Commit | Line | Data |
---|---|---|
9542cb1f | 1 | /* Coding system handler (conversion, detection, etc). |
acaf905b | 2 | Copyright (C) 2001-2012 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; | |
1965cb73 | 304 | Lisp_Object Qunix, Qdos; |
4ed46869 | 305 | Lisp_Object Qbuffer_file_coding_system; |
955cbe7b PE |
306 | static Lisp_Object Qpost_read_conversion, Qpre_write_conversion; |
307 | static Lisp_Object Qdefault_char; | |
27901516 | 308 | Lisp_Object Qno_conversion, Qundecided; |
955cbe7b PE |
309 | Lisp_Object Qcharset, Qutf_8; |
310 | static Lisp_Object Qiso_2022; | |
311 | static Lisp_Object Qutf_16, Qshift_jis, Qbig5; | |
312 | static Lisp_Object Qbig, Qlittle; | |
313 | static Lisp_Object Qcoding_system_history; | |
314 | static Lisp_Object Qvalid_codes; | |
315 | static Lisp_Object QCcategory, QCmnemonic, QCdefault_char; | |
316 | static Lisp_Object QCdecode_translation_table, QCencode_translation_table; | |
317 | static Lisp_Object QCpost_read_conversion, QCpre_write_conversion; | |
318 | static Lisp_Object QCascii_compatible_p; | |
4ed46869 | 319 | |
387f6ba5 | 320 | Lisp_Object Qcall_process, Qcall_process_region; |
4ed46869 | 321 | Lisp_Object Qstart_process, Qopen_network_stream; |
955cbe7b | 322 | static Lisp_Object Qtarget_idx; |
4ed46869 | 323 | |
955cbe7b PE |
324 | static Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source; |
325 | static Lisp_Object Qinterrupted, Qinsufficient_memory; | |
065e3595 | 326 | |
44e8490d KH |
327 | /* If a symbol has this property, evaluate the value to define the |
328 | symbol as a coding system. */ | |
329 | static Lisp_Object Qcoding_system_define_form; | |
330 | ||
fcbcfb64 KH |
331 | /* Format of end-of-line decided by system. This is Qunix on |
332 | Unix and Mac, Qdos on DOS/Windows. | |
333 | This has an effect only for external encoding (i.e. for output to | |
334 | file and process), not for in-buffer or Lisp string encoding. */ | |
335 | static Lisp_Object system_eol_type; | |
336 | ||
4ed46869 KH |
337 | #ifdef emacs |
338 | ||
4608c386 | 339 | Lisp_Object Qcoding_system_p, Qcoding_system_error; |
4ed46869 | 340 | |
d46c5b12 KH |
341 | /* Coding system emacs-mule and raw-text are for converting only |
342 | end-of-line format. */ | |
343 | Lisp_Object Qemacs_mule, Qraw_text; | |
8f924df7 | 344 | Lisp_Object Qutf_8_emacs; |
ecf488bc | 345 | |
4ed46869 KH |
346 | /* Coding-systems are handed between Emacs Lisp programs and C internal |
347 | routines by the following three variables. */ | |
c4825358 KH |
348 | /* Coding system to be used to encode text for terminal display when |
349 | terminal coding system is nil. */ | |
350 | struct coding_system safe_terminal_coding; | |
351 | ||
4ed46869 KH |
352 | #endif /* emacs */ |
353 | ||
f967223b KH |
354 | Lisp_Object Qtranslation_table; |
355 | Lisp_Object Qtranslation_table_id; | |
955cbe7b PE |
356 | static Lisp_Object Qtranslation_table_for_decode; |
357 | static Lisp_Object Qtranslation_table_for_encode; | |
4ed46869 | 358 | |
df7492f9 | 359 | /* Two special coding systems. */ |
74ab6df5 PE |
360 | static Lisp_Object Vsjis_coding_system; |
361 | static Lisp_Object Vbig5_coding_system; | |
df7492f9 | 362 | |
df7492f9 KH |
363 | /* ISO2022 section */ |
364 | ||
365 | #define CODING_ISO_INITIAL(coding, reg) \ | |
366 | (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id), \ | |
367 | coding_attr_iso_initial), \ | |
368 | reg))) | |
369 | ||
370 | ||
1b3b981b AS |
371 | #define CODING_ISO_REQUEST(coding, charset_id) \ |
372 | (((charset_id) <= (coding)->max_charset_id \ | |
373 | ? ((coding)->safe_charsets[charset_id] != 255 \ | |
374 | ? (coding)->safe_charsets[charset_id] \ | |
375 | : -1) \ | |
df7492f9 KH |
376 | : -1)) |
377 | ||
378 | ||
379 | #define CODING_ISO_FLAGS(coding) \ | |
380 | ((coding)->spec.iso_2022.flags) | |
381 | #define CODING_ISO_DESIGNATION(coding, reg) \ | |
382 | ((coding)->spec.iso_2022.current_designation[reg]) | |
383 | #define CODING_ISO_INVOCATION(coding, plane) \ | |
384 | ((coding)->spec.iso_2022.current_invocation[plane]) | |
385 | #define CODING_ISO_SINGLE_SHIFTING(coding) \ | |
386 | ((coding)->spec.iso_2022.single_shifting) | |
387 | #define CODING_ISO_BOL(coding) \ | |
388 | ((coding)->spec.iso_2022.bol) | |
389 | #define CODING_ISO_INVOKED_CHARSET(coding, plane) \ | |
390 | CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane))) | |
e951386e KH |
391 | #define CODING_ISO_CMP_STATUS(coding) \ |
392 | (&(coding)->spec.iso_2022.cmp_status) | |
393 | #define CODING_ISO_EXTSEGMENT_LEN(coding) \ | |
394 | ((coding)->spec.iso_2022.ctext_extended_segment_len) | |
395 | #define CODING_ISO_EMBEDDED_UTF_8(coding) \ | |
396 | ((coding)->spec.iso_2022.embedded_utf_8) | |
df7492f9 KH |
397 | |
398 | /* Control characters of ISO2022. */ | |
399 | /* code */ /* function */ | |
df7492f9 KH |
400 | #define ISO_CODE_SO 0x0E /* shift-out */ |
401 | #define ISO_CODE_SI 0x0F /* shift-in */ | |
402 | #define ISO_CODE_SS2_7 0x19 /* single-shift-2 for 7-bit code */ | |
403 | #define ISO_CODE_ESC 0x1B /* escape */ | |
404 | #define ISO_CODE_SS2 0x8E /* single-shift-2 */ | |
405 | #define ISO_CODE_SS3 0x8F /* single-shift-3 */ | |
406 | #define ISO_CODE_CSI 0x9B /* control-sequence-introducer */ | |
407 | ||
408 | /* All code (1-byte) of ISO2022 is classified into one of the | |
409 | followings. */ | |
410 | enum iso_code_class_type | |
411 | { | |
412 | ISO_control_0, /* Control codes in the range | |
413 | 0x00..0x1F and 0x7F, except for the | |
414 | following 5 codes. */ | |
df7492f9 KH |
415 | ISO_shift_out, /* ISO_CODE_SO (0x0E) */ |
416 | ISO_shift_in, /* ISO_CODE_SI (0x0F) */ | |
417 | ISO_single_shift_2_7, /* ISO_CODE_SS2_7 (0x19) */ | |
418 | ISO_escape, /* ISO_CODE_SO (0x1B) */ | |
419 | ISO_control_1, /* Control codes in the range | |
420 | 0x80..0x9F, except for the | |
421 | following 3 codes. */ | |
422 | ISO_single_shift_2, /* ISO_CODE_SS2 (0x8E) */ | |
423 | ISO_single_shift_3, /* ISO_CODE_SS3 (0x8F) */ | |
424 | ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */ | |
425 | ISO_0x20_or_0x7F, /* Codes of the values 0x20 or 0x7F. */ | |
426 | ISO_graphic_plane_0, /* Graphic codes in the range 0x21..0x7E. */ | |
427 | ISO_0xA0_or_0xFF, /* Codes of the values 0xA0 or 0xFF. */ | |
428 | ISO_graphic_plane_1 /* Graphic codes in the range 0xA1..0xFE. */ | |
429 | }; | |
05e6f5dc | 430 | |
df7492f9 KH |
431 | /** The macros CODING_ISO_FLAG_XXX defines a flag bit of the |
432 | `iso-flags' attribute of an iso2022 coding system. */ | |
05e6f5dc | 433 | |
df7492f9 KH |
434 | /* If set, produce long-form designation sequence (e.g. ESC $ ( A) |
435 | instead of the correct short-form sequence (e.g. ESC $ A). */ | |
436 | #define CODING_ISO_FLAG_LONG_FORM 0x0001 | |
93dec019 | 437 | |
df7492f9 KH |
438 | /* If set, reset graphic planes and registers at end-of-line to the |
439 | initial state. */ | |
440 | #define CODING_ISO_FLAG_RESET_AT_EOL 0x0002 | |
05e6f5dc | 441 | |
df7492f9 KH |
442 | /* If set, reset graphic planes and registers before any control |
443 | characters to the initial state. */ | |
444 | #define CODING_ISO_FLAG_RESET_AT_CNTL 0x0004 | |
05e6f5dc | 445 | |
df7492f9 KH |
446 | /* If set, encode by 7-bit environment. */ |
447 | #define CODING_ISO_FLAG_SEVEN_BITS 0x0008 | |
4ed46869 | 448 | |
df7492f9 KH |
449 | /* If set, use locking-shift function. */ |
450 | #define CODING_ISO_FLAG_LOCKING_SHIFT 0x0010 | |
b73bfc1c | 451 | |
df7492f9 KH |
452 | /* If set, use single-shift function. Overwrite |
453 | CODING_ISO_FLAG_LOCKING_SHIFT. */ | |
454 | #define CODING_ISO_FLAG_SINGLE_SHIFT 0x0020 | |
b73bfc1c | 455 | |
df7492f9 KH |
456 | /* If set, use designation escape sequence. */ |
457 | #define CODING_ISO_FLAG_DESIGNATION 0x0040 | |
b73bfc1c | 458 | |
df7492f9 KH |
459 | /* If set, produce revision number sequence. */ |
460 | #define CODING_ISO_FLAG_REVISION 0x0080 | |
b73bfc1c | 461 | |
df7492f9 KH |
462 | /* If set, produce ISO6429's direction specifying sequence. */ |
463 | #define CODING_ISO_FLAG_DIRECTION 0x0100 | |
f4dee582 | 464 | |
df7492f9 KH |
465 | /* If set, assume designation states are reset at beginning of line on |
466 | output. */ | |
467 | #define CODING_ISO_FLAG_INIT_AT_BOL 0x0200 | |
4ed46869 | 468 | |
df7492f9 KH |
469 | /* If set, designation sequence should be placed at beginning of line |
470 | on output. */ | |
471 | #define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400 | |
aa72b389 | 472 | |
ad1746f5 | 473 | /* If set, do not encode unsafe characters on output. */ |
df7492f9 | 474 | #define CODING_ISO_FLAG_SAFE 0x0800 |
aa72b389 | 475 | |
df7492f9 KH |
476 | /* If set, extra latin codes (128..159) are accepted as a valid code |
477 | on input. */ | |
478 | #define CODING_ISO_FLAG_LATIN_EXTRA 0x1000 | |
aa72b389 | 479 | |
df7492f9 | 480 | #define CODING_ISO_FLAG_COMPOSITION 0x2000 |
aa72b389 | 481 | |
5f58e762 | 482 | /* #define CODING_ISO_FLAG_EUC_TW_SHIFT 0x4000 */ |
aa72b389 | 483 | |
bf16eb23 | 484 | #define CODING_ISO_FLAG_USE_ROMAN 0x8000 |
aa72b389 | 485 | |
bf16eb23 | 486 | #define CODING_ISO_FLAG_USE_OLDJIS 0x10000 |
aa72b389 | 487 | |
bf16eb23 | 488 | #define CODING_ISO_FLAG_FULL_SUPPORT 0x100000 |
aa72b389 | 489 | |
df7492f9 KH |
490 | /* A character to be produced on output if encoding of the original |
491 | character is prohibited by CODING_ISO_FLAG_SAFE. */ | |
492 | #define CODING_INHIBIT_CHARACTER_SUBSTITUTION '?' | |
aa72b389 | 493 | |
a470d443 KH |
494 | /* UTF-8 section */ |
495 | #define CODING_UTF_8_BOM(coding) \ | |
496 | ((coding)->spec.utf_8_bom) | |
4ed46869 | 497 | |
df7492f9 KH |
498 | /* UTF-16 section */ |
499 | #define CODING_UTF_16_BOM(coding) \ | |
500 | ((coding)->spec.utf_16.bom) | |
4ed46869 | 501 | |
df7492f9 KH |
502 | #define CODING_UTF_16_ENDIAN(coding) \ |
503 | ((coding)->spec.utf_16.endian) | |
4ed46869 | 504 | |
df7492f9 KH |
505 | #define CODING_UTF_16_SURROGATE(coding) \ |
506 | ((coding)->spec.utf_16.surrogate) | |
4ed46869 | 507 | |
4ed46869 | 508 | |
df7492f9 KH |
509 | /* CCL section */ |
510 | #define CODING_CCL_DECODER(coding) \ | |
511 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder) | |
512 | #define CODING_CCL_ENCODER(coding) \ | |
513 | AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder) | |
514 | #define CODING_CCL_VALIDS(coding) \ | |
8f924df7 | 515 | (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids))) |
4ed46869 | 516 | |
5a936b46 | 517 | /* Index for each coding category in `coding_categories' */ |
4ed46869 | 518 | |
df7492f9 KH |
519 | enum coding_category |
520 | { | |
521 | coding_category_iso_7, | |
522 | coding_category_iso_7_tight, | |
523 | coding_category_iso_8_1, | |
524 | coding_category_iso_8_2, | |
525 | coding_category_iso_7_else, | |
526 | coding_category_iso_8_else, | |
a470d443 KH |
527 | coding_category_utf_8_auto, |
528 | coding_category_utf_8_nosig, | |
529 | coding_category_utf_8_sig, | |
df7492f9 KH |
530 | coding_category_utf_16_auto, |
531 | coding_category_utf_16_be, | |
532 | coding_category_utf_16_le, | |
533 | coding_category_utf_16_be_nosig, | |
534 | coding_category_utf_16_le_nosig, | |
535 | coding_category_charset, | |
536 | coding_category_sjis, | |
537 | coding_category_big5, | |
538 | coding_category_ccl, | |
539 | coding_category_emacs_mule, | |
540 | /* All above are targets of code detection. */ | |
541 | coding_category_raw_text, | |
542 | coding_category_undecided, | |
543 | coding_category_max | |
544 | }; | |
545 | ||
546 | /* Definitions of flag bits used in detect_coding_XXXX. */ | |
547 | #define CATEGORY_MASK_ISO_7 (1 << coding_category_iso_7) | |
548 | #define CATEGORY_MASK_ISO_7_TIGHT (1 << coding_category_iso_7_tight) | |
549 | #define CATEGORY_MASK_ISO_8_1 (1 << coding_category_iso_8_1) | |
550 | #define CATEGORY_MASK_ISO_8_2 (1 << coding_category_iso_8_2) | |
551 | #define CATEGORY_MASK_ISO_7_ELSE (1 << coding_category_iso_7_else) | |
552 | #define CATEGORY_MASK_ISO_8_ELSE (1 << coding_category_iso_8_else) | |
a470d443 KH |
553 | #define CATEGORY_MASK_UTF_8_AUTO (1 << coding_category_utf_8_auto) |
554 | #define CATEGORY_MASK_UTF_8_NOSIG (1 << coding_category_utf_8_nosig) | |
555 | #define CATEGORY_MASK_UTF_8_SIG (1 << coding_category_utf_8_sig) | |
b49a1807 | 556 | #define CATEGORY_MASK_UTF_16_AUTO (1 << coding_category_utf_16_auto) |
df7492f9 KH |
557 | #define CATEGORY_MASK_UTF_16_BE (1 << coding_category_utf_16_be) |
558 | #define CATEGORY_MASK_UTF_16_LE (1 << coding_category_utf_16_le) | |
559 | #define CATEGORY_MASK_UTF_16_BE_NOSIG (1 << coding_category_utf_16_be_nosig) | |
560 | #define CATEGORY_MASK_UTF_16_LE_NOSIG (1 << coding_category_utf_16_le_nosig) | |
561 | #define CATEGORY_MASK_CHARSET (1 << coding_category_charset) | |
562 | #define CATEGORY_MASK_SJIS (1 << coding_category_sjis) | |
563 | #define CATEGORY_MASK_BIG5 (1 << coding_category_big5) | |
564 | #define CATEGORY_MASK_CCL (1 << coding_category_ccl) | |
565 | #define CATEGORY_MASK_EMACS_MULE (1 << coding_category_emacs_mule) | |
ff0dacd7 | 566 | #define CATEGORY_MASK_RAW_TEXT (1 << coding_category_raw_text) |
df7492f9 KH |
567 | |
568 | /* This value is returned if detect_coding_mask () find nothing other | |
569 | than ASCII characters. */ | |
570 | #define CATEGORY_MASK_ANY \ | |
571 | (CATEGORY_MASK_ISO_7 \ | |
572 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
573 | | CATEGORY_MASK_ISO_8_1 \ | |
574 | | CATEGORY_MASK_ISO_8_2 \ | |
575 | | CATEGORY_MASK_ISO_7_ELSE \ | |
576 | | CATEGORY_MASK_ISO_8_ELSE \ | |
a470d443 KH |
577 | | CATEGORY_MASK_UTF_8_AUTO \ |
578 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
579 | | CATEGORY_MASK_UTF_8_SIG \ | |
2f3cbb32 | 580 | | CATEGORY_MASK_UTF_16_AUTO \ |
df7492f9 KH |
581 | | CATEGORY_MASK_UTF_16_BE \ |
582 | | CATEGORY_MASK_UTF_16_LE \ | |
583 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
584 | | CATEGORY_MASK_UTF_16_LE_NOSIG \ | |
585 | | CATEGORY_MASK_CHARSET \ | |
586 | | CATEGORY_MASK_SJIS \ | |
587 | | CATEGORY_MASK_BIG5 \ | |
588 | | CATEGORY_MASK_CCL \ | |
589 | | CATEGORY_MASK_EMACS_MULE) | |
590 | ||
591 | ||
592 | #define CATEGORY_MASK_ISO_7BIT \ | |
593 | (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT) | |
594 | ||
595 | #define CATEGORY_MASK_ISO_8BIT \ | |
596 | (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2) | |
597 | ||
598 | #define CATEGORY_MASK_ISO_ELSE \ | |
599 | (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE) | |
600 | ||
601 | #define CATEGORY_MASK_ISO_ESCAPE \ | |
602 | (CATEGORY_MASK_ISO_7 \ | |
603 | | CATEGORY_MASK_ISO_7_TIGHT \ | |
604 | | CATEGORY_MASK_ISO_7_ELSE \ | |
605 | | CATEGORY_MASK_ISO_8_ELSE) | |
606 | ||
607 | #define CATEGORY_MASK_ISO \ | |
608 | ( CATEGORY_MASK_ISO_7BIT \ | |
609 | | CATEGORY_MASK_ISO_8BIT \ | |
610 | | CATEGORY_MASK_ISO_ELSE) | |
611 | ||
612 | #define CATEGORY_MASK_UTF_16 \ | |
2f3cbb32 KH |
613 | (CATEGORY_MASK_UTF_16_AUTO \ |
614 | | CATEGORY_MASK_UTF_16_BE \ | |
df7492f9 KH |
615 | | CATEGORY_MASK_UTF_16_LE \ |
616 | | CATEGORY_MASK_UTF_16_BE_NOSIG \ | |
617 | | CATEGORY_MASK_UTF_16_LE_NOSIG) | |
618 | ||
a470d443 KH |
619 | #define CATEGORY_MASK_UTF_8 \ |
620 | (CATEGORY_MASK_UTF_8_AUTO \ | |
621 | | CATEGORY_MASK_UTF_8_NOSIG \ | |
622 | | CATEGORY_MASK_UTF_8_SIG) | |
df7492f9 | 623 | |
df7492f9 | 624 | /* Table of coding categories (Lisp symbols). This variable is for |
ad1746f5 | 625 | internal use only. */ |
df7492f9 KH |
626 | static Lisp_Object Vcoding_category_table; |
627 | ||
628 | /* Table of coding-categories ordered by priority. */ | |
629 | static enum coding_category coding_priorities[coding_category_max]; | |
630 | ||
631 | /* Nth element is a coding context for the coding system bound to the | |
632 | Nth coding category. */ | |
633 | static struct coding_system coding_categories[coding_category_max]; | |
634 | ||
df7492f9 KH |
635 | /*** Commonly used macros and functions ***/ |
636 | ||
637 | #ifndef min | |
638 | #define min(a, b) ((a) < (b) ? (a) : (b)) | |
639 | #endif | |
640 | #ifndef max | |
641 | #define max(a, b) ((a) > (b) ? (a) : (b)) | |
642 | #endif | |
4ed46869 | 643 | |
24a73b0a KH |
644 | #define CODING_GET_INFO(coding, attrs, charset_list) \ |
645 | do { \ | |
646 | (attrs) = CODING_ID_ATTRS ((coding)->id); \ | |
647 | (charset_list) = CODING_ATTR_CHARSET_LIST (attrs); \ | |
df7492f9 | 648 | } while (0) |
4ed46869 | 649 | |
4ed46869 | 650 | |
df7492f9 KH |
651 | /* Safely get one byte from the source text pointed by SRC which ends |
652 | at SRC_END, and set C to that byte. If there are not enough bytes | |
f10fe38f PE |
653 | in the source, it jumps to 'no_more_source'. If MULTIBYTEP, |
654 | and a multibyte character is found at SRC, set C to the | |
065e3595 KH |
655 | negative value of the character code. The caller should declare |
656 | and set these variables appropriately in advance: | |
657 | src, src_end, multibytep */ | |
aa72b389 | 658 | |
065e3595 KH |
659 | #define ONE_MORE_BYTE(c) \ |
660 | do { \ | |
661 | if (src == src_end) \ | |
662 | { \ | |
663 | if (src_base < src) \ | |
664 | record_conversion_result \ | |
665 | (coding, CODING_RESULT_INSUFFICIENT_SRC); \ | |
666 | goto no_more_source; \ | |
667 | } \ | |
668 | c = *src++; \ | |
669 | if (multibytep && (c & 0x80)) \ | |
670 | { \ | |
671 | if ((c & 0xFE) == 0xC0) \ | |
672 | c = ((c & 1) << 6) | *src++; \ | |
673 | else \ | |
674 | { \ | |
35befdaa KH |
675 | src--; \ |
676 | c = - string_char (src, &src, NULL); \ | |
065e3595 KH |
677 | record_conversion_result \ |
678 | (coding, CODING_RESULT_INVALID_SRC); \ | |
679 | } \ | |
680 | } \ | |
681 | consumed_chars++; \ | |
aa72b389 KH |
682 | } while (0) |
683 | ||
f56a4450 | 684 | /* Safely get two bytes from the source text pointed by SRC which ends |
220eeac9 KH |
685 | at SRC_END, and set C1 and C2 to those bytes while skipping the |
686 | heading multibyte characters. If there are not enough bytes in the | |
f10fe38f | 687 | source, it jumps to 'no_more_source'. If MULTIBYTEP and |
220eeac9 KH |
688 | a multibyte character is found for C2, set C2 to the negative value |
689 | of the character code. The caller should declare and set these | |
690 | variables appropriately in advance: | |
f56a4450 KH |
691 | src, src_end, multibytep |
692 | It is intended that this macro is used in detect_coding_utf_16. */ | |
693 | ||
220eeac9 KH |
694 | #define TWO_MORE_BYTES(c1, c2) \ |
695 | do { \ | |
696 | do { \ | |
697 | if (src == src_end) \ | |
698 | goto no_more_source; \ | |
699 | c1 = *src++; \ | |
700 | if (multibytep && (c1 & 0x80)) \ | |
701 | { \ | |
702 | if ((c1 & 0xFE) == 0xC0) \ | |
703 | c1 = ((c1 & 1) << 6) | *src++; \ | |
704 | else \ | |
705 | { \ | |
706 | src += BYTES_BY_CHAR_HEAD (c1) - 1; \ | |
707 | c1 = -1; \ | |
708 | } \ | |
709 | } \ | |
710 | } while (c1 < 0); \ | |
711 | if (src == src_end) \ | |
712 | goto no_more_source; \ | |
713 | c2 = *src++; \ | |
714 | if (multibytep && (c2 & 0x80)) \ | |
715 | { \ | |
716 | if ((c2 & 0xFE) == 0xC0) \ | |
717 | c2 = ((c2 & 1) << 6) | *src++; \ | |
718 | else \ | |
719 | c2 = -1; \ | |
720 | } \ | |
f56a4450 KH |
721 | } while (0) |
722 | ||
aa72b389 | 723 | |
df7492f9 KH |
724 | /* Store a byte C in the place pointed by DST and increment DST to the |
725 | next free point, and increment PRODUCED_CHARS. The caller should | |
726 | assure that C is 0..127, and declare and set the variable `dst' | |
727 | appropriately in advance. | |
728 | */ | |
aa72b389 KH |
729 | |
730 | ||
df7492f9 KH |
731 | #define EMIT_ONE_ASCII_BYTE(c) \ |
732 | do { \ | |
733 | produced_chars++; \ | |
734 | *dst++ = (c); \ | |
b6871cc7 | 735 | } while (0) |
aa72b389 KH |
736 | |
737 | ||
ad1746f5 | 738 | /* Like EMIT_ONE_ASCII_BYTE but store two bytes; C1 and C2. */ |
aa72b389 | 739 | |
df7492f9 KH |
740 | #define EMIT_TWO_ASCII_BYTES(c1, c2) \ |
741 | do { \ | |
742 | produced_chars += 2; \ | |
743 | *dst++ = (c1), *dst++ = (c2); \ | |
744 | } while (0) | |
aa72b389 KH |
745 | |
746 | ||
df7492f9 | 747 | /* Store a byte C in the place pointed by DST and increment DST to the |
f10fe38f PE |
748 | next free point, and increment PRODUCED_CHARS. If MULTIBYTEP, |
749 | store in an appropriate multibyte form. The caller should | |
df7492f9 KH |
750 | declare and set the variables `dst' and `multibytep' appropriately |
751 | in advance. */ | |
752 | ||
753 | #define EMIT_ONE_BYTE(c) \ | |
754 | do { \ | |
755 | produced_chars++; \ | |
756 | if (multibytep) \ | |
757 | { \ | |
b25d760e | 758 | unsigned ch = (c); \ |
df7492f9 KH |
759 | if (ch >= 0x80) \ |
760 | ch = BYTE8_TO_CHAR (ch); \ | |
761 | CHAR_STRING_ADVANCE (ch, dst); \ | |
762 | } \ | |
763 | else \ | |
764 | *dst++ = (c); \ | |
aa72b389 | 765 | } while (0) |
aa72b389 | 766 | |
aa72b389 | 767 | |
df7492f9 | 768 | /* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2. */ |
aa72b389 | 769 | |
e19c3639 KH |
770 | #define EMIT_TWO_BYTES(c1, c2) \ |
771 | do { \ | |
772 | produced_chars += 2; \ | |
773 | if (multibytep) \ | |
774 | { \ | |
b25d760e | 775 | unsigned ch; \ |
e19c3639 KH |
776 | \ |
777 | ch = (c1); \ | |
778 | if (ch >= 0x80) \ | |
779 | ch = BYTE8_TO_CHAR (ch); \ | |
780 | CHAR_STRING_ADVANCE (ch, dst); \ | |
781 | ch = (c2); \ | |
782 | if (ch >= 0x80) \ | |
783 | ch = BYTE8_TO_CHAR (ch); \ | |
784 | CHAR_STRING_ADVANCE (ch, dst); \ | |
785 | } \ | |
786 | else \ | |
787 | { \ | |
788 | *dst++ = (c1); \ | |
789 | *dst++ = (c2); \ | |
790 | } \ | |
aa72b389 KH |
791 | } while (0) |
792 | ||
793 | ||
df7492f9 KH |
794 | #define EMIT_THREE_BYTES(c1, c2, c3) \ |
795 | do { \ | |
796 | EMIT_ONE_BYTE (c1); \ | |
797 | EMIT_TWO_BYTES (c2, c3); \ | |
798 | } while (0) | |
aa72b389 | 799 | |
aa72b389 | 800 | |
df7492f9 KH |
801 | #define EMIT_FOUR_BYTES(c1, c2, c3, c4) \ |
802 | do { \ | |
803 | EMIT_TWO_BYTES (c1, c2); \ | |
804 | EMIT_TWO_BYTES (c3, c4); \ | |
805 | } while (0) | |
aa72b389 | 806 | |
aa72b389 | 807 | |
065e3595 KH |
808 | static void |
809 | record_conversion_result (struct coding_system *coding, | |
810 | enum coding_result_code result) | |
811 | { | |
812 | coding->result = result; | |
813 | switch (result) | |
814 | { | |
815 | case CODING_RESULT_INSUFFICIENT_SRC: | |
816 | Vlast_code_conversion_error = Qinsufficient_source; | |
817 | break; | |
818 | case CODING_RESULT_INCONSISTENT_EOL: | |
819 | Vlast_code_conversion_error = Qinconsistent_eol; | |
820 | break; | |
821 | case CODING_RESULT_INVALID_SRC: | |
822 | Vlast_code_conversion_error = Qinvalid_source; | |
823 | break; | |
824 | case CODING_RESULT_INTERRUPT: | |
825 | Vlast_code_conversion_error = Qinterrupted; | |
826 | break; | |
827 | case CODING_RESULT_INSUFFICIENT_MEM: | |
828 | Vlast_code_conversion_error = Qinsufficient_memory; | |
829 | break; | |
ebaf11b6 KH |
830 | case CODING_RESULT_INSUFFICIENT_DST: |
831 | /* Don't record this error in Vlast_code_conversion_error | |
832 | because it happens just temporarily and is resolved when the | |
833 | whole conversion is finished. */ | |
834 | break; | |
409ea3a1 AS |
835 | case CODING_RESULT_SUCCESS: |
836 | break; | |
35befdaa KH |
837 | default: |
838 | Vlast_code_conversion_error = intern ("Unknown error"); | |
065e3595 KH |
839 | } |
840 | } | |
841 | ||
5eb05ea3 KH |
842 | /* These wrapper macros are used to preserve validity of pointers into |
843 | buffer text across calls to decode_char, encode_char, etc, which | |
844 | could cause relocation of buffers if it loads a charset map, | |
845 | because loading a charset map allocates large structures. */ | |
846 | ||
df7492f9 KH |
847 | #define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \ |
848 | do { \ | |
8f50130c | 849 | ptrdiff_t offset; \ |
5eb05ea3 | 850 | \ |
df7492f9 KH |
851 | charset_map_loaded = 0; \ |
852 | c = DECODE_CHAR (charset, code); \ | |
5eb05ea3 | 853 | if (charset_map_loaded \ |
c1892f11 | 854 | && (offset = coding_change_source (coding))) \ |
df7492f9 | 855 | { \ |
df7492f9 KH |
856 | src += offset; \ |
857 | src_base += offset; \ | |
858 | src_end += offset; \ | |
859 | } \ | |
aa72b389 KH |
860 | } while (0) |
861 | ||
5eb05ea3 KH |
862 | #define CODING_ENCODE_CHAR(coding, dst, dst_end, charset, c, code) \ |
863 | do { \ | |
8f50130c | 864 | ptrdiff_t offset; \ |
5eb05ea3 KH |
865 | \ |
866 | charset_map_loaded = 0; \ | |
867 | code = ENCODE_CHAR (charset, c); \ | |
868 | if (charset_map_loaded \ | |
c1892f11 | 869 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
870 | { \ |
871 | dst += offset; \ | |
872 | dst_end += offset; \ | |
873 | } \ | |
874 | } while (0) | |
875 | ||
876 | #define CODING_CHAR_CHARSET(coding, dst, dst_end, c, charset_list, code_return, charset) \ | |
877 | do { \ | |
8f50130c | 878 | ptrdiff_t offset; \ |
5eb05ea3 KH |
879 | \ |
880 | charset_map_loaded = 0; \ | |
881 | charset = char_charset (c, charset_list, code_return); \ | |
882 | if (charset_map_loaded \ | |
c1892f11 | 883 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
884 | { \ |
885 | dst += offset; \ | |
886 | dst_end += offset; \ | |
887 | } \ | |
888 | } while (0) | |
889 | ||
890 | #define CODING_CHAR_CHARSET_P(coding, dst, dst_end, c, charset, result) \ | |
891 | do { \ | |
8f50130c | 892 | ptrdiff_t offset; \ |
5eb05ea3 KH |
893 | \ |
894 | charset_map_loaded = 0; \ | |
895 | result = CHAR_CHARSET_P (c, charset); \ | |
896 | if (charset_map_loaded \ | |
c1892f11 | 897 | && (offset = coding_change_destination (coding))) \ |
5eb05ea3 KH |
898 | { \ |
899 | dst += offset; \ | |
900 | dst_end += offset; \ | |
901 | } \ | |
902 | } while (0) | |
903 | ||
aa72b389 | 904 | |
119852e7 KH |
905 | /* If there are at least BYTES length of room at dst, allocate memory |
906 | for coding->destination and update dst and dst_end. We don't have | |
907 | to take care of coding->source which will be relocated. It is | |
908 | handled by calling coding_set_source in encode_coding. */ | |
909 | ||
df7492f9 KH |
910 | #define ASSURE_DESTINATION(bytes) \ |
911 | do { \ | |
912 | if (dst + (bytes) >= dst_end) \ | |
913 | { \ | |
d311d28c | 914 | ptrdiff_t more_bytes = charbuf_end - charbuf + (bytes); \ |
df7492f9 KH |
915 | \ |
916 | dst = alloc_destination (coding, more_bytes, dst); \ | |
917 | dst_end = coding->destination + coding->dst_bytes; \ | |
918 | } \ | |
919 | } while (0) | |
aa72b389 | 920 | |
aa72b389 | 921 | |
db274c7a | 922 | /* Store multibyte form of the character C in P, and advance P to the |
eedec3ee EZ |
923 | end of the multibyte form. This used to be like CHAR_STRING_ADVANCE |
924 | without ever calling MAYBE_UNIFY_CHAR, but nowadays we don't call | |
925 | MAYBE_UNIFY_CHAR in CHAR_STRING_ADVANCE. */ | |
db274c7a | 926 | |
eedec3ee | 927 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) CHAR_STRING_ADVANCE(c, p) |
db274c7a KH |
928 | |
929 | /* Return the character code of character whose multibyte form is at | |
eedec3ee EZ |
930 | P, and advance P to the end of the multibyte form. This used to be |
931 | like STRING_CHAR_ADVANCE without ever calling MAYBE_UNIFY_CHAR, but | |
932 | nowadays STRING_CHAR_ADVANCE doesn't call MAYBE_UNIFY_CHAR. */ | |
db274c7a | 933 | |
eedec3ee | 934 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) STRING_CHAR_ADVANCE(p) |
aa72b389 | 935 | |
c1892f11 | 936 | /* Set coding->source from coding->src_object. */ |
5eb05ea3 | 937 | |
c1892f11 | 938 | static void |
971de7fb | 939 | coding_set_source (struct coding_system *coding) |
aa72b389 | 940 | { |
df7492f9 KH |
941 | if (BUFFERP (coding->src_object)) |
942 | { | |
2cb26057 | 943 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 944 | |
df7492f9 | 945 | if (coding->src_pos < 0) |
2cb26057 | 946 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 947 | else |
2cb26057 | 948 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 949 | } |
df7492f9 | 950 | else if (STRINGP (coding->src_object)) |
aa72b389 | 951 | { |
8f924df7 | 952 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 953 | } |
df7492f9 | 954 | else |
f38b440c PE |
955 | { |
956 | /* Otherwise, the source is C string and is never relocated | |
957 | automatically. Thus we don't have to update anything. */ | |
958 | } | |
df7492f9 | 959 | } |
aa72b389 | 960 | |
5eb05ea3 | 961 | |
c1892f11 PE |
962 | /* Set coding->source from coding->src_object, and return how many |
963 | bytes coding->source was changed. */ | |
5eb05ea3 | 964 | |
8f50130c | 965 | static ptrdiff_t |
c1892f11 | 966 | coding_change_source (struct coding_system *coding) |
df7492f9 | 967 | { |
c1892f11 PE |
968 | const unsigned char *orig = coding->source; |
969 | coding_set_source (coding); | |
970 | return coding->source - orig; | |
971 | } | |
972 | ||
5eb05ea3 | 973 | |
c1892f11 PE |
974 | /* Set coding->destination from coding->dst_object. */ |
975 | ||
976 | static void | |
977 | coding_set_destination (struct coding_system *coding) | |
978 | { | |
df7492f9 | 979 | if (BUFFERP (coding->dst_object)) |
aa72b389 | 980 | { |
a0241d01 | 981 | if (BUFFERP (coding->src_object) && coding->src_pos < 0) |
aa72b389 | 982 | { |
13818c30 | 983 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
984 | coding->dst_bytes = (GAP_END_ADDR |
985 | - (coding->src_bytes - coding->consumed) | |
986 | - coding->destination); | |
aa72b389 | 987 | } |
df7492f9 | 988 | else |
28f67a95 KH |
989 | { |
990 | /* We are sure that coding->dst_pos_byte is before the gap | |
991 | of the buffer. */ | |
992 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 993 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
994 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
995 | - coding->destination); | |
996 | } | |
df7492f9 KH |
997 | } |
998 | else | |
f38b440c PE |
999 | { |
1000 | /* Otherwise, the destination is C string and is never relocated | |
1001 | automatically. Thus we don't have to update anything. */ | |
1002 | } | |
c1892f11 PE |
1003 | } |
1004 | ||
1005 | ||
1006 | /* Set coding->destination from coding->dst_object, and return how | |
1007 | many bytes coding->destination was changed. */ | |
1008 | ||
1009 | static ptrdiff_t | |
1010 | coding_change_destination (struct coding_system *coding) | |
1011 | { | |
1012 | const unsigned char *orig = coding->destination; | |
1013 | coding_set_destination (coding); | |
5eb05ea3 | 1014 | return coding->destination - orig; |
df7492f9 KH |
1015 | } |
1016 | ||
1017 | ||
1018 | static void | |
d311d28c | 1019 | coding_alloc_by_realloc (struct coding_system *coding, ptrdiff_t bytes) |
df7492f9 | 1020 | { |
c9d624c6 | 1021 | if (STRING_BYTES_BOUND - coding->dst_bytes < bytes) |
d1f3d2af | 1022 | string_overflow (); |
38182d90 PE |
1023 | coding->destination = xrealloc (coding->destination, |
1024 | coding->dst_bytes + bytes); | |
df7492f9 KH |
1025 | coding->dst_bytes += bytes; |
1026 | } | |
1027 | ||
1028 | static void | |
cf84bb53 | 1029 | coding_alloc_by_making_gap (struct coding_system *coding, |
d311d28c | 1030 | ptrdiff_t gap_head_used, ptrdiff_t bytes) |
df7492f9 | 1031 | { |
db274c7a | 1032 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1033 | { |
db274c7a KH |
1034 | /* The gap may contain the produced data at the head and not-yet |
1035 | consumed data at the tail. To preserve those data, we at | |
1036 | first make the gap size to zero, then increase the gap | |
1037 | size. */ | |
d311d28c | 1038 | ptrdiff_t add = GAP_SIZE; |
db274c7a KH |
1039 | |
1040 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1041 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1042 | make_gap (bytes); |
1043 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1044 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1045 | } |
730fff51 | 1046 | else |
df7492f9 | 1047 | { |
2c78b7e1 KH |
1048 | Lisp_Object this_buffer; |
1049 | ||
1050 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1051 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1052 | make_gap (bytes); | |
1053 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1054 | } |
df7492f9 | 1055 | } |
8f924df7 | 1056 | |
df7492f9 KH |
1057 | |
1058 | static unsigned char * | |
d311d28c | 1059 | alloc_destination (struct coding_system *coding, ptrdiff_t nbytes, |
cf84bb53 | 1060 | unsigned char *dst) |
df7492f9 | 1061 | { |
d311d28c | 1062 | ptrdiff_t offset = dst - coding->destination; |
df7492f9 KH |
1063 | |
1064 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1065 | { |
1066 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1067 | ||
1068 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1069 | } | |
aa72b389 | 1070 | else |
df7492f9 | 1071 | coding_alloc_by_realloc (coding, nbytes); |
df7492f9 KH |
1072 | coding_set_destination (coding); |
1073 | dst = coding->destination + offset; | |
1074 | return dst; | |
1075 | } | |
aa72b389 | 1076 | |
ff0dacd7 KH |
1077 | /** Macros for annotations. */ |
1078 | ||
ff0dacd7 KH |
1079 | /* An annotation data is stored in the array coding->charbuf in this |
1080 | format: | |
69a80ea3 | 1081 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1082 | LENGTH is the number of elements in the annotation. |
1083 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1084 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1085 | |
1086 | The format of the following elements depend on ANNOTATION_MASK. | |
1087 | ||
1088 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1089 | follows: | |
e951386e KH |
1090 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
1091 | ||
1092 | NBYTES is the number of bytes specified in the header part of | |
1093 | old-style emacs-mule encoding, or 0 for the other kind of | |
1094 | composition. | |
1095 | ||
ff0dacd7 | 1096 | METHOD is one of enum composition_method. |
e951386e | 1097 | |
ad1746f5 | 1098 | Optional COMPOSITION-COMPONENTS are characters and composition |
ff0dacd7 KH |
1099 | rules. |
1100 | ||
1101 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
e951386e KH |
1102 | follows. |
1103 | ||
1104 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | |
1105 | recover from an invalid annotation, and should be skipped by | |
1106 | produce_annotation. */ | |
1107 | ||
1108 | /* Maximum length of the header of annotation data. */ | |
1109 | #define MAX_ANNOTATION_LENGTH 5 | |
ff0dacd7 | 1110 | |
69a80ea3 | 1111 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1112 | do { \ |
1113 | *(buf)++ = -(len); \ | |
1114 | *(buf)++ = (mask); \ | |
69a80ea3 | 1115 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1116 | coding->annotated = 1; \ |
1117 | } while (0); | |
1118 | ||
e951386e | 1119 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
69a80ea3 | 1120 | do { \ |
e951386e KH |
1121 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
1122 | *buf++ = nbytes; \ | |
69a80ea3 | 1123 | *buf++ = method; \ |
ff0dacd7 KH |
1124 | } while (0) |
1125 | ||
1126 | ||
69a80ea3 KH |
1127 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1128 | do { \ | |
1129 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1130 | *buf++ = id; \ | |
ff0dacd7 KH |
1131 | } while (0) |
1132 | ||
df7492f9 KH |
1133 | \f |
1134 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1135 | ||
1136 | ||
1137 | ||
1138 | \f | |
1139 | /*** 3. UTF-8 ***/ | |
1140 | ||
1141 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 1142 | Return true if a text is encoded in UTF-8. */ |
df7492f9 KH |
1143 | |
1144 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1145 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1146 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1147 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1148 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1149 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1150 | ||
a470d443 KH |
1151 | #define UTF_8_BOM_1 0xEF |
1152 | #define UTF_8_BOM_2 0xBB | |
1153 | #define UTF_8_BOM_3 0xBF | |
1154 | ||
f10fe38f | 1155 | static bool |
cf84bb53 JB |
1156 | detect_coding_utf_8 (struct coding_system *coding, |
1157 | struct coding_detection_info *detect_info) | |
df7492f9 | 1158 | { |
065e3595 | 1159 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1160 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 1161 | bool multibytep = coding->src_multibyte; |
d311d28c | 1162 | ptrdiff_t consumed_chars = 0; |
f10fe38f PE |
1163 | bool bom_found = 0; |
1164 | bool found = 0; | |
df7492f9 | 1165 | |
ff0dacd7 | 1166 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1167 | /* A coding system of this category is always ASCII compatible. */ |
1168 | src += coding->head_ascii; | |
1169 | ||
1170 | while (1) | |
aa72b389 | 1171 | { |
df7492f9 | 1172 | int c, c1, c2, c3, c4; |
aa72b389 | 1173 | |
065e3595 | 1174 | src_base = src; |
df7492f9 | 1175 | ONE_MORE_BYTE (c); |
065e3595 | 1176 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1177 | continue; |
1178 | ONE_MORE_BYTE (c1); | |
065e3595 | 1179 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1180 | break; |
1181 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1182 | { |
a470d443 | 1183 | found = 1; |
df7492f9 | 1184 | continue; |
aa72b389 | 1185 | } |
df7492f9 | 1186 | ONE_MORE_BYTE (c2); |
065e3595 | 1187 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1188 | break; |
1189 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1190 | { |
a470d443 KH |
1191 | found = 1; |
1192 | if (src_base == coding->source | |
1193 | && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3) | |
1194 | bom_found = 1; | |
df7492f9 | 1195 | continue; |
aa72b389 | 1196 | } |
df7492f9 | 1197 | ONE_MORE_BYTE (c3); |
065e3595 | 1198 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1199 | break; |
1200 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1201 | { |
a470d443 | 1202 | found = 1; |
df7492f9 KH |
1203 | continue; |
1204 | } | |
1205 | ONE_MORE_BYTE (c4); | |
065e3595 | 1206 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1207 | break; |
1208 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1209 | { | |
a470d443 | 1210 | found = 1; |
df7492f9 KH |
1211 | continue; |
1212 | } | |
1213 | break; | |
aa72b389 | 1214 | } |
ff0dacd7 | 1215 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1216 | return 0; |
aa72b389 | 1217 | |
df7492f9 | 1218 | no_more_source: |
065e3595 | 1219 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1220 | { |
ff0dacd7 | 1221 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1222 | return 0; |
aa72b389 | 1223 | } |
a470d443 KH |
1224 | if (bom_found) |
1225 | { | |
1226 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
1227 | detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; | |
1228 | } | |
1229 | else | |
1230 | { | |
1231 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
0e17387a KH |
1232 | if (found) |
1233 | detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1234 | } |
ff0dacd7 | 1235 | return 1; |
aa72b389 KH |
1236 | } |
1237 | ||
4ed46869 | 1238 | |
b73bfc1c | 1239 | static void |
971de7fb | 1240 | decode_coding_utf_8 (struct coding_system *coding) |
b73bfc1c | 1241 | { |
8f924df7 KH |
1242 | const unsigned char *src = coding->source + coding->consumed; |
1243 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1244 | const unsigned char *src_base; | |
69a80ea3 KH |
1245 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1246 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
d311d28c | 1247 | ptrdiff_t consumed_chars = 0, consumed_chars_base = 0; |
f10fe38f | 1248 | bool multibytep = coding->src_multibyte; |
a470d443 | 1249 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
f10fe38f PE |
1250 | bool eol_dos |
1251 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1252 | int byte_after_cr = -1; |
4ed46869 | 1253 | |
a470d443 KH |
1254 | if (bom != utf_without_bom) |
1255 | { | |
1256 | int c1, c2, c3; | |
1257 | ||
1258 | src_base = src; | |
1259 | ONE_MORE_BYTE (c1); | |
1260 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1261 | src = src_base; | |
1262 | else | |
1263 | { | |
159bd5a2 | 1264 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1265 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1266 | src = src_base; | |
1267 | else | |
1268 | { | |
159bd5a2 | 1269 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1270 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1271 | src = src_base; | |
1272 | else | |
1273 | { | |
1274 | if ((c1 != UTF_8_BOM_1) | |
1275 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1276 | src = src_base; | |
1277 | else | |
1278 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1279 | } | |
1280 | } | |
1281 | } | |
1282 | } | |
1283 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1284 | ||
df7492f9 | 1285 | while (1) |
b73bfc1c | 1286 | { |
df7492f9 | 1287 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1288 | |
df7492f9 KH |
1289 | src_base = src; |
1290 | consumed_chars_base = consumed_chars; | |
4af310db | 1291 | |
df7492f9 | 1292 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1293 | { |
1294 | if (byte_after_cr >= 0) | |
1295 | src_base--; | |
1296 | break; | |
1297 | } | |
df7492f9 | 1298 | |
119852e7 KH |
1299 | if (byte_after_cr >= 0) |
1300 | c1 = byte_after_cr, byte_after_cr = -1; | |
1301 | else | |
1302 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1303 | if (c1 < 0) |
1304 | { | |
1305 | c = - c1; | |
1306 | } | |
1a4990fb | 1307 | else if (UTF_8_1_OCTET_P (c1)) |
df7492f9 | 1308 | { |
2735d060 | 1309 | if (eol_dos && c1 == '\r') |
119852e7 | 1310 | ONE_MORE_BYTE (byte_after_cr); |
df7492f9 | 1311 | c = c1; |
4af310db | 1312 | } |
df7492f9 | 1313 | else |
4af310db | 1314 | { |
df7492f9 | 1315 | ONE_MORE_BYTE (c2); |
065e3595 | 1316 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1317 | goto invalid_code; |
1318 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1319 | { |
b0edb2c5 DL |
1320 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1321 | /* Reject overlong sequences here and below. Encoders | |
1322 | producing them are incorrect, they can be misleading, | |
1323 | and they mess up read/write invariance. */ | |
1324 | if (c < 128) | |
1325 | goto invalid_code; | |
4af310db | 1326 | } |
df7492f9 | 1327 | else |
aa72b389 | 1328 | { |
df7492f9 | 1329 | ONE_MORE_BYTE (c3); |
065e3595 | 1330 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1331 | goto invalid_code; |
1332 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1333 | { |
1334 | c = (((c1 & 0xF) << 12) | |
1335 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1336 | if (c < 0x800 |
1337 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1338 | goto invalid_code; |
1339 | } | |
df7492f9 KH |
1340 | else |
1341 | { | |
1342 | ONE_MORE_BYTE (c4); | |
065e3595 | 1343 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1344 | goto invalid_code; |
1345 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1346 | { |
df7492f9 KH |
1347 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1348 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1349 | if (c < 0x10000) |
1350 | goto invalid_code; | |
1351 | } | |
df7492f9 KH |
1352 | else |
1353 | { | |
1354 | ONE_MORE_BYTE (c5); | |
065e3595 | 1355 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1356 | goto invalid_code; |
1357 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1358 | { | |
1359 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1360 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1361 | | (c5 & 0x3F)); | |
b0edb2c5 | 1362 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1363 | goto invalid_code; |
1364 | } | |
1365 | else | |
1366 | goto invalid_code; | |
1367 | } | |
1368 | } | |
aa72b389 | 1369 | } |
b73bfc1c | 1370 | } |
df7492f9 KH |
1371 | |
1372 | *charbuf++ = c; | |
1373 | continue; | |
1374 | ||
1375 | invalid_code: | |
1376 | src = src_base; | |
1377 | consumed_chars = consumed_chars_base; | |
1378 | ONE_MORE_BYTE (c); | |
1379 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1380 | coding->errors++; | |
aa72b389 KH |
1381 | } |
1382 | ||
df7492f9 KH |
1383 | no_more_source: |
1384 | coding->consumed_char += consumed_chars_base; | |
1385 | coding->consumed = src_base - coding->source; | |
1386 | coding->charbuf_used = charbuf - coding->charbuf; | |
1387 | } | |
1388 | ||
1389 | ||
f10fe38f | 1390 | static bool |
971de7fb | 1391 | encode_coding_utf_8 (struct coding_system *coding) |
df7492f9 | 1392 | { |
f10fe38f | 1393 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
1394 | int *charbuf = coding->charbuf; |
1395 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1396 | unsigned char *dst = coding->destination + coding->produced; | |
1397 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c | 1398 | ptrdiff_t produced_chars = 0; |
df7492f9 KH |
1399 | int c; |
1400 | ||
a470d443 KH |
1401 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1402 | { | |
1403 | ASSURE_DESTINATION (3); | |
1404 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1405 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1406 | } | |
1407 | ||
df7492f9 | 1408 | if (multibytep) |
aa72b389 | 1409 | { |
df7492f9 KH |
1410 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1411 | ||
1412 | while (charbuf < charbuf_end) | |
b73bfc1c | 1413 | { |
df7492f9 | 1414 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1415 | |
df7492f9 KH |
1416 | ASSURE_DESTINATION (safe_room); |
1417 | c = *charbuf++; | |
28f67a95 KH |
1418 | if (CHAR_BYTE8_P (c)) |
1419 | { | |
1420 | c = CHAR_TO_BYTE8 (c); | |
1421 | EMIT_ONE_BYTE (c); | |
1422 | } | |
1423 | else | |
1424 | { | |
db274c7a | 1425 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1426 | for (p = str; p < pend; p++) |
1427 | EMIT_ONE_BYTE (*p); | |
1428 | } | |
b73bfc1c | 1429 | } |
aa72b389 | 1430 | } |
df7492f9 KH |
1431 | else |
1432 | { | |
1433 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1434 | ||
1435 | while (charbuf < charbuf_end) | |
b73bfc1c | 1436 | { |
df7492f9 KH |
1437 | ASSURE_DESTINATION (safe_room); |
1438 | c = *charbuf++; | |
f03caae0 KH |
1439 | if (CHAR_BYTE8_P (c)) |
1440 | *dst++ = CHAR_TO_BYTE8 (c); | |
1441 | else | |
db274c7a | 1442 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1443 | produced_chars++; |
4ed46869 KH |
1444 | } |
1445 | } | |
065e3595 | 1446 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1447 | coding->produced_char += produced_chars; |
1448 | coding->produced = dst - coding->destination; | |
1449 | return 0; | |
4ed46869 KH |
1450 | } |
1451 | ||
b73bfc1c | 1452 | |
df7492f9 | 1453 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f | 1454 | Return true if a text is encoded in one of UTF-16 based coding systems. */ |
aa72b389 | 1455 | |
df7492f9 KH |
1456 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1457 | (((val) & 0xFC00) == 0xD800) | |
1458 | ||
1459 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1460 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1461 | |
aa72b389 | 1462 | |
f10fe38f | 1463 | static bool |
cf84bb53 JB |
1464 | detect_coding_utf_16 (struct coding_system *coding, |
1465 | struct coding_detection_info *detect_info) | |
aa72b389 | 1466 | { |
ef1b0ba7 | 1467 | const unsigned char *src = coding->source; |
8f924df7 | 1468 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 1469 | bool multibytep = coding->src_multibyte; |
df7492f9 | 1470 | int c1, c2; |
aa72b389 | 1471 | |
ff0dacd7 | 1472 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1473 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1474 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1475 | { |
1476 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1477 | return 0; | |
1478 | } | |
24a73b0a | 1479 | |
f56a4450 | 1480 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1481 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1482 | { |
b49a1807 KH |
1483 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1484 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1485 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1486 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1487 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1488 | } |
df7492f9 | 1489 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1490 | { |
b49a1807 KH |
1491 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1492 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1493 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1494 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1495 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1496 | } | |
220eeac9 | 1497 | else if (c2 < 0) |
f56a4450 KH |
1498 | { |
1499 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1500 | return 0; | |
1501 | } | |
2f3cbb32 | 1502 | else |
24a73b0a | 1503 | { |
2f3cbb32 KH |
1504 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1505 | O is odd. If both are high, we assume binary data.*/ | |
1506 | unsigned char e[256], o[256]; | |
1507 | unsigned e_num = 1, o_num = 1; | |
1508 | ||
1509 | memset (e, 0, 256); | |
1510 | memset (o, 0, 256); | |
1511 | e[c1] = 1; | |
1512 | o[c2] = 1; | |
1513 | ||
cc13543e KH |
1514 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO |
1515 | |CATEGORY_MASK_UTF_16_BE | |
1516 | | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 | 1517 | |
7f1faf1c KH |
1518 | while ((detect_info->rejected & CATEGORY_MASK_UTF_16) |
1519 | != CATEGORY_MASK_UTF_16) | |
2f3cbb32 | 1520 | { |
f56a4450 | 1521 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1522 | if (c2 < 0) |
f56a4450 | 1523 | break; |
2f3cbb32 KH |
1524 | if (! e[c1]) |
1525 | { | |
1526 | e[c1] = 1; | |
1527 | e_num++; | |
cc13543e KH |
1528 | if (e_num >= 128) |
1529 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
2f3cbb32 KH |
1530 | } |
1531 | if (! o[c2]) | |
1532 | { | |
977b85f4 | 1533 | o[c2] = 1; |
2f3cbb32 | 1534 | o_num++; |
cc13543e KH |
1535 | if (o_num >= 128) |
1536 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
2f3cbb32 KH |
1537 | } |
1538 | } | |
2f3cbb32 | 1539 | return 0; |
ff0dacd7 | 1540 | } |
2f3cbb32 | 1541 | |
df7492f9 | 1542 | no_more_source: |
ff0dacd7 | 1543 | return 1; |
df7492f9 | 1544 | } |
aa72b389 | 1545 | |
df7492f9 | 1546 | static void |
971de7fb | 1547 | decode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1548 | { |
8f924df7 KH |
1549 | const unsigned char *src = coding->source + coding->consumed; |
1550 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1551 | const unsigned char *src_base; | |
69a80ea3 | 1552 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
1553 | /* We may produces at most 3 chars in one loop. */ |
1554 | int *charbuf_end = coding->charbuf + coding->charbuf_size - 2; | |
d311d28c | 1555 | ptrdiff_t consumed_chars = 0, consumed_chars_base = 0; |
f10fe38f | 1556 | bool multibytep = coding->src_multibyte; |
a470d443 | 1557 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1558 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1559 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
f10fe38f PE |
1560 | bool eol_dos |
1561 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1562 | int byte_after_cr1 = -1, byte_after_cr2 = -1; |
df7492f9 | 1563 | |
a470d443 | 1564 | if (bom == utf_with_bom) |
aa72b389 | 1565 | { |
df7492f9 | 1566 | int c, c1, c2; |
4af310db | 1567 | |
aa72b389 | 1568 | src_base = src; |
df7492f9 KH |
1569 | ONE_MORE_BYTE (c1); |
1570 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1571 | c = (c1 << 8) | c2; |
aa72b389 | 1572 | |
b49a1807 KH |
1573 | if (endian == utf_16_big_endian |
1574 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1575 | { |
b49a1807 KH |
1576 | /* The first two bytes are not BOM. Treat them as bytes |
1577 | for a normal character. */ | |
1578 | src = src_base; | |
1579 | coding->errors++; | |
aa72b389 | 1580 | } |
a470d443 | 1581 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1582 | } |
a470d443 | 1583 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1584 | { |
1585 | /* We have already tried to detect BOM and failed in | |
1586 | detect_coding. */ | |
a470d443 | 1587 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1588 | } |
aa72b389 | 1589 | |
df7492f9 KH |
1590 | while (1) |
1591 | { | |
1592 | int c, c1, c2; | |
1593 | ||
1594 | src_base = src; | |
1595 | consumed_chars_base = consumed_chars; | |
1596 | ||
df80c7f0 | 1597 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1598 | { |
1599 | if (byte_after_cr1 >= 0) | |
1600 | src_base -= 2; | |
1601 | break; | |
1602 | } | |
df7492f9 | 1603 | |
119852e7 KH |
1604 | if (byte_after_cr1 >= 0) |
1605 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1606 | else | |
1607 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1608 | if (c1 < 0) |
1609 | { | |
1610 | *charbuf++ = -c1; | |
1611 | continue; | |
1612 | } | |
119852e7 KH |
1613 | if (byte_after_cr2 >= 0) |
1614 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1615 | else | |
1616 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1617 | if (c2 < 0) |
1618 | { | |
1619 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1620 | *charbuf++ = -c2; | |
1621 | continue; | |
1622 | } | |
df7492f9 | 1623 | c = (endian == utf_16_big_endian |
e19c3639 | 1624 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1625 | |
df7492f9 | 1626 | if (surrogate) |
fd3ae0b9 | 1627 | { |
df7492f9 | 1628 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1629 | { |
df7492f9 KH |
1630 | if (endian == utf_16_big_endian) |
1631 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1632 | else | |
1633 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1634 | *charbuf++ = c1; | |
1635 | *charbuf++ = c2; | |
1636 | coding->errors++; | |
1637 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1638 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1639 | else |
df7492f9 | 1640 | *charbuf++ = c; |
fd3ae0b9 KH |
1641 | } |
1642 | else | |
df7492f9 KH |
1643 | { |
1644 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1645 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1646 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1647 | } |
fd3ae0b9 | 1648 | } |
aa72b389 | 1649 | else |
df7492f9 KH |
1650 | { |
1651 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1652 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1653 | else | |
119852e7 | 1654 | { |
2735d060 | 1655 | if (eol_dos && c == '\r') |
119852e7 KH |
1656 | { |
1657 | ONE_MORE_BYTE (byte_after_cr1); | |
1658 | ONE_MORE_BYTE (byte_after_cr2); | |
1659 | } | |
1660 | *charbuf++ = c; | |
1661 | } | |
8f924df7 | 1662 | } |
aa72b389 | 1663 | } |
df7492f9 KH |
1664 | |
1665 | no_more_source: | |
1666 | coding->consumed_char += consumed_chars_base; | |
1667 | coding->consumed = src_base - coding->source; | |
1668 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1669 | } |
b73bfc1c | 1670 | |
f10fe38f | 1671 | static bool |
971de7fb | 1672 | encode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1673 | { |
f10fe38f | 1674 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
1675 | int *charbuf = coding->charbuf; |
1676 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1677 | unsigned char *dst = coding->destination + coding->produced; | |
1678 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1679 | int safe_room = 8; | |
a470d443 | 1680 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
f10fe38f | 1681 | bool big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
d311d28c | 1682 | ptrdiff_t produced_chars = 0; |
df7492f9 | 1683 | int c; |
4ed46869 | 1684 | |
a470d443 | 1685 | if (bom != utf_without_bom) |
df7492f9 KH |
1686 | { |
1687 | ASSURE_DESTINATION (safe_room); | |
1688 | if (big_endian) | |
df7492f9 | 1689 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1690 | else |
1691 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1692 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1693 | } |
1694 | ||
1695 | while (charbuf < charbuf_end) | |
1696 | { | |
1697 | ASSURE_DESTINATION (safe_room); | |
1698 | c = *charbuf++; | |
60afa08d | 1699 | if (c > MAX_UNICODE_CHAR) |
e19c3639 | 1700 | c = coding->default_char; |
df7492f9 KH |
1701 | |
1702 | if (c < 0x10000) | |
1703 | { | |
1704 | if (big_endian) | |
1705 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1706 | else | |
1707 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1708 | } | |
1709 | else | |
1710 | { | |
1711 | int c1, c2; | |
1712 | ||
1713 | c -= 0x10000; | |
1714 | c1 = (c >> 10) + 0xD800; | |
1715 | c2 = (c & 0x3FF) + 0xDC00; | |
1716 | if (big_endian) | |
1717 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1718 | else | |
1719 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1720 | } | |
1721 | } | |
065e3595 | 1722 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1723 | coding->produced = dst - coding->destination; |
1724 | coding->produced_char += produced_chars; | |
1725 | return 0; | |
1726 | } | |
1727 | ||
1728 | \f | |
1729 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1730 | ||
1731 | /* Emacs' internal format for representation of multiple character | |
1732 | sets is a kind of multi-byte encoding, i.e. characters are | |
1733 | represented by variable-length sequences of one-byte codes. | |
1734 | ||
1735 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1736 | represented by one-byte sequences which are their ASCII codes, in | |
1737 | the range 0x00 through 0x7F. | |
1738 | ||
1739 | 8-bit characters of the range 0x80..0x9F are represented by | |
1740 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1741 | code + 0x20). | |
1742 | ||
1743 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1744 | one-byte sequences which are their 8-bit code. | |
1745 | ||
1746 | The other characters are represented by a sequence of `base | |
1747 | leading-code', optional `extended leading-code', and one or two | |
1748 | `position-code's. The length of the sequence is determined by the | |
1749 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1750 | whereas extended leading-code and position-code take the range 0xA0 | |
1751 | through 0xFF. See `charset.h' for more details about leading-code | |
1752 | and position-code. | |
1753 | ||
1754 | --- CODE RANGE of Emacs' internal format --- | |
1755 | character set range | |
1756 | ------------- ----- | |
1757 | ascii 0x00..0x7F | |
1758 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1759 | eight-bit-graphic 0xA0..0xBF | |
1760 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1761 | --------------------------------------------- | |
1762 | ||
1763 | As this is the internal character representation, the format is | |
1764 | usually not used externally (i.e. in a file or in a data sent to a | |
1765 | process). But, it is possible to have a text externally in this | |
1766 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1767 | ||
1768 | In that case, a sequence of one-byte codes has a slightly different | |
1769 | form. | |
1770 | ||
1771 | At first, all characters in eight-bit-control are represented by | |
1772 | one-byte sequences which are their 8-bit code. | |
1773 | ||
1774 | Next, character composition data are represented by the byte | |
1775 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1776 | where, | |
e951386e | 1777 | METHOD is 0xF2 plus one of composition method (enum |
df7492f9 KH |
1778 | composition_method), |
1779 | ||
1780 | BYTES is 0xA0 plus a byte length of this composition data, | |
1781 | ||
e951386e | 1782 | CHARS is 0xA0 plus a number of characters composed by this |
df7492f9 KH |
1783 | data, |
1784 | ||
ad1746f5 | 1785 | COMPONENTs are characters of multibyte form or composition |
df7492f9 KH |
1786 | rules encoded by two-byte of ASCII codes. |
1787 | ||
1788 | In addition, for backward compatibility, the following formats are | |
1789 | also recognized as composition data on decoding. | |
1790 | ||
1791 | 0x80 MSEQ ... | |
1792 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1793 | ||
1794 | Here, | |
1795 | MSEQ is a multibyte form but in these special format: | |
1796 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1797 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1798 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1799 | represents a composition rule. | |
1800 | */ | |
1801 | ||
1802 | char emacs_mule_bytes[256]; | |
1803 | ||
e951386e KH |
1804 | |
1805 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 1806 | Return true if a text is encoded in 'emacs-mule'. */ |
e951386e | 1807 | |
f10fe38f | 1808 | static bool |
cf84bb53 JB |
1809 | detect_coding_emacs_mule (struct coding_system *coding, |
1810 | struct coding_detection_info *detect_info) | |
e951386e KH |
1811 | { |
1812 | const unsigned char *src = coding->source, *src_base; | |
1813 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
f10fe38f | 1814 | bool multibytep = coding->src_multibyte; |
d311d28c | 1815 | ptrdiff_t consumed_chars = 0; |
e951386e KH |
1816 | int c; |
1817 | int found = 0; | |
1818 | ||
1819 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | |
1820 | /* A coding system of this category is always ASCII compatible. */ | |
1821 | src += coding->head_ascii; | |
1822 | ||
1823 | while (1) | |
1824 | { | |
1825 | src_base = src; | |
1826 | ONE_MORE_BYTE (c); | |
1827 | if (c < 0) | |
1828 | continue; | |
1829 | if (c == 0x80) | |
1830 | { | |
1831 | /* Perhaps the start of composite character. We simply skip | |
1832 | it because analyzing it is too heavy for detecting. But, | |
1833 | at least, we check that the composite character | |
1834 | constitutes of more than 4 bytes. */ | |
2735d060 | 1835 | const unsigned char *src_start; |
e951386e KH |
1836 | |
1837 | repeat: | |
2735d060 | 1838 | src_start = src; |
e951386e KH |
1839 | do |
1840 | { | |
1841 | ONE_MORE_BYTE (c); | |
1842 | } | |
1843 | while (c >= 0xA0); | |
1844 | ||
2735d060 | 1845 | if (src - src_start <= 4) |
e951386e KH |
1846 | break; |
1847 | found = CATEGORY_MASK_EMACS_MULE; | |
1848 | if (c == 0x80) | |
1849 | goto repeat; | |
1850 | } | |
1851 | ||
1852 | if (c < 0x80) | |
1853 | { | |
1854 | if (c < 0x20 | |
1855 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1856 | break; | |
1857 | } | |
1858 | else | |
1859 | { | |
396475b7 | 1860 | int more_bytes = emacs_mule_bytes[c] - 1; |
e951386e KH |
1861 | |
1862 | while (more_bytes > 0) | |
1863 | { | |
1864 | ONE_MORE_BYTE (c); | |
1865 | if (c < 0xA0) | |
1866 | { | |
1867 | src--; /* Unread the last byte. */ | |
1868 | break; | |
1869 | } | |
1870 | more_bytes--; | |
1871 | } | |
1872 | if (more_bytes != 0) | |
1873 | break; | |
1874 | found = CATEGORY_MASK_EMACS_MULE; | |
1875 | } | |
1876 | } | |
1877 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1878 | return 0; | |
1879 | ||
1880 | no_more_source: | |
1881 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | |
1882 | { | |
1883 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1884 | return 0; | |
1885 | } | |
1886 | detect_info->found |= found; | |
1887 | return 1; | |
1888 | } | |
1889 | ||
1890 | ||
1891 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | |
1892 | character. If CMP_STATUS indicates that we must expect MSEQ or | |
1893 | RULE described above, decode it and return the negative value of | |
685ebdc8 | 1894 | the decoded character or rule. If an invalid byte is found, return |
e951386e KH |
1895 | -1. If SRC is too short, return -2. */ |
1896 | ||
e2f1bab9 | 1897 | static int |
cf84bb53 JB |
1898 | emacs_mule_char (struct coding_system *coding, const unsigned char *src, |
1899 | int *nbytes, int *nchars, int *id, | |
1900 | struct composition_status *cmp_status) | |
df7492f9 | 1901 | { |
8f924df7 KH |
1902 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1903 | const unsigned char *src_base = src; | |
f10fe38f | 1904 | bool multibytep = coding->src_multibyte; |
2735d060 | 1905 | int charset_ID; |
df7492f9 KH |
1906 | unsigned code; |
1907 | int c; | |
1908 | int consumed_chars = 0; | |
f10fe38f | 1909 | bool mseq_found = 0; |
df7492f9 KH |
1910 | |
1911 | ONE_MORE_BYTE (c); | |
065e3595 | 1912 | if (c < 0) |
df7492f9 | 1913 | { |
065e3595 | 1914 | c = -c; |
2735d060 | 1915 | charset_ID = emacs_mule_charset[0]; |
065e3595 KH |
1916 | } |
1917 | else | |
1918 | { | |
4d41e8b7 KH |
1919 | if (c >= 0xA0) |
1920 | { | |
e951386e KH |
1921 | if (cmp_status->state != COMPOSING_NO |
1922 | && cmp_status->old_form) | |
4d41e8b7 | 1923 | { |
e951386e KH |
1924 | if (cmp_status->state == COMPOSING_CHAR) |
1925 | { | |
1926 | if (c == 0xA0) | |
1927 | { | |
1928 | ONE_MORE_BYTE (c); | |
1929 | c -= 0x80; | |
1930 | if (c < 0) | |
1931 | goto invalid_code; | |
1932 | } | |
1933 | else | |
1934 | c -= 0x20; | |
1935 | mseq_found = 1; | |
1936 | } | |
1937 | else | |
1938 | { | |
1939 | *nbytes = src - src_base; | |
1940 | *nchars = consumed_chars; | |
1941 | return -c; | |
1942 | } | |
4d41e8b7 KH |
1943 | } |
1944 | else | |
e951386e | 1945 | goto invalid_code; |
4d41e8b7 KH |
1946 | } |
1947 | ||
065e3595 | 1948 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 1949 | { |
065e3595 | 1950 | case 2: |
2735d060 | 1951 | if ((charset_ID = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
1952 | goto invalid_code; |
1953 | ONE_MORE_BYTE (c); | |
9ffd559c | 1954 | if (c < 0xA0) |
065e3595 | 1955 | goto invalid_code; |
df7492f9 | 1956 | code = c & 0x7F; |
065e3595 KH |
1957 | break; |
1958 | ||
1959 | case 3: | |
1960 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
1961 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
1962 | { | |
1963 | ONE_MORE_BYTE (c); | |
2735d060 | 1964 | if (c < 0xA0 || (charset_ID = emacs_mule_charset[c]) < 0) |
065e3595 KH |
1965 | goto invalid_code; |
1966 | ONE_MORE_BYTE (c); | |
9ffd559c | 1967 | if (c < 0xA0) |
065e3595 KH |
1968 | goto invalid_code; |
1969 | code = c & 0x7F; | |
1970 | } | |
1971 | else | |
1972 | { | |
2735d060 | 1973 | if ((charset_ID = emacs_mule_charset[c]) < 0) |
065e3595 KH |
1974 | goto invalid_code; |
1975 | ONE_MORE_BYTE (c); | |
9ffd559c | 1976 | if (c < 0xA0) |
065e3595 KH |
1977 | goto invalid_code; |
1978 | code = (c & 0x7F) << 8; | |
1979 | ONE_MORE_BYTE (c); | |
9ffd559c | 1980 | if (c < 0xA0) |
065e3595 KH |
1981 | goto invalid_code; |
1982 | code |= c & 0x7F; | |
1983 | } | |
1984 | break; | |
1985 | ||
1986 | case 4: | |
1987 | ONE_MORE_BYTE (c); | |
2735d060 | 1988 | if (c < 0 || (charset_ID = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
1989 | goto invalid_code; |
1990 | ONE_MORE_BYTE (c); | |
9ffd559c | 1991 | if (c < 0xA0) |
065e3595 | 1992 | goto invalid_code; |
781d7a48 | 1993 | code = (c & 0x7F) << 8; |
df7492f9 | 1994 | ONE_MORE_BYTE (c); |
9ffd559c | 1995 | if (c < 0xA0) |
065e3595 | 1996 | goto invalid_code; |
df7492f9 | 1997 | code |= c & 0x7F; |
065e3595 | 1998 | break; |
df7492f9 | 1999 | |
065e3595 KH |
2000 | case 1: |
2001 | code = c; | |
2735d060 | 2002 | charset_ID = ASCII_BYTE_P (code) ? charset_ascii : charset_eight_bit; |
065e3595 | 2003 | break; |
df7492f9 | 2004 | |
065e3595 | 2005 | default: |
1088b922 | 2006 | emacs_abort (); |
065e3595 | 2007 | } |
b84ae584 | 2008 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
2735d060 | 2009 | CHARSET_FROM_ID (charset_ID), code, c); |
065e3595 KH |
2010 | if (c < 0) |
2011 | goto invalid_code; | |
df7492f9 | 2012 | } |
df7492f9 KH |
2013 | *nbytes = src - src_base; |
2014 | *nchars = consumed_chars; | |
ff0dacd7 | 2015 | if (id) |
2735d060 | 2016 | *id = charset_ID; |
e951386e | 2017 | return (mseq_found ? -c : c); |
df7492f9 KH |
2018 | |
2019 | no_more_source: | |
2020 | return -2; | |
2021 | ||
2022 | invalid_code: | |
2023 | return -1; | |
2024 | } | |
2025 | ||
2026 | ||
e951386e | 2027 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
df7492f9 | 2028 | |
e951386e KH |
2029 | /* Handle these composition sequence ('|': the end of header elements, |
2030 | BYTES and CHARS >= 0xA0): | |
df7492f9 | 2031 | |
e951386e KH |
2032 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
2033 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... | |
2034 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... | |
df7492f9 | 2035 | |
e951386e | 2036 | and these old form: |
1a4990fb | 2037 | |
e951386e KH |
2038 | (4) relative composition: 0x80 | MSEQ ... MSEQ |
2039 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ | |
df7492f9 | 2040 | |
e951386e KH |
2041 | When the starter 0x80 and the following header elements are found, |
2042 | this annotation header is produced. | |
df7492f9 | 2043 | |
e951386e | 2044 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
df7492f9 | 2045 | |
e951386e KH |
2046 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
2047 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). | |
df7492f9 | 2048 | |
e951386e KH |
2049 | Then, upon reading the following elements, these codes are produced |
2050 | until the composition end is found: | |
df7492f9 | 2051 | |
e951386e KH |
2052 | (1) CHAR ... CHAR |
2053 | (2) ALT ... ALT CHAR ... CHAR | |
2054 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR | |
2055 | (4) CHAR ... CHAR | |
2056 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
4ed46869 | 2057 | |
e951386e KH |
2058 | When the composition end is found, LENGTH and NCHARS in the |
2059 | annotation header is updated as below: | |
b73bfc1c | 2060 | |
e951386e KH |
2061 | (1) LENGTH: unchanged, NCHARS: unchanged |
2062 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2063 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2064 | (4) LENGTH: unchanged, NCHARS: number of CHARs | |
2065 | (5) LENGTH: unchanged, NCHARS: number of CHARs | |
df7492f9 | 2066 | |
e951386e KH |
2067 | If an error is found while composing, the annotation header is |
2068 | changed to the original composition header (plus filler -1s) as | |
2069 | below: | |
2070 | ||
2071 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] | |
2072 | (5) [ 0x80 0xFF -1 -1- -1 ] | |
2073 | ||
2074 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
2075 | byte sequence as below: | |
2076 | o the original byte sequence is B: [ B -1 ] | |
2077 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
2078 | ||
2079 | Most of the routines are implemented by macros because many | |
2080 | variables and labels in the caller decode_coding_emacs_mule must be | |
2081 | accessible, and they are usually called just once (thus doesn't | |
2082 | increase the size of compiled object). */ | |
2083 | ||
2084 | /* Decode a composition rule represented by C as a component of | |
2085 | composition sequence of Emacs 20 style. Set RULE to the decoded | |
2086 | rule. */ | |
2087 | ||
2088 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ | |
df7492f9 | 2089 | do { \ |
e951386e KH |
2090 | int gref, nref; \ |
2091 | \ | |
4d41e8b7 | 2092 | c -= 0xA0; \ |
df7492f9 KH |
2093 | if (c < 0 || c >= 81) \ |
2094 | goto invalid_code; \ | |
df7492f9 | 2095 | gref = c / 9, nref = c % 9; \ |
e951386e KH |
2096 | if (gref == 4) gref = 10; \ |
2097 | if (nref == 4) nref = 10; \ | |
2098 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
df7492f9 KH |
2099 | } while (0) |
2100 | ||
2101 | ||
e951386e KH |
2102 | /* Decode a composition rule represented by C and the following byte |
2103 | at SRC as a component of composition sequence of Emacs 21 style. | |
2104 | Set RULE to the decoded rule. */ | |
781d7a48 | 2105 | |
e951386e | 2106 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
781d7a48 KH |
2107 | do { \ |
2108 | int gref, nref; \ | |
e951386e KH |
2109 | \ |
2110 | gref = c - 0x20; \ | |
2111 | if (gref < 0 || gref >= 81) \ | |
781d7a48 | 2112 | goto invalid_code; \ |
e951386e KH |
2113 | ONE_MORE_BYTE (c); \ |
2114 | nref = c - 0x20; \ | |
2115 | if (nref < 0 || nref >= 81) \ | |
781d7a48 | 2116 | goto invalid_code; \ |
e951386e | 2117 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
781d7a48 KH |
2118 | } while (0) |
2119 | ||
2120 | ||
e951386e KH |
2121 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
2122 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | |
2123 | byte length of this composition information, CHARS is the number of | |
2124 | characters composed by this composition. */ | |
2125 | ||
2126 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | |
aa72b389 | 2127 | do { \ |
781d7a48 | 2128 | enum composition_method method = c - 0xF2; \ |
df7492f9 | 2129 | int nbytes, nchars; \ |
e951386e | 2130 | \ |
df7492f9 | 2131 | ONE_MORE_BYTE (c); \ |
065e3595 KH |
2132 | if (c < 0) \ |
2133 | goto invalid_code; \ | |
df7492f9 | 2134 | nbytes = c - 0xA0; \ |
e951386e | 2135 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
df7492f9 KH |
2136 | goto invalid_code; \ |
2137 | ONE_MORE_BYTE (c); \ | |
2138 | nchars = c - 0xA0; \ | |
e951386e KH |
2139 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
2140 | goto invalid_code; \ | |
2141 | cmp_status->old_form = 0; \ | |
2142 | cmp_status->method = method; \ | |
2143 | if (method == COMPOSITION_RELATIVE) \ | |
2144 | cmp_status->state = COMPOSING_CHAR; \ | |
2145 | else \ | |
2146 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ | |
2147 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2148 | cmp_status->nchars = nchars; \ | |
2149 | cmp_status->ncomps = nbytes - 4; \ | |
2150 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ | |
aa72b389 | 2151 | } while (0) |
93dec019 | 2152 | |
aa72b389 | 2153 | |
e951386e KH |
2154 | /* Start of Emacs 20 style format for relative composition. */ |
2155 | ||
2156 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ | |
2157 | do { \ | |
2158 | cmp_status->old_form = 1; \ | |
2159 | cmp_status->method = COMPOSITION_RELATIVE; \ | |
2160 | cmp_status->state = COMPOSING_CHAR; \ | |
2161 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2162 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2163 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
2164 | } while (0) | |
2165 | ||
2166 | ||
2167 | /* Start of Emacs 20 style format for rule-base composition. */ | |
2168 | ||
2169 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | |
2170 | do { \ | |
2171 | cmp_status->old_form = 1; \ | |
2172 | cmp_status->method = COMPOSITION_WITH_RULE; \ | |
2173 | cmp_status->state = COMPOSING_CHAR; \ | |
2174 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2175 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2176 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
df7492f9 KH |
2177 | } while (0) |
2178 | ||
2179 | ||
e951386e KH |
2180 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ |
2181 | do { \ | |
2182 | const unsigned char *current_src = src; \ | |
2183 | \ | |
2184 | ONE_MORE_BYTE (c); \ | |
2185 | if (c < 0) \ | |
2186 | goto invalid_code; \ | |
2187 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | |
2188 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | |
2189 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | |
2190 | else if (c < 0xA0) \ | |
2191 | goto invalid_code; \ | |
2192 | else if (c < 0xC0) \ | |
2193 | { \ | |
2194 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | |
2195 | /* Re-read C as a composition component. */ \ | |
2196 | src = current_src; \ | |
2197 | } \ | |
2198 | else if (c == 0xFF) \ | |
2199 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | |
2200 | else \ | |
2201 | goto invalid_code; \ | |
2202 | } while (0) | |
2203 | ||
2204 | #define EMACS_MULE_COMPOSITION_END() \ | |
df7492f9 | 2205 | do { \ |
e951386e | 2206 | int idx = - cmp_status->length; \ |
4d41e8b7 | 2207 | \ |
e951386e KH |
2208 | if (cmp_status->old_form) \ |
2209 | charbuf[idx + 2] = cmp_status->nchars; \ | |
2210 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ | |
2211 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ | |
2212 | cmp_status->state = COMPOSING_NO; \ | |
2213 | } while (0) | |
2214 | ||
2215 | ||
2216 | static int | |
cf84bb53 JB |
2217 | emacs_mule_finish_composition (int *charbuf, |
2218 | struct composition_status *cmp_status) | |
e951386e KH |
2219 | { |
2220 | int idx = - cmp_status->length; | |
2221 | int new_chars; | |
2222 | ||
2223 | if (cmp_status->old_form && cmp_status->nchars > 0) | |
2224 | { | |
2225 | charbuf[idx + 2] = cmp_status->nchars; | |
2226 | new_chars = 0; | |
2227 | if (cmp_status->method == COMPOSITION_WITH_RULE | |
2228 | && cmp_status->state == COMPOSING_CHAR) | |
2229 | { | |
2230 | /* The last rule was invalid. */ | |
2231 | int rule = charbuf[-1] + 0xA0; | |
2232 | ||
2233 | charbuf[-2] = BYTE8_TO_CHAR (rule); | |
2234 | charbuf[-1] = -1; | |
2235 | new_chars = 1; | |
2236 | } | |
2237 | } | |
2238 | else | |
2239 | { | |
2240 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | |
2241 | ||
2242 | if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2243 | { | |
2244 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | |
2245 | charbuf[idx++] = -3; | |
2246 | charbuf[idx++] = 0; | |
2247 | new_chars = 1; | |
2248 | } | |
2249 | else | |
2250 | { | |
2251 | int nchars = charbuf[idx + 1] + 0xA0; | |
2252 | int nbytes = charbuf[idx + 2] + 0xA0; | |
2253 | ||
2254 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | |
2255 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | |
2256 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | |
2257 | charbuf[idx++] = -1; | |
2258 | new_chars = 4; | |
2259 | } | |
2260 | } | |
2261 | cmp_status->state = COMPOSING_NO; | |
2262 | return new_chars; | |
2263 | } | |
2264 | ||
2265 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | |
2266 | do { \ | |
2267 | if (cmp_status->state != COMPOSING_NO) \ | |
2268 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | |
df7492f9 KH |
2269 | } while (0) |
2270 | ||
aa72b389 KH |
2271 | |
2272 | static void | |
971de7fb | 2273 | decode_coding_emacs_mule (struct coding_system *coding) |
aa72b389 | 2274 | { |
8f924df7 KH |
2275 | const unsigned char *src = coding->source + coding->consumed; |
2276 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2277 | const unsigned char *src_base; | |
69a80ea3 | 2278 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
2279 | /* We may produce two annotations (charset and composition) in one |
2280 | loop and one more charset annotation at the end. */ | |
69a80ea3 | 2281 | int *charbuf_end |
15cbd324 EZ |
2282 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3) |
2283 | /* We can produce up to 2 characters in a loop. */ | |
2284 | - 1; | |
d311d28c | 2285 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 2286 | bool multibytep = coding->src_multibyte; |
d311d28c PE |
2287 | ptrdiff_t char_offset = coding->produced_char; |
2288 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 2289 | int last_id = charset_ascii; |
f10fe38f PE |
2290 | bool eol_dos |
2291 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 2292 | int byte_after_cr = -1; |
e951386e | 2293 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; |
aa72b389 | 2294 | |
e951386e KH |
2295 | if (cmp_status->state != COMPOSING_NO) |
2296 | { | |
2297 | int i; | |
2298 | ||
15cbd324 | 2299 | if (charbuf_end - charbuf < cmp_status->length) |
1088b922 | 2300 | emacs_abort (); |
e951386e KH |
2301 | for (i = 0; i < cmp_status->length; i++) |
2302 | *charbuf++ = cmp_status->carryover[i]; | |
2303 | coding->annotated = 1; | |
2304 | } | |
2305 | ||
aa72b389 KH |
2306 | while (1) |
2307 | { | |
ee05f961 | 2308 | int c, id IF_LINT (= 0); |
df7492f9 | 2309 | |
aa72b389 | 2310 | src_base = src; |
df7492f9 KH |
2311 | consumed_chars_base = consumed_chars; |
2312 | ||
2313 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2314 | { |
2315 | if (byte_after_cr >= 0) | |
2316 | src_base--; | |
2317 | break; | |
2318 | } | |
aa72b389 | 2319 | |
119852e7 KH |
2320 | if (byte_after_cr >= 0) |
2321 | c = byte_after_cr, byte_after_cr = -1; | |
2322 | else | |
2323 | ONE_MORE_BYTE (c); | |
e951386e KH |
2324 | |
2325 | if (c < 0 || c == 0x80) | |
065e3595 | 2326 | { |
e951386e KH |
2327 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
2328 | if (c < 0) | |
2329 | { | |
2330 | *charbuf++ = -c; | |
2331 | char_offset++; | |
2332 | } | |
2333 | else | |
2334 | DECODE_EMACS_MULE_COMPOSITION_START (); | |
2335 | continue; | |
065e3595 | 2336 | } |
e951386e KH |
2337 | |
2338 | if (c < 0x80) | |
aa72b389 | 2339 | { |
2735d060 | 2340 | if (eol_dos && c == '\r') |
119852e7 | 2341 | ONE_MORE_BYTE (byte_after_cr); |
e951386e KH |
2342 | id = charset_ascii; |
2343 | if (cmp_status->state != COMPOSING_NO) | |
2344 | { | |
2345 | if (cmp_status->old_form) | |
2346 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2347 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2348 | cmp_status->ncomps--; | |
2349 | } | |
2350 | } | |
2351 | else | |
2352 | { | |
ee05f961 | 2353 | int nchars IF_LINT (= 0), nbytes IF_LINT (= 0); |
75f80e63 EZ |
2354 | /* emacs_mule_char can load a charset map from a file, which |
2355 | allocates a large structure and might cause buffer text | |
2356 | to be relocated as result. Thus, we need to remember the | |
ad1746f5 | 2357 | original pointer to buffer text, and fix up all related |
75f80e63 EZ |
2358 | pointers after the call. */ |
2359 | const unsigned char *orig = coding->source; | |
d311d28c | 2360 | ptrdiff_t offset; |
e951386e KH |
2361 | |
2362 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, | |
2363 | cmp_status); | |
75f80e63 EZ |
2364 | offset = coding->source - orig; |
2365 | if (offset) | |
2366 | { | |
2367 | src += offset; | |
2368 | src_base += offset; | |
2369 | src_end += offset; | |
2370 | } | |
e951386e KH |
2371 | if (c < 0) |
2372 | { | |
2373 | if (c == -1) | |
2374 | goto invalid_code; | |
2375 | if (c == -2) | |
2376 | break; | |
2377 | } | |
2378 | src = src_base + nbytes; | |
2379 | consumed_chars = consumed_chars_base + nchars; | |
2380 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2381 | cmp_status->ncomps -= nchars; | |
2382 | } | |
2383 | ||
ad1746f5 | 2384 | /* Now if C >= 0, we found a normally encoded character, if C < |
e951386e KH |
2385 | 0, we found an old-style composition component character or |
2386 | rule. */ | |
2387 | ||
2388 | if (cmp_status->state == COMPOSING_NO) | |
2389 | { | |
2390 | if (last_id != id) | |
2391 | { | |
2392 | if (last_id != charset_ascii) | |
2393 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, | |
2394 | last_id); | |
2395 | last_id = id; | |
2396 | last_offset = char_offset; | |
2397 | } | |
df7492f9 KH |
2398 | *charbuf++ = c; |
2399 | char_offset++; | |
aa72b389 | 2400 | } |
e951386e | 2401 | else if (cmp_status->state == COMPOSING_CHAR) |
df7492f9 | 2402 | { |
e951386e KH |
2403 | if (cmp_status->old_form) |
2404 | { | |
2405 | if (c >= 0) | |
2406 | { | |
2407 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2408 | *charbuf++ = c; | |
2409 | char_offset++; | |
2410 | } | |
2411 | else | |
2412 | { | |
2413 | *charbuf++ = -c; | |
2414 | cmp_status->nchars++; | |
2415 | cmp_status->length++; | |
2416 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | |
2417 | EMACS_MULE_COMPOSITION_END (); | |
2418 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2419 | cmp_status->state = COMPOSING_RULE; | |
2420 | } | |
2421 | } | |
df7492f9 | 2422 | else |
e951386e KH |
2423 | { |
2424 | *charbuf++ = c; | |
2425 | cmp_status->length++; | |
2426 | cmp_status->nchars--; | |
2427 | if (cmp_status->nchars == 0) | |
2428 | EMACS_MULE_COMPOSITION_END (); | |
2429 | } | |
df7492f9 | 2430 | } |
e951386e | 2431 | else if (cmp_status->state == COMPOSING_RULE) |
df7492f9 | 2432 | { |
e951386e | 2433 | int rule; |
ff0dacd7 | 2434 | |
e951386e | 2435 | if (c >= 0) |
df7492f9 | 2436 | { |
e951386e KH |
2437 | EMACS_MULE_COMPOSITION_END (); |
2438 | *charbuf++ = c; | |
2439 | char_offset++; | |
df7492f9 | 2440 | } |
e951386e | 2441 | else |
ff0dacd7 | 2442 | { |
e951386e KH |
2443 | c = -c; |
2444 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | |
2445 | if (rule < 0) | |
2446 | goto invalid_code; | |
2447 | *charbuf++ = -2; | |
2448 | *charbuf++ = rule; | |
2449 | cmp_status->length += 2; | |
2450 | cmp_status->state = COMPOSING_CHAR; | |
ff0dacd7 | 2451 | } |
e951386e KH |
2452 | } |
2453 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | |
2454 | { | |
df7492f9 | 2455 | *charbuf++ = c; |
e951386e KH |
2456 | cmp_status->length++; |
2457 | if (cmp_status->ncomps == 0) | |
2458 | cmp_status->state = COMPOSING_CHAR; | |
2459 | else if (cmp_status->ncomps > 0) | |
2460 | { | |
2461 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | |
2462 | cmp_status->state = COMPOSING_COMPONENT_RULE; | |
2463 | } | |
2464 | else | |
2465 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 2466 | } |
e951386e KH |
2467 | else /* COMPOSING_COMPONENT_RULE */ |
2468 | { | |
2469 | int rule; | |
2470 | ||
2471 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | |
2472 | if (rule < 0) | |
2473 | goto invalid_code; | |
2474 | *charbuf++ = -2; | |
2475 | *charbuf++ = rule; | |
2476 | cmp_status->length += 2; | |
2477 | cmp_status->ncomps--; | |
2478 | if (cmp_status->ncomps > 0) | |
2479 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | |
2480 | else | |
2481 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2482 | } | |
2483 | continue; | |
2484 | ||
df7492f9 | 2485 | invalid_code: |
e951386e | 2486 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
df7492f9 KH |
2487 | src = src_base; |
2488 | consumed_chars = consumed_chars_base; | |
2489 | ONE_MORE_BYTE (c); | |
2490 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2491 | char_offset++; |
df7492f9 KH |
2492 | coding->errors++; |
2493 | } | |
2494 | ||
2495 | no_more_source: | |
e951386e KH |
2496 | if (cmp_status->state != COMPOSING_NO) |
2497 | { | |
2498 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
2499 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2500 | else | |
2501 | { | |
2502 | int i; | |
2503 | ||
2504 | charbuf -= cmp_status->length; | |
2505 | for (i = 0; i < cmp_status->length; i++) | |
2506 | cmp_status->carryover[i] = charbuf[i]; | |
2507 | } | |
2508 | } | |
ff0dacd7 | 2509 | if (last_id != charset_ascii) |
69a80ea3 | 2510 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2511 | coding->consumed_char += consumed_chars_base; |
2512 | coding->consumed = src_base - coding->source; | |
2513 | coding->charbuf_used = charbuf - coding->charbuf; | |
2514 | } | |
2515 | ||
2516 | ||
2517 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2518 | do { \ | |
2519 | if (id < 0xA0) \ | |
2520 | codes[0] = id, codes[1] = 0; \ | |
2521 | else if (id < 0xE0) \ | |
2522 | codes[0] = 0x9A, codes[1] = id; \ | |
2523 | else if (id < 0xF0) \ | |
2524 | codes[0] = 0x9B, codes[1] = id; \ | |
2525 | else if (id < 0xF5) \ | |
2526 | codes[0] = 0x9C, codes[1] = id; \ | |
2527 | else \ | |
2528 | codes[0] = 0x9D, codes[1] = id; \ | |
2529 | } while (0); | |
2530 | ||
aa72b389 | 2531 | |
f10fe38f | 2532 | static bool |
971de7fb | 2533 | encode_coding_emacs_mule (struct coding_system *coding) |
df7492f9 | 2534 | { |
f10fe38f | 2535 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
2536 | int *charbuf = coding->charbuf; |
2537 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2538 | unsigned char *dst = coding->destination + coding->produced; | |
2539 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2540 | int safe_room = 8; | |
d311d28c | 2541 | ptrdiff_t produced_chars = 0; |
24a73b0a | 2542 | Lisp_Object attrs, charset_list; |
df7492f9 | 2543 | int c; |
ff0dacd7 | 2544 | int preferred_charset_id = -1; |
df7492f9 | 2545 | |
24a73b0a | 2546 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2547 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2548 | { | |
4939150c PE |
2549 | charset_list = Vemacs_mule_charset_list; |
2550 | ASET (attrs, coding_attr_charset_list, charset_list); | |
eccb6815 | 2551 | } |
df7492f9 KH |
2552 | |
2553 | while (charbuf < charbuf_end) | |
2554 | { | |
2555 | ASSURE_DESTINATION (safe_room); | |
2556 | c = *charbuf++; | |
ff0dacd7 KH |
2557 | |
2558 | if (c < 0) | |
2559 | { | |
2560 | /* Handle an annotation. */ | |
2561 | switch (*charbuf) | |
2562 | { | |
2563 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2564 | /* Not yet implemented. */ | |
2565 | break; | |
2566 | case CODING_ANNOTATE_CHARSET_MASK: | |
2567 | preferred_charset_id = charbuf[3]; | |
2568 | if (preferred_charset_id >= 0 | |
2569 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2570 | charset_list))) | |
2571 | preferred_charset_id = -1; | |
2572 | break; | |
2573 | default: | |
1088b922 | 2574 | emacs_abort (); |
ff0dacd7 KH |
2575 | } |
2576 | charbuf += -c - 1; | |
2577 | continue; | |
2578 | } | |
2579 | ||
df7492f9 KH |
2580 | if (ASCII_CHAR_P (c)) |
2581 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2582 | else if (CHAR_BYTE8_P (c)) |
2583 | { | |
2584 | c = CHAR_TO_BYTE8 (c); | |
2585 | EMIT_ONE_BYTE (c); | |
2586 | } | |
df7492f9 | 2587 | else |
aa72b389 | 2588 | { |
df7492f9 KH |
2589 | struct charset *charset; |
2590 | unsigned code; | |
2591 | int dimension; | |
2592 | int emacs_mule_id; | |
2593 | unsigned char leading_codes[2]; | |
2594 | ||
ff0dacd7 KH |
2595 | if (preferred_charset_id >= 0) |
2596 | { | |
f10fe38f | 2597 | bool result; |
5eb05ea3 | 2598 | |
ff0dacd7 | 2599 | charset = CHARSET_FROM_ID (preferred_charset_id); |
5eb05ea3 KH |
2600 | CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result); |
2601 | if (result) | |
905ca9d2 KH |
2602 | code = ENCODE_CHAR (charset, c); |
2603 | else | |
5eb05ea3 KH |
2604 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2605 | &code, charset); | |
ff0dacd7 KH |
2606 | } |
2607 | else | |
5eb05ea3 KH |
2608 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2609 | &code, charset); | |
df7492f9 KH |
2610 | if (! charset) |
2611 | { | |
2612 | c = coding->default_char; | |
2613 | if (ASCII_CHAR_P (c)) | |
2614 | { | |
2615 | EMIT_ONE_ASCII_BYTE (c); | |
2616 | continue; | |
2617 | } | |
5eb05ea3 KH |
2618 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2619 | &code, charset); | |
df7492f9 KH |
2620 | } |
2621 | dimension = CHARSET_DIMENSION (charset); | |
2622 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2623 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2624 | EMIT_ONE_BYTE (leading_codes[0]); | |
2625 | if (leading_codes[1]) | |
2626 | EMIT_ONE_BYTE (leading_codes[1]); | |
2627 | if (dimension == 1) | |
1fa663f9 | 2628 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2629 | else |
df7492f9 | 2630 | { |
1fa663f9 | 2631 | code |= 0x8080; |
df7492f9 KH |
2632 | EMIT_ONE_BYTE (code >> 8); |
2633 | EMIT_ONE_BYTE (code & 0xFF); | |
2634 | } | |
aa72b389 | 2635 | } |
aa72b389 | 2636 | } |
065e3595 | 2637 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2638 | coding->produced_char += produced_chars; |
2639 | coding->produced = dst - coding->destination; | |
2640 | return 0; | |
aa72b389 | 2641 | } |
b73bfc1c | 2642 | |
4ed46869 | 2643 | \f |
df7492f9 | 2644 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2645 | |
2646 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2647 | Since the intention of this note is to help understand the |
5a936b46 | 2648 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2649 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2650 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2651 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2652 | |
2653 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2654 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2655 | is encoded using bytes less than 128. This may make the encoded |
2656 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2657 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2658 | Significant Bit). |
b73bfc1c | 2659 | |
cfb43547 DL |
2660 | There are two kinds of character sets: control character sets and |
2661 | graphic character sets. The former contain control characters such | |
4ed46869 | 2662 | as `newline' and `escape' to provide control functions (control |
39787efd | 2663 | functions are also provided by escape sequences). The latter |
cfb43547 | 2664 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2665 | two control character sets and many graphic character sets. |
2666 | ||
2667 | Graphic character sets are classified into one of the following | |
39787efd KH |
2668 | four classes, according to the number of bytes (DIMENSION) and |
2669 | number of characters in one dimension (CHARS) of the set: | |
2670 | - DIMENSION1_CHARS94 | |
2671 | - DIMENSION1_CHARS96 | |
2672 | - DIMENSION2_CHARS94 | |
2673 | - DIMENSION2_CHARS96 | |
2674 | ||
2675 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2676 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2677 | hereafter). The <F> of each character set is decided by ECMA(*) |
2678 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2679 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2680 | |
2681 | Note (*): ECMA = European Computer Manufacturers Association | |
2682 | ||
cfb43547 | 2683 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2684 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2685 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2686 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2687 | o DIMENSION2_CHARS96 -- none for the moment | |
2688 | ||
39787efd | 2689 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2690 | C0 [0x00..0x1F] -- control character plane 0 |
2691 | GL [0x20..0x7F] -- graphic character plane 0 | |
2692 | C1 [0x80..0x9F] -- control character plane 1 | |
2693 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2694 | ||
2695 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2696 | C1 by an escape sequence. The most common case is that: |
2697 | - ISO646's control character set is designated/invoked to C0, and | |
2698 | - ISO6429's control character set is designated/invoked to C1, | |
2699 | and usually these designations/invocations are omitted in encoded | |
2700 | text. In a 7-bit environment, only C0 can be used, and a control | |
2701 | character for C1 is encoded by an appropriate escape sequence to | |
2702 | fit into the environment. All control characters for C1 are | |
2703 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2704 | |
2705 | A graphic character set is at first designated to one of four | |
2706 | graphic registers (G0 through G3), then these graphic registers are | |
2707 | invoked to GL or GR. These designations and invocations can be | |
2708 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2709 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2710 | these invocations and designations are omitted in encoded text. | |
2711 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2712 | |
39787efd KH |
2713 | When a graphic character set of CHARS94 is invoked to GL, codes |
2714 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2715 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2716 | be used. | |
4ed46869 KH |
2717 | |
2718 | There are two ways of invocation: locking-shift and single-shift. | |
2719 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2720 | invocation, whereas with single-shift, the invocation affects the |
2721 | following character only and doesn't affect the locking-shift | |
2722 | state. Invocations are done by the following control characters or | |
2723 | escape sequences: | |
4ed46869 KH |
2724 | |
2725 | ---------------------------------------------------------------------- | |
39787efd | 2726 | abbrev function cntrl escape seq description |
4ed46869 | 2727 | ---------------------------------------------------------------------- |
39787efd KH |
2728 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2729 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2730 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2731 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2732 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2733 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2734 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2735 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2736 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2737 | ---------------------------------------------------------------------- |
39787efd KH |
2738 | (*) These are not used by any known coding system. |
2739 | ||
2740 | Control characters for these functions are defined by macros | |
2741 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2742 | |
39787efd | 2743 | Designations are done by the following escape sequences: |
4ed46869 KH |
2744 | ---------------------------------------------------------------------- |
2745 | escape sequence description | |
2746 | ---------------------------------------------------------------------- | |
2747 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2748 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2749 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2750 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2751 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2752 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2753 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2754 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2755 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2756 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2757 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2758 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2759 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2760 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2761 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2762 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2763 | ---------------------------------------------------------------------- | |
2764 | ||
2765 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2766 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2767 | |
2768 | Note (*): Although these designations are not allowed in ISO2022, | |
2769 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2770 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2771 | 7-bit environment, non-locking-shift, and non-single-shift. |
2772 | ||
2773 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2774 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2775 | |
cfb43547 | 2776 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2777 | same multilingual text in ISO2022. Actually, there exist many |
2778 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2779 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2780 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2781 | localized platforms), and all of these are variants of ISO2022. |
2782 | ||
2783 | In addition to the above, Emacs handles two more kinds of escape | |
2784 | sequences: ISO6429's direction specification and Emacs' private | |
2785 | sequence for specifying character composition. | |
2786 | ||
39787efd | 2787 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2788 | o CSI ']' -- end of the current direction |
2789 | o CSI '0' ']' -- end of the current direction | |
2790 | o CSI '1' ']' -- start of left-to-right text | |
2791 | o CSI '2' ']' -- start of right-to-left text | |
2792 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2793 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2794 | ||
2795 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2796 | o ESC '0' -- start relative composition |
2797 | o ESC '1' -- end composition | |
2798 | o ESC '2' -- start rule-base composition (*) | |
2799 | o ESC '3' -- start relative composition with alternate chars (**) | |
2800 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2801 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2802 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2803 | |
5a936b46 DL |
2804 | (*) This form is used only in Emacs 20.7 and older versions, |
2805 | but newer versions can safely decode it. | |
cfb43547 | 2806 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2807 | and older versions can't decode it. |
ec6d2bb8 | 2808 | |
cfb43547 | 2809 | Here's a list of example usages of these composition escape |
b73bfc1c | 2810 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2811 | |
b73bfc1c | 2812 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2813 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2814 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2815 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2816 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2817 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2818 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2819 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 | 2820 | |
74ab6df5 | 2821 | static enum iso_code_class_type iso_code_class[256]; |
4ed46869 | 2822 | |
df7492f9 KH |
2823 | #define SAFE_CHARSET_P(coding, id) \ |
2824 | ((id) <= (coding)->max_charset_id \ | |
1b3b981b | 2825 | && (coding)->safe_charsets[id] != 255) |
df7492f9 | 2826 | |
df7492f9 | 2827 | static void |
971de7fb | 2828 | setup_iso_safe_charsets (Lisp_Object attrs) |
df7492f9 KH |
2829 | { |
2830 | Lisp_Object charset_list, safe_charsets; | |
2831 | Lisp_Object request; | |
2832 | Lisp_Object reg_usage; | |
2833 | Lisp_Object tail; | |
d311d28c | 2834 | EMACS_INT reg94, reg96; |
df7492f9 KH |
2835 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); |
2836 | int max_charset_id; | |
2837 | ||
2838 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2839 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2840 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2841 | { | |
4939150c PE |
2842 | charset_list = Viso_2022_charset_list; |
2843 | ASET (attrs, coding_attr_charset_list, charset_list); | |
df7492f9 KH |
2844 | ASET (attrs, coding_attr_safe_charsets, Qnil); |
2845 | } | |
2846 | ||
2847 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2848 | return; | |
2849 | ||
2850 | max_charset_id = 0; | |
2851 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2852 | { | |
2853 | int id = XINT (XCAR (tail)); | |
2854 | if (max_charset_id < id) | |
2855 | max_charset_id = id; | |
2856 | } | |
d46c5b12 | 2857 | |
1b3b981b AS |
2858 | safe_charsets = make_uninit_string (max_charset_id + 1); |
2859 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
2860 | request = AREF (attrs, coding_attr_iso_request); |
2861 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2862 | reg94 = XINT (XCAR (reg_usage)); | |
2863 | reg96 = XINT (XCDR (reg_usage)); | |
2864 | ||
2865 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2866 | { | |
2867 | Lisp_Object id; | |
2868 | Lisp_Object reg; | |
2869 | struct charset *charset; | |
2870 | ||
2871 | id = XCAR (tail); | |
2872 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2873 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2874 | if (! NILP (reg)) |
8f924df7 | 2875 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2876 | else if (charset->iso_chars_96) |
2877 | { | |
2878 | if (reg96 < 4) | |
8f924df7 | 2879 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2880 | } |
2881 | else | |
2882 | { | |
2883 | if (reg94 < 4) | |
8f924df7 | 2884 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2885 | } |
2886 | } | |
2887 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2888 | } | |
d46c5b12 | 2889 | |
b6871cc7 | 2890 | |
4ed46869 | 2891 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f PE |
2892 | Return true if a text is encoded in one of ISO-2022 based coding |
2893 | systems. */ | |
4ed46869 | 2894 | |
f10fe38f | 2895 | static bool |
cf84bb53 JB |
2896 | detect_coding_iso_2022 (struct coding_system *coding, |
2897 | struct coding_detection_info *detect_info) | |
4ed46869 | 2898 | { |
8f924df7 KH |
2899 | const unsigned char *src = coding->source, *src_base = src; |
2900 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
f10fe38f PE |
2901 | bool multibytep = coding->src_multibyte; |
2902 | bool single_shifting = 0; | |
0e48bb22 | 2903 | int id; |
df7492f9 | 2904 | int c, c1; |
d311d28c | 2905 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 2906 | int i; |
ff0dacd7 KH |
2907 | int rejected = 0; |
2908 | int found = 0; | |
cee53ed4 | 2909 | int composition_count = -1; |
ff0dacd7 KH |
2910 | |
2911 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2912 | |
2913 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2914 | { | |
2915 | struct coding_system *this = &(coding_categories[i]); | |
2916 | Lisp_Object attrs, val; | |
2917 | ||
c6b278e7 KH |
2918 | if (this->id < 0) |
2919 | continue; | |
df7492f9 KH |
2920 | attrs = CODING_ID_ATTRS (this->id); |
2921 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
1b3b981b | 2922 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list)) |
df7492f9 KH |
2923 | setup_iso_safe_charsets (attrs); |
2924 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 2925 | this->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 2926 | this->safe_charsets = SDATA (val); |
df7492f9 KH |
2927 | } |
2928 | ||
2929 | /* A coding system of this category is always ASCII compatible. */ | |
2930 | src += coding->head_ascii; | |
3f003981 | 2931 | |
ff0dacd7 | 2932 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2933 | { |
065e3595 | 2934 | src_base = src; |
df7492f9 | 2935 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2936 | switch (c) |
2937 | { | |
2938 | case ISO_CODE_ESC: | |
74383408 KH |
2939 | if (inhibit_iso_escape_detection) |
2940 | break; | |
f46869e4 | 2941 | single_shifting = 0; |
df7492f9 | 2942 | ONE_MORE_BYTE (c); |
0e48bb22 | 2943 | if (c == 'N' || c == 'O') |
d46c5b12 | 2944 | { |
ae9ff118 | 2945 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2946 | single_shifting = 1; |
2947 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
4ed46869 | 2948 | } |
cee53ed4 KH |
2949 | else if (c == '1') |
2950 | { | |
2951 | /* End of composition. */ | |
2952 | if (composition_count < 0 | |
2953 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
2954 | /* Invalid */ | |
2955 | break; | |
2956 | composition_count = -1; | |
2957 | found |= CATEGORY_MASK_ISO; | |
2958 | } | |
ec6d2bb8 KH |
2959 | else if (c >= '0' && c <= '4') |
2960 | { | |
2961 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 2962 | composition_count = 0; |
ec6d2bb8 | 2963 | } |
bf9cdd4e | 2964 | else |
df7492f9 | 2965 | { |
0e48bb22 AS |
2966 | if (c >= '(' && c <= '/') |
2967 | { | |
2968 | /* Designation sequence for a charset of dimension 1. */ | |
2969 | ONE_MORE_BYTE (c1); | |
2970 | if (c1 < ' ' || c1 >= 0x80 | |
2971 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) | |
2972 | /* Invalid designation sequence. Just ignore. */ | |
2973 | break; | |
2974 | } | |
2975 | else if (c == '$') | |
2976 | { | |
2977 | /* Designation sequence for a charset of dimension 2. */ | |
2978 | ONE_MORE_BYTE (c); | |
2979 | if (c >= '@' && c <= 'B') | |
2980 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
2981 | id = iso_charset_table[1][0][c]; | |
2982 | else if (c >= '(' && c <= '/') | |
2983 | { | |
2984 | ONE_MORE_BYTE (c1); | |
2985 | if (c1 < ' ' || c1 >= 0x80 | |
2986 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) | |
2987 | /* Invalid designation sequence. Just ignore. */ | |
2988 | break; | |
2989 | } | |
2990 | else | |
2991 | /* Invalid designation sequence. Just ignore it. */ | |
2992 | break; | |
2993 | } | |
2994 | else | |
2995 | { | |
2996 | /* Invalid escape sequence. Just ignore it. */ | |
2997 | break; | |
2998 | } | |
d46c5b12 | 2999 | |
0e48bb22 AS |
3000 | /* We found a valid designation sequence for CHARSET. */ |
3001 | rejected |= CATEGORY_MASK_ISO_8BIT; | |
3002 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], | |
3003 | id)) | |
3004 | found |= CATEGORY_MASK_ISO_7; | |
3005 | else | |
3006 | rejected |= CATEGORY_MASK_ISO_7; | |
3007 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], | |
3008 | id)) | |
3009 | found |= CATEGORY_MASK_ISO_7_TIGHT; | |
3010 | else | |
3011 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; | |
3012 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], | |
3013 | id)) | |
3014 | found |= CATEGORY_MASK_ISO_7_ELSE; | |
3015 | else | |
3016 | rejected |= CATEGORY_MASK_ISO_7_ELSE; | |
3017 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], | |
3018 | id)) | |
3019 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3020 | else | |
3021 | rejected |= CATEGORY_MASK_ISO_8_ELSE; | |
3022 | } | |
4ed46869 KH |
3023 | break; |
3024 | ||
4ed46869 | 3025 | case ISO_CODE_SO: |
d46c5b12 | 3026 | case ISO_CODE_SI: |
ff0dacd7 | 3027 | /* Locking shift out/in. */ |
74383408 KH |
3028 | if (inhibit_iso_escape_detection) |
3029 | break; | |
f46869e4 | 3030 | single_shifting = 0; |
ff0dacd7 | 3031 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
3032 | break; |
3033 | ||
4ed46869 | 3034 | case ISO_CODE_CSI: |
ff0dacd7 | 3035 | /* Control sequence introducer. */ |
f46869e4 | 3036 | single_shifting = 0; |
ff0dacd7 KH |
3037 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3038 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3039 | goto check_extra_latin; | |
3040 | ||
4ed46869 KH |
3041 | case ISO_CODE_SS2: |
3042 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
3043 | /* Single shift. */ |
3044 | if (inhibit_iso_escape_detection) | |
3045 | break; | |
75e2a253 | 3046 | single_shifting = 0; |
ff0dacd7 KH |
3047 | rejected |= CATEGORY_MASK_ISO_7BIT; |
3048 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3049 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
0e48bb22 AS |
3050 | { |
3051 | found |= CATEGORY_MASK_ISO_8_1; | |
3052 | single_shifting = 1; | |
3053 | } | |
ff0dacd7 KH |
3054 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
3055 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
0e48bb22 AS |
3056 | { |
3057 | found |= CATEGORY_MASK_ISO_8_2; | |
3058 | single_shifting = 1; | |
3059 | } | |
75e2a253 KH |
3060 | if (single_shifting) |
3061 | break; | |
0e48bb22 AS |
3062 | check_extra_latin: |
3063 | if (! VECTORP (Vlatin_extra_code_table) | |
28be1ada | 3064 | || NILP (AREF (Vlatin_extra_code_table, c))) |
0e48bb22 AS |
3065 | { |
3066 | rejected = CATEGORY_MASK_ISO; | |
3067 | break; | |
3068 | } | |
3069 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3070 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3071 | found |= CATEGORY_MASK_ISO_8_1; | |
3072 | else | |
3073 | rejected |= CATEGORY_MASK_ISO_8_1; | |
3074 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3075 | break; | |
4ed46869 KH |
3076 | |
3077 | default: | |
065e3595 KH |
3078 | if (c < 0) |
3079 | continue; | |
4ed46869 | 3080 | if (c < 0x80) |
f46869e4 | 3081 | { |
cee53ed4 KH |
3082 | if (composition_count >= 0) |
3083 | composition_count++; | |
f46869e4 KH |
3084 | single_shifting = 0; |
3085 | break; | |
3086 | } | |
ff0dacd7 | 3087 | if (c >= 0xA0) |
c4825358 | 3088 | { |
ff0dacd7 KH |
3089 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3090 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 3091 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
3092 | 0xA0..0FF. If the byte length is even, we include |
3093 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
3094 | only when we are not single shifting. */ | |
3095 | if (! single_shifting | |
3096 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 3097 | { |
2735d060 | 3098 | int len = 1; |
b73bfc1c KH |
3099 | while (src < src_end) |
3100 | { | |
d12bd917 | 3101 | src_base = src; |
df7492f9 | 3102 | ONE_MORE_BYTE (c); |
b73bfc1c | 3103 | if (c < 0xA0) |
d12bd917 KH |
3104 | { |
3105 | src = src_base; | |
3106 | break; | |
3107 | } | |
2735d060 | 3108 | len++; |
b73bfc1c KH |
3109 | } |
3110 | ||
2735d060 | 3111 | if (len & 1 && src < src_end) |
cee53ed4 KH |
3112 | { |
3113 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3114 | if (composition_count >= 0) | |
2735d060 | 3115 | composition_count += len; |
cee53ed4 | 3116 | } |
f46869e4 | 3117 | else |
cee53ed4 KH |
3118 | { |
3119 | found |= CATEGORY_MASK_ISO_8_2; | |
3120 | if (composition_count >= 0) | |
2735d060 | 3121 | composition_count += len / 2; |
cee53ed4 | 3122 | } |
f46869e4 | 3123 | } |
ff0dacd7 | 3124 | break; |
4ed46869 | 3125 | } |
4ed46869 KH |
3126 | } |
3127 | } | |
ff0dacd7 KH |
3128 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3129 | return 0; | |
4ed46869 | 3130 | |
df7492f9 | 3131 | no_more_source: |
ff0dacd7 KH |
3132 | detect_info->rejected |= rejected; |
3133 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3134 | return 1; |
4ed46869 | 3135 | } |
ec6d2bb8 | 3136 | |
4ed46869 | 3137 | |
134b9549 KH |
3138 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3139 | escape sequence should be kept. */ | |
df7492f9 KH |
3140 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3141 | do { \ | |
3142 | int id, prev; \ | |
3143 | \ | |
3144 | if (final < '0' || final >= 128 \ | |
3145 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3146 | || !SAFE_CHARSET_P (coding, id)) \ | |
3147 | { \ | |
3148 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3149 | chars_96 = -1; \ |
3150 | break; \ | |
df7492f9 KH |
3151 | } \ |
3152 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3153 | if (id == charset_jisx0201_roman) \ |
3154 | { \ | |
3155 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3156 | id = charset_ascii; \ | |
3157 | } \ | |
3158 | else if (id == charset_jisx0208_1978) \ | |
3159 | { \ | |
3160 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3161 | id = charset_jisx0208; \ | |
3162 | } \ | |
df7492f9 KH |
3163 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3164 | /* If there was an invalid designation to REG previously, and this \ | |
3165 | designation is ASCII to REG, we should keep this designation \ | |
3166 | sequence. */ \ | |
3167 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3168 | chars_96 = -1; \ |
4ed46869 KH |
3169 | } while (0) |
3170 | ||
d46c5b12 | 3171 | |
e951386e KH |
3172 | /* Handle these composition sequence (ALT: alternate char): |
3173 | ||
3174 | (1) relative composition: ESC 0 CHAR ... ESC 1 | |
3175 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
3176 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | |
3177 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | |
3178 | ||
3179 | When the start sequence (ESC 0/2/3/4) is found, this annotation | |
3180 | header is produced. | |
3181 | ||
3182 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | |
3183 | ||
3184 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | |
3185 | produced until the end sequence (ESC 1) is found: | |
3186 | ||
3187 | (1) CHAR ... CHAR | |
3188 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
3189 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | |
3190 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | |
3191 | ||
3192 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | |
3193 | annotation header is updated as below: | |
3194 | ||
3195 | (1) LENGTH: unchanged, NCHARS: number of CHARs | |
3196 | (2) LENGTH: unchanged, NCHARS: number of CHARs | |
3197 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | |
3198 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | |
3199 | ||
3200 | If an error is found while composing, the annotation header is | |
3201 | changed to: | |
3202 | ||
3203 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | |
3204 | ||
3205 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
3206 | byte sequence as below: | |
3207 | o the original byte sequence is B: [ B -1 ] | |
3208 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
3209 | and the sequence [ -1 -1 ] is changed to the original byte | |
3210 | sequence: | |
3211 | [ ESC '0' ] | |
3212 | */ | |
3213 | ||
3214 | /* Decode a composition rule C1 and maybe one more byte from the | |
66ebf983 | 3215 | source, and set RULE to the encoded composition rule. If the rule |
d5efd1d1 | 3216 | is invalid, goto invalid_code. */ |
e951386e | 3217 | |
66ebf983 | 3218 | #define DECODE_COMPOSITION_RULE(rule) \ |
e951386e KH |
3219 | do { \ |
3220 | rule = c1 - 32; \ | |
3221 | if (rule < 0) \ | |
d5efd1d1 | 3222 | goto invalid_code; \ |
e951386e KH |
3223 | if (rule < 81) /* old format (before ver.21) */ \ |
3224 | { \ | |
3225 | int gref = (rule) / 9; \ | |
3226 | int nref = (rule) % 9; \ | |
3227 | if (gref == 4) gref = 10; \ | |
3228 | if (nref == 4) nref = 10; \ | |
3229 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
e951386e KH |
3230 | } \ |
3231 | else /* new format (after ver.21) */ \ | |
3232 | { \ | |
2735d060 | 3233 | int b; \ |
e951386e | 3234 | \ |
2735d060 | 3235 | ONE_MORE_BYTE (b); \ |
d5efd1d1 PE |
3236 | if (! COMPOSITION_ENCODE_RULE_VALID (rule - 81, b - 32)) \ |
3237 | goto invalid_code; \ | |
2735d060 | 3238 | rule = COMPOSITION_ENCODE_RULE (rule - 81, b - 32); \ |
d5efd1d1 | 3239 | rule += 0x100; /* Distinguish it from the old format. */ \ |
e951386e KH |
3240 | } \ |
3241 | } while (0) | |
3242 | ||
3243 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
df7492f9 | 3244 | do { \ |
e951386e KH |
3245 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
3246 | \ | |
3247 | if (rule < 0x100) /* old format */ \ | |
df7492f9 | 3248 | { \ |
e951386e KH |
3249 | if (gref == 10) gref = 4; \ |
3250 | if (nref == 10) nref = 4; \ | |
3251 | charbuf[idx] = 32 + gref * 9 + nref; \ | |
3252 | charbuf[idx + 1] = -1; \ | |
3253 | new_chars++; \ | |
df7492f9 | 3254 | } \ |
e951386e | 3255 | else /* new format */ \ |
df7492f9 | 3256 | { \ |
e951386e KH |
3257 | charbuf[idx] = 32 + 81 + gref; \ |
3258 | charbuf[idx + 1] = 32 + nref; \ | |
3259 | new_chars += 2; \ | |
df7492f9 KH |
3260 | } \ |
3261 | } while (0) | |
3262 | ||
e951386e KH |
3263 | /* Finish the current composition as invalid. */ |
3264 | ||
e951386e | 3265 | static int |
971de7fb | 3266 | finish_composition (int *charbuf, struct composition_status *cmp_status) |
e951386e KH |
3267 | { |
3268 | int idx = - cmp_status->length; | |
3269 | int new_chars; | |
3270 | ||
3271 | /* Recover the original ESC sequence */ | |
3272 | charbuf[idx++] = ISO_CODE_ESC; | |
3273 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | |
3274 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | |
3275 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | |
3276 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | |
3277 | : '4'); | |
3278 | charbuf[idx++] = -2; | |
3279 | charbuf[idx++] = 0; | |
3280 | charbuf[idx++] = -1; | |
3281 | new_chars = cmp_status->nchars; | |
3282 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | |
3283 | for (; idx < 0; idx++) | |
3284 | { | |
3285 | int elt = charbuf[idx]; | |
3286 | ||
3287 | if (elt == -2) | |
3288 | { | |
3289 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | |
3290 | idx++; | |
3291 | } | |
3292 | else if (elt == -1) | |
3293 | { | |
3294 | charbuf[idx++] = ISO_CODE_ESC; | |
3295 | charbuf[idx] = '0'; | |
3296 | new_chars += 2; | |
3297 | } | |
3298 | } | |
3299 | cmp_status->state = COMPOSING_NO; | |
3300 | return new_chars; | |
3301 | } | |
3302 | ||
ad1746f5 | 3303 | /* If characters are under composition, finish the composition. */ |
e951386e KH |
3304 | #define MAYBE_FINISH_COMPOSITION() \ |
3305 | do { \ | |
3306 | if (cmp_status->state != COMPOSING_NO) \ | |
3307 | char_offset += finish_composition (charbuf, cmp_status); \ | |
3308 | } while (0) | |
d46c5b12 | 3309 | |
aa72b389 | 3310 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
e951386e | 3311 | |
aa72b389 KH |
3312 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
3313 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3314 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3315 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
ec6d2bb8 | 3316 | |
e951386e KH |
3317 | Produce this annotation sequence now: |
3318 | ||
3319 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] | |
3320 | */ | |
3321 | ||
3322 | #define DECODE_COMPOSITION_START(c1) \ | |
3323 | do { \ | |
3324 | if (c1 == '0' \ | |
3325 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ | |
3326 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ | |
3327 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ | |
3328 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ | |
3329 | { \ | |
3330 | *charbuf++ = -1; \ | |
3331 | *charbuf++= -1; \ | |
3332 | cmp_status->state = COMPOSING_CHAR; \ | |
3333 | cmp_status->length += 2; \ | |
3334 | } \ | |
3335 | else \ | |
3336 | { \ | |
3337 | MAYBE_FINISH_COMPOSITION (); \ | |
3338 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3339 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3340 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3341 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3342 | cmp_status->state \ | |
3343 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ | |
3344 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
3345 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
3346 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
3347 | coding->annotated = 1; \ | |
3348 | } \ | |
ec6d2bb8 KH |
3349 | } while (0) |
3350 | ||
ec6d2bb8 | 3351 | |
e951386e | 3352 | /* Handle composition end sequence ESC 1. */ |
df7492f9 KH |
3353 | |
3354 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3355 | do { \ |
e951386e KH |
3356 | if (cmp_status->nchars == 0 \ |
3357 | || ((cmp_status->state == COMPOSING_CHAR) \ | |
3358 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ | |
ec6d2bb8 | 3359 | { \ |
e951386e KH |
3360 | MAYBE_FINISH_COMPOSITION (); \ |
3361 | goto invalid_code; \ | |
ec6d2bb8 | 3362 | } \ |
e951386e KH |
3363 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
3364 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ | |
3365 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
3366 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ | |
3367 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ | |
3368 | char_offset += cmp_status->nchars; \ | |
3369 | cmp_status->state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3370 | } while (0) |
3371 | ||
e951386e | 3372 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ |
df7492f9 | 3373 | |
e951386e KH |
3374 | #define STORE_COMPOSITION_RULE(rule) \ |
3375 | do { \ | |
3376 | *charbuf++ = -2; \ | |
3377 | *charbuf++ = rule; \ | |
3378 | cmp_status->length += 2; \ | |
3379 | cmp_status->state--; \ | |
3380 | } while (0) | |
ec6d2bb8 | 3381 | |
e951386e KH |
3382 | /* Store a composed char or a component char C in charbuf, and update |
3383 | cmp_status. */ | |
3384 | ||
3385 | #define STORE_COMPOSITION_CHAR(c) \ | |
ec6d2bb8 | 3386 | do { \ |
e951386e KH |
3387 | *charbuf++ = (c); \ |
3388 | cmp_status->length++; \ | |
3389 | if (cmp_status->state == COMPOSING_CHAR) \ | |
3390 | cmp_status->nchars++; \ | |
df7492f9 | 3391 | else \ |
e951386e KH |
3392 | cmp_status->ncomps++; \ |
3393 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | |
3394 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | |
3395 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | |
3396 | cmp_status->state++; \ | |
ec6d2bb8 | 3397 | } while (0) |
88993dfd | 3398 | |
d46c5b12 | 3399 | |
4ed46869 KH |
3400 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3401 | ||
b73bfc1c | 3402 | static void |
971de7fb | 3403 | decode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 3404 | { |
8f924df7 KH |
3405 | const unsigned char *src = coding->source + coding->consumed; |
3406 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3407 | const unsigned char *src_base; | |
69a80ea3 | 3408 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
3409 | /* We may produce two annotations (charset and composition) in one |
3410 | loop and one more charset annotation at the end. */ | |
ff0dacd7 | 3411 | int *charbuf_end |
df80c7f0 | 3412 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
d311d28c | 3413 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 3414 | bool multibytep = coding->src_multibyte; |
4ed46869 | 3415 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3416 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3417 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3418 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3419 | struct charset *charset; |
3420 | int c; | |
e951386e | 3421 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
66ebf983 | 3422 | Lisp_Object attrs = CODING_ID_ATTRS (coding->id); |
d311d28c PE |
3423 | ptrdiff_t char_offset = coding->produced_char; |
3424 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 3425 | int last_id = charset_ascii; |
f10fe38f PE |
3426 | bool eol_dos |
3427 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 3428 | int byte_after_cr = -1; |
e951386e | 3429 | int i; |
df7492f9 | 3430 | |
df7492f9 | 3431 | setup_iso_safe_charsets (attrs); |
1b3b981b | 3432 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
b73bfc1c | 3433 | |
e951386e KH |
3434 | if (cmp_status->state != COMPOSING_NO) |
3435 | { | |
15cbd324 | 3436 | if (charbuf_end - charbuf < cmp_status->length) |
1088b922 | 3437 | emacs_abort (); |
e951386e KH |
3438 | for (i = 0; i < cmp_status->length; i++) |
3439 | *charbuf++ = cmp_status->carryover[i]; | |
3440 | coding->annotated = 1; | |
3441 | } | |
3442 | ||
b73bfc1c | 3443 | while (1) |
4ed46869 | 3444 | { |
cf299835 | 3445 | int c1, c2, c3; |
b73bfc1c KH |
3446 | |
3447 | src_base = src; | |
df7492f9 KH |
3448 | consumed_chars_base = consumed_chars; |
3449 | ||
3450 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3451 | { |
3452 | if (byte_after_cr >= 0) | |
3453 | src_base--; | |
3454 | break; | |
3455 | } | |
df7492f9 | 3456 | |
119852e7 KH |
3457 | if (byte_after_cr >= 0) |
3458 | c1 = byte_after_cr, byte_after_cr = -1; | |
3459 | else | |
3460 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3461 | if (c1 < 0) |
3462 | goto invalid_code; | |
4ed46869 | 3463 | |
e951386e | 3464 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
4ed46869 | 3465 | { |
e951386e KH |
3466 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
3467 | char_offset++; | |
3468 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | |
3469 | continue; | |
3470 | } | |
3471 | ||
3472 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | |
3473 | { | |
3474 | if (c1 == ISO_CODE_ESC) | |
ec6d2bb8 | 3475 | { |
e951386e KH |
3476 | if (src + 1 >= src_end) |
3477 | goto no_more_source; | |
3478 | *charbuf++ = ISO_CODE_ESC; | |
3479 | char_offset++; | |
3480 | if (src[0] == '%' && src[1] == '@') | |
df7492f9 | 3481 | { |
e951386e KH |
3482 | src += 2; |
3483 | consumed_chars += 2; | |
3484 | char_offset += 2; | |
3485 | /* We are sure charbuf can contain two more chars. */ | |
3486 | *charbuf++ = '%'; | |
3487 | *charbuf++ = '@'; | |
3488 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
df7492f9 | 3489 | } |
4ed46869 | 3490 | } |
e951386e KH |
3491 | else |
3492 | { | |
3493 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
3494 | char_offset++; | |
3495 | } | |
3496 | continue; | |
3497 | } | |
3498 | ||
3499 | if ((cmp_status->state == COMPOSING_RULE | |
3500 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | |
3501 | && c1 != ISO_CODE_ESC) | |
3502 | { | |
66ebf983 | 3503 | int rule; |
e951386e | 3504 | |
66ebf983 | 3505 | DECODE_COMPOSITION_RULE (rule); |
e951386e KH |
3506 | STORE_COMPOSITION_RULE (rule); |
3507 | continue; | |
3508 | } | |
3509 | ||
3510 | /* We produce at most one character. */ | |
3511 | switch (iso_code_class [c1]) | |
3512 | { | |
3513 | case ISO_0x20_or_0x7F: | |
df7492f9 KH |
3514 | if (charset_id_0 < 0 |
3515 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3516 | /* This is SPACE or DEL. */ |
3517 | charset = CHARSET_FROM_ID (charset_ascii); | |
3518 | else | |
3519 | charset = CHARSET_FROM_ID (charset_id_0); | |
3520 | break; | |
4ed46869 KH |
3521 | |
3522 | case ISO_graphic_plane_0: | |
134b9549 KH |
3523 | if (charset_id_0 < 0) |
3524 | charset = CHARSET_FROM_ID (charset_ascii); | |
3525 | else | |
3526 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3527 | break; |
3528 | ||
3529 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3530 | if (charset_id_1 < 0 |
3531 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3532 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3533 | goto invalid_code; | |
4ed46869 KH |
3534 | /* This is a graphic character, we fall down ... */ |
3535 | ||
3536 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3537 | if (charset_id_1 < 0) |
3538 | goto invalid_code; | |
3539 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3540 | break; |
3541 | ||
df7492f9 | 3542 | case ISO_control_0: |
2735d060 | 3543 | if (eol_dos && c1 == '\r') |
119852e7 | 3544 | ONE_MORE_BYTE (byte_after_cr); |
df7492f9 KH |
3545 | MAYBE_FINISH_COMPOSITION (); |
3546 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3547 | break; |
3548 | ||
df7492f9 | 3549 | case ISO_control_1: |
df7492f9 KH |
3550 | goto invalid_code; |
3551 | ||
4ed46869 | 3552 | case ISO_shift_out: |
df7492f9 KH |
3553 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3554 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3555 | goto invalid_code; | |
3556 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3557 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3558 | continue; |
4ed46869 KH |
3559 | |
3560 | case ISO_shift_in: | |
df7492f9 KH |
3561 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3562 | goto invalid_code; | |
3563 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3564 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3565 | continue; |
4ed46869 KH |
3566 | |
3567 | case ISO_single_shift_2_7: | |
a63dba42 KH |
3568 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)) |
3569 | goto invalid_code; | |
4ed46869 | 3570 | case ISO_single_shift_2: |
df7492f9 KH |
3571 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3572 | goto invalid_code; | |
4ed46869 KH |
3573 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3574 | c1 = 'N'; | |
3575 | goto label_escape_sequence; | |
3576 | ||
3577 | case ISO_single_shift_3: | |
df7492f9 KH |
3578 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3579 | goto invalid_code; | |
4ed46869 KH |
3580 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3581 | c1 = 'O'; | |
3582 | goto label_escape_sequence; | |
3583 | ||
3584 | case ISO_control_sequence_introducer: | |
3585 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3586 | c1 = '['; | |
3587 | goto label_escape_sequence; | |
3588 | ||
3589 | case ISO_escape: | |
3590 | ONE_MORE_BYTE (c1); | |
3591 | label_escape_sequence: | |
df7492f9 | 3592 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3593 | designation, direction specification, and character |
3594 | composition specification. */ | |
3595 | switch (c1) | |
3596 | { | |
3597 | case '&': /* revision of following character set */ | |
3598 | ONE_MORE_BYTE (c1); | |
3599 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3600 | goto invalid_code; |
4ed46869 KH |
3601 | ONE_MORE_BYTE (c1); |
3602 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3603 | goto invalid_code; |
4ed46869 KH |
3604 | ONE_MORE_BYTE (c1); |
3605 | goto label_escape_sequence; | |
3606 | ||
3607 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3608 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3609 | goto invalid_code; | |
134b9549 KH |
3610 | { |
3611 | int reg, chars96; | |
3612 | ||
3613 | ONE_MORE_BYTE (c1); | |
3614 | if (c1 >= '@' && c1 <= 'B') | |
3615 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3616 | or JISX0208.1980 */ |
134b9549 KH |
3617 | reg = 0, chars96 = 0; |
3618 | } | |
3619 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3620 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3621 | reg = c1 - 0x28, chars96 = 0; | |
3622 | ONE_MORE_BYTE (c1); | |
3623 | } | |
3624 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3625 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3626 | reg = c1 - 0x2C, chars96 = 1; | |
3627 | ONE_MORE_BYTE (c1); | |
3628 | } | |
3629 | else | |
3630 | goto invalid_code; | |
3631 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3632 | /* We must update these variables now. */ | |
3633 | if (reg == 0) | |
3634 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3635 | else if (reg == 1) | |
3636 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3637 | if (chars96 < 0) | |
3638 | goto invalid_code; | |
3639 | } | |
b73bfc1c | 3640 | continue; |
4ed46869 KH |
3641 | |
3642 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3643 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3644 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3645 | goto invalid_code; | |
3646 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3647 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3648 | continue; |
4ed46869 KH |
3649 | |
3650 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3651 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3652 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3653 | goto invalid_code; | |
3654 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3655 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3656 | continue; |
4ed46869 KH |
3657 | |
3658 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3659 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3660 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3661 | goto invalid_code; | |
134b9549 KH |
3662 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3663 | if (charset_id_2 < 0) | |
3664 | charset = CHARSET_FROM_ID (charset_ascii); | |
3665 | else | |
3666 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3667 | ONE_MORE_BYTE (c1); |
e7046a18 | 3668 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3669 | goto invalid_code; |
4ed46869 KH |
3670 | break; |
3671 | ||
3672 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3673 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3674 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3675 | goto invalid_code; | |
134b9549 KH |
3676 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3677 | if (charset_id_3 < 0) | |
3678 | charset = CHARSET_FROM_ID (charset_ascii); | |
3679 | else | |
3680 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3681 | ONE_MORE_BYTE (c1); |
e7046a18 | 3682 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3683 | goto invalid_code; |
4ed46869 KH |
3684 | break; |
3685 | ||
ec6d2bb8 | 3686 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3687 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3688 | goto invalid_code; | |
e951386e KH |
3689 | if (last_id != charset_ascii) |
3690 | { | |
3691 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | |
3692 | last_id = charset_ascii; | |
3693 | last_offset = char_offset; | |
3694 | } | |
ec6d2bb8 | 3695 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3696 | continue; |
4ed46869 | 3697 | |
ec6d2bb8 | 3698 | case '1': /* end composition */ |
e951386e | 3699 | if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3700 | goto invalid_code; |
3701 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3702 | continue; |
4ed46869 KH |
3703 | |
3704 | case '[': /* specification of direction */ | |
de59072a | 3705 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)) |
df7492f9 | 3706 | goto invalid_code; |
4ed46869 | 3707 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3708 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
ad1746f5 | 3709 | left-to-right, and nonzero means right-to-left. */ |
4ed46869 KH |
3710 | ONE_MORE_BYTE (c1); |
3711 | switch (c1) | |
3712 | { | |
3713 | case ']': /* end of the current direction */ | |
d46c5b12 | 3714 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3715 | |
3716 | case '0': /* end of the current direction */ | |
3717 | case '1': /* start of left-to-right direction */ | |
3718 | ONE_MORE_BYTE (c1); | |
3719 | if (c1 == ']') | |
d46c5b12 | 3720 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3721 | else |
df7492f9 | 3722 | goto invalid_code; |
4ed46869 KH |
3723 | break; |
3724 | ||
3725 | case '2': /* start of right-to-left direction */ | |
3726 | ONE_MORE_BYTE (c1); | |
3727 | if (c1 == ']') | |
d46c5b12 | 3728 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3729 | else |
df7492f9 | 3730 | goto invalid_code; |
4ed46869 KH |
3731 | break; |
3732 | ||
3733 | default: | |
df7492f9 | 3734 | goto invalid_code; |
4ed46869 | 3735 | } |
b73bfc1c | 3736 | continue; |
4ed46869 | 3737 | |
103e0180 | 3738 | case '%': |
103e0180 KH |
3739 | ONE_MORE_BYTE (c1); |
3740 | if (c1 == '/') | |
3741 | { | |
3742 | /* CTEXT extended segment: | |
3743 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3744 | We keep these bytes as is for the moment. | |
3745 | They may be decoded by post-read-conversion. */ | |
3746 | int dim, M, L; | |
4776e638 | 3747 | int size; |
8f924df7 | 3748 | |
103e0180 | 3749 | ONE_MORE_BYTE (dim); |
7a84eee5 | 3750 | if (dim < '0' || dim > '4') |
e951386e | 3751 | goto invalid_code; |
103e0180 | 3752 | ONE_MORE_BYTE (M); |
e951386e KH |
3753 | if (M < 128) |
3754 | goto invalid_code; | |
103e0180 | 3755 | ONE_MORE_BYTE (L); |
e951386e KH |
3756 | if (L < 128) |
3757 | goto invalid_code; | |
103e0180 | 3758 | size = ((M - 128) * 128) + (L - 128); |
e951386e | 3759 | if (charbuf + 6 > charbuf_end) |
4776e638 KH |
3760 | goto break_loop; |
3761 | *charbuf++ = ISO_CODE_ESC; | |
3762 | *charbuf++ = '%'; | |
3763 | *charbuf++ = '/'; | |
3764 | *charbuf++ = dim; | |
3765 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3766 | *charbuf++ = BYTE8_TO_CHAR (L); | |
e951386e | 3767 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
103e0180 KH |
3768 | } |
3769 | else if (c1 == 'G') | |
3770 | { | |
103e0180 KH |
3771 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3772 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3773 | We keep these bytes as is for the moment. | |
3774 | They may be decoded by post-read-conversion. */ | |
e951386e | 3775 | if (charbuf + 3 > charbuf_end) |
4776e638 | 3776 | goto break_loop; |
e951386e KH |
3777 | *charbuf++ = ISO_CODE_ESC; |
3778 | *charbuf++ = '%'; | |
3779 | *charbuf++ = 'G'; | |
3780 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; | |
103e0180 KH |
3781 | } |
3782 | else | |
4776e638 | 3783 | goto invalid_code; |
103e0180 | 3784 | continue; |
4776e638 | 3785 | break; |
103e0180 | 3786 | |
4ed46869 | 3787 | default: |
df7492f9 KH |
3788 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3789 | goto invalid_code; | |
134b9549 KH |
3790 | { |
3791 | int reg, chars96; | |
3792 | ||
3793 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3794 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3795 | reg = c1 - 0x28, chars96 = 0; | |
3796 | ONE_MORE_BYTE (c1); | |
3797 | } | |
3798 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3799 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3800 | reg = c1 - 0x2C, chars96 = 1; | |
3801 | ONE_MORE_BYTE (c1); | |
3802 | } | |
3803 | else | |
3804 | goto invalid_code; | |
3805 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3806 | /* We must update these variables now. */ | |
3807 | if (reg == 0) | |
3808 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3809 | else if (reg == 1) | |
3810 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3811 | if (chars96 < 0) | |
3812 | goto invalid_code; | |
3813 | } | |
b73bfc1c | 3814 | continue; |
4ed46869 | 3815 | } |
413bb2db PE |
3816 | break; |
3817 | ||
3818 | default: | |
1088b922 | 3819 | emacs_abort (); |
b73bfc1c | 3820 | } |
4ed46869 | 3821 | |
e951386e KH |
3822 | if (cmp_status->state == COMPOSING_NO |
3823 | && charset->id != charset_ascii | |
ff0dacd7 KH |
3824 | && last_id != charset->id) |
3825 | { | |
3826 | if (last_id != charset_ascii) | |
69a80ea3 | 3827 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3828 | last_id = charset->id; |
3829 | last_offset = char_offset; | |
3830 | } | |
3831 | ||
b73bfc1c | 3832 | /* Now we know CHARSET and 1st position code C1 of a character. |
cf299835 KH |
3833 | Produce a decoded character while getting 2nd and 3rd |
3834 | position codes C2, C3 if necessary. */ | |
df7492f9 | 3835 | if (CHARSET_DIMENSION (charset) > 1) |
b73bfc1c KH |
3836 | { |
3837 | ONE_MORE_BYTE (c2); | |
cf299835 KH |
3838 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0) |
3839 | || ((c1 & 0x80) != (c2 & 0x80))) | |
b73bfc1c | 3840 | /* C2 is not in a valid range. */ |
df7492f9 | 3841 | goto invalid_code; |
cf299835 KH |
3842 | if (CHARSET_DIMENSION (charset) == 2) |
3843 | c1 = (c1 << 8) | c2; | |
3844 | else | |
df7492f9 | 3845 | { |
cf299835 KH |
3846 | ONE_MORE_BYTE (c3); |
3847 | if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0) | |
3848 | || ((c1 & 0x80) != (c3 & 0x80))) | |
3849 | /* C3 is not in a valid range. */ | |
df7492f9 | 3850 | goto invalid_code; |
cf299835 | 3851 | c1 = (c1 << 16) | (c2 << 8) | c2; |
df7492f9 KH |
3852 | } |
3853 | } | |
cf299835 | 3854 | c1 &= 0x7F7F7F; |
df7492f9 KH |
3855 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); |
3856 | if (c < 0) | |
3857 | { | |
3858 | MAYBE_FINISH_COMPOSITION (); | |
3859 | for (; src_base < src; src_base++, char_offset++) | |
3860 | { | |
3861 | if (ASCII_BYTE_P (*src_base)) | |
3862 | *charbuf++ = *src_base; | |
3863 | else | |
3864 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3865 | } | |
3866 | } | |
e951386e | 3867 | else if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3868 | { |
3869 | *charbuf++ = c; | |
3870 | char_offset++; | |
4ed46869 | 3871 | } |
e951386e KH |
3872 | else if ((cmp_status->state == COMPOSING_CHAR |
3873 | ? cmp_status->nchars | |
3874 | : cmp_status->ncomps) | |
3875 | >= MAX_COMPOSITION_COMPONENTS) | |
781d7a48 | 3876 | { |
e951386e KH |
3877 | /* Too long composition. */ |
3878 | MAYBE_FINISH_COMPOSITION (); | |
3879 | *charbuf++ = c; | |
3880 | char_offset++; | |
4ed46869 | 3881 | } |
e951386e KH |
3882 | else |
3883 | STORE_COMPOSITION_CHAR (c); | |
4ed46869 KH |
3884 | continue; |
3885 | ||
df7492f9 KH |
3886 | invalid_code: |
3887 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3888 | src = src_base; |
df7492f9 KH |
3889 | consumed_chars = consumed_chars_base; |
3890 | ONE_MORE_BYTE (c); | |
065e3595 | 3891 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3892 | char_offset++; |
df7492f9 | 3893 | coding->errors++; |
4776e638 KH |
3894 | continue; |
3895 | ||
3896 | break_loop: | |
3897 | break; | |
4ed46869 | 3898 | } |
fb88bf2d | 3899 | |
df7492f9 | 3900 | no_more_source: |
e951386e KH |
3901 | if (cmp_status->state != COMPOSING_NO) |
3902 | { | |
3903 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
3904 | MAYBE_FINISH_COMPOSITION (); | |
3905 | else | |
3906 | { | |
3907 | charbuf -= cmp_status->length; | |
3908 | for (i = 0; i < cmp_status->length; i++) | |
3909 | cmp_status->carryover[i] = charbuf[i]; | |
3910 | } | |
3911 | } | |
3912 | else if (last_id != charset_ascii) | |
69a80ea3 | 3913 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3914 | coding->consumed_char += consumed_chars_base; |
3915 | coding->consumed = src_base - coding->source; | |
3916 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3917 | } |
3918 | ||
b73bfc1c | 3919 | |
f4dee582 | 3920 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3921 | |
3922 | /* | |
f4dee582 | 3923 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3924 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3925 | variant has the following specifications: |
df7492f9 | 3926 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3927 | 2. Allows short-form designation? |
3928 | 3. ASCII should be designated to G0 before control characters? | |
3929 | 4. ASCII should be designated to G0 at end of line? | |
3930 | 5. 7-bit environment or 8-bit environment? | |
3931 | 6. Use locking-shift? | |
3932 | 7. Use Single-shift? | |
3933 | And the following two are only for Japanese: | |
3934 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3935 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3936 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3937 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3938 | details. |
4ed46869 KH |
3939 | */ |
3940 | ||
3941 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3942 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3943 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3944 | designation sequence of short-form. */ | |
4ed46869 KH |
3945 | |
3946 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3947 | do { \ | |
df7492f9 | 3948 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
675e2c69 DN |
3949 | const char *intermediate_char_94 = "()*+"; \ |
3950 | const char *intermediate_char_96 = ",-./"; \ | |
df7492f9 | 3951 | int revision = -1; \ |
df7492f9 KH |
3952 | \ |
3953 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 3954 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
3955 | \ |
3956 | if (revision >= 0) \ | |
70c22245 | 3957 | { \ |
df7492f9 KH |
3958 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
3959 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 3960 | } \ |
df7492f9 | 3961 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
3962 | if (CHARSET_DIMENSION (charset) == 1) \ |
3963 | { \ | |
2735d060 | 3964 | int b; \ |
df7492f9 | 3965 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
2735d060 | 3966 | b = intermediate_char_94[reg]; \ |
4ed46869 | 3967 | else \ |
2735d060 PE |
3968 | b = intermediate_char_96[reg]; \ |
3969 | EMIT_ONE_ASCII_BYTE (b); \ | |
4ed46869 KH |
3970 | } \ |
3971 | else \ | |
3972 | { \ | |
df7492f9 KH |
3973 | EMIT_ONE_ASCII_BYTE ('$'); \ |
3974 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 3975 | { \ |
df7492f9 | 3976 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
3977 | || reg != 0 \ |
3978 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 3979 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
3980 | } \ |
3981 | else \ | |
df7492f9 | 3982 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 3983 | } \ |
df7492f9 KH |
3984 | EMIT_ONE_ASCII_BYTE (final_char); \ |
3985 | \ | |
3986 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
3987 | } while (0) |
3988 | ||
df7492f9 | 3989 | |
4ed46869 KH |
3990 | /* The following two macros produce codes (control character or escape |
3991 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
3992 | single-shift-3). */ | |
3993 | ||
df7492f9 KH |
3994 | #define ENCODE_SINGLE_SHIFT_2 \ |
3995 | do { \ | |
3996 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
3997 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
3998 | else \ | |
3999 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
4000 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4001 | } while (0) |
4002 | ||
df7492f9 KH |
4003 | |
4004 | #define ENCODE_SINGLE_SHIFT_3 \ | |
4005 | do { \ | |
4006 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4007 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
4008 | else \ | |
4009 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
4010 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4011 | } while (0) |
4012 | ||
df7492f9 | 4013 | |
4ed46869 KH |
4014 | /* The following four macros produce codes (control character or |
4015 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
4016 | shift-out, locking-shift-2, and locking-shift-3). */ | |
4017 | ||
df7492f9 KH |
4018 | #define ENCODE_SHIFT_IN \ |
4019 | do { \ | |
4020 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
4021 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
4022 | } while (0) |
4023 | ||
df7492f9 KH |
4024 | |
4025 | #define ENCODE_SHIFT_OUT \ | |
4026 | do { \ | |
4027 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
4028 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
4029 | } while (0) |
4030 | ||
df7492f9 KH |
4031 | |
4032 | #define ENCODE_LOCKING_SHIFT_2 \ | |
4033 | do { \ | |
4034 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4035 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
4036 | } while (0) |
4037 | ||
df7492f9 KH |
4038 | |
4039 | #define ENCODE_LOCKING_SHIFT_3 \ | |
4040 | do { \ | |
4041 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4042 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
4043 | } while (0) |
4044 | ||
df7492f9 | 4045 | |
f4dee582 RS |
4046 | /* Produce codes for a DIMENSION1 character whose character set is |
4047 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
4048 | sequences are also produced in advance if necessary. */ |
4049 | ||
6e85d753 KH |
4050 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
4051 | do { \ | |
df7492f9 | 4052 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4053 | \ |
4054 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
4055 | && id == charset_ascii) \ | |
4056 | { \ | |
4057 | id = charset_jisx0201_roman; \ | |
4058 | charset = CHARSET_FROM_ID (id); \ | |
4059 | } \ | |
4060 | \ | |
df7492f9 | 4061 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4062 | { \ |
df7492f9 KH |
4063 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4064 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 4065 | else \ |
df7492f9 KH |
4066 | EMIT_ONE_BYTE (c1 | 0x80); \ |
4067 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4068 | break; \ |
4069 | } \ | |
df7492f9 | 4070 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4071 | { \ |
df7492f9 | 4072 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
4073 | break; \ |
4074 | } \ | |
df7492f9 | 4075 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4076 | { \ |
df7492f9 | 4077 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
4078 | break; \ |
4079 | } \ | |
6e85d753 KH |
4080 | else \ |
4081 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4082 | must invoke it, or, at first, designate it to some graphic \ | |
4083 | register. Then repeat the loop to actually produce the \ | |
4084 | character. */ \ | |
df7492f9 KH |
4085 | dst = encode_invocation_designation (charset, coding, dst, \ |
4086 | &produced_chars); \ | |
4ed46869 KH |
4087 | } while (1) |
4088 | ||
df7492f9 | 4089 | |
f4dee582 RS |
4090 | /* Produce codes for a DIMENSION2 character whose character set is |
4091 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
4092 | invocation codes are also produced in advance if necessary. */ |
4093 | ||
6e85d753 KH |
4094 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
4095 | do { \ | |
df7492f9 | 4096 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4097 | \ |
4098 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
4099 | && id == charset_jisx0208) \ | |
4100 | { \ | |
4101 | id = charset_jisx0208_1978; \ | |
4102 | charset = CHARSET_FROM_ID (id); \ | |
4103 | } \ | |
4104 | \ | |
df7492f9 | 4105 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4106 | { \ |
df7492f9 KH |
4107 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4108 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 4109 | else \ |
df7492f9 KH |
4110 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
4111 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4112 | break; \ |
4113 | } \ | |
df7492f9 | 4114 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4115 | { \ |
df7492f9 | 4116 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
4117 | break; \ |
4118 | } \ | |
df7492f9 | 4119 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4120 | { \ |
df7492f9 | 4121 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
4122 | break; \ |
4123 | } \ | |
6e85d753 KH |
4124 | else \ |
4125 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4126 | must invoke it, or, at first, designate it to some graphic \ | |
4127 | register. Then repeat the loop to actually produce the \ | |
4128 | character. */ \ | |
df7492f9 KH |
4129 | dst = encode_invocation_designation (charset, coding, dst, \ |
4130 | &produced_chars); \ | |
4ed46869 KH |
4131 | } while (1) |
4132 | ||
05e6f5dc | 4133 | |
df7492f9 KH |
4134 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
4135 | do { \ | |
8f50130c | 4136 | unsigned code; \ |
5eb05ea3 | 4137 | CODING_ENCODE_CHAR (coding, dst, dst_end, (charset), (c), code); \ |
df7492f9 KH |
4138 | \ |
4139 | if (CHARSET_DIMENSION (charset) == 1) \ | |
4140 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
4141 | else \ | |
4142 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 4143 | } while (0) |
bdd9fb48 | 4144 | |
05e6f5dc | 4145 | |
4ed46869 | 4146 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 4147 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
4148 | Return new DST. */ |
4149 | ||
e2f1bab9 | 4150 | static unsigned char * |
cf84bb53 JB |
4151 | encode_invocation_designation (struct charset *charset, |
4152 | struct coding_system *coding, | |
d311d28c | 4153 | unsigned char *dst, ptrdiff_t *p_nchars) |
4ed46869 | 4154 | { |
f10fe38f | 4155 | bool multibytep = coding->dst_multibyte; |
d311d28c | 4156 | ptrdiff_t produced_chars = *p_nchars; |
4ed46869 | 4157 | int reg; /* graphic register number */ |
df7492f9 | 4158 | int id = CHARSET_ID (charset); |
4ed46869 KH |
4159 | |
4160 | /* At first, check designations. */ | |
4161 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 4162 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
4163 | break; |
4164 | ||
4165 | if (reg >= 4) | |
4166 | { | |
4167 | /* CHARSET is not yet designated to any graphic registers. */ | |
4168 | /* At first check the requested designation. */ | |
df7492f9 KH |
4169 | reg = CODING_ISO_REQUEST (coding, id); |
4170 | if (reg < 0) | |
1ba9e4ab KH |
4171 | /* Since CHARSET requests no special designation, designate it |
4172 | to graphic register 0. */ | |
4ed46869 KH |
4173 | reg = 0; |
4174 | ||
4175 | ENCODE_DESIGNATION (charset, reg, coding); | |
4176 | } | |
4177 | ||
df7492f9 KH |
4178 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
4179 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
4180 | { |
4181 | /* Since the graphic register REG is not invoked to any graphic | |
4182 | planes, invoke it to graphic plane 0. */ | |
4183 | switch (reg) | |
4184 | { | |
4185 | case 0: /* graphic register 0 */ | |
4186 | ENCODE_SHIFT_IN; | |
4187 | break; | |
4188 | ||
4189 | case 1: /* graphic register 1 */ | |
4190 | ENCODE_SHIFT_OUT; | |
4191 | break; | |
4192 | ||
4193 | case 2: /* graphic register 2 */ | |
df7492f9 | 4194 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4195 | ENCODE_SINGLE_SHIFT_2; |
4196 | else | |
4197 | ENCODE_LOCKING_SHIFT_2; | |
4198 | break; | |
4199 | ||
4200 | case 3: /* graphic register 3 */ | |
df7492f9 | 4201 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4202 | ENCODE_SINGLE_SHIFT_3; |
4203 | else | |
4204 | ENCODE_LOCKING_SHIFT_3; | |
4205 | break; | |
4206 | } | |
4207 | } | |
b73bfc1c | 4208 | |
df7492f9 | 4209 | *p_nchars = produced_chars; |
4ed46869 KH |
4210 | return dst; |
4211 | } | |
4212 | ||
4ed46869 KH |
4213 | |
4214 | /* Produce codes for designation and invocation to reset the graphic | |
4215 | planes and registers to initial state. */ | |
df7492f9 KH |
4216 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4217 | do { \ | |
4218 | int reg; \ | |
4219 | struct charset *charset; \ | |
4220 | \ | |
4221 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4222 | ENCODE_SHIFT_IN; \ | |
4223 | for (reg = 0; reg < 4; reg++) \ | |
4224 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4225 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4226 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4227 | { \ | |
4228 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4229 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4230 | } \ | |
4ed46869 KH |
4231 | } while (0) |
4232 | ||
df7492f9 | 4233 | |
bdd9fb48 | 4234 | /* Produce designation sequences of charsets in the line started from |
5eb05ea3 KH |
4235 | CHARBUF to a place pointed by DST, and return the number of |
4236 | produced bytes. DST should not directly point a buffer text area | |
4237 | which may be relocated by char_charset call. | |
bdd9fb48 KH |
4238 | |
4239 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4240 | find all the necessary designations. */ |
4241 | ||
6e6c82a4 | 4242 | static ptrdiff_t |
5eb05ea3 KH |
4243 | encode_designation_at_bol (struct coding_system *coding, |
4244 | int *charbuf, int *charbuf_end, | |
461c2ab9 | 4245 | unsigned char *dst) |
e0e989f6 | 4246 | { |
75a3b399 | 4247 | unsigned char *orig = dst; |
df7492f9 | 4248 | struct charset *charset; |
bdd9fb48 KH |
4249 | /* Table of charsets to be designated to each graphic register. */ |
4250 | int r[4]; | |
df7492f9 | 4251 | int c, found = 0, reg; |
d311d28c | 4252 | ptrdiff_t produced_chars = 0; |
f10fe38f | 4253 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4254 | Lisp_Object attrs; |
4255 | Lisp_Object charset_list; | |
4256 | ||
4257 | attrs = CODING_ID_ATTRS (coding->id); | |
4258 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4259 | if (EQ (charset_list, Qiso_2022)) | |
4260 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4261 | |
4262 | for (reg = 0; reg < 4; reg++) | |
4263 | r[reg] = -1; | |
4264 | ||
5eb05ea3 | 4265 | while (charbuf < charbuf_end && found < 4) |
e0e989f6 | 4266 | { |
df7492f9 KH |
4267 | int id; |
4268 | ||
4269 | c = *charbuf++; | |
b73bfc1c KH |
4270 | if (c == '\n') |
4271 | break; | |
df7492f9 KH |
4272 | charset = char_charset (c, charset_list, NULL); |
4273 | id = CHARSET_ID (charset); | |
4274 | reg = CODING_ISO_REQUEST (coding, id); | |
4275 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4276 | { |
4277 | found++; | |
df7492f9 | 4278 | r[reg] = id; |
bdd9fb48 | 4279 | } |
bdd9fb48 KH |
4280 | } |
4281 | ||
4282 | if (found) | |
4283 | { | |
4284 | for (reg = 0; reg < 4; reg++) | |
4285 | if (r[reg] >= 0 | |
df7492f9 KH |
4286 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4287 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4288 | } |
b73bfc1c | 4289 | |
5eb05ea3 | 4290 | return dst - orig; |
e0e989f6 KH |
4291 | } |
4292 | ||
4ed46869 KH |
4293 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4294 | ||
f10fe38f | 4295 | static bool |
971de7fb | 4296 | encode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 4297 | { |
f10fe38f | 4298 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4299 | int *charbuf = coding->charbuf; |
4300 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4301 | unsigned char *dst = coding->destination + coding->produced; | |
4302 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4303 | int safe_room = 16; | |
f10fe38f | 4304 | bool bol_designation |
df7492f9 KH |
4305 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL |
4306 | && CODING_ISO_BOL (coding)); | |
d311d28c | 4307 | ptrdiff_t produced_chars = 0; |
df7492f9 | 4308 | Lisp_Object attrs, eol_type, charset_list; |
f10fe38f | 4309 | bool ascii_compatible; |
b73bfc1c | 4310 | int c; |
ff0dacd7 | 4311 | int preferred_charset_id = -1; |
05e6f5dc | 4312 | |
24a73b0a | 4313 | CODING_GET_INFO (coding, attrs, charset_list); |
0a9564cb | 4314 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
24a73b0a KH |
4315 | if (VECTORP (eol_type)) |
4316 | eol_type = Qunix; | |
4317 | ||
004068e4 | 4318 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4319 | /* Charset list may have been changed. */ |
287c57d7 | 4320 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
1b3b981b | 4321 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
0eecad43 | 4322 | |
a552b35a KH |
4323 | ascii_compatible |
4324 | = (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)) | |
4325 | && ! (CODING_ISO_FLAGS (coding) & (CODING_ISO_FLAG_DESIGNATION | |
4326 | | CODING_ISO_FLAG_LOCKING_SHIFT))); | |
bdd9fb48 | 4327 | |
df7492f9 | 4328 | while (charbuf < charbuf_end) |
4ed46869 | 4329 | { |
df7492f9 | 4330 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4331 | |
df7492f9 | 4332 | if (bol_designation) |
b73bfc1c | 4333 | { |
bdd9fb48 | 4334 | /* We have to produce designation sequences if any now. */ |
5eb05ea3 KH |
4335 | unsigned char desig_buf[16]; |
4336 | int nbytes; | |
8f50130c | 4337 | ptrdiff_t offset; |
5eb05ea3 KH |
4338 | |
4339 | charset_map_loaded = 0; | |
4340 | nbytes = encode_designation_at_bol (coding, charbuf, charbuf_end, | |
4341 | desig_buf); | |
4342 | if (charset_map_loaded | |
c1892f11 | 4343 | && (offset = coding_change_destination (coding))) |
5eb05ea3 KH |
4344 | { |
4345 | dst += offset; | |
4346 | dst_end += offset; | |
4347 | } | |
4348 | memcpy (dst, desig_buf, nbytes); | |
4349 | dst += nbytes; | |
df7492f9 | 4350 | /* We are sure that designation sequences are all ASCII bytes. */ |
5eb05ea3 KH |
4351 | produced_chars += nbytes; |
4352 | bol_designation = 0; | |
4353 | ASSURE_DESTINATION (safe_room); | |
e0e989f6 KH |
4354 | } |
4355 | ||
df7492f9 | 4356 | c = *charbuf++; |
ec6d2bb8 | 4357 | |
ff0dacd7 KH |
4358 | if (c < 0) |
4359 | { | |
4360 | /* Handle an annotation. */ | |
4361 | switch (*charbuf) | |
ec6d2bb8 | 4362 | { |
ff0dacd7 KH |
4363 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4364 | /* Not yet implemented. */ | |
4365 | break; | |
4366 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4367 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4368 | if (preferred_charset_id >= 0 |
4369 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4370 | charset_list))) | |
4371 | preferred_charset_id = -1; | |
4372 | break; | |
4373 | default: | |
1088b922 | 4374 | emacs_abort (); |
4ed46869 | 4375 | } |
ff0dacd7 KH |
4376 | charbuf += -c - 1; |
4377 | continue; | |
4ed46869 | 4378 | } |
ec6d2bb8 | 4379 | |
b73bfc1c KH |
4380 | /* Now encode the character C. */ |
4381 | if (c < 0x20 || c == 0x7F) | |
4382 | { | |
df7492f9 KH |
4383 | if (c == '\n' |
4384 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4385 | { |
df7492f9 KH |
4386 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4387 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4388 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4389 | { |
df7492f9 KH |
4390 | int i; |
4391 | ||
4392 | for (i = 0; i < 4; i++) | |
4393 | CODING_ISO_DESIGNATION (coding, i) | |
4394 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4395 | } |
f10fe38f PE |
4396 | bol_designation = ((CODING_ISO_FLAGS (coding) |
4397 | & CODING_ISO_FLAG_DESIGNATE_AT_BOL) | |
4398 | != 0); | |
19a8d9e0 | 4399 | } |
df7492f9 KH |
4400 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4401 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4402 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4403 | } |
df7492f9 | 4404 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4405 | { |
df7492f9 KH |
4406 | if (ascii_compatible) |
4407 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4408 | else |
19a8d9e0 | 4409 | { |
bf16eb23 KH |
4410 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4411 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4412 | } |
4ed46869 | 4413 | } |
16eafb5d | 4414 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4415 | { |
16eafb5d KH |
4416 | c = CHAR_TO_BYTE8 (c); |
4417 | EMIT_ONE_BYTE (c); | |
88993dfd | 4418 | } |
b73bfc1c | 4419 | else |
df7492f9 | 4420 | { |
ff0dacd7 | 4421 | struct charset *charset; |
b73bfc1c | 4422 | |
ff0dacd7 KH |
4423 | if (preferred_charset_id >= 0) |
4424 | { | |
f10fe38f | 4425 | bool result; |
5eb05ea3 | 4426 | |
ff0dacd7 | 4427 | charset = CHARSET_FROM_ID (preferred_charset_id); |
5eb05ea3 KH |
4428 | CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result); |
4429 | if (! result) | |
4430 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4431 | NULL, charset); | |
ff0dacd7 KH |
4432 | } |
4433 | else | |
5eb05ea3 KH |
4434 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
4435 | NULL, charset); | |
df7492f9 KH |
4436 | if (!charset) |
4437 | { | |
41cbe562 KH |
4438 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4439 | { | |
4440 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4441 | charset = CHARSET_FROM_ID (charset_ascii); | |
4442 | } | |
4443 | else | |
4444 | { | |
4445 | c = coding->default_char; | |
5eb05ea3 KH |
4446 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4447 | charset_list, NULL, charset); | |
41cbe562 | 4448 | } |
df7492f9 KH |
4449 | } |
4450 | ENCODE_ISO_CHARACTER (charset, c); | |
4451 | } | |
84fbb8a0 | 4452 | } |
b73bfc1c | 4453 | |
df7492f9 KH |
4454 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4455 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4456 | { | |
4457 | ASSURE_DESTINATION (safe_room); | |
4458 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4459 | } | |
065e3595 | 4460 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4461 | CODING_ISO_BOL (coding) = bol_designation; |
4462 | coding->produced_char += produced_chars; | |
4463 | coding->produced = dst - coding->destination; | |
4464 | return 0; | |
4ed46869 KH |
4465 | } |
4466 | ||
4467 | \f | |
df7492f9 | 4468 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4469 | |
df7492f9 | 4470 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4471 | quite widely. So, for the moment, Emacs supports them in the bare |
4472 | C code. But, in the future, they may be supported only by CCL. */ | |
4473 | ||
4474 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4475 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4476 | as is. A character of charset katakana-jisx0201 is encoded by | |
4477 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4478 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4479 | so that it fit in the range below. |
4ed46869 KH |
4480 | |
4481 | --- CODE RANGE of SJIS --- | |
4482 | (character set) (range) | |
4483 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4484 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4485 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4486 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4487 | ------------------------------- |
4488 | ||
4489 | */ | |
4490 | ||
4491 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4492 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4493 | character set and is encoded in two-byte. |
4ed46869 KH |
4494 | |
4495 | --- CODE RANGE of BIG5 --- | |
4496 | (character set) (range) | |
4497 | ASCII 0x00 .. 0x7F | |
4498 | Big5 (1st byte) 0xA1 .. 0xFE | |
4499 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4500 | -------------------------- | |
4501 | ||
df7492f9 | 4502 | */ |
4ed46869 KH |
4503 | |
4504 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 4505 | Return true if a text is encoded in SJIS. */ |
4ed46869 | 4506 | |
f10fe38f | 4507 | static bool |
cf84bb53 JB |
4508 | detect_coding_sjis (struct coding_system *coding, |
4509 | struct coding_detection_info *detect_info) | |
4ed46869 | 4510 | { |
065e3595 | 4511 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4512 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 4513 | bool multibytep = coding->src_multibyte; |
d311d28c | 4514 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 4515 | int found = 0; |
b73bfc1c | 4516 | int c; |
f07190ca KH |
4517 | Lisp_Object attrs, charset_list; |
4518 | int max_first_byte_of_2_byte_code; | |
4519 | ||
4520 | CODING_GET_INFO (coding, attrs, charset_list); | |
4521 | max_first_byte_of_2_byte_code | |
4522 | = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF); | |
df7492f9 | 4523 | |
ff0dacd7 | 4524 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4525 | /* A coding system of this category is always ASCII compatible. */ |
4526 | src += coding->head_ascii; | |
4ed46869 | 4527 | |
b73bfc1c | 4528 | while (1) |
4ed46869 | 4529 | { |
065e3595 | 4530 | src_base = src; |
df7492f9 | 4531 | ONE_MORE_BYTE (c); |
682169fe KH |
4532 | if (c < 0x80) |
4533 | continue; | |
f07190ca KH |
4534 | if ((c >= 0x81 && c <= 0x9F) |
4535 | || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code)) | |
4ed46869 | 4536 | { |
df7492f9 | 4537 | ONE_MORE_BYTE (c); |
682169fe | 4538 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4539 | break; |
ff0dacd7 | 4540 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4541 | } |
df7492f9 | 4542 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4543 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4544 | else |
4545 | break; | |
4ed46869 | 4546 | } |
ff0dacd7 | 4547 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4548 | return 0; |
4549 | ||
4550 | no_more_source: | |
065e3595 | 4551 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4552 | { |
ff0dacd7 | 4553 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
89528eb3 | 4554 | return 0; |
4ed46869 | 4555 | } |
ff0dacd7 KH |
4556 | detect_info->found |= found; |
4557 | return 1; | |
4ed46869 KH |
4558 | } |
4559 | ||
4560 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 4561 | Return true if a text is encoded in BIG5. */ |
4ed46869 | 4562 | |
f10fe38f | 4563 | static bool |
cf84bb53 JB |
4564 | detect_coding_big5 (struct coding_system *coding, |
4565 | struct coding_detection_info *detect_info) | |
4ed46869 | 4566 | { |
065e3595 | 4567 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4568 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 4569 | bool multibytep = coding->src_multibyte; |
d311d28c | 4570 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 4571 | int found = 0; |
b73bfc1c | 4572 | int c; |
fa42c37f | 4573 | |
ff0dacd7 | 4574 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4575 | /* A coding system of this category is always ASCII compatible. */ |
4576 | src += coding->head_ascii; | |
fa42c37f | 4577 | |
b73bfc1c | 4578 | while (1) |
fa42c37f | 4579 | { |
065e3595 | 4580 | src_base = src; |
df7492f9 KH |
4581 | ONE_MORE_BYTE (c); |
4582 | if (c < 0x80) | |
fa42c37f | 4583 | continue; |
df7492f9 | 4584 | if (c >= 0xA1) |
fa42c37f | 4585 | { |
df7492f9 KH |
4586 | ONE_MORE_BYTE (c); |
4587 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4588 | return 0; |
ff0dacd7 | 4589 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4590 | } |
df7492f9 KH |
4591 | else |
4592 | break; | |
fa42c37f | 4593 | } |
ff0dacd7 | 4594 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4595 | return 0; |
fa42c37f | 4596 | |
df7492f9 | 4597 | no_more_source: |
065e3595 | 4598 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4599 | { |
ff0dacd7 | 4600 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4601 | return 0; |
4602 | } | |
ff0dacd7 KH |
4603 | detect_info->found |= found; |
4604 | return 1; | |
fa42c37f KH |
4605 | } |
4606 | ||
f10fe38f | 4607 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
fa42c37f | 4608 | |
b73bfc1c | 4609 | static void |
971de7fb | 4610 | decode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4611 | { |
8f924df7 KH |
4612 | const unsigned char *src = coding->source + coding->consumed; |
4613 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4614 | const unsigned char *src_base; | |
69a80ea3 | 4615 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4616 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4617 | the end. */ |
69a80ea3 | 4618 | int *charbuf_end |
df80c7f0 | 4619 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 4620 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 4621 | bool multibytep = coding->src_multibyte; |
df7492f9 | 4622 | struct charset *charset_roman, *charset_kanji, *charset_kana; |
57a47f8a | 4623 | struct charset *charset_kanji2; |
24a73b0a | 4624 | Lisp_Object attrs, charset_list, val; |
d311d28c PE |
4625 | ptrdiff_t char_offset = coding->produced_char; |
4626 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 4627 | int last_id = charset_ascii; |
f10fe38f PE |
4628 | bool eol_dos |
4629 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4630 | int byte_after_cr = -1; |
a5d301df | 4631 | |
24a73b0a | 4632 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4633 | |
4634 | val = charset_list; | |
4635 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4636 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4637 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4638 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4639 | |
b73bfc1c | 4640 | while (1) |
4ed46869 | 4641 | { |
df7492f9 | 4642 | int c, c1; |
24a73b0a | 4643 | struct charset *charset; |
fa42c37f | 4644 | |
b73bfc1c | 4645 | src_base = src; |
df7492f9 | 4646 | consumed_chars_base = consumed_chars; |
fa42c37f | 4647 | |
df7492f9 | 4648 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4649 | { |
4650 | if (byte_after_cr >= 0) | |
4651 | src_base--; | |
4652 | break; | |
4653 | } | |
df7492f9 | 4654 | |
119852e7 KH |
4655 | if (byte_after_cr >= 0) |
4656 | c = byte_after_cr, byte_after_cr = -1; | |
4657 | else | |
4658 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4659 | if (c < 0) |
4660 | goto invalid_code; | |
24a73b0a | 4661 | if (c < 0x80) |
119852e7 | 4662 | { |
2735d060 | 4663 | if (eol_dos && c == '\r') |
119852e7 KH |
4664 | ONE_MORE_BYTE (byte_after_cr); |
4665 | charset = charset_roman; | |
4666 | } | |
57a47f8a | 4667 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4668 | goto invalid_code; |
57a47f8a KH |
4669 | else if (c >= 0xA1 && c <= 0xDF) |
4670 | { | |
4671 | /* SJIS -> JISX0201-Kana */ | |
4672 | c &= 0x7F; | |
4673 | charset = charset_kana; | |
4674 | } | |
4675 | else if (c <= 0xEF) | |
df7492f9 | 4676 | { |
57a47f8a KH |
4677 | /* SJIS -> JISX0208 */ |
4678 | ONE_MORE_BYTE (c1); | |
4679 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4680 | goto invalid_code; |
57a47f8a KH |
4681 | c = (c << 8) | c1; |
4682 | SJIS_TO_JIS (c); | |
4683 | charset = charset_kanji; | |
4684 | } | |
4685 | else if (c <= 0xFC && charset_kanji2) | |
4686 | { | |
c6876370 | 4687 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4688 | ONE_MORE_BYTE (c1); |
4689 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4690 | goto invalid_code; |
57a47f8a KH |
4691 | c = (c << 8) | c1; |
4692 | SJIS_TO_JIS2 (c); | |
4693 | charset = charset_kanji2; | |
df7492f9 | 4694 | } |
57a47f8a KH |
4695 | else |
4696 | goto invalid_code; | |
24a73b0a KH |
4697 | if (charset->id != charset_ascii |
4698 | && last_id != charset->id) | |
4699 | { | |
4700 | if (last_id != charset_ascii) | |
69a80ea3 | 4701 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4702 | last_id = charset->id; |
4703 | last_offset = char_offset; | |
4704 | } | |
4705 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4706 | *charbuf++ = c; |
ff0dacd7 | 4707 | char_offset++; |
df7492f9 | 4708 | continue; |
b73bfc1c | 4709 | |
df7492f9 KH |
4710 | invalid_code: |
4711 | src = src_base; | |
4712 | consumed_chars = consumed_chars_base; | |
4713 | ONE_MORE_BYTE (c); | |
065e3595 | 4714 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4715 | char_offset++; |
df7492f9 KH |
4716 | coding->errors++; |
4717 | } | |
fa42c37f | 4718 | |
df7492f9 | 4719 | no_more_source: |
ff0dacd7 | 4720 | if (last_id != charset_ascii) |
69a80ea3 | 4721 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4722 | coding->consumed_char += consumed_chars_base; |
4723 | coding->consumed = src_base - coding->source; | |
4724 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4725 | } |
4726 | ||
b73bfc1c | 4727 | static void |
971de7fb | 4728 | decode_coding_big5 (struct coding_system *coding) |
4ed46869 | 4729 | { |
8f924df7 KH |
4730 | const unsigned char *src = coding->source + coding->consumed; |
4731 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4732 | const unsigned char *src_base; | |
69a80ea3 | 4733 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4734 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4735 | the end. */ |
69a80ea3 | 4736 | int *charbuf_end |
df80c7f0 | 4737 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 4738 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 4739 | bool multibytep = coding->src_multibyte; |
df7492f9 | 4740 | struct charset *charset_roman, *charset_big5; |
24a73b0a | 4741 | Lisp_Object attrs, charset_list, val; |
d311d28c PE |
4742 | ptrdiff_t char_offset = coding->produced_char; |
4743 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 4744 | int last_id = charset_ascii; |
f10fe38f PE |
4745 | bool eol_dos |
4746 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4747 | int byte_after_cr = -1; |
df7492f9 | 4748 | |
24a73b0a | 4749 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4750 | val = charset_list; |
4751 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4752 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4753 | |
b73bfc1c | 4754 | while (1) |
4ed46869 | 4755 | { |
df7492f9 | 4756 | int c, c1; |
24a73b0a | 4757 | struct charset *charset; |
b73bfc1c KH |
4758 | |
4759 | src_base = src; | |
df7492f9 KH |
4760 | consumed_chars_base = consumed_chars; |
4761 | ||
4762 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4763 | { |
4764 | if (byte_after_cr >= 0) | |
4765 | src_base--; | |
4766 | break; | |
4767 | } | |
df7492f9 | 4768 | |
119852e7 | 4769 | if (byte_after_cr >= 0) |
14daee73 | 4770 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4771 | else |
4772 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4773 | |
065e3595 KH |
4774 | if (c < 0) |
4775 | goto invalid_code; | |
24a73b0a | 4776 | if (c < 0x80) |
119852e7 | 4777 | { |
2735d060 | 4778 | if (eol_dos && c == '\r') |
119852e7 KH |
4779 | ONE_MORE_BYTE (byte_after_cr); |
4780 | charset = charset_roman; | |
4781 | } | |
24a73b0a | 4782 | else |
4ed46869 | 4783 | { |
24a73b0a KH |
4784 | /* BIG5 -> Big5 */ |
4785 | if (c < 0xA1 || c > 0xFE) | |
4786 | goto invalid_code; | |
4787 | ONE_MORE_BYTE (c1); | |
4788 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4789 | goto invalid_code; | |
4790 | c = c << 8 | c1; | |
4791 | charset = charset_big5; | |
4ed46869 | 4792 | } |
24a73b0a KH |
4793 | if (charset->id != charset_ascii |
4794 | && last_id != charset->id) | |
df7492f9 | 4795 | { |
24a73b0a | 4796 | if (last_id != charset_ascii) |
69a80ea3 | 4797 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4798 | last_id = charset->id; |
4799 | last_offset = char_offset; | |
4ed46869 | 4800 | } |
24a73b0a | 4801 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4802 | *charbuf++ = c; |
ff0dacd7 | 4803 | char_offset++; |
fb88bf2d KH |
4804 | continue; |
4805 | ||
df7492f9 | 4806 | invalid_code: |
4ed46869 | 4807 | src = src_base; |
df7492f9 KH |
4808 | consumed_chars = consumed_chars_base; |
4809 | ONE_MORE_BYTE (c); | |
065e3595 | 4810 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4811 | char_offset++; |
df7492f9 | 4812 | coding->errors++; |
fb88bf2d | 4813 | } |
d46c5b12 | 4814 | |
df7492f9 | 4815 | no_more_source: |
ff0dacd7 | 4816 | if (last_id != charset_ascii) |
69a80ea3 | 4817 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4818 | coding->consumed_char += consumed_chars_base; |
4819 | coding->consumed = src_base - coding->source; | |
4820 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4821 | } |
4822 | ||
4823 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4824 | This function can encode charsets `ascii', `katakana-jisx0201', |
4825 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4826 | are sure that all these charsets are registered as official charset | |
4ed46869 | 4827 | (i.e. do not have extended leading-codes). Characters of other |
f10fe38f | 4828 | charsets are produced without any encoding. */ |
4ed46869 | 4829 | |
f10fe38f | 4830 | static bool |
971de7fb | 4831 | encode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4832 | { |
f10fe38f | 4833 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4834 | int *charbuf = coding->charbuf; |
4835 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4836 | unsigned char *dst = coding->destination + coding->produced; | |
4837 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4838 | int safe_room = 4; | |
d311d28c | 4839 | ptrdiff_t produced_chars = 0; |
24a73b0a | 4840 | Lisp_Object attrs, charset_list, val; |
f10fe38f | 4841 | bool ascii_compatible; |
66ebf983 | 4842 | struct charset *charset_kanji, *charset_kana; |
57a47f8a | 4843 | struct charset *charset_kanji2; |
df7492f9 | 4844 | int c; |
a5d301df | 4845 | |
24a73b0a | 4846 | CODING_GET_INFO (coding, attrs, charset_list); |
66ebf983 | 4847 | val = XCDR (charset_list); |
df7492f9 | 4848 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4849 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4850 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4851 | |
df7492f9 | 4852 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4853 | |
df7492f9 KH |
4854 | while (charbuf < charbuf_end) |
4855 | { | |
4856 | ASSURE_DESTINATION (safe_room); | |
4857 | c = *charbuf++; | |
b73bfc1c | 4858 | /* Now encode the character C. */ |
df7492f9 KH |
4859 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4860 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4861 | else if (CHAR_BYTE8_P (c)) |
4862 | { | |
4863 | c = CHAR_TO_BYTE8 (c); | |
4864 | EMIT_ONE_BYTE (c); | |
4865 | } | |
df7492f9 | 4866 | else |
b73bfc1c | 4867 | { |
df7492f9 | 4868 | unsigned code; |
5eb05ea3 KH |
4869 | struct charset *charset; |
4870 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4871 | &code, charset); | |
df7492f9 KH |
4872 | |
4873 | if (!charset) | |
4ed46869 | 4874 | { |
41cbe562 | 4875 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4876 | { |
41cbe562 KH |
4877 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4878 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4879 | } |
41cbe562 | 4880 | else |
b73bfc1c | 4881 | { |
41cbe562 | 4882 | c = coding->default_char; |
5eb05ea3 KH |
4883 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4884 | charset_list, &code, charset); | |
b73bfc1c | 4885 | } |
b73bfc1c | 4886 | } |
df7492f9 | 4887 | if (code == CHARSET_INVALID_CODE (charset)) |
1088b922 | 4888 | emacs_abort (); |
df7492f9 KH |
4889 | if (charset == charset_kanji) |
4890 | { | |
4891 | int c1, c2; | |
4892 | JIS_TO_SJIS (code); | |
4893 | c1 = code >> 8, c2 = code & 0xFF; | |
4894 | EMIT_TWO_BYTES (c1, c2); | |
4895 | } | |
4896 | else if (charset == charset_kana) | |
4897 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4898 | else if (charset_kanji2 && charset == charset_kanji2) |
4899 | { | |
4900 | int c1, c2; | |
4901 | ||
4902 | c1 = code >> 8; | |
f07190ca KH |
4903 | if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25) |
4904 | || c1 == 0x28 | |
57a47f8a KH |
4905 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) |
4906 | { | |
4907 | JIS_TO_SJIS2 (code); | |
4908 | c1 = code >> 8, c2 = code & 0xFF; | |
4909 | EMIT_TWO_BYTES (c1, c2); | |
4910 | } | |
4911 | else | |
4912 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4913 | } | |
df7492f9 KH |
4914 | else |
4915 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4916 | } | |
4917 | } | |
065e3595 | 4918 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4919 | coding->produced_char += produced_chars; |
4920 | coding->produced = dst - coding->destination; | |
4921 | return 0; | |
4922 | } | |
4923 | ||
f10fe38f | 4924 | static bool |
971de7fb | 4925 | encode_coding_big5 (struct coding_system *coding) |
df7492f9 | 4926 | { |
f10fe38f | 4927 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4928 | int *charbuf = coding->charbuf; |
4929 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4930 | unsigned char *dst = coding->destination + coding->produced; | |
4931 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4932 | int safe_room = 4; | |
d311d28c | 4933 | ptrdiff_t produced_chars = 0; |
24a73b0a | 4934 | Lisp_Object attrs, charset_list, val; |
f10fe38f | 4935 | bool ascii_compatible; |
66ebf983 | 4936 | struct charset *charset_big5; |
df7492f9 KH |
4937 | int c; |
4938 | ||
24a73b0a | 4939 | CODING_GET_INFO (coding, attrs, charset_list); |
66ebf983 | 4940 | val = XCDR (charset_list); |
df7492f9 KH |
4941 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); |
4942 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4943 | ||
4944 | while (charbuf < charbuf_end) | |
4945 | { | |
4946 | ASSURE_DESTINATION (safe_room); | |
4947 | c = *charbuf++; | |
4948 | /* Now encode the character C. */ | |
4949 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4950 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4951 | else if (CHAR_BYTE8_P (c)) |
4952 | { | |
4953 | c = CHAR_TO_BYTE8 (c); | |
4954 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
4955 | } |
4956 | else | |
4957 | { | |
df7492f9 | 4958 | unsigned code; |
5eb05ea3 KH |
4959 | struct charset *charset; |
4960 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4961 | &code, charset); | |
df7492f9 KH |
4962 | |
4963 | if (! charset) | |
b73bfc1c | 4964 | { |
41cbe562 | 4965 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4966 | { |
41cbe562 KH |
4967 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4968 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4969 | } |
41cbe562 | 4970 | else |
0eecad43 | 4971 | { |
41cbe562 | 4972 | c = coding->default_char; |
5eb05ea3 KH |
4973 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4974 | charset_list, &code, charset); | |
0eecad43 | 4975 | } |
4ed46869 | 4976 | } |
df7492f9 | 4977 | if (code == CHARSET_INVALID_CODE (charset)) |
1088b922 | 4978 | emacs_abort (); |
df7492f9 | 4979 | if (charset == charset_big5) |
b73bfc1c | 4980 | { |
df7492f9 KH |
4981 | int c1, c2; |
4982 | ||
4983 | c1 = code >> 8, c2 = code & 0xFF; | |
4984 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 4985 | } |
df7492f9 KH |
4986 | else |
4987 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 4988 | } |
4ed46869 | 4989 | } |
065e3595 | 4990 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4991 | coding->produced_char += produced_chars; |
4992 | coding->produced = dst - coding->destination; | |
4993 | return 0; | |
4ed46869 KH |
4994 | } |
4995 | ||
4996 | \f | |
df7492f9 | 4997 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
4998 | |
4999 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f PE |
5000 | Return true if a text is encoded in a coding system of which |
5001 | encoder/decoder are written in CCL program. */ | |
1397dc18 | 5002 | |
f10fe38f | 5003 | static bool |
cf84bb53 JB |
5004 | detect_coding_ccl (struct coding_system *coding, |
5005 | struct coding_detection_info *detect_info) | |
1397dc18 | 5006 | { |
065e3595 | 5007 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5008 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 5009 | bool multibytep = coding->src_multibyte; |
d311d28c | 5010 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 5011 | int found = 0; |
0e219d54 | 5012 | unsigned char *valids; |
d311d28c | 5013 | ptrdiff_t head_ascii = coding->head_ascii; |
df7492f9 KH |
5014 | Lisp_Object attrs; |
5015 | ||
ff0dacd7 KH |
5016 | detect_info->checked |= CATEGORY_MASK_CCL; |
5017 | ||
df7492f9 | 5018 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 5019 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
5020 | attrs = CODING_ID_ATTRS (coding->id); |
5021 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
5022 | src += head_ascii; | |
1397dc18 | 5023 | |
b73bfc1c | 5024 | while (1) |
1397dc18 | 5025 | { |
df7492f9 | 5026 | int c; |
065e3595 KH |
5027 | |
5028 | src_base = src; | |
df7492f9 | 5029 | ONE_MORE_BYTE (c); |
065e3595 | 5030 | if (c < 0 || ! valids[c]) |
df7492f9 | 5031 | break; |
ff0dacd7 KH |
5032 | if ((valids[c] > 1)) |
5033 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 5034 | } |
ff0dacd7 | 5035 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
5036 | return 0; |
5037 | ||
5038 | no_more_source: | |
ff0dacd7 KH |
5039 | detect_info->found |= found; |
5040 | return 1; | |
df7492f9 KH |
5041 | } |
5042 | ||
5043 | static void | |
971de7fb | 5044 | decode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5045 | { |
7c78e542 | 5046 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 5047 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
5048 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5049 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
d311d28c | 5050 | ptrdiff_t consumed_chars = 0; |
f10fe38f | 5051 | bool multibytep = coding->src_multibyte; |
d0396581 | 5052 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 | 5053 | int source_charbuf[1024]; |
fbdc1721 | 5054 | int source_byteidx[1025]; |
24a73b0a | 5055 | Lisp_Object attrs, charset_list; |
df7492f9 | 5056 | |
24a73b0a | 5057 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5058 | |
d0396581 | 5059 | while (1) |
df7492f9 | 5060 | { |
7c78e542 | 5061 | const unsigned char *p = src; |
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 KH |
5078 | ccl->last_block = 1; |
5079 | ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf, | |
5080 | charset_list); | |
5081 | charbuf += ccl->produced; | |
fbdc1721 | 5082 | if (multibytep) |
d0396581 | 5083 | src += source_byteidx[ccl->consumed]; |
df7492f9 | 5084 | else |
d0396581 KH |
5085 | src += ccl->consumed; |
5086 | consumed_chars += ccl->consumed; | |
5087 | if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC) | |
df7492f9 KH |
5088 | break; |
5089 | } | |
5090 | ||
d0396581 | 5091 | switch (ccl->status) |
df7492f9 KH |
5092 | { |
5093 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5094 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5095 | break; |
5096 | case CCL_STAT_SUSPEND_BY_DST: | |
d0396581 | 5097 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5098 | break; |
5099 | case CCL_STAT_QUIT: | |
5100 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5101 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5102 | break; |
5103 | default: | |
065e3595 | 5104 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5105 | break; |
5106 | } | |
5107 | coding->consumed_char += consumed_chars; | |
5108 | coding->consumed = src - coding->source; | |
5109 | coding->charbuf_used = charbuf - coding->charbuf; | |
5110 | } | |
5111 | ||
f10fe38f | 5112 | static bool |
971de7fb | 5113 | encode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5114 | { |
fb608df3 | 5115 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
f10fe38f | 5116 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5117 | int *charbuf = coding->charbuf; |
5118 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5119 | unsigned char *dst = coding->destination + coding->produced; | |
5120 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 | 5121 | int destination_charbuf[1024]; |
d311d28c | 5122 | ptrdiff_t produced_chars = 0; |
a53e2e89 | 5123 | int i; |
24a73b0a | 5124 | Lisp_Object attrs, charset_list; |
df7492f9 | 5125 | |
24a73b0a | 5126 | CODING_GET_INFO (coding, attrs, charset_list); |
fb608df3 KH |
5127 | if (coding->consumed_char == coding->src_chars |
5128 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
5129 | ccl->last_block = 1; | |
df7492f9 | 5130 | |
76470ad1 | 5131 | do |
df7492f9 | 5132 | { |
fb608df3 | 5133 | ccl_driver (ccl, charbuf, destination_charbuf, |
8cffd3e7 | 5134 | charbuf_end - charbuf, 1024, charset_list); |
df7492f9 | 5135 | if (multibytep) |
8cffd3e7 | 5136 | { |
fb608df3 KH |
5137 | ASSURE_DESTINATION (ccl->produced * 2); |
5138 | for (i = 0; i < ccl->produced; i++) | |
8cffd3e7 KH |
5139 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); |
5140 | } | |
df7492f9 KH |
5141 | else |
5142 | { | |
fb608df3 KH |
5143 | ASSURE_DESTINATION (ccl->produced); |
5144 | for (i = 0; i < ccl->produced; i++) | |
df7492f9 | 5145 | *dst++ = destination_charbuf[i] & 0xFF; |
fb608df3 | 5146 | produced_chars += ccl->produced; |
df7492f9 | 5147 | } |
fb608df3 KH |
5148 | charbuf += ccl->consumed; |
5149 | if (ccl->status == CCL_STAT_QUIT | |
5150 | || ccl->status == CCL_STAT_INVALID_CMD) | |
8cffd3e7 | 5151 | break; |
df7492f9 | 5152 | } |
76470ad1 | 5153 | while (charbuf < charbuf_end); |
df7492f9 | 5154 | |
fb608df3 | 5155 | switch (ccl->status) |
df7492f9 KH |
5156 | { |
5157 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5158 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5159 | break; |
5160 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 5161 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5162 | break; |
5163 | case CCL_STAT_QUIT: | |
5164 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5165 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5166 | break; |
5167 | default: | |
065e3595 | 5168 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5169 | break; |
1397dc18 | 5170 | } |
df7492f9 KH |
5171 | |
5172 | coding->produced_char += produced_chars; | |
5173 | coding->produced = dst - coding->destination; | |
5174 | return 0; | |
1397dc18 KH |
5175 | } |
5176 | ||
5177 | \f | |
df7492f9 | 5178 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 5179 | |
b73bfc1c | 5180 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 5181 | |
b73bfc1c | 5182 | static void |
971de7fb | 5183 | decode_coding_raw_text (struct coding_system *coding) |
4ed46869 | 5184 | { |
f10fe38f PE |
5185 | bool eol_dos |
5186 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5187 | |
df7492f9 | 5188 | coding->chars_at_source = 1; |
119852e7 KH |
5189 | coding->consumed_char = coding->src_chars; |
5190 | coding->consumed = coding->src_bytes; | |
2735d060 | 5191 | if (eol_dos && coding->source[coding->src_bytes - 1] == '\r') |
119852e7 KH |
5192 | { |
5193 | coding->consumed_char--; | |
5194 | coding->consumed--; | |
5195 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
5196 | } | |
5197 | else | |
5198 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 5199 | } |
4ed46869 | 5200 | |
f10fe38f | 5201 | static bool |
971de7fb | 5202 | encode_coding_raw_text (struct coding_system *coding) |
df7492f9 | 5203 | { |
f10fe38f | 5204 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5205 | int *charbuf = coding->charbuf; |
5206 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5207 | unsigned char *dst = coding->destination + coding->produced; | |
5208 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c | 5209 | ptrdiff_t produced_chars = 0; |
b73bfc1c KH |
5210 | int c; |
5211 | ||
df7492f9 | 5212 | if (multibytep) |
b73bfc1c | 5213 | { |
df7492f9 | 5214 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5215 | |
df7492f9 KH |
5216 | if (coding->src_multibyte) |
5217 | while (charbuf < charbuf_end) | |
5218 | { | |
5219 | ASSURE_DESTINATION (safe_room); | |
5220 | c = *charbuf++; | |
5221 | if (ASCII_CHAR_P (c)) | |
5222 | EMIT_ONE_ASCII_BYTE (c); | |
5223 | else if (CHAR_BYTE8_P (c)) | |
5224 | { | |
5225 | c = CHAR_TO_BYTE8 (c); | |
5226 | EMIT_ONE_BYTE (c); | |
5227 | } | |
5228 | else | |
5229 | { | |
5230 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5231 | |
df7492f9 | 5232 | CHAR_STRING_ADVANCE (c, p1); |
8abc3f12 | 5233 | do |
9d123124 KH |
5234 | { |
5235 | EMIT_ONE_BYTE (*p0); | |
5236 | p0++; | |
5237 | } | |
8abc3f12 | 5238 | while (p0 < p1); |
df7492f9 KH |
5239 | } |
5240 | } | |
b73bfc1c | 5241 | else |
df7492f9 KH |
5242 | while (charbuf < charbuf_end) |
5243 | { | |
5244 | ASSURE_DESTINATION (safe_room); | |
5245 | c = *charbuf++; | |
5246 | EMIT_ONE_BYTE (c); | |
5247 | } | |
5248 | } | |
5249 | else | |
4ed46869 | 5250 | { |
df7492f9 | 5251 | if (coding->src_multibyte) |
d46c5b12 | 5252 | { |
df7492f9 KH |
5253 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5254 | ||
5255 | while (charbuf < charbuf_end) | |
d46c5b12 | 5256 | { |
df7492f9 KH |
5257 | ASSURE_DESTINATION (safe_room); |
5258 | c = *charbuf++; | |
5259 | if (ASCII_CHAR_P (c)) | |
5260 | *dst++ = c; | |
5261 | else if (CHAR_BYTE8_P (c)) | |
5262 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5263 | else |
df7492f9 | 5264 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5265 | } |
5266 | } | |
df7492f9 KH |
5267 | else |
5268 | { | |
5269 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5270 | while (charbuf < charbuf_end && dst < dst_end) | |
5271 | *dst++ = *charbuf++; | |
8f924df7 | 5272 | } |
319a3947 | 5273 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5274 | } |
065e3595 | 5275 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5276 | coding->produced_char += produced_chars; |
df7492f9 KH |
5277 | coding->produced = dst - coding->destination; |
5278 | return 0; | |
4ed46869 KH |
5279 | } |
5280 | ||
ff0dacd7 | 5281 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f | 5282 | Return true if a text is encoded in a charset-based coding system. */ |
ff0dacd7 | 5283 | |
f10fe38f | 5284 | static bool |
cf84bb53 JB |
5285 | detect_coding_charset (struct coding_system *coding, |
5286 | struct coding_detection_info *detect_info) | |
1397dc18 | 5287 | { |
065e3595 | 5288 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5289 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 5290 | bool multibytep = coding->src_multibyte; |
d311d28c | 5291 | ptrdiff_t consumed_chars = 0; |
07295713 | 5292 | Lisp_Object attrs, valids, name; |
584948ac | 5293 | int found = 0; |
d311d28c | 5294 | ptrdiff_t head_ascii = coding->head_ascii; |
f10fe38f | 5295 | bool check_latin_extra = 0; |
1397dc18 | 5296 | |
ff0dacd7 KH |
5297 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5298 | ||
df7492f9 KH |
5299 | coding = &coding_categories[coding_category_charset]; |
5300 | attrs = CODING_ID_ATTRS (coding->id); | |
5301 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 | 5302 | name = CODING_ID_NAME (coding->id); |
51b59d79 | 5303 | if (strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5304 | "iso-8859-", sizeof ("iso-8859-") - 1) == 0 |
51b59d79 | 5305 | || strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5306 | "iso-latin-", sizeof ("iso-latin-") - 1) == 0) |
07295713 | 5307 | check_latin_extra = 1; |
237aabf4 | 5308 | |
df7492f9 | 5309 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5310 | src += head_ascii; |
1397dc18 | 5311 | |
b73bfc1c | 5312 | while (1) |
1397dc18 | 5313 | { |
df7492f9 | 5314 | int c; |
716b3fa0 KH |
5315 | Lisp_Object val; |
5316 | struct charset *charset; | |
5317 | int dim, idx; | |
1397dc18 | 5318 | |
065e3595 | 5319 | src_base = src; |
df7492f9 | 5320 | ONE_MORE_BYTE (c); |
065e3595 KH |
5321 | if (c < 0) |
5322 | continue; | |
716b3fa0 KH |
5323 | val = AREF (valids, c); |
5324 | if (NILP (val)) | |
df7492f9 | 5325 | break; |
584948ac | 5326 | if (c >= 0x80) |
07295713 KH |
5327 | { |
5328 | if (c < 0xA0 | |
237aabf4 JR |
5329 | && check_latin_extra |
5330 | && (!VECTORP (Vlatin_extra_code_table) | |
28be1ada | 5331 | || NILP (AREF (Vlatin_extra_code_table, c)))) |
07295713 KH |
5332 | break; |
5333 | found = CATEGORY_MASK_CHARSET; | |
5334 | } | |
716b3fa0 KH |
5335 | if (INTEGERP (val)) |
5336 | { | |
5337 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5338 | dim = CHARSET_DIMENSION (charset); | |
5339 | for (idx = 1; idx < dim; idx++) | |
5340 | { | |
5341 | if (src == src_end) | |
5342 | goto too_short; | |
5343 | ONE_MORE_BYTE (c); | |
2f9442b8 PE |
5344 | if (c < charset->code_space[(dim - 1 - idx) * 4] |
5345 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
716b3fa0 KH |
5346 | break; |
5347 | } | |
5348 | if (idx < dim) | |
5349 | break; | |
5350 | } | |
5351 | else | |
5352 | { | |
5353 | idx = 1; | |
5354 | for (; CONSP (val); val = XCDR (val)) | |
5355 | { | |
5356 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5357 | dim = CHARSET_DIMENSION (charset); | |
5358 | while (idx < dim) | |
5359 | { | |
5360 | if (src == src_end) | |
5361 | goto too_short; | |
5362 | ONE_MORE_BYTE (c); | |
5363 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5364 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5365 | break; | |
5366 | idx++; | |
5367 | } | |
5368 | if (idx == dim) | |
5369 | { | |
5370 | val = Qnil; | |
5371 | break; | |
5372 | } | |
5373 | } | |
5374 | if (CONSP (val)) | |
5375 | break; | |
5376 | } | |
df7492f9 | 5377 | } |
716b3fa0 | 5378 | too_short: |
ff0dacd7 | 5379 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5380 | return 0; |
4ed46869 | 5381 | |
df7492f9 | 5382 | no_more_source: |
ff0dacd7 KH |
5383 | detect_info->found |= found; |
5384 | return 1; | |
df7492f9 | 5385 | } |
b73bfc1c | 5386 | |
b73bfc1c | 5387 | static void |
971de7fb | 5388 | decode_coding_charset (struct coding_system *coding) |
4ed46869 | 5389 | { |
8f924df7 KH |
5390 | const unsigned char *src = coding->source + coding->consumed; |
5391 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5392 | const unsigned char *src_base; | |
69a80ea3 | 5393 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 5394 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 5395 | the end. */ |
69a80ea3 | 5396 | int *charbuf_end |
df80c7f0 | 5397 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 5398 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 5399 | bool multibytep = coding->src_multibyte; |
66ebf983 PE |
5400 | Lisp_Object attrs = CODING_ID_ATTRS (coding->id); |
5401 | Lisp_Object valids; | |
d311d28c PE |
5402 | ptrdiff_t char_offset = coding->produced_char; |
5403 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 5404 | int last_id = charset_ascii; |
f10fe38f PE |
5405 | bool eol_dos |
5406 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5407 | int byte_after_cr = -1; |
df7492f9 | 5408 | |
4eb6d3f1 | 5409 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5410 | |
df7492f9 | 5411 | while (1) |
4ed46869 | 5412 | { |
4eb6d3f1 | 5413 | int c; |
24a73b0a KH |
5414 | Lisp_Object val; |
5415 | struct charset *charset; | |
5416 | int dim; | |
5417 | int len = 1; | |
5418 | unsigned code; | |
df7492f9 KH |
5419 | |
5420 | src_base = src; | |
5421 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5422 | |
df7492f9 | 5423 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5424 | { |
5425 | if (byte_after_cr >= 0) | |
5426 | src_base--; | |
5427 | break; | |
5428 | } | |
df7492f9 | 5429 | |
119852e7 KH |
5430 | if (byte_after_cr >= 0) |
5431 | { | |
5432 | c = byte_after_cr; | |
5433 | byte_after_cr = -1; | |
5434 | } | |
5435 | else | |
5436 | { | |
5437 | ONE_MORE_BYTE (c); | |
2735d060 | 5438 | if (eol_dos && c == '\r') |
119852e7 KH |
5439 | ONE_MORE_BYTE (byte_after_cr); |
5440 | } | |
065e3595 KH |
5441 | if (c < 0) |
5442 | goto invalid_code; | |
24a73b0a KH |
5443 | code = c; |
5444 | ||
5445 | val = AREF (valids, c); | |
1b17adfd | 5446 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5447 | goto invalid_code; |
5448 | if (INTEGERP (val)) | |
d46c5b12 | 5449 | { |
24a73b0a KH |
5450 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5451 | dim = CHARSET_DIMENSION (charset); | |
5452 | while (len < dim) | |
b73bfc1c | 5453 | { |
24a73b0a KH |
5454 | ONE_MORE_BYTE (c); |
5455 | code = (code << 8) | c; | |
5456 | len++; | |
b73bfc1c | 5457 | } |
24a73b0a KH |
5458 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5459 | charset, code, c); | |
d46c5b12 | 5460 | } |
df7492f9 | 5461 | else |
d46c5b12 | 5462 | { |
24a73b0a KH |
5463 | /* VAL is a list of charset IDs. It is assured that the |
5464 | list is sorted by charset dimensions (smaller one | |
5465 | comes first). */ | |
5466 | while (CONSP (val)) | |
4eb6d3f1 | 5467 | { |
24a73b0a | 5468 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5469 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5470 | while (len < dim) |
4eb6d3f1 | 5471 | { |
acb2a965 KH |
5472 | ONE_MORE_BYTE (c); |
5473 | code = (code << 8) | c; | |
f9d71dcd | 5474 | len++; |
4eb6d3f1 | 5475 | } |
24a73b0a KH |
5476 | CODING_DECODE_CHAR (coding, src, src_base, |
5477 | src_end, charset, code, c); | |
5478 | if (c >= 0) | |
5479 | break; | |
5480 | val = XCDR (val); | |
ff0dacd7 | 5481 | } |
d46c5b12 | 5482 | } |
24a73b0a KH |
5483 | if (c < 0) |
5484 | goto invalid_code; | |
5485 | if (charset->id != charset_ascii | |
5486 | && last_id != charset->id) | |
5487 | { | |
5488 | if (last_id != charset_ascii) | |
69a80ea3 | 5489 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5490 | last_id = charset->id; |
5491 | last_offset = char_offset; | |
5492 | } | |
5493 | ||
df7492f9 | 5494 | *charbuf++ = c; |
ff0dacd7 | 5495 | char_offset++; |
df7492f9 KH |
5496 | continue; |
5497 | ||
5498 | invalid_code: | |
5499 | src = src_base; | |
5500 | consumed_chars = consumed_chars_base; | |
5501 | ONE_MORE_BYTE (c); | |
065e3595 | 5502 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5503 | char_offset++; |
df7492f9 | 5504 | coding->errors++; |
4ed46869 KH |
5505 | } |
5506 | ||
df7492f9 | 5507 | no_more_source: |
ff0dacd7 | 5508 | if (last_id != charset_ascii) |
69a80ea3 | 5509 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5510 | coding->consumed_char += consumed_chars_base; |
5511 | coding->consumed = src_base - coding->source; | |
5512 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5513 | } |
5514 | ||
f10fe38f | 5515 | static bool |
971de7fb | 5516 | encode_coding_charset (struct coding_system *coding) |
4ed46869 | 5517 | { |
f10fe38f | 5518 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5519 | int *charbuf = coding->charbuf; |
5520 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5521 | unsigned char *dst = coding->destination + coding->produced; | |
5522 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5523 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
d311d28c | 5524 | ptrdiff_t produced_chars = 0; |
24a73b0a | 5525 | Lisp_Object attrs, charset_list; |
f10fe38f | 5526 | bool ascii_compatible; |
b73bfc1c | 5527 | int c; |
b73bfc1c | 5528 | |
24a73b0a | 5529 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5530 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5531 | |
df7492f9 | 5532 | while (charbuf < charbuf_end) |
4ed46869 | 5533 | { |
4eb6d3f1 | 5534 | struct charset *charset; |
df7492f9 | 5535 | unsigned code; |
8f924df7 | 5536 | |
df7492f9 KH |
5537 | ASSURE_DESTINATION (safe_room); |
5538 | c = *charbuf++; | |
5539 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5540 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5541 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5542 | { |
16eafb5d KH |
5543 | c = CHAR_TO_BYTE8 (c); |
5544 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5545 | } |
d46c5b12 | 5546 | else |
b73bfc1c | 5547 | { |
5eb05ea3 KH |
5548 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
5549 | &code, charset); | |
5550 | ||
4eb6d3f1 KH |
5551 | if (charset) |
5552 | { | |
5553 | if (CHARSET_DIMENSION (charset) == 1) | |
5554 | EMIT_ONE_BYTE (code); | |
5555 | else if (CHARSET_DIMENSION (charset) == 2) | |
5556 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5557 | else if (CHARSET_DIMENSION (charset) == 3) | |
5558 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5559 | else | |
5560 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5561 | (code >> 8) & 0xFF, code & 0xFF); | |
5562 | } | |
5563 | else | |
41cbe562 KH |
5564 | { |
5565 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5566 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5567 | else | |
5568 | c = coding->default_char; | |
5569 | EMIT_ONE_BYTE (c); | |
5570 | } | |
4ed46869 | 5571 | } |
4ed46869 KH |
5572 | } |
5573 | ||
065e3595 | 5574 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5575 | coding->produced_char += produced_chars; |
5576 | coding->produced = dst - coding->destination; | |
5577 | return 0; | |
4ed46869 KH |
5578 | } |
5579 | ||
5580 | \f | |
1397dc18 | 5581 | /*** 7. C library functions ***/ |
4ed46869 | 5582 | |
df7492f9 KH |
5583 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5584 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5585 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5586 | |
ec6d2bb8 | 5587 | void |
971de7fb | 5588 | setup_coding_system (Lisp_Object coding_system, struct coding_system *coding) |
4ed46869 | 5589 | { |
df7492f9 KH |
5590 | Lisp_Object attrs; |
5591 | Lisp_Object eol_type; | |
5592 | Lisp_Object coding_type; | |
4608c386 | 5593 | Lisp_Object val; |
4ed46869 | 5594 | |
df7492f9 | 5595 | if (NILP (coding_system)) |
ae6f73fa | 5596 | coding_system = Qundecided; |
c07c8e12 | 5597 | |
df7492f9 | 5598 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5599 | |
df7492f9 | 5600 | attrs = CODING_ID_ATTRS (coding->id); |
0a9564cb | 5601 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
1f5dbf34 | 5602 | |
df7492f9 KH |
5603 | coding->mode = 0; |
5604 | coding->head_ascii = -1; | |
4a015c45 KH |
5605 | if (VECTORP (eol_type)) |
5606 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5607 | | CODING_REQUIRE_DETECTION_MASK); | |
5608 | else if (! EQ (eol_type, Qunix)) | |
5609 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5610 | | CODING_REQUIRE_ENCODING_MASK); | |
5611 | else | |
5612 | coding->common_flags = 0; | |
5e5c78be KH |
5613 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5614 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5615 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5616 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5617 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5618 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5619 | |
df7492f9 | 5620 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 | 5621 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5622 | coding->safe_charsets = SDATA (val); |
df7492f9 | 5623 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
624bda09 | 5624 | coding->carryover_bytes = 0; |
4608c386 | 5625 | |
df7492f9 KH |
5626 | coding_type = CODING_ATTR_TYPE (attrs); |
5627 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5628 | { |
df7492f9 KH |
5629 | coding->detector = NULL; |
5630 | coding->decoder = decode_coding_raw_text; | |
5631 | coding->encoder = encode_coding_raw_text; | |
5632 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5633 | } |
df7492f9 | 5634 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5635 | { |
df7492f9 KH |
5636 | int i; |
5637 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5638 | ||
5639 | /* Invoke graphic register 0 to plane 0. */ | |
5640 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5641 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5642 | CODING_ISO_INVOCATION (coding, 1) | |
5643 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5644 | /* Setup the initial status of designation. */ | |
5645 | for (i = 0; i < 4; i++) | |
5646 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5647 | /* Not single shifting initially. */ | |
5648 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5649 | /* Beginning of buffer should also be regarded as bol. */ | |
5650 | CODING_ISO_BOL (coding) = 1; | |
5651 | coding->detector = detect_coding_iso_2022; | |
5652 | coding->decoder = decode_coding_iso_2022; | |
5653 | coding->encoder = encode_coding_iso_2022; | |
5654 | if (flags & CODING_ISO_FLAG_SAFE) | |
5655 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5656 | coding->common_flags |
df7492f9 KH |
5657 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5658 | | CODING_REQUIRE_FLUSHING_MASK); | |
5659 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5660 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5661 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5662 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5663 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5664 | { | |
5665 | setup_iso_safe_charsets (attrs); | |
5666 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 5667 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5668 | coding->safe_charsets = SDATA (val); |
df7492f9 KH |
5669 | } |
5670 | CODING_ISO_FLAGS (coding) = flags; | |
e951386e KH |
5671 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; |
5672 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | |
5673 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | |
5674 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
d46c5b12 | 5675 | } |
df7492f9 | 5676 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5677 | { |
df7492f9 KH |
5678 | coding->detector = detect_coding_charset; |
5679 | coding->decoder = decode_coding_charset; | |
5680 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5681 | coding->common_flags |
df7492f9 | 5682 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5683 | } |
df7492f9 | 5684 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5685 | { |
a470d443 KH |
5686 | val = AREF (attrs, coding_attr_utf_bom); |
5687 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5688 | : EQ (val, Qt) ? utf_with_bom | |
5689 | : utf_without_bom); | |
df7492f9 KH |
5690 | coding->detector = detect_coding_utf_8; |
5691 | coding->decoder = decode_coding_utf_8; | |
5692 | coding->encoder = encode_coding_utf_8; | |
5693 | coding->common_flags | |
5694 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5695 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5696 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5697 | } |
5698 | else if (EQ (coding_type, Qutf_16)) | |
5699 | { | |
a470d443 KH |
5700 | val = AREF (attrs, coding_attr_utf_bom); |
5701 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5702 | : EQ (val, Qt) ? utf_with_bom | |
5703 | : utf_without_bom); | |
df7492f9 | 5704 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5705 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5706 | : utf_16_little_endian); |
e19c3639 | 5707 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5708 | coding->detector = detect_coding_utf_16; |
5709 | coding->decoder = decode_coding_utf_16; | |
5710 | coding->encoder = encode_coding_utf_16; | |
5711 | coding->common_flags | |
5712 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5713 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5714 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5715 | } |
df7492f9 | 5716 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5717 | { |
df7492f9 KH |
5718 | coding->detector = detect_coding_ccl; |
5719 | coding->decoder = decode_coding_ccl; | |
5720 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5721 | coding->common_flags |
df7492f9 KH |
5722 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5723 | | CODING_REQUIRE_FLUSHING_MASK); | |
5724 | } | |
5725 | else if (EQ (coding_type, Qemacs_mule)) | |
5726 | { | |
5727 | coding->detector = detect_coding_emacs_mule; | |
5728 | coding->decoder = decode_coding_emacs_mule; | |
5729 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5730 | coding->common_flags |
df7492f9 KH |
5731 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5732 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5733 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5734 | { | |
5735 | Lisp_Object tail, safe_charsets; | |
5736 | int max_charset_id = 0; | |
5737 | ||
5738 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5739 | tail = XCDR (tail)) | |
5740 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5741 | max_charset_id = XFASTINT (XCAR (tail)); | |
1b3b981b AS |
5742 | safe_charsets = make_uninit_string (max_charset_id + 1); |
5743 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
5744 | for (tail = Vemacs_mule_charset_list; CONSP (tail); |
5745 | tail = XCDR (tail)) | |
8f924df7 | 5746 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5747 | coding->max_charset_id = max_charset_id; |
1b3b981b | 5748 | coding->safe_charsets = SDATA (safe_charsets); |
df7492f9 | 5749 | } |
e951386e KH |
5750 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; |
5751 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | |
df7492f9 KH |
5752 | } |
5753 | else if (EQ (coding_type, Qshift_jis)) | |
5754 | { | |
5755 | coding->detector = detect_coding_sjis; | |
5756 | coding->decoder = decode_coding_sjis; | |
5757 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5758 | coding->common_flags |
df7492f9 KH |
5759 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5760 | } | |
5761 | else if (EQ (coding_type, Qbig5)) | |
5762 | { | |
5763 | coding->detector = detect_coding_big5; | |
5764 | coding->decoder = decode_coding_big5; | |
5765 | coding->encoder = encode_coding_big5; | |
c952af22 | 5766 | coding->common_flags |
df7492f9 KH |
5767 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5768 | } | |
5769 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5770 | { |
df7492f9 KH |
5771 | coding->detector = NULL; |
5772 | coding->decoder = decode_coding_raw_text; | |
5773 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5774 | if (! EQ (eol_type, Qunix)) |
5775 | { | |
5776 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5777 | if (! VECTORP (eol_type)) | |
5778 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5779 | } | |
5780 | ||
4ed46869 | 5781 | } |
4ed46869 | 5782 | |
df7492f9 | 5783 | return; |
4ed46869 KH |
5784 | } |
5785 | ||
0ff61e78 KH |
5786 | /* Return a list of charsets supported by CODING. */ |
5787 | ||
5788 | Lisp_Object | |
971de7fb | 5789 | coding_charset_list (struct coding_system *coding) |
0ff61e78 | 5790 | { |
35befdaa | 5791 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5792 | |
5793 | CODING_GET_INFO (coding, attrs, charset_list); | |
5794 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5795 | { | |
5796 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5797 | ||
5798 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5799 | charset_list = Viso_2022_charset_list; | |
5800 | } | |
5801 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5802 | { | |
5803 | charset_list = Vemacs_mule_charset_list; | |
5804 | } | |
5805 | return charset_list; | |
5806 | } | |
5807 | ||
5808 | ||
e9f91ece KH |
5809 | /* Return a list of charsets supported by CODING-SYSTEM. */ |
5810 | ||
5811 | Lisp_Object | |
971de7fb | 5812 | coding_system_charset_list (Lisp_Object coding_system) |
e9f91ece | 5813 | { |
d3411f89 | 5814 | ptrdiff_t id; |
e9f91ece KH |
5815 | Lisp_Object attrs, charset_list; |
5816 | ||
5817 | CHECK_CODING_SYSTEM_GET_ID (coding_system, id); | |
5818 | attrs = CODING_ID_ATTRS (id); | |
5819 | ||
5820 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5821 | { | |
5822 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5823 | ||
5824 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5825 | charset_list = Viso_2022_charset_list; | |
5826 | else | |
5827 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5828 | } | |
5829 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5830 | { | |
5831 | charset_list = Vemacs_mule_charset_list; | |
5832 | } | |
5833 | else | |
5834 | { | |
5835 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5836 | } | |
5837 | return charset_list; | |
5838 | } | |
5839 | ||
5840 | ||
df7492f9 KH |
5841 | /* Return raw-text or one of its subsidiaries that has the same |
5842 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5843 | |
df7492f9 | 5844 | Lisp_Object |
971de7fb | 5845 | raw_text_coding_system (Lisp_Object coding_system) |
ec6d2bb8 | 5846 | { |
0be8721c | 5847 | Lisp_Object spec, attrs; |
df7492f9 | 5848 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5849 | |
d3e4cb56 KH |
5850 | if (NILP (coding_system)) |
5851 | return Qraw_text; | |
df7492f9 KH |
5852 | spec = CODING_SYSTEM_SPEC (coding_system); |
5853 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5854 | |
df7492f9 KH |
5855 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5856 | return coding_system; | |
ec6d2bb8 | 5857 | |
df7492f9 KH |
5858 | eol_type = AREF (spec, 2); |
5859 | if (VECTORP (eol_type)) | |
5860 | return Qraw_text; | |
5861 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5862 | raw_text_eol_type = AREF (spec, 2); | |
5863 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5864 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5865 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5866 | } |
5867 | ||
54f78171 | 5868 | |
1911a33b KH |
5869 | /* If CODING_SYSTEM doesn't specify end-of-line format, return one of |
5870 | the subsidiary that has the same eol-spec as PARENT (if it is not | |
5871 | nil and specifies end-of-line format) or the system's setting | |
fcbcfb64 | 5872 | (system_eol_type). */ |
df7492f9 KH |
5873 | |
5874 | Lisp_Object | |
971de7fb | 5875 | coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent) |
54f78171 | 5876 | { |
3e139625 | 5877 | Lisp_Object spec, eol_type; |
54f78171 | 5878 | |
d3e4cb56 KH |
5879 | if (NILP (coding_system)) |
5880 | coding_system = Qraw_text; | |
df7492f9 | 5881 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5882 | eol_type = AREF (spec, 2); |
fcbcfb64 | 5883 | if (VECTORP (eol_type)) |
df7492f9 | 5884 | { |
df7492f9 KH |
5885 | Lisp_Object parent_eol_type; |
5886 | ||
fcbcfb64 KH |
5887 | if (! NILP (parent)) |
5888 | { | |
5889 | Lisp_Object parent_spec; | |
5890 | ||
4a015c45 | 5891 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 | 5892 | parent_eol_type = AREF (parent_spec, 2); |
1911a33b | 5893 | if (VECTORP (parent_eol_type)) |
4628bef1 | 5894 | parent_eol_type = system_eol_type; |
fcbcfb64 KH |
5895 | } |
5896 | else | |
5897 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
5898 | if (EQ (parent_eol_type, Qunix)) |
5899 | coding_system = AREF (eol_type, 0); | |
5900 | else if (EQ (parent_eol_type, Qdos)) | |
5901 | coding_system = AREF (eol_type, 1); | |
5902 | else if (EQ (parent_eol_type, Qmac)) | |
5903 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5904 | } |
df7492f9 | 5905 | return coding_system; |
54f78171 KH |
5906 | } |
5907 | ||
fcaf8878 KH |
5908 | |
5909 | /* Check if text-conversion and eol-conversion of CODING_SYSTEM are | |
5910 | decided for writing to a process. If not, complement them, and | |
5911 | return a new coding system. */ | |
5912 | ||
5913 | Lisp_Object | |
4628bef1 | 5914 | complement_process_encoding_system (Lisp_Object coding_system) |
fcaf8878 | 5915 | { |
5886ec9c KH |
5916 | Lisp_Object coding_base = Qnil, eol_base = Qnil; |
5917 | Lisp_Object spec, attrs; | |
93d50df8 | 5918 | int i; |
fcaf8878 | 5919 | |
93d50df8 | 5920 | for (i = 0; i < 3; i++) |
fcaf8878 | 5921 | { |
93d50df8 KH |
5922 | if (i == 1) |
5923 | coding_system = CDR_SAFE (Vdefault_process_coding_system); | |
5924 | else if (i == 2) | |
5925 | coding_system = preferred_coding_system (); | |
5926 | spec = CODING_SYSTEM_SPEC (coding_system); | |
5927 | if (NILP (spec)) | |
5928 | continue; | |
5929 | attrs = AREF (spec, 0); | |
5930 | if (NILP (coding_base) && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
5931 | coding_base = CODING_ATTR_BASE_NAME (attrs); | |
5932 | if (NILP (eol_base) && ! VECTORP (AREF (spec, 2))) | |
5933 | eol_base = coding_system; | |
5934 | if (! NILP (coding_base) && ! NILP (eol_base)) | |
5935 | break; | |
fcaf8878 | 5936 | } |
fcaf8878 | 5937 | |
93d50df8 KH |
5938 | if (i > 0) |
5939 | /* The original CODING_SYSTEM didn't specify text-conversion or | |
5940 | eol-conversion. Be sure that we return a fully complemented | |
5941 | coding system. */ | |
5942 | coding_system = coding_inherit_eol_type (coding_base, eol_base); | |
5943 | return coding_system; | |
fcaf8878 KH |
5944 | } |
5945 | ||
5946 | ||
4ed46869 KH |
5947 | /* Emacs has a mechanism to automatically detect a coding system if it |
5948 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
5949 | it's impossible to distinguish some coding systems accurately | |
5950 | because they use the same range of codes. So, at first, coding | |
5951 | systems are categorized into 7, those are: | |
5952 | ||
0ef69138 | 5953 | o coding-category-emacs-mule |
4ed46869 KH |
5954 | |
5955 | The category for a coding system which has the same code range | |
5956 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 5957 | symbol) `emacs-mule' by default. |
4ed46869 KH |
5958 | |
5959 | o coding-category-sjis | |
5960 | ||
5961 | The category for a coding system which has the same code range | |
5962 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 5963 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
5964 | |
5965 | o coding-category-iso-7 | |
5966 | ||
5967 | The category for a coding system which has the same code range | |
7717c392 | 5968 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
5969 | shift and single shift functions. This can encode/decode all |
5970 | charsets. Assigned the coding-system (Lisp symbol) | |
5971 | `iso-2022-7bit' by default. | |
5972 | ||
5973 | o coding-category-iso-7-tight | |
5974 | ||
5975 | Same as coding-category-iso-7 except that this can | |
5976 | encode/decode only the specified charsets. | |
4ed46869 KH |
5977 | |
5978 | o coding-category-iso-8-1 | |
5979 | ||
5980 | The category for a coding system which has the same code range | |
5981 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5982 | for DIMENSION1 charset. This doesn't use any locking shift |
5983 | and single shift functions. Assigned the coding-system (Lisp | |
5984 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
5985 | |
5986 | o coding-category-iso-8-2 | |
5987 | ||
5988 | The category for a coding system which has the same code range | |
5989 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
5990 | for DIMENSION2 charset. This doesn't use any locking shift |
5991 | and single shift functions. Assigned the coding-system (Lisp | |
5992 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 5993 | |
7717c392 | 5994 | o coding-category-iso-7-else |
4ed46869 KH |
5995 | |
5996 | The category for a coding system which has the same code range | |
ad1746f5 | 5997 | as ISO2022 of 7-bit environment but uses locking shift or |
7717c392 KH |
5998 | single shift functions. Assigned the coding-system (Lisp |
5999 | symbol) `iso-2022-7bit-lock' by default. | |
6000 | ||
6001 | o coding-category-iso-8-else | |
6002 | ||
6003 | The category for a coding system which has the same code range | |
ad1746f5 | 6004 | as ISO2022 of 8-bit environment but uses locking shift or |
7717c392 KH |
6005 | single shift functions. Assigned the coding-system (Lisp |
6006 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
6007 | |
6008 | o coding-category-big5 | |
6009 | ||
6010 | The category for a coding system which has the same code range | |
6011 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6012 | `cn-big5' by default. |
4ed46869 | 6013 | |
fa42c37f KH |
6014 | o coding-category-utf-8 |
6015 | ||
6016 | The category for a coding system which has the same code range | |
6e76ae91 | 6017 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
6018 | symbol) `utf-8' by default. |
6019 | ||
6020 | o coding-category-utf-16-be | |
6021 | ||
6022 | The category for a coding system in which a text has an | |
6023 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
6024 | endian at the head. Assigned the coding-system (Lisp symbol) | |
6025 | `utf-16-be' by default. | |
6026 | ||
6027 | o coding-category-utf-16-le | |
6028 | ||
6029 | The category for a coding system in which a text has an | |
6030 | Unicode signature (cf. Unicode Standard) in the order of | |
6031 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
6032 | symbol) `utf-16-le' by default. | |
6033 | ||
1397dc18 KH |
6034 | o coding-category-ccl |
6035 | ||
6036 | The category for a coding system of which encoder/decoder is | |
6037 | written in CCL programs. The default value is nil, i.e., no | |
6038 | coding system is assigned. | |
6039 | ||
4ed46869 KH |
6040 | o coding-category-binary |
6041 | ||
6042 | The category for a coding system not categorized in any of the | |
6043 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6044 | `no-conversion' by default. |
4ed46869 KH |
6045 | |
6046 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 6047 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
6048 | What Emacs does actually is to detect a category of coding system. |
6049 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 6050 | decide only one possible category, it selects a category of the |
4ed46869 KH |
6051 | highest priority. Priorities of categories are also specified by a |
6052 | user in a Lisp variable `coding-category-list'. | |
6053 | ||
6054 | */ | |
6055 | ||
df7492f9 KH |
6056 | #define EOL_SEEN_NONE 0 |
6057 | #define EOL_SEEN_LF 1 | |
6058 | #define EOL_SEEN_CR 2 | |
6059 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 6060 | |
ff0dacd7 KH |
6061 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
6062 | SOURCE is encoded. If CATEGORY is one of | |
6063 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
6064 | two-byte, else they are encoded by one-byte. | |
6065 | ||
6066 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 6067 | |
bc4bc72a | 6068 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
6069 | |
6070 | static int | |
d311d28c | 6071 | detect_eol (const unsigned char *source, ptrdiff_t src_bytes, |
cf84bb53 | 6072 | enum coding_category category) |
4ed46869 | 6073 | { |
f6cbaf43 | 6074 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 6075 | unsigned char c; |
df7492f9 KH |
6076 | int total = 0; |
6077 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 6078 | |
89528eb3 | 6079 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 6080 | { |
f10fe38f PE |
6081 | bool msb = category == (coding_category_utf_16_le |
6082 | | coding_category_utf_16_le_nosig); | |
6083 | bool lsb = !msb; | |
fa42c37f | 6084 | |
df7492f9 | 6085 | while (src + 1 < src_end) |
fa42c37f | 6086 | { |
df7492f9 KH |
6087 | c = src[lsb]; |
6088 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 6089 | { |
df7492f9 KH |
6090 | int this_eol; |
6091 | ||
6092 | if (c == '\n') | |
6093 | this_eol = EOL_SEEN_LF; | |
6094 | else if (src + 3 >= src_end | |
6095 | || src[msb + 2] != 0 | |
6096 | || src[lsb + 2] != '\n') | |
6097 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 6098 | else |
75f4f1ac EZ |
6099 | { |
6100 | this_eol = EOL_SEEN_CRLF; | |
6101 | src += 2; | |
6102 | } | |
df7492f9 KH |
6103 | |
6104 | if (eol_seen == EOL_SEEN_NONE) | |
6105 | /* This is the first end-of-line. */ | |
6106 | eol_seen = this_eol; | |
6107 | else if (eol_seen != this_eol) | |
fa42c37f | 6108 | { |
75f4f1ac EZ |
6109 | /* The found type is different from what found before. |
6110 | Allow for stray ^M characters in DOS EOL files. */ | |
ef1b0ba7 SM |
6111 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) |
6112 | || (eol_seen == EOL_SEEN_CRLF | |
6113 | && this_eol == EOL_SEEN_CR)) | |
75f4f1ac EZ |
6114 | eol_seen = EOL_SEEN_CRLF; |
6115 | else | |
6116 | { | |
6117 | eol_seen = EOL_SEEN_LF; | |
6118 | break; | |
6119 | } | |
fa42c37f | 6120 | } |
df7492f9 KH |
6121 | if (++total == MAX_EOL_CHECK_COUNT) |
6122 | break; | |
fa42c37f | 6123 | } |
df7492f9 | 6124 | src += 2; |
fa42c37f | 6125 | } |
bcf26d6a | 6126 | } |
d46c5b12 | 6127 | else |
ef1b0ba7 SM |
6128 | while (src < src_end) |
6129 | { | |
6130 | c = *src++; | |
6131 | if (c == '\n' || c == '\r') | |
6132 | { | |
6133 | int this_eol; | |
d46c5b12 | 6134 | |
ef1b0ba7 SM |
6135 | if (c == '\n') |
6136 | this_eol = EOL_SEEN_LF; | |
6137 | else if (src >= src_end || *src != '\n') | |
6138 | this_eol = EOL_SEEN_CR; | |
6139 | else | |
6140 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 6141 | |
ef1b0ba7 SM |
6142 | if (eol_seen == EOL_SEEN_NONE) |
6143 | /* This is the first end-of-line. */ | |
6144 | eol_seen = this_eol; | |
6145 | else if (eol_seen != this_eol) | |
6146 | { | |
6147 | /* The found type is different from what found before. | |
6148 | Allow for stray ^M characters in DOS EOL files. */ | |
6149 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) | |
6150 | || (eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR)) | |
6151 | eol_seen = EOL_SEEN_CRLF; | |
6152 | else | |
6153 | { | |
6154 | eol_seen = EOL_SEEN_LF; | |
6155 | break; | |
6156 | } | |
6157 | } | |
6158 | if (++total == MAX_EOL_CHECK_COUNT) | |
6159 | break; | |
6160 | } | |
6161 | } | |
df7492f9 | 6162 | return eol_seen; |
73be902c KH |
6163 | } |
6164 | ||
df7492f9 | 6165 | |
24a73b0a | 6166 | static Lisp_Object |
971de7fb | 6167 | adjust_coding_eol_type (struct coding_system *coding, int eol_seen) |
73be902c | 6168 | { |
0be8721c | 6169 | Lisp_Object eol_type; |
8f924df7 | 6170 | |
df7492f9 KH |
6171 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6172 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
6173 | { |
6174 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6175 | eol_type = Qunix; | |
6176 | } | |
6f197c07 | 6177 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
6178 | { |
6179 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
6180 | eol_type = Qdos; | |
6181 | } | |
6f197c07 | 6182 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
6183 | { |
6184 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
6185 | eol_type = Qmac; | |
6186 | } | |
6187 | return eol_type; | |
d46c5b12 | 6188 | } |
4ed46869 | 6189 | |
df7492f9 KH |
6190 | /* Detect how a text specified in CODING is encoded. If a coding |
6191 | system is detected, update fields of CODING by the detected coding | |
6192 | system. */ | |
0a28aafb | 6193 | |
74ab6df5 | 6194 | static void |
971de7fb | 6195 | detect_coding (struct coding_system *coding) |
d46c5b12 | 6196 | { |
8f924df7 | 6197 | const unsigned char *src, *src_end; |
f10fe38f | 6198 | unsigned int saved_mode = coding->mode; |
d46c5b12 | 6199 | |
df7492f9 KH |
6200 | coding->consumed = coding->consumed_char = 0; |
6201 | coding->produced = coding->produced_char = 0; | |
6202 | coding_set_source (coding); | |
1c3478b0 | 6203 | |
df7492f9 | 6204 | src_end = coding->source + coding->src_bytes; |
c0e16b14 | 6205 | coding->head_ascii = 0; |
1c3478b0 | 6206 | |
df7492f9 KH |
6207 | /* If we have not yet decided the text encoding type, detect it |
6208 | now. */ | |
6209 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 6210 | { |
df7492f9 | 6211 | int c, i; |
6cb21a4f | 6212 | struct coding_detection_info detect_info; |
f10fe38f | 6213 | bool null_byte_found = 0, eight_bit_found = 0; |
df7492f9 | 6214 | |
6cb21a4f | 6215 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 6216 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 6217 | { |
df7492f9 | 6218 | c = *src; |
6cb21a4f | 6219 | if (c & 0x80) |
6cb21a4f | 6220 | { |
2f3cbb32 | 6221 | eight_bit_found = 1; |
2f3cbb32 KH |
6222 | if (null_byte_found) |
6223 | break; | |
6224 | } | |
6225 | else if (c < 0x20) | |
6226 | { | |
6227 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
6228 | && ! inhibit_iso_escape_detection | |
6229 | && ! detect_info.checked) | |
6cb21a4f | 6230 | { |
2f3cbb32 KH |
6231 | if (detect_coding_iso_2022 (coding, &detect_info)) |
6232 | { | |
6233 | /* We have scanned the whole data. */ | |
6234 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
6235 | { |
6236 | /* We didn't find an 8-bit code. We may | |
6237 | have found a null-byte, but it's very | |
ce5b453a | 6238 | rare that a binary file conforms to |
c0e16b14 KH |
6239 | ISO-2022. */ |
6240 | src = src_end; | |
6241 | coding->head_ascii = src - coding->source; | |
6242 | } | |
6243 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
6244 | break; |
6245 | } | |
6246 | } | |
97b1b294 | 6247 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
6248 | { |
6249 | null_byte_found = 1; | |
6250 | if (eight_bit_found) | |
6251 | break; | |
6cb21a4f | 6252 | } |
c006c0c8 KH |
6253 | if (! eight_bit_found) |
6254 | coding->head_ascii++; | |
6cb21a4f | 6255 | } |
c006c0c8 | 6256 | else if (! eight_bit_found) |
c0e16b14 | 6257 | coding->head_ascii++; |
d46c5b12 | 6258 | } |
df7492f9 | 6259 | |
2f3cbb32 KH |
6260 | if (null_byte_found || eight_bit_found |
6261 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 6262 | || detect_info.found) |
d46c5b12 | 6263 | { |
ff0dacd7 KH |
6264 | enum coding_category category; |
6265 | struct coding_system *this; | |
df7492f9 | 6266 | |
6cb21a4f KH |
6267 | if (coding->head_ascii == coding->src_bytes) |
6268 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
6269 | for (i = 0; i < coding_category_raw_text; i++) | |
6270 | { | |
6271 | category = coding_priorities[i]; | |
6272 | this = coding_categories + category; | |
6273 | if (detect_info.found & (1 << category)) | |
24a73b0a | 6274 | break; |
6cb21a4f KH |
6275 | } |
6276 | else | |
2f3cbb32 KH |
6277 | { |
6278 | if (null_byte_found) | |
ff0dacd7 | 6279 | { |
2f3cbb32 KH |
6280 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
6281 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 6282 | } |
2f3cbb32 KH |
6283 | for (i = 0; i < coding_category_raw_text; i++) |
6284 | { | |
6285 | category = coding_priorities[i]; | |
6286 | this = coding_categories + category; | |
6287 | if (this->id < 0) | |
6288 | { | |
6289 | /* No coding system of this category is defined. */ | |
6290 | detect_info.rejected |= (1 << category); | |
6291 | } | |
6292 | else if (category >= coding_category_raw_text) | |
6293 | continue; | |
6294 | else if (detect_info.checked & (1 << category)) | |
6295 | { | |
6296 | if (detect_info.found & (1 << category)) | |
6297 | break; | |
6298 | } | |
6299 | else if ((*(this->detector)) (coding, &detect_info) | |
6300 | && detect_info.found & (1 << category)) | |
6301 | { | |
6302 | if (category == coding_category_utf_16_auto) | |
6303 | { | |
6304 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6305 | category = coding_category_utf_16_le; | |
6306 | else | |
6307 | category = coding_category_utf_16_be; | |
6308 | } | |
6309 | break; | |
6310 | } | |
6311 | } | |
2f3cbb32 | 6312 | } |
c0e16b14 KH |
6313 | |
6314 | if (i < coding_category_raw_text) | |
6315 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6316 | else if (null_byte_found) | |
6317 | setup_coding_system (Qno_conversion, coding); | |
6318 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) | |
6319 | == CATEGORY_MASK_ANY) | |
6320 | setup_coding_system (Qraw_text, coding); | |
6321 | else if (detect_info.rejected) | |
6322 | for (i = 0; i < coding_category_raw_text; i++) | |
6323 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6324 | { | |
6325 | this = coding_categories + coding_priorities[i]; | |
6326 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6327 | break; | |
6328 | } | |
d46c5b12 | 6329 | } |
b73bfc1c | 6330 | } |
a470d443 KH |
6331 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6332 | == coding_category_utf_8_auto) | |
6333 | { | |
6334 | Lisp_Object coding_systems; | |
6335 | struct coding_detection_info detect_info; | |
6336 | ||
6337 | coding_systems | |
6338 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6339 | detect_info.found = detect_info.rejected = 0; | |
6340 | coding->head_ascii = 0; | |
6341 | if (CONSP (coding_systems) | |
6342 | && detect_coding_utf_8 (coding, &detect_info)) | |
6343 | { | |
6344 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6345 | setup_coding_system (XCAR (coding_systems), coding); | |
6346 | else | |
6347 | setup_coding_system (XCDR (coding_systems), coding); | |
6348 | } | |
6349 | } | |
24a73b0a KH |
6350 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6351 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6352 | { |
6353 | Lisp_Object coding_systems; | |
6354 | struct coding_detection_info detect_info; | |
6355 | ||
6356 | coding_systems | |
a470d443 | 6357 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6358 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6359 | coding->head_ascii = 0; |
b49a1807 | 6360 | if (CONSP (coding_systems) |
24a73b0a | 6361 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6362 | { |
6363 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6364 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 6365 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
6366 | setup_coding_system (XCDR (coding_systems), coding); |
6367 | } | |
6368 | } | |
73cce38d | 6369 | coding->mode = saved_mode; |
4ed46869 | 6370 | } |
4ed46869 | 6371 | |
d46c5b12 | 6372 | |
aaaf0b1e | 6373 | static void |
971de7fb | 6374 | decode_eol (struct coding_system *coding) |
aaaf0b1e | 6375 | { |
24a73b0a KH |
6376 | Lisp_Object eol_type; |
6377 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6378 | |
24a73b0a | 6379 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
0a9564cb | 6380 | if (EQ (eol_type, Qunix) || inhibit_eol_conversion) |
24a73b0a KH |
6381 | return; |
6382 | ||
6383 | if (NILP (coding->dst_object)) | |
6384 | pbeg = coding->destination; | |
6385 | else | |
6386 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6387 | pend = pbeg + coding->produced; | |
6388 | ||
6389 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6390 | { |
df7492f9 | 6391 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6392 | |
24a73b0a | 6393 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6394 | { |
df7492f9 KH |
6395 | if (*p == '\n') |
6396 | eol_seen |= EOL_SEEN_LF; | |
6397 | else if (*p == '\r') | |
aaaf0b1e | 6398 | { |
df7492f9 | 6399 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6400 | { |
df7492f9 KH |
6401 | eol_seen |= EOL_SEEN_CRLF; |
6402 | p++; | |
aaaf0b1e | 6403 | } |
aaaf0b1e | 6404 | else |
df7492f9 | 6405 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6406 | } |
aaaf0b1e | 6407 | } |
75f4f1ac EZ |
6408 | /* Handle DOS-style EOLs in a file with stray ^M characters. */ |
6409 | if ((eol_seen & EOL_SEEN_CRLF) != 0 | |
6410 | && (eol_seen & EOL_SEEN_CR) != 0 | |
6411 | && (eol_seen & EOL_SEEN_LF) == 0) | |
6412 | eol_seen = EOL_SEEN_CRLF; | |
6413 | else if (eol_seen != EOL_SEEN_NONE | |
24a73b0a KH |
6414 | && eol_seen != EOL_SEEN_LF |
6415 | && eol_seen != EOL_SEEN_CRLF | |
6416 | && eol_seen != EOL_SEEN_CR) | |
6417 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6418 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6419 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6420 | } |
d46c5b12 | 6421 | |
24a73b0a | 6422 | if (EQ (eol_type, Qmac)) |
27901516 | 6423 | { |
24a73b0a | 6424 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6425 | if (*p == '\r') |
6426 | *p = '\n'; | |
4ed46869 | 6427 | } |
24a73b0a | 6428 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6429 | { |
d311d28c | 6430 | ptrdiff_t n = 0; |
b73bfc1c | 6431 | |
24a73b0a KH |
6432 | if (NILP (coding->dst_object)) |
6433 | { | |
4347441b KH |
6434 | /* Start deleting '\r' from the tail to minimize the memory |
6435 | movement. */ | |
24a73b0a KH |
6436 | for (p = pend - 2; p >= pbeg; p--) |
6437 | if (*p == '\r') | |
6438 | { | |
72af86bd | 6439 | memmove (p, p + 1, pend-- - p - 1); |
24a73b0a KH |
6440 | n++; |
6441 | } | |
6442 | } | |
6443 | else | |
6444 | { | |
d311d28c PE |
6445 | ptrdiff_t pos_byte = coding->dst_pos_byte; |
6446 | ptrdiff_t pos = coding->dst_pos; | |
6447 | ptrdiff_t pos_end = pos + coding->produced_char - 1; | |
4347441b KH |
6448 | |
6449 | while (pos < pos_end) | |
6450 | { | |
6451 | p = BYTE_POS_ADDR (pos_byte); | |
6452 | if (*p == '\r' && p[1] == '\n') | |
6453 | { | |
6454 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6455 | n++; | |
6456 | pos_end--; | |
6457 | } | |
6458 | pos++; | |
69b8522d KH |
6459 | if (coding->dst_multibyte) |
6460 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6461 | else | |
6462 | pos_byte++; | |
4347441b | 6463 | } |
24a73b0a KH |
6464 | } |
6465 | coding->produced -= n; | |
6466 | coding->produced_char -= n; | |
aaaf0b1e | 6467 | } |
4ed46869 KH |
6468 | } |
6469 | ||
7d64c6ad | 6470 | |
a6f87d34 | 6471 | /* Return a translation table (or list of them) from coding system |
f10fe38f PE |
6472 | attribute vector ATTRS for encoding (if ENCODEP) or decoding (if |
6473 | not ENCODEP). */ | |
7d64c6ad | 6474 | |
e6a54062 | 6475 | static Lisp_Object |
f10fe38f | 6476 | get_translation_table (Lisp_Object attrs, bool encodep, int *max_lookup) |
7d64c6ad KH |
6477 | { |
6478 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6479 | Lisp_Object val; |
7d64c6ad | 6480 | |
4bed5909 CY |
6481 | if (NILP (Venable_character_translation)) |
6482 | { | |
6483 | if (max_lookup) | |
6484 | *max_lookup = 0; | |
6485 | return Qnil; | |
6486 | } | |
7d64c6ad KH |
6487 | if (encodep) |
6488 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6489 | standard = Vstandard_translation_table_for_encode; | |
6490 | else | |
6491 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6492 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6493 | if (NILP (translation_table)) |
09ee6fdd KH |
6494 | translation_table = standard; |
6495 | else | |
a6f87d34 | 6496 | { |
09ee6fdd KH |
6497 | if (SYMBOLP (translation_table)) |
6498 | translation_table = Fget (translation_table, Qtranslation_table); | |
6499 | else if (CONSP (translation_table)) | |
6500 | { | |
6501 | translation_table = Fcopy_sequence (translation_table); | |
6502 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6503 | if (SYMBOLP (XCAR (val))) | |
6504 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6505 | } | |
6506 | if (CHAR_TABLE_P (standard)) | |
6507 | { | |
6508 | if (CONSP (translation_table)) | |
6509 | translation_table = nconc2 (translation_table, | |
6510 | Fcons (standard, Qnil)); | |
6511 | else | |
6512 | translation_table = Fcons (translation_table, | |
6513 | Fcons (standard, Qnil)); | |
6514 | } | |
a6f87d34 | 6515 | } |
2170c8f0 KH |
6516 | |
6517 | if (max_lookup) | |
09ee6fdd | 6518 | { |
2170c8f0 KH |
6519 | *max_lookup = 1; |
6520 | if (CHAR_TABLE_P (translation_table) | |
6521 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6522 | { | |
6523 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6524 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6525 | *max_lookup = XFASTINT (val); | |
6526 | } | |
6527 | else if (CONSP (translation_table)) | |
6528 | { | |
2735d060 | 6529 | Lisp_Object tail; |
09ee6fdd | 6530 | |
2170c8f0 KH |
6531 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6532 | if (CHAR_TABLE_P (XCAR (tail)) | |
6533 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6534 | { | |
2735d060 PE |
6535 | Lisp_Object tailval = XCHAR_TABLE (XCAR (tail))->extras[1]; |
6536 | if (NATNUMP (tailval) && *max_lookup < XFASTINT (tailval)) | |
6537 | *max_lookup = XFASTINT (tailval); | |
2170c8f0 KH |
6538 | } |
6539 | } | |
a6f87d34 | 6540 | } |
7d64c6ad KH |
6541 | return translation_table; |
6542 | } | |
6543 | ||
09ee6fdd KH |
6544 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6545 | do { \ | |
6546 | trans = Qnil; \ | |
6547 | if (CHAR_TABLE_P (table)) \ | |
6548 | { \ | |
6549 | trans = CHAR_TABLE_REF (table, c); \ | |
6550 | if (CHARACTERP (trans)) \ | |
6551 | c = XFASTINT (trans), trans = Qnil; \ | |
6552 | } \ | |
6553 | else if (CONSP (table)) \ | |
6554 | { \ | |
6555 | Lisp_Object tail; \ | |
6556 | \ | |
6557 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6558 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6559 | { \ | |
6560 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6561 | if (CHARACTERP (trans)) \ | |
6562 | c = XFASTINT (trans), trans = Qnil; \ | |
6563 | else if (! NILP (trans)) \ | |
6564 | break; \ | |
6565 | } \ | |
6566 | } \ | |
e6a54062 KH |
6567 | } while (0) |
6568 | ||
7d64c6ad | 6569 | |
e951386e KH |
6570 | /* Return a translation of character(s) at BUF according to TRANS. |
6571 | TRANS is TO-CHAR or ((FROM . TO) ...) where | |
6572 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | |
6573 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | |
6574 | translation is found, and Qnil if not found.. | |
6575 | If BUF is too short to lookup characters in FROM, return Qt. */ | |
6576 | ||
69a80ea3 | 6577 | static Lisp_Object |
971de7fb | 6578 | get_translation (Lisp_Object trans, int *buf, int *buf_end) |
69a80ea3 | 6579 | { |
e951386e KH |
6580 | |
6581 | if (INTEGERP (trans)) | |
6582 | return trans; | |
6583 | for (; CONSP (trans); trans = XCDR (trans)) | |
69a80ea3 | 6584 | { |
e951386e KH |
6585 | Lisp_Object val = XCAR (trans); |
6586 | Lisp_Object from = XCAR (val); | |
2c6a9faa PE |
6587 | ptrdiff_t len = ASIZE (from); |
6588 | ptrdiff_t i; | |
69a80ea3 | 6589 | |
e951386e | 6590 | for (i = 0; i < len; i++) |
69a80ea3 | 6591 | { |
e951386e KH |
6592 | if (buf + i == buf_end) |
6593 | return Qt; | |
6594 | if (XINT (AREF (from, i)) != buf[i]) | |
6595 | break; | |
69a80ea3 | 6596 | } |
e951386e KH |
6597 | if (i == len) |
6598 | return val; | |
69a80ea3 | 6599 | } |
e951386e | 6600 | return Qnil; |
69a80ea3 KH |
6601 | } |
6602 | ||
6603 | ||
d46c5b12 | 6604 | static int |
cf84bb53 | 6605 | produce_chars (struct coding_system *coding, Lisp_Object translation_table, |
f10fe38f | 6606 | bool last_block) |
4ed46869 | 6607 | { |
df7492f9 KH |
6608 | unsigned char *dst = coding->destination + coding->produced; |
6609 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c PE |
6610 | ptrdiff_t produced; |
6611 | ptrdiff_t produced_chars = 0; | |
69a80ea3 | 6612 | int carryover = 0; |
4ed46869 | 6613 | |
df7492f9 | 6614 | if (! coding->chars_at_source) |
4ed46869 | 6615 | { |
119852e7 | 6616 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6617 | int *buf = coding->charbuf; |
6618 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6619 | |
db274c7a KH |
6620 | if (EQ (coding->src_object, coding->dst_object)) |
6621 | { | |
6622 | coding_set_source (coding); | |
6623 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6624 | } | |
4ed46869 | 6625 | |
df7492f9 | 6626 | while (buf < buf_end) |
4ed46869 | 6627 | { |
27bb1ca4 PE |
6628 | int c = *buf; |
6629 | ptrdiff_t i; | |
bc4bc72a | 6630 | |
df7492f9 KH |
6631 | if (c >= 0) |
6632 | { | |
d311d28c | 6633 | ptrdiff_t from_nchars = 1, to_nchars = 1; |
69a80ea3 KH |
6634 | Lisp_Object trans = Qnil; |
6635 | ||
09ee6fdd | 6636 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6637 | if (! NILP (trans)) |
69a80ea3 | 6638 | { |
e951386e KH |
6639 | trans = get_translation (trans, buf, buf_end); |
6640 | if (INTEGERP (trans)) | |
6641 | c = XINT (trans); | |
6642 | else if (CONSP (trans)) | |
6643 | { | |
6644 | from_nchars = ASIZE (XCAR (trans)); | |
6645 | trans = XCDR (trans); | |
6646 | if (INTEGERP (trans)) | |
6647 | c = XINT (trans); | |
6648 | else | |
6649 | { | |
6650 | to_nchars = ASIZE (trans); | |
6651 | c = XINT (AREF (trans, 0)); | |
6652 | } | |
6653 | } | |
6654 | else if (EQ (trans, Qt) && ! last_block) | |
69a80ea3 | 6655 | break; |
69a80ea3 KH |
6656 | } |
6657 | ||
5d009b3a | 6658 | if ((dst_end - dst) / MAX_MULTIBYTE_LENGTH < to_nchars) |
69a80ea3 | 6659 | { |
5d009b3a PE |
6660 | if (((min (PTRDIFF_MAX, SIZE_MAX) - (buf_end - buf)) |
6661 | / MAX_MULTIBYTE_LENGTH) | |
6662 | < to_nchars) | |
6663 | memory_full (SIZE_MAX); | |
69a80ea3 KH |
6664 | dst = alloc_destination (coding, |
6665 | buf_end - buf | |
6666 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
6667 | dst); | |
db274c7a KH |
6668 | if (EQ (coding->src_object, coding->dst_object)) |
6669 | { | |
6670 | coding_set_source (coding); | |
e951386e KH |
6671 | dst_end = (((unsigned char *) coding->source) |
6672 | + coding->consumed); | |
db274c7a KH |
6673 | } |
6674 | else | |
6675 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
6676 | } |
6677 | ||
433f7f87 | 6678 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 6679 | { |
433f7f87 KH |
6680 | if (i > 0) |
6681 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
6682 | if (coding->dst_multibyte |
6683 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 6684 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
6685 | else |
6686 | *dst++ = CHAR_TO_BYTE8 (c); | |
6687 | } | |
6688 | produced_chars += to_nchars; | |
e951386e | 6689 | buf += from_nchars; |
d46c5b12 | 6690 | } |
df7492f9 | 6691 | else |
69a80ea3 KH |
6692 | /* This is an annotation datum. (-C) is the length. */ |
6693 | buf += -c; | |
4ed46869 | 6694 | } |
69a80ea3 | 6695 | carryover = buf_end - buf; |
4ed46869 | 6696 | } |
fa42c37f | 6697 | else |
fa42c37f | 6698 | { |
119852e7 | 6699 | /* Source characters are at coding->source. */ |
8f924df7 | 6700 | const unsigned char *src = coding->source; |
119852e7 | 6701 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 6702 | |
db274c7a KH |
6703 | if (EQ (coding->dst_object, coding->src_object)) |
6704 | dst_end = (unsigned char *) src; | |
df7492f9 | 6705 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 6706 | { |
df7492f9 | 6707 | if (coding->src_multibyte) |
fa42c37f | 6708 | { |
f10fe38f | 6709 | bool multibytep = 1; |
d311d28c | 6710 | ptrdiff_t consumed_chars = 0; |
d46c5b12 | 6711 | |
df7492f9 KH |
6712 | while (1) |
6713 | { | |
8f924df7 | 6714 | const unsigned char *src_base = src; |
df7492f9 | 6715 | int c; |
b73bfc1c | 6716 | |
df7492f9 | 6717 | ONE_MORE_BYTE (c); |
119852e7 | 6718 | if (dst == dst_end) |
df7492f9 | 6719 | { |
119852e7 KH |
6720 | if (EQ (coding->src_object, coding->dst_object)) |
6721 | dst_end = (unsigned char *) src; | |
6722 | if (dst == dst_end) | |
df7492f9 | 6723 | { |
d311d28c | 6724 | ptrdiff_t offset = src - coding->source; |
119852e7 KH |
6725 | |
6726 | dst = alloc_destination (coding, src_end - src + 1, | |
6727 | dst); | |
6728 | dst_end = coding->destination + coding->dst_bytes; | |
6729 | coding_set_source (coding); | |
6730 | src = coding->source + offset; | |
5c1ca13d | 6731 | src_end = coding->source + coding->consumed; |
db274c7a KH |
6732 | if (EQ (coding->src_object, coding->dst_object)) |
6733 | dst_end = (unsigned char *) src; | |
df7492f9 | 6734 | } |
df7492f9 KH |
6735 | } |
6736 | *dst++ = c; | |
6737 | produced_chars++; | |
6738 | } | |
6739 | no_more_source: | |
6740 | ; | |
fa42c37f KH |
6741 | } |
6742 | else | |
df7492f9 KH |
6743 | while (src < src_end) |
6744 | { | |
f10fe38f | 6745 | bool multibytep = 1; |
df7492f9 | 6746 | int c = *src++; |
b73bfc1c | 6747 | |
df7492f9 KH |
6748 | if (dst >= dst_end - 1) |
6749 | { | |
2c78b7e1 | 6750 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 6751 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
6752 | if (dst >= dst_end - 1) |
6753 | { | |
d311d28c PE |
6754 | ptrdiff_t offset = src - coding->source; |
6755 | ptrdiff_t more_bytes; | |
119852e7 | 6756 | |
db274c7a KH |
6757 | if (EQ (coding->src_object, coding->dst_object)) |
6758 | more_bytes = ((src_end - src) / 2) + 2; | |
6759 | else | |
6760 | more_bytes = src_end - src + 2; | |
6761 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
6762 | dst_end = coding->destination + coding->dst_bytes; |
6763 | coding_set_source (coding); | |
119852e7 | 6764 | src = coding->source + offset; |
5c1ca13d | 6765 | src_end = coding->source + coding->consumed; |
db274c7a KH |
6766 | if (EQ (coding->src_object, coding->dst_object)) |
6767 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 6768 | } |
df7492f9 KH |
6769 | } |
6770 | EMIT_ONE_BYTE (c); | |
6771 | } | |
d46c5b12 | 6772 | } |
df7492f9 KH |
6773 | else |
6774 | { | |
6775 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 6776 | { |
d311d28c | 6777 | ptrdiff_t require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 6778 | |
df7492f9 | 6779 | if (require > 0) |
fa42c37f | 6780 | { |
d311d28c | 6781 | ptrdiff_t offset = src - coding->source; |
df7492f9 KH |
6782 | |
6783 | dst = alloc_destination (coding, require, dst); | |
6784 | coding_set_source (coding); | |
6785 | src = coding->source + offset; | |
5c1ca13d | 6786 | src_end = coding->source + coding->consumed; |
fa42c37f KH |
6787 | } |
6788 | } | |
119852e7 | 6789 | produced_chars = coding->consumed_char; |
df7492f9 | 6790 | while (src < src_end) |
14daee73 | 6791 | *dst++ = *src++; |
fa42c37f KH |
6792 | } |
6793 | } | |
6794 | ||
df7492f9 | 6795 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 6796 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
df7492f9 KH |
6797 | insert_from_gap (produced_chars, produced); |
6798 | coding->produced += produced; | |
6799 | coding->produced_char += produced_chars; | |
69a80ea3 | 6800 | return carryover; |
fa42c37f KH |
6801 | } |
6802 | ||
ff0dacd7 KH |
6803 | /* Compose text in CODING->object according to the annotation data at |
6804 | CHARBUF. CHARBUF is an array: | |
e951386e | 6805 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
df7492f9 | 6806 | */ |
4ed46869 | 6807 | |
55d4c1b2 | 6808 | static inline void |
d311d28c | 6809 | produce_composition (struct coding_system *coding, int *charbuf, ptrdiff_t pos) |
4ed46869 | 6810 | { |
df7492f9 | 6811 | int len; |
d311d28c | 6812 | ptrdiff_t to; |
df7492f9 | 6813 | enum composition_method method; |
df7492f9 | 6814 | Lisp_Object components; |
fa42c37f | 6815 | |
e951386e | 6816 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
69a80ea3 | 6817 | to = pos + charbuf[2]; |
e951386e | 6818 | method = (enum composition_method) (charbuf[4]); |
d46c5b12 | 6819 | |
df7492f9 KH |
6820 | if (method == COMPOSITION_RELATIVE) |
6821 | components = Qnil; | |
e951386e | 6822 | else |
d46c5b12 | 6823 | { |
df7492f9 | 6824 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
e951386e | 6825 | int i, j; |
b73bfc1c | 6826 | |
e951386e KH |
6827 | if (method == COMPOSITION_WITH_RULE) |
6828 | len = charbuf[2] * 3 - 2; | |
6829 | charbuf += MAX_ANNOTATION_LENGTH; | |
6830 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | |
6831 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | |
9ffd559c | 6832 | { |
e951386e KH |
6833 | if (charbuf[i] >= 0) |
6834 | args[j] = make_number (charbuf[i]); | |
6835 | else | |
6836 | { | |
6837 | i++; | |
6838 | args[j] = make_number (charbuf[i] % 0x100); | |
6839 | } | |
9ffd559c | 6840 | } |
e951386e | 6841 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
d46c5b12 | 6842 | } |
69a80ea3 | 6843 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6844 | } |
6845 | ||
d46c5b12 | 6846 | |
ff0dacd7 KH |
6847 | /* Put `charset' property on text in CODING->object according to |
6848 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6849 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6850 | */ |
d46c5b12 | 6851 | |
55d4c1b2 | 6852 | static inline void |
d311d28c | 6853 | produce_charset (struct coding_system *coding, int *charbuf, ptrdiff_t pos) |
d46c5b12 | 6854 | { |
d311d28c | 6855 | ptrdiff_t from = pos - charbuf[2]; |
69a80ea3 | 6856 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); |
b73bfc1c | 6857 | |
69a80ea3 | 6858 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6859 | Qcharset, CHARSET_NAME (charset), |
6860 | coding->dst_object); | |
d46c5b12 KH |
6861 | } |
6862 | ||
d46c5b12 | 6863 | |
df7492f9 KH |
6864 | #define CHARBUF_SIZE 0x4000 |
6865 | ||
6866 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6867 | do { \ | |
8510724d | 6868 | int size = CHARBUF_SIZE; \ |
df7492f9 KH |
6869 | \ |
6870 | coding->charbuf = NULL; \ | |
6871 | while (size > 1024) \ | |
6872 | { \ | |
38182d90 | 6873 | coding->charbuf = alloca (sizeof (int) * size); \ |
df7492f9 KH |
6874 | if (coding->charbuf) \ |
6875 | break; \ | |
6876 | size >>= 1; \ | |
6877 | } \ | |
6878 | if (! coding->charbuf) \ | |
6879 | { \ | |
065e3595 | 6880 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
f10fe38f | 6881 | return; \ |
df7492f9 KH |
6882 | } \ |
6883 | coding->charbuf_size = size; \ | |
6884 | } while (0) | |
4ed46869 | 6885 | |
d46c5b12 KH |
6886 | |
6887 | static void | |
d311d28c | 6888 | produce_annotation (struct coding_system *coding, ptrdiff_t pos) |
d46c5b12 | 6889 | { |
df7492f9 KH |
6890 | int *charbuf = coding->charbuf; |
6891 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6892 | |
ff0dacd7 KH |
6893 | if (NILP (coding->dst_object)) |
6894 | return; | |
d46c5b12 | 6895 | |
df7492f9 | 6896 | while (charbuf < charbuf_end) |
a84f1519 | 6897 | { |
df7492f9 | 6898 | if (*charbuf >= 0) |
e951386e | 6899 | pos++, charbuf++; |
d46c5b12 | 6900 | else |
d46c5b12 | 6901 | { |
df7492f9 | 6902 | int len = -*charbuf; |
e951386e KH |
6903 | |
6904 | if (len > 2) | |
6905 | switch (charbuf[1]) | |
6906 | { | |
6907 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
6908 | produce_composition (coding, charbuf, pos); | |
6909 | break; | |
6910 | case CODING_ANNOTATE_CHARSET_MASK: | |
6911 | produce_charset (coding, charbuf, pos); | |
6912 | break; | |
6913 | } | |
df7492f9 | 6914 | charbuf += len; |
d46c5b12 | 6915 | } |
a84f1519 | 6916 | } |
d46c5b12 KH |
6917 | } |
6918 | ||
df7492f9 KH |
6919 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6920 | CODING->src_object is a buffer, a string, or nil. | |
6921 | CODING->dst_object is a buffer. | |
d46c5b12 | 6922 | |
df7492f9 KH |
6923 | If CODING->src_object is a buffer, it must be the current buffer. |
6924 | In this case, if CODING->src_pos is positive, it is a position of | |
6925 | the source text in the buffer, otherwise, the source text is in the | |
6926 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
6927 | the text from GPT (which must be the same as PT). If this is the | |
6928 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6929 | negative. | |
d46c5b12 | 6930 | |
b6828792 | 6931 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 6932 | that string. |
d46c5b12 | 6933 | |
df7492f9 KH |
6934 | If CODING->src_object is nil, CODING->source must already point to |
6935 | the non-relocatable memory area. In this case, CODING->src_pos is | |
6936 | an offset from CODING->source. | |
73be902c | 6937 | |
df7492f9 KH |
6938 | The decoded data is inserted at the current point of the buffer |
6939 | CODING->dst_object. | |
6940 | */ | |
d46c5b12 | 6941 | |
f10fe38f | 6942 | static void |
971de7fb | 6943 | decode_coding (struct coding_system *coding) |
d46c5b12 | 6944 | { |
df7492f9 | 6945 | Lisp_Object attrs; |
24a73b0a | 6946 | Lisp_Object undo_list; |
7d64c6ad | 6947 | Lisp_Object translation_table; |
d0396581 | 6948 | struct ccl_spec cclspec; |
69a80ea3 KH |
6949 | int carryover; |
6950 | int i; | |
d46c5b12 | 6951 | |
df7492f9 KH |
6952 | if (BUFFERP (coding->src_object) |
6953 | && coding->src_pos > 0 | |
6954 | && coding->src_pos < GPT | |
6955 | && coding->src_pos + coding->src_chars > GPT) | |
6956 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 6957 | |
24a73b0a | 6958 | undo_list = Qt; |
df7492f9 | 6959 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 6960 | { |
a3d794a1 | 6961 | set_buffer_internal (XBUFFER (coding->dst_object)); |
df7492f9 KH |
6962 | if (GPT != PT) |
6963 | move_gap_both (PT, PT_BYTE); | |
f48b82fd GR |
6964 | |
6965 | /* We must disable undo_list in order to record the whole insert | |
6966 | transaction via record_insert at the end. But doing so also | |
6967 | disables the recording of the first change to the undo_list. | |
6968 | Therefore we check for first change here and record it via | |
6969 | record_first_change if needed. */ | |
6970 | if (MODIFF <= SAVE_MODIFF) | |
6971 | record_first_change (); | |
6972 | ||
4b4deea2 | 6973 | undo_list = BVAR (current_buffer, undo_list); |
39eb03f1 | 6974 | bset_undo_list (current_buffer, Qt); |
1c3478b0 KH |
6975 | } |
6976 | ||
df7492f9 KH |
6977 | coding->consumed = coding->consumed_char = 0; |
6978 | coding->produced = coding->produced_char = 0; | |
6979 | coding->chars_at_source = 0; | |
065e3595 | 6980 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 6981 | coding->errors = 0; |
1c3478b0 | 6982 | |
df7492f9 KH |
6983 | ALLOC_CONVERSION_WORK_AREA (coding); |
6984 | ||
6985 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 6986 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 6987 | |
69a80ea3 | 6988 | carryover = 0; |
d0396581 KH |
6989 | if (coding->decoder == decode_coding_ccl) |
6990 | { | |
6991 | coding->spec.ccl = &cclspec; | |
6992 | setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding)); | |
6993 | } | |
df7492f9 | 6994 | do |
b73bfc1c | 6995 | { |
d311d28c | 6996 | ptrdiff_t pos = coding->dst_pos + coding->produced_char; |
69a80ea3 | 6997 | |
df7492f9 KH |
6998 | coding_set_source (coding); |
6999 | coding->annotated = 0; | |
69a80ea3 | 7000 | coding->charbuf_used = carryover; |
df7492f9 | 7001 | (*(coding->decoder)) (coding); |
df7492f9 | 7002 | coding_set_destination (coding); |
69a80ea3 | 7003 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 7004 | if (coding->annotated) |
69a80ea3 KH |
7005 | produce_annotation (coding, pos); |
7006 | for (i = 0; i < carryover; i++) | |
7007 | coding->charbuf[i] | |
7008 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 7009 | } |
d0396581 KH |
7010 | while (coding->result == CODING_RESULT_INSUFFICIENT_DST |
7011 | || (coding->consumed < coding->src_bytes | |
7012 | && (coding->result == CODING_RESULT_SUCCESS | |
7013 | || coding->result == CODING_RESULT_INVALID_SRC))); | |
d46c5b12 | 7014 | |
69a80ea3 KH |
7015 | if (carryover > 0) |
7016 | { | |
7017 | coding_set_destination (coding); | |
7018 | coding->charbuf_used = carryover; | |
7019 | produce_chars (coding, translation_table, 1); | |
7020 | } | |
7021 | ||
df7492f9 KH |
7022 | coding->carryover_bytes = 0; |
7023 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 7024 | { |
df7492f9 | 7025 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 7026 | const unsigned char *src; |
df7492f9 KH |
7027 | |
7028 | coding_set_source (coding); | |
7029 | coding_set_destination (coding); | |
7030 | src = coding->source + coding->consumed; | |
7031 | ||
7032 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 7033 | { |
df7492f9 KH |
7034 | /* Flush out unprocessed data as binary chars. We are sure |
7035 | that the number of data is less than the size of | |
7036 | coding->charbuf. */ | |
065e3595 | 7037 | coding->charbuf_used = 0; |
b2dab6c8 JR |
7038 | coding->chars_at_source = 0; |
7039 | ||
df7492f9 | 7040 | while (nbytes-- > 0) |
1c3478b0 | 7041 | { |
df7492f9 | 7042 | int c = *src++; |
98725083 | 7043 | |
1c91457d KH |
7044 | if (c & 0x80) |
7045 | c = BYTE8_TO_CHAR (c); | |
7046 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 7047 | } |
f6cbaf43 | 7048 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 7049 | } |
d46c5b12 | 7050 | else |
df7492f9 KH |
7051 | { |
7052 | /* Record unprocessed bytes in coding->carryover. We are | |
7053 | sure that the number of data is less than the size of | |
7054 | coding->carryover. */ | |
7055 | unsigned char *p = coding->carryover; | |
7056 | ||
f289d375 KH |
7057 | if (nbytes > sizeof coding->carryover) |
7058 | nbytes = sizeof coding->carryover; | |
df7492f9 KH |
7059 | coding->carryover_bytes = nbytes; |
7060 | while (nbytes-- > 0) | |
7061 | *p++ = *src++; | |
1c3478b0 | 7062 | } |
df7492f9 | 7063 | coding->consumed = coding->src_bytes; |
b73bfc1c | 7064 | } |
69f76525 | 7065 | |
0a9564cb EZ |
7066 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix) |
7067 | && !inhibit_eol_conversion) | |
4347441b | 7068 | decode_eol (coding); |
24a73b0a KH |
7069 | if (BUFFERP (coding->dst_object)) |
7070 | { | |
39eb03f1 | 7071 | bset_undo_list (current_buffer, undo_list); |
24a73b0a KH |
7072 | record_insert (coding->dst_pos, coding->produced_char); |
7073 | } | |
4ed46869 KH |
7074 | } |
7075 | ||
aaaf0b1e | 7076 | |
e1c23804 | 7077 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
7078 | ending before LIMIT of CODING->src_object (buffer or string), store |
7079 | the data in BUF, set *STOP to a starting position of the next | |
7080 | composition (if any) or to LIMIT, and return the address of the | |
7081 | next element of BUF. | |
7082 | ||
7083 | If such an annotation is not found, set *STOP to a starting | |
7084 | position of a composition after POS (if any) or to LIMIT, and | |
7085 | return BUF. */ | |
7086 | ||
55d4c1b2 | 7087 | static inline int * |
d311d28c | 7088 | handle_composition_annotation (ptrdiff_t pos, ptrdiff_t limit, |
cf84bb53 | 7089 | struct coding_system *coding, int *buf, |
d311d28c | 7090 | ptrdiff_t *stop) |
aaaf0b1e | 7091 | { |
d311d28c | 7092 | ptrdiff_t start, end; |
ff0dacd7 | 7093 | Lisp_Object prop; |
aaaf0b1e | 7094 | |
ff0dacd7 KH |
7095 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
7096 | || end > limit) | |
7097 | *stop = limit; | |
7098 | else if (start > pos) | |
7099 | *stop = start; | |
7100 | else | |
aaaf0b1e | 7101 | { |
ff0dacd7 | 7102 | if (start == pos) |
aaaf0b1e | 7103 | { |
ff0dacd7 KH |
7104 | /* We found a composition. Store the corresponding |
7105 | annotation data in BUF. */ | |
7106 | int *head = buf; | |
7107 | enum composition_method method = COMPOSITION_METHOD (prop); | |
7108 | int nchars = COMPOSITION_LENGTH (prop); | |
7109 | ||
e951386e | 7110 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
ff0dacd7 | 7111 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 7112 | { |
ff0dacd7 | 7113 | Lisp_Object components; |
2c6a9faa | 7114 | ptrdiff_t i, len, i_byte; |
ff0dacd7 KH |
7115 | |
7116 | components = COMPOSITION_COMPONENTS (prop); | |
7117 | if (VECTORP (components)) | |
aaaf0b1e | 7118 | { |
77b37c05 | 7119 | len = ASIZE (components); |
ff0dacd7 KH |
7120 | for (i = 0; i < len; i++) |
7121 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 7122 | } |
ff0dacd7 | 7123 | else if (STRINGP (components)) |
aaaf0b1e | 7124 | { |
8f924df7 | 7125 | len = SCHARS (components); |
ff0dacd7 KH |
7126 | i = i_byte = 0; |
7127 | while (i < len) | |
7128 | { | |
7129 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
7130 | buf++; | |
7131 | } | |
7132 | } | |
7133 | else if (INTEGERP (components)) | |
7134 | { | |
7135 | len = 1; | |
7136 | *buf++ = XINT (components); | |
7137 | } | |
7138 | else if (CONSP (components)) | |
7139 | { | |
7140 | for (len = 0; CONSP (components); | |
7141 | len++, components = XCDR (components)) | |
7142 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 7143 | } |
aaaf0b1e | 7144 | else |
1088b922 | 7145 | emacs_abort (); |
ff0dacd7 | 7146 | *head -= len; |
aaaf0b1e | 7147 | } |
aaaf0b1e | 7148 | } |
ff0dacd7 KH |
7149 | |
7150 | if (find_composition (end, limit, &start, &end, &prop, | |
7151 | coding->src_object) | |
7152 | && end <= limit) | |
7153 | *stop = start; | |
7154 | else | |
7155 | *stop = limit; | |
aaaf0b1e | 7156 | } |
ff0dacd7 KH |
7157 | return buf; |
7158 | } | |
7159 | ||
7160 | ||
e1c23804 | 7161 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
7162 | CODING->src_object (buffer of string), store the data in BUF, set |
7163 | *STOP to the position where the value of `charset' property changes | |
7164 | (limiting by LIMIT), and return the address of the next element of | |
7165 | BUF. | |
7166 | ||
7167 | If the property value is nil, set *STOP to the position where the | |
7168 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
7169 | ||
55d4c1b2 | 7170 | static inline int * |
d311d28c | 7171 | handle_charset_annotation (ptrdiff_t pos, ptrdiff_t limit, |
cf84bb53 | 7172 | struct coding_system *coding, int *buf, |
d311d28c | 7173 | ptrdiff_t *stop) |
ff0dacd7 KH |
7174 | { |
7175 | Lisp_Object val, next; | |
7176 | int id; | |
7177 | ||
7178 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
7179 | if (! NILP (val) && CHARSETP (val)) | |
7180 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
7181 | else | |
7182 | id = -1; | |
69a80ea3 | 7183 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
7184 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
7185 | coding->src_object, | |
7186 | make_number (limit)); | |
7187 | *stop = XINT (next); | |
7188 | return buf; | |
7189 | } | |
7190 | ||
7191 | ||
df7492f9 | 7192 | static void |
cf84bb53 JB |
7193 | consume_chars (struct coding_system *coding, Lisp_Object translation_table, |
7194 | int max_lookup) | |
df7492f9 KH |
7195 | { |
7196 | int *buf = coding->charbuf; | |
ff0dacd7 | 7197 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 7198 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 7199 | const unsigned char *src_end = coding->source + coding->src_bytes; |
d311d28c PE |
7200 | ptrdiff_t pos = coding->src_pos + coding->consumed_char; |
7201 | ptrdiff_t end_pos = coding->src_pos + coding->src_chars; | |
f10fe38f | 7202 | bool multibytep = coding->src_multibyte; |
df7492f9 KH |
7203 | Lisp_Object eol_type; |
7204 | int c; | |
d311d28c | 7205 | ptrdiff_t stop, stop_composition, stop_charset; |
09ee6fdd | 7206 | int *lookup_buf = NULL; |
433f7f87 KH |
7207 | |
7208 | if (! NILP (translation_table)) | |
09ee6fdd | 7209 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 7210 | |
0a9564cb | 7211 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
df7492f9 KH |
7212 | if (VECTORP (eol_type)) |
7213 | eol_type = Qunix; | |
88993dfd | 7214 | |
df7492f9 KH |
7215 | /* Note: composition handling is not yet implemented. */ |
7216 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 7217 | |
0b5670c9 KH |
7218 | if (NILP (coding->src_object)) |
7219 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 7220 | else |
0b5670c9 KH |
7221 | { |
7222 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
7223 | stop = stop_composition = pos; | |
7224 | else | |
7225 | stop = stop_composition = end_pos; | |
7226 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
7227 | stop = stop_charset = pos; | |
7228 | else | |
7229 | stop_charset = end_pos; | |
7230 | } | |
ec6d2bb8 | 7231 | |
24a73b0a | 7232 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 7233 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 7234 | while (buf < buf_end) |
aaaf0b1e | 7235 | { |
433f7f87 KH |
7236 | Lisp_Object trans; |
7237 | ||
df7492f9 | 7238 | if (pos == stop) |
ec6d2bb8 | 7239 | { |
df7492f9 KH |
7240 | if (pos == end_pos) |
7241 | break; | |
ff0dacd7 KH |
7242 | if (pos == stop_composition) |
7243 | buf = handle_composition_annotation (pos, end_pos, coding, | |
7244 | buf, &stop_composition); | |
7245 | if (pos == stop_charset) | |
7246 | buf = handle_charset_annotation (pos, end_pos, coding, | |
7247 | buf, &stop_charset); | |
7248 | stop = (stop_composition < stop_charset | |
7249 | ? stop_composition : stop_charset); | |
df7492f9 KH |
7250 | } |
7251 | ||
7252 | if (! multibytep) | |
4776e638 | 7253 | { |
d311d28c | 7254 | int bytes; |
aaaf0b1e | 7255 | |
4d1e6632 KH |
7256 | if (coding->encoder == encode_coding_raw_text |
7257 | || coding->encoder == encode_coding_ccl) | |
ea29edf2 KH |
7258 | c = *src++, pos++; |
7259 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 7260 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 7261 | else |
f03caae0 | 7262 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 7263 | } |
df7492f9 | 7264 | else |
db274c7a | 7265 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
7266 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
7267 | c = '\n'; | |
7268 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 7269 | { |
df7492f9 | 7270 | if (c == '\n') |
aaaf0b1e | 7271 | { |
df7492f9 KH |
7272 | if (EQ (eol_type, Qdos)) |
7273 | *buf++ = '\r'; | |
7274 | else | |
7275 | c = '\r'; | |
aaaf0b1e KH |
7276 | } |
7277 | } | |
433f7f87 | 7278 | |
e6a54062 | 7279 | trans = Qnil; |
09ee6fdd | 7280 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 7281 | if (NILP (trans)) |
433f7f87 KH |
7282 | *buf++ = c; |
7283 | else | |
7284 | { | |
2c6a9faa | 7285 | ptrdiff_t from_nchars = 1, to_nchars = 1; |
433f7f87 KH |
7286 | int *lookup_buf_end; |
7287 | const unsigned char *p = src; | |
7288 | int i; | |
7289 | ||
7290 | lookup_buf[0] = c; | |
7291 | for (i = 1; i < max_lookup && p < src_end; i++) | |
7292 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
7293 | lookup_buf_end = lookup_buf + i; | |
e951386e KH |
7294 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
7295 | if (INTEGERP (trans)) | |
7296 | c = XINT (trans); | |
7297 | else if (CONSP (trans)) | |
7298 | { | |
7299 | from_nchars = ASIZE (XCAR (trans)); | |
7300 | trans = XCDR (trans); | |
7301 | if (INTEGERP (trans)) | |
7302 | c = XINT (trans); | |
7303 | else | |
7304 | { | |
7305 | to_nchars = ASIZE (trans); | |
2c6a9faa | 7306 | if (buf_end - buf < to_nchars) |
e951386e KH |
7307 | break; |
7308 | c = XINT (AREF (trans, 0)); | |
7309 | } | |
7310 | } | |
7311 | else | |
433f7f87 | 7312 | break; |
e951386e | 7313 | *buf++ = c; |
433f7f87 KH |
7314 | for (i = 1; i < to_nchars; i++) |
7315 | *buf++ = XINT (AREF (trans, i)); | |
7316 | for (i = 1; i < from_nchars; i++, pos++) | |
7317 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7318 | } | |
aaaf0b1e | 7319 | } |
ec6d2bb8 | 7320 | |
df7492f9 KH |
7321 | coding->consumed = src - coding->source; |
7322 | coding->consumed_char = pos - coding->src_pos; | |
7323 | coding->charbuf_used = buf - coding->charbuf; | |
7324 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7325 | } |
7326 | ||
4ed46869 | 7327 | |
df7492f9 KH |
7328 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7329 | CODING->src_object is a buffer or a string. | |
7330 | CODING->dst_object is a buffer or nil. | |
7331 | ||
7332 | If CODING->src_object is a buffer, it must be the current buffer. | |
7333 | In this case, if CODING->src_pos is positive, it is a position of | |
7334 | the source text in the buffer, otherwise. the source text is in the | |
7335 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7336 | the text from GPT (which must be the same as PT). If this is the | |
7337 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7338 | negative and CODING should not have `pre-write-conversion'. | |
7339 | ||
7340 | If CODING->src_object is a string, CODING should not have | |
7341 | `pre-write-conversion'. | |
7342 | ||
7343 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7344 | the current point of that buffer. | |
7345 | ||
7346 | If CODING->dst_object is nil, the encoded data is placed at the | |
7347 | memory area specified by CODING->destination. */ | |
7348 | ||
f10fe38f | 7349 | static void |
971de7fb | 7350 | encode_coding (struct coding_system *coding) |
4ed46869 | 7351 | { |
df7492f9 | 7352 | Lisp_Object attrs; |
7d64c6ad | 7353 | Lisp_Object translation_table; |
09ee6fdd | 7354 | int max_lookup; |
fb608df3 | 7355 | struct ccl_spec cclspec; |
9861e777 | 7356 | |
df7492f9 | 7357 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7358 | if (coding->encoder == encode_coding_raw_text) |
7359 | translation_table = Qnil, max_lookup = 0; | |
7360 | else | |
7361 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7362 | |
df7492f9 | 7363 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7364 | { |
df7492f9 KH |
7365 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7366 | coding->dst_multibyte | |
4b4deea2 | 7367 | = ! NILP (BVAR (current_buffer, enable_multibyte_characters)); |
8844fa83 | 7368 | } |
4ed46869 | 7369 | |
b73bfc1c | 7370 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7371 | coding->produced = coding->produced_char = 0; |
065e3595 | 7372 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7373 | coding->errors = 0; |
b73bfc1c | 7374 | |
df7492f9 | 7375 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7376 | |
fb608df3 KH |
7377 | if (coding->encoder == encode_coding_ccl) |
7378 | { | |
7379 | coding->spec.ccl = &cclspec; | |
7380 | setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding)); | |
7381 | } | |
df7492f9 KH |
7382 | do { |
7383 | coding_set_source (coding); | |
09ee6fdd | 7384 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7385 | coding_set_destination (coding); |
7386 | (*(coding->encoder)) (coding); | |
7387 | } while (coding->consumed_char < coding->src_chars); | |
7388 | ||
284201e4 | 7389 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
df7492f9 | 7390 | insert_from_gap (coding->produced_char, coding->produced); |
ec6d2bb8 KH |
7391 | } |
7392 | ||
fb88bf2d | 7393 | |
24a73b0a KH |
7394 | /* Name (or base name) of work buffer for code conversion. */ |
7395 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7396 | |
24a73b0a KH |
7397 | /* A working buffer used by the top level conversion. Once it is |
7398 | created, it is never destroyed. It has the name | |
7399 | Vcode_conversion_workbuf_name. The other working buffers are | |
7400 | destroyed after the use is finished, and their names are modified | |
7401 | versions of Vcode_conversion_workbuf_name. */ | |
7402 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7403 | |
f10fe38f PE |
7404 | /* True iff Vcode_conversion_reused_workbuf is already in use. */ |
7405 | static bool reused_workbuf_in_use; | |
4ed46869 | 7406 | |
24a73b0a | 7407 | |
ad1746f5 | 7408 | /* Return a working buffer of code conversion. MULTIBYTE specifies the |
24a73b0a | 7409 | multibyteness of returning buffer. */ |
b73bfc1c | 7410 | |
f6cbaf43 | 7411 | static Lisp_Object |
f10fe38f | 7412 | make_conversion_work_buffer (bool multibyte) |
df7492f9 | 7413 | { |
24a73b0a KH |
7414 | Lisp_Object name, workbuf; |
7415 | struct buffer *current; | |
4ed46869 | 7416 | |
f10fe38f | 7417 | if (reused_workbuf_in_use) |
065e3595 KH |
7418 | { |
7419 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7420 | workbuf = Fget_buffer_create (name); | |
7421 | } | |
df7492f9 | 7422 | else |
065e3595 | 7423 | { |
f10fe38f | 7424 | reused_workbuf_in_use = 1; |
159bd5a2 | 7425 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7426 | Vcode_conversion_reused_workbuf |
7427 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7428 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7429 | } |
24a73b0a KH |
7430 | current = current_buffer; |
7431 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7432 | /* We can't allow modification hooks to run in the work buffer. For |
7433 | instance, directory_files_internal assumes that file decoding | |
7434 | doesn't compile new regexps. */ | |
7435 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7436 | Ferase_buffer (); |
39eb03f1 PE |
7437 | bset_undo_list (current_buffer, Qt); |
7438 | bset_enable_multibyte_characters (current_buffer, multibyte ? Qt : Qnil); | |
df7492f9 | 7439 | set_buffer_internal (current); |
24a73b0a | 7440 | return workbuf; |
df7492f9 | 7441 | } |
d46c5b12 | 7442 | |
24a73b0a | 7443 | |
4776e638 | 7444 | static Lisp_Object |
971de7fb | 7445 | code_conversion_restore (Lisp_Object arg) |
4776e638 | 7446 | { |
24a73b0a | 7447 | Lisp_Object current, workbuf; |
948bdcf3 | 7448 | struct gcpro gcpro1; |
24a73b0a | 7449 | |
948bdcf3 | 7450 | GCPRO1 (arg); |
24a73b0a KH |
7451 | current = XCAR (arg); |
7452 | workbuf = XCDR (arg); | |
7453 | if (! NILP (workbuf)) | |
7454 | { | |
7455 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7456 | reused_workbuf_in_use = 0; | |
d17337e5 | 7457 | else |
24a73b0a KH |
7458 | Fkill_buffer (workbuf); |
7459 | } | |
7460 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7461 | UNGCPRO; |
4776e638 KH |
7462 | return Qnil; |
7463 | } | |
b73bfc1c | 7464 | |
24a73b0a | 7465 | Lisp_Object |
f10fe38f | 7466 | code_conversion_save (bool with_work_buf, bool multibyte) |
df7492f9 | 7467 | { |
24a73b0a | 7468 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7469 | |
4776e638 | 7470 | if (with_work_buf) |
24a73b0a KH |
7471 | workbuf = make_conversion_work_buffer (multibyte); |
7472 | record_unwind_protect (code_conversion_restore, | |
7473 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7474 | return workbuf; |
df7492f9 | 7475 | } |
d46c5b12 | 7476 | |
f10fe38f | 7477 | void |
cf84bb53 | 7478 | decode_coding_gap (struct coding_system *coding, |
d311d28c | 7479 | ptrdiff_t chars, ptrdiff_t bytes) |
df7492f9 | 7480 | { |
d311d28c | 7481 | ptrdiff_t count = SPECPDL_INDEX (); |
5e5c78be | 7482 | Lisp_Object attrs; |
fb88bf2d | 7483 | |
24a73b0a | 7484 | code_conversion_save (0, 0); |
ec6d2bb8 | 7485 | |
24a73b0a | 7486 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7487 | coding->src_chars = chars; |
7488 | coding->src_bytes = bytes; | |
7489 | coding->src_pos = -chars; | |
7490 | coding->src_pos_byte = -bytes; | |
7491 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7492 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7493 | coding->dst_pos = PT; |
7494 | coding->dst_pos_byte = PT_BYTE; | |
4b4deea2 | 7495 | coding->dst_multibyte = ! NILP (BVAR (current_buffer, enable_multibyte_characters)); |
4ed46869 | 7496 | |
df7492f9 KH |
7497 | if (CODING_REQUIRE_DETECTION (coding)) |
7498 | detect_coding (coding); | |
8f924df7 | 7499 | |
9286b333 | 7500 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7501 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7502 | decode_coding (coding); |
287c57d7 | 7503 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7504 | |
5e5c78be KH |
7505 | attrs = CODING_ID_ATTRS (coding->id); |
7506 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 7507 | { |
d311d28c | 7508 | ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
5e5c78be KH |
7509 | Lisp_Object val; |
7510 | ||
7511 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7512 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7513 | make_number (coding->produced_char)); | |
5e5c78be KH |
7514 | CHECK_NATNUM (val); |
7515 | coding->produced_char += Z - prev_Z; | |
7516 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7517 | } |
4ed46869 | 7518 | |
df7492f9 | 7519 | unbind_to (count, Qnil); |
b73bfc1c | 7520 | } |
52d41803 | 7521 | |
d46c5b12 | 7522 | |
df7492f9 KH |
7523 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7524 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7525 | |
df7492f9 | 7526 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7527 | |
df7492f9 KH |
7528 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7529 | are positions in the buffer. | |
b73bfc1c | 7530 | |
df7492f9 KH |
7531 | If it is a string, the text is at the beginning of the string. |
7532 | FROM and TO are indices to the string. | |
4ed46869 | 7533 | |
df7492f9 KH |
7534 | If it is nil, the text is at coding->source. FROM and TO are |
7535 | indices to coding->source. | |
bb10be8b | 7536 | |
df7492f9 | 7537 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7538 | |
df7492f9 KH |
7539 | If it is a buffer, the decoded text is inserted at point of the |
7540 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7541 | is deleted. | |
4ed46869 | 7542 | |
df7492f9 KH |
7543 | If it is Qt, a string is made from the decoded text, and |
7544 | set in CODING->dst_object. | |
d46c5b12 | 7545 | |
df7492f9 | 7546 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7547 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7548 | CODING->destination by xmalloc. If the decoded text is longer than |
7549 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7550 | */ | |
d46c5b12 | 7551 | |
df7492f9 | 7552 | void |
cf84bb53 JB |
7553 | decode_coding_object (struct coding_system *coding, |
7554 | Lisp_Object src_object, | |
d311d28c PE |
7555 | ptrdiff_t from, ptrdiff_t from_byte, |
7556 | ptrdiff_t to, ptrdiff_t to_byte, | |
cf84bb53 | 7557 | Lisp_Object dst_object) |
d46c5b12 | 7558 | { |
d311d28c | 7559 | ptrdiff_t count = SPECPDL_INDEX (); |
c4a63b12 | 7560 | unsigned char *destination IF_LINT (= NULL); |
d311d28c PE |
7561 | ptrdiff_t dst_bytes IF_LINT (= 0); |
7562 | ptrdiff_t chars = to - from; | |
7563 | ptrdiff_t bytes = to_byte - from_byte; | |
df7492f9 | 7564 | Lisp_Object attrs; |
f10fe38f PE |
7565 | ptrdiff_t saved_pt = -1, saved_pt_byte IF_LINT (= 0); |
7566 | bool need_marker_adjustment = 0; | |
b3bfad50 | 7567 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7568 | |
b3bfad50 | 7569 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 7570 | |
df7492f9 | 7571 | if (NILP (dst_object)) |
d46c5b12 | 7572 | { |
df7492f9 KH |
7573 | destination = coding->destination; |
7574 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 7575 | } |
93dec019 | 7576 | |
df7492f9 KH |
7577 | coding->src_object = src_object; |
7578 | coding->src_chars = chars; | |
7579 | coding->src_bytes = bytes; | |
7580 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 7581 | |
df7492f9 | 7582 | if (STRINGP (src_object)) |
d46c5b12 | 7583 | { |
df7492f9 KH |
7584 | coding->src_pos = from; |
7585 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7586 | } |
df7492f9 | 7587 | else if (BUFFERP (src_object)) |
88993dfd | 7588 | { |
df7492f9 KH |
7589 | set_buffer_internal (XBUFFER (src_object)); |
7590 | if (from != GPT) | |
7591 | move_gap_both (from, from_byte); | |
7592 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 7593 | { |
64cedb0c KH |
7594 | struct Lisp_Marker *tail; |
7595 | ||
7596 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7597 | { | |
7598 | tail->need_adjustment | |
7599 | = tail->charpos == (tail->insertion_type ? from : to); | |
7600 | need_marker_adjustment |= tail->need_adjustment; | |
7601 | } | |
4776e638 | 7602 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 7603 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 7604 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
7605 | del_range_both (from, from_byte, to, to_byte, 1); |
7606 | coding->src_pos = -chars; | |
7607 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 7608 | } |
df7492f9 | 7609 | else |
fb88bf2d | 7610 | { |
df7492f9 KH |
7611 | coding->src_pos = from; |
7612 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 7613 | } |
88993dfd KH |
7614 | } |
7615 | ||
df7492f9 KH |
7616 | if (CODING_REQUIRE_DETECTION (coding)) |
7617 | detect_coding (coding); | |
7618 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 7619 | |
2cb26057 KH |
7620 | if (EQ (dst_object, Qt) |
7621 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
7622 | && NILP (dst_object))) | |
b73bfc1c | 7623 | { |
a1567c45 SM |
7624 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
7625 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
7626 | coding->dst_pos = BEG; |
7627 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 7628 | } |
df7492f9 | 7629 | else if (BUFFERP (dst_object)) |
d46c5b12 | 7630 | { |
24a73b0a | 7631 | code_conversion_save (0, 0); |
df7492f9 KH |
7632 | coding->dst_object = dst_object; |
7633 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
7634 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
7635 | coding->dst_multibyte | |
4b4deea2 | 7636 | = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters)); |
d46c5b12 KH |
7637 | } |
7638 | else | |
7639 | { | |
24a73b0a | 7640 | code_conversion_save (0, 0); |
df7492f9 | 7641 | coding->dst_object = Qnil; |
0154725e SM |
7642 | /* Most callers presume this will return a multibyte result, and they |
7643 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
7644 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 7645 | coding->dst_multibyte = 1; |
d46c5b12 KH |
7646 | } |
7647 | ||
df7492f9 | 7648 | decode_coding (coding); |
fa46990e | 7649 | |
df7492f9 KH |
7650 | if (BUFFERP (coding->dst_object)) |
7651 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 7652 | |
df7492f9 | 7653 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 7654 | { |
b3bfad50 | 7655 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d311d28c | 7656 | ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 7657 | Lisp_Object val; |
d46c5b12 | 7658 | |
c0cc7f7f | 7659 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
7660 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7661 | old_deactivate_mark); | |
d4850d67 KH |
7662 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
7663 | make_number (coding->produced_char)); | |
df7492f9 KH |
7664 | UNGCPRO; |
7665 | CHECK_NATNUM (val); | |
7666 | coding->produced_char += Z - prev_Z; | |
7667 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 7668 | } |
de79a6a5 | 7669 | |
df7492f9 | 7670 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 7671 | { |
df7492f9 KH |
7672 | coding->dst_object = Fbuffer_string (); |
7673 | } | |
7674 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
7675 | { | |
7676 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7677 | if (dst_bytes < coding->produced) | |
7678 | { | |
b3bfad50 | 7679 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
7680 | if (! destination) |
7681 | { | |
065e3595 | 7682 | record_conversion_result (coding, |
ebaf11b6 | 7683 | CODING_RESULT_INSUFFICIENT_MEM); |
df7492f9 KH |
7684 | unbind_to (count, Qnil); |
7685 | return; | |
7686 | } | |
7687 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
7688 | move_gap_both (BEGV, BEGV_BYTE); | |
72af86bd | 7689 | memcpy (destination, BEGV_ADDR, coding->produced); |
df7492f9 | 7690 | coding->destination = destination; |
d46c5b12 | 7691 | } |
ec6d2bb8 | 7692 | } |
b73bfc1c | 7693 | |
4776e638 KH |
7694 | if (saved_pt >= 0) |
7695 | { | |
7696 | /* This is the case of: | |
7697 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7698 | As we have moved PT while replacing the original buffer | |
7699 | contents, we must recover it now. */ | |
7700 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 7701 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
7702 | if (saved_pt < from) |
7703 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7704 | else if (saved_pt < from + chars) | |
7705 | TEMP_SET_PT_BOTH (from, from_byte); | |
4b4deea2 | 7706 | else if (! NILP (BVAR (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
7707 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
7708 | saved_pt_byte + (coding->produced - bytes)); | |
7709 | else | |
7710 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
7711 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7712 | |
7713 | if (need_marker_adjustment) | |
7714 | { | |
7715 | struct Lisp_Marker *tail; | |
7716 | ||
7717 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7718 | if (tail->need_adjustment) | |
7719 | { | |
7720 | tail->need_adjustment = 0; | |
7721 | if (tail->insertion_type) | |
7722 | { | |
7723 | tail->bytepos = from_byte; | |
7724 | tail->charpos = from; | |
7725 | } | |
7726 | else | |
7727 | { | |
7728 | tail->bytepos = from_byte + coding->produced; | |
7729 | tail->charpos | |
4b4deea2 | 7730 | = (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
7731 | ? tail->bytepos : from + coding->produced_char); |
7732 | } | |
7733 | } | |
7734 | } | |
d46c5b12 | 7735 | } |
4776e638 | 7736 | |
b3bfad50 | 7737 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 7738 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
7739 | } |
7740 | ||
d46c5b12 | 7741 | |
df7492f9 | 7742 | void |
cf84bb53 JB |
7743 | encode_coding_object (struct coding_system *coding, |
7744 | Lisp_Object src_object, | |
d311d28c PE |
7745 | ptrdiff_t from, ptrdiff_t from_byte, |
7746 | ptrdiff_t to, ptrdiff_t to_byte, | |
cf84bb53 | 7747 | Lisp_Object dst_object) |
d46c5b12 | 7748 | { |
d311d28c PE |
7749 | ptrdiff_t count = SPECPDL_INDEX (); |
7750 | ptrdiff_t chars = to - from; | |
7751 | ptrdiff_t bytes = to_byte - from_byte; | |
df7492f9 | 7752 | Lisp_Object attrs; |
f10fe38f PE |
7753 | ptrdiff_t saved_pt = -1, saved_pt_byte IF_LINT (= 0); |
7754 | bool need_marker_adjustment = 0; | |
7755 | bool kill_src_buffer = 0; | |
b3bfad50 | 7756 | Lisp_Object old_deactivate_mark; |
df7492f9 | 7757 | |
b3bfad50 | 7758 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
7759 | |
7760 | coding->src_object = src_object; | |
7761 | coding->src_chars = chars; | |
7762 | coding->src_bytes = bytes; | |
7763 | coding->src_multibyte = chars < bytes; | |
7764 | ||
7765 | attrs = CODING_ID_ATTRS (coding->id); | |
7766 | ||
64cedb0c KH |
7767 | if (EQ (src_object, dst_object)) |
7768 | { | |
7769 | struct Lisp_Marker *tail; | |
7770 | ||
7771 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7772 | { | |
7773 | tail->need_adjustment | |
7774 | = tail->charpos == (tail->insertion_type ? from : to); | |
7775 | need_marker_adjustment |= tail->need_adjustment; | |
7776 | } | |
7777 | } | |
7778 | ||
df7492f9 | 7779 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 7780 | { |
24a73b0a | 7781 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
7782 | set_buffer_internal (XBUFFER (coding->src_object)); |
7783 | if (STRINGP (src_object)) | |
7784 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
7785 | else if (BUFFERP (src_object)) | |
7786 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
7787 | else | |
b68864e5 | 7788 | insert_1_both ((char *) coding->source + from, chars, bytes, 0, 0, 0); |
d46c5b12 | 7789 | |
df7492f9 KH |
7790 | if (EQ (src_object, dst_object)) |
7791 | { | |
7792 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 7793 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
7794 | del_range_both (from, from_byte, to, to_byte, 1); |
7795 | set_buffer_internal (XBUFFER (coding->src_object)); | |
7796 | } | |
7797 | ||
d4850d67 | 7798 | { |
b3bfad50 | 7799 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 7800 | |
b3bfad50 KH |
7801 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7802 | old_deactivate_mark); | |
6cd7a139 DA |
7803 | safe_call2 (CODING_ATTR_PRE_WRITE (attrs), |
7804 | make_number (BEG), make_number (Z)); | |
b3bfad50 | 7805 | UNGCPRO; |
d4850d67 | 7806 | } |
c02d943b KH |
7807 | if (XBUFFER (coding->src_object) != current_buffer) |
7808 | kill_src_buffer = 1; | |
ac87bbef | 7809 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7810 | if (BEG != GPT) |
7811 | move_gap_both (BEG, BEG_BYTE); | |
7812 | coding->src_chars = Z - BEG; | |
7813 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
7814 | coding->src_pos = BEG; | |
7815 | coding->src_pos_byte = BEG_BYTE; | |
7816 | coding->src_multibyte = Z < Z_BYTE; | |
7817 | } | |
7818 | else if (STRINGP (src_object)) | |
d46c5b12 | 7819 | { |
24a73b0a | 7820 | code_conversion_save (0, 0); |
df7492f9 KH |
7821 | coding->src_pos = from; |
7822 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 7823 | } |
df7492f9 | 7824 | else if (BUFFERP (src_object)) |
b73bfc1c | 7825 | { |
24a73b0a | 7826 | code_conversion_save (0, 0); |
df7492f9 | 7827 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 7828 | if (EQ (src_object, dst_object)) |
d46c5b12 | 7829 | { |
4776e638 | 7830 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
7831 | coding->src_object = del_range_1 (from, to, 1, 1); |
7832 | coding->src_pos = 0; | |
7833 | coding->src_pos_byte = 0; | |
d46c5b12 | 7834 | } |
df7492f9 | 7835 | else |
d46c5b12 | 7836 | { |
ff0dacd7 KH |
7837 | if (from < GPT && to >= GPT) |
7838 | move_gap_both (from, from_byte); | |
df7492f9 KH |
7839 | coding->src_pos = from; |
7840 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7841 | } |
d46c5b12 | 7842 | } |
4776e638 | 7843 | else |
24a73b0a | 7844 | code_conversion_save (0, 0); |
d46c5b12 | 7845 | |
df7492f9 | 7846 | if (BUFFERP (dst_object)) |
88993dfd | 7847 | { |
df7492f9 | 7848 | coding->dst_object = dst_object; |
28f67a95 KH |
7849 | if (EQ (src_object, dst_object)) |
7850 | { | |
7851 | coding->dst_pos = from; | |
7852 | coding->dst_pos_byte = from_byte; | |
7853 | } | |
7854 | else | |
7855 | { | |
319a3947 KH |
7856 | struct buffer *current = current_buffer; |
7857 | ||
7858 | set_buffer_temp (XBUFFER (dst_object)); | |
7859 | coding->dst_pos = PT; | |
7860 | coding->dst_pos_byte = PT_BYTE; | |
7861 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
7862 | set_buffer_temp (current); | |
28f67a95 | 7863 | } |
df7492f9 | 7864 | coding->dst_multibyte |
4b4deea2 | 7865 | = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters)); |
88993dfd | 7866 | } |
df7492f9 | 7867 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 7868 | { |
5d009b3a | 7869 | ptrdiff_t dst_bytes = max (1, coding->src_chars); |
df7492f9 | 7870 | coding->dst_object = Qnil; |
23f86fce | 7871 | coding->destination = xmalloc (dst_bytes); |
5d009b3a | 7872 | coding->dst_bytes = dst_bytes; |
df7492f9 | 7873 | coding->dst_multibyte = 0; |
d46c5b12 KH |
7874 | } |
7875 | else | |
7876 | { | |
df7492f9 KH |
7877 | coding->dst_object = Qnil; |
7878 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
7879 | } |
7880 | ||
df7492f9 | 7881 | encode_coding (coding); |
d46c5b12 | 7882 | |
df7492f9 | 7883 | if (EQ (dst_object, Qt)) |
d46c5b12 | 7884 | { |
df7492f9 KH |
7885 | if (BUFFERP (coding->dst_object)) |
7886 | coding->dst_object = Fbuffer_string (); | |
7887 | else | |
d46c5b12 | 7888 | { |
df7492f9 KH |
7889 | coding->dst_object |
7890 | = make_unibyte_string ((char *) coding->destination, | |
7891 | coding->produced); | |
7892 | xfree (coding->destination); | |
d46c5b12 | 7893 | } |
4ed46869 | 7894 | } |
d46c5b12 | 7895 | |
4776e638 KH |
7896 | if (saved_pt >= 0) |
7897 | { | |
7898 | /* This is the case of: | |
7899 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7900 | As we have moved PT while replacing the original buffer | |
7901 | contents, we must recover it now. */ | |
7902 | set_buffer_internal (XBUFFER (src_object)); | |
7903 | if (saved_pt < from) | |
7904 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7905 | else if (saved_pt < from + chars) | |
7906 | TEMP_SET_PT_BOTH (from, from_byte); | |
4b4deea2 | 7907 | else if (! NILP (BVAR (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
7908 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
7909 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 7910 | else |
4776e638 KH |
7911 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
7912 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7913 | |
7914 | if (need_marker_adjustment) | |
7915 | { | |
7916 | struct Lisp_Marker *tail; | |
7917 | ||
7918 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7919 | if (tail->need_adjustment) | |
7920 | { | |
7921 | tail->need_adjustment = 0; | |
7922 | if (tail->insertion_type) | |
7923 | { | |
7924 | tail->bytepos = from_byte; | |
7925 | tail->charpos = from; | |
7926 | } | |
7927 | else | |
7928 | { | |
7929 | tail->bytepos = from_byte + coding->produced; | |
7930 | tail->charpos | |
4b4deea2 | 7931 | = (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
7932 | ? tail->bytepos : from + coding->produced_char); |
7933 | } | |
7934 | } | |
7935 | } | |
4776e638 KH |
7936 | } |
7937 | ||
c02d943b KH |
7938 | if (kill_src_buffer) |
7939 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
7940 | |
7941 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 7942 | unbind_to (count, Qnil); |
b73bfc1c KH |
7943 | } |
7944 | ||
df7492f9 | 7945 | |
b73bfc1c | 7946 | Lisp_Object |
971de7fb | 7947 | preferred_coding_system (void) |
b73bfc1c | 7948 | { |
df7492f9 | 7949 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 7950 | |
df7492f9 | 7951 | return CODING_ID_NAME (id); |
4ed46869 KH |
7952 | } |
7953 | ||
7954 | \f | |
7955 | #ifdef emacs | |
1397dc18 | 7956 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 7957 | |
a7ca3326 | 7958 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 7959 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 7960 | See the documentation of `define-coding-system' for information |
48b0f3ae | 7961 | about coding-system objects. */) |
5842a27b | 7962 | (Lisp_Object object) |
4ed46869 | 7963 | { |
d4a1d553 JB |
7964 | if (NILP (object) |
7965 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 7966 | return Qt; |
d4a1d553 JB |
7967 | if (! SYMBOLP (object) |
7968 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
7969 | return Qnil; |
7970 | return Qt; | |
4ed46869 KH |
7971 | } |
7972 | ||
a7ca3326 | 7973 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
9d991de8 | 7974 | Sread_non_nil_coding_system, 1, 1, 0, |
48b0f3ae | 7975 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
5842a27b | 7976 | (Lisp_Object prompt) |
4ed46869 | 7977 | { |
e0e989f6 | 7978 | Lisp_Object val; |
9d991de8 RS |
7979 | do |
7980 | { | |
4608c386 KH |
7981 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
7982 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 7983 | } |
8f924df7 | 7984 | while (SCHARS (val) == 0); |
e0e989f6 | 7985 | return (Fintern (val, Qnil)); |
4ed46869 KH |
7986 | } |
7987 | ||
a7ca3326 | 7988 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 7989 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
7990 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
7991 | Ignores case when completing coding systems (all Emacs coding systems | |
7992 | are lower-case). */) | |
5842a27b | 7993 | (Lisp_Object prompt, Lisp_Object default_coding_system) |
4ed46869 | 7994 | { |
f44d27ce | 7995 | Lisp_Object val; |
d311d28c | 7996 | ptrdiff_t count = SPECPDL_INDEX (); |
c7183fb8 | 7997 | |
9b787f3e | 7998 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 7999 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 8000 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 8001 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
8002 | Qt, Qnil, Qcoding_system_history, |
8003 | default_coding_system, Qnil); | |
c7183fb8 | 8004 | unbind_to (count, Qnil); |
8f924df7 | 8005 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
8006 | } |
8007 | ||
a7ca3326 | 8008 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, |
4ed46869 | 8009 | 1, 1, 0, |
48b0f3ae | 8010 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
8011 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
8012 | It is valid if it is nil or a symbol defined as a coding system by the | |
8013 | function `define-coding-system'. */) | |
5842a27b | 8014 | (Lisp_Object coding_system) |
4ed46869 | 8015 | { |
44e8490d KH |
8016 | Lisp_Object define_form; |
8017 | ||
8018 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
8019 | if (! NILP (define_form)) | |
8020 | { | |
8021 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
8022 | safe_eval (define_form); | |
8023 | } | |
4ed46869 KH |
8024 | if (!NILP (Fcoding_system_p (coding_system))) |
8025 | return coding_system; | |
fcad4ec4 | 8026 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 8027 | } |
df7492f9 | 8028 | |
3a73fa5d | 8029 | \f |
89528eb3 | 8030 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
f10fe38f | 8031 | HIGHEST, return the coding system of the highest |
ad1746f5 | 8032 | priority among the detected coding systems. Otherwise return a |
89528eb3 | 8033 | list of detected coding systems sorted by their priorities. If |
f10fe38f | 8034 | MULTIBYTEP, it is assumed that the bytes are in correct |
89528eb3 KH |
8035 | multibyte form but contains only ASCII and eight-bit chars. |
8036 | Otherwise, the bytes are raw bytes. | |
8037 | ||
8038 | CODING-SYSTEM controls the detection as below: | |
8039 | ||
8040 | If it is nil, detect both text-format and eol-format. If the | |
8041 | text-format part of CODING-SYSTEM is already specified | |
8042 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
8043 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
8044 | detect only text-format. */ | |
8045 | ||
d46c5b12 | 8046 | Lisp_Object |
cf84bb53 | 8047 | detect_coding_system (const unsigned char *src, |
d311d28c | 8048 | ptrdiff_t src_chars, ptrdiff_t src_bytes, |
f10fe38f | 8049 | bool highest, bool multibytep, |
cf84bb53 | 8050 | Lisp_Object coding_system) |
4ed46869 | 8051 | { |
8f924df7 | 8052 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 8053 | Lisp_Object attrs, eol_type; |
4533845d | 8054 | Lisp_Object val = Qnil; |
df7492f9 | 8055 | struct coding_system coding; |
d3411f89 | 8056 | ptrdiff_t id; |
ff0dacd7 | 8057 | struct coding_detection_info detect_info; |
24a73b0a | 8058 | enum coding_category base_category; |
f10fe38f | 8059 | bool null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 8060 | |
df7492f9 KH |
8061 | if (NILP (coding_system)) |
8062 | coding_system = Qundecided; | |
8063 | setup_coding_system (coding_system, &coding); | |
8064 | attrs = CODING_ID_ATTRS (coding.id); | |
8065 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 8066 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 8067 | |
df7492f9 | 8068 | coding.source = src; |
24a73b0a | 8069 | coding.src_chars = src_chars; |
df7492f9 KH |
8070 | coding.src_bytes = src_bytes; |
8071 | coding.src_multibyte = multibytep; | |
8072 | coding.consumed = 0; | |
89528eb3 | 8073 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 8074 | coding.head_ascii = 0; |
d46c5b12 | 8075 | |
ff0dacd7 | 8076 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 8077 | |
89528eb3 | 8078 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
8079 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
8080 | if (base_category == coding_category_undecided) | |
4ed46869 | 8081 | { |
c4a63b12 PE |
8082 | enum coding_category category IF_LINT (= 0); |
8083 | struct coding_system *this IF_LINT (= NULL); | |
ff0dacd7 | 8084 | int c, i; |
88993dfd | 8085 | |
24a73b0a | 8086 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 8087 | for (; src < src_end; src++) |
4ed46869 | 8088 | { |
df7492f9 | 8089 | c = *src; |
6cb21a4f | 8090 | if (c & 0x80) |
6cb21a4f | 8091 | { |
2f3cbb32 | 8092 | eight_bit_found = 1; |
2f3cbb32 KH |
8093 | if (null_byte_found) |
8094 | break; | |
8095 | } | |
c0e16b14 | 8096 | else if (c < 0x20) |
2f3cbb32 KH |
8097 | { |
8098 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
8099 | && ! inhibit_iso_escape_detection | |
8100 | && ! detect_info.checked) | |
6cb21a4f | 8101 | { |
2f3cbb32 KH |
8102 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
8103 | { | |
8104 | /* We have scanned the whole data. */ | |
8105 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
8106 | { |
8107 | /* We didn't find an 8-bit code. We may | |
8108 | have found a null-byte, but it's very | |
8109 | rare that a binary file confirm to | |
8110 | ISO-2022. */ | |
8111 | src = src_end; | |
8112 | coding.head_ascii = src - coding.source; | |
8113 | } | |
8114 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
8115 | break; |
8116 | } | |
8117 | } | |
97b1b294 | 8118 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
8119 | { |
8120 | null_byte_found = 1; | |
8121 | if (eight_bit_found) | |
8122 | break; | |
6cb21a4f | 8123 | } |
c006c0c8 KH |
8124 | if (! eight_bit_found) |
8125 | coding.head_ascii++; | |
6cb21a4f | 8126 | } |
c006c0c8 | 8127 | else if (! eight_bit_found) |
c0e16b14 | 8128 | coding.head_ascii++; |
4ed46869 | 8129 | } |
88993dfd | 8130 | |
2f3cbb32 KH |
8131 | if (null_byte_found || eight_bit_found |
8132 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
8133 | || detect_info.found) |
8134 | { | |
2f3cbb32 | 8135 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
8136 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
8137 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 8138 | { |
6cb21a4f | 8139 | category = coding_priorities[i]; |
c7266f4a | 8140 | this = coding_categories + category; |
6cb21a4f | 8141 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
8142 | break; |
8143 | } | |
6cb21a4f | 8144 | else |
2f3cbb32 KH |
8145 | { |
8146 | if (null_byte_found) | |
8147 | { | |
8148 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
8149 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
8150 | } | |
8151 | for (i = 0; i < coding_category_raw_text; i++) | |
8152 | { | |
8153 | category = coding_priorities[i]; | |
8154 | this = coding_categories + category; | |
6cb21a4f | 8155 | |
2f3cbb32 KH |
8156 | if (this->id < 0) |
8157 | { | |
8158 | /* No coding system of this category is defined. */ | |
8159 | detect_info.rejected |= (1 << category); | |
8160 | } | |
8161 | else if (category >= coding_category_raw_text) | |
8162 | continue; | |
8163 | else if (detect_info.checked & (1 << category)) | |
8164 | { | |
8165 | if (highest | |
8166 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 8167 | break; |
2f3cbb32 KH |
8168 | } |
8169 | else if ((*(this->detector)) (&coding, &detect_info) | |
8170 | && highest | |
8171 | && (detect_info.found & (1 << category))) | |
8172 | { | |
8173 | if (category == coding_category_utf_16_auto) | |
8174 | { | |
8175 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8176 | category = coding_category_utf_16_le; | |
8177 | else | |
8178 | category = coding_category_utf_16_be; | |
8179 | } | |
8180 | break; | |
8181 | } | |
8182 | } | |
8183 | } | |
6cb21a4f | 8184 | } |
ec6d2bb8 | 8185 | |
4cddb209 KH |
8186 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
8187 | || null_byte_found) | |
ec6d2bb8 | 8188 | { |
ff0dacd7 | 8189 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 8190 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
8191 | val = Fcons (make_number (id), Qnil); |
8192 | } | |
ff0dacd7 | 8193 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 8194 | { |
ff0dacd7 | 8195 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
8196 | id = coding_categories[coding_category_undecided].id; |
8197 | val = Fcons (make_number (id), Qnil); | |
8198 | } | |
8199 | else if (highest) | |
8200 | { | |
ff0dacd7 | 8201 | if (detect_info.found) |
ec6d2bb8 | 8202 | { |
ff0dacd7 KH |
8203 | detect_info.found = 1 << category; |
8204 | val = Fcons (make_number (this->id), Qnil); | |
8205 | } | |
8206 | else | |
8207 | for (i = 0; i < coding_category_raw_text; i++) | |
8208 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
8209 | { | |
8210 | detect_info.found = 1 << coding_priorities[i]; | |
8211 | id = coding_categories[coding_priorities[i]].id; | |
8212 | val = Fcons (make_number (id), Qnil); | |
8213 | break; | |
8214 | } | |
8215 | } | |
89528eb3 KH |
8216 | else |
8217 | { | |
ff0dacd7 KH |
8218 | int mask = detect_info.rejected | detect_info.found; |
8219 | int found = 0; | |
ec6d2bb8 | 8220 | |
89528eb3 | 8221 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
8222 | { |
8223 | category = coding_priorities[i]; | |
8224 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 8225 | { |
ff0dacd7 KH |
8226 | found |= 1 << category; |
8227 | id = coding_categories[category].id; | |
c7266f4a KH |
8228 | if (id >= 0) |
8229 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
8230 | } |
8231 | } | |
8232 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
8233 | { | |
8234 | category = coding_priorities[i]; | |
8235 | if (detect_info.found & (1 << category)) | |
8236 | { | |
8237 | id = coding_categories[category].id; | |
8238 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 8239 | } |
ec6d2bb8 | 8240 | } |
ff0dacd7 | 8241 | detect_info.found |= found; |
ec6d2bb8 | 8242 | } |
ec6d2bb8 | 8243 | } |
a470d443 KH |
8244 | else if (base_category == coding_category_utf_8_auto) |
8245 | { | |
8246 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
8247 | { | |
8248 | struct coding_system *this; | |
8249 | ||
8250 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
8251 | this = coding_categories + coding_category_utf_8_sig; | |
8252 | else | |
8253 | this = coding_categories + coding_category_utf_8_nosig; | |
8254 | val = Fcons (make_number (this->id), Qnil); | |
8255 | } | |
8256 | } | |
24a73b0a KH |
8257 | else if (base_category == coding_category_utf_16_auto) |
8258 | { | |
8259 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
8260 | { | |
24a73b0a KH |
8261 | struct coding_system *this; |
8262 | ||
8263 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8264 | this = coding_categories + coding_category_utf_16_le; | |
8265 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
8266 | this = coding_categories + coding_category_utf_16_be; | |
8267 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
8268 | this = coding_categories + coding_category_utf_16_be_nosig; | |
8269 | else | |
8270 | this = coding_categories + coding_category_utf_16_le_nosig; | |
8271 | val = Fcons (make_number (this->id), Qnil); | |
8272 | } | |
8273 | } | |
df7492f9 KH |
8274 | else |
8275 | { | |
ff0dacd7 | 8276 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 8277 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8278 | } |
df7492f9 | 8279 | |
89528eb3 | 8280 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8281 | { |
4533845d | 8282 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8283 | Lisp_Object tail; |
8284 | ||
89528eb3 KH |
8285 | if (VECTORP (eol_type)) |
8286 | { | |
ff0dacd7 | 8287 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8288 | { |
8289 | if (null_byte_found) | |
8290 | normal_eol = EOL_SEEN_LF; | |
8291 | else | |
8292 | normal_eol = detect_eol (coding.source, src_bytes, | |
8293 | coding_category_raw_text); | |
8294 | } | |
ff0dacd7 KH |
8295 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8296 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8297 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8298 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8299 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8300 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8301 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8302 | coding_category_utf_16_le); | |
8303 | } | |
8304 | else | |
8305 | { | |
8306 | if (EQ (eol_type, Qunix)) | |
8307 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8308 | else if (EQ (eol_type, Qdos)) | |
8309 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8310 | else | |
8311 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8312 | } | |
8313 | ||
df7492f9 KH |
8314 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8315 | { | |
89528eb3 | 8316 | enum coding_category category; |
df7492f9 | 8317 | int this_eol; |
89528eb3 KH |
8318 | |
8319 | id = XINT (XCAR (tail)); | |
8320 | attrs = CODING_ID_ATTRS (id); | |
8321 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8322 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8323 | if (VECTORP (eol_type)) |
8324 | { | |
89528eb3 KH |
8325 | if (category == coding_category_utf_16_be |
8326 | || category == coding_category_utf_16_be_nosig) | |
8327 | this_eol = utf_16_be_eol; | |
8328 | else if (category == coding_category_utf_16_le | |
8329 | || category == coding_category_utf_16_le_nosig) | |
8330 | this_eol = utf_16_le_eol; | |
df7492f9 | 8331 | else |
89528eb3 KH |
8332 | this_eol = normal_eol; |
8333 | ||
df7492f9 KH |
8334 | if (this_eol == EOL_SEEN_LF) |
8335 | XSETCAR (tail, AREF (eol_type, 0)); | |
8336 | else if (this_eol == EOL_SEEN_CRLF) | |
8337 | XSETCAR (tail, AREF (eol_type, 1)); | |
8338 | else if (this_eol == EOL_SEEN_CR) | |
8339 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8340 | else |
8341 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8342 | } |
89528eb3 KH |
8343 | else |
8344 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8345 | } |
8346 | } | |
ec6d2bb8 | 8347 | |
4533845d | 8348 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8349 | } |
8350 | ||
ec6d2bb8 | 8351 | |
d46c5b12 KH |
8352 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8353 | 2, 3, 0, | |
48b0f3ae PJ |
8354 | doc: /* Detect coding system of the text in the region between START and END. |
8355 | Return a list of possible coding systems ordered by priority. | |
b811c52b KH |
8356 | The coding systems to try and their priorities follows what |
8357 | the function `coding-system-priority-list' (which see) returns. | |
ec6d2bb8 | 8358 | |
12e0131a | 8359 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8360 | characters as ESC), it returns a list of single element `undecided' |
8361 | or its subsidiary coding system according to a detected end-of-line | |
8362 | format. | |
ec6d2bb8 | 8363 | |
48b0f3ae PJ |
8364 | If optional argument HIGHEST is non-nil, return the coding system of |
8365 | highest priority. */) | |
5842a27b | 8366 | (Lisp_Object start, Lisp_Object end, Lisp_Object highest) |
d46c5b12 | 8367 | { |
d311d28c PE |
8368 | ptrdiff_t from, to; |
8369 | ptrdiff_t from_byte, to_byte; | |
ec6d2bb8 | 8370 | |
b7826503 PJ |
8371 | CHECK_NUMBER_COERCE_MARKER (start); |
8372 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 8373 | |
d46c5b12 KH |
8374 | validate_region (&start, &end); |
8375 | from = XINT (start), to = XINT (end); | |
8376 | from_byte = CHAR_TO_BYTE (from); | |
8377 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8378 | |
d46c5b12 KH |
8379 | if (from < GPT && to >= GPT) |
8380 | move_gap_both (to, to_byte); | |
c210f766 | 8381 | |
d46c5b12 | 8382 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8383 | to - from, to_byte - from_byte, |
0a28aafb | 8384 | !NILP (highest), |
4b4deea2 | 8385 | !NILP (BVAR (current_buffer |
5d8ea120 | 8386 | , enable_multibyte_characters)), |
df7492f9 | 8387 | Qnil); |
ec6d2bb8 KH |
8388 | } |
8389 | ||
d46c5b12 KH |
8390 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8391 | 1, 2, 0, | |
48b0f3ae PJ |
8392 | doc: /* Detect coding system of the text in STRING. |
8393 | Return a list of possible coding systems ordered by priority. | |
67ceab9d KH |
8394 | The coding systems to try and their priorities follows what |
8395 | the function `coding-system-priority-list' (which see) returns. | |
fb88bf2d | 8396 | |
12e0131a | 8397 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8398 | characters as ESC), it returns a list of single element `undecided' |
8399 | or its subsidiary coding system according to a detected end-of-line | |
8400 | format. | |
d46c5b12 | 8401 | |
48b0f3ae PJ |
8402 | If optional argument HIGHEST is non-nil, return the coding system of |
8403 | highest priority. */) | |
5842a27b | 8404 | (Lisp_Object string, Lisp_Object highest) |
d46c5b12 | 8405 | { |
b7826503 | 8406 | CHECK_STRING (string); |
b73bfc1c | 8407 | |
24a73b0a KH |
8408 | return detect_coding_system (SDATA (string), |
8409 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8410 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8411 | Qnil); |
4ed46869 | 8412 | } |
4ed46869 | 8413 | |
b73bfc1c | 8414 | |
f10fe38f | 8415 | static inline bool |
971de7fb | 8416 | char_encodable_p (int c, Lisp_Object attrs) |
05e6f5dc | 8417 | { |
df7492f9 | 8418 | Lisp_Object tail; |
df7492f9 | 8419 | struct charset *charset; |
7d64c6ad | 8420 | Lisp_Object translation_table; |
d46c5b12 | 8421 | |
7d64c6ad | 8422 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8423 | if (! NILP (translation_table)) |
7d64c6ad | 8424 | c = translate_char (translation_table, c); |
df7492f9 KH |
8425 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8426 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8427 | { |
df7492f9 KH |
8428 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8429 | if (CHAR_CHARSET_P (c, charset)) | |
8430 | break; | |
e133c8fa | 8431 | } |
df7492f9 | 8432 | return (! NILP (tail)); |
05e6f5dc | 8433 | } |
83fa074f | 8434 | |
fb88bf2d | 8435 | |
df7492f9 KH |
8436 | /* Return a list of coding systems that safely encode the text between |
8437 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8438 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8439 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8440 | unibyte, return t. */ |
e077cc80 | 8441 | |
df7492f9 KH |
8442 | DEFUN ("find-coding-systems-region-internal", |
8443 | Ffind_coding_systems_region_internal, | |
8444 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8445 | doc: /* Internal use only. */) | |
5842a27b | 8446 | (Lisp_Object start, Lisp_Object end, Lisp_Object exclude) |
df7492f9 KH |
8447 | { |
8448 | Lisp_Object coding_attrs_list, safe_codings; | |
d311d28c | 8449 | ptrdiff_t start_byte, end_byte; |
7c78e542 | 8450 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8451 | int c; |
0e727afa | 8452 | Lisp_Object tail, elt, work_table; |
d46c5b12 | 8453 | |
df7492f9 KH |
8454 | if (STRINGP (start)) |
8455 | { | |
8456 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8457 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8458 | return Qt; |
8459 | start_byte = 0; | |
8f924df7 | 8460 | end_byte = SBYTES (start); |
df7492f9 KH |
8461 | } |
8462 | else | |
d46c5b12 | 8463 | { |
df7492f9 KH |
8464 | CHECK_NUMBER_COERCE_MARKER (start); |
8465 | CHECK_NUMBER_COERCE_MARKER (end); | |
8466 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8467 | args_out_of_range (start, end); | |
4b4deea2 | 8468 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8469 | return Qt; |
8470 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8471 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8472 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8473 | return Qt; | |
d46c5b12 | 8474 | |
e1c23804 | 8475 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8476 | { |
e1c23804 DL |
8477 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8478 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8479 | else |
e1c23804 | 8480 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8481 | } |
8482 | } | |
8483 | ||
df7492f9 KH |
8484 | coding_attrs_list = Qnil; |
8485 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8486 | if (NILP (exclude) | |
8487 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8488 | { | |
8489 | Lisp_Object attrs; | |
d46c5b12 | 8490 | |
df7492f9 KH |
8491 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
8492 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
8493 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
8494 | { |
8495 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8496 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8497 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8498 | } | |
df7492f9 | 8499 | } |
d46c5b12 | 8500 | |
df7492f9 | 8501 | if (STRINGP (start)) |
8f924df7 | 8502 | p = pbeg = SDATA (start); |
df7492f9 KH |
8503 | else |
8504 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8505 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8506 | |
df7492f9 KH |
8507 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8508 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8509 | |
0e727afa | 8510 | work_table = Fmake_char_table (Qnil, Qnil); |
05e6f5dc | 8511 | while (p < pend) |
72d1a715 | 8512 | { |
df7492f9 KH |
8513 | if (ASCII_BYTE_P (*p)) |
8514 | p++; | |
72d1a715 RS |
8515 | else |
8516 | { | |
df7492f9 | 8517 | c = STRING_CHAR_ADVANCE (p); |
0e727afa YM |
8518 | if (!NILP (char_table_ref (work_table, c))) |
8519 | /* This character was already checked. Ignore it. */ | |
8520 | continue; | |
12410ef1 | 8521 | |
df7492f9 KH |
8522 | charset_map_loaded = 0; |
8523 | for (tail = coding_attrs_list; CONSP (tail);) | |
8524 | { | |
8525 | elt = XCAR (tail); | |
8526 | if (NILP (elt)) | |
8527 | tail = XCDR (tail); | |
8528 | else if (char_encodable_p (c, elt)) | |
8529 | tail = XCDR (tail); | |
8530 | else if (CONSP (XCDR (tail))) | |
8531 | { | |
8532 | XSETCAR (tail, XCAR (XCDR (tail))); | |
8533 | XSETCDR (tail, XCDR (XCDR (tail))); | |
8534 | } | |
8535 | else | |
8536 | { | |
8537 | XSETCAR (tail, Qnil); | |
8538 | tail = XCDR (tail); | |
8539 | } | |
8540 | } | |
8541 | if (charset_map_loaded) | |
8542 | { | |
d311d28c | 8543 | ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg; |
05e6f5dc | 8544 | |
df7492f9 | 8545 | if (STRINGP (start)) |
8f924df7 | 8546 | pbeg = SDATA (start); |
df7492f9 KH |
8547 | else |
8548 | pbeg = BYTE_POS_ADDR (start_byte); | |
8549 | p = pbeg + p_offset; | |
8550 | pend = pbeg + pend_offset; | |
8551 | } | |
0e727afa | 8552 | char_table_set (work_table, c, Qt); |
df7492f9 | 8553 | } |
ec6d2bb8 | 8554 | } |
fb88bf2d | 8555 | |
988b3759 | 8556 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
8557 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
8558 | if (! NILP (XCAR (tail))) | |
8559 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 8560 | |
05e6f5dc KH |
8561 | return safe_codings; |
8562 | } | |
4956c225 | 8563 | |
d46c5b12 | 8564 | |
8f924df7 KH |
8565 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
8566 | Sunencodable_char_position, 3, 5, 0, | |
8567 | doc: /* | |
8568 | Return position of first un-encodable character in a region. | |
d4a1d553 | 8569 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 8570 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 8571 | |
8f924df7 KH |
8572 | If optional 4th argument COUNT is non-nil, it specifies at most how |
8573 | many un-encodable characters to search. In this case, the value is a | |
8574 | list of positions. | |
d46c5b12 | 8575 | |
8f924df7 KH |
8576 | If optional 5th argument STRING is non-nil, it is a string to search |
8577 | for un-encodable characters. In that case, START and END are indexes | |
8578 | to the string. */) | |
5842a27b | 8579 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object count, Lisp_Object string) |
8f924df7 | 8580 | { |
d311d28c | 8581 | EMACS_INT n; |
8f924df7 | 8582 | struct coding_system coding; |
7d64c6ad | 8583 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 | 8584 | Lisp_Object positions; |
d311d28c | 8585 | ptrdiff_t from, to; |
8f924df7 | 8586 | const unsigned char *p, *stop, *pend; |
f10fe38f | 8587 | bool ascii_compatible; |
fb88bf2d | 8588 | |
8f924df7 KH |
8589 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
8590 | attrs = CODING_ID_ATTRS (coding.id); | |
8591 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
8592 | return Qnil; | |
8593 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
8594 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 8595 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 8596 | |
8f924df7 KH |
8597 | if (NILP (string)) |
8598 | { | |
8599 | validate_region (&start, &end); | |
8600 | from = XINT (start); | |
8601 | to = XINT (end); | |
4b4deea2 | 8602 | if (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
8f924df7 KH |
8603 | || (ascii_compatible |
8604 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
8605 | return Qnil; | |
8606 | p = CHAR_POS_ADDR (from); | |
8607 | pend = CHAR_POS_ADDR (to); | |
8608 | if (from < GPT && to >= GPT) | |
8609 | stop = GPT_ADDR; | |
8610 | else | |
8611 | stop = pend; | |
8612 | } | |
8613 | else | |
8614 | { | |
8615 | CHECK_STRING (string); | |
8616 | CHECK_NATNUM (start); | |
8617 | CHECK_NATNUM (end); | |
d311d28c PE |
8618 | if (! (XINT (start) <= XINT (end) && XINT (end) <= SCHARS (string))) |
8619 | args_out_of_range_3 (string, start, end); | |
8f924df7 KH |
8620 | from = XINT (start); |
8621 | to = XINT (end); | |
8f924df7 KH |
8622 | if (! STRING_MULTIBYTE (string)) |
8623 | return Qnil; | |
8624 | p = SDATA (string) + string_char_to_byte (string, from); | |
8625 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
8626 | if (ascii_compatible && (to - from) == (pend - p)) | |
8627 | return Qnil; | |
8628 | } | |
f2558efd | 8629 | |
8f924df7 KH |
8630 | if (NILP (count)) |
8631 | n = 1; | |
8632 | else | |
b73bfc1c | 8633 | { |
8f924df7 KH |
8634 | CHECK_NATNUM (count); |
8635 | n = XINT (count); | |
b73bfc1c KH |
8636 | } |
8637 | ||
8f924df7 | 8638 | positions = Qnil; |
3633e3aa | 8639 | charset_map_loaded = 0; |
8f924df7 | 8640 | while (1) |
d46c5b12 | 8641 | { |
8f924df7 | 8642 | int c; |
ec6d2bb8 | 8643 | |
8f924df7 KH |
8644 | if (ascii_compatible) |
8645 | while (p < stop && ASCII_BYTE_P (*p)) | |
8646 | p++, from++; | |
8647 | if (p >= stop) | |
0e79d667 | 8648 | { |
8f924df7 KH |
8649 | if (p >= pend) |
8650 | break; | |
8651 | stop = pend; | |
8652 | p = GAP_END_ADDR; | |
0e79d667 | 8653 | } |
ec6d2bb8 | 8654 | |
8f924df7 KH |
8655 | c = STRING_CHAR_ADVANCE (p); |
8656 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
8657 | && ! char_charset (translate_char (translation_table, c), |
8658 | charset_list, NULL)) | |
ec6d2bb8 | 8659 | { |
8f924df7 KH |
8660 | positions = Fcons (make_number (from), positions); |
8661 | n--; | |
8662 | if (n == 0) | |
8663 | break; | |
ec6d2bb8 KH |
8664 | } |
8665 | ||
8f924df7 | 8666 | from++; |
3633e3aa KH |
8667 | if (charset_map_loaded && NILP (string)) |
8668 | { | |
8669 | p = CHAR_POS_ADDR (from); | |
8670 | pend = CHAR_POS_ADDR (to); | |
8671 | if (from < GPT && to >= GPT) | |
8672 | stop = GPT_ADDR; | |
8673 | else | |
8674 | stop = pend; | |
8675 | charset_map_loaded = 0; | |
8676 | } | |
8f924df7 | 8677 | } |
d46c5b12 | 8678 | |
8f924df7 KH |
8679 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
8680 | } | |
d46c5b12 | 8681 | |
d46c5b12 | 8682 | |
df7492f9 KH |
8683 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
8684 | Scheck_coding_systems_region, 3, 3, 0, | |
8685 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 8686 | |
df7492f9 KH |
8687 | START and END are buffer positions specifying the region. |
8688 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 8689 | |
df7492f9 | 8690 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 8691 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
8692 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
8693 | characters are found. | |
93dec019 | 8694 | |
df7492f9 KH |
8695 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
8696 | value is nil. | |
93dec019 | 8697 | |
df7492f9 KH |
8698 | START may be a string. In that case, check if the string is |
8699 | encodable, and the value contains indices to the string instead of | |
5704f39a KH |
8700 | buffer positions. END is ignored. |
8701 | ||
4c1958f4 | 8702 | If the current buffer (or START if it is a string) is unibyte, the value |
5704f39a | 8703 | is nil. */) |
5842a27b | 8704 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system_list) |
05e6f5dc | 8705 | { |
df7492f9 | 8706 | Lisp_Object list; |
d311d28c PE |
8707 | ptrdiff_t start_byte, end_byte; |
8708 | ptrdiff_t pos; | |
7c78e542 | 8709 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8710 | int c; |
7d64c6ad | 8711 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 8712 | |
05e6f5dc KH |
8713 | if (STRINGP (start)) |
8714 | { | |
df7492f9 | 8715 | if (!STRING_MULTIBYTE (start) |
4c1958f4 | 8716 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8717 | return Qnil; |
8718 | start_byte = 0; | |
8f924df7 | 8719 | end_byte = SBYTES (start); |
df7492f9 | 8720 | pos = 0; |
d46c5b12 | 8721 | } |
05e6f5dc | 8722 | else |
b73bfc1c | 8723 | { |
b7826503 PJ |
8724 | CHECK_NUMBER_COERCE_MARKER (start); |
8725 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
8726 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
8727 | args_out_of_range (start, end); | |
4b4deea2 | 8728 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8729 | return Qnil; |
8730 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8731 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8732 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
5704f39a | 8733 | return Qnil; |
df7492f9 | 8734 | |
e1c23804 | 8735 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 8736 | { |
e1c23804 DL |
8737 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8738 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8739 | else |
e1c23804 | 8740 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 8741 | } |
e1c23804 | 8742 | pos = XINT (start); |
b73bfc1c | 8743 | } |
7553d0e1 | 8744 | |
df7492f9 KH |
8745 | list = Qnil; |
8746 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 8747 | { |
df7492f9 | 8748 | elt = XCAR (tail); |
7d64c6ad | 8749 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
8750 | ASET (attrs, coding_attr_trans_tbl, |
8751 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 8752 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
8753 | } |
8754 | ||
df7492f9 | 8755 | if (STRINGP (start)) |
8f924df7 | 8756 | p = pbeg = SDATA (start); |
72d1a715 | 8757 | else |
df7492f9 KH |
8758 | p = pbeg = BYTE_POS_ADDR (start_byte); |
8759 | pend = p + (end_byte - start_byte); | |
4ed46869 | 8760 | |
df7492f9 KH |
8761 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
8762 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 8763 | |
df7492f9 | 8764 | while (p < pend) |
d46c5b12 | 8765 | { |
df7492f9 KH |
8766 | if (ASCII_BYTE_P (*p)) |
8767 | p++; | |
e133c8fa | 8768 | else |
05e6f5dc | 8769 | { |
df7492f9 KH |
8770 | c = STRING_CHAR_ADVANCE (p); |
8771 | ||
8772 | charset_map_loaded = 0; | |
8773 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
8774 | { | |
8775 | elt = XCDR (XCAR (tail)); | |
8776 | if (! char_encodable_p (c, XCAR (elt))) | |
8777 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
8778 | } | |
8779 | if (charset_map_loaded) | |
8780 | { | |
d311d28c | 8781 | ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg; |
df7492f9 KH |
8782 | |
8783 | if (STRINGP (start)) | |
8f924df7 | 8784 | pbeg = SDATA (start); |
df7492f9 KH |
8785 | else |
8786 | pbeg = BYTE_POS_ADDR (start_byte); | |
8787 | p = pbeg + p_offset; | |
8788 | pend = pbeg + pend_offset; | |
8789 | } | |
05e6f5dc | 8790 | } |
df7492f9 | 8791 | pos++; |
d46c5b12 | 8792 | } |
4ed46869 | 8793 | |
df7492f9 KH |
8794 | tail = list; |
8795 | list = Qnil; | |
8796 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 8797 | { |
df7492f9 KH |
8798 | elt = XCAR (tail); |
8799 | if (CONSP (XCDR (XCDR (elt)))) | |
8800 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
8801 | list); | |
ec6d2bb8 | 8802 | } |
2b4f9037 | 8803 | |
df7492f9 | 8804 | return list; |
d46c5b12 KH |
8805 | } |
8806 | ||
3fd9494b | 8807 | |
74ab6df5 | 8808 | static Lisp_Object |
cf84bb53 JB |
8809 | code_convert_region (Lisp_Object start, Lisp_Object end, |
8810 | Lisp_Object coding_system, Lisp_Object dst_object, | |
f10fe38f | 8811 | bool encodep, bool norecord) |
4ed46869 | 8812 | { |
3a73fa5d | 8813 | struct coding_system coding; |
d311d28c | 8814 | ptrdiff_t from, from_byte, to, to_byte; |
df7492f9 | 8815 | Lisp_Object src_object; |
4ed46869 | 8816 | |
b7826503 PJ |
8817 | CHECK_NUMBER_COERCE_MARKER (start); |
8818 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
8819 | if (NILP (coding_system)) |
8820 | coding_system = Qno_conversion; | |
8821 | else | |
8822 | CHECK_CODING_SYSTEM (coding_system); | |
8823 | src_object = Fcurrent_buffer (); | |
8824 | if (NILP (dst_object)) | |
8825 | dst_object = src_object; | |
8826 | else if (! EQ (dst_object, Qt)) | |
8827 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 8828 | |
d46c5b12 KH |
8829 | validate_region (&start, &end); |
8830 | from = XFASTINT (start); | |
df7492f9 | 8831 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 8832 | to = XFASTINT (end); |
df7492f9 | 8833 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 8834 | |
df7492f9 KH |
8835 | setup_coding_system (coding_system, &coding); |
8836 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 8837 | |
df7492f9 KH |
8838 | if (encodep) |
8839 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8840 | dst_object); | |
8841 | else | |
8842 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8843 | dst_object); | |
8844 | if (! norecord) | |
8845 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 8846 | |
df7492f9 KH |
8847 | return (BUFFERP (dst_object) |
8848 | ? make_number (coding.produced_char) | |
8849 | : coding.dst_object); | |
4031e2bf | 8850 | } |
78108bcd | 8851 | |
4ed46869 | 8852 | |
4031e2bf | 8853 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 8854 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 8855 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
8856 | When called from a program, takes four arguments: |
8857 | START, END, CODING-SYSTEM, and DESTINATION. | |
8858 | START and END are buffer positions. | |
8844fa83 | 8859 | |
df7492f9 | 8860 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 8861 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
8862 | If buffer, the decoded text is inserted in that buffer after point (point |
8863 | does not move). | |
446dcd75 | 8864 | In those cases, the length of the decoded text is returned. |
319a3947 | 8865 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 8866 | |
48b0f3ae PJ |
8867 | This function sets `last-coding-system-used' to the precise coding system |
8868 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8869 | not fully specified.) */) |
5842a27b | 8870 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
4031e2bf | 8871 | { |
df7492f9 | 8872 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 8873 | } |
8844fa83 | 8874 | |
3a73fa5d | 8875 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
8876 | 3, 4, "r\nzCoding system: ", |
8877 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
8878 | When called from a program, takes four arguments: |
8879 | START, END, CODING-SYSTEM and DESTINATION. | |
8880 | START and END are buffer positions. | |
d46c5b12 | 8881 | |
df7492f9 KH |
8882 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
8883 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
8884 | If buffer, the encoded text is inserted in that buffer after point (point |
8885 | does not move). | |
446dcd75 | 8886 | In those cases, the length of the encoded text is returned. |
319a3947 | 8887 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 8888 | |
48b0f3ae PJ |
8889 | This function sets `last-coding-system-used' to the precise coding system |
8890 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8891 | not fully specified.) */) |
5842a27b | 8892 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
3a73fa5d | 8893 | { |
df7492f9 | 8894 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
8895 | } |
8896 | ||
8897 | Lisp_Object | |
6f704c76 | 8898 | code_convert_string (Lisp_Object string, Lisp_Object coding_system, |
f10fe38f PE |
8899 | Lisp_Object dst_object, bool encodep, bool nocopy, |
8900 | bool norecord) | |
b73bfc1c | 8901 | { |
4031e2bf | 8902 | struct coding_system coding; |
d311d28c | 8903 | ptrdiff_t chars, bytes; |
ec6d2bb8 | 8904 | |
b7826503 | 8905 | CHECK_STRING (string); |
d46c5b12 | 8906 | if (NILP (coding_system)) |
4956c225 | 8907 | { |
df7492f9 KH |
8908 | if (! norecord) |
8909 | Vlast_coding_system_used = Qno_conversion; | |
8910 | if (NILP (dst_object)) | |
8911 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 8912 | } |
b73bfc1c | 8913 | |
df7492f9 KH |
8914 | if (NILP (coding_system)) |
8915 | coding_system = Qno_conversion; | |
8916 | else | |
8917 | CHECK_CODING_SYSTEM (coding_system); | |
8918 | if (NILP (dst_object)) | |
8919 | dst_object = Qt; | |
8920 | else if (! EQ (dst_object, Qt)) | |
8921 | CHECK_BUFFER (dst_object); | |
73be902c | 8922 | |
df7492f9 | 8923 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 8924 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
8925 | chars = SCHARS (string); |
8926 | bytes = SBYTES (string); | |
df7492f9 KH |
8927 | if (encodep) |
8928 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
8929 | else | |
8930 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
8931 | if (! norecord) | |
8932 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 8933 | |
df7492f9 KH |
8934 | return (BUFFERP (dst_object) |
8935 | ? make_number (coding.produced_char) | |
8936 | : coding.dst_object); | |
4ed46869 | 8937 | } |
73be902c | 8938 | |
b73bfc1c | 8939 | |
ecec61c1 | 8940 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 8941 | Do not set Vlast_coding_system_used. |
4ed46869 | 8942 | |
ec6d2bb8 KH |
8943 | This function is called only from macros DECODE_FILE and |
8944 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 8945 | |
ecec61c1 | 8946 | Lisp_Object |
cf84bb53 | 8947 | code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system, |
f10fe38f | 8948 | bool encodep) |
4ed46869 | 8949 | { |
0be8721c | 8950 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
8951 | } |
8952 | ||
4ed46869 | 8953 | |
a7ca3326 | 8954 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
df7492f9 KH |
8955 | 2, 4, 0, |
8956 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
8957 | ||
8958 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
8959 | if the decoding operation is trivial. | |
ecec61c1 | 8960 | |
d4a1d553 | 8961 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
8962 | inserted in that buffer after point (point does not move). In this |
8963 | case, the return value is the length of the decoded text. | |
ecec61c1 | 8964 | |
df7492f9 KH |
8965 | This function sets `last-coding-system-used' to the precise coding system |
8966 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 8967 | not fully specified.) */) |
5842a27b | 8968 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 8969 | { |
df7492f9 KH |
8970 | return code_convert_string (string, coding_system, buffer, |
8971 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
8972 | } |
8973 | ||
df7492f9 KH |
8974 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
8975 | 2, 4, 0, | |
8976 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
8977 | ||
8978 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
8979 | itself if the encoding operation is trivial. | |
8980 | ||
d4a1d553 | 8981 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
8982 | inserted in that buffer after point (point does not move). In this |
8983 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
8984 | |
8985 | This function sets `last-coding-system-used' to the precise coding system | |
8986 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
8987 | not fully specified.) */) | |
5842a27b | 8988 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 8989 | { |
df7492f9 | 8990 | return code_convert_string (string, coding_system, buffer, |
4550efdf | 8991 | 1, ! NILP (nocopy), 0); |
4ed46869 | 8992 | } |
df7492f9 | 8993 | |
3a73fa5d | 8994 | \f |
4ed46869 | 8995 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
8996 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
8997 | Return the corresponding character. */) | |
5842a27b | 8998 | (Lisp_Object code) |
4ed46869 | 8999 | { |
df7492f9 KH |
9000 | Lisp_Object spec, attrs, val; |
9001 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
5fdb398c PE |
9002 | EMACS_INT ch; |
9003 | int c; | |
4ed46869 | 9004 | |
df7492f9 | 9005 | CHECK_NATNUM (code); |
5fdb398c | 9006 | ch = XFASTINT (code); |
df7492f9 KH |
9007 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); |
9008 | attrs = AREF (spec, 0); | |
4ed46869 | 9009 | |
5fdb398c | 9010 | if (ASCII_BYTE_P (ch) |
df7492f9 KH |
9011 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
9012 | return code; | |
4ed46869 | 9013 | |
df7492f9 KH |
9014 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9015 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
9016 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
9017 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 9018 | |
5fdb398c PE |
9019 | if (ch <= 0x7F) |
9020 | { | |
9021 | c = ch; | |
9022 | charset = charset_roman; | |
9023 | } | |
9024 | else if (ch >= 0xA0 && ch < 0xDF) | |
55ab7be3 | 9025 | { |
5fdb398c | 9026 | c = ch - 0x80; |
df7492f9 | 9027 | charset = charset_kana; |
4ed46869 | 9028 | } |
55ab7be3 | 9029 | else |
4ed46869 | 9030 | { |
5fdb398c PE |
9031 | EMACS_INT c1 = ch >> 8; |
9032 | int c2 = ch & 0xFF; | |
df7492f9 | 9033 | |
2735d060 PE |
9034 | if (c1 < 0x81 || (c1 > 0x9F && c1 < 0xE0) || c1 > 0xEF |
9035 | || c2 < 0x40 || c2 == 0x7F || c2 > 0xFC) | |
c2982e87 | 9036 | error ("Invalid code: %"pI"d", ch); |
5fdb398c | 9037 | c = ch; |
df7492f9 KH |
9038 | SJIS_TO_JIS (c); |
9039 | charset = charset_kanji; | |
4ed46869 | 9040 | } |
df7492f9 KH |
9041 | c = DECODE_CHAR (charset, c); |
9042 | if (c < 0) | |
c2982e87 | 9043 | error ("Invalid code: %"pI"d", ch); |
df7492f9 | 9044 | return make_number (c); |
93dec019 | 9045 | } |
4ed46869 | 9046 | |
48b0f3ae | 9047 | |
4ed46869 | 9048 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 9049 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae | 9050 | Return the corresponding code in SJIS. */) |
5842a27b | 9051 | (Lisp_Object ch) |
4ed46869 | 9052 | { |
df7492f9 KH |
9053 | Lisp_Object spec, attrs, charset_list; |
9054 | int c; | |
9055 | struct charset *charset; | |
9056 | unsigned code; | |
48b0f3ae | 9057 | |
df7492f9 KH |
9058 | CHECK_CHARACTER (ch); |
9059 | c = XFASTINT (ch); | |
9060 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9061 | attrs = AREF (spec, 0); | |
9062 | ||
9063 | if (ASCII_CHAR_P (c) | |
9064 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9065 | return ch; | |
9066 | ||
9067 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9068 | charset = char_charset (c, charset_list, &code); | |
9069 | if (code == CHARSET_INVALID_CODE (charset)) | |
e6c3da20 | 9070 | error ("Can't encode by shift_jis encoding: %c", c); |
df7492f9 KH |
9071 | JIS_TO_SJIS (code); |
9072 | ||
9073 | return make_number (code); | |
4ed46869 KH |
9074 | } |
9075 | ||
9076 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
9077 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
9078 | Return the corresponding character. */) | |
5842a27b | 9079 | (Lisp_Object code) |
d46c5b12 | 9080 | { |
df7492f9 KH |
9081 | Lisp_Object spec, attrs, val; |
9082 | struct charset *charset_roman, *charset_big5, *charset; | |
5fdb398c | 9083 | EMACS_INT ch; |
df7492f9 | 9084 | int c; |
6289dd10 | 9085 | |
df7492f9 | 9086 | CHECK_NATNUM (code); |
5fdb398c | 9087 | ch = XFASTINT (code); |
df7492f9 KH |
9088 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); |
9089 | attrs = AREF (spec, 0); | |
4ed46869 | 9090 | |
5fdb398c | 9091 | if (ASCII_BYTE_P (ch) |
df7492f9 KH |
9092 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
9093 | return code; | |
6289dd10 | 9094 | |
df7492f9 KH |
9095 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9096 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
9097 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 9098 | |
5fdb398c PE |
9099 | if (ch <= 0x7F) |
9100 | { | |
9101 | c = ch; | |
9102 | charset = charset_roman; | |
9103 | } | |
c28a9453 KH |
9104 | else |
9105 | { | |
5fdb398c PE |
9106 | EMACS_INT b1 = ch >> 8; |
9107 | int b2 = ch & 0x7F; | |
df7492f9 KH |
9108 | if (b1 < 0xA1 || b1 > 0xFE |
9109 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
c2982e87 | 9110 | error ("Invalid code: %"pI"d", ch); |
5fdb398c | 9111 | c = ch; |
df7492f9 | 9112 | charset = charset_big5; |
c28a9453 | 9113 | } |
5fdb398c | 9114 | c = DECODE_CHAR (charset, c); |
df7492f9 | 9115 | if (c < 0) |
c2982e87 | 9116 | error ("Invalid code: %"pI"d", ch); |
df7492f9 | 9117 | return make_number (c); |
d46c5b12 | 9118 | } |
6289dd10 | 9119 | |
4ed46869 | 9120 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 9121 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae | 9122 | Return the corresponding character code in Big5. */) |
5842a27b | 9123 | (Lisp_Object ch) |
4ed46869 | 9124 | { |
df7492f9 KH |
9125 | Lisp_Object spec, attrs, charset_list; |
9126 | struct charset *charset; | |
9127 | int c; | |
9128 | unsigned code; | |
9129 | ||
9130 | CHECK_CHARACTER (ch); | |
9131 | c = XFASTINT (ch); | |
9132 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9133 | attrs = AREF (spec, 0); | |
9134 | if (ASCII_CHAR_P (c) | |
9135 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9136 | return ch; | |
9137 | ||
9138 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9139 | charset = char_charset (c, charset_list, &code); | |
9140 | if (code == CHARSET_INVALID_CODE (charset)) | |
e6c3da20 | 9141 | error ("Can't encode by Big5 encoding: %c", c); |
df7492f9 KH |
9142 | |
9143 | return make_number (code); | |
4ed46869 | 9144 | } |
48b0f3ae | 9145 | |
3a73fa5d | 9146 | \f |
002fdb44 | 9147 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 9148 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9149 | doc: /* Internal use only. */) |
5842a27b | 9150 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9151 | { |
b18fad6d KH |
9152 | struct terminal *term = get_terminal (terminal, 1); |
9153 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term); | |
b7826503 | 9154 | CHECK_SYMBOL (coding_system); |
b8299c66 | 9155 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 9156 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 9157 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
ad1746f5 | 9158 | /* Character composition should be disabled. */ |
c73bd236 | 9159 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
9160 | terminal_coding->src_multibyte = 1; |
9161 | terminal_coding->dst_multibyte = 0; | |
3f22b86f PE |
9162 | tset_charset_list |
9163 | (term, (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK | |
9164 | ? coding_charset_list (terminal_coding) | |
9165 | : Fcons (make_number (charset_ascii), Qnil))); | |
4ed46869 KH |
9166 | return Qnil; |
9167 | } | |
9168 | ||
c4825358 KH |
9169 | DEFUN ("set-safe-terminal-coding-system-internal", |
9170 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 9171 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 9172 | doc: /* Internal use only. */) |
5842a27b | 9173 | (Lisp_Object coding_system) |
d46c5b12 | 9174 | { |
b7826503 | 9175 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
9176 | setup_coding_system (Fcheck_coding_system (coding_system), |
9177 | &safe_terminal_coding); | |
ad1746f5 | 9178 | /* Character composition should be disabled. */ |
df7492f9 | 9179 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b73bfc1c KH |
9180 | safe_terminal_coding.src_multibyte = 1; |
9181 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
9182 | return Qnil; |
9183 | } | |
4ed46869 | 9184 | |
002fdb44 | 9185 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 9186 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff | 9187 | doc: /* Return coding system specified for terminal output on the given terminal. |
708e05dc | 9188 | TERMINAL may be a terminal object, a frame, or nil for the selected |
6ed8eeff | 9189 | frame's terminal device. */) |
5842a27b | 9190 | (Lisp_Object terminal) |
4ed46869 | 9191 | { |
985773c9 MB |
9192 | struct coding_system *terminal_coding |
9193 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
9194 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 9195 | |
6d5eb5b0 | 9196 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 9197 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
9198 | } |
9199 | ||
002fdb44 | 9200 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 9201 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9202 | doc: /* Internal use only. */) |
5842a27b | 9203 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9204 | { |
6ed8eeff | 9205 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 9206 | CHECK_SYMBOL (coding_system); |
624bda09 KH |
9207 | if (NILP (coding_system)) |
9208 | coding_system = Qno_conversion; | |
9209 | else | |
9210 | Fcheck_coding_system (coding_system); | |
9211 | setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t)); | |
ad1746f5 | 9212 | /* Character composition should be disabled. */ |
c73bd236 MB |
9213 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
9214 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
9215 | return Qnil; |
9216 | } | |
9217 | ||
9218 | DEFUN ("keyboard-coding-system", | |
985773c9 | 9219 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 9220 | doc: /* Return coding system specified for decoding keyboard input. */) |
5842a27b | 9221 | (Lisp_Object terminal) |
4ed46869 | 9222 | { |
985773c9 MB |
9223 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
9224 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
9225 | } |
9226 | ||
4ed46869 | 9227 | \f |
a7ca3326 | 9228 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
a5d301df | 9229 | Sfind_operation_coding_system, 1, MANY, 0, |
48b0f3ae PJ |
9230 | doc: /* Choose a coding system for an operation based on the target name. |
9231 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
9232 | DECODING-SYSTEM is the coding system to use for decoding | |
9233 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
9234 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 9235 | |
48b0f3ae PJ |
9236 | The first argument OPERATION specifies an I/O primitive: |
9237 | For file I/O, `insert-file-contents' or `write-region'. | |
9238 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
9239 | For network I/O, `open-network-stream'. | |
05e6f5dc | 9240 | |
48b0f3ae PJ |
9241 | The remaining arguments should be the same arguments that were passed |
9242 | to the primitive. Depending on which primitive, one of those arguments | |
9243 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
9244 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 9245 | |
48b0f3ae | 9246 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 9247 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 9248 | For process I/O, TARGET is a process name. |
d4a1d553 | 9249 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 9250 | |
d4a1d553 | 9251 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
9252 | `file-coding-system-alist', `process-coding-system-alist', |
9253 | or `network-coding-system-alist' depending on OPERATION. | |
9254 | They may specify a coding system, a cons of coding systems, | |
9255 | or a function symbol to call. | |
9256 | In the last case, we call the function with one argument, | |
9257 | which is a list of all the arguments given to this function. | |
1011c487 MB |
9258 | If the function can't decide a coding system, it can return |
9259 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 9260 | |
b883cdb2 MB |
9261 | If OPERATION is `insert-file-contents', the argument corresponding to |
9262 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
9263 | file name to look up, and BUFFER is a buffer that contains the file's | |
9264 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
9265 | function to call for FILENAME, that function should examine the | |
9266 | contents of BUFFER instead of reading the file. | |
9267 | ||
d918f936 | 9268 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
f66c7cf8 | 9269 | (ptrdiff_t nargs, Lisp_Object *args) |
6b89e3aa | 9270 | { |
4ed46869 KH |
9271 | Lisp_Object operation, target_idx, target, val; |
9272 | register Lisp_Object chain; | |
177c0ea7 | 9273 | |
4ed46869 KH |
9274 | if (nargs < 2) |
9275 | error ("Too few arguments"); | |
9276 | operation = args[0]; | |
9277 | if (!SYMBOLP (operation) | |
d311d28c | 9278 | || (target_idx = Fget (operation, Qtarget_idx), !NATNUMP (target_idx))) |
3ed051d4 | 9279 | error ("Invalid first argument"); |
7b09a37a | 9280 | if (nargs <= 1 + XFASTINT (target_idx)) |
94dcfacf | 9281 | error ("Too few arguments for operation `%s'", |
8f924df7 | 9282 | SDATA (SYMBOL_NAME (operation))); |
c5101a77 | 9283 | target = args[XFASTINT (target_idx) + 1]; |
4ed46869 | 9284 | if (!(STRINGP (target) |
091a0ff0 KH |
9285 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
9286 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 9287 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
94dcfacf EZ |
9288 | error ("Invalid argument %"pI"d of operation `%s'", |
9289 | XFASTINT (target_idx) + 1, SDATA (SYMBOL_NAME (operation))); | |
091a0ff0 KH |
9290 | if (CONSP (target)) |
9291 | target = XCAR (target); | |
4ed46869 | 9292 | |
2e34157c RS |
9293 | chain = ((EQ (operation, Qinsert_file_contents) |
9294 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9295 | ? Vfile_coding_system_alist |
2e34157c | 9296 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9297 | ? Vnetwork_coding_system_alist |
9298 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9299 | if (NILP (chain)) |
9300 | return Qnil; | |
9301 | ||
03699b14 | 9302 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9303 | { |
f44d27ce | 9304 | Lisp_Object elt; |
6b89e3aa | 9305 | |
df7492f9 | 9306 | elt = XCAR (chain); |
4ed46869 KH |
9307 | if (CONSP (elt) |
9308 | && ((STRINGP (target) | |
03699b14 KR |
9309 | && STRINGP (XCAR (elt)) |
9310 | && fast_string_match (XCAR (elt), target) >= 0) | |
9311 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9312 | { |
03699b14 | 9313 | val = XCDR (elt); |
b19fd4c5 KH |
9314 | /* Here, if VAL is both a valid coding system and a valid |
9315 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9316 | if (CONSP (val)) |
9317 | return val; | |
9318 | if (! SYMBOLP (val)) | |
9319 | return Qnil; | |
9320 | if (! NILP (Fcoding_system_p (val))) | |
9321 | return Fcons (val, val); | |
b19fd4c5 | 9322 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9323 | { |
e2b97060 MB |
9324 | /* We use call1 rather than safe_call1 |
9325 | so as to get bug reports about functions called here | |
9326 | which don't handle the current interface. */ | |
9327 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9328 | if (CONSP (val)) |
9329 | return val; | |
9330 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9331 | return Fcons (val, val); | |
6b89e3aa | 9332 | } |
02ba4723 | 9333 | return Qnil; |
6b89e3aa KH |
9334 | } |
9335 | } | |
4ed46869 | 9336 | return Qnil; |
6b89e3aa KH |
9337 | } |
9338 | ||
df7492f9 | 9339 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9340 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9341 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9342 | If multiple coding systems belong to the same category, |
a3181084 DL |
9343 | all but the first one are ignored. |
9344 | ||
d4a1d553 | 9345 | usage: (set-coding-system-priority &rest coding-systems) */) |
f66c7cf8 | 9346 | (ptrdiff_t nargs, Lisp_Object *args) |
df7492f9 | 9347 | { |
f66c7cf8 | 9348 | ptrdiff_t i, j; |
f10fe38f | 9349 | bool changed[coding_category_max]; |
df7492f9 KH |
9350 | enum coding_category priorities[coding_category_max]; |
9351 | ||
72af86bd | 9352 | memset (changed, 0, sizeof changed); |
6b89e3aa | 9353 | |
df7492f9 | 9354 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9355 | { |
df7492f9 KH |
9356 | enum coding_category category; |
9357 | Lisp_Object spec, attrs; | |
6b89e3aa | 9358 | |
df7492f9 KH |
9359 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9360 | attrs = AREF (spec, 0); | |
9361 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9362 | if (changed[category]) | |
9363 | /* Ignore this coding system because a coding system of the | |
9364 | same category already had a higher priority. */ | |
9365 | continue; | |
9366 | changed[category] = 1; | |
9367 | priorities[j++] = category; | |
9368 | if (coding_categories[category].id >= 0 | |
9369 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9370 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9371 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9372 | } |
6b89e3aa | 9373 | |
df7492f9 KH |
9374 | /* Now we have decided top J priorities. Reflect the order of the |
9375 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9376 | |
df7492f9 | 9377 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9378 | { |
df7492f9 KH |
9379 | while (j < coding_category_max |
9380 | && changed[coding_priorities[j]]) | |
9381 | j++; | |
9382 | if (j == coding_category_max) | |
1088b922 | 9383 | emacs_abort (); |
df7492f9 KH |
9384 | priorities[i] = coding_priorities[j]; |
9385 | } | |
6b89e3aa | 9386 | |
72af86bd | 9387 | memcpy (coding_priorities, priorities, sizeof priorities); |
177c0ea7 | 9388 | |
ff563fce KH |
9389 | /* Update `coding-category-list'. */ |
9390 | Vcoding_category_list = Qnil; | |
c5101a77 | 9391 | for (i = coding_category_max; i-- > 0; ) |
ff563fce KH |
9392 | Vcoding_category_list |
9393 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9394 | Vcoding_category_list); | |
6b89e3aa | 9395 | |
df7492f9 | 9396 | return Qnil; |
6b89e3aa KH |
9397 | } |
9398 | ||
df7492f9 KH |
9399 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9400 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 | 9401 | doc: /* Return a list of coding systems ordered by their priorities. |
b811c52b KH |
9402 | The list contains a subset of coding systems; i.e. coding systems |
9403 | assigned to each coding category (see `coding-category-list'). | |
9404 | ||
da7db224 | 9405 | HIGHESTP non-nil means just return the highest priority one. */) |
5842a27b | 9406 | (Lisp_Object highestp) |
d46c5b12 KH |
9407 | { |
9408 | int i; | |
df7492f9 | 9409 | Lisp_Object val; |
6b89e3aa | 9410 | |
df7492f9 | 9411 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9412 | { |
df7492f9 KH |
9413 | enum coding_category category = coding_priorities[i]; |
9414 | int id = coding_categories[category].id; | |
9415 | Lisp_Object attrs; | |
068a9dbd | 9416 | |
df7492f9 KH |
9417 | if (id < 0) |
9418 | continue; | |
9419 | attrs = CODING_ID_ATTRS (id); | |
9420 | if (! NILP (highestp)) | |
9421 | return CODING_ATTR_BASE_NAME (attrs); | |
9422 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9423 | } | |
9424 | return Fnreverse (val); | |
9425 | } | |
068a9dbd | 9426 | |
91433552 | 9427 | static const char *const suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9428 | |
9429 | static Lisp_Object | |
971de7fb | 9430 | make_subsidiaries (Lisp_Object base) |
068a9dbd | 9431 | { |
df7492f9 | 9432 | Lisp_Object subsidiaries; |
1bfdaf10 | 9433 | ptrdiff_t base_name_len = SBYTES (SYMBOL_NAME (base)); |
38182d90 | 9434 | char *buf = alloca (base_name_len + 6); |
df7492f9 | 9435 | int i; |
068a9dbd | 9436 | |
72af86bd | 9437 | memcpy (buf, SDATA (SYMBOL_NAME (base)), base_name_len); |
df7492f9 KH |
9438 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
9439 | for (i = 0; i < 3; i++) | |
068a9dbd | 9440 | { |
1bfdaf10 | 9441 | strcpy (buf + base_name_len, suffixes[i]); |
df7492f9 | 9442 | ASET (subsidiaries, i, intern (buf)); |
068a9dbd | 9443 | } |
df7492f9 | 9444 | return subsidiaries; |
068a9dbd KH |
9445 | } |
9446 | ||
9447 | ||
df7492f9 KH |
9448 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9449 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9450 | doc: /* For internal use only. |
9451 | usage: (define-coding-system-internal ...) */) | |
f66c7cf8 | 9452 | (ptrdiff_t nargs, Lisp_Object *args) |
068a9dbd | 9453 | { |
df7492f9 KH |
9454 | Lisp_Object name; |
9455 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9456 | Lisp_Object attrs; /* Vector of attributes. */ | |
9457 | Lisp_Object eol_type; | |
9458 | Lisp_Object aliases; | |
9459 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9460 | enum coding_category category; | |
9461 | Lisp_Object tail, val; | |
9462 | int max_charset_id = 0; | |
9463 | int i; | |
068a9dbd | 9464 | |
df7492f9 KH |
9465 | if (nargs < coding_arg_max) |
9466 | goto short_args; | |
068a9dbd | 9467 | |
df7492f9 | 9468 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9469 | |
df7492f9 KH |
9470 | name = args[coding_arg_name]; |
9471 | CHECK_SYMBOL (name); | |
4939150c | 9472 | ASET (attrs, coding_attr_base_name, name); |
068a9dbd | 9473 | |
df7492f9 KH |
9474 | val = args[coding_arg_mnemonic]; |
9475 | if (! STRINGP (val)) | |
9476 | CHECK_CHARACTER (val); | |
4939150c | 9477 | ASET (attrs, coding_attr_mnemonic, val); |
068a9dbd | 9478 | |
df7492f9 KH |
9479 | coding_type = args[coding_arg_coding_type]; |
9480 | CHECK_SYMBOL (coding_type); | |
4939150c | 9481 | ASET (attrs, coding_attr_type, coding_type); |
068a9dbd | 9482 | |
df7492f9 KH |
9483 | charset_list = args[coding_arg_charset_list]; |
9484 | if (SYMBOLP (charset_list)) | |
9485 | { | |
9486 | if (EQ (charset_list, Qiso_2022)) | |
9487 | { | |
9488 | if (! EQ (coding_type, Qiso_2022)) | |
9489 | error ("Invalid charset-list"); | |
9490 | charset_list = Viso_2022_charset_list; | |
9491 | } | |
9492 | else if (EQ (charset_list, Qemacs_mule)) | |
9493 | { | |
9494 | if (! EQ (coding_type, Qemacs_mule)) | |
9495 | error ("Invalid charset-list"); | |
9496 | charset_list = Vemacs_mule_charset_list; | |
9497 | } | |
9498 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
d311d28c PE |
9499 | { |
9500 | if (! RANGED_INTEGERP (0, XCAR (tail), INT_MAX - 1)) | |
9501 | error ("Invalid charset-list"); | |
9502 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9503 | max_charset_id = XFASTINT (XCAR (tail)); | |
9504 | } | |
df7492f9 | 9505 | } |
068a9dbd KH |
9506 | else |
9507 | { | |
df7492f9 | 9508 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9509 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9510 | { |
df7492f9 KH |
9511 | struct charset *charset; |
9512 | ||
985773c9 | 9513 | val = XCAR (tail); |
df7492f9 KH |
9514 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9515 | if (EQ (coding_type, Qiso_2022) | |
9516 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9517 | : EQ (coding_type, Qemacs_mule) | |
9518 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9519 | : 0) | |
9520 | error ("Can't handle charset `%s'", | |
8f924df7 | 9521 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9522 | |
8f924df7 | 9523 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9524 | if (max_charset_id < charset->id) |
9525 | max_charset_id = charset->id; | |
068a9dbd KH |
9526 | } |
9527 | } | |
4939150c | 9528 | ASET (attrs, coding_attr_charset_list, charset_list); |
068a9dbd | 9529 | |
1b3b981b AS |
9530 | safe_charsets = make_uninit_string (max_charset_id + 1); |
9531 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 | 9532 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8f924df7 | 9533 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
4939150c | 9534 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); |
068a9dbd | 9535 | |
4939150c | 9536 | ASET (attrs, coding_attr_ascii_compat, args[coding_arg_ascii_compatible_p]); |
3a73fa5d | 9537 | |
df7492f9 | 9538 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 9539 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9540 | CHECK_SYMBOL (val); |
4939150c | 9541 | ASET (attrs, coding_attr_decode_tbl, val); |
3a73fa5d | 9542 | |
df7492f9 | 9543 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 9544 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9545 | CHECK_SYMBOL (val); |
4939150c | 9546 | ASET (attrs, coding_attr_encode_tbl, val); |
d46c5b12 | 9547 | |
df7492f9 KH |
9548 | val = args[coding_arg_post_read_conversion]; |
9549 | CHECK_SYMBOL (val); | |
4939150c | 9550 | ASET (attrs, coding_attr_post_read, val); |
d46c5b12 | 9551 | |
df7492f9 KH |
9552 | val = args[coding_arg_pre_write_conversion]; |
9553 | CHECK_SYMBOL (val); | |
4939150c | 9554 | ASET (attrs, coding_attr_pre_write, val); |
3a73fa5d | 9555 | |
df7492f9 KH |
9556 | val = args[coding_arg_default_char]; |
9557 | if (NILP (val)) | |
4939150c | 9558 | ASET (attrs, coding_attr_default_char, make_number (' ')); |
df7492f9 KH |
9559 | else |
9560 | { | |
8f924df7 | 9561 | CHECK_CHARACTER (val); |
4939150c | 9562 | ASET (attrs, coding_attr_default_char, val); |
df7492f9 | 9563 | } |
4031e2bf | 9564 | |
8f924df7 | 9565 | val = args[coding_arg_for_unibyte]; |
4939150c | 9566 | ASET (attrs, coding_attr_for_unibyte, NILP (val) ? Qnil : Qt); |
3a73fa5d | 9567 | |
df7492f9 KH |
9568 | val = args[coding_arg_plist]; |
9569 | CHECK_LIST (val); | |
4939150c | 9570 | ASET (attrs, coding_attr_plist, val); |
3a73fa5d | 9571 | |
df7492f9 KH |
9572 | if (EQ (coding_type, Qcharset)) |
9573 | { | |
c7c66a95 KH |
9574 | /* Generate a lisp vector of 256 elements. Each element is nil, |
9575 | integer, or a list of charset IDs. | |
3a73fa5d | 9576 | |
c7c66a95 KH |
9577 | If Nth element is nil, the byte code N is invalid in this |
9578 | coding system. | |
4ed46869 | 9579 | |
c7c66a95 KH |
9580 | If Nth element is a number NUM, N is the first byte of a |
9581 | charset whose ID is NUM. | |
4ed46869 | 9582 | |
c7c66a95 KH |
9583 | If Nth element is a list of charset IDs, N is the first byte |
9584 | of one of them. The list is sorted by dimensions of the | |
ad1746f5 | 9585 | charsets. A charset of smaller dimension comes first. */ |
df7492f9 | 9586 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 9587 | |
5c99c2e6 | 9588 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9589 | { |
c7c66a95 KH |
9590 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
9591 | int dim = CHARSET_DIMENSION (charset); | |
9592 | int idx = (dim - 1) * 4; | |
4ed46869 | 9593 | |
5c99c2e6 | 9594 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9595 | ASET (attrs, coding_attr_ascii_compat, Qt); |
4031e2bf | 9596 | |
15d143f7 KH |
9597 | for (i = charset->code_space[idx]; |
9598 | i <= charset->code_space[idx + 1]; i++) | |
9599 | { | |
c7c66a95 KH |
9600 | Lisp_Object tmp, tmp2; |
9601 | int dim2; | |
ec6d2bb8 | 9602 | |
c7c66a95 KH |
9603 | tmp = AREF (val, i); |
9604 | if (NILP (tmp)) | |
9605 | tmp = XCAR (tail); | |
9606 | else if (NUMBERP (tmp)) | |
9607 | { | |
9608 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
9609 | if (dim < dim2) | |
c7c66a95 | 9610 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
9611 | else |
9612 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 9613 | } |
15d143f7 | 9614 | else |
c7c66a95 KH |
9615 | { |
9616 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
9617 | { | |
9618 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
9619 | if (dim < dim2) | |
9620 | break; | |
9621 | } | |
9622 | if (NILP (tmp2)) | |
9623 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
9624 | else | |
9625 | { | |
9626 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
9627 | XSETCAR (tmp2, XCAR (tail)); | |
9628 | } | |
9629 | } | |
9630 | ASET (val, i, tmp); | |
15d143f7 | 9631 | } |
df7492f9 KH |
9632 | } |
9633 | ASET (attrs, coding_attr_charset_valids, val); | |
9634 | category = coding_category_charset; | |
9635 | } | |
9636 | else if (EQ (coding_type, Qccl)) | |
9637 | { | |
9638 | Lisp_Object valids; | |
ecec61c1 | 9639 | |
df7492f9 KH |
9640 | if (nargs < coding_arg_ccl_max) |
9641 | goto short_args; | |
ecec61c1 | 9642 | |
df7492f9 KH |
9643 | val = args[coding_arg_ccl_decoder]; |
9644 | CHECK_CCL_PROGRAM (val); | |
9645 | if (VECTORP (val)) | |
9646 | val = Fcopy_sequence (val); | |
9647 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 9648 | |
df7492f9 KH |
9649 | val = args[coding_arg_ccl_encoder]; |
9650 | CHECK_CCL_PROGRAM (val); | |
9651 | if (VECTORP (val)) | |
9652 | val = Fcopy_sequence (val); | |
9653 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 9654 | |
df7492f9 KH |
9655 | val = args[coding_arg_ccl_valids]; |
9656 | valids = Fmake_string (make_number (256), make_number (0)); | |
7d7bbefd | 9657 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9658 | { |
8dcbea82 | 9659 | int from, to; |
ecec61c1 | 9660 | |
34348bd4 | 9661 | val = XCAR (tail); |
df7492f9 | 9662 | if (INTEGERP (val)) |
8dcbea82 | 9663 | { |
d311d28c | 9664 | if (! (0 <= XINT (val) && XINT (val) <= 255)) |
8dcbea82 | 9665 | args_out_of_range_3 (val, make_number (0), make_number (255)); |
d311d28c | 9666 | from = to = XINT (val); |
8dcbea82 | 9667 | } |
df7492f9 KH |
9668 | else |
9669 | { | |
df7492f9 | 9670 | CHECK_CONS (val); |
8f924df7 | 9671 | CHECK_NATNUM_CAR (val); |
d311d28c PE |
9672 | CHECK_NUMBER_CDR (val); |
9673 | if (XINT (XCAR (val)) > 255) | |
8dcbea82 KH |
9674 | args_out_of_range_3 (XCAR (val), |
9675 | make_number (0), make_number (255)); | |
d311d28c PE |
9676 | from = XINT (XCAR (val)); |
9677 | if (! (from <= XINT (XCDR (val)) && XINT (XCDR (val)) <= 255)) | |
8dcbea82 KH |
9678 | args_out_of_range_3 (XCDR (val), |
9679 | XCAR (val), make_number (255)); | |
d311d28c | 9680 | to = XINT (XCDR (val)); |
df7492f9 | 9681 | } |
8dcbea82 | 9682 | for (i = from; i <= to; i++) |
8f924df7 | 9683 | SSET (valids, i, 1); |
df7492f9 KH |
9684 | } |
9685 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 9686 | |
df7492f9 | 9687 | category = coding_category_ccl; |
55ab7be3 | 9688 | } |
df7492f9 | 9689 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 9690 | { |
df7492f9 | 9691 | Lisp_Object bom, endian; |
4ed46869 | 9692 | |
4939150c | 9693 | ASET (attrs, coding_attr_ascii_compat, Qnil); |
4ed46869 | 9694 | |
df7492f9 KH |
9695 | if (nargs < coding_arg_utf16_max) |
9696 | goto short_args; | |
4ed46869 | 9697 | |
df7492f9 KH |
9698 | bom = args[coding_arg_utf16_bom]; |
9699 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9700 | { | |
9701 | CHECK_CONS (bom); | |
8f924df7 KH |
9702 | val = XCAR (bom); |
9703 | CHECK_CODING_SYSTEM (val); | |
9704 | val = XCDR (bom); | |
9705 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 9706 | } |
a470d443 | 9707 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
9708 | |
9709 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
9710 | CHECK_SYMBOL (endian); |
9711 | if (NILP (endian)) | |
9712 | endian = Qbig; | |
9713 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 9714 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
9715 | ASET (attrs, coding_attr_utf_16_endian, endian); |
9716 | ||
9717 | category = (CONSP (bom) | |
9718 | ? coding_category_utf_16_auto | |
9719 | : NILP (bom) | |
b49a1807 | 9720 | ? (EQ (endian, Qbig) |
df7492f9 KH |
9721 | ? coding_category_utf_16_be_nosig |
9722 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 9723 | : (EQ (endian, Qbig) |
df7492f9 KH |
9724 | ? coding_category_utf_16_be |
9725 | : coding_category_utf_16_le)); | |
9726 | } | |
9727 | else if (EQ (coding_type, Qiso_2022)) | |
9728 | { | |
9729 | Lisp_Object initial, reg_usage, request, flags; | |
1397dc18 | 9730 | |
df7492f9 KH |
9731 | if (nargs < coding_arg_iso2022_max) |
9732 | goto short_args; | |
9733 | ||
9734 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
9735 | CHECK_VECTOR (initial); | |
9736 | for (i = 0; i < 4; i++) | |
9737 | { | |
9738 | val = Faref (initial, make_number (i)); | |
9739 | if (! NILP (val)) | |
9740 | { | |
584948ac KH |
9741 | struct charset *charset; |
9742 | ||
9743 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
9744 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
9745 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
4939150c | 9746 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9747 | } |
9748 | else | |
9749 | ASET (initial, i, make_number (-1)); | |
9750 | } | |
9751 | ||
9752 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
9753 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
9754 | CHECK_NUMBER_CAR (reg_usage); |
9755 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
9756 | |
9757 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
7d7bbefd | 9758 | for (tail = request; CONSP (tail); tail = XCDR (tail)) |
1397dc18 | 9759 | { |
df7492f9 | 9760 | int id; |
2735d060 | 9761 | Lisp_Object tmp1; |
df7492f9 | 9762 | |
34348bd4 | 9763 | val = XCAR (tail); |
df7492f9 | 9764 | CHECK_CONS (val); |
2735d060 PE |
9765 | tmp1 = XCAR (val); |
9766 | CHECK_CHARSET_GET_ID (tmp1, id); | |
8f924df7 | 9767 | CHECK_NATNUM_CDR (val); |
df7492f9 | 9768 | if (XINT (XCDR (val)) >= 4) |
c2982e87 | 9769 | error ("Invalid graphic register number: %"pI"d", XINT (XCDR (val))); |
8f924df7 | 9770 | XSETCAR (val, make_number (id)); |
1397dc18 | 9771 | } |
4ed46869 | 9772 | |
df7492f9 KH |
9773 | flags = args[coding_arg_iso2022_flags]; |
9774 | CHECK_NATNUM (flags); | |
d311d28c | 9775 | i = XINT (flags) & INT_MAX; |
df7492f9 | 9776 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) |
d311d28c PE |
9777 | i |= CODING_ISO_FLAG_FULL_SUPPORT; |
9778 | flags = make_number (i); | |
df7492f9 KH |
9779 | |
9780 | ASET (attrs, coding_attr_iso_initial, initial); | |
9781 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
9782 | ASET (attrs, coding_attr_iso_request, request); | |
9783 | ASET (attrs, coding_attr_iso_flags, flags); | |
9784 | setup_iso_safe_charsets (attrs); | |
9785 | ||
9786 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
9787 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
9788 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
9789 | ? coding_category_iso_7_else | |
9790 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
9791 | ? coding_category_iso_7 | |
9792 | : coding_category_iso_7_tight); | |
9793 | else | |
9794 | { | |
9795 | int id = XINT (AREF (initial, 1)); | |
9796 | ||
c6fb6e98 | 9797 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
9798 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
9799 | || id < 0) | |
9800 | ? coding_category_iso_8_else | |
9801 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
9802 | ? coding_category_iso_8_1 | |
9803 | : coding_category_iso_8_2); | |
9804 | } | |
0ce7886f KH |
9805 | if (category != coding_category_iso_8_1 |
9806 | && category != coding_category_iso_8_2) | |
4939150c | 9807 | ASET (attrs, coding_attr_ascii_compat, Qnil); |
df7492f9 KH |
9808 | } |
9809 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 9810 | { |
df7492f9 KH |
9811 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
9812 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
4939150c | 9813 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 | 9814 | category = coding_category_emacs_mule; |
c28a9453 | 9815 | } |
df7492f9 | 9816 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 9817 | { |
df7492f9 KH |
9818 | |
9819 | struct charset *charset; | |
9820 | ||
7d64c6ad | 9821 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 9822 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 9823 | error ("There should be three or four charsets"); |
df7492f9 KH |
9824 | |
9825 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9826 | if (CHARSET_DIMENSION (charset) != 1) | |
9827 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9828 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac | 9829 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9830 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9831 | |
9832 | charset_list = XCDR (charset_list); | |
9833 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9834 | if (CHARSET_DIMENSION (charset) != 1) | |
9835 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9836 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
9837 | |
9838 | charset_list = XCDR (charset_list); | |
9839 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9840 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
9841 | error ("Dimension of charset %s is not two", |
9842 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9843 | ||
9844 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
9845 | if (! NILP (charset_list)) |
9846 | { | |
9847 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9848 | if (CHARSET_DIMENSION (charset) != 2) | |
9849 | error ("Dimension of charset %s is not two", | |
9850 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9851 | } | |
df7492f9 KH |
9852 | |
9853 | category = coding_category_sjis; | |
9854 | Vsjis_coding_system = name; | |
c28a9453 | 9855 | } |
df7492f9 KH |
9856 | else if (EQ (coding_type, Qbig5)) |
9857 | { | |
9858 | struct charset *charset; | |
4ed46869 | 9859 | |
df7492f9 KH |
9860 | if (XINT (Flength (charset_list)) != 2) |
9861 | error ("There should be just two charsets"); | |
9862 | ||
9863 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9864 | if (CHARSET_DIMENSION (charset) != 1) | |
9865 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9866 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac | 9867 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9868 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9869 | |
9870 | charset_list = XCDR (charset_list); | |
9871 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9872 | if (CHARSET_DIMENSION (charset) != 2) | |
9873 | error ("Dimension of charset %s is not two", | |
8f924df7 | 9874 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 9875 | |
df7492f9 KH |
9876 | category = coding_category_big5; |
9877 | Vbig5_coding_system = name; | |
9878 | } | |
9879 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 9880 | { |
584948ac | 9881 | category = coding_category_raw_text; |
4939150c | 9882 | ASET (attrs, coding_attr_ascii_compat, Qt); |
c28a9453 | 9883 | } |
df7492f9 | 9884 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 9885 | { |
a470d443 KH |
9886 | Lisp_Object bom; |
9887 | ||
a470d443 KH |
9888 | if (nargs < coding_arg_utf8_max) |
9889 | goto short_args; | |
9890 | ||
9891 | bom = args[coding_arg_utf8_bom]; | |
9892 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9893 | { | |
9894 | CHECK_CONS (bom); | |
9895 | val = XCAR (bom); | |
9896 | CHECK_CODING_SYSTEM (val); | |
9897 | val = XCDR (bom); | |
9898 | CHECK_CODING_SYSTEM (val); | |
9899 | } | |
9900 | ASET (attrs, coding_attr_utf_bom, bom); | |
0e5317f7 | 9901 | if (NILP (bom)) |
4939150c | 9902 | ASET (attrs, coding_attr_ascii_compat, Qt); |
a470d443 KH |
9903 | |
9904 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
9905 | : NILP (bom) ? coding_category_utf_8_nosig | |
9906 | : coding_category_utf_8_sig); | |
4ed46869 | 9907 | } |
df7492f9 KH |
9908 | else if (EQ (coding_type, Qundecided)) |
9909 | category = coding_category_undecided; | |
4ed46869 | 9910 | else |
df7492f9 | 9911 | error ("Invalid coding system type: %s", |
8f924df7 | 9912 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 9913 | |
4939150c PE |
9914 | ASET (attrs, coding_attr_category, make_number (category)); |
9915 | ASET (attrs, coding_attr_plist, | |
9916 | Fcons (QCcategory, | |
9917 | Fcons (AREF (Vcoding_category_table, category), | |
9918 | CODING_ATTR_PLIST (attrs)))); | |
9919 | ASET (attrs, coding_attr_plist, | |
9920 | Fcons (QCascii_compatible_p, | |
9921 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), | |
9922 | CODING_ATTR_PLIST (attrs)))); | |
c4825358 | 9923 | |
df7492f9 KH |
9924 | eol_type = args[coding_arg_eol_type]; |
9925 | if (! NILP (eol_type) | |
9926 | && ! EQ (eol_type, Qunix) | |
9927 | && ! EQ (eol_type, Qdos) | |
9928 | && ! EQ (eol_type, Qmac)) | |
9929 | error ("Invalid eol-type"); | |
4ed46869 | 9930 | |
df7492f9 | 9931 | aliases = Fcons (name, Qnil); |
4ed46869 | 9932 | |
df7492f9 KH |
9933 | if (NILP (eol_type)) |
9934 | { | |
9935 | eol_type = make_subsidiaries (name); | |
9936 | for (i = 0; i < 3; i++) | |
1397dc18 | 9937 | { |
df7492f9 KH |
9938 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
9939 | ||
9940 | this_name = AREF (eol_type, i); | |
9941 | this_aliases = Fcons (this_name, Qnil); | |
9942 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
9943 | this_spec = Fmake_vector (make_number (3), attrs); | |
9944 | ASET (this_spec, 1, this_aliases); | |
9945 | ASET (this_spec, 2, this_eol_type); | |
9946 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
9947 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
9948 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
9949 | if (NILP (val)) | |
9950 | Vcoding_system_alist | |
9951 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
9952 | Vcoding_system_alist); | |
1397dc18 | 9953 | } |
d46c5b12 | 9954 | } |
4ed46869 | 9955 | |
df7492f9 KH |
9956 | spec_vec = Fmake_vector (make_number (3), attrs); |
9957 | ASET (spec_vec, 1, aliases); | |
9958 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 9959 | |
df7492f9 KH |
9960 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
9961 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
9962 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
9963 | if (NILP (val)) | |
9964 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
9965 | Vcoding_system_alist); | |
48b0f3ae | 9966 | |
df7492f9 KH |
9967 | { |
9968 | int id = coding_categories[category].id; | |
48b0f3ae | 9969 | |
df7492f9 KH |
9970 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
9971 | setup_coding_system (name, &coding_categories[category]); | |
9972 | } | |
48b0f3ae | 9973 | |
d46c5b12 | 9974 | return Qnil; |
48b0f3ae | 9975 | |
df7492f9 KH |
9976 | short_args: |
9977 | return Fsignal (Qwrong_number_of_arguments, | |
9978 | Fcons (intern ("define-coding-system-internal"), | |
9979 | make_number (nargs))); | |
d46c5b12 | 9980 | } |
4ed46869 | 9981 | |
d6925f38 | 9982 | |
a6f87d34 KH |
9983 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
9984 | 3, 3, 0, | |
9985 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
5842a27b | 9986 | (Lisp_Object coding_system, Lisp_Object prop, Lisp_Object val) |
a6f87d34 | 9987 | { |
3dbe7859 | 9988 | Lisp_Object spec, attrs; |
a6f87d34 KH |
9989 | |
9990 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
9991 | attrs = AREF (spec, 0); | |
9992 | if (EQ (prop, QCmnemonic)) | |
9993 | { | |
9994 | if (! STRINGP (val)) | |
9995 | CHECK_CHARACTER (val); | |
4939150c | 9996 | ASET (attrs, coding_attr_mnemonic, val); |
a6f87d34 | 9997 | } |
2133e2d1 | 9998 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
9999 | { |
10000 | if (NILP (val)) | |
10001 | val = make_number (' '); | |
10002 | else | |
10003 | CHECK_CHARACTER (val); | |
4939150c | 10004 | ASET (attrs, coding_attr_default_char, val); |
a6f87d34 KH |
10005 | } |
10006 | else if (EQ (prop, QCdecode_translation_table)) | |
10007 | { | |
10008 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10009 | CHECK_SYMBOL (val); | |
4939150c | 10010 | ASET (attrs, coding_attr_decode_tbl, val); |
a6f87d34 KH |
10011 | } |
10012 | else if (EQ (prop, QCencode_translation_table)) | |
10013 | { | |
10014 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10015 | CHECK_SYMBOL (val); | |
4939150c | 10016 | ASET (attrs, coding_attr_encode_tbl, val); |
a6f87d34 KH |
10017 | } |
10018 | else if (EQ (prop, QCpost_read_conversion)) | |
10019 | { | |
10020 | CHECK_SYMBOL (val); | |
4939150c | 10021 | ASET (attrs, coding_attr_post_read, val); |
a6f87d34 KH |
10022 | } |
10023 | else if (EQ (prop, QCpre_write_conversion)) | |
10024 | { | |
10025 | CHECK_SYMBOL (val); | |
4939150c | 10026 | ASET (attrs, coding_attr_pre_write, val); |
a6f87d34 | 10027 | } |
35befdaa KH |
10028 | else if (EQ (prop, QCascii_compatible_p)) |
10029 | { | |
4939150c | 10030 | ASET (attrs, coding_attr_ascii_compat, val); |
35befdaa | 10031 | } |
a6f87d34 | 10032 | |
4939150c PE |
10033 | ASET (attrs, coding_attr_plist, |
10034 | Fplist_put (CODING_ATTR_PLIST (attrs), prop, val)); | |
a6f87d34 KH |
10035 | return val; |
10036 | } | |
10037 | ||
10038 | ||
df7492f9 KH |
10039 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
10040 | Sdefine_coding_system_alias, 2, 2, 0, | |
10041 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
5842a27b | 10042 | (Lisp_Object alias, Lisp_Object coding_system) |
66cfb530 | 10043 | { |
583f71ca | 10044 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 10045 | |
df7492f9 KH |
10046 | CHECK_SYMBOL (alias); |
10047 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10048 | aliases = AREF (spec, 1); | |
d4a1d553 | 10049 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
10050 | element is a base coding system. Append ALIAS at the tail of the |
10051 | list. */ | |
df7492f9 KH |
10052 | while (!NILP (XCDR (aliases))) |
10053 | aliases = XCDR (aliases); | |
8f924df7 | 10054 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 10055 | |
df7492f9 KH |
10056 | eol_type = AREF (spec, 2); |
10057 | if (VECTORP (eol_type)) | |
4ed46869 | 10058 | { |
df7492f9 KH |
10059 | Lisp_Object subsidiaries; |
10060 | int i; | |
4ed46869 | 10061 | |
df7492f9 KH |
10062 | subsidiaries = make_subsidiaries (alias); |
10063 | for (i = 0; i < 3; i++) | |
10064 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
10065 | AREF (eol_type, i)); | |
4ed46869 | 10066 | } |
df7492f9 KH |
10067 | |
10068 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 10069 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
10070 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
10071 | if (NILP (val)) | |
10072 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
10073 | Vcoding_system_alist); | |
66cfb530 | 10074 | |
4ed46869 KH |
10075 | return Qnil; |
10076 | } | |
10077 | ||
a7ca3326 | 10078 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
df7492f9 KH |
10079 | 1, 1, 0, |
10080 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 10081 | Any alias or subsidiary coding system is not a base coding system. */) |
5842a27b | 10082 | (Lisp_Object coding_system) |
d46c5b12 | 10083 | { |
df7492f9 | 10084 | Lisp_Object spec, attrs; |
d46c5b12 | 10085 | |
df7492f9 KH |
10086 | if (NILP (coding_system)) |
10087 | return (Qno_conversion); | |
10088 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10089 | attrs = AREF (spec, 0); | |
10090 | return CODING_ATTR_BASE_NAME (attrs); | |
10091 | } | |
1397dc18 | 10092 | |
df7492f9 KH |
10093 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
10094 | 1, 1, 0, | |
10095 | doc: "Return the property list of CODING-SYSTEM.") | |
5842a27b | 10096 | (Lisp_Object coding_system) |
df7492f9 KH |
10097 | { |
10098 | Lisp_Object spec, attrs; | |
1397dc18 | 10099 | |
df7492f9 KH |
10100 | if (NILP (coding_system)) |
10101 | coding_system = Qno_conversion; | |
10102 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10103 | attrs = AREF (spec, 0); | |
10104 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
10105 | } |
10106 | ||
df7492f9 KH |
10107 | |
10108 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
10109 | 1, 1, 0, | |
da7db224 | 10110 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
5842a27b | 10111 | (Lisp_Object coding_system) |
66cfb530 | 10112 | { |
df7492f9 | 10113 | Lisp_Object spec; |
84d60297 | 10114 | |
df7492f9 KH |
10115 | if (NILP (coding_system)) |
10116 | coding_system = Qno_conversion; | |
10117 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 10118 | return AREF (spec, 1); |
df7492f9 | 10119 | } |
66cfb530 | 10120 | |
a7ca3326 | 10121 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
df7492f9 KH |
10122 | Scoding_system_eol_type, 1, 1, 0, |
10123 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 10124 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 10125 | |
df7492f9 KH |
10126 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
10127 | and CR respectively. | |
66cfb530 | 10128 | |
df7492f9 KH |
10129 | A vector value indicates that a format of end-of-line should be |
10130 | detected automatically. Nth element of the vector is the subsidiary | |
10131 | coding system whose eol-type is N. */) | |
5842a27b | 10132 | (Lisp_Object coding_system) |
6b89e3aa | 10133 | { |
df7492f9 KH |
10134 | Lisp_Object spec, eol_type; |
10135 | int n; | |
6b89e3aa | 10136 | |
df7492f9 KH |
10137 | if (NILP (coding_system)) |
10138 | coding_system = Qno_conversion; | |
10139 | if (! CODING_SYSTEM_P (coding_system)) | |
10140 | return Qnil; | |
10141 | spec = CODING_SYSTEM_SPEC (coding_system); | |
10142 | eol_type = AREF (spec, 2); | |
10143 | if (VECTORP (eol_type)) | |
10144 | return Fcopy_sequence (eol_type); | |
10145 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
10146 | return make_number (n); | |
6b89e3aa KH |
10147 | } |
10148 | ||
4ed46869 KH |
10149 | #endif /* emacs */ |
10150 | ||
10151 | \f | |
1397dc18 | 10152 | /*** 9. Post-amble ***/ |
4ed46869 | 10153 | |
dfcf069d | 10154 | void |
971de7fb | 10155 | init_coding_once (void) |
4ed46869 KH |
10156 | { |
10157 | int i; | |
10158 | ||
df7492f9 KH |
10159 | for (i = 0; i < coding_category_max; i++) |
10160 | { | |
10161 | coding_categories[i].id = -1; | |
10162 | coding_priorities[i] = i; | |
10163 | } | |
4ed46869 KH |
10164 | |
10165 | /* ISO2022 specific initialize routine. */ | |
10166 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 10167 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
10168 | for (i = 0x21; i < 0x7F; i++) |
10169 | iso_code_class[i] = ISO_graphic_plane_0; | |
10170 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 10171 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
10172 | for (i = 0xA1; i < 0xFF; i++) |
10173 | iso_code_class[i] = ISO_graphic_plane_1; | |
10174 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
10175 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
10176 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
10177 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
10178 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
10179 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
10180 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
10181 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
10182 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
10183 | ||
df7492f9 KH |
10184 | for (i = 0; i < 256; i++) |
10185 | { | |
10186 | emacs_mule_bytes[i] = 1; | |
10187 | } | |
7c78e542 KH |
10188 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
10189 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
10190 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
10191 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
10192 | } |
10193 | ||
10194 | #ifdef emacs | |
10195 | ||
dfcf069d | 10196 | void |
971de7fb | 10197 | syms_of_coding (void) |
e0e989f6 | 10198 | { |
df7492f9 | 10199 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
10200 | { |
10201 | Lisp_Object args[2]; | |
10202 | args[0] = QCtest; | |
10203 | args[1] = Qeq; | |
10204 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
10205 | } | |
df7492f9 KH |
10206 | |
10207 | staticpro (&Vsjis_coding_system); | |
10208 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 10209 | |
df7492f9 KH |
10210 | staticpro (&Vbig5_coding_system); |
10211 | Vbig5_coding_system = Qnil; | |
10212 | ||
24a73b0a KH |
10213 | staticpro (&Vcode_conversion_reused_workbuf); |
10214 | Vcode_conversion_reused_workbuf = Qnil; | |
10215 | ||
10216 | staticpro (&Vcode_conversion_workbuf_name); | |
2a0213a6 | 10217 | Vcode_conversion_workbuf_name = build_pure_c_string (" *code-conversion-work*"); |
e0e989f6 | 10218 | |
24a73b0a | 10219 | reused_workbuf_in_use = 0; |
df7492f9 KH |
10220 | |
10221 | DEFSYM (Qcharset, "charset"); | |
10222 | DEFSYM (Qtarget_idx, "target-idx"); | |
10223 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
10224 | Fset (Qcoding_system_history, Qnil); |
10225 | ||
9ce27fde | 10226 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 10227 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 10228 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
10229 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
10230 | ||
df7492f9 | 10231 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 10232 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
10233 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
10234 | ||
df7492f9 | 10235 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 10236 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10237 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
10238 | ||
df7492f9 | 10239 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 10240 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10241 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
10242 | ||
df7492f9 | 10243 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 10244 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
10245 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
10246 | ||
df7492f9 KH |
10247 | DEFSYM (Qcoding_system, "coding-system"); |
10248 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 10249 | |
df7492f9 KH |
10250 | DEFSYM (Qeol_type, "eol-type"); |
10251 | DEFSYM (Qunix, "unix"); | |
10252 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 10253 | |
df7492f9 KH |
10254 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
10255 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
10256 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
10257 | DEFSYM (Qdefault_char, "default-char"); | |
10258 | DEFSYM (Qundecided, "undecided"); | |
10259 | DEFSYM (Qno_conversion, "no-conversion"); | |
10260 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 10261 | |
df7492f9 | 10262 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 10263 | |
df7492f9 | 10264 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 10265 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 10266 | |
df7492f9 | 10267 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
10268 | DEFSYM (Qbig, "big"); |
10269 | DEFSYM (Qlittle, "little"); | |
27901516 | 10270 | |
df7492f9 KH |
10271 | DEFSYM (Qshift_jis, "shift-jis"); |
10272 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 10273 | |
df7492f9 | 10274 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 10275 | |
df7492f9 | 10276 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 | 10277 | Fput (Qcoding_system_error, Qerror_conditions, |
3438fe21 | 10278 | listn (CONSTYPE_PURE, 2, Qcoding_system_error, Qerror)); |
4ed46869 | 10279 | Fput (Qcoding_system_error, Qerror_message, |
2a0213a6 | 10280 | build_pure_c_string ("Invalid coding system")); |
4ed46869 | 10281 | |
05e6f5dc KH |
10282 | /* Intern this now in case it isn't already done. |
10283 | Setting this variable twice is harmless. | |
10284 | But don't staticpro it here--that is done in alloc.c. */ | |
d67b4f80 | 10285 | Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots"); |
70c22245 | 10286 | |
df7492f9 | 10287 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 10288 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
10289 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
10290 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10291 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10292 | |
df7492f9 | 10293 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10294 | |
df7492f9 | 10295 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10296 | |
01378f49 | 10297 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10298 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10299 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10300 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10301 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10302 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10303 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10304 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10305 | |
df7492f9 KH |
10306 | Vcoding_category_table |
10307 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10308 | staticpro (&Vcoding_category_table); | |
10309 | /* Followings are target of code detection. */ | |
10310 | ASET (Vcoding_category_table, coding_category_iso_7, | |
d67b4f80 | 10311 | intern_c_string ("coding-category-iso-7")); |
df7492f9 | 10312 | ASET (Vcoding_category_table, coding_category_iso_7_tight, |
d67b4f80 | 10313 | intern_c_string ("coding-category-iso-7-tight")); |
df7492f9 | 10314 | ASET (Vcoding_category_table, coding_category_iso_8_1, |
d67b4f80 | 10315 | intern_c_string ("coding-category-iso-8-1")); |
df7492f9 | 10316 | ASET (Vcoding_category_table, coding_category_iso_8_2, |
d67b4f80 | 10317 | intern_c_string ("coding-category-iso-8-2")); |
df7492f9 | 10318 | ASET (Vcoding_category_table, coding_category_iso_7_else, |
d67b4f80 | 10319 | intern_c_string ("coding-category-iso-7-else")); |
df7492f9 | 10320 | ASET (Vcoding_category_table, coding_category_iso_8_else, |
d67b4f80 | 10321 | intern_c_string ("coding-category-iso-8-else")); |
a470d443 | 10322 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
d67b4f80 | 10323 | intern_c_string ("coding-category-utf-8-auto")); |
a470d443 | 10324 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, |
d67b4f80 | 10325 | intern_c_string ("coding-category-utf-8")); |
a470d443 | 10326 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
d67b4f80 | 10327 | intern_c_string ("coding-category-utf-8-sig")); |
df7492f9 | 10328 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
d67b4f80 | 10329 | intern_c_string ("coding-category-utf-16-be")); |
ff563fce | 10330 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
d67b4f80 | 10331 | intern_c_string ("coding-category-utf-16-auto")); |
df7492f9 | 10332 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
d67b4f80 | 10333 | intern_c_string ("coding-category-utf-16-le")); |
df7492f9 | 10334 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, |
d67b4f80 | 10335 | intern_c_string ("coding-category-utf-16-be-nosig")); |
df7492f9 | 10336 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, |
d67b4f80 | 10337 | intern_c_string ("coding-category-utf-16-le-nosig")); |
df7492f9 | 10338 | ASET (Vcoding_category_table, coding_category_charset, |
d67b4f80 | 10339 | intern_c_string ("coding-category-charset")); |
df7492f9 | 10340 | ASET (Vcoding_category_table, coding_category_sjis, |
d67b4f80 | 10341 | intern_c_string ("coding-category-sjis")); |
df7492f9 | 10342 | ASET (Vcoding_category_table, coding_category_big5, |
d67b4f80 | 10343 | intern_c_string ("coding-category-big5")); |
df7492f9 | 10344 | ASET (Vcoding_category_table, coding_category_ccl, |
d67b4f80 | 10345 | intern_c_string ("coding-category-ccl")); |
df7492f9 | 10346 | ASET (Vcoding_category_table, coding_category_emacs_mule, |
d67b4f80 | 10347 | intern_c_string ("coding-category-emacs-mule")); |
df7492f9 KH |
10348 | /* Followings are NOT target of code detection. */ |
10349 | ASET (Vcoding_category_table, coding_category_raw_text, | |
d67b4f80 | 10350 | intern_c_string ("coding-category-raw-text")); |
df7492f9 | 10351 | ASET (Vcoding_category_table, coding_category_undecided, |
d67b4f80 | 10352 | intern_c_string ("coding-category-undecided")); |
ecf488bc | 10353 | |
065e3595 KH |
10354 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
10355 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
10356 | DEFSYM (Qinvalid_source, "invalid-source"); | |
10357 | DEFSYM (Qinterrupted, "interrupted"); | |
10358 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 10359 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10360 | |
4ed46869 KH |
10361 | defsubr (&Scoding_system_p); |
10362 | defsubr (&Sread_coding_system); | |
10363 | defsubr (&Sread_non_nil_coding_system); | |
10364 | defsubr (&Scheck_coding_system); | |
10365 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10366 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10367 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10368 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10369 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10370 | defsubr (&Sdecode_coding_region); |
10371 | defsubr (&Sencode_coding_region); | |
10372 | defsubr (&Sdecode_coding_string); | |
10373 | defsubr (&Sencode_coding_string); | |
10374 | defsubr (&Sdecode_sjis_char); | |
10375 | defsubr (&Sencode_sjis_char); | |
10376 | defsubr (&Sdecode_big5_char); | |
10377 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10378 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10379 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10380 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10381 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10382 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10383 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10384 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10385 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10386 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10387 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10388 | defsubr (&Scoding_system_base); |
10389 | defsubr (&Scoding_system_plist); | |
10390 | defsubr (&Scoding_system_aliases); | |
10391 | defsubr (&Scoding_system_eol_type); | |
10392 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10393 | |
29208e82 | 10394 | DEFVAR_LISP ("coding-system-list", Vcoding_system_list, |
48b0f3ae PJ |
10395 | doc: /* List of coding systems. |
10396 | ||
10397 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10398 | updated by the functions `define-coding-system' and |
48b0f3ae | 10399 | `define-coding-system-alias'. */); |
4608c386 KH |
10400 | Vcoding_system_list = Qnil; |
10401 | ||
29208e82 | 10402 | DEFVAR_LISP ("coding-system-alist", Vcoding_system_alist, |
48b0f3ae PJ |
10403 | doc: /* Alist of coding system names. |
10404 | Each element is one element list of coding system name. | |
446dcd75 | 10405 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10406 | |
10407 | Do not alter the value of this variable manually. This variable should be | |
10408 | updated by the functions `make-coding-system' and | |
10409 | `define-coding-system-alias'. */); | |
4608c386 KH |
10410 | Vcoding_system_alist = Qnil; |
10411 | ||
29208e82 | 10412 | DEFVAR_LISP ("coding-category-list", Vcoding_category_list, |
48b0f3ae PJ |
10413 | doc: /* List of coding-categories (symbols) ordered by priority. |
10414 | ||
10415 | On detecting a coding system, Emacs tries code detection algorithms | |
10416 | associated with each coding-category one by one in this order. When | |
10417 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10418 | system bound to the corresponding coding-category is selected. |
10419 | ||
448e17d6 | 10420 | Don't modify this variable directly, but use `set-coding-system-priority'. */); |
4ed46869 KH |
10421 | { |
10422 | int i; | |
10423 | ||
10424 | Vcoding_category_list = Qnil; | |
df7492f9 | 10425 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10426 | Vcoding_category_list |
28be1ada | 10427 | = Fcons (AREF (Vcoding_category_table, i), |
d46c5b12 | 10428 | Vcoding_category_list); |
4ed46869 KH |
10429 | } |
10430 | ||
29208e82 | 10431 | DEFVAR_LISP ("coding-system-for-read", Vcoding_system_for_read, |
48b0f3ae PJ |
10432 | doc: /* Specify the coding system for read operations. |
10433 | It is useful to bind this variable with `let', but do not set it globally. | |
10434 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10435 | If not, an appropriate element is used from one of the coding system alists. |
10436 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10437 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10438 | Vcoding_system_for_read = Qnil; |
10439 | ||
29208e82 | 10440 | DEFVAR_LISP ("coding-system-for-write", Vcoding_system_for_write, |
48b0f3ae PJ |
10441 | doc: /* Specify the coding system for write operations. |
10442 | Programs bind this variable with `let', but you should not set it globally. | |
10443 | If the value is a coding system, it is used for encoding of output, | |
10444 | when writing it to a file and when sending it to a file or subprocess. | |
10445 | ||
10446 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10447 | is used from one of the coding system alists. |
10448 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10449 | `process-coding-system-alist', and `network-coding-system-alist'. |
10450 | For output to files, if the above procedure does not specify a coding system, | |
10451 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10452 | Vcoding_system_for_write = Qnil; |
10453 | ||
29208e82 | 10454 | DEFVAR_LISP ("last-coding-system-used", Vlast_coding_system_used, |
df7492f9 KH |
10455 | doc: /* |
10456 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10457 | Vlast_coding_system_used = Qnil; |
10458 | ||
29208e82 | 10459 | DEFVAR_LISP ("last-code-conversion-error", Vlast_code_conversion_error, |
065e3595 KH |
10460 | doc: /* |
10461 | Error status of the last code conversion. | |
10462 | ||
10463 | When an error was detected in the last code conversion, this variable | |
10464 | is set to one of the following symbols. | |
10465 | `insufficient-source' | |
10466 | `inconsistent-eol' | |
10467 | `invalid-source' | |
10468 | `interrupted' | |
10469 | `insufficient-memory' | |
10470 | When no error was detected, the value doesn't change. So, to check | |
10471 | the error status of a code conversion by this variable, you must | |
10472 | explicitly set this variable to nil before performing code | |
10473 | conversion. */); | |
10474 | Vlast_code_conversion_error = Qnil; | |
10475 | ||
29208e82 | 10476 | DEFVAR_BOOL ("inhibit-eol-conversion", inhibit_eol_conversion, |
df7492f9 KH |
10477 | doc: /* |
10478 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10479 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10480 | such conversion. */); | |
9ce27fde KH |
10481 | inhibit_eol_conversion = 0; |
10482 | ||
29208e82 | 10483 | DEFVAR_BOOL ("inherit-process-coding-system", inherit_process_coding_system, |
df7492f9 KH |
10484 | doc: /* |
10485 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10486 | Bind it to t if the process output is to be treated as if it were a file |
10487 | read from some filesystem. */); | |
ed29121d EZ |
10488 | inherit_process_coding_system = 0; |
10489 | ||
29208e82 | 10490 | DEFVAR_LISP ("file-coding-system-alist", Vfile_coding_system_alist, |
df7492f9 KH |
10491 | doc: /* |
10492 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10493 | The format is ((PATTERN . VAL) ...), |
10494 | where PATTERN is a regular expression matching a file name, | |
10495 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10496 | If VAL is a coding system, it is used for both decoding and encoding | |
10497 | the file contents. | |
10498 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10499 | and the cdr part is used for encoding. | |
10500 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10501 | or a cons of coding systems which are used as above. The function is |
10502 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10503 | `find-operation-coding-system' was called. If the function can't decide |
10504 | a coding system, it can return `undecided' so that the normal | |
10505 | code-detection is performed. | |
48b0f3ae PJ |
10506 | |
10507 | See also the function `find-operation-coding-system' | |
10508 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10509 | Vfile_coding_system_alist = Qnil; |
10510 | ||
29208e82 | 10511 | DEFVAR_LISP ("process-coding-system-alist", Vprocess_coding_system_alist, |
df7492f9 KH |
10512 | doc: /* |
10513 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
10514 | The format is ((PATTERN . VAL) ...), |
10515 | where PATTERN is a regular expression matching a program name, | |
10516 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10517 | If VAL is a coding system, it is used for both decoding what received | |
10518 | from the program and encoding what sent to the program. | |
10519 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10520 | and the cdr part is used for encoding. | |
10521 | If VAL is a function symbol, the function must return a coding system | |
10522 | or a cons of coding systems which are used as above. | |
10523 | ||
10524 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
10525 | Vprocess_coding_system_alist = Qnil; |
10526 | ||
29208e82 | 10527 | DEFVAR_LISP ("network-coding-system-alist", Vnetwork_coding_system_alist, |
df7492f9 KH |
10528 | doc: /* |
10529 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
10530 | The format is ((PATTERN . VAL) ...), |
10531 | where PATTERN is a regular expression matching a network service name | |
10532 | or is a port number to connect to, | |
10533 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10534 | If VAL is a coding system, it is used for both decoding what received | |
10535 | from the network stream and encoding what sent to the network stream. | |
10536 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10537 | and the cdr part is used for encoding. | |
10538 | If VAL is a function symbol, the function must return a coding system | |
10539 | or a cons of coding systems which are used as above. | |
10540 | ||
10541 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 10542 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 10543 | |
29208e82 | 10544 | DEFVAR_LISP ("locale-coding-system", Vlocale_coding_system, |
75205970 RS |
10545 | doc: /* Coding system to use with system messages. |
10546 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
10547 | Vlocale_coding_system = Qnil; |
10548 | ||
005f0d35 | 10549 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
29208e82 | 10550 | DEFVAR_LISP ("eol-mnemonic-unix", eol_mnemonic_unix, |
df7492f9 KH |
10551 | doc: /* |
10552 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
2a0213a6 | 10553 | eol_mnemonic_unix = build_pure_c_string (":"); |
4ed46869 | 10554 | |
29208e82 | 10555 | DEFVAR_LISP ("eol-mnemonic-dos", eol_mnemonic_dos, |
df7492f9 KH |
10556 | doc: /* |
10557 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
2a0213a6 | 10558 | eol_mnemonic_dos = build_pure_c_string ("\\"); |
4ed46869 | 10559 | |
29208e82 | 10560 | DEFVAR_LISP ("eol-mnemonic-mac", eol_mnemonic_mac, |
df7492f9 KH |
10561 | doc: /* |
10562 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
2a0213a6 | 10563 | eol_mnemonic_mac = build_pure_c_string ("/"); |
4ed46869 | 10564 | |
29208e82 | 10565 | DEFVAR_LISP ("eol-mnemonic-undecided", eol_mnemonic_undecided, |
df7492f9 KH |
10566 | doc: /* |
10567 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
2a0213a6 | 10568 | eol_mnemonic_undecided = build_pure_c_string (":"); |
4ed46869 | 10569 | |
29208e82 | 10570 | DEFVAR_LISP ("enable-character-translation", Venable_character_translation, |
df7492f9 KH |
10571 | doc: /* |
10572 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 10573 | Venable_character_translation = Qt; |
bdd9fb48 | 10574 | |
f967223b | 10575 | DEFVAR_LISP ("standard-translation-table-for-decode", |
29208e82 | 10576 | Vstandard_translation_table_for_decode, |
48b0f3ae | 10577 | doc: /* Table for translating characters while decoding. */); |
f967223b | 10578 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 10579 | |
f967223b | 10580 | DEFVAR_LISP ("standard-translation-table-for-encode", |
29208e82 | 10581 | Vstandard_translation_table_for_encode, |
48b0f3ae | 10582 | doc: /* Table for translating characters while encoding. */); |
f967223b | 10583 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 10584 | |
29208e82 | 10585 | DEFVAR_LISP ("charset-revision-table", Vcharset_revision_table, |
48b0f3ae PJ |
10586 | doc: /* Alist of charsets vs revision numbers. |
10587 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
10588 | designate it with the escape sequence identifying revision (cdr part |
10589 | of the element). */); | |
10590 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
10591 | |
10592 | DEFVAR_LISP ("default-process-coding-system", | |
29208e82 | 10593 | Vdefault_process_coding_system, |
48b0f3ae PJ |
10594 | doc: /* Cons of coding systems used for process I/O by default. |
10595 | The car part is used for decoding a process output, | |
10596 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 10597 | Vdefault_process_coding_system = Qnil; |
c4825358 | 10598 | |
29208e82 | 10599 | DEFVAR_LISP ("latin-extra-code-table", Vlatin_extra_code_table, |
df7492f9 KH |
10600 | doc: /* |
10601 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
10602 | This is a vector of length 256. |
10603 | If Nth element is non-nil, the existence of code N in a file | |
10604 | \(or output of subprocess) doesn't prevent it to be detected as | |
10605 | a coding system of ISO 2022 variant which has a flag | |
10606 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
10607 | or reading output of a subprocess. | |
446dcd75 | 10608 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 10609 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
10610 | |
10611 | DEFVAR_LISP ("select-safe-coding-system-function", | |
29208e82 | 10612 | Vselect_safe_coding_system_function, |
df7492f9 KH |
10613 | doc: /* |
10614 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
10615 | |
10616 | If set, this function is called to force a user to select a proper | |
10617 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
10618 | coding system used in each operation can't encode the text. The |
10619 | function should take care that the buffer is not modified while | |
10620 | the coding system is being selected. | |
48b0f3ae PJ |
10621 | |
10622 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
10623 | Vselect_safe_coding_system_function = Qnil; |
10624 | ||
5d5bf4d8 | 10625 | DEFVAR_BOOL ("coding-system-require-warning", |
29208e82 | 10626 | coding_system_require_warning, |
5d5bf4d8 | 10627 | doc: /* Internal use only. |
6b89e3aa KH |
10628 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
10629 | called even if `coding-system-for-write' is non-nil. The command | |
10630 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
10631 | coding_system_require_warning = 0; |
10632 | ||
10633 | ||
22ab2303 | 10634 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
29208e82 | 10635 | inhibit_iso_escape_detection, |
df7492f9 | 10636 | doc: /* |
97b1b294 | 10637 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 10638 | |
97b1b294 EZ |
10639 | When Emacs reads text, it tries to detect how the text is encoded. |
10640 | This code detection is sensitive to escape sequences. If Emacs sees | |
10641 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
10642 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
10643 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
10644 | |
10645 | However, there may be a case that you want to read escape sequences in | |
10646 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
10647 | Then the code detection will ignore any escape sequences, and no text is |
10648 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
10649 | escape sequences become visible in a buffer. |
10650 | ||
10651 | The default value is nil, and it is strongly recommended not to change | |
10652 | it. That is because many Emacs Lisp source files that contain | |
10653 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
10654 | in Emacs's distribution, and they won't be decoded correctly on | |
10655 | reading if you suppress escape sequence detection. | |
10656 | ||
10657 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 10658 | to explicitly specify some coding system that doesn't use ISO-2022 |
48b0f3ae | 10659 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 10660 | inhibit_iso_escape_detection = 0; |
002fdb44 | 10661 | |
97b1b294 | 10662 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
29208e82 | 10663 | inhibit_null_byte_detection, |
97b1b294 EZ |
10664 | doc: /* If non-nil, Emacs ignores null bytes on code detection. |
10665 | By default, Emacs treats it as binary data, and does not attempt to | |
10666 | decode it. The effect is as if you specified `no-conversion' for | |
10667 | reading that text. | |
10668 | ||
10669 | Set this to non-nil when a regular text happens to include null bytes. | |
10670 | Examples are Index nodes of Info files and null-byte delimited output | |
10671 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
10672 | decode text as usual. */); | |
10673 | inhibit_null_byte_detection = 0; | |
10674 | ||
29208e82 | 10675 | DEFVAR_LISP ("translation-table-for-input", Vtranslation_table_for_input, |
15c8f9d1 | 10676 | doc: /* Char table for translating self-inserting characters. |
446dcd75 | 10677 | This is applied to the result of input methods, not their input. |
8434d0b8 EZ |
10678 | See also `keyboard-translate-table'. |
10679 | ||
10680 | Use of this variable for character code unification was rendered | |
10681 | obsolete in Emacs 23.1 and later, since Unicode is now the basis of | |
10682 | internal character representation. */); | |
002fdb44 | 10683 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 10684 | |
2c78b7e1 KH |
10685 | { |
10686 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 10687 | Lisp_Object plist[16]; |
2c78b7e1 KH |
10688 | int i; |
10689 | ||
10690 | for (i = 0; i < coding_arg_max; i++) | |
10691 | args[i] = Qnil; | |
10692 | ||
d67b4f80 | 10693 | plist[0] = intern_c_string (":name"); |
2c78b7e1 | 10694 | plist[1] = args[coding_arg_name] = Qno_conversion; |
d67b4f80 | 10695 | plist[2] = intern_c_string (":mnemonic"); |
2c78b7e1 | 10696 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); |
d67b4f80 | 10697 | plist[4] = intern_c_string (":coding-type"); |
2c78b7e1 | 10698 | plist[5] = args[coding_arg_coding_type] = Qraw_text; |
d67b4f80 | 10699 | plist[6] = intern_c_string (":ascii-compatible-p"); |
2c78b7e1 | 10700 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; |
d67b4f80 | 10701 | plist[8] = intern_c_string (":default-char"); |
2c78b7e1 | 10702 | plist[9] = args[coding_arg_default_char] = make_number (0); |
d67b4f80 | 10703 | plist[10] = intern_c_string (":for-unibyte"); |
8f924df7 | 10704 | plist[11] = args[coding_arg_for_unibyte] = Qt; |
d67b4f80 | 10705 | plist[12] = intern_c_string (":docstring"); |
2a0213a6 | 10706 | plist[13] = build_pure_c_string ("Do no conversion.\n\ |
2c78b7e1 KH |
10707 | \n\ |
10708 | When you visit a file with this coding, the file is read into a\n\ | |
10709 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
10710 | character."); | |
d67b4f80 | 10711 | plist[14] = intern_c_string (":eol-type"); |
8f924df7 KH |
10712 | plist[15] = args[coding_arg_eol_type] = Qunix; |
10713 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 10714 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
10715 | |
10716 | plist[1] = args[coding_arg_name] = Qundecided; | |
10717 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
10718 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
10719 | /* This is already set. | |
35befdaa | 10720 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
d67b4f80 | 10721 | plist[8] = intern_c_string (":charset-list"); |
ae6f73fa KH |
10722 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); |
10723 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
2a0213a6 | 10724 | plist[13] = build_pure_c_string ("No conversion on encoding, automatic conversion on decoding."); |
ae6f73fa KH |
10725 | plist[15] = args[coding_arg_eol_type] = Qnil; |
10726 | args[coding_arg_plist] = Flist (16, plist); | |
10727 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
10728 | } |
10729 | ||
2c78b7e1 | 10730 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
10731 | |
10732 | { | |
10733 | int i; | |
10734 | ||
10735 | for (i = 0; i < coding_category_max; i++) | |
10736 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
10737 | } | |
1a4990fb | 10738 | #if defined (DOS_NT) |
fcbcfb64 KH |
10739 | system_eol_type = Qdos; |
10740 | #else | |
10741 | system_eol_type = Qunix; | |
10742 | #endif | |
10743 | staticpro (&system_eol_type); | |
4ed46869 KH |
10744 | } |
10745 | ||
68c45bf0 | 10746 | char * |
971de7fb | 10747 | emacs_strerror (int error_number) |
68c45bf0 PE |
10748 | { |
10749 | char *str; | |
10750 | ||
ca9c0567 | 10751 | synchronize_system_messages_locale (); |
68c45bf0 PE |
10752 | str = strerror (error_number); |
10753 | ||
10754 | if (! NILP (Vlocale_coding_system)) | |
10755 | { | |
10756 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
10757 | Vlocale_coding_system, | |
10758 | 0); | |
51b59d79 | 10759 | str = SSDATA (dec); |
68c45bf0 PE |
10760 | } |
10761 | ||
10762 | return str; | |
10763 | } | |
10764 | ||
4ed46869 | 10765 | #endif /* emacs */ |