CODING_DECODE_CHAR (coding, src, src_base, |
5493 | src_end, charset, code, c); | |
5494 | if (c >= 0) | |
5495 | break; | |
5496 | val = XCDR (val); | |
ff0dacd7 | 5497 | } |
d46c5b12 | 5498 | } |
24a73b0a KH |
5499 | if (c < 0) |
5500 | goto invalid_code; | |
5501 | if (charset->id != charset_ascii | |
5502 | && last_id != charset->id) | |
5503 | { | |
5504 | if (last_id != charset_ascii) | |
69a80ea3 | 5505 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5506 | last_id = charset->id; |
5507 | last_offset = char_offset; | |
5508 | } | |
5509 | ||
df7492f9 | 5510 | *charbuf++ = c; |
ff0dacd7 | 5511 | char_offset++; |
df7492f9 KH |
5512 | continue; |
5513 | ||
5514 | invalid_code: | |
5515 | src = src_base; | |
5516 | consumed_chars = consumed_chars_base; | |
5517 | ONE_MORE_BYTE (c); | |
065e3595 | 5518 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5519 | char_offset++; |
df7492f9 | 5520 | coding->errors++; |
4ed46869 KH |
5521 | } |
5522 | ||
df7492f9 | 5523 | no_more_source: |
ff0dacd7 | 5524 | if (last_id != charset_ascii) |
69a80ea3 | 5525 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5526 | coding->consumed_char += consumed_chars_base; |
5527 | coding->consumed = src_base - coding->source; | |
5528 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5529 | } |
5530 | ||
f10fe38f | 5531 | static bool |
971de7fb | 5532 | encode_coding_charset (struct coding_system *coding) |
4ed46869 | 5533 | { |
f10fe38f | 5534 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5535 | int *charbuf = coding->charbuf; |
5536 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5537 | unsigned char *dst = coding->destination + coding->produced; | |
5538 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5539 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
d311d28c | 5540 | ptrdiff_t produced_chars = 0; |
24a73b0a | 5541 | Lisp_Object attrs, charset_list; |
f10fe38f | 5542 | bool ascii_compatible; |
b73bfc1c | 5543 | int c; |
b73bfc1c | 5544 | |
24a73b0a | 5545 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5546 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5547 | |
df7492f9 | 5548 | while (charbuf < charbuf_end) |
4ed46869 | 5549 | { |
4eb6d3f1 | 5550 | struct charset *charset; |
df7492f9 | 5551 | unsigned code; |
8f924df7 | 5552 | |
df7492f9 KH |
5553 | ASSURE_DESTINATION (safe_room); |
5554 | c = *charbuf++; | |
5555 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5556 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5557 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5558 | { |
16eafb5d KH |
5559 | c = CHAR_TO_BYTE8 (c); |
5560 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5561 | } |
d46c5b12 | 5562 | else |
b73bfc1c | 5563 | { |
5eb05ea3 KH |
5564 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
5565 | &code, charset); | |
5566 | ||
4eb6d3f1 KH |
5567 | if (charset) |
5568 | { | |
5569 | if (CHARSET_DIMENSION (charset) == 1) | |
5570 | EMIT_ONE_BYTE (code); | |
5571 | else if (CHARSET_DIMENSION (charset) == 2) | |
5572 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5573 | else if (CHARSET_DIMENSION (charset) == 3) | |
5574 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5575 | else | |
5576 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5577 | (code >> 8) & 0xFF, code & 0xFF); | |
5578 | } | |
5579 | else | |
41cbe562 KH |
5580 | { |
5581 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5582 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5583 | else | |
5584 | c = coding->default_char; | |
5585 | EMIT_ONE_BYTE (c); | |
5586 | } | |
4ed46869 | 5587 | } |
4ed46869 KH |
5588 | } |
5589 | ||
065e3595 | 5590 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5591 | coding->produced_char += produced_chars; |
5592 | coding->produced = dst - coding->destination; | |
5593 | return 0; | |
4ed46869 KH |
5594 | } |
5595 | ||
5596 | \f | |
1397dc18 | 5597 | /*** 7. C library functions ***/ |
4ed46869 | 5598 | |
df7492f9 KH |
5599 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5600 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5601 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5602 | |
ec6d2bb8 | 5603 | void |
971de7fb | 5604 | setup_coding_system (Lisp_Object coding_system, struct coding_system *coding) |
4ed46869 | 5605 | { |
df7492f9 KH |
5606 | Lisp_Object attrs; |
5607 | Lisp_Object eol_type; | |
5608 | Lisp_Object coding_type; | |
4608c386 | 5609 | Lisp_Object val; |
4ed46869 | 5610 | |
df7492f9 | 5611 | if (NILP (coding_system)) |
ae6f73fa | 5612 | coding_system = Qundecided; |
c07c8e12 | 5613 | |
df7492f9 | 5614 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5615 | |
df7492f9 | 5616 | attrs = CODING_ID_ATTRS (coding->id); |
0a9564cb | 5617 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
1f5dbf34 | 5618 | |
df7492f9 KH |
5619 | coding->mode = 0; |
5620 | coding->head_ascii = -1; | |
4a015c45 KH |
5621 | if (VECTORP (eol_type)) |
5622 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5623 | | CODING_REQUIRE_DETECTION_MASK); | |
5624 | else if (! EQ (eol_type, Qunix)) | |
5625 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5626 | | CODING_REQUIRE_ENCODING_MASK); | |
5627 | else | |
5628 | coding->common_flags = 0; | |
5e5c78be KH |
5629 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5630 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5631 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5632 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5633 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5634 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5635 | |
df7492f9 | 5636 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 | 5637 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5638 | coding->safe_charsets = SDATA (val); |
df7492f9 | 5639 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
624bda09 | 5640 | coding->carryover_bytes = 0; |
4608c386 | 5641 | |
df7492f9 KH |
5642 | coding_type = CODING_ATTR_TYPE (attrs); |
5643 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5644 | { |
df7492f9 KH |
5645 | coding->detector = NULL; |
5646 | coding->decoder = decode_coding_raw_text; | |
5647 | coding->encoder = encode_coding_raw_text; | |
5648 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5649 | } |
df7492f9 | 5650 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5651 | { |
df7492f9 KH |
5652 | int i; |
5653 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5654 | ||
5655 | /* Invoke graphic register 0 to plane 0. */ | |
5656 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5657 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5658 | CODING_ISO_INVOCATION (coding, 1) | |
5659 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5660 | /* Setup the initial status of designation. */ | |
5661 | for (i = 0; i < 4; i++) | |
5662 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5663 | /* Not single shifting initially. */ | |
5664 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5665 | /* Beginning of buffer should also be regarded as bol. */ | |
5666 | CODING_ISO_BOL (coding) = 1; | |
5667 | coding->detector = detect_coding_iso_2022; | |
5668 | coding->decoder = decode_coding_iso_2022; | |
5669 | coding->encoder = encode_coding_iso_2022; | |
5670 | if (flags & CODING_ISO_FLAG_SAFE) | |
5671 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5672 | coding->common_flags |
df7492f9 KH |
5673 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5674 | | CODING_REQUIRE_FLUSHING_MASK); | |
5675 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5676 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5677 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5678 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5679 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5680 | { | |
5681 | setup_iso_safe_charsets (attrs); | |
5682 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 5683 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5684 | coding->safe_charsets = SDATA (val); |
df7492f9 KH |
5685 | } |
5686 | CODING_ISO_FLAGS (coding) = flags; | |
e951386e KH |
5687 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; |
5688 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | |
5689 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | |
5690 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
d46c5b12 | 5691 | } |
df7492f9 | 5692 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5693 | { |
df7492f9 KH |
5694 | coding->detector = detect_coding_charset; |
5695 | coding->decoder = decode_coding_charset; | |
5696 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5697 | coding->common_flags |
df7492f9 | 5698 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5699 | } |
df7492f9 | 5700 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5701 | { |
a470d443 KH |
5702 | val = AREF (attrs, coding_attr_utf_bom); |
5703 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5704 | : EQ (val, Qt) ? utf_with_bom | |
5705 | : utf_without_bom); | |
df7492f9 KH |
5706 | coding->detector = detect_coding_utf_8; |
5707 | coding->decoder = decode_coding_utf_8; | |
5708 | coding->encoder = encode_coding_utf_8; | |
5709 | coding->common_flags | |
5710 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5711 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5712 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5713 | } |
5714 | else if (EQ (coding_type, Qutf_16)) | |
5715 | { | |
a470d443 KH |
5716 | val = AREF (attrs, coding_attr_utf_bom); |
5717 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5718 | : EQ (val, Qt) ? utf_with_bom | |
5719 | : utf_without_bom); | |
df7492f9 | 5720 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5721 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5722 | : utf_16_little_endian); |
e19c3639 | 5723 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5724 | coding->detector = detect_coding_utf_16; |
5725 | coding->decoder = decode_coding_utf_16; | |
5726 | coding->encoder = encode_coding_utf_16; | |
5727 | coding->common_flags | |
5728 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5729 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5730 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5731 | } |
df7492f9 | 5732 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5733 | { |
df7492f9 KH |
5734 | coding->detector = detect_coding_ccl; |
5735 | coding->decoder = decode_coding_ccl; | |
5736 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5737 | coding->common_flags |
df7492f9 KH |
5738 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5739 | | CODING_REQUIRE_FLUSHING_MASK); | |
5740 | } | |
5741 | else if (EQ (coding_type, Qemacs_mule)) | |
5742 | { | |
5743 | coding->detector = detect_coding_emacs_mule; | |
5744 | coding->decoder = decode_coding_emacs_mule; | |
5745 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5746 | coding->common_flags |
df7492f9 KH |
5747 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5748 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5749 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5750 | { | |
5751 | Lisp_Object tail, safe_charsets; | |
5752 | int max_charset_id = 0; | |
5753 | ||
5754 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5755 | tail = XCDR (tail)) | |
5756 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5757 | max_charset_id = XFASTINT (XCAR (tail)); | |
1b3b981b AS |
5758 | safe_charsets = make_uninit_string (max_charset_id + 1); |
5759 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
5760 | for (tail = Vemacs_mule_charset_list; CONSP (tail); |
5761 | tail = XCDR (tail)) | |
8f924df7 | 5762 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5763 | coding->max_charset_id = max_charset_id; |
1b3b981b | 5764 | coding->safe_charsets = SDATA (safe_charsets); |
df7492f9 | 5765 | } |
e951386e KH |
5766 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; |
5767 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | |
df7492f9 KH |
5768 | } |
5769 | else if (EQ (coding_type, Qshift_jis)) | |
5770 | { | |
5771 | coding->detector = detect_coding_sjis; | |
5772 | coding->decoder = decode_coding_sjis; | |
5773 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5774 | coding->common_flags |
df7492f9 KH |
5775 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5776 | } | |
5777 | else if (EQ (coding_type, Qbig5)) | |
5778 | { | |
5779 | coding->detector = detect_coding_big5; | |
5780 | coding->decoder = decode_coding_big5; | |
5781 | coding->encoder = encode_coding_big5; | |
c952af22 | 5782 | coding->common_flags |
df7492f9 KH |
5783 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5784 | } | |
5785 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5786 | { |
df7492f9 KH |
5787 | coding->detector = NULL; |
5788 | coding->decoder = decode_coding_raw_text; | |
5789 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5790 | if (! EQ (eol_type, Qunix)) |
5791 | { | |
5792 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5793 | if (! VECTORP (eol_type)) | |
5794 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5795 | } | |
5796 | ||
4ed46869 | 5797 | } |
4ed46869 | 5798 | |
df7492f9 | 5799 | return; |
4ed46869 KH |
5800 | } |
5801 | ||
0ff61e78 KH |
5802 | /* Return a list of charsets supported by CODING. */ |
5803 | ||
5804 | Lisp_Object | |
971de7fb | 5805 | coding_charset_list (struct coding_system *coding) |
0ff61e78 | 5806 | { |
35befdaa | 5807 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5808 | |
5809 | CODING_GET_INFO (coding, attrs, charset_list); | |
5810 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5811 | { | |
5812 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5813 | ||
5814 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5815 | charset_list = Viso_2022_charset_list; | |
5816 | } | |
5817 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5818 | { | |
5819 | charset_list = Vemacs_mule_charset_list; | |
5820 | } | |
5821 | return charset_list; | |
5822 | } | |
5823 | ||
5824 | ||
e9f91ece KH |
5825 | /* Return a list of charsets supported by CODING-SYSTEM. */ |
5826 | ||
5827 | Lisp_Object | |
971de7fb | 5828 | coding_system_charset_list (Lisp_Object coding_system) |
e9f91ece | 5829 | { |
d3411f89 | 5830 | ptrdiff_t id; |
e9f91ece KH |
5831 | Lisp_Object attrs, charset_list; |
5832 | ||
5833 | CHECK_CODING_SYSTEM_GET_ID (coding_system, id); | |
5834 | attrs = CODING_ID_ATTRS (id); | |
5835 | ||
5836 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5837 | { | |
5838 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5839 | ||
5840 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5841 | charset_list = Viso_2022_charset_list; | |
5842 | else | |
5843 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5844 | } | |
5845 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5846 | { | |
5847 | charset_list = Vemacs_mule_charset_list; | |
5848 | } | |
5849 | else | |
5850 | { | |
5851 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5852 | } | |
5853 | return charset_list; | |
5854 | } | |
5855 | ||
5856 | ||
df7492f9 KH |
5857 | /* Return raw-text or one of its subsidiaries that has the same |
5858 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5859 | |
df7492f9 | 5860 | Lisp_Object |
971de7fb | 5861 | raw_text_coding_system (Lisp_Object coding_system) |
ec6d2bb8 | 5862 | { |
0be8721c | 5863 | Lisp_Object spec, attrs; |
df7492f9 | 5864 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5865 | |
d3e4cb56 KH |
5866 | if (NILP (coding_system)) |
5867 | return Qraw_text; | |
df7492f9 KH |
5868 | spec = CODING_SYSTEM_SPEC (coding_system); |
5869 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5870 | |
df7492f9 KH |
5871 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5872 | return coding_system; | |
ec6d2bb8 | 5873 | |
df7492f9 KH |
5874 | eol_type = AREF (spec, 2); |
5875 | if (VECTORP (eol_type)) | |
5876 | return Qraw_text; | |
5877 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5878 | raw_text_eol_type = AREF (spec, 2); | |
5879 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5880 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5881 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5882 | } |
5883 | ||
54f78171 | 5884 | |
1911a33b KH |
5885 | /* If CODING_SYSTEM doesn't specify end-of-line format, return one of |
5886 | the subsidiary that has the same eol-spec as PARENT (if it is not | |
5887 | nil and specifies end-of-line format) or the system's setting | |
fcbcfb64 | 5888 | (system_eol_type). */ |
df7492f9 KH |
5889 | |
5890 | Lisp_Object | |
971de7fb | 5891 | coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent) |
54f78171 | 5892 | { |
3e139625 | 5893 | Lisp_Object spec, eol_type; |
54f78171 | 5894 | |
d3e4cb56 KH |
5895 | if (NILP (coding_system)) |
5896 | coding_system = Qraw_text; | |
df7492f9 | 5897 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5898 | eol_type = AREF (spec, 2); |
fcbcfb64 | 5899 | if (VECTORP (eol_type)) |
df7492f9 | 5900 | { |
df7492f9 KH |
5901 | Lisp_Object parent_eol_type; |
5902 | ||
fcbcfb64 KH |
5903 | if (! NILP (parent)) |
5904 | { | |
5905 | Lisp_Object parent_spec; | |
5906 | ||
4a015c45 | 5907 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 | 5908 | parent_eol_type = AREF (parent_spec, 2); |
1911a33b | 5909 | if (VECTORP (parent_eol_type)) |
4628bef1 | 5910 | parent_eol_type = system_eol_type; |
fcbcfb64 KH |
5911 | } |
5912 | else | |
5913 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
5914 | if (EQ (parent_eol_type, Qunix)) |
5915 | coding_system = AREF (eol_type, 0); | |
5916 | else if (EQ (parent_eol_type, Qdos)) | |
5917 | coding_system = AREF (eol_type, 1); | |
5918 | else if (EQ (parent_eol_type, Qmac)) | |
5919 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5920 | } |
df7492f9 | 5921 | return coding_system; |
54f78171 KH |
5922 | } |
5923 | ||
fcaf8878 KH |
5924 | |
5925 | /* Check if text-conversion and eol-conversion of CODING_SYSTEM are | |
5926 | decided for writing to a process. If not, complement them, and | |
5927 | return a new coding system. */ | |
5928 | ||
5929 | Lisp_Object | |
4628bef1 | 5930 | complement_process_encoding_system (Lisp_Object coding_system) |
fcaf8878 | 5931 | { |
5886ec9c KH |
5932 | Lisp_Object coding_base = Qnil, eol_base = Qnil; |
5933 | Lisp_Object spec, attrs; | |
93d50df8 | 5934 | int i; |
fcaf8878 | 5935 | |
93d50df8 | 5936 | for (i = 0; i < 3; i++) |
fcaf8878 | 5937 | { |
93d50df8 KH |
5938 | if (i == 1) |
5939 | coding_system = CDR_SAFE (Vdefault_process_coding_system); | |
5940 | else if (i == 2) | |
5941 | coding_system = preferred_coding_system (); | |
5942 | spec = CODING_SYSTEM_SPEC (coding_system); | |
5943 | if (NILP (spec)) | |
5944 | continue; | |
5945 | attrs = AREF (spec, 0); | |
5946 | if (NILP (coding_base) && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
5947 | coding_base = CODING_ATTR_BASE_NAME (attrs); | |
5948 | if (NILP (eol_base) && ! VECTORP (AREF (spec, 2))) | |
5949 | eol_base = coding_system; | |
5950 | if (! NILP (coding_base) && ! NILP (eol_base)) | |
5951 | break; | |
fcaf8878 | 5952 | } |
fcaf8878 | 5953 | |
93d50df8 KH |
5954 | if (i > 0) |
5955 | /* The original CODING_SYSTEM didn't specify text-conversion or | |
5956 | eol-conversion. Be sure that we return a fully complemented | |
5957 | coding system. */ | |
5958 | coding_system = coding_inherit_eol_type (coding_base, eol_base); | |
5959 | return coding_system; | |
fcaf8878 KH |
5960 | } |
5961 | ||
5962 | ||
4ed46869 KH |
5963 | /* Emacs has a mechanism to automatically detect a coding system if it |
5964 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5965 | it's impossible to distinguish some coding systems accurately | |
5966 | because they use the same range of codes. So, at first, coding | |
5967 | systems are categorized into 7, those are: | |
5968 | ||
0ef69138 | 5969 | o coding-category-emacs-mule |
4ed46869 KH |
5970 | |
5971 | The category for a coding system which has the same code range | |
5972 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5973 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5974 | |
5975 | o coding-category-sjis | |
5976 | ||
5977 | The category for a coding system which has the same code range | |
5978 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5979 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5980 | |
5981 | o coding-category-iso-7 | |
5982 | ||
5983 | The category for a coding system which has the same code range | |
7717c392 | 5984 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5985 | shift and single shift functions. This can encode/decode all |
5986 | charsets. Assigned the coding-system (Lisp symbol) | |
5987 | `iso-2022-7bit' by default. | |
5988 | ||
5989 | o coding-category-iso-7-tight | |
5990 | ||
5991 | Same as coding-category-iso-7 except that this can | |
5992 | encode/decode only the specified charsets. | |
4ed46869 KH |
5993 | |
5994 | o coding-category-iso-8-1 | |
5995 | ||
5996 | The category for a coding system which has the same code range | |
5997 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5998 | for DIMENSION1 charset. This doesn't use any locking shift |
5999 | and single shift functions. Assigned the coding-system (Lisp | |
6000 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
6001 | |
6002 | o coding-category-iso-8-2 | |
6003 | ||
6004 | The category for a coding system which has the same code range | |
6005 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6006 | for DIMENSION2 charset. This doesn't use any locking shift |
6007 | and single shift functions. Assigned the coding-system (Lisp | |
6008 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 6009 | |
7717c392 | 6010 | o coding-category-iso-7-else |
4ed46869 KH |
6011 | |
6012 | The category for a coding system which has the same code range | |
ad1746f5 | 6013 | as ISO2022 of 7-bit environment but uses locking shift or |
7717c392 KH |
6014 | single shift functions. Assigned the coding-system (Lisp |
6015 | symbol) `iso-2022-7bit-lock' by default. | |
6016 | ||
6017 | o coding-category-iso-8-else | |
6018 | ||
6019 | The category for a coding system which has the same code range | |
ad1746f5 | 6020 | as ISO2022 of 8-bit environment but uses locking shift or |
7717c392 KH |
6021 | single shift functions. Assigned the coding-system (Lisp |
6022 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
6023 | |
6024 | o coding-category-big5 | |
6025 | ||
6026 | The category for a coding system which has the same code range | |
6027 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6028 | `cn-big5' by default. |
4ed46869 | 6029 | |
fa42c37f KH |
6030 | o coding-category-utf-8 |
6031 | ||
6032 | The category for a coding system which has the same code range | |
6e76ae91 | 6033 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
6034 | symbol) `utf-8' by default. |
6035 | ||
6036 | o coding-category-utf-16-be | |
6037 | ||
6038 | The category for a coding system in which a text has an | |
6039 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
6040 | endian at the head. Assigned the coding-system (Lisp symbol) | |
6041 | `utf-16-be' by default. | |
6042 | ||
6043 | o coding-category-utf-16-le | |
6044 | ||
6045 | The category for a coding system in which a text has an | |
6046 | Unicode signature (cf. Unicode Standard) in the order of | |
6047 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
6048 | symbol) `utf-16-le' by default. | |
6049 | ||
1397dc18 KH |
6050 | o coding-category-ccl |
6051 | ||
6052 | The category for a coding system of which encoder/decoder is | |
6053 | written in CCL programs. The default value is nil, i.e., no | |
6054 | coding system is assigned. | |
6055 | ||
4ed46869 KH |
6056 | o coding-category-binary |
6057 | ||
6058 | The category for a coding system not categorized in any of the | |
6059 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6060 | `no-conversion' by default. |
4ed46869 KH |
6061 | |
6062 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 6063 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
6064 | What Emacs does actually is to detect a category of coding system. |
6065 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 6066 | decide only one possible category, it selects a category of the |
4ed46869 KH |
6067 | highest priority. Priorities of categories are also specified by a |
6068 | user in a Lisp variable `coding-category-list'. | |
6069 | ||
6070 | */ | |
6071 | ||
df7492f9 KH |
6072 | #define EOL_SEEN_NONE 0 |
6073 | #define EOL_SEEN_LF 1 | |
6074 | #define EOL_SEEN_CR 2 | |
6075 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 6076 | |
ff0dacd7 KH |
6077 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
6078 | SOURCE is encoded. If CATEGORY is one of | |
6079 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
6080 | two-byte, else they are encoded by one-byte. | |
6081 | ||
6082 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 6083 | |
bc4bc72a | 6084 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
6085 | |
6086 | static int | |
d311d28c | 6087 | detect_eol (const unsigned char *source, ptrdiff_t src_bytes, |
cf84bb53 | 6088 | enum coding_category category) |
4ed46869 | 6089 | { |
f6cbaf43 | 6090 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 6091 | unsigned char c; |
df7492f9 KH |
6092 | int total = 0; |
6093 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 6094 | |
89528eb3 | 6095 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 6096 | { |
f10fe38f PE |
6097 | bool msb = category == (coding_category_utf_16_le |
6098 | | coding_category_utf_16_le_nosig); | |
6099 | bool lsb = !msb; | |
fa42c37f | 6100 | |
df7492f9 | 6101 | while (src + 1 < src_end) |
fa42c37f | 6102 | { |
df7492f9 KH |
6103 | c = src[lsb]; |
6104 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 6105 | { |
df7492f9 KH |
6106 | int this_eol; |
6107 | ||
6108 | if (c == '\n') | |
6109 | this_eol = EOL_SEEN_LF; | |
6110 | else if (src + 3 >= src_end | |
6111 | || src[msb + 2] != 0 | |
6112 | || src[lsb + 2] != '\n') | |
6113 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 6114 | else |
75f4f1ac EZ |
6115 | { |
6116 | this_eol = EOL_SEEN_CRLF; | |
6117 | src += 2; | |
6118 | } | |
df7492f9 KH |
6119 | |
6120 | if (eol_seen == EOL_SEEN_NONE) | |
6121 | /* This is the first end-of-line. */ | |
6122 | eol_seen = this_eol; | |
6123 | else if (eol_seen != this_eol) | |
fa42c37f | 6124 | { |
75f4f1ac EZ |
6125 | /* The found type is different from what found before. |
6126 | Allow for stray ^M characters in DOS EOL files. */ | |
ef1b0ba7 SM |
6127 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) |
6128 | || (eol_seen == EOL_SEEN_CRLF | |
6129 | && this_eol == EOL_SEEN_CR)) | |
75f4f1ac EZ |
6130 | eol_seen = EOL_SEEN_CRLF; |
6131 | else | |
6132 | { | |
6133 | eol_seen = EOL_SEEN_LF; | |
6134 | break; | |
6135 | } | |
fa42c37f | 6136 | } |
df7492f9 KH |
6137 | if (++total == MAX_EOL_CHECK_COUNT) |
6138 | break; | |
fa42c37f | 6139 | } |
df7492f9 | 6140 | src += 2; |
fa42c37f | 6141 | } |
bcf26d6a | 6142 | } |
d46c5b12 | 6143 | else |
ef1b0ba7 SM |
6144 | while (src < src_end) |
6145 | { | |
6146 | c = *src++; | |
6147 | if (c == '\n' || c == '\r') | |
6148 | { | |
6149 | int this_eol; | |
d46c5b12 | 6150 | |
ef1b0ba7 SM |
6151 | if (c == '\n') |
6152 | this_eol = EOL_SEEN_LF; | |
6153 | else if (src >= src_end || *src != '\n') | |
6154 | this_eol = EOL_SEEN_CR; | |
6155 | else | |
6156 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 6157 | |
ef1b0ba7 SM |
6158 | if (eol_seen == EOL_SEEN_NONE) |
6159 | /* This is the first end-of-line. */ | |
6160 | eol_seen = this_eol; | |
6161 | else if (eol_seen != this_eol) | |
6162 | { | |
6163 | /* The found type is different from what found before. | |
6164 | Allow for stray ^M characters in DOS EOL files. */ | |
6165 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) | |
6166 | || (eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR)) | |
6167 | eol_seen = EOL_SEEN_CRLF; | |
6168 | else | |
6169 | { | |
6170 | eol_seen = EOL_SEEN_LF; | |
6171 | break; | |
6172 | } | |
6173 | } | |
6174 | if (++total == MAX_EOL_CHECK_COUNT) | |
6175 | break; | |
6176 | } | |
6177 | } | |
df7492f9 | 6178 | return eol_seen; |
73be902c KH |
6179 | } |
6180 | ||
df7492f9 | 6181 | |
24a73b0a | 6182 | static Lisp_Object |
971de7fb | 6183 | adjust_coding_eol_type (struct coding_system *coding, int eol_seen) |
73be902c | 6184 | { |
0be8721c | 6185 | Lisp_Object eol_type; |
8f924df7 | 6186 | |
df7492f9 KH |
6187 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6188 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
6189 | { |
6190 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6191 | eol_type = Qunix; | |
6192 | } | |
6f197c07 | 6193 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
6194 | { |
6195 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
6196 | eol_type = Qdos; | |
6197 | } | |
6f197c07 | 6198 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
6199 | { |
6200 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
6201 | eol_type = Qmac; | |
6202 | } | |
6203 | return eol_type; | |
d46c5b12 | 6204 | } |
4ed46869 | 6205 | |
df7492f9 KH |
6206 | /* Detect how a text specified in CODING is encoded. If a coding |
6207 | system is detected, update fields of CODING by the detected coding | |
6208 | system. */ | |
0a28aafb | 6209 | |
74ab6df5 | 6210 | static void |
971de7fb | 6211 | detect_coding (struct coding_system *coding) |
d46c5b12 | 6212 | { |
8f924df7 | 6213 | const unsigned char *src, *src_end; |
f10fe38f | 6214 | unsigned int saved_mode = coding->mode; |
d46c5b12 | 6215 | |
df7492f9 KH |
6216 | coding->consumed = coding->consumed_char = 0; |
6217 | coding->produced = coding->produced_char = 0; | |
6218 | coding_set_source (coding); | |
1c3478b0 | 6219 | |
df7492f9 | 6220 | src_end = coding->source + coding->src_bytes; |
c0e16b14 | 6221 | coding->head_ascii = 0; |
1c3478b0 | 6222 | |
df7492f9 KH |
6223 | /* If we have not yet decided the text encoding type, detect it |
6224 | now. */ | |
6225 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 6226 | { |
df7492f9 | 6227 | int c, i; |
6cb21a4f | 6228 | struct coding_detection_info detect_info; |
f10fe38f | 6229 | bool null_byte_found = 0, eight_bit_found = 0; |
df7492f9 | 6230 | |
6cb21a4f | 6231 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 6232 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 6233 | { |
df7492f9 | 6234 | c = *src; |
6cb21a4f | 6235 | if (c & 0x80) |
6cb21a4f | 6236 | { |
2f3cbb32 | 6237 | eight_bit_found = 1; |
2f3cbb32 KH |
6238 | if (null_byte_found) |
6239 | break; | |
6240 | } | |
6241 | else if (c < 0x20) | |
6242 | { | |
6243 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
6244 | && ! inhibit_iso_escape_detection | |
6245 | && ! detect_info.checked) | |
6cb21a4f | 6246 | { |
2f3cbb32 KH |
6247 | if (detect_coding_iso_2022 (coding, &detect_info)) |
6248 | { | |
6249 | /* We have scanned the whole data. */ | |
6250 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
6251 | { |
6252 | /* We didn't find an 8-bit code. We may | |
6253 | have found a null-byte, but it's very | |
ce5b453a | 6254 | rare that a binary file conforms to |
c0e16b14 KH |
6255 | ISO-2022. */ |
6256 | src = src_end; | |
6257 | coding->head_ascii = src - coding->source; | |
6258 | } | |
6259 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
6260 | break; |
6261 | } | |
6262 | } | |
97b1b294 | 6263 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
6264 | { |
6265 | null_byte_found = 1; | |
6266 | if (eight_bit_found) | |
6267 | break; | |
6cb21a4f | 6268 | } |
c006c0c8 KH |
6269 | if (! eight_bit_found) |
6270 | coding->head_ascii++; | |
6cb21a4f | 6271 | } |
c006c0c8 | 6272 | else if (! eight_bit_found) |
c0e16b14 | 6273 | coding->head_ascii++; |
d46c5b12 | 6274 | } |
df7492f9 | 6275 | |
2f3cbb32 KH |
6276 | if (null_byte_found || eight_bit_found |
6277 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 6278 | || detect_info.found) |
d46c5b12 | 6279 | { |
ff0dacd7 KH |
6280 | enum coding_category category; |
6281 | struct coding_system *this; | |
df7492f9 | 6282 | |
6cb21a4f KH |
6283 | if (coding->head_ascii == coding->src_bytes) |
6284 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
6285 | for (i = 0; i < coding_category_raw_text; i++) | |
6286 | { | |
6287 | category = coding_priorities[i]; | |
6288 | this = coding_categories + category; | |
6289 | if (detect_info.found & (1 << category)) | |
24a73b0a | 6290 | break; |
6cb21a4f KH |
6291 | } |
6292 | else | |
2f3cbb32 KH |
6293 | { |
6294 | if (null_byte_found) | |
ff0dacd7 | 6295 | { |
2f3cbb32 KH |
6296 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
6297 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 6298 | } |
2f3cbb32 KH |
6299 | for (i = 0; i < coding_category_raw_text; i++) |
6300 | { | |
6301 | category = coding_priorities[i]; | |
6302 | this = coding_categories + category; | |
0ba06a77 KH |
6303 | /* Some of this->detector (e.g. detect_coding_sjis) |
6304 | require this information. */ | |
6305 | coding->id = this->id; | |
2f3cbb32 KH |
6306 | if (this->id < 0) |
6307 | { | |
6308 | /* No coding system of this category is defined. */ | |
6309 | detect_info.rejected |= (1 << category); | |
6310 | } | |
6311 | else if (category >= coding_category_raw_text) | |
6312 | continue; | |
6313 | else if (detect_info.checked & (1 << category)) | |
6314 | { | |
6315 | if (detect_info.found & (1 << category)) | |
6316 | break; | |
6317 | } | |
6318 | else if ((*(this->detector)) (coding, &detect_info) | |
6319 | && detect_info.found & (1 << category)) | |
6320 | { | |
6321 | if (category == coding_category_utf_16_auto) | |
6322 | { | |
6323 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6324 | category = coding_category_utf_16_le; | |
6325 | else | |
6326 | category = coding_category_utf_16_be; | |
6327 | } | |
6328 | break; | |
6329 | } | |
6330 | } | |
2f3cbb32 | 6331 | } |
c0e16b14 KH |
6332 | |
6333 | if (i < coding_category_raw_text) | |
6334 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6335 | else if (null_byte_found) | |
6336 | setup_coding_system (Qno_conversion, coding); | |
6337 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) | |
6338 | == CATEGORY_MASK_ANY) | |
6339 | setup_coding_system (Qraw_text, coding); | |
6340 | else if (detect_info.rejected) | |
6341 | for (i = 0; i < coding_category_raw_text; i++) | |
6342 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6343 | { | |
6344 | this = coding_categories + coding_priorities[i]; | |
6345 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6346 | break; | |
6347 | } | |
d46c5b12 | 6348 | } |
b73bfc1c | 6349 | } |
a470d443 KH |
6350 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6351 | == coding_category_utf_8_auto) | |
6352 | { | |
6353 | Lisp_Object coding_systems; | |
6354 | struct coding_detection_info detect_info; | |
6355 | ||
6356 | coding_systems | |
6357 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6358 | detect_info.found = detect_info.rejected = 0; | |
6359 | coding->head_ascii = 0; | |
6360 | if (CONSP (coding_systems) | |
6361 | && detect_coding_utf_8 (coding, &detect_info)) | |
6362 | { | |
6363 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6364 | setup_coding_system (XCAR (coding_systems), coding); | |
6365 | else | |
6366 | setup_coding_system (XCDR (coding_systems), coding); | |
6367 | } | |
6368 | } | |
24a73b0a KH |
6369 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6370 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6371 | { |
6372 | Lisp_Object coding_systems; | |
6373 | struct coding_detection_info detect_info; | |
6374 | ||
6375 | coding_systems | |
a470d443 | 6376 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6377 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6378 | coding->head_ascii = 0; |
b49a1807 | 6379 | if (CONSP (coding_systems) |
24a73b0a | 6380 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6381 | { |
6382 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6383 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 6384 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
6385 | setup_coding_system (XCDR (coding_systems), coding); |
6386 | } | |
6387 | } | |
73cce38d | 6388 | coding->mode = saved_mode; |
4ed46869 | 6389 | } |
4ed46869 | 6390 | |
d46c5b12 | 6391 | |
aaaf0b1e | 6392 | static void |
971de7fb | 6393 | decode_eol (struct coding_system *coding) |
aaaf0b1e | 6394 | { |
24a73b0a KH |
6395 | Lisp_Object eol_type; |
6396 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6397 | |
24a73b0a | 6398 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
0a9564cb | 6399 | if (EQ (eol_type, Qunix) || inhibit_eol_conversion) |
24a73b0a KH |
6400 | return; |
6401 | ||
6402 | if (NILP (coding->dst_object)) | |
6403 | pbeg = coding->destination; | |
6404 | else | |
6405 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6406 | pend = pbeg + coding->produced; | |
6407 | ||
6408 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6409 | { |
df7492f9 | 6410 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6411 | |
24a73b0a | 6412 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6413 | { |
df7492f9 KH |
6414 | if (*p == '\n') |
6415 | eol_seen |= EOL_SEEN_LF; | |
6416 | else if (*p == '\r') | |
aaaf0b1e | 6417 | { |
df7492f9 | 6418 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6419 | { |
df7492f9 KH |
6420 | eol_seen |= EOL_SEEN_CRLF; |
6421 | p++; | |
aaaf0b1e | 6422 | } |
aaaf0b1e | 6423 | else |
df7492f9 | 6424 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6425 | } |
aaaf0b1e | 6426 | } |
75f4f1ac EZ |
6427 | /* Handle DOS-style EOLs in a file with stray ^M characters. */ |
6428 | if ((eol_seen & EOL_SEEN_CRLF) != 0 | |
6429 | && (eol_seen & EOL_SEEN_CR) != 0 | |
6430 | && (eol_seen & EOL_SEEN_LF) == 0) | |
6431 | eol_seen = EOL_SEEN_CRLF; | |
6432 | else if (eol_seen != EOL_SEEN_NONE | |
24a73b0a KH |
6433 | && eol_seen != EOL_SEEN_LF |
6434 | && eol_seen != EOL_SEEN_CRLF | |
6435 | && eol_seen != EOL_SEEN_CR) | |
6436 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6437 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6438 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6439 | } |
d46c5b12 | 6440 | |
24a73b0a | 6441 | if (EQ (eol_type, Qmac)) |
27901516 | 6442 | { |
24a73b0a | 6443 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6444 | if (*p == '\r') |
6445 | *p = '\n'; | |
4ed46869 | 6446 | } |
24a73b0a | 6447 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6448 | { |
d311d28c | 6449 | ptrdiff_t n = 0; |
b73bfc1c | 6450 | |
24a73b0a KH |
6451 | if (NILP (coding->dst_object)) |
6452 | { | |
4347441b KH |
6453 | /* Start deleting '\r' from the tail to minimize the memory |
6454 | movement. */ | |
24a73b0a KH |
6455 | for (p = pend - 2; p >= pbeg; p--) |
6456 | if (*p == '\r') | |
6457 | { | |
72af86bd | 6458 | memmove (p, p + 1, pend-- - p - 1); |
24a73b0a KH |
6459 | n++; |
6460 | } | |
6461 | } | |
6462 | else | |
6463 | { | |
d311d28c PE |
6464 | ptrdiff_t pos_byte = coding->dst_pos_byte; |
6465 | ptrdiff_t pos = coding->dst_pos; | |
6466 | ptrdiff_t pos_end = pos + coding->produced_char - 1; | |
4347441b KH |
6467 | |
6468 | while (pos < pos_end) | |
6469 | { | |
6470 | p = BYTE_POS_ADDR (pos_byte); | |
6471 | if (*p == '\r' && p[1] == '\n') | |
6472 | { | |
6473 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6474 | n++; | |
6475 | pos_end--; | |
6476 | } | |
6477 | pos++; | |
69b8522d KH |
6478 | if (coding->dst_multibyte) |
6479 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6480 | else | |
6481 | pos_byte++; | |
4347441b | 6482 | } |
24a73b0a KH |
6483 | } |
6484 | coding->produced -= n; | |
6485 | coding->produced_char -= n; | |
aaaf0b1e | 6486 | } |
4ed46869 KH |
6487 | } |
6488 | ||
7d64c6ad | 6489 | |
a6f87d34 | 6490 | /* Return a translation table (or list of them) from coding system |
f10fe38f PE |
6491 | attribute vector ATTRS for encoding (if ENCODEP) or decoding (if |
6492 | not ENCODEP). */ | |
7d64c6ad | 6493 | |
e6a54062 | 6494 | static Lisp_Object |
f10fe38f | 6495 | get_translation_table (Lisp_Object attrs, bool encodep, int *max_lookup) |
7d64c6ad KH |
6496 | { |
6497 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6498 | Lisp_Object val; |
7d64c6ad | 6499 | |
4bed5909 CY |
6500 | if (NILP (Venable_character_translation)) |
6501 | { | |
6502 | if (max_lookup) | |
6503 | *max_lookup = 0; | |
6504 | return Qnil; | |
6505 | } | |
7d64c6ad KH |
6506 | if (encodep) |
6507 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6508 | standard = Vstandard_translation_table_for_encode; | |
6509 | else | |
6510 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6511 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6512 | if (NILP (translation_table)) |
09ee6fdd KH |
6513 | translation_table = standard; |
6514 | else | |
a6f87d34 | 6515 | { |
09ee6fdd KH |
6516 | if (SYMBOLP (translation_table)) |
6517 | translation_table = Fget (translation_table, Qtranslation_table); | |
6518 | else if (CONSP (translation_table)) | |
6519 | { | |
6520 | translation_table = Fcopy_sequence (translation_table); | |
6521 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6522 | if (SYMBOLP (XCAR (val))) | |
6523 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6524 | } | |
6525 | if (CHAR_TABLE_P (standard)) | |
6526 | { | |
6527 | if (CONSP (translation_table)) | |
6528 | translation_table = nconc2 (translation_table, | |
6529 | Fcons (standard, Qnil)); | |
6530 | else | |
6531 | translation_table = Fcons (translation_table, | |
6532 | Fcons (standard, Qnil)); | |
6533 | } | |
a6f87d34 | 6534 | } |
2170c8f0 KH |
6535 | |
6536 | if (max_lookup) | |
09ee6fdd | 6537 | { |
2170c8f0 KH |
6538 | *max_lookup = 1; |
6539 | if (CHAR_TABLE_P (translation_table) | |
6540 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6541 | { | |
6542 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6543 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6544 | *max_lookup = XFASTINT (val); | |
6545 | } | |
6546 | else if (CONSP (translation_table)) | |
6547 | { | |
2735d060 | 6548 | Lisp_Object tail; |
09ee6fdd | 6549 | |
2170c8f0 KH |
6550 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6551 | if (CHAR_TABLE_P (XCAR (tail)) | |
6552 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6553 | { | |
2735d060 PE |
6554 | Lisp_Object tailval = XCHAR_TABLE (XCAR (tail))->extras[1]; |
6555 | if (NATNUMP (tailval) && *max_lookup < XFASTINT (tailval)) | |
6556 | *max_lookup = XFASTINT (tailval); | |
2170c8f0 KH |
6557 | } |
6558 | } | |
a6f87d34 | 6559 | } |
7d64c6ad KH |
6560 | return translation_table; |
6561 | } | |
6562 | ||
09ee6fdd KH |
6563 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6564 | do { \ | |
6565 | trans = Qnil; \ | |
6566 | if (CHAR_TABLE_P (table)) \ | |
6567 | { \ | |
6568 | trans = CHAR_TABLE_REF (table, c); \ | |
6569 | if (CHARACTERP (trans)) \ | |
6570 | c = XFASTINT (trans), trans = Qnil; \ | |
6571 | } \ | |
6572 | else if (CONSP (table)) \ | |
6573 | { \ | |
6574 | Lisp_Object tail; \ | |
6575 | \ | |
6576 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6577 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6578 | { \ | |
6579 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6580 | if (CHARACTERP (trans)) \ | |
6581 | c = XFASTINT (trans), trans = Qnil; \ | |
6582 | else if (! NILP (trans)) \ | |
6583 | break; \ | |
6584 | } \ | |
6585 | } \ | |
e6a54062 KH |
6586 | } while (0) |
6587 | ||
7d64c6ad | 6588 | |
e951386e KH |
6589 | /* Return a translation of character(s) at BUF according to TRANS. |
6590 | TRANS is TO-CHAR or ((FROM . TO) ...) where | |
6591 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | |
6592 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | |
6593 | translation is found, and Qnil if not found.. | |
6594 | If BUF is too short to lookup characters in FROM, return Qt. */ | |
6595 | ||
69a80ea3 | 6596 | static Lisp_Object |
971de7fb | 6597 | get_translation (Lisp_Object trans, int *buf, int *buf_end) |
69a80ea3 | 6598 | { |
e951386e KH |
6599 | |
6600 | if (INTEGERP (trans)) | |
6601 | return trans; | |
6602 | for (; CONSP (trans); trans = XCDR (trans)) | |
69a80ea3 | 6603 | { |
e951386e KH |
6604 | Lisp_Object val = XCAR (trans); |
6605 | Lisp_Object from = XCAR (val); | |
2c6a9faa PE |
6606 | ptrdiff_t len = ASIZE (from); |
6607 | ptrdiff_t i; | |
69a80ea3 | 6608 | |
e951386e | 6609 | for (i = 0; i < len; i++) |
69a80ea3 | 6610 | { |
e951386e KH |
6611 | if (buf + i == buf_end) |
6612 | return Qt; | |
6613 | if (XINT (AREF (from, i)) != buf[i]) | |
6614 | break; | |
69a80ea3 | 6615 | } |
e951386e KH |
6616 | if (i == len) |
6617 | return val; | |
69a80ea3 | 6618 | } |
e951386e | 6619 | return Qnil; |
69a80ea3 KH |
6620 | } |
6621 | ||
6622 | ||
d46c5b12 | 6623 | static int |
cf84bb53 | 6624 | produce_chars (struct coding_system *coding, Lisp_Object translation_table, |
f10fe38f | 6625 | bool last_block) |
4ed46869 | 6626 | { |
df7492f9 KH |
6627 | unsigned char *dst = coding->destination + coding->produced; |
6628 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c PE |
6629 | ptrdiff_t produced; |
6630 | ptrdiff_t produced_chars = 0; | |
69a80ea3 | 6631 | int carryover = 0; |
4ed46869 | 6632 | |
df7492f9 | 6633 | if (! coding->chars_at_source) |
4ed46869 | 6634 | { |
119852e7 | 6635 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6636 | int *buf = coding->charbuf; |
6637 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6638 | |
db274c7a KH |
6639 | if (EQ (coding->src_object, coding->dst_object)) |
6640 | { | |
6641 | coding_set_source (coding); | |
6642 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6643 | } | |
4ed46869 | 6644 | |
df7492f9 | 6645 | while (buf < buf_end) |
4ed46869 | 6646 | { |
27bb1ca4 PE |
6647 | int c = *buf; |
6648 | ptrdiff_t i; | |
bc4bc72a | 6649 | |
df7492f9 KH |
6650 | if (c >= 0) |
6651 | { | |
d311d28c | 6652 | ptrdiff_t from_nchars = 1, to_nchars = 1; |
69a80ea3 KH |
6653 | Lisp_Object trans = Qnil; |
6654 | ||
09ee6fdd | 6655 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6656 | if (! NILP (trans)) |
69a80ea3 | 6657 | { |
e951386e KH |
6658 | trans = get_translation (trans, buf, buf_end); |
6659 | if (INTEGERP (trans)) | |
6660 | c = XINT (trans); | |
6661 | else if (CONSP (trans)) | |
6662 | { | |
6663 | from_nchars = ASIZE (XCAR (trans)); | |
6664 | trans = XCDR (trans); | |
6665 | if (INTEGERP (trans)) | |
6666 | c = XINT (trans); | |
6667 | else | |
6668 | { | |
6669 | to_nchars = ASIZE (trans); | |
6670 | c = XINT (AREF (trans, 0)); | |
6671 | } | |
6672 | } | |
6673 | else if (EQ (trans, Qt) && ! last_block) | |
69a80ea3 | 6674 | break; |
69a80ea3 KH |
6675 | } |
6676 | ||
5d009b3a | 6677 | if ((dst_end - dst) / MAX_MULTIBYTE_LENGTH < to_nchars) |
69a80ea3 | 6678 | { |
5d009b3a PE |
6679 | if (((min (PTRDIFF_MAX, SIZE_MAX) - (buf_end - buf)) |
6680 | / MAX_MULTIBYTE_LENGTH) | |
6681 | < to_nchars) | |
6682 | memory_full (SIZE_MAX); | |
69a80ea3 KH |
6683 | dst = alloc_destination (coding, |
6684 | buf_end - buf | |
6685 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
6686 | dst); | |
db274c7a KH |
6687 | if (EQ (coding->src_object, coding->dst_object)) |
6688 | { | |
6689 | coding_set_source (coding); | |
e951386e KH |
6690 | dst_end = (((unsigned char *) coding->source) |
6691 | + coding->consumed); | |
db274c7a KH |
6692 | } |
6693 | else | |
6694 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
6695 | } |
6696 | ||
433f7f87 | 6697 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 6698 | { |
433f7f87 KH |
6699 | if (i > 0) |
6700 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
6701 | if (coding->dst_multibyte |
6702 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 6703 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
6704 | else |
6705 | *dst++ = CHAR_TO_BYTE8 (c); | |
6706 | } | |
6707 | produced_chars += to_nchars; | |
e951386e | 6708 | buf += from_nchars; |
d46c5b12 | 6709 | } |
df7492f9 | 6710 | else |
69a80ea3 KH |
6711 | /* This is an annotation datum. (-C) is the length. */ |
6712 | buf += -c; | |
4ed46869 | 6713 | } |
69a80ea3 | 6714 | carryover = buf_end - buf; |
4ed46869 | 6715 | } |
fa42c37f | 6716 | else |
fa42c37f | 6717 | { |
119852e7 | 6718 | /* Source characters are at coding->source. */ |
8f924df7 | 6719 | const unsigned char *src = coding->source; |
119852e7 | 6720 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 6721 | |
db274c7a KH |
6722 | if (EQ (coding->dst_object, coding->src_object)) |
6723 | dst_end = (unsigned char *) src; | |
df7492f9 | 6724 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 6725 | { |
df7492f9 | 6726 | if (coding->src_multibyte) |
fa42c37f | 6727 | { |
f10fe38f | 6728 | bool multibytep = 1; |
d311d28c | 6729 | ptrdiff_t consumed_chars = 0; |
d46c5b12 | 6730 | |
df7492f9 KH |
6731 | while (1) |
6732 | { | |
8f924df7 | 6733 | const unsigned char *src_base = src; |
df7492f9 | 6734 | int c; |
b73bfc1c | 6735 | |
df7492f9 | 6736 | ONE_MORE_BYTE (c); |
119852e7 | 6737 | if (dst == dst_end) |
df7492f9 | 6738 | { |
119852e7 KH |
6739 | if (EQ (coding->src_object, coding->dst_object)) |
6740 | dst_end = (unsigned char *) src; | |
6741 | if (dst == dst_end) | |
df7492f9 | 6742 | { |
d311d28c | 6743 | ptrdiff_t offset = src - coding->source; |
119852e7 KH |
6744 | |
6745 | dst = alloc_destination (coding, src_end - src + 1, | |
6746 | dst); | |
6747 | dst_end = coding->destination + coding->dst_bytes; | |
6748 | coding_set_source (coding); | |
6749 | src = coding->source + offset; | |
5c1ca13d | 6750 | src_end = coding->source + coding->consumed; |
db274c7a KH |
6751 | if (EQ (coding->src_object, coding->dst_object)) |
6752 | dst_end = (unsigned char *) src; | |
df7492f9 | 6753 | } |
df7492f9 KH |
6754 | } |
6755 | *dst++ = c; | |
6756 | produced_chars++; | |
6757 | } | |
6758 | no_more_source: | |
6759 | ; | |
fa42c37f KH |
6760 | } |
6761 | else | |
df7492f9 KH |
6762 | while (src < src_end) |
6763 | { | |
f10fe38f | 6764 | bool multibytep = 1; |
df7492f9 | 6765 | int c = *src++; |
b73bfc1c | 6766 | |
df7492f9 KH |
6767 | if (dst >= dst_end - 1) |
6768 | { | |
2c78b7e1 | 6769 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 6770 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
6771 | if (dst >= dst_end - 1) |
6772 | { | |
d311d28c PE |
6773 | ptrdiff_t offset = src - coding->source; |
6774 | ptrdiff_t more_bytes; | |
119852e7 | 6775 | |
db274c7a KH |
6776 | if (EQ (coding->src_object, coding->dst_object)) |
6777 | more_bytes = ((src_end - src) / 2) + 2; | |
6778 | else | |
6779 | more_bytes = src_end - src + 2; | |
6780 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
6781 | dst_end = coding->destination + coding->dst_bytes; |
6782 | coding_set_source (coding); | |
119852e7 | 6783 | src = coding->source + offset; |
5c1ca13d | 6784 | src_end = coding->source + coding->consumed; |
db274c7a KH |
6785 | if (EQ (coding->src_object, coding->dst_object)) |
6786 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 6787 | } |
df7492f9 KH |
6788 | } |
6789 | EMIT_ONE_BYTE (c); | |
6790 | } | |
d46c5b12 | 6791 | } |
df7492f9 KH |
6792 | else |
6793 | { | |
6794 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 6795 | { |
d311d28c | 6796 | ptrdiff_t require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 6797 | |
df7492f9 | 6798 | if (require > 0) |
fa42c37f | 6799 | { |
d311d28c | 6800 | ptrdiff_t offset = src - coding->source; |
df7492f9 KH |
6801 | |
6802 | dst = alloc_destination (coding, require, dst); | |
6803 | coding_set_source (coding); | |
6804 | src = coding->source + offset; | |
5c1ca13d | 6805 | src_end = coding->source + coding->consumed; |
fa42c37f KH |
6806 | } |
6807 | } | |
119852e7 | 6808 | produced_chars = coding->consumed_char; |
df7492f9 | 6809 | while (src < src_end) |
14daee73 | 6810 | *dst++ = *src++; |
fa42c37f KH |
6811 | } |
6812 | } | |
6813 | ||
df7492f9 | 6814 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 6815 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
df7492f9 KH |
6816 | insert_from_gap (produced_chars, produced); |
6817 | coding->produced += produced; | |
6818 | coding->produced_char += produced_chars; | |
69a80ea3 | 6819 | return carryover; |
fa42c37f KH |
6820 | } |
6821 | ||
ff0dacd7 KH |
6822 | /* Compose text in CODING->object according to the annotation data at |
6823 | CHARBUF. CHARBUF is an array: | |
e951386e | 6824 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
df7492f9 | 6825 | */ |
4ed46869 | 6826 | |
b0ab8123 | 6827 | static void |
d311d28c | 6828 | produce_composition (struct coding_system *coding, int *charbuf, ptrdiff_t pos) |
4ed46869 | 6829 | { |
df7492f9 | 6830 | int len; |
d311d28c | 6831 | ptrdiff_t to; |
df7492f9 | 6832 | enum composition_method method; |
df7492f9 | 6833 | Lisp_Object components; |
fa42c37f | 6834 | |
e951386e | 6835 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
69a80ea3 | 6836 | to = pos + charbuf[2]; |
e951386e | 6837 | method = (enum composition_method) (charbuf[4]); |
d46c5b12 | 6838 | |
df7492f9 KH |
6839 | if (method == COMPOSITION_RELATIVE) |
6840 | components = Qnil; | |
e951386e | 6841 | else |
d46c5b12 | 6842 | { |
df7492f9 | 6843 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
e951386e | 6844 | int i, j; |
b73bfc1c | 6845 | |
e951386e KH |
6846 | if (method == COMPOSITION_WITH_RULE) |
6847 | len = charbuf[2] * 3 - 2; | |
6848 | charbuf += MAX_ANNOTATION_LENGTH; | |
6849 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | |
6850 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | |
9ffd559c | 6851 | { |
e951386e KH |
6852 | if (charbuf[i] >= 0) |
6853 | args[j] = make_number (charbuf[i]); | |
6854 | else | |
6855 | { | |
6856 | i++; | |
6857 | args[j] = make_number (charbuf[i] % 0x100); | |
6858 | } | |
9ffd559c | 6859 | } |
e951386e | 6860 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
d46c5b12 | 6861 | } |
69a80ea3 | 6862 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6863 | } |
6864 | ||
d46c5b12 | 6865 | |
ff0dacd7 KH |
6866 | /* Put `charset' property on text in CODING->object according to |
6867 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6868 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6869 | */ |
d46c5b12 | 6870 | |
b0ab8123 | 6871 | static void |
d311d28c | 6872 | produce_charset (struct coding_system *coding, int *charbuf, ptrdiff_t pos) |
d46c5b12 | 6873 | { |
d311d28c | 6874 | ptrdiff_t from = pos - charbuf[2]; |
69a80ea3 | 6875 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); |
b73bfc1c | 6876 | |
69a80ea3 | 6877 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6878 | Qcharset, CHARSET_NAME (charset), |
6879 | coding->dst_object); | |
d46c5b12 KH |
6880 | } |
6881 | ||
d46c5b12 | 6882 | |
df7492f9 KH |
6883 | #define CHARBUF_SIZE 0x4000 |
6884 | ||
6885 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6886 | do { \ | |
8510724d | 6887 | int size = CHARBUF_SIZE; \ |
df7492f9 KH |
6888 | \ |
6889 | coding->charbuf = NULL; \ | |
6890 | while (size > 1024) \ | |
6891 | { \ | |
38182d90 | 6892 | coding->charbuf = alloca (sizeof (int) * size); \ |
df7492f9 KH |
6893 | if (coding->charbuf) \ |
6894 | break; \ | |
6895 | size >>= 1; \ | |
6896 | } \ | |
6897 | if (! coding->charbuf) \ | |
6898 | { \ | |
065e3595 | 6899 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
f10fe38f | 6900 | return; \ |
df7492f9 KH |
6901 | } \ |
6902 | coding->charbuf_size = size; \ | |
6903 | } while (0) | |
4ed46869 | 6904 | |
d46c5b12 KH |
6905 | |
6906 | static void | |
d311d28c | 6907 | produce_annotation (struct coding_system *coding, ptrdiff_t pos) |
d46c5b12 | 6908 | { |
df7492f9 KH |
6909 | int *charbuf = coding->charbuf; |
6910 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6911 | |
ff0dacd7 KH |
6912 | if (NILP (coding->dst_object)) |
6913 | return; | |
d46c5b12 | 6914 | |
df7492f9 | 6915 | while (charbuf < charbuf_end) |
a84f1519 | 6916 | { |
df7492f9 | 6917 | if (*charbuf >= 0) |
e951386e | 6918 | pos++, charbuf++; |
d46c5b12 | 6919 | else |
d46c5b12 | 6920 | { |
df7492f9 | 6921 | int len = -*charbuf; |
e951386e KH |
6922 | |
6923 | if (len > 2) | |
6924 | switch (charbuf[1]) | |
6925 | { | |
6926 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
6927 | produce_composition (coding, charbuf, pos); | |
6928 | break; | |
6929 | case CODING_ANNOTATE_CHARSET_MASK: | |
6930 | produce_charset (coding, charbuf, pos); | |
6931 | break; | |
6932 | } | |
df7492f9 | 6933 | charbuf += len; |
d46c5b12 | 6934 | } |
a84f1519 | 6935 | } |
d46c5b12 KH |
6936 | } |
6937 | ||
df7492f9 KH |
6938 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6939 | CODING->src_object is a buffer, a string, or nil. | |
6940 | CODING->dst_object is a buffer. | |
d46c5b12 | 6941 | |
df7492f9 KH |
6942 | If CODING->src_object is a buffer, it must be the current buffer. |
6943 | In this case, if CODING->src_pos is positive, it is a position of | |
6944 | the source text in the buffer, otherwise, the source text is in the | |
6945 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
6946 | the text from GPT (which must be the same as PT). If this is the | |
6947 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6948 | negative. | |
d46c5b12 | 6949 | |
b6828792 | 6950 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 6951 | that string. |
d46c5b12 | 6952 | |
df7492f9 KH |
6953 | If CODING->src_object is nil, CODING->source must already point to |
6954 | the non-relocatable memory area. In this case, CODING->src_pos is | |
6955 | an offset from CODING->source. | |
73be902c | 6956 | |
df7492f9 KH |
6957 | The decoded data is inserted at the current point of the buffer |
6958 | CODING->dst_object. | |
6959 | */ | |
d46c5b12 | 6960 | |
f10fe38f | 6961 | static void |
971de7fb | 6962 | decode_coding (struct coding_system *coding) |
d46c5b12 | 6963 | { |
df7492f9 | 6964 | Lisp_Object attrs; |
24a73b0a | 6965 | Lisp_Object undo_list; |
7d64c6ad | 6966 | Lisp_Object translation_table; |
d0396581 | 6967 | struct ccl_spec cclspec; |
69a80ea3 KH |
6968 | int carryover; |
6969 | int i; | |
d46c5b12 | 6970 | |
df7492f9 KH |
6971 | if (BUFFERP (coding->src_object) |
6972 | && coding->src_pos > 0 | |
6973 | && coding->src_pos < GPT | |
6974 | && coding->src_pos + coding->src_chars > GPT) | |
6975 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 6976 | |
24a73b0a | 6977 | undo_list = Qt; |
df7492f9 | 6978 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 6979 | { |
a3d794a1 | 6980 | set_buffer_internal (XBUFFER (coding->dst_object)); |
df7492f9 KH |
6981 | if (GPT != PT) |
6982 | move_gap_both (PT, PT_BYTE); | |
f48b82fd GR |
6983 | |
6984 | /* We must disable undo_list in order to record the whole insert | |
6985 | transaction via record_insert at the end. But doing so also | |
6986 | disables the recording of the first change to the undo_list. | |
6987 | Therefore we check for first change here and record it via | |
6988 | record_first_change if needed. */ | |
6989 | if (MODIFF <= SAVE_MODIFF) | |
6990 | record_first_change (); | |
6991 | ||
4b4deea2 | 6992 | undo_list = BVAR (current_buffer, undo_list); |
39eb03f1 | 6993 | bset_undo_list (current_buffer, Qt); |
1c3478b0 KH |
6994 | } |
6995 | ||
df7492f9 KH |
6996 | coding->consumed = coding->consumed_char = 0; |
6997 | coding->produced = coding->produced_char = 0; | |
6998 | coding->chars_at_source = 0; | |
065e3595 | 6999 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 7000 | coding->errors = 0; |
1c3478b0 | 7001 | |
df7492f9 KH |
7002 | ALLOC_CONVERSION_WORK_AREA (coding); |
7003 | ||
7004 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 7005 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 7006 | |
69a80ea3 | 7007 | carryover = 0; |
d0396581 KH |
7008 | if (coding->decoder == decode_coding_ccl) |
7009 | { | |
7010 | coding->spec.ccl = &cclspec; | |
7011 | setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding)); | |
7012 | } | |
df7492f9 | 7013 | do |
b73bfc1c | 7014 | { |
d311d28c | 7015 | ptrdiff_t pos = coding->dst_pos + coding->produced_char; |
69a80ea3 | 7016 | |
df7492f9 KH |
7017 | coding_set_source (coding); |
7018 | coding->annotated = 0; | |
69a80ea3 | 7019 | coding->charbuf_used = carryover; |
df7492f9 | 7020 | (*(coding->decoder)) (coding); |
df7492f9 | 7021 | coding_set_destination (coding); |
69a80ea3 | 7022 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 7023 | if (coding->annotated) |
69a80ea3 KH |
7024 | produce_annotation (coding, pos); |
7025 | for (i = 0; i < carryover; i++) | |
7026 | coding->charbuf[i] | |
7027 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 7028 | } |
d0396581 KH |
7029 | while (coding->result == CODING_RESULT_INSUFFICIENT_DST |
7030 | || (coding->consumed < coding->src_bytes | |
7031 | && (coding->result == CODING_RESULT_SUCCESS | |
7032 | || coding->result == CODING_RESULT_INVALID_SRC))); | |
d46c5b12 | 7033 | |
69a80ea3 KH |
7034 | if (carryover > 0) |
7035 | { | |
7036 | coding_set_destination (coding); | |
7037 | coding->charbuf_used = carryover; | |
7038 | produce_chars (coding, translation_table, 1); | |
7039 | } | |
7040 | ||
df7492f9 KH |
7041 | coding->carryover_bytes = 0; |
7042 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 7043 | { |
df7492f9 | 7044 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 7045 | const unsigned char *src; |
df7492f9 KH |
7046 | |
7047 | coding_set_source (coding); | |
7048 | coding_set_destination (coding); | |
7049 | src = coding->source + coding->consumed; | |
7050 | ||
7051 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 7052 | { |
df7492f9 KH |
7053 | /* Flush out unprocessed data as binary chars. We are sure |
7054 | that the number of data is less than the size of | |
7055 | coding->charbuf. */ | |
065e3595 | 7056 | coding->charbuf_used = 0; |
b2dab6c8 JR |
7057 | coding->chars_at_source = 0; |
7058 | ||
df7492f9 | 7059 | while (nbytes-- > 0) |
1c3478b0 | 7060 | { |
df7492f9 | 7061 | int c = *src++; |
98725083 | 7062 | |
1c91457d KH |
7063 | if (c & 0x80) |
7064 | c = BYTE8_TO_CHAR (c); | |
7065 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 7066 | } |
f6cbaf43 | 7067 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 7068 | } |
d46c5b12 | 7069 | else |
df7492f9 KH |
7070 | { |
7071 | /* Record unprocessed bytes in coding->carryover. We are | |
7072 | sure that the number of data is less than the size of | |
7073 | coding->carryover. */ | |
7074 | unsigned char *p = coding->carryover; | |
7075 | ||
f289d375 KH |
7076 | if (nbytes > sizeof coding->carryover) |
7077 | nbytes = sizeof coding->carryover; | |
df7492f9 KH |
7078 | coding->carryover_bytes = nbytes; |
7079 | while (nbytes-- > 0) | |
7080 | *p++ = *src++; | |
1c3478b0 | 7081 | } |
df7492f9 | 7082 | coding->consumed = coding->src_bytes; |
b73bfc1c | 7083 | } |
69f76525 | 7084 | |
0a9564cb EZ |
7085 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix) |
7086 | && !inhibit_eol_conversion) | |
4347441b | 7087 | decode_eol (coding); |
24a73b0a KH |
7088 | if (BUFFERP (coding->dst_object)) |
7089 | { | |
39eb03f1 | 7090 | bset_undo_list (current_buffer, undo_list); |
24a73b0a KH |
7091 | record_insert (coding->dst_pos, coding->produced_char); |
7092 | } | |
4ed46869 KH |
7093 | } |
7094 | ||
aaaf0b1e | 7095 | |
e1c23804 | 7096 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
7097 | ending before LIMIT of CODING->src_object (buffer or string), store |
7098 | the data in BUF, set *STOP to a starting position of the next | |
7099 | composition (if any) or to LIMIT, and return the address of the | |
7100 | next element of BUF. | |
7101 | ||
7102 | If such an annotation is not found, set *STOP to a starting | |
7103 | position of a composition after POS (if any) or to LIMIT, and | |
7104 | return BUF. */ | |
7105 | ||
b0ab8123 | 7106 | static int * |
d311d28c | 7107 | handle_composition_annotation (ptrdiff_t pos, ptrdiff_t limit, |
cf84bb53 | 7108 | struct coding_system *coding, int *buf, |
d311d28c | 7109 | ptrdiff_t *stop) |
aaaf0b1e | 7110 | { |
d311d28c | 7111 | ptrdiff_t start, end; |
ff0dacd7 | 7112 | Lisp_Object prop; |
aaaf0b1e | 7113 | |
ff0dacd7 KH |
7114 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
7115 | || end > limit) | |
7116 | *stop = limit; | |
7117 | else if (start > pos) | |
7118 | *stop = start; | |
7119 | else | |
aaaf0b1e | 7120 | { |
ff0dacd7 | 7121 | if (start == pos) |
aaaf0b1e | 7122 | { |
ff0dacd7 KH |
7123 | /* We found a composition. Store the corresponding |
7124 | annotation data in BUF. */ | |
7125 | int *head = buf; | |
7126 | enum composition_method method = COMPOSITION_METHOD (prop); | |
7127 | int nchars = COMPOSITION_LENGTH (prop); | |
7128 | ||
e951386e | 7129 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
ff0dacd7 | 7130 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 7131 | { |
ff0dacd7 | 7132 | Lisp_Object components; |
2c6a9faa | 7133 | ptrdiff_t i, len, i_byte; |
ff0dacd7 KH |
7134 | |
7135 | components = COMPOSITION_COMPONENTS (prop); | |
7136 | if (VECTORP (components)) | |
aaaf0b1e | 7137 | { |
77b37c05 | 7138 | len = ASIZE (components); |
ff0dacd7 KH |
7139 | for (i = 0; i < len; i++) |
7140 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 7141 | } |
ff0dacd7 | 7142 | else if (STRINGP (components)) |
aaaf0b1e | 7143 | { |
8f924df7 | 7144 | len = SCHARS (components); |
ff0dacd7 KH |
7145 | i = i_byte = 0; |
7146 | while (i < len) | |
7147 | { | |
7148 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
7149 | buf++; | |
7150 | } | |
7151 | } | |
7152 | else if (INTEGERP (components)) | |
7153 | { | |
7154 | len = 1; | |
7155 | *buf++ = XINT (components); | |
7156 | } | |
7157 | else if (CONSP (components)) | |
7158 | { | |
7159 | for (len = 0; CONSP (components); | |
7160 | len++, components = XCDR (components)) | |
7161 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 7162 | } |
aaaf0b1e | 7163 | else |
1088b922 | 7164 | emacs_abort (); |
ff0dacd7 | 7165 | *head -= len; |
aaaf0b1e | 7166 | } |
aaaf0b1e | 7167 | } |
ff0dacd7 KH |
7168 | |
7169 | if (find_composition (end, limit, &start, &end, &prop, | |
7170 | coding->src_object) | |
7171 | && end <= limit) | |
7172 | *stop = start; | |
7173 | else | |
7174 | *stop = limit; | |
aaaf0b1e | 7175 | } |
ff0dacd7 KH |
7176 | return buf; |
7177 | } | |
7178 | ||
7179 | ||
e1c23804 | 7180 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
7181 | CODING->src_object (buffer of string), store the data in BUF, set |
7182 | *STOP to the position where the value of `charset' property changes | |
7183 | (limiting by LIMIT), and return the address of the next element of | |
7184 | BUF. | |
7185 | ||
7186 | If the property value is nil, set *STOP to the position where the | |
7187 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
7188 | ||
b0ab8123 | 7189 | static int * |
d311d28c | 7190 | handle_charset_annotation (ptrdiff_t pos, ptrdiff_t limit, |
cf84bb53 | 7191 | struct coding_system *coding, int *buf, |
d311d28c | 7192 | ptrdiff_t *stop) |
ff0dacd7 KH |
7193 | { |
7194 | Lisp_Object val, next; | |
7195 | int id; | |
7196 | ||
7197 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
7198 | if (! NILP (val) && CHARSETP (val)) | |
7199 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
7200 | else | |
7201 | id = -1; | |
69a80ea3 | 7202 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
7203 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
7204 | coding->src_object, | |
7205 | make_number (limit)); | |
7206 | *stop = XINT (next); | |
7207 | return buf; | |
7208 | } | |
7209 | ||
7210 | ||
df7492f9 | 7211 | static void |
cf84bb53 JB |
7212 | consume_chars (struct coding_system *coding, Lisp_Object translation_table, |
7213 | int max_lookup) | |
df7492f9 KH |
7214 | { |
7215 | int *buf = coding->charbuf; | |
ff0dacd7 | 7216 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 7217 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 7218 | const unsigned char *src_end = coding->source + coding->src_bytes; |
d311d28c PE |
7219 | ptrdiff_t pos = coding->src_pos + coding->consumed_char; |
7220 | ptrdiff_t end_pos = coding->src_pos + coding->src_chars; | |
f10fe38f | 7221 | bool multibytep = coding->src_multibyte; |
df7492f9 KH |
7222 | Lisp_Object eol_type; |
7223 | int c; | |
d311d28c | 7224 | ptrdiff_t stop, stop_composition, stop_charset; |
09ee6fdd | 7225 | int *lookup_buf = NULL; |
433f7f87 KH |
7226 | |
7227 | if (! NILP (translation_table)) | |
09ee6fdd | 7228 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 7229 | |
0a9564cb | 7230 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
df7492f9 KH |
7231 | if (VECTORP (eol_type)) |
7232 | eol_type = Qunix; | |
88993dfd | 7233 | |
df7492f9 KH |
7234 | /* Note: composition handling is not yet implemented. */ |
7235 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 7236 | |
0b5670c9 KH |
7237 | if (NILP (coding->src_object)) |
7238 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 7239 | else |
0b5670c9 KH |
7240 | { |
7241 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
7242 | stop = stop_composition = pos; | |
7243 | else | |
7244 | stop = stop_composition = end_pos; | |
7245 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
7246 | stop = stop_charset = pos; | |
7247 | else | |
7248 | stop_charset = end_pos; | |
7249 | } | |
ec6d2bb8 | 7250 | |
24a73b0a | 7251 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 7252 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 7253 | while (buf < buf_end) |
aaaf0b1e | 7254 | { |
433f7f87 KH |
7255 | Lisp_Object trans; |
7256 | ||
df7492f9 | 7257 | if (pos == stop) |
ec6d2bb8 | 7258 | { |
df7492f9 KH |
7259 | if (pos == end_pos) |
7260 | break; | |
ff0dacd7 KH |
7261 | if (pos == stop_composition) |
7262 | buf = handle_composition_annotation (pos, end_pos, coding, | |
7263 | buf, &stop_composition); | |
7264 | if (pos == stop_charset) | |
7265 | buf = handle_charset_annotation (pos, end_pos, coding, | |
7266 | buf, &stop_charset); | |
7267 | stop = (stop_composition < stop_charset | |
7268 | ? stop_composition : stop_charset); | |
df7492f9 KH |
7269 | } |
7270 | ||
7271 | if (! multibytep) | |
4776e638 | 7272 | { |
d311d28c | 7273 | int bytes; |
aaaf0b1e | 7274 | |
4d1e6632 KH |
7275 | if (coding->encoder == encode_coding_raw_text |
7276 | || coding->encoder == encode_coding_ccl) | |
ea29edf2 KH |
7277 | c = *src++, pos++; |
7278 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 7279 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 7280 | else |
f03caae0 | 7281 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 7282 | } |
df7492f9 | 7283 | else |
db274c7a | 7284 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
7285 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
7286 | c = '\n'; | |
7287 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 7288 | { |
df7492f9 | 7289 | if (c == '\n') |
aaaf0b1e | 7290 | { |
df7492f9 KH |
7291 | if (EQ (eol_type, Qdos)) |
7292 | *buf++ = '\r'; | |
7293 | else | |
7294 | c = '\r'; | |
aaaf0b1e KH |
7295 | } |
7296 | } | |
433f7f87 | 7297 | |
e6a54062 | 7298 | trans = Qnil; |
09ee6fdd | 7299 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 7300 | if (NILP (trans)) |
433f7f87 KH |
7301 | *buf++ = c; |
7302 | else | |
7303 | { | |
2c6a9faa | 7304 | ptrdiff_t from_nchars = 1, to_nchars = 1; |
433f7f87 KH |
7305 | int *lookup_buf_end; |
7306 | const unsigned char *p = src; | |
7307 | int i; | |
7308 | ||
7309 | lookup_buf[0] = c; | |
7310 | for (i = 1; i < max_lookup && p < src_end; i++) | |
7311 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
7312 | lookup_buf_end = lookup_buf + i; | |
e951386e KH |
7313 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
7314 | if (INTEGERP (trans)) | |
7315 | c = XINT (trans); | |
7316 | else if (CONSP (trans)) | |
7317 | { | |
7318 | from_nchars = ASIZE (XCAR (trans)); | |
7319 | trans = XCDR (trans); | |
7320 | if (INTEGERP (trans)) | |
7321 | c = XINT (trans); | |
7322 | else | |
7323 | { | |
7324 | to_nchars = ASIZE (trans); | |
2c6a9faa | 7325 | if (buf_end - buf < to_nchars) |
e951386e KH |
7326 | break; |
7327 | c = XINT (AREF (trans, 0)); | |
7328 | } | |
7329 | } | |
7330 | else | |
433f7f87 | 7331 | break; |
e951386e | 7332 | *buf++ = c; |
433f7f87 KH |
7333 | for (i = 1; i < to_nchars; i++) |
7334 | *buf++ = XINT (AREF (trans, i)); | |
7335 | for (i = 1; i < from_nchars; i++, pos++) | |
7336 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7337 | } | |
aaaf0b1e | 7338 | } |
ec6d2bb8 | 7339 | |
df7492f9 KH |
7340 | coding->consumed = src - coding->source; |
7341 | coding->consumed_char = pos - coding->src_pos; | |
7342 | coding->charbuf_used = buf - coding->charbuf; | |
7343 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7344 | } |
7345 | ||
4ed46869 | 7346 | |
df7492f9 KH |
7347 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7348 | CODING->src_object is a buffer or a string. | |
7349 | CODING->dst_object is a buffer or nil. | |
7350 | ||
7351 | If CODING->src_object is a buffer, it must be the current buffer. | |
7352 | In this case, if CODING->src_pos is positive, it is a position of | |
7353 | the source text in the buffer, otherwise. the source text is in the | |
7354 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7355 | the text from GPT (which must be the same as PT). If this is the | |
7356 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7357 | negative and CODING should not have `pre-write-conversion'. | |
7358 | ||
7359 | If CODING->src_object is a string, CODING should not have | |
7360 | `pre-write-conversion'. | |
7361 | ||
7362 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7363 | the current point of that buffer. | |
7364 | ||
7365 | If CODING->dst_object is nil, the encoded data is placed at the | |
7366 | memory area specified by CODING->destination. */ | |
7367 | ||
f10fe38f | 7368 | static void |
971de7fb | 7369 | encode_coding (struct coding_system *coding) |
4ed46869 | 7370 | { |
df7492f9 | 7371 | Lisp_Object attrs; |
7d64c6ad | 7372 | Lisp_Object translation_table; |
09ee6fdd | 7373 | int max_lookup; |
fb608df3 | 7374 | struct ccl_spec cclspec; |
9861e777 | 7375 | |
df7492f9 | 7376 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7377 | if (coding->encoder == encode_coding_raw_text) |
7378 | translation_table = Qnil, max_lookup = 0; | |
7379 | else | |
7380 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7381 | |
df7492f9 | 7382 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7383 | { |
df7492f9 KH |
7384 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7385 | coding->dst_multibyte | |
4b4deea2 | 7386 | = ! NILP (BVAR (current_buffer, enable_multibyte_characters)); |
8844fa83 | 7387 | } |
4ed46869 | 7388 | |
b73bfc1c | 7389 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7390 | coding->produced = coding->produced_char = 0; |
065e3595 | 7391 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7392 | coding->errors = 0; |
b73bfc1c | 7393 | |
df7492f9 | 7394 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7395 | |
fb608df3 KH |
7396 | if (coding->encoder == encode_coding_ccl) |
7397 | { | |
7398 | coding->spec.ccl = &cclspec; | |
7399 | setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding)); | |
7400 | } | |
df7492f9 KH |
7401 | do { |
7402 | coding_set_source (coding); | |
09ee6fdd | 7403 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7404 | coding_set_destination (coding); |
7405 | (*(coding->encoder)) (coding); | |
7406 | } while (coding->consumed_char < coding->src_chars); | |
7407 | ||
284201e4 | 7408 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
df7492f9 | 7409 | insert_from_gap (coding->produced_char, coding->produced); |
ec6d2bb8 KH |
7410 | } |
7411 | ||
fb88bf2d | 7412 | |
24a73b0a KH |
7413 | /* Name (or base name) of work buffer for code conversion. */ |
7414 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7415 | |
24a73b0a KH |
7416 | /* A working buffer used by the top level conversion. Once it is |
7417 | created, it is never destroyed. It has the name | |
7418 | Vcode_conversion_workbuf_name. The other working buffers are | |
7419 | destroyed after the use is finished, and their names are modified | |
7420 | versions of Vcode_conversion_workbuf_name. */ | |
7421 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7422 | |
f10fe38f PE |
7423 | /* True iff Vcode_conversion_reused_workbuf is already in use. */ |
7424 | static bool reused_workbuf_in_use; | |
4ed46869 | 7425 | |
24a73b0a | 7426 | |
ad1746f5 | 7427 | /* Return a working buffer of code conversion. MULTIBYTE specifies the |
24a73b0a | 7428 | multibyteness of returning buffer. */ |
b73bfc1c | 7429 | |
f6cbaf43 | 7430 | static Lisp_Object |
f10fe38f | 7431 | make_conversion_work_buffer (bool multibyte) |
df7492f9 | 7432 | { |
24a73b0a KH |
7433 | Lisp_Object name, workbuf; |
7434 | struct buffer *current; | |
4ed46869 | 7435 | |
f10fe38f | 7436 | if (reused_workbuf_in_use) |
065e3595 KH |
7437 | { |
7438 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7439 | workbuf = Fget_buffer_create (name); | |
7440 | } | |
df7492f9 | 7441 | else |
065e3595 | 7442 | { |
f10fe38f | 7443 | reused_workbuf_in_use = 1; |
159bd5a2 | 7444 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7445 | Vcode_conversion_reused_workbuf |
7446 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7447 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7448 | } |
24a73b0a KH |
7449 | current = current_buffer; |
7450 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7451 | /* We can't allow modification hooks to run in the work buffer. For |
7452 | instance, directory_files_internal assumes that file decoding | |
7453 | doesn't compile new regexps. */ | |
7454 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7455 | Ferase_buffer (); |
39eb03f1 PE |
7456 | bset_undo_list (current_buffer, Qt); |
7457 | bset_enable_multibyte_characters (current_buffer, multibyte ? Qt : Qnil); | |
df7492f9 | 7458 | set_buffer_internal (current); |
24a73b0a | 7459 | return workbuf; |
df7492f9 | 7460 | } |
d46c5b12 | 7461 | |
24a73b0a | 7462 | |
4776e638 | 7463 | static Lisp_Object |
971de7fb | 7464 | code_conversion_restore (Lisp_Object arg) |
4776e638 | 7465 | { |
24a73b0a | 7466 | Lisp_Object current, workbuf; |
948bdcf3 | 7467 | struct gcpro gcpro1; |
24a73b0a | 7468 | |
948bdcf3 | 7469 | GCPRO1 (arg); |
24a73b0a KH |
7470 | current = XCAR (arg); |
7471 | workbuf = XCDR (arg); | |
7472 | if (! NILP (workbuf)) | |
7473 | { | |
7474 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7475 | reused_workbuf_in_use = 0; | |
d17337e5 | 7476 | else |
24a73b0a KH |
7477 | Fkill_buffer (workbuf); |
7478 | } | |
7479 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7480 | UNGCPRO; |
4776e638 KH |
7481 | return Qnil; |
7482 | } | |
b73bfc1c | 7483 | |
24a73b0a | 7484 | Lisp_Object |
f10fe38f | 7485 | code_conversion_save (bool with_work_buf, bool multibyte) |
df7492f9 | 7486 | { |
24a73b0a | 7487 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7488 | |
4776e638 | 7489 | if (with_work_buf) |
24a73b0a KH |
7490 | workbuf = make_conversion_work_buffer (multibyte); |
7491 | record_unwind_protect (code_conversion_restore, | |
7492 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7493 | return workbuf; |
df7492f9 | 7494 | } |
d46c5b12 | 7495 | |
f10fe38f | 7496 | void |
cf84bb53 | 7497 | decode_coding_gap (struct coding_system *coding, |
d311d28c | 7498 | ptrdiff_t chars, ptrdiff_t bytes) |
df7492f9 | 7499 | { |
d311d28c | 7500 | ptrdiff_t count = SPECPDL_INDEX (); |
5e5c78be | 7501 | Lisp_Object attrs; |
fb88bf2d | 7502 | |
24a73b0a | 7503 | code_conversion_save (0, 0); |
ec6d2bb8 | 7504 | |
24a73b0a | 7505 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7506 | coding->src_chars = chars; |
7507 | coding->src_bytes = bytes; | |
7508 | coding->src_pos = -chars; | |
7509 | coding->src_pos_byte = -bytes; | |
7510 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7511 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7512 | coding->dst_pos = PT; |
7513 | coding->dst_pos_byte = PT_BYTE; | |
4b4deea2 | 7514 | coding->dst_multibyte = ! NILP (BVAR (current_buffer, enable_multibyte_characters)); |
4ed46869 | 7515 | |
df7492f9 KH |
7516 | if (CODING_REQUIRE_DETECTION (coding)) |
7517 | detect_coding (coding); | |
8f924df7 | 7518 | |
9286b333 | 7519 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7520 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7521 | decode_coding (coding); |
287c57d7 | 7522 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7523 | |
5e5c78be KH |
7524 | attrs = CODING_ID_ATTRS (coding->id); |
7525 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 7526 | { |
d311d28c | 7527 | ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
5e5c78be KH |
7528 | Lisp_Object val; |
7529 | ||
7530 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7531 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7532 | make_number (coding->produced_char)); | |
5e5c78be KH |
7533 | CHECK_NATNUM (val); |
7534 | coding->produced_char += Z - prev_Z; | |
7535 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7536 | } |
4ed46869 | 7537 | |
df7492f9 | 7538 | unbind_to (count, Qnil); |
b73bfc1c | 7539 | } |
52d41803 | 7540 | |
d46c5b12 | 7541 | |
df7492f9 KH |
7542 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7543 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7544 | |
df7492f9 | 7545 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7546 | |
df7492f9 KH |
7547 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7548 | are positions in the buffer. | |
b73bfc1c | 7549 | |
df7492f9 KH |
7550 | If it is a string, the text is at the beginning of the string. |
7551 | FROM and TO are indices to the string. | |
4ed46869 | 7552 | |
df7492f9 KH |
7553 | If it is nil, the text is at coding->source. FROM and TO are |
7554 | indices to coding->source. | |
bb10be8b | 7555 | |
df7492f9 | 7556 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7557 | |
df7492f9 KH |
7558 | If it is a buffer, the decoded text is inserted at point of the |
7559 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7560 | is deleted. | |
4ed46869 | 7561 | |
df7492f9 KH |
7562 | If it is Qt, a string is made from the decoded text, and |
7563 | set in CODING->dst_object. | |
d46c5b12 | 7564 | |
df7492f9 | 7565 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7566 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7567 | CODING->destination by xmalloc. If the decoded text is longer than |
7568 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7569 | */ | |
d46c5b12 | 7570 | |
df7492f9 | 7571 | void |
cf84bb53 JB |
7572 | decode_coding_object (struct coding_system *coding, |
7573 | Lisp_Object src_object, | |
d311d28c PE |
7574 | ptrdiff_t from, ptrdiff_t from_byte, |
7575 | ptrdiff_t to, ptrdiff_t to_byte, | |
cf84bb53 | 7576 | Lisp_Object dst_object) |
d46c5b12 | 7577 | { |
d311d28c | 7578 | ptrdiff_t count = SPECPDL_INDEX (); |
c4a63b12 | 7579 | unsigned char *destination IF_LINT (= NULL); |
d311d28c PE |
7580 | ptrdiff_t dst_bytes IF_LINT (= 0); |
7581 | ptrdiff_t chars = to - from; | |
7582 | ptrdiff_t bytes = to_byte - from_byte; | |
df7492f9 | 7583 | Lisp_Object attrs; |
f10fe38f PE |
7584 | ptrdiff_t saved_pt = -1, saved_pt_byte IF_LINT (= 0); |
7585 | bool need_marker_adjustment = 0; | |
b3bfad50 | 7586 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7587 | |
b3bfad50 | 7588 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 7589 | |
df7492f9 | 7590 | if (NILP (dst_object)) |
d46c5b12 | 7591 | { |
df7492f9 KH |
7592 | destination = coding->destination; |
7593 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 7594 | } |
93dec019 | 7595 | |
df7492f9 KH |
7596 | coding->src_object = src_object; |
7597 | coding->src_chars = chars; | |
7598 | coding->src_bytes = bytes; | |
7599 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 7600 | |
df7492f9 | 7601 | if (STRINGP (src_object)) |
d46c5b12 | 7602 | { |
df7492f9 KH |
7603 | coding->src_pos = from; |
7604 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7605 | } |
df7492f9 | 7606 | else if (BUFFERP (src_object)) |
88993dfd | 7607 | { |
df7492f9 KH |
7608 | set_buffer_internal (XBUFFER (src_object)); |
7609 | if (from != GPT) | |
7610 | move_gap_both (from, from_byte); | |
7611 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 7612 | { |
64cedb0c KH |
7613 | struct Lisp_Marker *tail; |
7614 | ||
7615 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7616 | { | |
7617 | tail->need_adjustment | |
7618 | = tail->charpos == (tail->insertion_type ? from : to); | |
7619 | need_marker_adjustment |= tail->need_adjustment; | |
7620 | } | |
4776e638 | 7621 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 7622 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 7623 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
7624 | del_range_both (from, from_byte, to, to_byte, 1); |
7625 | coding->src_pos = -chars; | |
7626 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 7627 | } |
df7492f9 | 7628 | else |
fb88bf2d | 7629 | { |
df7492f9 KH |
7630 | coding->src_pos = from; |
7631 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 7632 | } |
88993dfd KH |
7633 | } |
7634 | ||
df7492f9 KH |
7635 | if (CODING_REQUIRE_DETECTION (coding)) |
7636 | detect_coding (coding); | |
7637 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 7638 | |
2cb26057 KH |
7639 | if (EQ (dst_object, Qt) |
7640 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
7641 | && NILP (dst_object))) | |
b73bfc1c | 7642 | { |
a1567c45 SM |
7643 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
7644 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
7645 | coding->dst_pos = BEG; |
7646 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 7647 | } |
df7492f9 | 7648 | else if (BUFFERP (dst_object)) |
d46c5b12 | 7649 | { |
24a73b0a | 7650 | code_conversion_save (0, 0); |
df7492f9 KH |
7651 | coding->dst_object = dst_object; |
7652 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
7653 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
7654 | coding->dst_multibyte | |
4b4deea2 | 7655 | = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters)); |
d46c5b12 KH |
7656 | } |
7657 | else | |
7658 | { | |
24a73b0a | 7659 | code_conversion_save (0, 0); |
df7492f9 | 7660 | coding->dst_object = Qnil; |
0154725e SM |
7661 | /* Most callers presume this will return a multibyte result, and they |
7662 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
7663 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 7664 | coding->dst_multibyte = 1; |
d46c5b12 KH |
7665 | } |
7666 | ||
df7492f9 | 7667 | decode_coding (coding); |
fa46990e | 7668 | |
df7492f9 KH |
7669 | if (BUFFERP (coding->dst_object)) |
7670 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 7671 | |
df7492f9 | 7672 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 7673 | { |
b3bfad50 | 7674 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d311d28c | 7675 | ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 7676 | Lisp_Object val; |
d46c5b12 | 7677 | |
c0cc7f7f | 7678 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
7679 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7680 | old_deactivate_mark); | |
d4850d67 KH |
7681 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
7682 | make_number (coding->produced_char)); | |
df7492f9 KH |
7683 | UNGCPRO; |
7684 | CHECK_NATNUM (val); | |
7685 | coding->produced_char += Z - prev_Z; | |
7686 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 7687 | } |
de79a6a5 | 7688 | |
df7492f9 | 7689 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 7690 | { |
df7492f9 KH |
7691 | coding->dst_object = Fbuffer_string (); |
7692 | } | |
7693 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
7694 | { | |
7695 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7696 | if (dst_bytes < coding->produced) | |
7697 | { | |
b3bfad50 | 7698 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
7699 | if (! destination) |
7700 | { | |
065e3595 | 7701 | record_conversion_result (coding, |
ebaf11b6 | 7702 | CODING_RESULT_INSUFFICIENT_MEM); |
df7492f9 KH |
7703 | unbind_to (count, Qnil); |
7704 | return; | |
7705 | } | |
7706 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
7707 | move_gap_both (BEGV, BEGV_BYTE); | |
72af86bd | 7708 | memcpy (destination, BEGV_ADDR, coding->produced); |
df7492f9 | 7709 | coding->destination = destination; |
d46c5b12 | 7710 | } |
ec6d2bb8 | 7711 | } |
b73bfc1c | 7712 | |
4776e638 KH |
7713 | if (saved_pt >= 0) |
7714 | { | |
7715 | /* This is the case of: | |
7716 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7717 | As we have moved PT while replacing the original buffer | |
7718 | contents, we must recover it now. */ | |
7719 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 7720 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
7721 | if (saved_pt < from) |
7722 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7723 | else if (saved_pt < from + chars) | |
7724 | TEMP_SET_PT_BOTH (from, from_byte); | |
4b4deea2 | 7725 | else if (! NILP (BVAR (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
7726 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
7727 | saved_pt_byte + (coding->produced - bytes)); | |
7728 | else | |
7729 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
7730 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7731 | |
7732 | if (need_marker_adjustment) | |
7733 | { | |
7734 | struct Lisp_Marker *tail; | |
7735 | ||
7736 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7737 | if (tail->need_adjustment) | |
7738 | { | |
7739 | tail->need_adjustment = 0; | |
7740 | if (tail->insertion_type) | |
7741 | { | |
7742 | tail->bytepos = from_byte; | |
7743 | tail->charpos = from; | |
7744 | } | |
7745 | else | |
7746 | { | |
7747 | tail->bytepos = from_byte + coding->produced; | |
7748 | tail->charpos | |
4b4deea2 | 7749 | = (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
7750 | ? tail->bytepos : from + coding->produced_char); |
7751 | } | |
7752 | } | |
7753 | } | |
d46c5b12 | 7754 | } |
4776e638 | 7755 | |
b3bfad50 | 7756 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 7757 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
7758 | } |
7759 | ||
d46c5b12 | 7760 | |
df7492f9 | 7761 | void |
cf84bb53 JB |
7762 | encode_coding_object (struct coding_system *coding, |
7763 | Lisp_Object src_object, | |
d311d28c PE |
7764 | ptrdiff_t from, ptrdiff_t from_byte, |
7765 | ptrdiff_t to, ptrdiff_t to_byte, | |
cf84bb53 | 7766 | Lisp_Object dst_object) |
d46c5b12 | 7767 | { |
d311d28c PE |
7768 | ptrdiff_t count = SPECPDL_INDEX (); |
7769 | ptrdiff_t chars = to - from; | |
7770 | ptrdiff_t bytes = to_byte - from_byte; | |
df7492f9 | 7771 | Lisp_Object attrs; |
f10fe38f PE |
7772 | ptrdiff_t saved_pt = -1, saved_pt_byte IF_LINT (= 0); |
7773 | bool need_marker_adjustment = 0; | |
7774 | bool kill_src_buffer = 0; | |
b3bfad50 | 7775 | Lisp_Object old_deactivate_mark; |
df7492f9 | 7776 | |
b3bfad50 | 7777 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
7778 | |
7779 | coding->src_object = src_object; | |
7780 | coding->src_chars = chars; | |
7781 | coding->src_bytes = bytes; | |
7782 | coding->src_multibyte = chars < bytes; | |
7783 | ||
7784 | attrs = CODING_ID_ATTRS (coding->id); | |
7785 | ||
64cedb0c KH |
7786 | if (EQ (src_object, dst_object)) |
7787 | { | |
7788 | struct Lisp_Marker *tail; | |
7789 | ||
7790 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7791 | { | |
7792 | tail->need_adjustment | |
7793 | = tail->charpos == (tail->insertion_type ? from : to); | |
7794 | need_marker_adjustment |= tail->need_adjustment; | |
7795 | } | |
7796 | } | |
7797 | ||
df7492f9 | 7798 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 7799 | { |
24a73b0a | 7800 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
7801 | set_buffer_internal (XBUFFER (coding->src_object)); |
7802 | if (STRINGP (src_object)) | |
7803 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
7804 | else if (BUFFERP (src_object)) | |
7805 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
7806 | else | |
b68864e5 | 7807 | insert_1_both ((char *) coding->source + from, chars, bytes, 0, 0, 0); |
d46c5b12 | 7808 | |
df7492f9 KH |
7809 | if (EQ (src_object, dst_object)) |
7810 | { | |
7811 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 7812 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
7813 | del_range_both (from, from_byte, to, to_byte, 1); |
7814 | set_buffer_internal (XBUFFER (coding->src_object)); | |
7815 | } | |
7816 | ||
d4850d67 | 7817 | { |
b3bfad50 | 7818 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 7819 | |
b3bfad50 KH |
7820 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7821 | old_deactivate_mark); | |
6cd7a139 DA |
7822 | safe_call2 (CODING_ATTR_PRE_WRITE (attrs), |
7823 | make_number (BEG), make_number (Z)); | |
b3bfad50 | 7824 | UNGCPRO; |
d4850d67 | 7825 | } |
c02d943b KH |
7826 | if (XBUFFER (coding->src_object) != current_buffer) |
7827 | kill_src_buffer = 1; | |
ac87bbef | 7828 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7829 | if (BEG != GPT) |
7830 | move_gap_both (BEG, BEG_BYTE); | |
7831 | coding->src_chars = Z - BEG; | |
7832 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
7833 | coding->src_pos = BEG; | |
7834 | coding->src_pos_byte = BEG_BYTE; | |
7835 | coding->src_multibyte = Z < Z_BYTE; | |
7836 | } | |
7837 | else if (STRINGP (src_object)) | |
d46c5b12 | 7838 | { |
24a73b0a | 7839 | code_conversion_save (0, 0); |
df7492f9 KH |
7840 | coding->src_pos = from; |
7841 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 7842 | } |
df7492f9 | 7843 | else if (BUFFERP (src_object)) |
b73bfc1c | 7844 | { |
24a73b0a | 7845 | code_conversion_save (0, 0); |
df7492f9 | 7846 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 7847 | if (EQ (src_object, dst_object)) |
d46c5b12 | 7848 | { |
4776e638 | 7849 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
7850 | coding->src_object = del_range_1 (from, to, 1, 1); |
7851 | coding->src_pos = 0; | |
7852 | coding->src_pos_byte = 0; | |
d46c5b12 | 7853 | } |
df7492f9 | 7854 | else |
d46c5b12 | 7855 | { |
ff0dacd7 KH |
7856 | if (from < GPT && to >= GPT) |
7857 | move_gap_both (from, from_byte); | |
df7492f9 KH |
7858 | coding->src_pos = from; |
7859 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7860 | } |
d46c5b12 | 7861 | } |
4776e638 | 7862 | else |
24a73b0a | 7863 | code_conversion_save (0, 0); |
d46c5b12 | 7864 | |
df7492f9 | 7865 | if (BUFFERP (dst_object)) |
88993dfd | 7866 | { |
df7492f9 | 7867 | coding->dst_object = dst_object; |
28f67a95 KH |
7868 | if (EQ (src_object, dst_object)) |
7869 | { | |
7870 | coding->dst_pos = from; | |
7871 | coding->dst_pos_byte = from_byte; | |
7872 | } | |
7873 | else | |
7874 | { | |
319a3947 KH |
7875 | struct buffer *current = current_buffer; |
7876 | ||
7877 | set_buffer_temp (XBUFFER (dst_object)); | |
7878 | coding->dst_pos = PT; | |
7879 | coding->dst_pos_byte = PT_BYTE; | |
7880 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
7881 | set_buffer_temp (current); | |
28f67a95 | 7882 | } |
df7492f9 | 7883 | coding->dst_multibyte |
4b4deea2 | 7884 | = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters)); |
88993dfd | 7885 | } |
df7492f9 | 7886 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 7887 | { |
5d009b3a | 7888 | ptrdiff_t dst_bytes = max (1, coding->src_chars); |
df7492f9 | 7889 | coding->dst_object = Qnil; |
23f86fce | 7890 | coding->destination = xmalloc (dst_bytes); |
5d009b3a | 7891 | coding->dst_bytes = dst_bytes; |
df7492f9 | 7892 | coding->dst_multibyte = 0; |
d46c5b12 KH |
7893 | } |
7894 | else | |
7895 | { | |
df7492f9 KH |
7896 | coding->dst_object = Qnil; |
7897 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
7898 | } |
7899 | ||
df7492f9 | 7900 | encode_coding (coding); |
d46c5b12 | 7901 | |
df7492f9 | 7902 | if (EQ (dst_object, Qt)) |
d46c5b12 | 7903 | { |
df7492f9 KH |
7904 | if (BUFFERP (coding->dst_object)) |
7905 | coding->dst_object = Fbuffer_string (); | |
7906 | else | |
d46c5b12 | 7907 | { |
df7492f9 KH |
7908 | coding->dst_object |
7909 | = make_unibyte_string ((char *) coding->destination, | |
7910 | coding->produced); | |
7911 | xfree (coding->destination); | |
d46c5b12 | 7912 | } |
4ed46869 | 7913 | } |
d46c5b12 | 7914 | |
4776e638 KH |
7915 | if (saved_pt >= 0) |
7916 | { | |
7917 | /* This is the case of: | |
7918 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7919 | As we have moved PT while replacing the original buffer | |
7920 | contents, we must recover it now. */ | |
7921 | set_buffer_internal (XBUFFER (src_object)); | |
7922 | if (saved_pt < from) | |
7923 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7924 | else if (saved_pt < from + chars) | |
7925 | TEMP_SET_PT_BOTH (from, from_byte); | |
4b4deea2 | 7926 | else if (! NILP (BVAR (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
7927 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
7928 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 7929 | else |
4776e638 KH |
7930 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
7931 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7932 | |
7933 | if (need_marker_adjustment) | |
7934 | { | |
7935 | struct Lisp_Marker *tail; | |
7936 | ||
7937 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7938 | if (tail->need_adjustment) | |
7939 | { | |
7940 | tail->need_adjustment = 0; | |
7941 | if (tail->insertion_type) | |
7942 | { | |
7943 | tail->bytepos = from_byte; | |
7944 | tail->charpos = from; | |
7945 | } | |
7946 | else | |
7947 | { | |
7948 | tail->bytepos = from_byte + coding->produced; | |
7949 | tail->charpos | |
4b4deea2 | 7950 | = (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
7951 | ? tail->bytepos : from + coding->produced_char); |
7952 | } | |
7953 | } | |
7954 | } | |
4776e638 KH |
7955 | } |
7956 | ||
c02d943b KH |
7957 | if (kill_src_buffer) |
7958 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
7959 | |
7960 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 7961 | unbind_to (count, Qnil); |
b73bfc1c KH |
7962 | } |
7963 | ||
df7492f9 | 7964 | |
b73bfc1c | 7965 | Lisp_Object |
971de7fb | 7966 | preferred_coding_system (void) |
b73bfc1c | 7967 | { |
df7492f9 | 7968 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 7969 | |
df7492f9 | 7970 | return CODING_ID_NAME (id); |
4ed46869 KH |
7971 | } |
7972 | ||
7f590b0c | 7973 | #if defined (WINDOWSNT) || defined (CYGWIN) |
ba116008 DC |
7974 | |
7975 | Lisp_Object | |
7976 | from_unicode (Lisp_Object str) | |
7977 | { | |
7978 | CHECK_STRING (str); | |
7979 | if (!STRING_MULTIBYTE (str) && | |
7980 | SBYTES (str) & 1) | |
7981 | { | |
7982 | str = Fsubstring (str, make_number (0), make_number (-1)); | |
7983 | } | |
7984 | ||
7985 | return code_convert_string_norecord (str, Qutf_16le, 0); | |
7986 | } | |
7987 | ||
7988 | wchar_t * | |
7989 | to_unicode (Lisp_Object str, Lisp_Object *buf) | |
7990 | { | |
7991 | *buf = code_convert_string_norecord (str, Qutf_16le, 1); | |
7992 | /* We need to make a another copy (in addition to the one made by | |
7993 | code_convert_string_norecord) to ensure that the final string is | |
7994 | _doubly_ zero terminated --- that is, that the string is | |
7995 | terminated by two zero bytes and one utf-16le null character. | |
7996 | Because strings are already terminated with a single zero byte, | |
7997 | we just add one additional zero. */ | |
7998 | str = make_uninit_string (SBYTES (*buf) + 1); | |
7999 | memcpy (SDATA (str), SDATA (*buf), SBYTES (*buf)); | |
8000 | SDATA (str) [SBYTES (*buf)] = '\0'; | |
8001 | *buf = str; | |
8002 | return WCSDATA (*buf); | |
8003 | } | |
7f590b0c DC |
8004 | |
8005 | #endif /* WINDOWSNT || CYGWIN */ | |
ba116008 | 8006 | |
4ed46869 KH |
8007 | \f |
8008 | #ifdef emacs | |
1397dc18 | 8009 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 8010 | |
a7ca3326 | 8011 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 8012 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 8013 | See the documentation of `define-coding-system' for information |
48b0f3ae | 8014 | about coding-system objects. */) |
5842a27b | 8015 | (Lisp_Object object) |
4ed46869 | 8016 | { |
d4a1d553 JB |
8017 | if (NILP (object) |
8018 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 8019 | return Qt; |
d4a1d553 JB |
8020 | if (! SYMBOLP (object) |
8021 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
8022 | return Qnil; |
8023 | return Qt; | |
4ed46869 KH |
8024 | } |
8025 | ||
a7ca3326 | 8026 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
9d991de8 | 8027 | Sread_non_nil_coding_system, 1, 1, 0, |
48b0f3ae | 8028 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
5842a27b | 8029 | (Lisp_Object prompt) |
4ed46869 | 8030 | { |
e0e989f6 | 8031 | Lisp_Object val; |
9d991de8 RS |
8032 | do |
8033 | { | |
4608c386 KH |
8034 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
8035 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 8036 | } |
8f924df7 | 8037 | while (SCHARS (val) == 0); |
e0e989f6 | 8038 | return (Fintern (val, Qnil)); |
4ed46869 KH |
8039 | } |
8040 | ||
a7ca3326 | 8041 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 8042 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
8043 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
8044 | Ignores case when completing coding systems (all Emacs coding systems | |
8045 | are lower-case). */) | |
5842a27b | 8046 | (Lisp_Object prompt, Lisp_Object default_coding_system) |
4ed46869 | 8047 | { |
f44d27ce | 8048 | Lisp_Object val; |
d311d28c | 8049 | ptrdiff_t count = SPECPDL_INDEX (); |
c7183fb8 | 8050 | |
9b787f3e | 8051 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 8052 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 8053 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 8054 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
8055 | Qt, Qnil, Qcoding_system_history, |
8056 | default_coding_system, Qnil); | |
c7183fb8 | 8057 | unbind_to (count, Qnil); |
8f924df7 | 8058 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
8059 | } |
8060 | ||
a7ca3326 | 8061 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, |
4ed46869 | 8062 | 1, 1, 0, |
48b0f3ae | 8063 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
8064 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
8065 | It is valid if it is nil or a symbol defined as a coding system by the | |
8066 | function `define-coding-system'. */) | |
5842a27b | 8067 | (Lisp_Object coding_system) |
4ed46869 | 8068 | { |
44e8490d KH |
8069 | Lisp_Object define_form; |
8070 | ||
8071 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
8072 | if (! NILP (define_form)) | |
8073 | { | |
8074 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
8075 | safe_eval (define_form); | |
8076 | } | |
4ed46869 KH |
8077 | if (!NILP (Fcoding_system_p (coding_system))) |
8078 | return coding_system; | |
fcad4ec4 | 8079 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 8080 | } |
df7492f9 | 8081 | |
3a73fa5d | 8082 | \f |
89528eb3 | 8083 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
f10fe38f | 8084 | HIGHEST, return the coding system of the highest |
ad1746f5 | 8085 | priority among the detected coding systems. Otherwise return a |
89528eb3 | 8086 | list of detected coding systems sorted by their priorities. If |
f10fe38f | 8087 | MULTIBYTEP, it is assumed that the bytes are in correct |
89528eb3 KH |
8088 | multibyte form but contains only ASCII and eight-bit chars. |
8089 | Otherwise, the bytes are raw bytes. | |
8090 | ||
8091 | CODING-SYSTEM controls the detection as below: | |
8092 | ||
8093 | If it is nil, detect both text-format and eol-format. If the | |
8094 | text-format part of CODING-SYSTEM is already specified | |
8095 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
8096 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
8097 | detect only text-format. */ | |
8098 | ||
d46c5b12 | 8099 | Lisp_Object |
cf84bb53 | 8100 | detect_coding_system (const unsigned char *src, |
d311d28c | 8101 | ptrdiff_t src_chars, ptrdiff_t src_bytes, |
f10fe38f | 8102 | bool highest, bool multibytep, |
cf84bb53 | 8103 | Lisp_Object coding_system) |
4ed46869 | 8104 | { |
8f924df7 | 8105 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 8106 | Lisp_Object attrs, eol_type; |
4533845d | 8107 | Lisp_Object val = Qnil; |
df7492f9 | 8108 | struct coding_system coding; |
d3411f89 | 8109 | ptrdiff_t id; |
ff0dacd7 | 8110 | struct coding_detection_info detect_info; |
24a73b0a | 8111 | enum coding_category base_category; |
f10fe38f | 8112 | bool null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 8113 | |
df7492f9 KH |
8114 | if (NILP (coding_system)) |
8115 | coding_system = Qundecided; | |
8116 | setup_coding_system (coding_system, &coding); | |
8117 | attrs = CODING_ID_ATTRS (coding.id); | |
8118 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 8119 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 8120 | |
df7492f9 | 8121 | coding.source = src; |
24a73b0a | 8122 | coding.src_chars = src_chars; |
df7492f9 KH |
8123 | coding.src_bytes = src_bytes; |
8124 | coding.src_multibyte = multibytep; | |
8125 | coding.consumed = 0; | |
89528eb3 | 8126 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 8127 | coding.head_ascii = 0; |
d46c5b12 | 8128 | |
ff0dacd7 | 8129 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 8130 | |
89528eb3 | 8131 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
8132 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
8133 | if (base_category == coding_category_undecided) | |
4ed46869 | 8134 | { |
c4a63b12 PE |
8135 | enum coding_category category IF_LINT (= 0); |
8136 | struct coding_system *this IF_LINT (= NULL); | |
ff0dacd7 | 8137 | int c, i; |
88993dfd | 8138 | |
24a73b0a | 8139 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 8140 | for (; src < src_end; src++) |
4ed46869 | 8141 | { |
df7492f9 | 8142 | c = *src; |
6cb21a4f | 8143 | if (c & 0x80) |
6cb21a4f | 8144 | { |
2f3cbb32 | 8145 | eight_bit_found = 1; |
2f3cbb32 KH |
8146 | if (null_byte_found) |
8147 | break; | |
8148 | } | |
c0e16b14 | 8149 | else if (c < 0x20) |
2f3cbb32 KH |
8150 | { |
8151 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
8152 | && ! inhibit_iso_escape_detection | |
8153 | && ! detect_info.checked) | |
6cb21a4f | 8154 | { |
2f3cbb32 KH |
8155 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
8156 | { | |
8157 | /* We have scanned the whole data. */ | |
8158 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
8159 | { |
8160 | /* We didn't find an 8-bit code. We may | |
8161 | have found a null-byte, but it's very | |
8162 | rare that a binary file confirm to | |
8163 | ISO-2022. */ | |
8164 | src = src_end; | |
8165 | coding.head_ascii = src - coding.source; | |
8166 | } | |
8167 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
8168 | break; |
8169 | } | |
8170 | } | |
97b1b294 | 8171 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
8172 | { |
8173 | null_byte_found = 1; | |
8174 | if (eight_bit_found) | |
8175 | break; | |
6cb21a4f | 8176 | } |
c006c0c8 KH |
8177 | if (! eight_bit_found) |
8178 | coding.head_ascii++; | |
6cb21a4f | 8179 | } |
c006c0c8 | 8180 | else if (! eight_bit_found) |
c0e16b14 | 8181 | coding.head_ascii++; |
4ed46869 | 8182 | } |
88993dfd | 8183 | |
2f3cbb32 KH |
8184 | if (null_byte_found || eight_bit_found |
8185 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
8186 | || detect_info.found) |
8187 | { | |
2f3cbb32 | 8188 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
8189 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
8190 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 8191 | { |
6cb21a4f | 8192 | category = coding_priorities[i]; |
c7266f4a | 8193 | this = coding_categories + category; |
6cb21a4f | 8194 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
8195 | break; |
8196 | } | |
6cb21a4f | 8197 | else |
2f3cbb32 KH |
8198 | { |
8199 | if (null_byte_found) | |
8200 | { | |
8201 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
8202 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
8203 | } | |
8204 | for (i = 0; i < coding_category_raw_text; i++) | |
8205 | { | |
8206 | category = coding_priorities[i]; | |
8207 | this = coding_categories + category; | |
6cb21a4f | 8208 | |
2f3cbb32 KH |
8209 | if (this->id < 0) |
8210 | { | |
8211 | /* No coding system of this category is defined. */ | |
8212 | detect_info.rejected |= (1 << category); | |
8213 | } | |
8214 | else if (category >= coding_category_raw_text) | |
8215 | continue; | |
8216 | else if (detect_info.checked & (1 << category)) | |
8217 | { | |
8218 | if (highest | |
8219 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 8220 | break; |
2f3cbb32 KH |
8221 | } |
8222 | else if ((*(this->detector)) (&coding, &detect_info) | |
8223 | && highest | |
8224 | && (detect_info.found & (1 << category))) | |
8225 | { | |
8226 | if (category == coding_category_utf_16_auto) | |
8227 | { | |
8228 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8229 | category = coding_category_utf_16_le; | |
8230 | else | |
8231 | category = coding_category_utf_16_be; | |
8232 | } | |
8233 | break; | |
8234 | } | |
8235 | } | |
8236 | } | |
6cb21a4f | 8237 | } |
ec6d2bb8 | 8238 | |
4cddb209 KH |
8239 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
8240 | || null_byte_found) | |
ec6d2bb8 | 8241 | { |
ff0dacd7 | 8242 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 8243 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
8244 | val = Fcons (make_number (id), Qnil); |
8245 | } | |
ff0dacd7 | 8246 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 8247 | { |
ff0dacd7 | 8248 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
8249 | id = coding_categories[coding_category_undecided].id; |
8250 | val = Fcons (make_number (id), Qnil); | |
8251 | } | |
8252 | else if (highest) | |
8253 | { | |
ff0dacd7 | 8254 | if (detect_info.found) |
ec6d2bb8 | 8255 | { |
ff0dacd7 KH |
8256 | detect_info.found = 1 << category; |
8257 | val = Fcons (make_number (this->id), Qnil); | |
8258 | } | |
8259 | else | |
8260 | for (i = 0; i < coding_category_raw_text; i++) | |
8261 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
8262 | { | |
8263 | detect_info.found = 1 << coding_priorities[i]; | |
8264 | id = coding_categories[coding_priorities[i]].id; | |
8265 | val = Fcons (make_number (id), Qnil); | |
8266 | break; | |
8267 | } | |
8268 | } | |
89528eb3 KH |
8269 | else |
8270 | { | |
ff0dacd7 KH |
8271 | int mask = detect_info.rejected | detect_info.found; |
8272 | int found = 0; | |
ec6d2bb8 | 8273 | |
89528eb3 | 8274 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
8275 | { |
8276 | category = coding_priorities[i]; | |
8277 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 8278 | { |
ff0dacd7 KH |
8279 | found |= 1 << category; |
8280 | id = coding_categories[category].id; | |
c7266f4a KH |
8281 | if (id >= 0) |
8282 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
8283 | } |
8284 | } | |
8285 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
8286 | { | |
8287 | category = coding_priorities[i]; | |
8288 | if (detect_info.found & (1 << category)) | |
8289 | { | |
8290 | id = coding_categories[category].id; | |
8291 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 8292 | } |
ec6d2bb8 | 8293 | } |
ff0dacd7 | 8294 | detect_info.found |= found; |
ec6d2bb8 | 8295 | } |
ec6d2bb8 | 8296 | } |
a470d443 KH |
8297 | else if (base_category == coding_category_utf_8_auto) |
8298 | { | |
8299 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
8300 | { | |
8301 | struct coding_system *this; | |
8302 | ||
8303 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
8304 | this = coding_categories + coding_category_utf_8_sig; | |
8305 | else | |
8306 | this = coding_categories + coding_category_utf_8_nosig; | |
8307 | val = Fcons (make_number (this->id), Qnil); | |
8308 | } | |
8309 | } | |
24a73b0a KH |
8310 | else if (base_category == coding_category_utf_16_auto) |
8311 | { | |
8312 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
8313 | { | |
24a73b0a KH |
8314 | struct coding_system *this; |
8315 | ||
8316 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8317 | this = coding_categories + coding_category_utf_16_le; | |
8318 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
8319 | this = coding_categories + coding_category_utf_16_be; | |
8320 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
8321 | this = coding_categories + coding_category_utf_16_be_nosig; | |
8322 | else | |
8323 | this = coding_categories + coding_category_utf_16_le_nosig; | |
8324 | val = Fcons (make_number (this->id), Qnil); | |
8325 | } | |
8326 | } | |
df7492f9 KH |
8327 | else |
8328 | { | |
ff0dacd7 | 8329 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 8330 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8331 | } |
df7492f9 | 8332 | |
89528eb3 | 8333 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8334 | { |
4533845d | 8335 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8336 | Lisp_Object tail; |
8337 | ||
89528eb3 KH |
8338 | if (VECTORP (eol_type)) |
8339 | { | |
ff0dacd7 | 8340 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8341 | { |
8342 | if (null_byte_found) | |
8343 | normal_eol = EOL_SEEN_LF; | |
8344 | else | |
8345 | normal_eol = detect_eol (coding.source, src_bytes, | |
8346 | coding_category_raw_text); | |
8347 | } | |
ff0dacd7 KH |
8348 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8349 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8350 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8351 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8352 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8353 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8354 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8355 | coding_category_utf_16_le); | |
8356 | } | |
8357 | else | |
8358 | { | |
8359 | if (EQ (eol_type, Qunix)) | |
8360 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8361 | else if (EQ (eol_type, Qdos)) | |
8362 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8363 | else | |
8364 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8365 | } | |
8366 | ||
df7492f9 KH |
8367 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8368 | { | |
89528eb3 | 8369 | enum coding_category category; |
df7492f9 | 8370 | int this_eol; |
89528eb3 KH |
8371 | |
8372 | id = XINT (XCAR (tail)); | |
8373 | attrs = CODING_ID_ATTRS (id); | |
8374 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8375 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8376 | if (VECTORP (eol_type)) |
8377 | { | |
89528eb3 KH |
8378 | if (category == coding_category_utf_16_be |
8379 | || category == coding_category_utf_16_be_nosig) | |
8380 | this_eol = utf_16_be_eol; | |
8381 | else if (category == coding_category_utf_16_le | |
8382 | || category == coding_category_utf_16_le_nosig) | |
8383 | this_eol = utf_16_le_eol; | |
df7492f9 | 8384 | else |
89528eb3 KH |
8385 | this_eol = normal_eol; |
8386 | ||
df7492f9 KH |
8387 | if (this_eol == EOL_SEEN_LF) |
8388 | XSETCAR (tail, AREF (eol_type, 0)); | |
8389 | else if (this_eol == EOL_SEEN_CRLF) | |
8390 | XSETCAR (tail, AREF (eol_type, 1)); | |
8391 | else if (this_eol == EOL_SEEN_CR) | |
8392 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8393 | else |
8394 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8395 | } |
89528eb3 KH |
8396 | else |
8397 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8398 | } |
8399 | } | |
ec6d2bb8 | 8400 | |
4533845d | 8401 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8402 | } |
8403 | ||
ec6d2bb8 | 8404 | |
d46c5b12 KH |
8405 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8406 | 2, 3, 0, | |
48b0f3ae PJ |
8407 | doc: /* Detect coding system of the text in the region between START and END. |
8408 | Return a list of possible coding systems ordered by priority. | |
b811c52b KH |
8409 | The coding systems to try and their priorities follows what |
8410 | the function `coding-system-priority-list' (which see) returns. | |
ec6d2bb8 | 8411 | |
12e0131a | 8412 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8413 | characters as ESC), it returns a list of single element `undecided' |
8414 | or its subsidiary coding system according to a detected end-of-line | |
8415 | format. | |
ec6d2bb8 | 8416 | |
48b0f3ae PJ |
8417 | If optional argument HIGHEST is non-nil, return the coding system of |
8418 | highest priority. */) | |
5842a27b | 8419 | (Lisp_Object start, Lisp_Object end, Lisp_Object highest) |
d46c5b12 | 8420 | { |
d311d28c PE |
8421 | ptrdiff_t from, to; |
8422 | ptrdiff_t from_byte, to_byte; | |
ec6d2bb8 | 8423 | |
d46c5b12 KH |
8424 | validate_region (&start, &end); |
8425 | from = XINT (start), to = XINT (end); | |
8426 | from_byte = CHAR_TO_BYTE (from); | |
8427 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8428 | |
d46c5b12 KH |
8429 | if (from < GPT && to >= GPT) |
8430 | move_gap_both (to, to_byte); | |
c210f766 | 8431 | |
d46c5b12 | 8432 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8433 | to - from, to_byte - from_byte, |
0a28aafb | 8434 | !NILP (highest), |
4b4deea2 | 8435 | !NILP (BVAR (current_buffer |
5d8ea120 | 8436 | , enable_multibyte_characters)), |
df7492f9 | 8437 | Qnil); |
ec6d2bb8 KH |
8438 | } |
8439 | ||
d46c5b12 KH |
8440 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8441 | 1, 2, 0, | |
48b0f3ae PJ |
8442 | doc: /* Detect coding system of the text in STRING. |
8443 | Return a list of possible coding systems ordered by priority. | |
67ceab9d KH |
8444 | The coding systems to try and their priorities follows what |
8445 | the function `coding-system-priority-list' (which see) returns. | |
fb88bf2d | 8446 | |
12e0131a | 8447 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8448 | characters as ESC), it returns a list of single element `undecided' |
8449 | or its subsidiary coding system according to a detected end-of-line | |
8450 | format. | |
d46c5b12 | 8451 | |
48b0f3ae PJ |
8452 | If optional argument HIGHEST is non-nil, return the coding system of |
8453 | highest priority. */) | |
5842a27b | 8454 | (Lisp_Object string, Lisp_Object highest) |
d46c5b12 | 8455 | { |
b7826503 | 8456 | CHECK_STRING (string); |
b73bfc1c | 8457 | |
24a73b0a KH |
8458 | return detect_coding_system (SDATA (string), |
8459 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8460 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8461 | Qnil); |
4ed46869 | 8462 | } |
4ed46869 | 8463 | |
b73bfc1c | 8464 | |
b0ab8123 | 8465 | static bool |
971de7fb | 8466 | char_encodable_p (int c, Lisp_Object attrs) |
05e6f5dc | 8467 | { |
df7492f9 | 8468 | Lisp_Object tail; |
df7492f9 | 8469 | struct charset *charset; |
7d64c6ad | 8470 | Lisp_Object translation_table; |
d46c5b12 | 8471 | |
7d64c6ad | 8472 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8473 | if (! NILP (translation_table)) |
7d64c6ad | 8474 | c = translate_char (translation_table, c); |
df7492f9 KH |
8475 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8476 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8477 | { |
df7492f9 KH |
8478 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8479 | if (CHAR_CHARSET_P (c, charset)) | |
8480 | break; | |
e133c8fa | 8481 | } |
df7492f9 | 8482 | return (! NILP (tail)); |
05e6f5dc | 8483 | } |
83fa074f | 8484 | |
fb88bf2d | 8485 | |
df7492f9 KH |
8486 | /* Return a list of coding systems that safely encode the text between |
8487 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8488 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8489 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8490 | unibyte, return t. */ |
e077cc80 | 8491 | |
df7492f9 KH |
8492 | DEFUN ("find-coding-systems-region-internal", |
8493 | Ffind_coding_systems_region_internal, | |
8494 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8495 | doc: /* Internal use only. */) | |
5842a27b | 8496 | (Lisp_Object start, Lisp_Object end, Lisp_Object exclude) |
df7492f9 KH |
8497 | { |
8498 | Lisp_Object coding_attrs_list, safe_codings; | |
d311d28c | 8499 | ptrdiff_t start_byte, end_byte; |
7c78e542 | 8500 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8501 | int c; |
0e727afa | 8502 | Lisp_Object tail, elt, work_table; |
d46c5b12 | 8503 | |
df7492f9 KH |
8504 | if (STRINGP (start)) |
8505 | { | |
8506 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8507 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8508 | return Qt; |
8509 | start_byte = 0; | |
8f924df7 | 8510 | end_byte = SBYTES (start); |
df7492f9 KH |
8511 | } |
8512 | else | |
d46c5b12 | 8513 | { |
df7492f9 KH |
8514 | CHECK_NUMBER_COERCE_MARKER (start); |
8515 | CHECK_NUMBER_COERCE_MARKER (end); | |
8516 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8517 | args_out_of_range (start, end); | |
4b4deea2 | 8518 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8519 | return Qt; |
8520 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8521 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8522 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8523 | return Qt; | |
d46c5b12 | 8524 | |
e1c23804 | 8525 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8526 | { |
e1c23804 DL |
8527 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8528 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8529 | else |
e1c23804 | 8530 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8531 | } |
8532 | } | |
8533 | ||
df7492f9 KH |
8534 | coding_attrs_list = Qnil; |
8535 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8536 | if (NILP (exclude) | |
8537 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8538 | { | |
8539 | Lisp_Object attrs; | |
d46c5b12 | 8540 | |
df7492f9 KH |
8541 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
8542 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
8543 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
8544 | { |
8545 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8546 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8547 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8548 | } | |
df7492f9 | 8549 | } |
d46c5b12 | 8550 | |
df7492f9 | 8551 | if (STRINGP (start)) |
8f924df7 | 8552 | p = pbeg = SDATA (start); |
df7492f9 KH |
8553 | else |
8554 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8555 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8556 | |
df7492f9 KH |
8557 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8558 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8559 | |
0e727afa | 8560 | work_table = Fmake_char_table (Qnil, Qnil); |
05e6f5dc | 8561 | while (p < pend) |
72d1a715 | 8562 | { |
df7492f9 KH |
8563 | if (ASCII_BYTE_P (*p)) |
8564 | p++; | |
72d1a715 RS |
8565 | else |
8566 | { | |
df7492f9 | 8567 | c = STRING_CHAR_ADVANCE (p); |
0e727afa YM |
8568 | if (!NILP (char_table_ref (work_table, c))) |
8569 | /* This character was already checked. Ignore it. */ | |
8570 | continue; | |
12410ef1 | 8571 | |
df7492f9 KH |
8572 | charset_map_loaded = 0; |
8573 | for (tail = coding_attrs_list; CONSP (tail);) | |
8574 | { | |
8575 | elt = XCAR (tail); | |
8576 | if (NILP (elt)) | |
8577 | tail = XCDR (tail); | |
8578 | else if (char_encodable_p (c, elt)) | |
8579 | tail = XCDR (tail); | |
8580 | else if (CONSP (XCDR (tail))) | |
8581 | { | |
8582 | XSETCAR (tail, XCAR (XCDR (tail))); | |
8583 | XSETCDR (tail, XCDR (XCDR (tail))); | |
8584 | } | |
8585 | else | |
8586 | { | |
8587 | XSETCAR (tail, Qnil); | |
8588 | tail = XCDR (tail); | |
8589 | } | |
8590 | } | |
8591 | if (charset_map_loaded) | |
8592 | { | |
d311d28c | 8593 | ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg; |
05e6f5dc | 8594 | |
df7492f9 | 8595 | if (STRINGP (start)) |
8f924df7 | 8596 | pbeg = SDATA (start); |
df7492f9 KH |
8597 | else |
8598 | pbeg = BYTE_POS_ADDR (start_byte); | |
8599 | p = pbeg + p_offset; | |
8600 | pend = pbeg + pend_offset; | |
8601 | } | |
0e727afa | 8602 | char_table_set (work_table, c, Qt); |
df7492f9 | 8603 | } |
ec6d2bb8 | 8604 | } |
fb88bf2d | 8605 | |
988b3759 | 8606 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
8607 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
8608 | if (! NILP (XCAR (tail))) | |
8609 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 8610 | |
05e6f5dc KH |
8611 | return safe_codings; |
8612 | } | |
4956c225 | 8613 | |
d46c5b12 | 8614 | |
8f924df7 KH |
8615 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
8616 | Sunencodable_char_position, 3, 5, 0, | |
8617 | doc: /* | |
8618 | Return position of first un-encodable character in a region. | |
d4a1d553 | 8619 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 8620 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 8621 | |
8f924df7 KH |
8622 | If optional 4th argument COUNT is non-nil, it specifies at most how |
8623 | many un-encodable characters to search. In this case, the value is a | |
8624 | list of positions. | |
d46c5b12 | 8625 | |
8f924df7 KH |
8626 | If optional 5th argument STRING is non-nil, it is a string to search |
8627 | for un-encodable characters. In that case, START and END are indexes | |
8628 | to the string. */) | |
5842a27b | 8629 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object count, Lisp_Object string) |
8f924df7 | 8630 | { |
d311d28c | 8631 | EMACS_INT n; |
8f924df7 | 8632 | struct coding_system coding; |
7d64c6ad | 8633 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 | 8634 | Lisp_Object positions; |
d311d28c | 8635 | ptrdiff_t from, to; |
8f924df7 | 8636 | const unsigned char *p, *stop, *pend; |
f10fe38f | 8637 | bool ascii_compatible; |
fb88bf2d | 8638 | |
8f924df7 KH |
8639 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
8640 | attrs = CODING_ID_ATTRS (coding.id); | |
8641 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
8642 | return Qnil; | |
8643 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
8644 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 8645 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 8646 | |
8f924df7 KH |
8647 | if (NILP (string)) |
8648 | { | |
8649 | validate_region (&start, &end); | |
8650 | from = XINT (start); | |
8651 | to = XINT (end); | |
4b4deea2 | 8652 | if (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
8f924df7 KH |
8653 | || (ascii_compatible |
8654 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
8655 | return Qnil; | |
8656 | p = CHAR_POS_ADDR (from); | |
8657 | pend = CHAR_POS_ADDR (to); | |
8658 | if (from < GPT && to >= GPT) | |
8659 | stop = GPT_ADDR; | |
8660 | else | |
8661 | stop = pend; | |
8662 | } | |
8663 | else | |
8664 | { | |
8665 | CHECK_STRING (string); | |
8666 | CHECK_NATNUM (start); | |
8667 | CHECK_NATNUM (end); | |
d311d28c PE |
8668 | if (! (XINT (start) <= XINT (end) && XINT (end) <= SCHARS (string))) |
8669 | args_out_of_range_3 (string, start, end); | |
8f924df7 KH |
8670 | from = XINT (start); |
8671 | to = XINT (end); | |
8f924df7 KH |
8672 | if (! STRING_MULTIBYTE (string)) |
8673 | return Qnil; | |
8674 | p = SDATA (string) + string_char_to_byte (string, from); | |
8675 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
8676 | if (ascii_compatible && (to - from) == (pend - p)) | |
8677 | return Qnil; | |
8678 | } | |
f2558efd | 8679 | |
8f924df7 KH |
8680 | if (NILP (count)) |
8681 | n = 1; | |
8682 | else | |
b73bfc1c | 8683 | { |
8f924df7 KH |
8684 | CHECK_NATNUM (count); |
8685 | n = XINT (count); | |
b73bfc1c KH |
8686 | } |
8687 | ||
8f924df7 | 8688 | positions = Qnil; |
3633e3aa | 8689 | charset_map_loaded = 0; |
8f924df7 | 8690 | while (1) |
d46c5b12 | 8691 | { |
8f924df7 | 8692 | int c; |
ec6d2bb8 | 8693 | |
8f924df7 KH |
8694 | if (ascii_compatible) |
8695 | while (p < stop && ASCII_BYTE_P (*p)) | |
8696 | p++, from++; | |
8697 | if (p >= stop) | |
0e79d667 | 8698 | { |
8f924df7 KH |
8699 | if (p >= pend) |
8700 | break; | |
8701 | stop = pend; | |
8702 | p = GAP_END_ADDR; | |
0e79d667 | 8703 | } |
ec6d2bb8 | 8704 | |
8f924df7 KH |
8705 | c = STRING_CHAR_ADVANCE (p); |
8706 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
8707 | && ! char_charset (translate_char (translation_table, c), |
8708 | charset_list, NULL)) | |
ec6d2bb8 | 8709 | { |
8f924df7 KH |
8710 | positions = Fcons (make_number (from), positions); |
8711 | n--; | |
8712 | if (n == 0) | |
8713 | break; | |
ec6d2bb8 KH |
8714 | } |
8715 | ||
8f924df7 | 8716 | from++; |
3633e3aa KH |
8717 | if (charset_map_loaded && NILP (string)) |
8718 | { | |
8719 | p = CHAR_POS_ADDR (from); | |
8720 | pend = CHAR_POS_ADDR (to); | |
8721 | if (from < GPT && to >= GPT) | |
8722 | stop = GPT_ADDR; | |
8723 | else | |
8724 | stop = pend; | |
8725 | charset_map_loaded = 0; | |
8726 | } | |
8f924df7 | 8727 | } |
d46c5b12 | 8728 | |
8f924df7 KH |
8729 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
8730 | } | |
d46c5b12 | 8731 | |
d46c5b12 | 8732 | |
df7492f9 KH |
8733 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
8734 | Scheck_coding_systems_region, 3, 3, 0, | |
8735 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 8736 | |
df7492f9 KH |
8737 | START and END are buffer positions specifying the region. |
8738 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 8739 | |
df7492f9 | 8740 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 8741 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
8742 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
8743 | characters are found. | |
93dec019 | 8744 | |
df7492f9 KH |
8745 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
8746 | value is nil. | |
93dec019 | 8747 | |
df7492f9 KH |
8748 | START may be a string. In that case, check if the string is |
8749 | encodable, and the value contains indices to the string instead of | |
5704f39a KH |
8750 | buffer positions. END is ignored. |
8751 | ||
4c1958f4 | 8752 | If the current buffer (or START if it is a string) is unibyte, the value |
5704f39a | 8753 | is nil. */) |
5842a27b | 8754 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system_list) |
05e6f5dc | 8755 | { |
df7492f9 | 8756 | Lisp_Object list; |
d311d28c PE |
8757 | ptrdiff_t start_byte, end_byte; |
8758 | ptrdiff_t pos; | |
7c78e542 | 8759 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8760 | int c; |
7d64c6ad | 8761 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 8762 | |
05e6f5dc KH |
8763 | if (STRINGP (start)) |
8764 | { | |
df7492f9 | 8765 | if (!STRING_MULTIBYTE (start) |
4c1958f4 | 8766 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8767 | return Qnil; |
8768 | start_byte = 0; | |
8f924df7 | 8769 | end_byte = SBYTES (start); |
df7492f9 | 8770 | pos = 0; |
d46c5b12 | 8771 | } |
05e6f5dc | 8772 | else |
b73bfc1c | 8773 | { |
b7826503 PJ |
8774 | CHECK_NUMBER_COERCE_MARKER (start); |
8775 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
8776 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
8777 | args_out_of_range (start, end); | |
4b4deea2 | 8778 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8779 | return Qnil; |
8780 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8781 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8782 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
5704f39a | 8783 | return Qnil; |
df7492f9 | 8784 | |
e1c23804 | 8785 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 8786 | { |
e1c23804 DL |
8787 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8788 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8789 | else |
e1c23804 | 8790 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 8791 | } |
e1c23804 | 8792 | pos = XINT (start); |
b73bfc1c | 8793 | } |
7553d0e1 | 8794 | |
df7492f9 KH |
8795 | list = Qnil; |
8796 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 8797 | { |
df7492f9 | 8798 | elt = XCAR (tail); |
7d64c6ad | 8799 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
8800 | ASET (attrs, coding_attr_trans_tbl, |
8801 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 8802 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
8803 | } |
8804 | ||
df7492f9 | 8805 | if (STRINGP (start)) |
8f924df7 | 8806 | p = pbeg = SDATA (start); |
72d1a715 | 8807 | else |
df7492f9 KH |
8808 | p = pbeg = BYTE_POS_ADDR (start_byte); |
8809 | pend = p + (end_byte - start_byte); | |
4ed46869 | 8810 | |
df7492f9 KH |
8811 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
8812 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 8813 | |
df7492f9 | 8814 | while (p < pend) |
d46c5b12 | 8815 | { |
df7492f9 KH |
8816 | if (ASCII_BYTE_P (*p)) |
8817 | p++; | |
e133c8fa | 8818 | else |
05e6f5dc | 8819 | { |
df7492f9 KH |
8820 | c = STRING_CHAR_ADVANCE (p); |
8821 | ||
8822 | charset_map_loaded = 0; | |
8823 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
8824 | { | |
8825 | elt = XCDR (XCAR (tail)); | |
8826 | if (! char_encodable_p (c, XCAR (elt))) | |
8827 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
8828 | } | |
8829 | if (charset_map_loaded) | |
8830 | { | |
d311d28c | 8831 | ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg; |
df7492f9 KH |
8832 | |
8833 | if (STRINGP (start)) | |
8f924df7 | 8834 | pbeg = SDATA (start); |
df7492f9 KH |
8835 | else |
8836 | pbeg = BYTE_POS_ADDR (start_byte); | |
8837 | p = pbeg + p_offset; | |
8838 | pend = pbeg + pend_offset; | |
8839 | } | |
05e6f5dc | 8840 | } |
df7492f9 | 8841 | pos++; |
d46c5b12 | 8842 | } |
4ed46869 | 8843 | |
df7492f9 KH |
8844 | tail = list; |
8845 | list = Qnil; | |
8846 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 8847 | { |
df7492f9 KH |
8848 | elt = XCAR (tail); |
8849 | if (CONSP (XCDR (XCDR (elt)))) | |
8850 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
8851 | list); | |
ec6d2bb8 | 8852 | } |
2b4f9037 | 8853 | |
df7492f9 | 8854 | return list; |
d46c5b12 KH |
8855 | } |
8856 | ||
3fd9494b | 8857 | |
74ab6df5 | 8858 | static Lisp_Object |
cf84bb53 JB |
8859 | code_convert_region (Lisp_Object start, Lisp_Object end, |
8860 | Lisp_Object coding_system, Lisp_Object dst_object, | |
f10fe38f | 8861 | bool encodep, bool norecord) |
4ed46869 | 8862 | { |
3a73fa5d | 8863 | struct coding_system coding; |
d311d28c | 8864 | ptrdiff_t from, from_byte, to, to_byte; |
df7492f9 | 8865 | Lisp_Object src_object; |
4ed46869 | 8866 | |
df7492f9 KH |
8867 | if (NILP (coding_system)) |
8868 | coding_system = Qno_conversion; | |
8869 | else | |
8870 | CHECK_CODING_SYSTEM (coding_system); | |
8871 | src_object = Fcurrent_buffer (); | |
8872 | if (NILP (dst_object)) | |
8873 | dst_object = src_object; | |
8874 | else if (! EQ (dst_object, Qt)) | |
8875 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 8876 | |
d46c5b12 KH |
8877 | validate_region (&start, &end); |
8878 | from = XFASTINT (start); | |
df7492f9 | 8879 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 8880 | to = XFASTINT (end); |
df7492f9 | 8881 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 8882 | |
df7492f9 KH |
8883 | setup_coding_system (coding_system, &coding); |
8884 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 8885 | |
df7492f9 KH |
8886 | if (encodep) |
8887 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8888 | dst_object); | |
8889 | else | |
8890 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8891 | dst_object); | |
8892 | if (! norecord) | |
8893 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 8894 | |
df7492f9 KH |
8895 | return (BUFFERP (dst_object) |
8896 | ? make_number (coding.produced_char) | |
8897 | : coding.dst_object); | |
4031e2bf | 8898 | } |
78108bcd | 8899 | |
4ed46869 | 8900 | |
4031e2bf | 8901 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 8902 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 8903 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
8904 | When called from a program, takes four arguments: |
8905 | START, END, CODING-SYSTEM, and DESTINATION. | |
8906 | START and END are buffer positions. | |
8844fa83 | 8907 | |
df7492f9 | 8908 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 8909 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
8910 | If buffer, the decoded text is inserted in that buffer after point (point |
8911 | does not move). | |
446dcd75 | 8912 | In those cases, the length of the decoded text is returned. |
319a3947 | 8913 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 8914 | |
48b0f3ae PJ |
8915 | This function sets `last-coding-system-used' to the precise coding system |
8916 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8917 | not fully specified.) */) |
5842a27b | 8918 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
4031e2bf | 8919 | { |
df7492f9 | 8920 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 8921 | } |
8844fa83 | 8922 | |
3a73fa5d | 8923 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
8924 | 3, 4, "r\nzCoding system: ", |
8925 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
8926 | When called from a program, takes four arguments: |
8927 | START, END, CODING-SYSTEM and DESTINATION. | |
8928 | START and END are buffer positions. | |
d46c5b12 | 8929 | |
df7492f9 KH |
8930 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
8931 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
8932 | If buffer, the encoded text is inserted in that buffer after point (point |
8933 | does not move). | |
446dcd75 | 8934 | In those cases, the length of the encoded text is returned. |
319a3947 | 8935 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 8936 | |
48b0f3ae PJ |
8937 | This function sets `last-coding-system-used' to the precise coding system |
8938 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8939 | not fully specified.) */) |
5842a27b | 8940 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
3a73fa5d | 8941 | { |
df7492f9 | 8942 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
8943 | } |
8944 | ||
8945 | Lisp_Object | |
6f704c76 | 8946 | code_convert_string (Lisp_Object string, Lisp_Object coding_system, |
f10fe38f PE |
8947 | Lisp_Object dst_object, bool encodep, bool nocopy, |
8948 | bool norecord) | |
b73bfc1c | 8949 | { |
4031e2bf | 8950 | struct coding_system coding; |
d311d28c | 8951 | ptrdiff_t chars, bytes; |
ec6d2bb8 | 8952 | |
b7826503 | 8953 | CHECK_STRING (string); |
d46c5b12 | 8954 | if (NILP (coding_system)) |
4956c225 | 8955 | { |
df7492f9 KH |
8956 | if (! norecord) |
8957 | Vlast_coding_system_used = Qno_conversion; | |
8958 | if (NILP (dst_object)) | |
8959 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 8960 | } |
b73bfc1c | 8961 | |
df7492f9 KH |
8962 | if (NILP (coding_system)) |
8963 | coding_system = Qno_conversion; | |
8964 | else | |
8965 | CHECK_CODING_SYSTEM (coding_system); | |
8966 | if (NILP (dst_object)) | |
8967 | dst_object = Qt; | |
8968 | else if (! EQ (dst_object, Qt)) | |
8969 | CHECK_BUFFER (dst_object); | |
73be902c | 8970 | |
df7492f9 | 8971 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 8972 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
8973 | chars = SCHARS (string); |
8974 | bytes = SBYTES (string); | |
df7492f9 KH |
8975 | if (encodep) |
8976 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
8977 | else | |
8978 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
8979 | if (! norecord) | |
8980 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 8981 | |
df7492f9 KH |
8982 | return (BUFFERP (dst_object) |
8983 | ? make_number (coding.produced_char) | |
8984 | : coding.dst_object); | |
4ed46869 | 8985 | } |
73be902c | 8986 | |
b73bfc1c | 8987 | |
ecec61c1 | 8988 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 8989 | Do not set Vlast_coding_system_used. |
4ed46869 | 8990 | |
ec6d2bb8 KH |
8991 | This function is called only from macros DECODE_FILE and |
8992 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 8993 | |
ecec61c1 | 8994 | Lisp_Object |
cf84bb53 | 8995 | code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system, |
f10fe38f | 8996 | bool encodep) |
4ed46869 | 8997 | { |
0be8721c | 8998 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
8999 | } |
9000 | ||
4ed46869 | 9001 | |
a7ca3326 | 9002 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
df7492f9 KH |
9003 | 2, 4, 0, |
9004 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
9005 | ||
9006 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
9007 | if the decoding operation is trivial. | |
ecec61c1 | 9008 | |
d4a1d553 | 9009 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
9010 | inserted in that buffer after point (point does not move). In this |
9011 | case, the return value is the length of the decoded text. | |
ecec61c1 | 9012 | |
df7492f9 KH |
9013 | This function sets `last-coding-system-used' to the precise coding system |
9014 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 9015 | not fully specified.) */) |
5842a27b | 9016 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9017 | { |
df7492f9 KH |
9018 | return code_convert_string (string, coding_system, buffer, |
9019 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
9020 | } |
9021 | ||
df7492f9 KH |
9022 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
9023 | 2, 4, 0, | |
9024 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
9025 | ||
9026 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
9027 | itself if the encoding operation is trivial. | |
9028 | ||
d4a1d553 | 9029 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
9030 | inserted in that buffer after point (point does not move). In this |
9031 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
9032 | |
9033 | This function sets `last-coding-system-used' to the precise coding system | |
9034 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
9035 | not fully specified.) */) | |
5842a27b | 9036 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9037 | { |
df7492f9 | 9038 | return code_convert_string (string, coding_system, buffer, |
4550efdf | 9039 | 1, ! NILP (nocopy), 0); |
4ed46869 | 9040 | } |
df7492f9 | 9041 | |
3a73fa5d | 9042 | \f |
4ed46869 | 9043 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
9044 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
9045 | Return the corresponding character. */) | |
5842a27b | 9046 | (Lisp_Object code) |
4ed46869 | 9047 | { |
df7492f9 KH |
9048 | Lisp_Object spec, attrs, val; |
9049 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
5fdb398c PE |
9050 | EMACS_INT ch; |
9051 | int c; | |
4ed46869 | 9052 | |
df7492f9 | 9053 | CHECK_NATNUM (code); |
5fdb398c | 9054 | ch = XFASTINT (code); |
df7492f9 KH |
9055 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); |
9056 | attrs = AREF (spec, 0); | |
4ed46869 | 9057 | |
5fdb398c | 9058 | if (ASCII_BYTE_P (ch) |
df7492f9 KH |
9059 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
9060 | return code; | |
4ed46869 | 9061 | |
df7492f9 KH |
9062 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9063 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
9064 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
9065 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 9066 | |
5fdb398c PE |
9067 | if (ch <= 0x7F) |
9068 | { | |
9069 | c = ch; | |
9070 | charset = charset_roman; | |
9071 | } | |
9072 | else if (ch >= 0xA0 && ch < 0xDF) | |
55ab7be3 | 9073 | { |
5fdb398c | 9074 | c = ch - 0x80; |
df7492f9 | 9075 | charset = charset_kana; |
4ed46869 | 9076 | } |
55ab7be3 | 9077 | else |
4ed46869 | 9078 | { |
5fdb398c PE |
9079 | EMACS_INT c1 = ch >> 8; |
9080 | int c2 = ch & 0xFF; | |
df7492f9 | 9081 | |
2735d060 PE |
9082 | if (c1 < 0x81 || (c1 > 0x9F && c1 < 0xE0) || c1 > 0xEF |
9083 | || c2 < 0x40 || c2 == 0x7F || c2 > 0xFC) | |
c2982e87 | 9084 | error ("Invalid code: %"pI"d", ch); |
5fdb398c | 9085 | c = ch; |
df7492f9 KH |
9086 | SJIS_TO_JIS (c); |
9087 | charset = charset_kanji; | |
4ed46869 | 9088 | } |
df7492f9 KH |
9089 | c = DECODE_CHAR (charset, c); |
9090 | if (c < 0) | |
c2982e87 | 9091 | error ("Invalid code: %"pI"d", ch); |
df7492f9 | 9092 | return make_number (c); |
93dec019 | 9093 | } |
4ed46869 | 9094 | |
48b0f3ae | 9095 | |
4ed46869 | 9096 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 9097 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae | 9098 | Return the corresponding code in SJIS. */) |
5842a27b | 9099 | (Lisp_Object ch) |
4ed46869 | 9100 | { |
df7492f9 KH |
9101 | Lisp_Object spec, attrs, charset_list; |
9102 | int c; | |
9103 | struct charset *charset; | |
9104 | unsigned code; | |
48b0f3ae | 9105 | |
df7492f9 KH |
9106 | CHECK_CHARACTER (ch); |
9107 | c = XFASTINT (ch); | |
9108 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9109 | attrs = AREF (spec, 0); | |
9110 | ||
9111 | if (ASCII_CHAR_P (c) | |
9112 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9113 | return ch; | |
9114 | ||
9115 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9116 | charset = char_charset (c, charset_list, &code); | |
9117 | if (code == CHARSET_INVALID_CODE (charset)) | |
e6c3da20 | 9118 | error ("Can't encode by shift_jis encoding: %c", c); |
df7492f9 KH |
9119 | JIS_TO_SJIS (code); |
9120 | ||
9121 | return make_number (code); | |
4ed46869 KH |
9122 | } |
9123 | ||
9124 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
9125 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
9126 | Return the corresponding character. */) | |
5842a27b | 9127 | (Lisp_Object code) |
d46c5b12 | 9128 | { |
df7492f9 KH |
9129 | Lisp_Object spec, attrs, val; |
9130 | struct charset *charset_roman, *charset_big5, *charset; | |
5fdb398c | 9131 | EMACS_INT ch; |
df7492f9 | 9132 | int c; |
6289dd10 | 9133 | |
df7492f9 | 9134 | CHECK_NATNUM (code); |
5fdb398c | 9135 | ch = XFASTINT (code); |
df7492f9 KH |
9136 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); |
9137 | attrs = AREF (spec, 0); | |
4ed46869 | 9138 | |
5fdb398c | 9139 | if (ASCII_BYTE_P (ch) |
df7492f9 KH |
9140 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
9141 | return code; | |
6289dd10 | 9142 | |
df7492f9 KH |
9143 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9144 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
9145 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 9146 | |
5fdb398c PE |
9147 | if (ch <= 0x7F) |
9148 | { | |
9149 | c = ch; | |
9150 | charset = charset_roman; | |
9151 | } | |
c28a9453 KH |
9152 | else |
9153 | { | |
5fdb398c PE |
9154 | EMACS_INT b1 = ch >> 8; |
9155 | int b2 = ch & 0x7F; | |
df7492f9 KH |
9156 | if (b1 < 0xA1 || b1 > 0xFE |
9157 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
c2982e87 | 9158 | error ("Invalid code: %"pI"d", ch); |
5fdb398c | 9159 | c = ch; |
df7492f9 | 9160 | charset = charset_big5; |
c28a9453 | 9161 | } |
5fdb398c | 9162 | c = DECODE_CHAR (charset, c); |
df7492f9 | 9163 | if (c < 0) |
c2982e87 | 9164 | error ("Invalid code: %"pI"d", ch); |
df7492f9 | 9165 | return make_number (c); |
d46c5b12 | 9166 | } |
6289dd10 | 9167 | |
4ed46869 | 9168 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 9169 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae | 9170 | Return the corresponding character code in Big5. */) |
5842a27b | 9171 | (Lisp_Object ch) |
4ed46869 | 9172 | { |
df7492f9 KH |
9173 | Lisp_Object spec, attrs, charset_list; |
9174 | struct charset *charset; | |
9175 | int c; | |
9176 | unsigned code; | |
9177 | ||
9178 | CHECK_CHARACTER (ch); | |
9179 | c = XFASTINT (ch); | |
9180 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9181 | attrs = AREF (spec, 0); | |
9182 | if (ASCII_CHAR_P (c) | |
9183 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9184 | return ch; | |
9185 | ||
9186 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9187 | charset = char_charset (c, charset_list, &code); | |
9188 | if (code == CHARSET_INVALID_CODE (charset)) | |
e6c3da20 | 9189 | error ("Can't encode by Big5 encoding: %c", c); |
df7492f9 KH |
9190 | |
9191 | return make_number (code); | |
4ed46869 | 9192 | } |
48b0f3ae | 9193 | |
3a73fa5d | 9194 | \f |
002fdb44 | 9195 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 9196 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9197 | doc: /* Internal use only. */) |
5842a27b | 9198 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9199 | { |
b18fad6d KH |
9200 | struct terminal *term = get_terminal (terminal, 1); |
9201 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term); | |
b7826503 | 9202 | CHECK_SYMBOL (coding_system); |
b8299c66 | 9203 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 9204 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 9205 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
ad1746f5 | 9206 | /* Character composition should be disabled. */ |
c73bd236 | 9207 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
9208 | terminal_coding->src_multibyte = 1; |
9209 | terminal_coding->dst_multibyte = 0; | |
3f22b86f PE |
9210 | tset_charset_list |
9211 | (term, (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK | |
9212 | ? coding_charset_list (terminal_coding) | |
9213 | : Fcons (make_number (charset_ascii), Qnil))); | |
4ed46869 KH |
9214 | return Qnil; |
9215 | } | |
9216 | ||
c4825358 KH |
9217 | DEFUN ("set-safe-terminal-coding-system-internal", |
9218 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 9219 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 9220 | doc: /* Internal use only. */) |
5842a27b | 9221 | (Lisp_Object coding_system) |
d46c5b12 | 9222 | { |
b7826503 | 9223 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
9224 | setup_coding_system (Fcheck_coding_system (coding_system), |
9225 | &safe_terminal_coding); | |
ad1746f5 | 9226 | /* Character composition should be disabled. */ |
df7492f9 | 9227 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b73bfc1c KH |
9228 | safe_terminal_coding.src_multibyte = 1; |
9229 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
9230 | return Qnil; |
9231 | } | |
4ed46869 | 9232 | |
002fdb44 | 9233 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 9234 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff | 9235 | doc: /* Return coding system specified for terminal output on the given terminal. |
708e05dc | 9236 | TERMINAL may be a terminal object, a frame, or nil for the selected |
6ed8eeff | 9237 | frame's terminal device. */) |
5842a27b | 9238 | (Lisp_Object terminal) |
4ed46869 | 9239 | { |
985773c9 MB |
9240 | struct coding_system *terminal_coding |
9241 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
9242 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 9243 | |
6d5eb5b0 | 9244 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 9245 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
9246 | } |
9247 | ||
002fdb44 | 9248 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 9249 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9250 | doc: /* Internal use only. */) |
5842a27b | 9251 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9252 | { |
6ed8eeff | 9253 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 9254 | CHECK_SYMBOL (coding_system); |
624bda09 KH |
9255 | if (NILP (coding_system)) |
9256 | coding_system = Qno_conversion; | |
9257 | else | |
9258 | Fcheck_coding_system (coding_system); | |
9259 | setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t)); | |
ad1746f5 | 9260 | /* Character composition should be disabled. */ |
c73bd236 MB |
9261 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
9262 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
9263 | return Qnil; |
9264 | } | |
9265 | ||
9266 | DEFUN ("keyboard-coding-system", | |
985773c9 | 9267 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 9268 | doc: /* Return coding system specified for decoding keyboard input. */) |
5842a27b | 9269 | (Lisp_Object terminal) |
4ed46869 | 9270 | { |
985773c9 MB |
9271 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
9272 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
9273 | } |
9274 | ||
4ed46869 | 9275 | \f |
a7ca3326 | 9276 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
a5d301df | 9277 | Sfind_operation_coding_system, 1, MANY, 0, |
48b0f3ae PJ |
9278 | doc: /* Choose a coding system for an operation based on the target name. |
9279 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
9280 | DECODING-SYSTEM is the coding system to use for decoding | |
9281 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
9282 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 9283 | |
48b0f3ae PJ |
9284 | The first argument OPERATION specifies an I/O primitive: |
9285 | For file I/O, `insert-file-contents' or `write-region'. | |
9286 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
9287 | For network I/O, `open-network-stream'. | |
05e6f5dc | 9288 | |
48b0f3ae PJ |
9289 | The remaining arguments should be the same arguments that were passed |
9290 | to the primitive. Depending on which primitive, one of those arguments | |
9291 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
9292 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 9293 | |
48b0f3ae | 9294 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 9295 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 9296 | For process I/O, TARGET is a process name. |
d4a1d553 | 9297 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 9298 | |
d4a1d553 | 9299 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
9300 | `file-coding-system-alist', `process-coding-system-alist', |
9301 | or `network-coding-system-alist' depending on OPERATION. | |
9302 | They may specify a coding system, a cons of coding systems, | |
9303 | or a function symbol to call. | |
9304 | In the last case, we call the function with one argument, | |
9305 | which is a list of all the arguments given to this function. | |
1011c487 MB |
9306 | If the function can't decide a coding system, it can return |
9307 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 9308 | |
b883cdb2 MB |
9309 | If OPERATION is `insert-file-contents', the argument corresponding to |
9310 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
9311 | file name to look up, and BUFFER is a buffer that contains the file's | |
9312 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
9313 | function to call for FILENAME, that function should examine the | |
9314 | contents of BUFFER instead of reading the file. | |
9315 | ||
d918f936 | 9316 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
f66c7cf8 | 9317 | (ptrdiff_t nargs, Lisp_Object *args) |
6b89e3aa | 9318 | { |
4ed46869 KH |
9319 | Lisp_Object operation, target_idx, target, val; |
9320 | register Lisp_Object chain; | |
177c0ea7 | 9321 | |
4ed46869 KH |
9322 | if (nargs < 2) |
9323 | error ("Too few arguments"); | |
9324 | operation = args[0]; | |
9325 | if (!SYMBOLP (operation) | |
d311d28c | 9326 | || (target_idx = Fget (operation, Qtarget_idx), !NATNUMP (target_idx))) |
3ed051d4 | 9327 | error ("Invalid first argument"); |
7b09a37a | 9328 | if (nargs <= 1 + XFASTINT (target_idx)) |
94dcfacf | 9329 | error ("Too few arguments for operation `%s'", |
8f924df7 | 9330 | SDATA (SYMBOL_NAME (operation))); |
c5101a77 | 9331 | target = args[XFASTINT (target_idx) + 1]; |
4ed46869 | 9332 | if (!(STRINGP (target) |
091a0ff0 KH |
9333 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
9334 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 9335 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
94dcfacf EZ |
9336 | error ("Invalid argument %"pI"d of operation `%s'", |
9337 | XFASTINT (target_idx) + 1, SDATA (SYMBOL_NAME (operation))); | |
091a0ff0 KH |
9338 | if (CONSP (target)) |
9339 | target = XCAR (target); | |
4ed46869 | 9340 | |
2e34157c RS |
9341 | chain = ((EQ (operation, Qinsert_file_contents) |
9342 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9343 | ? Vfile_coding_system_alist |
2e34157c | 9344 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9345 | ? Vnetwork_coding_system_alist |
9346 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9347 | if (NILP (chain)) |
9348 | return Qnil; | |
9349 | ||
03699b14 | 9350 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9351 | { |
f44d27ce | 9352 | Lisp_Object elt; |
6b89e3aa | 9353 | |
df7492f9 | 9354 | elt = XCAR (chain); |
4ed46869 KH |
9355 | if (CONSP (elt) |
9356 | && ((STRINGP (target) | |
03699b14 KR |
9357 | && STRINGP (XCAR (elt)) |
9358 | && fast_string_match (XCAR (elt), target) >= 0) | |
9359 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9360 | { |
03699b14 | 9361 | val = XCDR (elt); |
b19fd4c5 KH |
9362 | /* Here, if VAL is both a valid coding system and a valid |
9363 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9364 | if (CONSP (val)) |
9365 | return val; | |
9366 | if (! SYMBOLP (val)) | |
9367 | return Qnil; | |
9368 | if (! NILP (Fcoding_system_p (val))) | |
9369 | return Fcons (val, val); | |
b19fd4c5 | 9370 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9371 | { |
e2b97060 MB |
9372 | /* We use call1 rather than safe_call1 |
9373 | so as to get bug reports about functions called here | |
9374 | which don't handle the current interface. */ | |
9375 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9376 | if (CONSP (val)) |
9377 | return val; | |
9378 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9379 | return Fcons (val, val); | |
6b89e3aa | 9380 | } |
02ba4723 | 9381 | return Qnil; |
6b89e3aa KH |
9382 | } |
9383 | } | |
4ed46869 | 9384 | return Qnil; |
6b89e3aa KH |
9385 | } |
9386 | ||
df7492f9 | 9387 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9388 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9389 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9390 | If multiple coding systems belong to the same category, |
a3181084 DL |
9391 | all but the first one are ignored. |
9392 | ||
d4a1d553 | 9393 | usage: (set-coding-system-priority &rest coding-systems) */) |
f66c7cf8 | 9394 | (ptrdiff_t nargs, Lisp_Object *args) |
df7492f9 | 9395 | { |
f66c7cf8 | 9396 | ptrdiff_t i, j; |
f10fe38f | 9397 | bool changed[coding_category_max]; |
df7492f9 KH |
9398 | enum coding_category priorities[coding_category_max]; |
9399 | ||
72af86bd | 9400 | memset (changed, 0, sizeof changed); |
6b89e3aa | 9401 | |
df7492f9 | 9402 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9403 | { |
df7492f9 KH |
9404 | enum coding_category category; |
9405 | Lisp_Object spec, attrs; | |
6b89e3aa | 9406 | |
df7492f9 KH |
9407 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9408 | attrs = AREF (spec, 0); | |
9409 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9410 | if (changed[category]) | |
9411 | /* Ignore this coding system because a coding system of the | |
9412 | same category already had a higher priority. */ | |
9413 | continue; | |
9414 | changed[category] = 1; | |
9415 | priorities[j++] = category; | |
9416 | if (coding_categories[category].id >= 0 | |
9417 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9418 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9419 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9420 | } |
6b89e3aa | 9421 | |
df7492f9 KH |
9422 | /* Now we have decided top J priorities. Reflect the order of the |
9423 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9424 | |
df7492f9 | 9425 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9426 | { |
df7492f9 KH |
9427 | while (j < coding_category_max |
9428 | && changed[coding_priorities[j]]) | |
9429 | j++; | |
9430 | if (j == coding_category_max) | |
1088b922 | 9431 | emacs_abort (); |
df7492f9 KH |
9432 | priorities[i] = coding_priorities[j]; |
9433 | } | |
6b89e3aa | 9434 | |
72af86bd | 9435 | memcpy (coding_priorities, priorities, sizeof priorities); |
177c0ea7 | 9436 | |
ff563fce KH |
9437 | /* Update `coding-category-list'. */ |
9438 | Vcoding_category_list = Qnil; | |
c5101a77 | 9439 | for (i = coding_category_max; i-- > 0; ) |
ff563fce KH |
9440 | Vcoding_category_list |
9441 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9442 | Vcoding_category_list); | |
6b89e3aa | 9443 | |
df7492f9 | 9444 | return Qnil; |
6b89e3aa KH |
9445 | } |
9446 | ||
df7492f9 KH |
9447 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9448 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 | 9449 | doc: /* Return a list of coding systems ordered by their priorities. |
b811c52b KH |
9450 | The list contains a subset of coding systems; i.e. coding systems |
9451 | assigned to each coding category (see `coding-category-list'). | |
9452 | ||
da7db224 | 9453 | HIGHESTP non-nil means just return the highest priority one. */) |
5842a27b | 9454 | (Lisp_Object highestp) |
d46c5b12 KH |
9455 | { |
9456 | int i; | |
df7492f9 | 9457 | Lisp_Object val; |
6b89e3aa | 9458 | |
df7492f9 | 9459 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9460 | { |
df7492f9 KH |
9461 | enum coding_category category = coding_priorities[i]; |
9462 | int id = coding_categories[category].id; | |
9463 | Lisp_Object attrs; | |
068a9dbd | 9464 | |
df7492f9 KH |
9465 | if (id < 0) |
9466 | continue; | |
9467 | attrs = CODING_ID_ATTRS (id); | |
9468 | if (! NILP (highestp)) | |
9469 | return CODING_ATTR_BASE_NAME (attrs); | |
9470 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9471 | } | |
9472 | return Fnreverse (val); | |
9473 | } | |
068a9dbd | 9474 | |
91433552 | 9475 | static const char *const suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9476 | |
9477 | static Lisp_Object | |
971de7fb | 9478 | make_subsidiaries (Lisp_Object base) |
068a9dbd | 9479 | { |
df7492f9 | 9480 | Lisp_Object subsidiaries; |
1bfdaf10 | 9481 | ptrdiff_t base_name_len = SBYTES (SYMBOL_NAME (base)); |
38182d90 | 9482 | char *buf = alloca (base_name_len + 6); |
df7492f9 | 9483 | int i; |
068a9dbd | 9484 | |
72af86bd | 9485 | memcpy (buf, SDATA (SYMBOL_NAME (base)), base_name_len); |
25721f5b | 9486 | subsidiaries = make_uninit_vector (3); |
df7492f9 | 9487 | for (i = 0; i < 3; i++) |
068a9dbd | 9488 | { |
1bfdaf10 | 9489 | strcpy (buf + base_name_len, suffixes[i]); |
df7492f9 | 9490 | ASET (subsidiaries, i, intern (buf)); |
068a9dbd | 9491 | } |
df7492f9 | 9492 | return subsidiaries; |
068a9dbd KH |
9493 | } |
9494 | ||
9495 | ||
df7492f9 KH |
9496 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9497 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9498 | doc: /* For internal use only. |
9499 | usage: (define-coding-system-internal ...) */) | |
f66c7cf8 | 9500 | (ptrdiff_t nargs, Lisp_Object *args) |
068a9dbd | 9501 | { |
df7492f9 KH |
9502 | Lisp_Object name; |
9503 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9504 | Lisp_Object attrs; /* Vector of attributes. */ | |
9505 | Lisp_Object eol_type; | |
9506 | Lisp_Object aliases; | |
9507 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9508 | enum coding_category category; | |
9509 | Lisp_Object tail, val; | |
9510 | int max_charset_id = 0; | |
9511 | int i; | |
068a9dbd | 9512 | |
df7492f9 KH |
9513 | if (nargs < coding_arg_max) |
9514 | goto short_args; | |
068a9dbd | 9515 | |
df7492f9 | 9516 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9517 | |
df7492f9 KH |
9518 | name = args[coding_arg_name]; |
9519 | CHECK_SYMBOL (name); | |
4939150c | 9520 | ASET (attrs, coding_attr_base_name, name); |
068a9dbd | 9521 | |
df7492f9 KH |
9522 | val = args[coding_arg_mnemonic]; |
9523 | if (! STRINGP (val)) | |
9524 | CHECK_CHARACTER (val); | |
4939150c | 9525 | ASET (attrs, coding_attr_mnemonic, val); |
068a9dbd | 9526 | |
df7492f9 KH |
9527 | coding_type = args[coding_arg_coding_type]; |
9528 | CHECK_SYMBOL (coding_type); | |
4939150c | 9529 | ASET (attrs, coding_attr_type, coding_type); |
068a9dbd | 9530 | |
df7492f9 KH |
9531 | charset_list = args[coding_arg_charset_list]; |
9532 | if (SYMBOLP (charset_list)) | |
9533 | { | |
9534 | if (EQ (charset_list, Qiso_2022)) | |
9535 | { | |
9536 | if (! EQ (coding_type, Qiso_2022)) | |
9537 | error ("Invalid charset-list"); | |
9538 | charset_list = Viso_2022_charset_list; | |
9539 | } | |
9540 | else if (EQ (charset_list, Qemacs_mule)) | |
9541 | { | |
9542 | if (! EQ (coding_type, Qemacs_mule)) | |
9543 | error ("Invalid charset-list"); | |
9544 | charset_list = Vemacs_mule_charset_list; | |
9545 | } | |
9546 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
d311d28c PE |
9547 | { |
9548 | if (! RANGED_INTEGERP (0, XCAR (tail), INT_MAX - 1)) | |
9549 | error ("Invalid charset-list"); | |
9550 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9551 | max_charset_id = XFASTINT (XCAR (tail)); | |
9552 | } | |
df7492f9 | 9553 | } |
068a9dbd KH |
9554 | else |
9555 | { | |
df7492f9 | 9556 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9557 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9558 | { |
df7492f9 KH |
9559 | struct charset *charset; |
9560 | ||
985773c9 | 9561 | val = XCAR (tail); |
df7492f9 KH |
9562 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9563 | if (EQ (coding_type, Qiso_2022) | |
9564 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9565 | : EQ (coding_type, Qemacs_mule) | |
9566 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9567 | : 0) | |
9568 | error ("Can't handle charset `%s'", | |
8f924df7 | 9569 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9570 | |
8f924df7 | 9571 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9572 | if (max_charset_id < charset->id) |
9573 | max_charset_id = charset->id; | |
068a9dbd KH |
9574 | } |
9575 | } | |
4939150c | 9576 | ASET (attrs, coding_attr_charset_list, charset_list); |
068a9dbd | 9577 | |
1b3b981b AS |
9578 | safe_charsets = make_uninit_string (max_charset_id + 1); |
9579 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 | 9580 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8f924df7 | 9581 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
4939150c | 9582 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); |
068a9dbd | 9583 | |
4939150c | 9584 | ASET (attrs, coding_attr_ascii_compat, args[coding_arg_ascii_compatible_p]); |
3a73fa5d | 9585 | |
df7492f9 | 9586 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 9587 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9588 | CHECK_SYMBOL (val); |
4939150c | 9589 | ASET (attrs, coding_attr_decode_tbl, val); |
3a73fa5d | 9590 | |
df7492f9 | 9591 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 9592 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9593 | CHECK_SYMBOL (val); |
4939150c | 9594 | ASET (attrs, coding_attr_encode_tbl, val); |
d46c5b12 | 9595 | |
df7492f9 KH |
9596 | val = args[coding_arg_post_read_conversion]; |
9597 | CHECK_SYMBOL (val); | |
4939150c | 9598 | ASET (attrs, coding_attr_post_read, val); |
d46c5b12 | 9599 | |
df7492f9 KH |
9600 | val = args[coding_arg_pre_write_conversion]; |
9601 | CHECK_SYMBOL (val); | |
4939150c | 9602 | ASET (attrs, coding_attr_pre_write, val); |
3a73fa5d | 9603 | |
df7492f9 KH |
9604 | val = args[coding_arg_default_char]; |
9605 | if (NILP (val)) | |
4939150c | 9606 | ASET (attrs, coding_attr_default_char, make_number (' ')); |
df7492f9 KH |
9607 | else |
9608 | { | |
8f924df7 | 9609 | CHECK_CHARACTER (val); |
4939150c | 9610 | ASET (attrs, coding_attr_default_char, val); |
df7492f9 | 9611 | } |
4031e2bf | 9612 | |
8f924df7 | 9613 | val = args[coding_arg_for_unibyte]; |
4939150c | 9614 | ASET (attrs, coding_attr_for_unibyte, NILP (val) ? Qnil : Qt); |
3a73fa5d | 9615 | |
df7492f9 KH |
9616 | val = args[coding_arg_plist]; |
9617 | CHECK_LIST (val); | |
4939150c | 9618 | ASET (attrs, coding_attr_plist, val); |
3a73fa5d | 9619 | |
df7492f9 KH |
9620 | if (EQ (coding_type, Qcharset)) |
9621 | { | |
c7c66a95 KH |
9622 | /* Generate a lisp vector of 256 elements. Each element is nil, |
9623 | integer, or a list of charset IDs. | |
3a73fa5d | 9624 | |
c7c66a95 KH |
9625 | If Nth element is nil, the byte code N is invalid in this |
9626 | coding system. | |
4ed46869 | 9627 | |
c7c66a95 KH |
9628 | If Nth element is a number NUM, N is the first byte of a |
9629 | charset whose ID is NUM. | |
4ed46869 | 9630 | |
c7c66a95 KH |
9631 | If Nth element is a list of charset IDs, N is the first byte |
9632 | of one of them. The list is sorted by dimensions of the | |
ad1746f5 | 9633 | charsets. A charset of smaller dimension comes first. */ |
df7492f9 | 9634 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 9635 | |
5c99c2e6 | 9636 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9637 | { |
c7c66a95 KH |
9638 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
9639 | int dim = CHARSET_DIMENSION (charset); | |
9640 | int idx = (dim - 1) * 4; | |
4ed46869 | 9641 | |
5c99c2e6 | 9642 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9643 | ASET (attrs, coding_attr_ascii_compat, Qt); |
4031e2bf | 9644 | |
15d143f7 KH |
9645 | for (i = charset->code_space[idx]; |
9646 | i <= charset->code_space[idx + 1]; i++) | |
9647 | { | |
c7c66a95 KH |
9648 | Lisp_Object tmp, tmp2; |
9649 | int dim2; | |
ec6d2bb8 | 9650 | |
c7c66a95 KH |
9651 | tmp = AREF (val, i); |
9652 | if (NILP (tmp)) | |
9653 | tmp = XCAR (tail); | |
9654 | else if (NUMBERP (tmp)) | |
9655 | { | |
9656 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
9657 | if (dim < dim2) | |
c7c66a95 | 9658 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
9659 | else |
9660 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 9661 | } |
15d143f7 | 9662 | else |
c7c66a95 KH |
9663 | { |
9664 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
9665 | { | |
9666 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
9667 | if (dim < dim2) | |
9668 | break; | |
9669 | } | |
9670 | if (NILP (tmp2)) | |
9671 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
9672 | else | |
9673 | { | |
9674 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
9675 | XSETCAR (tmp2, XCAR (tail)); | |
9676 | } | |
9677 | } | |
9678 | ASET (val, i, tmp); | |
15d143f7 | 9679 | } |
df7492f9 KH |
9680 | } |
9681 | ASET (attrs, coding_attr_charset_valids, val); | |
9682 | category = coding_category_charset; | |
9683 | } | |
9684 | else if (EQ (coding_type, Qccl)) | |
9685 | { | |
9686 | Lisp_Object valids; | |
ecec61c1 | 9687 | |
df7492f9 KH |
9688 | if (nargs < coding_arg_ccl_max) |
9689 | goto short_args; | |
ecec61c1 | 9690 | |
df7492f9 KH |
9691 | val = args[coding_arg_ccl_decoder]; |
9692 | CHECK_CCL_PROGRAM (val); | |
9693 | if (VECTORP (val)) | |
9694 | val = Fcopy_sequence (val); | |
9695 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 9696 | |
df7492f9 KH |
9697 | val = args[coding_arg_ccl_encoder]; |
9698 | CHECK_CCL_PROGRAM (val); | |
9699 | if (VECTORP (val)) | |
9700 | val = Fcopy_sequence (val); | |
9701 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 9702 | |
df7492f9 KH |
9703 | val = args[coding_arg_ccl_valids]; |
9704 | valids = Fmake_string (make_number (256), make_number (0)); | |
7d7bbefd | 9705 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9706 | { |
8dcbea82 | 9707 | int from, to; |
ecec61c1 | 9708 | |
34348bd4 | 9709 | val = XCAR (tail); |
df7492f9 | 9710 | if (INTEGERP (val)) |
8dcbea82 | 9711 | { |
d311d28c | 9712 | if (! (0 <= XINT (val) && XINT (val) <= 255)) |
8dcbea82 | 9713 | args_out_of_range_3 (val, make_number (0), make_number (255)); |
d311d28c | 9714 | from = to = XINT (val); |
8dcbea82 | 9715 | } |
df7492f9 KH |
9716 | else |
9717 | { | |
df7492f9 | 9718 | CHECK_CONS (val); |
8f924df7 | 9719 | CHECK_NATNUM_CAR (val); |
d311d28c PE |
9720 | CHECK_NUMBER_CDR (val); |
9721 | if (XINT (XCAR (val)) > 255) | |
8dcbea82 KH |
9722 | args_out_of_range_3 (XCAR (val), |
9723 | make_number (0), make_number (255)); | |
d311d28c PE |
9724 | from = XINT (XCAR (val)); |
9725 | if (! (from <= XINT (XCDR (val)) && XINT (XCDR (val)) <= 255)) | |
8dcbea82 KH |
9726 | args_out_of_range_3 (XCDR (val), |
9727 | XCAR (val), make_number (255)); | |
d311d28c | 9728 | to = XINT (XCDR (val)); |
df7492f9 | 9729 | } |
8dcbea82 | 9730 | for (i = from; i <= to; i++) |
8f924df7 | 9731 | SSET (valids, i, 1); |
df7492f9 KH |
9732 | } |
9733 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 9734 | |
df7492f9 | 9735 | category = coding_category_ccl; |
55ab7be3 | 9736 | } |
df7492f9 | 9737 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 9738 | { |
df7492f9 | 9739 | Lisp_Object bom, endian; |
4ed46869 | 9740 | |
4939150c | 9741 | ASET (attrs, coding_attr_ascii_compat, Qnil); |
4ed46869 | 9742 | |
df7492f9 KH |
9743 | if (nargs < coding_arg_utf16_max) |
9744 | goto short_args; | |
4ed46869 | 9745 | |
df7492f9 KH |
9746 | bom = args[coding_arg_utf16_bom]; |
9747 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9748 | { | |
9749 | CHECK_CONS (bom); | |
8f924df7 KH |
9750 | val = XCAR (bom); |
9751 | CHECK_CODING_SYSTEM (val); | |
9752 | val = XCDR (bom); | |
9753 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 9754 | } |
a470d443 | 9755 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
9756 | |
9757 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
9758 | CHECK_SYMBOL (endian); |
9759 | if (NILP (endian)) | |
9760 | endian = Qbig; | |
9761 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 9762 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
9763 | ASET (attrs, coding_attr_utf_16_endian, endian); |
9764 | ||
9765 | category = (CONSP (bom) | |
9766 | ? coding_category_utf_16_auto | |
9767 | : NILP (bom) | |
b49a1807 | 9768 | ? (EQ (endian, Qbig) |
df7492f9 KH |
9769 | ? coding_category_utf_16_be_nosig |
9770 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 9771 | : (EQ (endian, Qbig) |
df7492f9 KH |
9772 | ? coding_category_utf_16_be |
9773 | : coding_category_utf_16_le)); | |
9774 | } | |
9775 | else if (EQ (coding_type, Qiso_2022)) | |
9776 | { | |
9777 | Lisp_Object initial, reg_usage, request, flags; | |
1397dc18 | 9778 | |
df7492f9 KH |
9779 | if (nargs < coding_arg_iso2022_max) |
9780 | goto short_args; | |
9781 | ||
9782 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
9783 | CHECK_VECTOR (initial); | |
9784 | for (i = 0; i < 4; i++) | |
9785 | { | |
9a9d91d9 | 9786 | val = AREF (initial, i); |
df7492f9 KH |
9787 | if (! NILP (val)) |
9788 | { | |
584948ac KH |
9789 | struct charset *charset; |
9790 | ||
9791 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
9792 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
9793 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
4939150c | 9794 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9795 | } |
9796 | else | |
9797 | ASET (initial, i, make_number (-1)); | |
9798 | } | |
9799 | ||
9800 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
9801 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
9802 | CHECK_NUMBER_CAR (reg_usage); |
9803 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
9804 | |
9805 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
7d7bbefd | 9806 | for (tail = request; CONSP (tail); tail = XCDR (tail)) |
1397dc18 | 9807 | { |
df7492f9 | 9808 | int id; |
2735d060 | 9809 | Lisp_Object tmp1; |
df7492f9 | 9810 | |
34348bd4 | 9811 | val = XCAR (tail); |
df7492f9 | 9812 | CHECK_CONS (val); |
2735d060 PE |
9813 | tmp1 = XCAR (val); |
9814 | CHECK_CHARSET_GET_ID (tmp1, id); | |
8f924df7 | 9815 | CHECK_NATNUM_CDR (val); |
df7492f9 | 9816 | if (XINT (XCDR (val)) >= 4) |
c2982e87 | 9817 | error ("Invalid graphic register number: %"pI"d", XINT (XCDR (val))); |
8f924df7 | 9818 | XSETCAR (val, make_number (id)); |
1397dc18 | 9819 | } |
4ed46869 | 9820 | |
df7492f9 KH |
9821 | flags = args[coding_arg_iso2022_flags]; |
9822 | CHECK_NATNUM (flags); | |
d311d28c | 9823 | i = XINT (flags) & INT_MAX; |
df7492f9 | 9824 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) |
d311d28c PE |
9825 | i |= CODING_ISO_FLAG_FULL_SUPPORT; |
9826 | flags = make_number (i); | |
df7492f9 KH |
9827 | |
9828 | ASET (attrs, coding_attr_iso_initial, initial); | |
9829 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
9830 | ASET (attrs, coding_attr_iso_request, request); | |
9831 | ASET (attrs, coding_attr_iso_flags, flags); | |
9832 | setup_iso_safe_charsets (attrs); | |
9833 | ||
9834 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
9835 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
9836 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
9837 | ? coding_category_iso_7_else | |
9838 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
9839 | ? coding_category_iso_7 | |
9840 | : coding_category_iso_7_tight); | |
9841 | else | |
9842 | { | |
9843 | int id = XINT (AREF (initial, 1)); | |
9844 | ||
c6fb6e98 | 9845 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
9846 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
9847 | || id < 0) | |
9848 | ? coding_category_iso_8_else | |
9849 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
9850 | ? coding_category_iso_8_1 | |
9851 | : coding_category_iso_8_2); | |
9852 | } | |
0ce7886f KH |
9853 | if (category != coding_category_iso_8_1 |
9854 | && category != coding_category_iso_8_2) | |
4939150c | 9855 | ASET (attrs, coding_attr_ascii_compat, Qnil); |
df7492f9 KH |
9856 | } |
9857 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 9858 | { |
df7492f9 KH |
9859 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
9860 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
4939150c | 9861 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 | 9862 | category = coding_category_emacs_mule; |
c28a9453 | 9863 | } |
df7492f9 | 9864 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 9865 | { |
df7492f9 KH |
9866 | |
9867 | struct charset *charset; | |
9868 | ||
7d64c6ad | 9869 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 9870 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 9871 | error ("There should be three or four charsets"); |
df7492f9 KH |
9872 | |
9873 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9874 | if (CHARSET_DIMENSION (charset) != 1) | |
9875 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9876 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac | 9877 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9878 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9879 | |
9880 | charset_list = XCDR (charset_list); | |
9881 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9882 | if (CHARSET_DIMENSION (charset) != 1) | |
9883 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9884 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
9885 | |
9886 | charset_list = XCDR (charset_list); | |
9887 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9888 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
9889 | error ("Dimension of charset %s is not two", |
9890 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9891 | ||
9892 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
9893 | if (! NILP (charset_list)) |
9894 | { | |
9895 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9896 | if (CHARSET_DIMENSION (charset) != 2) | |
9897 | error ("Dimension of charset %s is not two", | |
9898 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9899 | } | |
df7492f9 KH |
9900 | |
9901 | category = coding_category_sjis; | |
9902 | Vsjis_coding_system = name; | |
c28a9453 | 9903 | } |
df7492f9 KH |
9904 | else if (EQ (coding_type, Qbig5)) |
9905 | { | |
9906 | struct charset *charset; | |
4ed46869 | 9907 | |
df7492f9 KH |
9908 | if (XINT (Flength (charset_list)) != 2) |
9909 | error ("There should be just two charsets"); | |
9910 | ||
9911 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9912 | if (CHARSET_DIMENSION (charset) != 1) | |
9913 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9914 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac | 9915 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9916 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9917 | |
9918 | charset_list = XCDR (charset_list); | |
9919 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9920 | if (CHARSET_DIMENSION (charset) != 2) | |
9921 | error ("Dimension of charset %s is not two", | |
8f924df7 | 9922 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 9923 | |
df7492f9 KH |
9924 | category = coding_category_big5; |
9925 | Vbig5_coding_system = name; | |
9926 | } | |
9927 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 9928 | { |
584948ac | 9929 | category = coding_category_raw_text; |
4939150c | 9930 | ASET (attrs, coding_attr_ascii_compat, Qt); |
c28a9453 | 9931 | } |
df7492f9 | 9932 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 9933 | { |
a470d443 KH |
9934 | Lisp_Object bom; |
9935 | ||
a470d443 KH |
9936 | if (nargs < coding_arg_utf8_max) |
9937 | goto short_args; | |
9938 | ||
9939 | bom = args[coding_arg_utf8_bom]; | |
9940 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9941 | { | |
9942 | CHECK_CONS (bom); | |
9943 | val = XCAR (bom); | |
9944 | CHECK_CODING_SYSTEM (val); | |
9945 | val = XCDR (bom); | |
9946 | CHECK_CODING_SYSTEM (val); | |
9947 | } | |
9948 | ASET (attrs, coding_attr_utf_bom, bom); | |
0e5317f7 | 9949 | if (NILP (bom)) |
4939150c | 9950 | ASET (attrs, coding_attr_ascii_compat, Qt); |
a470d443 KH |
9951 | |
9952 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
9953 | : NILP (bom) ? coding_category_utf_8_nosig | |
9954 | : coding_category_utf_8_sig); | |
4ed46869 | 9955 | } |
df7492f9 KH |
9956 | else if (EQ (coding_type, Qundecided)) |
9957 | category = coding_category_undecided; | |
4ed46869 | 9958 | else |
df7492f9 | 9959 | error ("Invalid coding system type: %s", |
8f924df7 | 9960 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 9961 | |
4939150c PE |
9962 | ASET (attrs, coding_attr_category, make_number (category)); |
9963 | ASET (attrs, coding_attr_plist, | |
9964 | Fcons (QCcategory, | |
9965 | Fcons (AREF (Vcoding_category_table, category), | |
9966 | CODING_ATTR_PLIST (attrs)))); | |
9967 | ASET (attrs, coding_attr_plist, | |
9968 | Fcons (QCascii_compatible_p, | |
9969 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), | |
9970 | CODING_ATTR_PLIST (attrs)))); | |
c4825358 | 9971 | |
df7492f9 KH |
9972 | eol_type = args[coding_arg_eol_type]; |
9973 | if (! NILP (eol_type) | |
9974 | && ! EQ (eol_type, Qunix) | |
9975 | && ! EQ (eol_type, Qdos) | |
9976 | && ! EQ (eol_type, Qmac)) | |
9977 | error ("Invalid eol-type"); | |
4ed46869 | 9978 | |
df7492f9 | 9979 | aliases = Fcons (name, Qnil); |
4ed46869 | 9980 | |
df7492f9 KH |
9981 | if (NILP (eol_type)) |
9982 | { | |
9983 | eol_type = make_subsidiaries (name); | |
9984 | for (i = 0; i < 3; i++) | |
1397dc18 | 9985 | { |
df7492f9 KH |
9986 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
9987 | ||
9988 | this_name = AREF (eol_type, i); | |
9989 | this_aliases = Fcons (this_name, Qnil); | |
9990 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
25721f5b DA |
9991 | this_spec = make_uninit_vector (3); |
9992 | ASET (this_spec, 0, attrs); | |
df7492f9 KH |
9993 | ASET (this_spec, 1, this_aliases); |
9994 | ASET (this_spec, 2, this_eol_type); | |
9995 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
9996 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
9997 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
9998 | if (NILP (val)) | |
9999 | Vcoding_system_alist | |
10000 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
10001 | Vcoding_system_alist); | |
1397dc18 | 10002 | } |
d46c5b12 | 10003 | } |
4ed46869 | 10004 | |
25721f5b DA |
10005 | spec_vec = make_uninit_vector (3); |
10006 | ASET (spec_vec, 0, attrs); | |
df7492f9 KH |
10007 | ASET (spec_vec, 1, aliases); |
10008 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 10009 | |
df7492f9 KH |
10010 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
10011 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
10012 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
10013 | if (NILP (val)) | |
10014 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
10015 | Vcoding_system_alist); | |
48b0f3ae | 10016 | |
df7492f9 KH |
10017 | { |
10018 | int id = coding_categories[category].id; | |
48b0f3ae | 10019 | |
df7492f9 KH |
10020 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
10021 | setup_coding_system (name, &coding_categories[category]); | |
10022 | } | |
48b0f3ae | 10023 | |
d46c5b12 | 10024 | return Qnil; |
48b0f3ae | 10025 | |
df7492f9 KH |
10026 | short_args: |
10027 | return Fsignal (Qwrong_number_of_arguments, | |
10028 | Fcons (intern ("define-coding-system-internal"), | |
10029 | make_number (nargs))); | |
d46c5b12 | 10030 | } |
4ed46869 | 10031 | |
d6925f38 | 10032 | |
a6f87d34 KH |
10033 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
10034 | 3, 3, 0, | |
10035 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
5842a27b | 10036 | (Lisp_Object coding_system, Lisp_Object prop, Lisp_Object val) |
a6f87d34 | 10037 | { |
3dbe7859 | 10038 | Lisp_Object spec, attrs; |
a6f87d34 KH |
10039 | |
10040 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10041 | attrs = AREF (spec, 0); | |
10042 | if (EQ (prop, QCmnemonic)) | |
10043 | { | |
10044 | if (! STRINGP (val)) | |
10045 | CHECK_CHARACTER (val); | |
4939150c | 10046 | ASET (attrs, coding_attr_mnemonic, val); |
a6f87d34 | 10047 | } |
2133e2d1 | 10048 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
10049 | { |
10050 | if (NILP (val)) | |
10051 | val = make_number (' '); | |
10052 | else | |
10053 | CHECK_CHARACTER (val); | |
4939150c | 10054 | ASET (attrs, coding_attr_default_char, val); |
a6f87d34 KH |
10055 | } |
10056 | else if (EQ (prop, QCdecode_translation_table)) | |
10057 | { | |
10058 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10059 | CHECK_SYMBOL (val); | |
4939150c | 10060 | ASET (attrs, coding_attr_decode_tbl, val); |
a6f87d34 KH |
10061 | } |
10062 | else if (EQ (prop, QCencode_translation_table)) | |
10063 | { | |
10064 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10065 | CHECK_SYMBOL (val); | |
4939150c | 10066 | ASET (attrs, coding_attr_encode_tbl, val); |
a6f87d34 KH |
10067 | } |
10068 | else if (EQ (prop, QCpost_read_conversion)) | |
10069 | { | |
10070 | CHECK_SYMBOL (val); | |
4939150c | 10071 | ASET (attrs, coding_attr_post_read, val); |
a6f87d34 KH |
10072 | } |
10073 | else if (EQ (prop, QCpre_write_conversion)) | |
10074 | { | |
10075 | CHECK_SYMBOL (val); | |
4939150c | 10076 | ASET (attrs, coding_attr_pre_write, val); |
a6f87d34 | 10077 | } |
35befdaa KH |
10078 | else if (EQ (prop, QCascii_compatible_p)) |
10079 | { | |
4939150c | 10080 | ASET (attrs, coding_attr_ascii_compat, val); |
35befdaa | 10081 | } |
a6f87d34 | 10082 | |
4939150c PE |
10083 | ASET (attrs, coding_attr_plist, |
10084 | Fplist_put (CODING_ATTR_PLIST (attrs), prop, val)); | |
a6f87d34 KH |
10085 | return val; |
10086 | } | |
10087 | ||
10088 | ||
df7492f9 KH |
10089 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
10090 | Sdefine_coding_system_alias, 2, 2, 0, | |
10091 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
5842a27b | 10092 | (Lisp_Object alias, Lisp_Object coding_system) |
66cfb530 | 10093 | { |
583f71ca | 10094 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 10095 | |
df7492f9 KH |
10096 | CHECK_SYMBOL (alias); |
10097 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10098 | aliases = AREF (spec, 1); | |
d4a1d553 | 10099 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
10100 | element is a base coding system. Append ALIAS at the tail of the |
10101 | list. */ | |
df7492f9 KH |
10102 | while (!NILP (XCDR (aliases))) |
10103 | aliases = XCDR (aliases); | |
8f924df7 | 10104 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 10105 | |
df7492f9 KH |
10106 | eol_type = AREF (spec, 2); |
10107 | if (VECTORP (eol_type)) | |
4ed46869 | 10108 | { |
df7492f9 KH |
10109 | Lisp_Object subsidiaries; |
10110 | int i; | |
4ed46869 | 10111 | |
df7492f9 KH |
10112 | subsidiaries = make_subsidiaries (alias); |
10113 | for (i = 0; i < 3; i++) | |
10114 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
10115 | AREF (eol_type, i)); | |
4ed46869 | 10116 | } |
df7492f9 KH |
10117 | |
10118 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 10119 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
10120 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
10121 | if (NILP (val)) | |
10122 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
10123 | Vcoding_system_alist); | |
66cfb530 | 10124 | |
4ed46869 KH |
10125 | return Qnil; |
10126 | } | |
10127 | ||
a7ca3326 | 10128 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
df7492f9 KH |
10129 | 1, 1, 0, |
10130 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 10131 | Any alias or subsidiary coding system is not a base coding system. */) |
5842a27b | 10132 | (Lisp_Object coding_system) |
d46c5b12 | 10133 | { |
df7492f9 | 10134 | Lisp_Object spec, attrs; |
d46c5b12 | 10135 | |
df7492f9 KH |
10136 | if (NILP (coding_system)) |
10137 | return (Qno_conversion); | |
10138 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10139 | attrs = AREF (spec, 0); | |
10140 | return CODING_ATTR_BASE_NAME (attrs); | |
10141 | } | |
1397dc18 | 10142 | |
df7492f9 KH |
10143 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
10144 | 1, 1, 0, | |
10145 | doc: "Return the property list of CODING-SYSTEM.") | |
5842a27b | 10146 | (Lisp_Object coding_system) |
df7492f9 KH |
10147 | { |
10148 | Lisp_Object spec, attrs; | |
1397dc18 | 10149 | |
df7492f9 KH |
10150 | if (NILP (coding_system)) |
10151 | coding_system = Qno_conversion; | |
10152 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10153 | attrs = AREF (spec, 0); | |
10154 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
10155 | } |
10156 | ||
df7492f9 KH |
10157 | |
10158 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
10159 | 1, 1, 0, | |
da7db224 | 10160 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
5842a27b | 10161 | (Lisp_Object coding_system) |
66cfb530 | 10162 | { |
df7492f9 | 10163 | Lisp_Object spec; |
84d60297 | 10164 | |
df7492f9 KH |
10165 | if (NILP (coding_system)) |
10166 | coding_system = Qno_conversion; | |
10167 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 10168 | return AREF (spec, 1); |
df7492f9 | 10169 | } |
66cfb530 | 10170 | |
a7ca3326 | 10171 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
df7492f9 KH |
10172 | Scoding_system_eol_type, 1, 1, 0, |
10173 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 10174 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 10175 | |
df7492f9 KH |
10176 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
10177 | and CR respectively. | |
66cfb530 | 10178 | |
df7492f9 KH |
10179 | A vector value indicates that a format of end-of-line should be |
10180 | detected automatically. Nth element of the vector is the subsidiary | |
10181 | coding system whose eol-type is N. */) | |
5842a27b | 10182 | (Lisp_Object coding_system) |
6b89e3aa | 10183 | { |
df7492f9 KH |
10184 | Lisp_Object spec, eol_type; |
10185 | int n; | |
6b89e3aa | 10186 | |
df7492f9 KH |
10187 | if (NILP (coding_system)) |
10188 | coding_system = Qno_conversion; | |
10189 | if (! CODING_SYSTEM_P (coding_system)) | |
10190 | return Qnil; | |
10191 | spec = CODING_SYSTEM_SPEC (coding_system); | |
10192 | eol_type = AREF (spec, 2); | |
10193 | if (VECTORP (eol_type)) | |
10194 | return Fcopy_sequence (eol_type); | |
10195 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
10196 | return make_number (n); | |
6b89e3aa KH |
10197 | } |
10198 | ||
4ed46869 KH |
10199 | #endif /* emacs */ |
10200 | ||
10201 | \f | |
1397dc18 | 10202 | /*** 9. Post-amble ***/ |
4ed46869 | 10203 | |
dfcf069d | 10204 | void |
971de7fb | 10205 | init_coding_once (void) |
4ed46869 KH |
10206 | { |
10207 | int i; | |
10208 | ||
df7492f9 KH |
10209 | for (i = 0; i < coding_category_max; i++) |
10210 | { | |
10211 | coding_categories[i].id = -1; | |
10212 | coding_priorities[i] = i; | |
10213 | } | |
4ed46869 KH |
10214 | |
10215 | /* ISO2022 specific initialize routine. */ | |
10216 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 10217 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
10218 | for (i = 0x21; i < 0x7F; i++) |
10219 | iso_code_class[i] = ISO_graphic_plane_0; | |
10220 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 10221 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
10222 | for (i = 0xA1; i < 0xFF; i++) |
10223 | iso_code_class[i] = ISO_graphic_plane_1; | |
10224 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
10225 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
10226 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
10227 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
10228 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
10229 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
10230 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
10231 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
10232 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
10233 | ||
df7492f9 KH |
10234 | for (i = 0; i < 256; i++) |
10235 | { | |
10236 | emacs_mule_bytes[i] = 1; | |
10237 | } | |
7c78e542 KH |
10238 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
10239 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
10240 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
10241 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
10242 | } |
10243 | ||
10244 | #ifdef emacs | |
10245 | ||
dfcf069d | 10246 | void |
971de7fb | 10247 | syms_of_coding (void) |
e0e989f6 | 10248 | { |
df7492f9 | 10249 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
10250 | { |
10251 | Lisp_Object args[2]; | |
10252 | args[0] = QCtest; | |
10253 | args[1] = Qeq; | |
10254 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
10255 | } | |
df7492f9 KH |
10256 | |
10257 | staticpro (&Vsjis_coding_system); | |
10258 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 10259 | |
df7492f9 KH |
10260 | staticpro (&Vbig5_coding_system); |
10261 | Vbig5_coding_system = Qnil; | |
10262 | ||
24a73b0a KH |
10263 | staticpro (&Vcode_conversion_reused_workbuf); |
10264 | Vcode_conversion_reused_workbuf = Qnil; | |
10265 | ||
10266 | staticpro (&Vcode_conversion_workbuf_name); | |
2a0213a6 | 10267 | Vcode_conversion_workbuf_name = build_pure_c_string (" *code-conversion-work*"); |
e0e989f6 | 10268 | |
24a73b0a | 10269 | reused_workbuf_in_use = 0; |
df7492f9 KH |
10270 | |
10271 | DEFSYM (Qcharset, "charset"); | |
10272 | DEFSYM (Qtarget_idx, "target-idx"); | |
10273 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
10274 | Fset (Qcoding_system_history, Qnil); |
10275 | ||
9ce27fde | 10276 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 10277 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 10278 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
10279 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
10280 | ||
df7492f9 | 10281 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 10282 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
10283 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
10284 | ||
df7492f9 | 10285 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 10286 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10287 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
10288 | ||
df7492f9 | 10289 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 10290 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10291 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
10292 | ||
df7492f9 | 10293 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 10294 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
10295 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
10296 | ||
df7492f9 KH |
10297 | DEFSYM (Qcoding_system, "coding-system"); |
10298 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 10299 | |
df7492f9 KH |
10300 | DEFSYM (Qeol_type, "eol-type"); |
10301 | DEFSYM (Qunix, "unix"); | |
10302 | DEFSYM (Qdos, "dos"); | |
4b298d5a | 10303 | DEFSYM (Qmac, "mac"); |
4ed46869 | 10304 | |
df7492f9 KH |
10305 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
10306 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
10307 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
10308 | DEFSYM (Qdefault_char, "default-char"); | |
10309 | DEFSYM (Qundecided, "undecided"); | |
10310 | DEFSYM (Qno_conversion, "no-conversion"); | |
10311 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 10312 | |
df7492f9 | 10313 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 10314 | |
df7492f9 | 10315 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 10316 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 10317 | |
7f590b0c | 10318 | #if defined (WINDOWSNT) || defined (CYGWIN) |
ba116008 DC |
10319 | /* No, not utf-16-le: that one has a BOM. */ |
10320 | DEFSYM (Qutf_16le, "utf-16le"); | |
10321 | #endif | |
10322 | ||
df7492f9 | 10323 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
10324 | DEFSYM (Qbig, "big"); |
10325 | DEFSYM (Qlittle, "little"); | |
27901516 | 10326 | |
df7492f9 KH |
10327 | DEFSYM (Qshift_jis, "shift-jis"); |
10328 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 10329 | |
df7492f9 | 10330 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 10331 | |
df7492f9 | 10332 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 | 10333 | Fput (Qcoding_system_error, Qerror_conditions, |
3438fe21 | 10334 | listn (CONSTYPE_PURE, 2, Qcoding_system_error, Qerror)); |
4ed46869 | 10335 | Fput (Qcoding_system_error, Qerror_message, |
2a0213a6 | 10336 | build_pure_c_string ("Invalid coding system")); |
4ed46869 | 10337 | |
05e6f5dc KH |
10338 | /* Intern this now in case it isn't already done. |
10339 | Setting this variable twice is harmless. | |
10340 | But don't staticpro it here--that is done in alloc.c. */ | |
d67b4f80 | 10341 | Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots"); |
70c22245 | 10342 | |
df7492f9 | 10343 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 10344 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
10345 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
10346 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10347 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10348 | |
df7492f9 | 10349 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10350 | |
df7492f9 | 10351 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10352 | |
01378f49 | 10353 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10354 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10355 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10356 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10357 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10358 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10359 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10360 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10361 | |
df7492f9 KH |
10362 | Vcoding_category_table |
10363 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10364 | staticpro (&Vcoding_category_table); | |
10365 | /* Followings are target of code detection. */ | |
10366 | ASET (Vcoding_category_table, coding_category_iso_7, | |
d67b4f80 | 10367 | intern_c_string ("coding-category-iso-7")); |
df7492f9 | 10368 | ASET (Vcoding_category_table, coding_category_iso_7_tight, |
d67b4f80 | 10369 | intern_c_string ("coding-category-iso-7-tight")); |
df7492f9 | 10370 | ASET (Vcoding_category_table, coding_category_iso_8_1, |
d67b4f80 | 10371 | intern_c_string ("coding-category-iso-8-1")); |
df7492f9 | 10372 | ASET (Vcoding_category_table, coding_category_iso_8_2, |
d67b4f80 | 10373 | intern_c_string ("coding-category-iso-8-2")); |
df7492f9 | 10374 | ASET (Vcoding_category_table, coding_category_iso_7_else, |
d67b4f80 | 10375 | intern_c_string ("coding-category-iso-7-else")); |
df7492f9 | 10376 | ASET (Vcoding_category_table, coding_category_iso_8_else, |
d67b4f80 | 10377 | intern_c_string ("coding-category-iso-8-else")); |
a470d443 | 10378 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
d67b4f80 | 10379 | intern_c_string ("coding-category-utf-8-auto")); |
a470d443 | 10380 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, |
d67b4f80 | 10381 | intern_c_string ("coding-category-utf-8")); |
a470d443 | 10382 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
d67b4f80 | 10383 | intern_c_string ("coding-category-utf-8-sig")); |
df7492f9 | 10384 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
d67b4f80 | 10385 | intern_c_string ("coding-category-utf-16-be")); |
ff563fce | 10386 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
d67b4f80 | 10387 | intern_c_string ("coding-category-utf-16-auto")); |
df7492f9 | 10388 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
d67b4f80 | 10389 | intern_c_string ("coding-category-utf-16-le")); |
df7492f9 | 10390 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, |
d67b4f80 | 10391 | intern_c_string ("coding-category-utf-16-be-nosig")); |
df7492f9 | 10392 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, |
d67b4f80 | 10393 | intern_c_string ("coding-category-utf-16-le-nosig")); |
df7492f9 | 10394 | ASET (Vcoding_category_table, coding_category_charset, |
d67b4f80 | 10395 | intern_c_string ("coding-category-charset")); |
df7492f9 | 10396 | ASET (Vcoding_category_table, coding_category_sjis, |
d67b4f80 | 10397 | intern_c_string ("coding-category-sjis")); |
df7492f9 | 10398 | ASET (Vcoding_category_table, coding_category_big5, |
d67b4f80 | 10399 | intern_c_string ("coding-category-big5")); |
df7492f9 | 10400 | ASET (Vcoding_category_table, coding_category_ccl, |
d67b4f80 | 10401 | intern_c_string ("coding-category-ccl")); |
df7492f9 | 10402 | ASET (Vcoding_category_table, coding_category_emacs_mule, |
d67b4f80 | 10403 | intern_c_string ("coding-category-emacs-mule")); |
df7492f9 KH |
10404 | /* Followings are NOT target of code detection. */ |
10405 | ASET (Vcoding_category_table, coding_category_raw_text, | |
d67b4f80 | 10406 | intern_c_string ("coding-category-raw-text")); |
df7492f9 | 10407 | ASET (Vcoding_category_table, coding_category_undecided, |
d67b4f80 | 10408 | intern_c_string ("coding-category-undecided")); |
ecf488bc | 10409 | |
065e3595 KH |
10410 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
10411 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
10412 | DEFSYM (Qinvalid_source, "invalid-source"); | |
10413 | DEFSYM (Qinterrupted, "interrupted"); | |
10414 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 10415 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10416 | |
4ed46869 KH |
10417 | defsubr (&Scoding_system_p); |
10418 | defsubr (&Sread_coding_system); | |
10419 | defsubr (&Sread_non_nil_coding_system); | |
10420 | defsubr (&Scheck_coding_system); | |
10421 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10422 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10423 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10424 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10425 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10426 | defsubr (&Sdecode_coding_region); |
10427 | defsubr (&Sencode_coding_region); | |
10428 | defsubr (&Sdecode_coding_string); | |
10429 | defsubr (&Sencode_coding_string); | |
10430 | defsubr (&Sdecode_sjis_char); | |
10431 | defsubr (&Sencode_sjis_char); | |
10432 | defsubr (&Sdecode_big5_char); | |
10433 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10434 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10435 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10436 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10437 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10438 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10439 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10440 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10441 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10442 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10443 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10444 | defsubr (&Scoding_system_base); |
10445 | defsubr (&Scoding_system_plist); | |
10446 | defsubr (&Scoding_system_aliases); | |
10447 | defsubr (&Scoding_system_eol_type); | |
10448 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10449 | |
29208e82 | 10450 | DEFVAR_LISP ("coding-system-list", Vcoding_system_list, |
48b0f3ae PJ |
10451 | doc: /* List of coding systems. |
10452 | ||
10453 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10454 | updated by the functions `define-coding-system' and |
48b0f3ae | 10455 | `define-coding-system-alias'. */); |
4608c386 KH |
10456 | Vcoding_system_list = Qnil; |
10457 | ||
29208e82 | 10458 | DEFVAR_LISP ("coding-system-alist", Vcoding_system_alist, |
48b0f3ae PJ |
10459 | doc: /* Alist of coding system names. |
10460 | Each element is one element list of coding system name. | |
446dcd75 | 10461 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10462 | |
10463 | Do not alter the value of this variable manually. This variable should be | |
10464 | updated by the functions `make-coding-system' and | |
10465 | `define-coding-system-alias'. */); | |
4608c386 KH |
10466 | Vcoding_system_alist = Qnil; |
10467 | ||
29208e82 | 10468 | DEFVAR_LISP ("coding-category-list", Vcoding_category_list, |
48b0f3ae PJ |
10469 | doc: /* List of coding-categories (symbols) ordered by priority. |
10470 | ||
10471 | On detecting a coding system, Emacs tries code detection algorithms | |
10472 | associated with each coding-category one by one in this order. When | |
10473 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10474 | system bound to the corresponding coding-category is selected. |
10475 | ||
448e17d6 | 10476 | Don't modify this variable directly, but use `set-coding-system-priority'. */); |
4ed46869 KH |
10477 | { |
10478 | int i; | |
10479 | ||
10480 | Vcoding_category_list = Qnil; | |
df7492f9 | 10481 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10482 | Vcoding_category_list |
28be1ada | 10483 | = Fcons (AREF (Vcoding_category_table, i), |
d46c5b12 | 10484 | Vcoding_category_list); |
4ed46869 KH |
10485 | } |
10486 | ||
29208e82 | 10487 | DEFVAR_LISP ("coding-system-for-read", Vcoding_system_for_read, |
48b0f3ae PJ |
10488 | doc: /* Specify the coding system for read operations. |
10489 | It is useful to bind this variable with `let', but do not set it globally. | |
10490 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10491 | If not, an appropriate element is used from one of the coding system alists. |
10492 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10493 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10494 | Vcoding_system_for_read = Qnil; |
10495 | ||
29208e82 | 10496 | DEFVAR_LISP ("coding-system-for-write", Vcoding_system_for_write, |
48b0f3ae PJ |
10497 | doc: /* Specify the coding system for write operations. |
10498 | Programs bind this variable with `let', but you should not set it globally. | |
10499 | If the value is a coding system, it is used for encoding of output, | |
10500 | when writing it to a file and when sending it to a file or subprocess. | |
10501 | ||
10502 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10503 | is used from one of the coding system alists. |
10504 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10505 | `process-coding-system-alist', and `network-coding-system-alist'. |
10506 | For output to files, if the above procedure does not specify a coding system, | |
10507 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10508 | Vcoding_system_for_write = Qnil; |
10509 | ||
29208e82 | 10510 | DEFVAR_LISP ("last-coding-system-used", Vlast_coding_system_used, |
df7492f9 KH |
10511 | doc: /* |
10512 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10513 | Vlast_coding_system_used = Qnil; |
10514 | ||
29208e82 | 10515 | DEFVAR_LISP ("last-code-conversion-error", Vlast_code_conversion_error, |
065e3595 KH |
10516 | doc: /* |
10517 | Error status of the last code conversion. | |
10518 | ||
10519 | When an error was detected in the last code conversion, this variable | |
10520 | is set to one of the following symbols. | |
10521 | `insufficient-source' | |
10522 | `inconsistent-eol' | |
10523 | `invalid-source' | |
10524 | `interrupted' | |
10525 | `insufficient-memory' | |
10526 | When no error was detected, the value doesn't change. So, to check | |
10527 | the error status of a code conversion by this variable, you must | |
10528 | explicitly set this variable to nil before performing code | |
10529 | conversion. */); | |
10530 | Vlast_code_conversion_error = Qnil; | |
10531 | ||
29208e82 | 10532 | DEFVAR_BOOL ("inhibit-eol-conversion", inhibit_eol_conversion, |
df7492f9 KH |
10533 | doc: /* |
10534 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10535 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10536 | such conversion. */); | |
9ce27fde KH |
10537 | inhibit_eol_conversion = 0; |
10538 | ||
29208e82 | 10539 | DEFVAR_BOOL ("inherit-process-coding-system", inherit_process_coding_system, |
df7492f9 KH |
10540 | doc: /* |
10541 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10542 | Bind it to t if the process output is to be treated as if it were a file |
10543 | read from some filesystem. */); | |
ed29121d EZ |
10544 | inherit_process_coding_system = 0; |
10545 | ||
29208e82 | 10546 | DEFVAR_LISP ("file-coding-system-alist", Vfile_coding_system_alist, |
df7492f9 KH |
10547 | doc: /* |
10548 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10549 | The format is ((PATTERN . VAL) ...), |
10550 | where PATTERN is a regular expression matching a file name, | |
10551 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10552 | If VAL is a coding system, it is used for both decoding and encoding | |
10553 | the file contents. | |
10554 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10555 | and the cdr part is used for encoding. | |
10556 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10557 | or a cons of coding systems which are used as above. The function is |
10558 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10559 | `find-operation-coding-system' was called. If the function can't decide |
10560 | a coding system, it can return `undecided' so that the normal | |
10561 | code-detection is performed. | |
48b0f3ae PJ |
10562 | |
10563 | See also the function `find-operation-coding-system' | |
10564 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10565 | Vfile_coding_system_alist = Qnil; |
10566 | ||
29208e82 | 10567 | DEFVAR_LISP ("process-coding-system-alist", Vprocess_coding_system_alist, |
df7492f9 KH |
10568 | doc: /* |
10569 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
10570 | The format is ((PATTERN . VAL) ...), |
10571 | where PATTERN is a regular expression matching a program name, | |
10572 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10573 | If VAL is a coding system, it is used for both decoding what received | |
10574 | from the program and encoding what sent to the program. | |
10575 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10576 | and the cdr part is used for encoding. | |
10577 | If VAL is a function symbol, the function must return a coding system | |
10578 | or a cons of coding systems which are used as above. | |
10579 | ||
10580 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
10581 | Vprocess_coding_system_alist = Qnil; |
10582 | ||
29208e82 | 10583 | DEFVAR_LISP ("network-coding-system-alist", Vnetwork_coding_system_alist, |
df7492f9 KH |
10584 | doc: /* |
10585 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
10586 | The format is ((PATTERN . VAL) ...), |
10587 | where PATTERN is a regular expression matching a network service name | |
10588 | or is a port number to connect to, | |
10589 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10590 | If VAL is a coding system, it is used for both decoding what received | |
10591 | from the network stream and encoding what sent to the network stream. | |
10592 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10593 | and the cdr part is used for encoding. | |
10594 | If VAL is a function symbol, the function must return a coding system | |
10595 | or a cons of coding systems which are used as above. | |
10596 | ||
10597 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 10598 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 10599 | |
29208e82 | 10600 | DEFVAR_LISP ("locale-coding-system", Vlocale_coding_system, |
75205970 RS |
10601 | doc: /* Coding system to use with system messages. |
10602 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
10603 | Vlocale_coding_system = Qnil; |
10604 | ||
005f0d35 | 10605 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
29208e82 | 10606 | DEFVAR_LISP ("eol-mnemonic-unix", eol_mnemonic_unix, |
df7492f9 KH |
10607 | doc: /* |
10608 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
2a0213a6 | 10609 | eol_mnemonic_unix = build_pure_c_string (":"); |
4ed46869 | 10610 | |
29208e82 | 10611 | DEFVAR_LISP ("eol-mnemonic-dos", eol_mnemonic_dos, |
df7492f9 KH |
10612 | doc: /* |
10613 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
2a0213a6 | 10614 | eol_mnemonic_dos = build_pure_c_string ("\\"); |
4ed46869 | 10615 | |
29208e82 | 10616 | DEFVAR_LISP ("eol-mnemonic-mac", eol_mnemonic_mac, |
df7492f9 KH |
10617 | doc: /* |
10618 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
2a0213a6 | 10619 | eol_mnemonic_mac = build_pure_c_string ("/"); |
4ed46869 | 10620 | |
29208e82 | 10621 | DEFVAR_LISP ("eol-mnemonic-undecided", eol_mnemonic_undecided, |
df7492f9 KH |
10622 | doc: /* |
10623 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
2a0213a6 | 10624 | eol_mnemonic_undecided = build_pure_c_string (":"); |
4ed46869 | 10625 | |
29208e82 | 10626 | DEFVAR_LISP ("enable-character-translation", Venable_character_translation, |
df7492f9 KH |
10627 | doc: /* |
10628 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 10629 | Venable_character_translation = Qt; |
bdd9fb48 | 10630 | |
f967223b | 10631 | DEFVAR_LISP ("standard-translation-table-for-decode", |
29208e82 | 10632 | Vstandard_translation_table_for_decode, |
48b0f3ae | 10633 | doc: /* Table for translating characters while decoding. */); |
f967223b | 10634 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 10635 | |
f967223b | 10636 | DEFVAR_LISP ("standard-translation-table-for-encode", |
29208e82 | 10637 | Vstandard_translation_table_for_encode, |
48b0f3ae | 10638 | doc: /* Table for translating characters while encoding. */); |
f967223b | 10639 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 10640 | |
29208e82 | 10641 | DEFVAR_LISP ("charset-revision-table", Vcharset_revision_table, |
48b0f3ae PJ |
10642 | doc: /* Alist of charsets vs revision numbers. |
10643 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
10644 | designate it with the escape sequence identifying revision (cdr part |
10645 | of the element). */); | |
10646 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
10647 | |
10648 | DEFVAR_LISP ("default-process-coding-system", | |
29208e82 | 10649 | Vdefault_process_coding_system, |
48b0f3ae PJ |
10650 | doc: /* Cons of coding systems used for process I/O by default. |
10651 | The car part is used for decoding a process output, | |
10652 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 10653 | Vdefault_process_coding_system = Qnil; |
c4825358 | 10654 | |
29208e82 | 10655 | DEFVAR_LISP ("latin-extra-code-table", Vlatin_extra_code_table, |
df7492f9 KH |
10656 | doc: /* |
10657 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
10658 | This is a vector of length 256. |
10659 | If Nth element is non-nil, the existence of code N in a file | |
10660 | \(or output of subprocess) doesn't prevent it to be detected as | |
10661 | a coding system of ISO 2022 variant which has a flag | |
10662 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
10663 | or reading output of a subprocess. | |
446dcd75 | 10664 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 10665 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
10666 | |
10667 | DEFVAR_LISP ("select-safe-coding-system-function", | |
29208e82 | 10668 | Vselect_safe_coding_system_function, |
df7492f9 KH |
10669 | doc: /* |
10670 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
10671 | |
10672 | If set, this function is called to force a user to select a proper | |
10673 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
10674 | coding system used in each operation can't encode the text. The |
10675 | function should take care that the buffer is not modified while | |
10676 | the coding system is being selected. | |
48b0f3ae PJ |
10677 | |
10678 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
10679 | Vselect_safe_coding_system_function = Qnil; |
10680 | ||
5d5bf4d8 | 10681 | DEFVAR_BOOL ("coding-system-require-warning", |
29208e82 | 10682 | coding_system_require_warning, |
5d5bf4d8 | 10683 | doc: /* Internal use only. |
6b89e3aa KH |
10684 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
10685 | called even if `coding-system-for-write' is non-nil. The command | |
10686 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
10687 | coding_system_require_warning = 0; |
10688 | ||
10689 | ||
22ab2303 | 10690 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
29208e82 | 10691 | inhibit_iso_escape_detection, |
df7492f9 | 10692 | doc: /* |
97b1b294 | 10693 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 10694 | |
97b1b294 EZ |
10695 | When Emacs reads text, it tries to detect how the text is encoded. |
10696 | This code detection is sensitive to escape sequences. If Emacs sees | |
10697 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
10698 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
10699 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
10700 | |
10701 | However, there may be a case that you want to read escape sequences in | |
10702 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
10703 | Then the code detection will ignore any escape sequences, and no text is |
10704 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
10705 | escape sequences become visible in a buffer. |
10706 | ||
10707 | The default value is nil, and it is strongly recommended not to change | |
10708 | it. That is because many Emacs Lisp source files that contain | |
10709 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
10710 | in Emacs's distribution, and they won't be decoded correctly on | |
10711 | reading if you suppress escape sequence detection. | |
10712 | ||
10713 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 10714 | to explicitly specify some coding system that doesn't use ISO-2022 |
48b0f3ae | 10715 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 10716 | inhibit_iso_escape_detection = 0; |
002fdb44 | 10717 | |
97b1b294 | 10718 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
29208e82 | 10719 | inhibit_null_byte_detection, |
97b1b294 EZ |
10720 | doc: /* If non-nil, Emacs ignores null bytes on code detection. |
10721 | By default, Emacs treats it as binary data, and does not attempt to | |
10722 | decode it. The effect is as if you specified `no-conversion' for | |
10723 | reading that text. | |
10724 | ||
10725 | Set this to non-nil when a regular text happens to include null bytes. | |
10726 | Examples are Index nodes of Info files and null-byte delimited output | |
10727 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
10728 | decode text as usual. */); | |
10729 | inhibit_null_byte_detection = 0; | |
10730 | ||
29208e82 | 10731 | DEFVAR_LISP ("translation-table-for-input", Vtranslation_table_for_input, |
15c8f9d1 | 10732 | doc: /* Char table for translating self-inserting characters. |
446dcd75 | 10733 | This is applied to the result of input methods, not their input. |
8434d0b8 EZ |
10734 | See also `keyboard-translate-table'. |
10735 | ||
10736 | Use of this variable for character code unification was rendered | |
10737 | obsolete in Emacs 23.1 and later, since Unicode is now the basis of | |
10738 | internal character representation. */); | |
002fdb44 | 10739 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 10740 | |
2c78b7e1 KH |
10741 | { |
10742 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 10743 | Lisp_Object plist[16]; |
2c78b7e1 KH |
10744 | int i; |
10745 | ||
10746 | for (i = 0; i < coding_arg_max; i++) | |
10747 | args[i] = Qnil; | |
10748 | ||
d67b4f80 | 10749 | plist[0] = intern_c_string (":name"); |
2c78b7e1 | 10750 | plist[1] = args[coding_arg_name] = Qno_conversion; |
d67b4f80 | 10751 | plist[2] = intern_c_string (":mnemonic"); |
2c78b7e1 | 10752 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); |
d67b4f80 | 10753 | plist[4] = intern_c_string (":coding-type"); |
2c78b7e1 | 10754 | plist[5] = args[coding_arg_coding_type] = Qraw_text; |
d67b4f80 | 10755 | plist[6] = intern_c_string (":ascii-compatible-p"); |
2c78b7e1 | 10756 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; |
d67b4f80 | 10757 | plist[8] = intern_c_string (":default-char"); |
2c78b7e1 | 10758 | plist[9] = args[coding_arg_default_char] = make_number (0); |
d67b4f80 | 10759 | plist[10] = intern_c_string (":for-unibyte"); |
8f924df7 | 10760 | plist[11] = args[coding_arg_for_unibyte] = Qt; |
d67b4f80 | 10761 | plist[12] = intern_c_string (":docstring"); |
2a0213a6 | 10762 | plist[13] = build_pure_c_string ("Do no conversion.\n\ |
2c78b7e1 KH |
10763 | \n\ |
10764 | When you visit a file with this coding, the file is read into a\n\ | |
10765 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
10766 | character."); | |
d67b4f80 | 10767 | plist[14] = intern_c_string (":eol-type"); |
8f924df7 KH |
10768 | plist[15] = args[coding_arg_eol_type] = Qunix; |
10769 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 10770 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
10771 | |
10772 | plist[1] = args[coding_arg_name] = Qundecided; | |
10773 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
10774 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
10775 | /* This is already set. | |
35befdaa | 10776 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
d67b4f80 | 10777 | plist[8] = intern_c_string (":charset-list"); |
ae6f73fa KH |
10778 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); |
10779 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
2a0213a6 | 10780 | plist[13] = build_pure_c_string ("No conversion on encoding, automatic conversion on decoding."); |
ae6f73fa KH |
10781 | plist[15] = args[coding_arg_eol_type] = Qnil; |
10782 | args[coding_arg_plist] = Flist (16, plist); | |
10783 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
10784 | } |
10785 | ||
2c78b7e1 | 10786 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
10787 | |
10788 | { | |
10789 | int i; | |
10790 | ||
10791 | for (i = 0; i < coding_category_max; i++) | |
10792 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
10793 | } | |
1a4990fb | 10794 | #if defined (DOS_NT) |
fcbcfb64 KH |
10795 | system_eol_type = Qdos; |
10796 | #else | |
10797 | system_eol_type = Qunix; | |
10798 | #endif | |
10799 | staticpro (&system_eol_type); | |
4ed46869 KH |
10800 | } |
10801 | ||
68c45bf0 | 10802 | char * |
971de7fb | 10803 | emacs_strerror (int error_number) |
68c45bf0 PE |
10804 | { |
10805 | char *str; | |
10806 | ||
ca9c0567 | 10807 | synchronize_system_messages_locale (); |
68c45bf0 PE |
10808 | str = strerror (error_number); |
10809 | ||
10810 | if (! NILP (Vlocale_coding_system)) | |
10811 | { | |
10812 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
10813 | Vlocale_coding_system, | |
10814 | 0); | |
51b59d79 | 10815 | str = SSDATA (dec); |
68c45bf0 PE |
10816 | } |
10817 | ||
10818 | return str; | |
10819 | } | |
10820 | ||
4ed46869 | 10821 | #endif /* emacs */ |