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 KH |
922 | /* Store multibyte form of the character C in P, and advance P to the |
923 | end of the multibyte form. This is like CHAR_STRING_ADVANCE but it | |
924 | never calls MAYBE_UNIFY_CHAR. */ | |
925 | ||
926 | #define CHAR_STRING_ADVANCE_NO_UNIFY(c, p) \ | |
927 | do { \ | |
928 | if ((c) <= MAX_1_BYTE_CHAR) \ | |
929 | *(p)++ = (c); \ | |
930 | else if ((c) <= MAX_2_BYTE_CHAR) \ | |
931 | *(p)++ = (0xC0 | ((c) >> 6)), \ | |
932 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
933 | else if ((c) <= MAX_3_BYTE_CHAR) \ | |
934 | *(p)++ = (0xE0 | ((c) >> 12)), \ | |
935 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ | |
936 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
937 | else if ((c) <= MAX_4_BYTE_CHAR) \ | |
938 | *(p)++ = (0xF0 | (c >> 18)), \ | |
939 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
940 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
941 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
942 | else if ((c) <= MAX_5_BYTE_CHAR) \ | |
943 | *(p)++ = 0xF8, \ | |
944 | *(p)++ = (0x80 | ((c >> 18) & 0x0F)), \ | |
945 | *(p)++ = (0x80 | ((c >> 12) & 0x3F)), \ | |
946 | *(p)++ = (0x80 | ((c >> 6) & 0x3F)), \ | |
947 | *(p)++ = (0x80 | (c & 0x3F)); \ | |
948 | else \ | |
949 | (p) += BYTE8_STRING ((c) - 0x3FFF80, p); \ | |
950 | } while (0) | |
951 | ||
952 | ||
953 | /* Return the character code of character whose multibyte form is at | |
954 | P, and advance P to the end of the multibyte form. This is like | |
955 | STRING_CHAR_ADVANCE, but it never calls MAYBE_UNIFY_CHAR. */ | |
956 | ||
957 | #define STRING_CHAR_ADVANCE_NO_UNIFY(p) \ | |
958 | (!((p)[0] & 0x80) \ | |
959 | ? *(p)++ \ | |
960 | : ! ((p)[0] & 0x20) \ | |
961 | ? ((p) += 2, \ | |
962 | ((((p)[-2] & 0x1F) << 6) \ | |
963 | | ((p)[-1] & 0x3F) \ | |
964 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
965 | : ! ((p)[0] & 0x10) \ | |
966 | ? ((p) += 3, \ | |
967 | ((((p)[-3] & 0x0F) << 12) \ | |
968 | | (((p)[-2] & 0x3F) << 6) \ | |
969 | | ((p)[-1] & 0x3F))) \ | |
970 | : ! ((p)[0] & 0x08) \ | |
971 | ? ((p) += 4, \ | |
972 | ((((p)[-4] & 0xF) << 18) \ | |
973 | | (((p)[-3] & 0x3F) << 12) \ | |
974 | | (((p)[-2] & 0x3F) << 6) \ | |
975 | | ((p)[-1] & 0x3F))) \ | |
976 | : ((p) += 5, \ | |
977 | ((((p)[-4] & 0x3F) << 18) \ | |
978 | | (((p)[-3] & 0x3F) << 12) \ | |
979 | | (((p)[-2] & 0x3F) << 6) \ | |
980 | | ((p)[-1] & 0x3F)))) | |
981 | ||
aa72b389 | 982 | |
c1892f11 | 983 | /* Set coding->source from coding->src_object. */ |
5eb05ea3 | 984 | |
c1892f11 | 985 | static void |
971de7fb | 986 | coding_set_source (struct coding_system *coding) |
aa72b389 | 987 | { |
df7492f9 KH |
988 | if (BUFFERP (coding->src_object)) |
989 | { | |
2cb26057 | 990 | struct buffer *buf = XBUFFER (coding->src_object); |
aa72b389 | 991 | |
df7492f9 | 992 | if (coding->src_pos < 0) |
2cb26057 | 993 | coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte; |
df7492f9 | 994 | else |
2cb26057 | 995 | coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte); |
aa72b389 | 996 | } |
df7492f9 | 997 | else if (STRINGP (coding->src_object)) |
aa72b389 | 998 | { |
8f924df7 | 999 | coding->source = SDATA (coding->src_object) + coding->src_pos_byte; |
aa72b389 | 1000 | } |
df7492f9 | 1001 | else |
f38b440c PE |
1002 | { |
1003 | /* Otherwise, the source is C string and is never relocated | |
1004 | automatically. Thus we don't have to update anything. */ | |
1005 | } | |
df7492f9 | 1006 | } |
aa72b389 | 1007 | |
5eb05ea3 | 1008 | |
c1892f11 PE |
1009 | /* Set coding->source from coding->src_object, and return how many |
1010 | bytes coding->source was changed. */ | |
5eb05ea3 | 1011 | |
8f50130c | 1012 | static ptrdiff_t |
c1892f11 | 1013 | coding_change_source (struct coding_system *coding) |
df7492f9 | 1014 | { |
c1892f11 PE |
1015 | const unsigned char *orig = coding->source; |
1016 | coding_set_source (coding); | |
1017 | return coding->source - orig; | |
1018 | } | |
1019 | ||
5eb05ea3 | 1020 | |
c1892f11 PE |
1021 | /* Set coding->destination from coding->dst_object. */ |
1022 | ||
1023 | static void | |
1024 | coding_set_destination (struct coding_system *coding) | |
1025 | { | |
df7492f9 | 1026 | if (BUFFERP (coding->dst_object)) |
aa72b389 | 1027 | { |
a0241d01 | 1028 | if (BUFFERP (coding->src_object) && coding->src_pos < 0) |
aa72b389 | 1029 | { |
13818c30 | 1030 | coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE; |
28f67a95 KH |
1031 | coding->dst_bytes = (GAP_END_ADDR |
1032 | - (coding->src_bytes - coding->consumed) | |
1033 | - coding->destination); | |
aa72b389 | 1034 | } |
df7492f9 | 1035 | else |
28f67a95 KH |
1036 | { |
1037 | /* We are sure that coding->dst_pos_byte is before the gap | |
1038 | of the buffer. */ | |
1039 | coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object)) | |
13818c30 | 1040 | + coding->dst_pos_byte - BEG_BYTE); |
28f67a95 KH |
1041 | coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object)) |
1042 | - coding->destination); | |
1043 | } | |
df7492f9 KH |
1044 | } |
1045 | else | |
f38b440c PE |
1046 | { |
1047 | /* Otherwise, the destination is C string and is never relocated | |
1048 | automatically. Thus we don't have to update anything. */ | |
1049 | } | |
c1892f11 PE |
1050 | } |
1051 | ||
1052 | ||
1053 | /* Set coding->destination from coding->dst_object, and return how | |
1054 | many bytes coding->destination was changed. */ | |
1055 | ||
1056 | static ptrdiff_t | |
1057 | coding_change_destination (struct coding_system *coding) | |
1058 | { | |
1059 | const unsigned char *orig = coding->destination; | |
1060 | coding_set_destination (coding); | |
5eb05ea3 | 1061 | return coding->destination - orig; |
df7492f9 KH |
1062 | } |
1063 | ||
1064 | ||
1065 | static void | |
d311d28c | 1066 | coding_alloc_by_realloc (struct coding_system *coding, ptrdiff_t bytes) |
df7492f9 | 1067 | { |
c9d624c6 | 1068 | if (STRING_BYTES_BOUND - coding->dst_bytes < bytes) |
d1f3d2af | 1069 | string_overflow (); |
38182d90 PE |
1070 | coding->destination = xrealloc (coding->destination, |
1071 | coding->dst_bytes + bytes); | |
df7492f9 KH |
1072 | coding->dst_bytes += bytes; |
1073 | } | |
1074 | ||
1075 | static void | |
cf84bb53 | 1076 | coding_alloc_by_making_gap (struct coding_system *coding, |
d311d28c | 1077 | ptrdiff_t gap_head_used, ptrdiff_t bytes) |
df7492f9 | 1078 | { |
db274c7a | 1079 | if (EQ (coding->src_object, coding->dst_object)) |
df7492f9 | 1080 | { |
db274c7a KH |
1081 | /* The gap may contain the produced data at the head and not-yet |
1082 | consumed data at the tail. To preserve those data, we at | |
1083 | first make the gap size to zero, then increase the gap | |
1084 | size. */ | |
d311d28c | 1085 | ptrdiff_t add = GAP_SIZE; |
db274c7a KH |
1086 | |
1087 | GPT += gap_head_used, GPT_BYTE += gap_head_used; | |
1088 | GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add; | |
df7492f9 KH |
1089 | make_gap (bytes); |
1090 | GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add; | |
db274c7a | 1091 | GPT -= gap_head_used, GPT_BYTE -= gap_head_used; |
df7492f9 | 1092 | } |
730fff51 | 1093 | else |
df7492f9 | 1094 | { |
2c78b7e1 KH |
1095 | Lisp_Object this_buffer; |
1096 | ||
1097 | this_buffer = Fcurrent_buffer (); | |
df7492f9 KH |
1098 | set_buffer_internal (XBUFFER (coding->dst_object)); |
1099 | make_gap (bytes); | |
1100 | set_buffer_internal (XBUFFER (this_buffer)); | |
aa72b389 | 1101 | } |
df7492f9 | 1102 | } |
8f924df7 | 1103 | |
df7492f9 KH |
1104 | |
1105 | static unsigned char * | |
d311d28c | 1106 | alloc_destination (struct coding_system *coding, ptrdiff_t nbytes, |
cf84bb53 | 1107 | unsigned char *dst) |
df7492f9 | 1108 | { |
d311d28c | 1109 | ptrdiff_t offset = dst - coding->destination; |
df7492f9 KH |
1110 | |
1111 | if (BUFFERP (coding->dst_object)) | |
db274c7a KH |
1112 | { |
1113 | struct buffer *buf = XBUFFER (coding->dst_object); | |
1114 | ||
1115 | coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes); | |
1116 | } | |
aa72b389 | 1117 | else |
df7492f9 | 1118 | coding_alloc_by_realloc (coding, nbytes); |
df7492f9 KH |
1119 | coding_set_destination (coding); |
1120 | dst = coding->destination + offset; | |
1121 | return dst; | |
1122 | } | |
aa72b389 | 1123 | |
ff0dacd7 KH |
1124 | /** Macros for annotations. */ |
1125 | ||
ff0dacd7 KH |
1126 | /* An annotation data is stored in the array coding->charbuf in this |
1127 | format: | |
69a80ea3 | 1128 | [ -LENGTH ANNOTATION_MASK NCHARS ... ] |
ff0dacd7 KH |
1129 | LENGTH is the number of elements in the annotation. |
1130 | ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK. | |
69a80ea3 | 1131 | NCHARS is the number of characters in the text annotated. |
ff0dacd7 KH |
1132 | |
1133 | The format of the following elements depend on ANNOTATION_MASK. | |
1134 | ||
1135 | In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements | |
1136 | follows: | |
e951386e KH |
1137 | ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ] |
1138 | ||
1139 | NBYTES is the number of bytes specified in the header part of | |
1140 | old-style emacs-mule encoding, or 0 for the other kind of | |
1141 | composition. | |
1142 | ||
ff0dacd7 | 1143 | METHOD is one of enum composition_method. |
e951386e | 1144 | |
ad1746f5 | 1145 | Optional COMPOSITION-COMPONENTS are characters and composition |
ff0dacd7 KH |
1146 | rules. |
1147 | ||
1148 | In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID | |
e951386e KH |
1149 | follows. |
1150 | ||
1151 | If ANNOTATION_MASK is 0, this annotation is just a space holder to | |
1152 | recover from an invalid annotation, and should be skipped by | |
1153 | produce_annotation. */ | |
1154 | ||
1155 | /* Maximum length of the header of annotation data. */ | |
1156 | #define MAX_ANNOTATION_LENGTH 5 | |
ff0dacd7 | 1157 | |
69a80ea3 | 1158 | #define ADD_ANNOTATION_DATA(buf, len, mask, nchars) \ |
ff0dacd7 KH |
1159 | do { \ |
1160 | *(buf)++ = -(len); \ | |
1161 | *(buf)++ = (mask); \ | |
69a80ea3 | 1162 | *(buf)++ = (nchars); \ |
ff0dacd7 KH |
1163 | coding->annotated = 1; \ |
1164 | } while (0); | |
1165 | ||
e951386e | 1166 | #define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method) \ |
69a80ea3 | 1167 | do { \ |
e951386e KH |
1168 | ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \ |
1169 | *buf++ = nbytes; \ | |
69a80ea3 | 1170 | *buf++ = method; \ |
ff0dacd7 KH |
1171 | } while (0) |
1172 | ||
1173 | ||
69a80ea3 KH |
1174 | #define ADD_CHARSET_DATA(buf, nchars, id) \ |
1175 | do { \ | |
1176 | ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars); \ | |
1177 | *buf++ = id; \ | |
ff0dacd7 KH |
1178 | } while (0) |
1179 | ||
df7492f9 KH |
1180 | \f |
1181 | /*** 2. Emacs' internal format (emacs-utf-8) ***/ | |
1182 | ||
1183 | ||
1184 | ||
1185 | \f | |
1186 | /*** 3. UTF-8 ***/ | |
1187 | ||
1188 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 1189 | Return true if a text is encoded in UTF-8. */ |
df7492f9 KH |
1190 | |
1191 | #define UTF_8_1_OCTET_P(c) ((c) < 0x80) | |
1192 | #define UTF_8_EXTRA_OCTET_P(c) (((c) & 0xC0) == 0x80) | |
1193 | #define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0) | |
1194 | #define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0) | |
1195 | #define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0) | |
1196 | #define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8) | |
1197 | ||
a470d443 KH |
1198 | #define UTF_8_BOM_1 0xEF |
1199 | #define UTF_8_BOM_2 0xBB | |
1200 | #define UTF_8_BOM_3 0xBF | |
1201 | ||
f10fe38f | 1202 | static bool |
cf84bb53 JB |
1203 | detect_coding_utf_8 (struct coding_system *coding, |
1204 | struct coding_detection_info *detect_info) | |
df7492f9 | 1205 | { |
065e3595 | 1206 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 1207 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 1208 | bool multibytep = coding->src_multibyte; |
d311d28c | 1209 | ptrdiff_t consumed_chars = 0; |
f10fe38f PE |
1210 | bool bom_found = 0; |
1211 | bool found = 0; | |
df7492f9 | 1212 | |
ff0dacd7 | 1213 | detect_info->checked |= CATEGORY_MASK_UTF_8; |
df7492f9 KH |
1214 | /* A coding system of this category is always ASCII compatible. */ |
1215 | src += coding->head_ascii; | |
1216 | ||
1217 | while (1) | |
aa72b389 | 1218 | { |
df7492f9 | 1219 | int c, c1, c2, c3, c4; |
aa72b389 | 1220 | |
065e3595 | 1221 | src_base = src; |
df7492f9 | 1222 | ONE_MORE_BYTE (c); |
065e3595 | 1223 | if (c < 0 || UTF_8_1_OCTET_P (c)) |
df7492f9 KH |
1224 | continue; |
1225 | ONE_MORE_BYTE (c1); | |
065e3595 | 1226 | if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1)) |
df7492f9 KH |
1227 | break; |
1228 | if (UTF_8_2_OCTET_LEADING_P (c)) | |
aa72b389 | 1229 | { |
a470d443 | 1230 | found = 1; |
df7492f9 | 1231 | continue; |
aa72b389 | 1232 | } |
df7492f9 | 1233 | ONE_MORE_BYTE (c2); |
065e3595 | 1234 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1235 | break; |
1236 | if (UTF_8_3_OCTET_LEADING_P (c)) | |
aa72b389 | 1237 | { |
a470d443 KH |
1238 | found = 1; |
1239 | if (src_base == coding->source | |
1240 | && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3) | |
1241 | bom_found = 1; | |
df7492f9 | 1242 | continue; |
aa72b389 | 1243 | } |
df7492f9 | 1244 | ONE_MORE_BYTE (c3); |
065e3595 | 1245 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1246 | break; |
1247 | if (UTF_8_4_OCTET_LEADING_P (c)) | |
aa72b389 | 1248 | { |
a470d443 | 1249 | found = 1; |
df7492f9 KH |
1250 | continue; |
1251 | } | |
1252 | ONE_MORE_BYTE (c4); | |
065e3595 | 1253 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1254 | break; |
1255 | if (UTF_8_5_OCTET_LEADING_P (c)) | |
1256 | { | |
a470d443 | 1257 | found = 1; |
df7492f9 KH |
1258 | continue; |
1259 | } | |
1260 | break; | |
aa72b389 | 1261 | } |
ff0dacd7 | 1262 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
df7492f9 | 1263 | return 0; |
aa72b389 | 1264 | |
df7492f9 | 1265 | no_more_source: |
065e3595 | 1266 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
aa72b389 | 1267 | { |
ff0dacd7 | 1268 | detect_info->rejected |= CATEGORY_MASK_UTF_8; |
89528eb3 | 1269 | return 0; |
aa72b389 | 1270 | } |
a470d443 KH |
1271 | if (bom_found) |
1272 | { | |
1273 | /* The first character 0xFFFE doesn't necessarily mean a BOM. */ | |
1274 | detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG; | |
1275 | } | |
1276 | else | |
1277 | { | |
1278 | detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG; | |
0e17387a KH |
1279 | if (found) |
1280 | detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG; | |
a470d443 | 1281 | } |
ff0dacd7 | 1282 | return 1; |
aa72b389 KH |
1283 | } |
1284 | ||
4ed46869 | 1285 | |
b73bfc1c | 1286 | static void |
971de7fb | 1287 | decode_coding_utf_8 (struct coding_system *coding) |
b73bfc1c | 1288 | { |
8f924df7 KH |
1289 | const unsigned char *src = coding->source + coding->consumed; |
1290 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1291 | const unsigned char *src_base; | |
69a80ea3 KH |
1292 | int *charbuf = coding->charbuf + coding->charbuf_used; |
1293 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
d311d28c | 1294 | ptrdiff_t consumed_chars = 0, consumed_chars_base = 0; |
f10fe38f | 1295 | bool multibytep = coding->src_multibyte; |
a470d443 | 1296 | enum utf_bom_type bom = CODING_UTF_8_BOM (coding); |
f10fe38f PE |
1297 | bool eol_dos |
1298 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1299 | int byte_after_cr = -1; |
4ed46869 | 1300 | |
a470d443 KH |
1301 | if (bom != utf_without_bom) |
1302 | { | |
1303 | int c1, c2, c3; | |
1304 | ||
1305 | src_base = src; | |
1306 | ONE_MORE_BYTE (c1); | |
1307 | if (! UTF_8_3_OCTET_LEADING_P (c1)) | |
1308 | src = src_base; | |
1309 | else | |
1310 | { | |
159bd5a2 | 1311 | ONE_MORE_BYTE (c2); |
a470d443 KH |
1312 | if (! UTF_8_EXTRA_OCTET_P (c2)) |
1313 | src = src_base; | |
1314 | else | |
1315 | { | |
159bd5a2 | 1316 | ONE_MORE_BYTE (c3); |
a470d443 KH |
1317 | if (! UTF_8_EXTRA_OCTET_P (c3)) |
1318 | src = src_base; | |
1319 | else | |
1320 | { | |
1321 | if ((c1 != UTF_8_BOM_1) | |
1322 | || (c2 != UTF_8_BOM_2) || (c3 != UTF_8_BOM_3)) | |
1323 | src = src_base; | |
1324 | else | |
1325 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1326 | } | |
1327 | } | |
1328 | } | |
1329 | } | |
1330 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1331 | ||
df7492f9 | 1332 | while (1) |
b73bfc1c | 1333 | { |
df7492f9 | 1334 | int c, c1, c2, c3, c4, c5; |
ec6d2bb8 | 1335 | |
df7492f9 KH |
1336 | src_base = src; |
1337 | consumed_chars_base = consumed_chars; | |
4af310db | 1338 | |
df7492f9 | 1339 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1340 | { |
1341 | if (byte_after_cr >= 0) | |
1342 | src_base--; | |
1343 | break; | |
1344 | } | |
df7492f9 | 1345 | |
119852e7 KH |
1346 | if (byte_after_cr >= 0) |
1347 | c1 = byte_after_cr, byte_after_cr = -1; | |
1348 | else | |
1349 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1350 | if (c1 < 0) |
1351 | { | |
1352 | c = - c1; | |
1353 | } | |
1a4990fb | 1354 | else if (UTF_8_1_OCTET_P (c1)) |
df7492f9 | 1355 | { |
2735d060 | 1356 | if (eol_dos && c1 == '\r') |
119852e7 | 1357 | ONE_MORE_BYTE (byte_after_cr); |
df7492f9 | 1358 | c = c1; |
4af310db | 1359 | } |
df7492f9 | 1360 | else |
4af310db | 1361 | { |
df7492f9 | 1362 | ONE_MORE_BYTE (c2); |
065e3595 | 1363 | if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2)) |
df7492f9 KH |
1364 | goto invalid_code; |
1365 | if (UTF_8_2_OCTET_LEADING_P (c1)) | |
4af310db | 1366 | { |
b0edb2c5 DL |
1367 | c = ((c1 & 0x1F) << 6) | (c2 & 0x3F); |
1368 | /* Reject overlong sequences here and below. Encoders | |
1369 | producing them are incorrect, they can be misleading, | |
1370 | and they mess up read/write invariance. */ | |
1371 | if (c < 128) | |
1372 | goto invalid_code; | |
4af310db | 1373 | } |
df7492f9 | 1374 | else |
aa72b389 | 1375 | { |
df7492f9 | 1376 | ONE_MORE_BYTE (c3); |
065e3595 | 1377 | if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3)) |
df7492f9 KH |
1378 | goto invalid_code; |
1379 | if (UTF_8_3_OCTET_LEADING_P (c1)) | |
b0edb2c5 DL |
1380 | { |
1381 | c = (((c1 & 0xF) << 12) | |
1382 | | ((c2 & 0x3F) << 6) | (c3 & 0x3F)); | |
72fe1301 DL |
1383 | if (c < 0x800 |
1384 | || (c >= 0xd800 && c < 0xe000)) /* surrogates (invalid) */ | |
b0edb2c5 DL |
1385 | goto invalid_code; |
1386 | } | |
df7492f9 KH |
1387 | else |
1388 | { | |
1389 | ONE_MORE_BYTE (c4); | |
065e3595 | 1390 | if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4)) |
df7492f9 KH |
1391 | goto invalid_code; |
1392 | if (UTF_8_4_OCTET_LEADING_P (c1)) | |
b0edb2c5 | 1393 | { |
df7492f9 KH |
1394 | c = (((c1 & 0x7) << 18) | ((c2 & 0x3F) << 12) |
1395 | | ((c3 & 0x3F) << 6) | (c4 & 0x3F)); | |
b0edb2c5 DL |
1396 | if (c < 0x10000) |
1397 | goto invalid_code; | |
1398 | } | |
df7492f9 KH |
1399 | else |
1400 | { | |
1401 | ONE_MORE_BYTE (c5); | |
065e3595 | 1402 | if (c5 < 0 || ! UTF_8_EXTRA_OCTET_P (c5)) |
df7492f9 KH |
1403 | goto invalid_code; |
1404 | if (UTF_8_5_OCTET_LEADING_P (c1)) | |
1405 | { | |
1406 | c = (((c1 & 0x3) << 24) | ((c2 & 0x3F) << 18) | |
1407 | | ((c3 & 0x3F) << 12) | ((c4 & 0x3F) << 6) | |
1408 | | (c5 & 0x3F)); | |
b0edb2c5 | 1409 | if ((c > MAX_CHAR) || (c < 0x200000)) |
df7492f9 KH |
1410 | goto invalid_code; |
1411 | } | |
1412 | else | |
1413 | goto invalid_code; | |
1414 | } | |
1415 | } | |
aa72b389 | 1416 | } |
b73bfc1c | 1417 | } |
df7492f9 KH |
1418 | |
1419 | *charbuf++ = c; | |
1420 | continue; | |
1421 | ||
1422 | invalid_code: | |
1423 | src = src_base; | |
1424 | consumed_chars = consumed_chars_base; | |
1425 | ONE_MORE_BYTE (c); | |
1426 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
1427 | coding->errors++; | |
aa72b389 KH |
1428 | } |
1429 | ||
df7492f9 KH |
1430 | no_more_source: |
1431 | coding->consumed_char += consumed_chars_base; | |
1432 | coding->consumed = src_base - coding->source; | |
1433 | coding->charbuf_used = charbuf - coding->charbuf; | |
1434 | } | |
1435 | ||
1436 | ||
f10fe38f | 1437 | static bool |
971de7fb | 1438 | encode_coding_utf_8 (struct coding_system *coding) |
df7492f9 | 1439 | { |
f10fe38f | 1440 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
1441 | int *charbuf = coding->charbuf; |
1442 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1443 | unsigned char *dst = coding->destination + coding->produced; | |
1444 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c | 1445 | ptrdiff_t produced_chars = 0; |
df7492f9 KH |
1446 | int c; |
1447 | ||
a470d443 KH |
1448 | if (CODING_UTF_8_BOM (coding) == utf_with_bom) |
1449 | { | |
1450 | ASSURE_DESTINATION (3); | |
1451 | EMIT_THREE_BYTES (UTF_8_BOM_1, UTF_8_BOM_2, UTF_8_BOM_3); | |
1452 | CODING_UTF_8_BOM (coding) = utf_without_bom; | |
1453 | } | |
1454 | ||
df7492f9 | 1455 | if (multibytep) |
aa72b389 | 1456 | { |
df7492f9 KH |
1457 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
1458 | ||
1459 | while (charbuf < charbuf_end) | |
b73bfc1c | 1460 | { |
df7492f9 | 1461 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p, *pend = str; |
8f924df7 | 1462 | |
df7492f9 KH |
1463 | ASSURE_DESTINATION (safe_room); |
1464 | c = *charbuf++; | |
28f67a95 KH |
1465 | if (CHAR_BYTE8_P (c)) |
1466 | { | |
1467 | c = CHAR_TO_BYTE8 (c); | |
1468 | EMIT_ONE_BYTE (c); | |
1469 | } | |
1470 | else | |
1471 | { | |
db274c7a | 1472 | CHAR_STRING_ADVANCE_NO_UNIFY (c, pend); |
28f67a95 KH |
1473 | for (p = str; p < pend; p++) |
1474 | EMIT_ONE_BYTE (*p); | |
1475 | } | |
b73bfc1c | 1476 | } |
aa72b389 | 1477 | } |
df7492f9 KH |
1478 | else |
1479 | { | |
1480 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
1481 | ||
1482 | while (charbuf < charbuf_end) | |
b73bfc1c | 1483 | { |
df7492f9 KH |
1484 | ASSURE_DESTINATION (safe_room); |
1485 | c = *charbuf++; | |
f03caae0 KH |
1486 | if (CHAR_BYTE8_P (c)) |
1487 | *dst++ = CHAR_TO_BYTE8 (c); | |
1488 | else | |
db274c7a | 1489 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
df7492f9 | 1490 | produced_chars++; |
4ed46869 KH |
1491 | } |
1492 | } | |
065e3595 | 1493 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1494 | coding->produced_char += produced_chars; |
1495 | coding->produced = dst - coding->destination; | |
1496 | return 0; | |
4ed46869 KH |
1497 | } |
1498 | ||
b73bfc1c | 1499 | |
df7492f9 | 1500 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f | 1501 | Return true if a text is encoded in one of UTF-16 based coding systems. */ |
aa72b389 | 1502 | |
df7492f9 KH |
1503 | #define UTF_16_HIGH_SURROGATE_P(val) \ |
1504 | (((val) & 0xFC00) == 0xD800) | |
1505 | ||
1506 | #define UTF_16_LOW_SURROGATE_P(val) \ | |
1507 | (((val) & 0xFC00) == 0xDC00) | |
93dec019 | 1508 | |
aa72b389 | 1509 | |
f10fe38f | 1510 | static bool |
cf84bb53 JB |
1511 | detect_coding_utf_16 (struct coding_system *coding, |
1512 | struct coding_detection_info *detect_info) | |
aa72b389 | 1513 | { |
ef1b0ba7 | 1514 | const unsigned char *src = coding->source; |
8f924df7 | 1515 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 1516 | bool multibytep = coding->src_multibyte; |
df7492f9 | 1517 | int c1, c2; |
aa72b389 | 1518 | |
ff0dacd7 | 1519 | detect_info->checked |= CATEGORY_MASK_UTF_16; |
ff0dacd7 | 1520 | if (coding->mode & CODING_MODE_LAST_BLOCK |
24a73b0a | 1521 | && (coding->src_chars & 1)) |
ff0dacd7 KH |
1522 | { |
1523 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1524 | return 0; | |
1525 | } | |
24a73b0a | 1526 | |
f56a4450 | 1527 | TWO_MORE_BYTES (c1, c2); |
df7492f9 | 1528 | if ((c1 == 0xFF) && (c2 == 0xFE)) |
aa72b389 | 1529 | { |
b49a1807 KH |
1530 | detect_info->found |= (CATEGORY_MASK_UTF_16_LE |
1531 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1532 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_BE |
1533 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1534 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
aa72b389 | 1535 | } |
df7492f9 | 1536 | else if ((c1 == 0xFE) && (c2 == 0xFF)) |
ff0dacd7 | 1537 | { |
b49a1807 KH |
1538 | detect_info->found |= (CATEGORY_MASK_UTF_16_BE |
1539 | | CATEGORY_MASK_UTF_16_AUTO); | |
24a73b0a KH |
1540 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_LE |
1541 | | CATEGORY_MASK_UTF_16_BE_NOSIG | |
1542 | | CATEGORY_MASK_UTF_16_LE_NOSIG); | |
1543 | } | |
220eeac9 | 1544 | else if (c2 < 0) |
f56a4450 KH |
1545 | { |
1546 | detect_info->rejected |= CATEGORY_MASK_UTF_16; | |
1547 | return 0; | |
1548 | } | |
2f3cbb32 | 1549 | else |
24a73b0a | 1550 | { |
2f3cbb32 KH |
1551 | /* We check the dispersion of Eth and Oth bytes where E is even and |
1552 | O is odd. If both are high, we assume binary data.*/ | |
1553 | unsigned char e[256], o[256]; | |
1554 | unsigned e_num = 1, o_num = 1; | |
1555 | ||
1556 | memset (e, 0, 256); | |
1557 | memset (o, 0, 256); | |
1558 | e[c1] = 1; | |
1559 | o[c2] = 1; | |
1560 | ||
cc13543e KH |
1561 | detect_info->rejected |= (CATEGORY_MASK_UTF_16_AUTO |
1562 | |CATEGORY_MASK_UTF_16_BE | |
1563 | | CATEGORY_MASK_UTF_16_LE); | |
2f3cbb32 | 1564 | |
7f1faf1c KH |
1565 | while ((detect_info->rejected & CATEGORY_MASK_UTF_16) |
1566 | != CATEGORY_MASK_UTF_16) | |
2f3cbb32 | 1567 | { |
f56a4450 | 1568 | TWO_MORE_BYTES (c1, c2); |
220eeac9 | 1569 | if (c2 < 0) |
f56a4450 | 1570 | break; |
2f3cbb32 KH |
1571 | if (! e[c1]) |
1572 | { | |
1573 | e[c1] = 1; | |
1574 | e_num++; | |
cc13543e KH |
1575 | if (e_num >= 128) |
1576 | detect_info->rejected |= CATEGORY_MASK_UTF_16_BE_NOSIG; | |
2f3cbb32 KH |
1577 | } |
1578 | if (! o[c2]) | |
1579 | { | |
977b85f4 | 1580 | o[c2] = 1; |
2f3cbb32 | 1581 | o_num++; |
cc13543e KH |
1582 | if (o_num >= 128) |
1583 | detect_info->rejected |= CATEGORY_MASK_UTF_16_LE_NOSIG; | |
2f3cbb32 KH |
1584 | } |
1585 | } | |
2f3cbb32 | 1586 | return 0; |
ff0dacd7 | 1587 | } |
2f3cbb32 | 1588 | |
df7492f9 | 1589 | no_more_source: |
ff0dacd7 | 1590 | return 1; |
df7492f9 | 1591 | } |
aa72b389 | 1592 | |
df7492f9 | 1593 | static void |
971de7fb | 1594 | decode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1595 | { |
8f924df7 KH |
1596 | const unsigned char *src = coding->source + coding->consumed; |
1597 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
1598 | const unsigned char *src_base; | |
69a80ea3 | 1599 | int *charbuf = coding->charbuf + coding->charbuf_used; |
df80c7f0 KH |
1600 | /* We may produces at most 3 chars in one loop. */ |
1601 | int *charbuf_end = coding->charbuf + coding->charbuf_size - 2; | |
d311d28c | 1602 | ptrdiff_t consumed_chars = 0, consumed_chars_base = 0; |
f10fe38f | 1603 | bool multibytep = coding->src_multibyte; |
a470d443 | 1604 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
df7492f9 KH |
1605 | enum utf_16_endian_type endian = CODING_UTF_16_ENDIAN (coding); |
1606 | int surrogate = CODING_UTF_16_SURROGATE (coding); | |
f10fe38f PE |
1607 | bool eol_dos |
1608 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 1609 | int byte_after_cr1 = -1, byte_after_cr2 = -1; |
df7492f9 | 1610 | |
a470d443 | 1611 | if (bom == utf_with_bom) |
aa72b389 | 1612 | { |
df7492f9 | 1613 | int c, c1, c2; |
4af310db | 1614 | |
aa72b389 | 1615 | src_base = src; |
df7492f9 KH |
1616 | ONE_MORE_BYTE (c1); |
1617 | ONE_MORE_BYTE (c2); | |
e19c3639 | 1618 | c = (c1 << 8) | c2; |
aa72b389 | 1619 | |
b49a1807 KH |
1620 | if (endian == utf_16_big_endian |
1621 | ? c != 0xFEFF : c != 0xFFFE) | |
aa72b389 | 1622 | { |
b49a1807 KH |
1623 | /* The first two bytes are not BOM. Treat them as bytes |
1624 | for a normal character. */ | |
1625 | src = src_base; | |
1626 | coding->errors++; | |
aa72b389 | 1627 | } |
a470d443 | 1628 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
b49a1807 | 1629 | } |
a470d443 | 1630 | else if (bom == utf_detect_bom) |
b49a1807 KH |
1631 | { |
1632 | /* We have already tried to detect BOM and failed in | |
1633 | detect_coding. */ | |
a470d443 | 1634 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 | 1635 | } |
aa72b389 | 1636 | |
df7492f9 KH |
1637 | while (1) |
1638 | { | |
1639 | int c, c1, c2; | |
1640 | ||
1641 | src_base = src; | |
1642 | consumed_chars_base = consumed_chars; | |
1643 | ||
df80c7f0 | 1644 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
1645 | { |
1646 | if (byte_after_cr1 >= 0) | |
1647 | src_base -= 2; | |
1648 | break; | |
1649 | } | |
df7492f9 | 1650 | |
119852e7 KH |
1651 | if (byte_after_cr1 >= 0) |
1652 | c1 = byte_after_cr1, byte_after_cr1 = -1; | |
1653 | else | |
1654 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
1655 | if (c1 < 0) |
1656 | { | |
1657 | *charbuf++ = -c1; | |
1658 | continue; | |
1659 | } | |
119852e7 KH |
1660 | if (byte_after_cr2 >= 0) |
1661 | c2 = byte_after_cr2, byte_after_cr2 = -1; | |
1662 | else | |
1663 | ONE_MORE_BYTE (c2); | |
065e3595 KH |
1664 | if (c2 < 0) |
1665 | { | |
1666 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
1667 | *charbuf++ = -c2; | |
1668 | continue; | |
1669 | } | |
df7492f9 | 1670 | c = (endian == utf_16_big_endian |
e19c3639 | 1671 | ? ((c1 << 8) | c2) : ((c2 << 8) | c1)); |
119852e7 | 1672 | |
df7492f9 | 1673 | if (surrogate) |
fd3ae0b9 | 1674 | { |
df7492f9 | 1675 | if (! UTF_16_LOW_SURROGATE_P (c)) |
fd3ae0b9 | 1676 | { |
df7492f9 KH |
1677 | if (endian == utf_16_big_endian) |
1678 | c1 = surrogate >> 8, c2 = surrogate & 0xFF; | |
1679 | else | |
1680 | c1 = surrogate & 0xFF, c2 = surrogate >> 8; | |
1681 | *charbuf++ = c1; | |
1682 | *charbuf++ = c2; | |
1683 | coding->errors++; | |
1684 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1685 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
fd3ae0b9 | 1686 | else |
df7492f9 | 1687 | *charbuf++ = c; |
fd3ae0b9 KH |
1688 | } |
1689 | else | |
df7492f9 KH |
1690 | { |
1691 | c = ((surrogate - 0xD800) << 10) | (c - 0xDC00); | |
1692 | CODING_UTF_16_SURROGATE (coding) = surrogate = 0; | |
29f7ffd0 | 1693 | *charbuf++ = 0x10000 + c; |
df7492f9 | 1694 | } |
fd3ae0b9 | 1695 | } |
aa72b389 | 1696 | else |
df7492f9 KH |
1697 | { |
1698 | if (UTF_16_HIGH_SURROGATE_P (c)) | |
1699 | CODING_UTF_16_SURROGATE (coding) = surrogate = c; | |
1700 | else | |
119852e7 | 1701 | { |
2735d060 | 1702 | if (eol_dos && c == '\r') |
119852e7 KH |
1703 | { |
1704 | ONE_MORE_BYTE (byte_after_cr1); | |
1705 | ONE_MORE_BYTE (byte_after_cr2); | |
1706 | } | |
1707 | *charbuf++ = c; | |
1708 | } | |
8f924df7 | 1709 | } |
aa72b389 | 1710 | } |
df7492f9 KH |
1711 | |
1712 | no_more_source: | |
1713 | coding->consumed_char += consumed_chars_base; | |
1714 | coding->consumed = src_base - coding->source; | |
1715 | coding->charbuf_used = charbuf - coding->charbuf; | |
aa72b389 | 1716 | } |
b73bfc1c | 1717 | |
f10fe38f | 1718 | static bool |
971de7fb | 1719 | encode_coding_utf_16 (struct coding_system *coding) |
df7492f9 | 1720 | { |
f10fe38f | 1721 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
1722 | int *charbuf = coding->charbuf; |
1723 | int *charbuf_end = charbuf + coding->charbuf_used; | |
1724 | unsigned char *dst = coding->destination + coding->produced; | |
1725 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
1726 | int safe_room = 8; | |
a470d443 | 1727 | enum utf_bom_type bom = CODING_UTF_16_BOM (coding); |
f10fe38f | 1728 | bool big_endian = CODING_UTF_16_ENDIAN (coding) == utf_16_big_endian; |
d311d28c | 1729 | ptrdiff_t produced_chars = 0; |
df7492f9 | 1730 | int c; |
4ed46869 | 1731 | |
a470d443 | 1732 | if (bom != utf_without_bom) |
df7492f9 KH |
1733 | { |
1734 | ASSURE_DESTINATION (safe_room); | |
1735 | if (big_endian) | |
df7492f9 | 1736 | EMIT_TWO_BYTES (0xFE, 0xFF); |
880cf180 KH |
1737 | else |
1738 | EMIT_TWO_BYTES (0xFF, 0xFE); | |
a470d443 | 1739 | CODING_UTF_16_BOM (coding) = utf_without_bom; |
df7492f9 KH |
1740 | } |
1741 | ||
1742 | while (charbuf < charbuf_end) | |
1743 | { | |
1744 | ASSURE_DESTINATION (safe_room); | |
1745 | c = *charbuf++; | |
60afa08d | 1746 | if (c > MAX_UNICODE_CHAR) |
e19c3639 | 1747 | c = coding->default_char; |
df7492f9 KH |
1748 | |
1749 | if (c < 0x10000) | |
1750 | { | |
1751 | if (big_endian) | |
1752 | EMIT_TWO_BYTES (c >> 8, c & 0xFF); | |
1753 | else | |
1754 | EMIT_TWO_BYTES (c & 0xFF, c >> 8); | |
1755 | } | |
1756 | else | |
1757 | { | |
1758 | int c1, c2; | |
1759 | ||
1760 | c -= 0x10000; | |
1761 | c1 = (c >> 10) + 0xD800; | |
1762 | c2 = (c & 0x3FF) + 0xDC00; | |
1763 | if (big_endian) | |
1764 | EMIT_FOUR_BYTES (c1 >> 8, c1 & 0xFF, c2 >> 8, c2 & 0xFF); | |
1765 | else | |
1766 | EMIT_FOUR_BYTES (c1 & 0xFF, c1 >> 8, c2 & 0xFF, c2 >> 8); | |
1767 | } | |
1768 | } | |
065e3595 | 1769 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
1770 | coding->produced = dst - coding->destination; |
1771 | coding->produced_char += produced_chars; | |
1772 | return 0; | |
1773 | } | |
1774 | ||
1775 | \f | |
1776 | /*** 6. Old Emacs' internal format (emacs-mule) ***/ | |
1777 | ||
1778 | /* Emacs' internal format for representation of multiple character | |
1779 | sets is a kind of multi-byte encoding, i.e. characters are | |
1780 | represented by variable-length sequences of one-byte codes. | |
1781 | ||
1782 | ASCII characters and control characters (e.g. `tab', `newline') are | |
1783 | represented by one-byte sequences which are their ASCII codes, in | |
1784 | the range 0x00 through 0x7F. | |
1785 | ||
1786 | 8-bit characters of the range 0x80..0x9F are represented by | |
1787 | two-byte sequences of LEADING_CODE_8_BIT_CONTROL and (their 8-bit | |
1788 | code + 0x20). | |
1789 | ||
1790 | 8-bit characters of the range 0xA0..0xFF are represented by | |
1791 | one-byte sequences which are their 8-bit code. | |
1792 | ||
1793 | The other characters are represented by a sequence of `base | |
1794 | leading-code', optional `extended leading-code', and one or two | |
1795 | `position-code's. The length of the sequence is determined by the | |
1796 | base leading-code. Leading-code takes the range 0x81 through 0x9D, | |
1797 | whereas extended leading-code and position-code take the range 0xA0 | |
1798 | through 0xFF. See `charset.h' for more details about leading-code | |
1799 | and position-code. | |
1800 | ||
1801 | --- CODE RANGE of Emacs' internal format --- | |
1802 | character set range | |
1803 | ------------- ----- | |
1804 | ascii 0x00..0x7F | |
1805 | eight-bit-control LEADING_CODE_8_BIT_CONTROL + 0xA0..0xBF | |
1806 | eight-bit-graphic 0xA0..0xBF | |
1807 | ELSE 0x81..0x9D + [0xA0..0xFF]+ | |
1808 | --------------------------------------------- | |
1809 | ||
1810 | As this is the internal character representation, the format is | |
1811 | usually not used externally (i.e. in a file or in a data sent to a | |
1812 | process). But, it is possible to have a text externally in this | |
1813 | format (i.e. by encoding by the coding system `emacs-mule'). | |
1814 | ||
1815 | In that case, a sequence of one-byte codes has a slightly different | |
1816 | form. | |
1817 | ||
1818 | At first, all characters in eight-bit-control are represented by | |
1819 | one-byte sequences which are their 8-bit code. | |
1820 | ||
1821 | Next, character composition data are represented by the byte | |
1822 | sequence of the form: 0x80 METHOD BYTES CHARS COMPONENT ..., | |
1823 | where, | |
e951386e | 1824 | METHOD is 0xF2 plus one of composition method (enum |
df7492f9 KH |
1825 | composition_method), |
1826 | ||
1827 | BYTES is 0xA0 plus a byte length of this composition data, | |
1828 | ||
e951386e | 1829 | CHARS is 0xA0 plus a number of characters composed by this |
df7492f9 KH |
1830 | data, |
1831 | ||
ad1746f5 | 1832 | COMPONENTs are characters of multibyte form or composition |
df7492f9 KH |
1833 | rules encoded by two-byte of ASCII codes. |
1834 | ||
1835 | In addition, for backward compatibility, the following formats are | |
1836 | also recognized as composition data on decoding. | |
1837 | ||
1838 | 0x80 MSEQ ... | |
1839 | 0x80 0xFF MSEQ RULE MSEQ RULE ... MSEQ | |
1840 | ||
1841 | Here, | |
1842 | MSEQ is a multibyte form but in these special format: | |
1843 | ASCII: 0xA0 ASCII_CODE+0x80, | |
1844 | other: LEADING_CODE+0x20 FOLLOWING-BYTE ..., | |
1845 | RULE is a one byte code of the range 0xA0..0xF0 that | |
1846 | represents a composition rule. | |
1847 | */ | |
1848 | ||
1849 | char emacs_mule_bytes[256]; | |
1850 | ||
e951386e KH |
1851 | |
1852 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 1853 | Return true if a text is encoded in 'emacs-mule'. */ |
e951386e | 1854 | |
f10fe38f | 1855 | static bool |
cf84bb53 JB |
1856 | detect_coding_emacs_mule (struct coding_system *coding, |
1857 | struct coding_detection_info *detect_info) | |
e951386e KH |
1858 | { |
1859 | const unsigned char *src = coding->source, *src_base; | |
1860 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
f10fe38f | 1861 | bool multibytep = coding->src_multibyte; |
d311d28c | 1862 | ptrdiff_t consumed_chars = 0; |
e951386e KH |
1863 | int c; |
1864 | int found = 0; | |
1865 | ||
1866 | detect_info->checked |= CATEGORY_MASK_EMACS_MULE; | |
1867 | /* A coding system of this category is always ASCII compatible. */ | |
1868 | src += coding->head_ascii; | |
1869 | ||
1870 | while (1) | |
1871 | { | |
1872 | src_base = src; | |
1873 | ONE_MORE_BYTE (c); | |
1874 | if (c < 0) | |
1875 | continue; | |
1876 | if (c == 0x80) | |
1877 | { | |
1878 | /* Perhaps the start of composite character. We simply skip | |
1879 | it because analyzing it is too heavy for detecting. But, | |
1880 | at least, we check that the composite character | |
1881 | constitutes of more than 4 bytes. */ | |
2735d060 | 1882 | const unsigned char *src_start; |
e951386e KH |
1883 | |
1884 | repeat: | |
2735d060 | 1885 | src_start = src; |
e951386e KH |
1886 | do |
1887 | { | |
1888 | ONE_MORE_BYTE (c); | |
1889 | } | |
1890 | while (c >= 0xA0); | |
1891 | ||
2735d060 | 1892 | if (src - src_start <= 4) |
e951386e KH |
1893 | break; |
1894 | found = CATEGORY_MASK_EMACS_MULE; | |
1895 | if (c == 0x80) | |
1896 | goto repeat; | |
1897 | } | |
1898 | ||
1899 | if (c < 0x80) | |
1900 | { | |
1901 | if (c < 0x20 | |
1902 | && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)) | |
1903 | break; | |
1904 | } | |
1905 | else | |
1906 | { | |
396475b7 | 1907 | int more_bytes = emacs_mule_bytes[c] - 1; |
e951386e KH |
1908 | |
1909 | while (more_bytes > 0) | |
1910 | { | |
1911 | ONE_MORE_BYTE (c); | |
1912 | if (c < 0xA0) | |
1913 | { | |
1914 | src--; /* Unread the last byte. */ | |
1915 | break; | |
1916 | } | |
1917 | more_bytes--; | |
1918 | } | |
1919 | if (more_bytes != 0) | |
1920 | break; | |
1921 | found = CATEGORY_MASK_EMACS_MULE; | |
1922 | } | |
1923 | } | |
1924 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1925 | return 0; | |
1926 | ||
1927 | no_more_source: | |
1928 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) | |
1929 | { | |
1930 | detect_info->rejected |= CATEGORY_MASK_EMACS_MULE; | |
1931 | return 0; | |
1932 | } | |
1933 | detect_info->found |= found; | |
1934 | return 1; | |
1935 | } | |
1936 | ||
1937 | ||
1938 | /* Parse emacs-mule multibyte sequence at SRC and return the decoded | |
1939 | character. If CMP_STATUS indicates that we must expect MSEQ or | |
1940 | RULE described above, decode it and return the negative value of | |
685ebdc8 | 1941 | the decoded character or rule. If an invalid byte is found, return |
e951386e KH |
1942 | -1. If SRC is too short, return -2. */ |
1943 | ||
e2f1bab9 | 1944 | static int |
cf84bb53 JB |
1945 | emacs_mule_char (struct coding_system *coding, const unsigned char *src, |
1946 | int *nbytes, int *nchars, int *id, | |
1947 | struct composition_status *cmp_status) | |
df7492f9 | 1948 | { |
8f924df7 KH |
1949 | const unsigned char *src_end = coding->source + coding->src_bytes; |
1950 | const unsigned char *src_base = src; | |
f10fe38f | 1951 | bool multibytep = coding->src_multibyte; |
2735d060 | 1952 | int charset_ID; |
df7492f9 KH |
1953 | unsigned code; |
1954 | int c; | |
1955 | int consumed_chars = 0; | |
f10fe38f | 1956 | bool mseq_found = 0; |
df7492f9 KH |
1957 | |
1958 | ONE_MORE_BYTE (c); | |
065e3595 | 1959 | if (c < 0) |
df7492f9 | 1960 | { |
065e3595 | 1961 | c = -c; |
2735d060 | 1962 | charset_ID = emacs_mule_charset[0]; |
065e3595 KH |
1963 | } |
1964 | else | |
1965 | { | |
4d41e8b7 KH |
1966 | if (c >= 0xA0) |
1967 | { | |
e951386e KH |
1968 | if (cmp_status->state != COMPOSING_NO |
1969 | && cmp_status->old_form) | |
4d41e8b7 | 1970 | { |
e951386e KH |
1971 | if (cmp_status->state == COMPOSING_CHAR) |
1972 | { | |
1973 | if (c == 0xA0) | |
1974 | { | |
1975 | ONE_MORE_BYTE (c); | |
1976 | c -= 0x80; | |
1977 | if (c < 0) | |
1978 | goto invalid_code; | |
1979 | } | |
1980 | else | |
1981 | c -= 0x20; | |
1982 | mseq_found = 1; | |
1983 | } | |
1984 | else | |
1985 | { | |
1986 | *nbytes = src - src_base; | |
1987 | *nchars = consumed_chars; | |
1988 | return -c; | |
1989 | } | |
4d41e8b7 KH |
1990 | } |
1991 | else | |
e951386e | 1992 | goto invalid_code; |
4d41e8b7 KH |
1993 | } |
1994 | ||
065e3595 | 1995 | switch (emacs_mule_bytes[c]) |
b73bfc1c | 1996 | { |
065e3595 | 1997 | case 2: |
2735d060 | 1998 | if ((charset_ID = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
1999 | goto invalid_code; |
2000 | ONE_MORE_BYTE (c); | |
9ffd559c | 2001 | if (c < 0xA0) |
065e3595 | 2002 | goto invalid_code; |
df7492f9 | 2003 | code = c & 0x7F; |
065e3595 KH |
2004 | break; |
2005 | ||
2006 | case 3: | |
2007 | if (c == EMACS_MULE_LEADING_CODE_PRIVATE_11 | |
2008 | || c == EMACS_MULE_LEADING_CODE_PRIVATE_12) | |
2009 | { | |
2010 | ONE_MORE_BYTE (c); | |
2735d060 | 2011 | if (c < 0xA0 || (charset_ID = emacs_mule_charset[c]) < 0) |
065e3595 KH |
2012 | goto invalid_code; |
2013 | ONE_MORE_BYTE (c); | |
9ffd559c | 2014 | if (c < 0xA0) |
065e3595 KH |
2015 | goto invalid_code; |
2016 | code = c & 0x7F; | |
2017 | } | |
2018 | else | |
2019 | { | |
2735d060 | 2020 | if ((charset_ID = emacs_mule_charset[c]) < 0) |
065e3595 KH |
2021 | goto invalid_code; |
2022 | ONE_MORE_BYTE (c); | |
9ffd559c | 2023 | if (c < 0xA0) |
065e3595 KH |
2024 | goto invalid_code; |
2025 | code = (c & 0x7F) << 8; | |
2026 | ONE_MORE_BYTE (c); | |
9ffd559c | 2027 | if (c < 0xA0) |
065e3595 KH |
2028 | goto invalid_code; |
2029 | code |= c & 0x7F; | |
2030 | } | |
2031 | break; | |
2032 | ||
2033 | case 4: | |
2034 | ONE_MORE_BYTE (c); | |
2735d060 | 2035 | if (c < 0 || (charset_ID = emacs_mule_charset[c]) < 0) |
df7492f9 KH |
2036 | goto invalid_code; |
2037 | ONE_MORE_BYTE (c); | |
9ffd559c | 2038 | if (c < 0xA0) |
065e3595 | 2039 | goto invalid_code; |
781d7a48 | 2040 | code = (c & 0x7F) << 8; |
df7492f9 | 2041 | ONE_MORE_BYTE (c); |
9ffd559c | 2042 | if (c < 0xA0) |
065e3595 | 2043 | goto invalid_code; |
df7492f9 | 2044 | code |= c & 0x7F; |
065e3595 | 2045 | break; |
df7492f9 | 2046 | |
065e3595 KH |
2047 | case 1: |
2048 | code = c; | |
2735d060 | 2049 | charset_ID = ASCII_BYTE_P (code) ? charset_ascii : charset_eight_bit; |
065e3595 | 2050 | break; |
df7492f9 | 2051 | |
065e3595 | 2052 | default: |
1088b922 | 2053 | emacs_abort (); |
065e3595 | 2054 | } |
b84ae584 | 2055 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
2735d060 | 2056 | CHARSET_FROM_ID (charset_ID), code, c); |
065e3595 KH |
2057 | if (c < 0) |
2058 | goto invalid_code; | |
df7492f9 | 2059 | } |
df7492f9 KH |
2060 | *nbytes = src - src_base; |
2061 | *nchars = consumed_chars; | |
ff0dacd7 | 2062 | if (id) |
2735d060 | 2063 | *id = charset_ID; |
e951386e | 2064 | return (mseq_found ? -c : c); |
df7492f9 KH |
2065 | |
2066 | no_more_source: | |
2067 | return -2; | |
2068 | ||
2069 | invalid_code: | |
2070 | return -1; | |
2071 | } | |
2072 | ||
2073 | ||
e951386e | 2074 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
df7492f9 | 2075 | |
e951386e KH |
2076 | /* Handle these composition sequence ('|': the end of header elements, |
2077 | BYTES and CHARS >= 0xA0): | |
df7492f9 | 2078 | |
e951386e KH |
2079 | (1) relative composition: 0x80 0xF2 BYTES CHARS | CHAR ... |
2080 | (2) altchar composition: 0x80 0xF4 BYTES CHARS | ALT ... ALT CHAR ... | |
2081 | (3) alt&rule composition: 0x80 0xF5 BYTES CHARS | ALT RULE ... ALT CHAR ... | |
df7492f9 | 2082 | |
e951386e | 2083 | and these old form: |
1a4990fb | 2084 | |
e951386e KH |
2085 | (4) relative composition: 0x80 | MSEQ ... MSEQ |
2086 | (5) rulebase composition: 0x80 0xFF | MSEQ MRULE ... MSEQ | |
df7492f9 | 2087 | |
e951386e KH |
2088 | When the starter 0x80 and the following header elements are found, |
2089 | this annotation header is produced. | |
df7492f9 | 2090 | |
e951386e | 2091 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS NBYTES METHOD ] |
df7492f9 | 2092 | |
e951386e KH |
2093 | NCHARS is CHARS - 0xA0 for (1), (2), (3), and 0 for (4), (5). |
2094 | NBYTES is BYTES - 0xA0 for (1), (2), (3), and 0 for (4), (5). | |
df7492f9 | 2095 | |
e951386e KH |
2096 | Then, upon reading the following elements, these codes are produced |
2097 | until the composition end is found: | |
df7492f9 | 2098 | |
e951386e KH |
2099 | (1) CHAR ... CHAR |
2100 | (2) ALT ... ALT CHAR ... CHAR | |
2101 | (3) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT CHAR ... CHAR | |
2102 | (4) CHAR ... CHAR | |
2103 | (5) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
4ed46869 | 2104 | |
e951386e KH |
2105 | When the composition end is found, LENGTH and NCHARS in the |
2106 | annotation header is updated as below: | |
b73bfc1c | 2107 | |
e951386e KH |
2108 | (1) LENGTH: unchanged, NCHARS: unchanged |
2109 | (2) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2110 | (3) LENGTH: length of the whole sequence minus NCHARS, NCHARS: unchanged | |
2111 | (4) LENGTH: unchanged, NCHARS: number of CHARs | |
2112 | (5) LENGTH: unchanged, NCHARS: number of CHARs | |
df7492f9 | 2113 | |
e951386e KH |
2114 | If an error is found while composing, the annotation header is |
2115 | changed to the original composition header (plus filler -1s) as | |
2116 | below: | |
2117 | ||
2118 | (1),(2),(3) [ 0x80 0xF2+METHOD BYTES CHARS -1 ] | |
2119 | (5) [ 0x80 0xFF -1 -1- -1 ] | |
2120 | ||
2121 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
2122 | byte sequence as below: | |
2123 | o the original byte sequence is B: [ B -1 ] | |
2124 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
2125 | ||
2126 | Most of the routines are implemented by macros because many | |
2127 | variables and labels in the caller decode_coding_emacs_mule must be | |
2128 | accessible, and they are usually called just once (thus doesn't | |
2129 | increase the size of compiled object). */ | |
2130 | ||
2131 | /* Decode a composition rule represented by C as a component of | |
2132 | composition sequence of Emacs 20 style. Set RULE to the decoded | |
2133 | rule. */ | |
2134 | ||
2135 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_20(c, rule) \ | |
df7492f9 | 2136 | do { \ |
e951386e KH |
2137 | int gref, nref; \ |
2138 | \ | |
4d41e8b7 | 2139 | c -= 0xA0; \ |
df7492f9 KH |
2140 | if (c < 0 || c >= 81) \ |
2141 | goto invalid_code; \ | |
df7492f9 | 2142 | gref = c / 9, nref = c % 9; \ |
e951386e KH |
2143 | if (gref == 4) gref = 10; \ |
2144 | if (nref == 4) nref = 10; \ | |
2145 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
df7492f9 KH |
2146 | } while (0) |
2147 | ||
2148 | ||
e951386e KH |
2149 | /* Decode a composition rule represented by C and the following byte |
2150 | at SRC as a component of composition sequence of Emacs 21 style. | |
2151 | Set RULE to the decoded rule. */ | |
781d7a48 | 2152 | |
e951386e | 2153 | #define DECODE_EMACS_MULE_COMPOSITION_RULE_21(c, rule) \ |
781d7a48 KH |
2154 | do { \ |
2155 | int gref, nref; \ | |
e951386e KH |
2156 | \ |
2157 | gref = c - 0x20; \ | |
2158 | if (gref < 0 || gref >= 81) \ | |
781d7a48 | 2159 | goto invalid_code; \ |
e951386e KH |
2160 | ONE_MORE_BYTE (c); \ |
2161 | nref = c - 0x20; \ | |
2162 | if (nref < 0 || nref >= 81) \ | |
781d7a48 | 2163 | goto invalid_code; \ |
e951386e | 2164 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ |
781d7a48 KH |
2165 | } while (0) |
2166 | ||
2167 | ||
e951386e KH |
2168 | /* Start of Emacs 21 style format. The first three bytes at SRC are |
2169 | (METHOD - 0xF2), (BYTES - 0xA0), (CHARS - 0xA0), where BYTES is the | |
2170 | byte length of this composition information, CHARS is the number of | |
2171 | characters composed by this composition. */ | |
2172 | ||
2173 | #define DECODE_EMACS_MULE_21_COMPOSITION() \ | |
aa72b389 | 2174 | do { \ |
781d7a48 | 2175 | enum composition_method method = c - 0xF2; \ |
df7492f9 | 2176 | int nbytes, nchars; \ |
e951386e | 2177 | \ |
df7492f9 | 2178 | ONE_MORE_BYTE (c); \ |
065e3595 KH |
2179 | if (c < 0) \ |
2180 | goto invalid_code; \ | |
df7492f9 | 2181 | nbytes = c - 0xA0; \ |
e951386e | 2182 | if (nbytes < 3 || (method == COMPOSITION_RELATIVE && nbytes != 4)) \ |
df7492f9 KH |
2183 | goto invalid_code; \ |
2184 | ONE_MORE_BYTE (c); \ | |
2185 | nchars = c - 0xA0; \ | |
e951386e KH |
2186 | if (nchars <= 0 || nchars >= MAX_COMPOSITION_COMPONENTS) \ |
2187 | goto invalid_code; \ | |
2188 | cmp_status->old_form = 0; \ | |
2189 | cmp_status->method = method; \ | |
2190 | if (method == COMPOSITION_RELATIVE) \ | |
2191 | cmp_status->state = COMPOSING_CHAR; \ | |
2192 | else \ | |
2193 | cmp_status->state = COMPOSING_COMPONENT_CHAR; \ | |
2194 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2195 | cmp_status->nchars = nchars; \ | |
2196 | cmp_status->ncomps = nbytes - 4; \ | |
2197 | ADD_COMPOSITION_DATA (charbuf, nchars, nbytes, method); \ | |
aa72b389 | 2198 | } while (0) |
93dec019 | 2199 | |
aa72b389 | 2200 | |
e951386e KH |
2201 | /* Start of Emacs 20 style format for relative composition. */ |
2202 | ||
2203 | #define DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION() \ | |
2204 | do { \ | |
2205 | cmp_status->old_form = 1; \ | |
2206 | cmp_status->method = COMPOSITION_RELATIVE; \ | |
2207 | cmp_status->state = COMPOSING_CHAR; \ | |
2208 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2209 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2210 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
2211 | } while (0) | |
2212 | ||
2213 | ||
2214 | /* Start of Emacs 20 style format for rule-base composition. */ | |
2215 | ||
2216 | #define DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION() \ | |
2217 | do { \ | |
2218 | cmp_status->old_form = 1; \ | |
2219 | cmp_status->method = COMPOSITION_WITH_RULE; \ | |
2220 | cmp_status->state = COMPOSING_CHAR; \ | |
2221 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
2222 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
2223 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
df7492f9 KH |
2224 | } while (0) |
2225 | ||
2226 | ||
e951386e KH |
2227 | #define DECODE_EMACS_MULE_COMPOSITION_START() \ |
2228 | do { \ | |
2229 | const unsigned char *current_src = src; \ | |
2230 | \ | |
2231 | ONE_MORE_BYTE (c); \ | |
2232 | if (c < 0) \ | |
2233 | goto invalid_code; \ | |
2234 | if (c - 0xF2 >= COMPOSITION_RELATIVE \ | |
2235 | && c - 0xF2 <= COMPOSITION_WITH_RULE_ALTCHARS) \ | |
2236 | DECODE_EMACS_MULE_21_COMPOSITION (); \ | |
2237 | else if (c < 0xA0) \ | |
2238 | goto invalid_code; \ | |
2239 | else if (c < 0xC0) \ | |
2240 | { \ | |
2241 | DECODE_EMACS_MULE_20_RELATIVE_COMPOSITION (); \ | |
2242 | /* Re-read C as a composition component. */ \ | |
2243 | src = current_src; \ | |
2244 | } \ | |
2245 | else if (c == 0xFF) \ | |
2246 | DECODE_EMACS_MULE_20_RULEBASE_COMPOSITION (); \ | |
2247 | else \ | |
2248 | goto invalid_code; \ | |
2249 | } while (0) | |
2250 | ||
2251 | #define EMACS_MULE_COMPOSITION_END() \ | |
df7492f9 | 2252 | do { \ |
e951386e | 2253 | int idx = - cmp_status->length; \ |
4d41e8b7 | 2254 | \ |
e951386e KH |
2255 | if (cmp_status->old_form) \ |
2256 | charbuf[idx + 2] = cmp_status->nchars; \ | |
2257 | else if (cmp_status->method > COMPOSITION_RELATIVE) \ | |
2258 | charbuf[idx] = charbuf[idx + 2] - cmp_status->length; \ | |
2259 | cmp_status->state = COMPOSING_NO; \ | |
2260 | } while (0) | |
2261 | ||
2262 | ||
2263 | static int | |
cf84bb53 JB |
2264 | emacs_mule_finish_composition (int *charbuf, |
2265 | struct composition_status *cmp_status) | |
e951386e KH |
2266 | { |
2267 | int idx = - cmp_status->length; | |
2268 | int new_chars; | |
2269 | ||
2270 | if (cmp_status->old_form && cmp_status->nchars > 0) | |
2271 | { | |
2272 | charbuf[idx + 2] = cmp_status->nchars; | |
2273 | new_chars = 0; | |
2274 | if (cmp_status->method == COMPOSITION_WITH_RULE | |
2275 | && cmp_status->state == COMPOSING_CHAR) | |
2276 | { | |
2277 | /* The last rule was invalid. */ | |
2278 | int rule = charbuf[-1] + 0xA0; | |
2279 | ||
2280 | charbuf[-2] = BYTE8_TO_CHAR (rule); | |
2281 | charbuf[-1] = -1; | |
2282 | new_chars = 1; | |
2283 | } | |
2284 | } | |
2285 | else | |
2286 | { | |
2287 | charbuf[idx++] = BYTE8_TO_CHAR (0x80); | |
2288 | ||
2289 | if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2290 | { | |
2291 | charbuf[idx++] = BYTE8_TO_CHAR (0xFF); | |
2292 | charbuf[idx++] = -3; | |
2293 | charbuf[idx++] = 0; | |
2294 | new_chars = 1; | |
2295 | } | |
2296 | else | |
2297 | { | |
2298 | int nchars = charbuf[idx + 1] + 0xA0; | |
2299 | int nbytes = charbuf[idx + 2] + 0xA0; | |
2300 | ||
2301 | charbuf[idx++] = BYTE8_TO_CHAR (0xF2 + cmp_status->method); | |
2302 | charbuf[idx++] = BYTE8_TO_CHAR (nbytes); | |
2303 | charbuf[idx++] = BYTE8_TO_CHAR (nchars); | |
2304 | charbuf[idx++] = -1; | |
2305 | new_chars = 4; | |
2306 | } | |
2307 | } | |
2308 | cmp_status->state = COMPOSING_NO; | |
2309 | return new_chars; | |
2310 | } | |
2311 | ||
2312 | #define EMACS_MULE_MAYBE_FINISH_COMPOSITION() \ | |
2313 | do { \ | |
2314 | if (cmp_status->state != COMPOSING_NO) \ | |
2315 | char_offset += emacs_mule_finish_composition (charbuf, cmp_status); \ | |
df7492f9 KH |
2316 | } while (0) |
2317 | ||
aa72b389 KH |
2318 | |
2319 | static void | |
971de7fb | 2320 | decode_coding_emacs_mule (struct coding_system *coding) |
aa72b389 | 2321 | { |
8f924df7 KH |
2322 | const unsigned char *src = coding->source + coding->consumed; |
2323 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
2324 | const unsigned char *src_base; | |
69a80ea3 | 2325 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
2326 | /* We may produce two annotations (charset and composition) in one |
2327 | loop and one more charset annotation at the end. */ | |
69a80ea3 | 2328 | int *charbuf_end |
15cbd324 EZ |
2329 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3) |
2330 | /* We can produce up to 2 characters in a loop. */ | |
2331 | - 1; | |
d311d28c | 2332 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 2333 | bool multibytep = coding->src_multibyte; |
d311d28c PE |
2334 | ptrdiff_t char_offset = coding->produced_char; |
2335 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 2336 | int last_id = charset_ascii; |
f10fe38f PE |
2337 | bool eol_dos |
2338 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 2339 | int byte_after_cr = -1; |
e951386e | 2340 | struct composition_status *cmp_status = &coding->spec.emacs_mule.cmp_status; |
aa72b389 | 2341 | |
e951386e KH |
2342 | if (cmp_status->state != COMPOSING_NO) |
2343 | { | |
2344 | int i; | |
2345 | ||
15cbd324 | 2346 | if (charbuf_end - charbuf < cmp_status->length) |
1088b922 | 2347 | emacs_abort (); |
e951386e KH |
2348 | for (i = 0; i < cmp_status->length; i++) |
2349 | *charbuf++ = cmp_status->carryover[i]; | |
2350 | coding->annotated = 1; | |
2351 | } | |
2352 | ||
aa72b389 KH |
2353 | while (1) |
2354 | { | |
ee05f961 | 2355 | int c, id IF_LINT (= 0); |
df7492f9 | 2356 | |
aa72b389 | 2357 | src_base = src; |
df7492f9 KH |
2358 | consumed_chars_base = consumed_chars; |
2359 | ||
2360 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
2361 | { |
2362 | if (byte_after_cr >= 0) | |
2363 | src_base--; | |
2364 | break; | |
2365 | } | |
aa72b389 | 2366 | |
119852e7 KH |
2367 | if (byte_after_cr >= 0) |
2368 | c = byte_after_cr, byte_after_cr = -1; | |
2369 | else | |
2370 | ONE_MORE_BYTE (c); | |
e951386e KH |
2371 | |
2372 | if (c < 0 || c == 0x80) | |
065e3595 | 2373 | { |
e951386e KH |
2374 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
2375 | if (c < 0) | |
2376 | { | |
2377 | *charbuf++ = -c; | |
2378 | char_offset++; | |
2379 | } | |
2380 | else | |
2381 | DECODE_EMACS_MULE_COMPOSITION_START (); | |
2382 | continue; | |
065e3595 | 2383 | } |
e951386e KH |
2384 | |
2385 | if (c < 0x80) | |
aa72b389 | 2386 | { |
2735d060 | 2387 | if (eol_dos && c == '\r') |
119852e7 | 2388 | ONE_MORE_BYTE (byte_after_cr); |
e951386e KH |
2389 | id = charset_ascii; |
2390 | if (cmp_status->state != COMPOSING_NO) | |
2391 | { | |
2392 | if (cmp_status->old_form) | |
2393 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2394 | else if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2395 | cmp_status->ncomps--; | |
2396 | } | |
2397 | } | |
2398 | else | |
2399 | { | |
ee05f961 | 2400 | int nchars IF_LINT (= 0), nbytes IF_LINT (= 0); |
75f80e63 EZ |
2401 | /* emacs_mule_char can load a charset map from a file, which |
2402 | allocates a large structure and might cause buffer text | |
2403 | to be relocated as result. Thus, we need to remember the | |
ad1746f5 | 2404 | original pointer to buffer text, and fix up all related |
75f80e63 EZ |
2405 | pointers after the call. */ |
2406 | const unsigned char *orig = coding->source; | |
d311d28c | 2407 | ptrdiff_t offset; |
e951386e KH |
2408 | |
2409 | c = emacs_mule_char (coding, src_base, &nbytes, &nchars, &id, | |
2410 | cmp_status); | |
75f80e63 EZ |
2411 | offset = coding->source - orig; |
2412 | if (offset) | |
2413 | { | |
2414 | src += offset; | |
2415 | src_base += offset; | |
2416 | src_end += offset; | |
2417 | } | |
e951386e KH |
2418 | if (c < 0) |
2419 | { | |
2420 | if (c == -1) | |
2421 | goto invalid_code; | |
2422 | if (c == -2) | |
2423 | break; | |
2424 | } | |
2425 | src = src_base + nbytes; | |
2426 | consumed_chars = consumed_chars_base + nchars; | |
2427 | if (cmp_status->state >= COMPOSING_COMPONENT_CHAR) | |
2428 | cmp_status->ncomps -= nchars; | |
2429 | } | |
2430 | ||
ad1746f5 | 2431 | /* Now if C >= 0, we found a normally encoded character, if C < |
e951386e KH |
2432 | 0, we found an old-style composition component character or |
2433 | rule. */ | |
2434 | ||
2435 | if (cmp_status->state == COMPOSING_NO) | |
2436 | { | |
2437 | if (last_id != id) | |
2438 | { | |
2439 | if (last_id != charset_ascii) | |
2440 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, | |
2441 | last_id); | |
2442 | last_id = id; | |
2443 | last_offset = char_offset; | |
2444 | } | |
df7492f9 KH |
2445 | *charbuf++ = c; |
2446 | char_offset++; | |
aa72b389 | 2447 | } |
e951386e | 2448 | else if (cmp_status->state == COMPOSING_CHAR) |
df7492f9 | 2449 | { |
e951386e KH |
2450 | if (cmp_status->old_form) |
2451 | { | |
2452 | if (c >= 0) | |
2453 | { | |
2454 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2455 | *charbuf++ = c; | |
2456 | char_offset++; | |
2457 | } | |
2458 | else | |
2459 | { | |
2460 | *charbuf++ = -c; | |
2461 | cmp_status->nchars++; | |
2462 | cmp_status->length++; | |
2463 | if (cmp_status->nchars == MAX_COMPOSITION_COMPONENTS) | |
2464 | EMACS_MULE_COMPOSITION_END (); | |
2465 | else if (cmp_status->method == COMPOSITION_WITH_RULE) | |
2466 | cmp_status->state = COMPOSING_RULE; | |
2467 | } | |
2468 | } | |
df7492f9 | 2469 | else |
e951386e KH |
2470 | { |
2471 | *charbuf++ = c; | |
2472 | cmp_status->length++; | |
2473 | cmp_status->nchars--; | |
2474 | if (cmp_status->nchars == 0) | |
2475 | EMACS_MULE_COMPOSITION_END (); | |
2476 | } | |
df7492f9 | 2477 | } |
e951386e | 2478 | else if (cmp_status->state == COMPOSING_RULE) |
df7492f9 | 2479 | { |
e951386e | 2480 | int rule; |
ff0dacd7 | 2481 | |
e951386e | 2482 | if (c >= 0) |
df7492f9 | 2483 | { |
e951386e KH |
2484 | EMACS_MULE_COMPOSITION_END (); |
2485 | *charbuf++ = c; | |
2486 | char_offset++; | |
df7492f9 | 2487 | } |
e951386e | 2488 | else |
ff0dacd7 | 2489 | { |
e951386e KH |
2490 | c = -c; |
2491 | DECODE_EMACS_MULE_COMPOSITION_RULE_20 (c, rule); | |
2492 | if (rule < 0) | |
2493 | goto invalid_code; | |
2494 | *charbuf++ = -2; | |
2495 | *charbuf++ = rule; | |
2496 | cmp_status->length += 2; | |
2497 | cmp_status->state = COMPOSING_CHAR; | |
ff0dacd7 | 2498 | } |
e951386e KH |
2499 | } |
2500 | else if (cmp_status->state == COMPOSING_COMPONENT_CHAR) | |
2501 | { | |
df7492f9 | 2502 | *charbuf++ = c; |
e951386e KH |
2503 | cmp_status->length++; |
2504 | if (cmp_status->ncomps == 0) | |
2505 | cmp_status->state = COMPOSING_CHAR; | |
2506 | else if (cmp_status->ncomps > 0) | |
2507 | { | |
2508 | if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) | |
2509 | cmp_status->state = COMPOSING_COMPONENT_RULE; | |
2510 | } | |
2511 | else | |
2512 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
df7492f9 | 2513 | } |
e951386e KH |
2514 | else /* COMPOSING_COMPONENT_RULE */ |
2515 | { | |
2516 | int rule; | |
2517 | ||
2518 | DECODE_EMACS_MULE_COMPOSITION_RULE_21 (c, rule); | |
2519 | if (rule < 0) | |
2520 | goto invalid_code; | |
2521 | *charbuf++ = -2; | |
2522 | *charbuf++ = rule; | |
2523 | cmp_status->length += 2; | |
2524 | cmp_status->ncomps--; | |
2525 | if (cmp_status->ncomps > 0) | |
2526 | cmp_status->state = COMPOSING_COMPONENT_CHAR; | |
2527 | else | |
2528 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2529 | } | |
2530 | continue; | |
2531 | ||
df7492f9 | 2532 | invalid_code: |
e951386e | 2533 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); |
df7492f9 KH |
2534 | src = src_base; |
2535 | consumed_chars = consumed_chars_base; | |
2536 | ONE_MORE_BYTE (c); | |
2537 | *charbuf++ = ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); | |
ff0dacd7 | 2538 | char_offset++; |
df7492f9 KH |
2539 | coding->errors++; |
2540 | } | |
2541 | ||
2542 | no_more_source: | |
e951386e KH |
2543 | if (cmp_status->state != COMPOSING_NO) |
2544 | { | |
2545 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
2546 | EMACS_MULE_MAYBE_FINISH_COMPOSITION (); | |
2547 | else | |
2548 | { | |
2549 | int i; | |
2550 | ||
2551 | charbuf -= cmp_status->length; | |
2552 | for (i = 0; i < cmp_status->length; i++) | |
2553 | cmp_status->carryover[i] = charbuf[i]; | |
2554 | } | |
2555 | } | |
ff0dacd7 | 2556 | if (last_id != charset_ascii) |
69a80ea3 | 2557 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
2558 | coding->consumed_char += consumed_chars_base; |
2559 | coding->consumed = src_base - coding->source; | |
2560 | coding->charbuf_used = charbuf - coding->charbuf; | |
2561 | } | |
2562 | ||
2563 | ||
2564 | #define EMACS_MULE_LEADING_CODES(id, codes) \ | |
2565 | do { \ | |
2566 | if (id < 0xA0) \ | |
2567 | codes[0] = id, codes[1] = 0; \ | |
2568 | else if (id < 0xE0) \ | |
2569 | codes[0] = 0x9A, codes[1] = id; \ | |
2570 | else if (id < 0xF0) \ | |
2571 | codes[0] = 0x9B, codes[1] = id; \ | |
2572 | else if (id < 0xF5) \ | |
2573 | codes[0] = 0x9C, codes[1] = id; \ | |
2574 | else \ | |
2575 | codes[0] = 0x9D, codes[1] = id; \ | |
2576 | } while (0); | |
2577 | ||
aa72b389 | 2578 | |
f10fe38f | 2579 | static bool |
971de7fb | 2580 | encode_coding_emacs_mule (struct coding_system *coding) |
df7492f9 | 2581 | { |
f10fe38f | 2582 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
2583 | int *charbuf = coding->charbuf; |
2584 | int *charbuf_end = charbuf + coding->charbuf_used; | |
2585 | unsigned char *dst = coding->destination + coding->produced; | |
2586 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
2587 | int safe_room = 8; | |
d311d28c | 2588 | ptrdiff_t produced_chars = 0; |
24a73b0a | 2589 | Lisp_Object attrs, charset_list; |
df7492f9 | 2590 | int c; |
ff0dacd7 | 2591 | int preferred_charset_id = -1; |
df7492f9 | 2592 | |
24a73b0a | 2593 | CODING_GET_INFO (coding, attrs, charset_list); |
eccb6815 KH |
2594 | if (! EQ (charset_list, Vemacs_mule_charset_list)) |
2595 | { | |
4939150c PE |
2596 | charset_list = Vemacs_mule_charset_list; |
2597 | ASET (attrs, coding_attr_charset_list, charset_list); | |
eccb6815 | 2598 | } |
df7492f9 KH |
2599 | |
2600 | while (charbuf < charbuf_end) | |
2601 | { | |
2602 | ASSURE_DESTINATION (safe_room); | |
2603 | c = *charbuf++; | |
ff0dacd7 KH |
2604 | |
2605 | if (c < 0) | |
2606 | { | |
2607 | /* Handle an annotation. */ | |
2608 | switch (*charbuf) | |
2609 | { | |
2610 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
2611 | /* Not yet implemented. */ | |
2612 | break; | |
2613 | case CODING_ANNOTATE_CHARSET_MASK: | |
2614 | preferred_charset_id = charbuf[3]; | |
2615 | if (preferred_charset_id >= 0 | |
2616 | && NILP (Fmemq (make_number (preferred_charset_id), | |
2617 | charset_list))) | |
2618 | preferred_charset_id = -1; | |
2619 | break; | |
2620 | default: | |
1088b922 | 2621 | emacs_abort (); |
ff0dacd7 KH |
2622 | } |
2623 | charbuf += -c - 1; | |
2624 | continue; | |
2625 | } | |
2626 | ||
df7492f9 KH |
2627 | if (ASCII_CHAR_P (c)) |
2628 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
2629 | else if (CHAR_BYTE8_P (c)) |
2630 | { | |
2631 | c = CHAR_TO_BYTE8 (c); | |
2632 | EMIT_ONE_BYTE (c); | |
2633 | } | |
df7492f9 | 2634 | else |
aa72b389 | 2635 | { |
df7492f9 KH |
2636 | struct charset *charset; |
2637 | unsigned code; | |
2638 | int dimension; | |
2639 | int emacs_mule_id; | |
2640 | unsigned char leading_codes[2]; | |
2641 | ||
ff0dacd7 KH |
2642 | if (preferred_charset_id >= 0) |
2643 | { | |
f10fe38f | 2644 | bool result; |
5eb05ea3 | 2645 | |
ff0dacd7 | 2646 | charset = CHARSET_FROM_ID (preferred_charset_id); |
5eb05ea3 KH |
2647 | CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result); |
2648 | if (result) | |
905ca9d2 KH |
2649 | code = ENCODE_CHAR (charset, c); |
2650 | else | |
5eb05ea3 KH |
2651 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2652 | &code, charset); | |
ff0dacd7 KH |
2653 | } |
2654 | else | |
5eb05ea3 KH |
2655 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2656 | &code, charset); | |
df7492f9 KH |
2657 | if (! charset) |
2658 | { | |
2659 | c = coding->default_char; | |
2660 | if (ASCII_CHAR_P (c)) | |
2661 | { | |
2662 | EMIT_ONE_ASCII_BYTE (c); | |
2663 | continue; | |
2664 | } | |
5eb05ea3 KH |
2665 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
2666 | &code, charset); | |
df7492f9 KH |
2667 | } |
2668 | dimension = CHARSET_DIMENSION (charset); | |
2669 | emacs_mule_id = CHARSET_EMACS_MULE_ID (charset); | |
2670 | EMACS_MULE_LEADING_CODES (emacs_mule_id, leading_codes); | |
2671 | EMIT_ONE_BYTE (leading_codes[0]); | |
2672 | if (leading_codes[1]) | |
2673 | EMIT_ONE_BYTE (leading_codes[1]); | |
2674 | if (dimension == 1) | |
1fa663f9 | 2675 | EMIT_ONE_BYTE (code | 0x80); |
aa72b389 | 2676 | else |
df7492f9 | 2677 | { |
1fa663f9 | 2678 | code |= 0x8080; |
df7492f9 KH |
2679 | EMIT_ONE_BYTE (code >> 8); |
2680 | EMIT_ONE_BYTE (code & 0xFF); | |
2681 | } | |
aa72b389 | 2682 | } |
aa72b389 | 2683 | } |
065e3595 | 2684 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
2685 | coding->produced_char += produced_chars; |
2686 | coding->produced = dst - coding->destination; | |
2687 | return 0; | |
aa72b389 | 2688 | } |
b73bfc1c | 2689 | |
4ed46869 | 2690 | \f |
df7492f9 | 2691 | /*** 7. ISO2022 handlers ***/ |
4ed46869 KH |
2692 | |
2693 | /* The following note describes the coding system ISO2022 briefly. | |
39787efd | 2694 | Since the intention of this note is to help understand the |
5a936b46 | 2695 | functions in this file, some parts are NOT ACCURATE or are OVERLY |
39787efd | 2696 | SIMPLIFIED. For thorough understanding, please refer to the |
5a936b46 | 2697 | original document of ISO2022. This is equivalent to the standard |
cfb43547 | 2698 | ECMA-35, obtainable from <URL:http://www.ecma.ch/> (*). |
4ed46869 KH |
2699 | |
2700 | ISO2022 provides many mechanisms to encode several character sets | |
cfb43547 | 2701 | in 7-bit and 8-bit environments. For 7-bit environments, all text |
39787efd KH |
2702 | is encoded using bytes less than 128. This may make the encoded |
2703 | text a little bit longer, but the text passes more easily through | |
cfb43547 | 2704 | several types of gateway, some of which strip off the MSB (Most |
8ca3766a | 2705 | Significant Bit). |
b73bfc1c | 2706 | |
cfb43547 DL |
2707 | There are two kinds of character sets: control character sets and |
2708 | graphic character sets. The former contain control characters such | |
4ed46869 | 2709 | as `newline' and `escape' to provide control functions (control |
39787efd | 2710 | functions are also provided by escape sequences). The latter |
cfb43547 | 2711 | contain graphic characters such as 'A' and '-'. Emacs recognizes |
4ed46869 KH |
2712 | two control character sets and many graphic character sets. |
2713 | ||
2714 | Graphic character sets are classified into one of the following | |
39787efd KH |
2715 | four classes, according to the number of bytes (DIMENSION) and |
2716 | number of characters in one dimension (CHARS) of the set: | |
2717 | - DIMENSION1_CHARS94 | |
2718 | - DIMENSION1_CHARS96 | |
2719 | - DIMENSION2_CHARS94 | |
2720 | - DIMENSION2_CHARS96 | |
2721 | ||
2722 | In addition, each character set is assigned an identification tag, | |
cfb43547 | 2723 | unique for each set, called the "final character" (denoted as <F> |
39787efd KH |
2724 | hereafter). The <F> of each character set is decided by ECMA(*) |
2725 | when it is registered in ISO. The code range of <F> is 0x30..0x7F | |
2726 | (0x30..0x3F are for private use only). | |
4ed46869 KH |
2727 | |
2728 | Note (*): ECMA = European Computer Manufacturers Association | |
2729 | ||
cfb43547 | 2730 | Here are examples of graphic character sets [NAME(<F>)]: |
4ed46869 KH |
2731 | o DIMENSION1_CHARS94 -- ASCII('B'), right-half-of-JISX0201('I'), ... |
2732 | o DIMENSION1_CHARS96 -- right-half-of-ISO8859-1('A'), ... | |
2733 | o DIMENSION2_CHARS94 -- GB2312('A'), JISX0208('B'), ... | |
2734 | o DIMENSION2_CHARS96 -- none for the moment | |
2735 | ||
39787efd | 2736 | A code area (1 byte=8 bits) is divided into 4 areas, C0, GL, C1, and GR. |
4ed46869 KH |
2737 | C0 [0x00..0x1F] -- control character plane 0 |
2738 | GL [0x20..0x7F] -- graphic character plane 0 | |
2739 | C1 [0x80..0x9F] -- control character plane 1 | |
2740 | GR [0xA0..0xFF] -- graphic character plane 1 | |
2741 | ||
2742 | A control character set is directly designated and invoked to C0 or | |
39787efd KH |
2743 | C1 by an escape sequence. The most common case is that: |
2744 | - ISO646's control character set is designated/invoked to C0, and | |
2745 | - ISO6429's control character set is designated/invoked to C1, | |
2746 | and usually these designations/invocations are omitted in encoded | |
2747 | text. In a 7-bit environment, only C0 can be used, and a control | |
2748 | character for C1 is encoded by an appropriate escape sequence to | |
2749 | fit into the environment. All control characters for C1 are | |
2750 | defined to have corresponding escape sequences. | |
4ed46869 KH |
2751 | |
2752 | A graphic character set is at first designated to one of four | |
2753 | graphic registers (G0 through G3), then these graphic registers are | |
2754 | invoked to GL or GR. These designations and invocations can be | |
2755 | done independently. The most common case is that G0 is invoked to | |
39787efd KH |
2756 | GL, G1 is invoked to GR, and ASCII is designated to G0. Usually |
2757 | these invocations and designations are omitted in encoded text. | |
2758 | In a 7-bit environment, only GL can be used. | |
4ed46869 | 2759 | |
39787efd KH |
2760 | When a graphic character set of CHARS94 is invoked to GL, codes |
2761 | 0x20 and 0x7F of the GL area work as control characters SPACE and | |
2762 | DEL respectively, and codes 0xA0 and 0xFF of the GR area should not | |
2763 | be used. | |
4ed46869 KH |
2764 | |
2765 | There are two ways of invocation: locking-shift and single-shift. | |
2766 | With locking-shift, the invocation lasts until the next different | |
39787efd KH |
2767 | invocation, whereas with single-shift, the invocation affects the |
2768 | following character only and doesn't affect the locking-shift | |
2769 | state. Invocations are done by the following control characters or | |
2770 | escape sequences: | |
4ed46869 KH |
2771 | |
2772 | ---------------------------------------------------------------------- | |
39787efd | 2773 | abbrev function cntrl escape seq description |
4ed46869 | 2774 | ---------------------------------------------------------------------- |
39787efd KH |
2775 | SI/LS0 (shift-in) 0x0F none invoke G0 into GL |
2776 | SO/LS1 (shift-out) 0x0E none invoke G1 into GL | |
2777 | LS2 (locking-shift-2) none ESC 'n' invoke G2 into GL | |
2778 | LS3 (locking-shift-3) none ESC 'o' invoke G3 into GL | |
2779 | LS1R (locking-shift-1 right) none ESC '~' invoke G1 into GR (*) | |
2780 | LS2R (locking-shift-2 right) none ESC '}' invoke G2 into GR (*) | |
2781 | LS3R (locking-shift 3 right) none ESC '|' invoke G3 into GR (*) | |
2782 | SS2 (single-shift-2) 0x8E ESC 'N' invoke G2 for one char | |
2783 | SS3 (single-shift-3) 0x8F ESC 'O' invoke G3 for one char | |
4ed46869 | 2784 | ---------------------------------------------------------------------- |
39787efd KH |
2785 | (*) These are not used by any known coding system. |
2786 | ||
2787 | Control characters for these functions are defined by macros | |
2788 | ISO_CODE_XXX in `coding.h'. | |
4ed46869 | 2789 | |
39787efd | 2790 | Designations are done by the following escape sequences: |
4ed46869 KH |
2791 | ---------------------------------------------------------------------- |
2792 | escape sequence description | |
2793 | ---------------------------------------------------------------------- | |
2794 | ESC '(' <F> designate DIMENSION1_CHARS94<F> to G0 | |
2795 | ESC ')' <F> designate DIMENSION1_CHARS94<F> to G1 | |
2796 | ESC '*' <F> designate DIMENSION1_CHARS94<F> to G2 | |
2797 | ESC '+' <F> designate DIMENSION1_CHARS94<F> to G3 | |
2798 | ESC ',' <F> designate DIMENSION1_CHARS96<F> to G0 (*) | |
2799 | ESC '-' <F> designate DIMENSION1_CHARS96<F> to G1 | |
2800 | ESC '.' <F> designate DIMENSION1_CHARS96<F> to G2 | |
2801 | ESC '/' <F> designate DIMENSION1_CHARS96<F> to G3 | |
2802 | ESC '$' '(' <F> designate DIMENSION2_CHARS94<F> to G0 (**) | |
2803 | ESC '$' ')' <F> designate DIMENSION2_CHARS94<F> to G1 | |
2804 | ESC '$' '*' <F> designate DIMENSION2_CHARS94<F> to G2 | |
2805 | ESC '$' '+' <F> designate DIMENSION2_CHARS94<F> to G3 | |
2806 | ESC '$' ',' <F> designate DIMENSION2_CHARS96<F> to G0 (*) | |
2807 | ESC '$' '-' <F> designate DIMENSION2_CHARS96<F> to G1 | |
2808 | ESC '$' '.' <F> designate DIMENSION2_CHARS96<F> to G2 | |
2809 | ESC '$' '/' <F> designate DIMENSION2_CHARS96<F> to G3 | |
2810 | ---------------------------------------------------------------------- | |
2811 | ||
2812 | In this list, "DIMENSION1_CHARS94<F>" means a graphic character set | |
39787efd | 2813 | of dimension 1, chars 94, and final character <F>, etc... |
4ed46869 KH |
2814 | |
2815 | Note (*): Although these designations are not allowed in ISO2022, | |
2816 | Emacs accepts them on decoding, and produces them on encoding | |
39787efd | 2817 | CHARS96 character sets in a coding system which is characterized as |
4ed46869 KH |
2818 | 7-bit environment, non-locking-shift, and non-single-shift. |
2819 | ||
2820 | Note (**): If <F> is '@', 'A', or 'B', the intermediate character | |
df7492f9 | 2821 | '(' must be omitted. We refer to this as "short-form" hereafter. |
4ed46869 | 2822 | |
cfb43547 | 2823 | Now you may notice that there are a lot of ways of encoding the |
39787efd KH |
2824 | same multilingual text in ISO2022. Actually, there exist many |
2825 | coding systems such as Compound Text (used in X11's inter client | |
8ca3766a DL |
2826 | communication, ISO-2022-JP (used in Japanese Internet), ISO-2022-KR |
2827 | (used in Korean Internet), EUC (Extended UNIX Code, used in Asian | |
4ed46869 KH |
2828 | localized platforms), and all of these are variants of ISO2022. |
2829 | ||
2830 | In addition to the above, Emacs handles two more kinds of escape | |
2831 | sequences: ISO6429's direction specification and Emacs' private | |
2832 | sequence for specifying character composition. | |
2833 | ||
39787efd | 2834 | ISO6429's direction specification takes the following form: |
4ed46869 KH |
2835 | o CSI ']' -- end of the current direction |
2836 | o CSI '0' ']' -- end of the current direction | |
2837 | o CSI '1' ']' -- start of left-to-right text | |
2838 | o CSI '2' ']' -- start of right-to-left text | |
2839 | The control character CSI (0x9B: control sequence introducer) is | |
39787efd KH |
2840 | abbreviated to the escape sequence ESC '[' in a 7-bit environment. |
2841 | ||
2842 | Character composition specification takes the following form: | |
ec6d2bb8 KH |
2843 | o ESC '0' -- start relative composition |
2844 | o ESC '1' -- end composition | |
2845 | o ESC '2' -- start rule-base composition (*) | |
2846 | o ESC '3' -- start relative composition with alternate chars (**) | |
2847 | o ESC '4' -- start rule-base composition with alternate chars (**) | |
b73bfc1c | 2848 | Since these are not standard escape sequences of any ISO standard, |
cfb43547 | 2849 | the use of them with these meanings is restricted to Emacs only. |
ec6d2bb8 | 2850 | |
5a936b46 DL |
2851 | (*) This form is used only in Emacs 20.7 and older versions, |
2852 | but newer versions can safely decode it. | |
cfb43547 | 2853 | (**) This form is used only in Emacs 21.1 and newer versions, |
5a936b46 | 2854 | and older versions can't decode it. |
ec6d2bb8 | 2855 | |
cfb43547 | 2856 | Here's a list of example usages of these composition escape |
b73bfc1c | 2857 | sequences (categorized by `enum composition_method'). |
ec6d2bb8 | 2858 | |
b73bfc1c | 2859 | COMPOSITION_RELATIVE: |
ec6d2bb8 | 2860 | ESC 0 CHAR [ CHAR ] ESC 1 |
8ca3766a | 2861 | COMPOSITION_WITH_RULE: |
ec6d2bb8 | 2862 | ESC 2 CHAR [ RULE CHAR ] ESC 1 |
b73bfc1c | 2863 | COMPOSITION_WITH_ALTCHARS: |
ec6d2bb8 | 2864 | ESC 3 ALTCHAR [ ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 |
b73bfc1c | 2865 | COMPOSITION_WITH_RULE_ALTCHARS: |
ec6d2bb8 | 2866 | ESC 4 ALTCHAR [ RULE ALTCHAR ] ESC 0 CHAR [ CHAR ] ESC 1 */ |
4ed46869 | 2867 | |
74ab6df5 | 2868 | static enum iso_code_class_type iso_code_class[256]; |
4ed46869 | 2869 | |
df7492f9 KH |
2870 | #define SAFE_CHARSET_P(coding, id) \ |
2871 | ((id) <= (coding)->max_charset_id \ | |
1b3b981b | 2872 | && (coding)->safe_charsets[id] != 255) |
df7492f9 | 2873 | |
df7492f9 | 2874 | static void |
971de7fb | 2875 | setup_iso_safe_charsets (Lisp_Object attrs) |
df7492f9 KH |
2876 | { |
2877 | Lisp_Object charset_list, safe_charsets; | |
2878 | Lisp_Object request; | |
2879 | Lisp_Object reg_usage; | |
2880 | Lisp_Object tail; | |
d311d28c | 2881 | EMACS_INT reg94, reg96; |
df7492f9 KH |
2882 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); |
2883 | int max_charset_id; | |
2884 | ||
2885 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2886 | if ((flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
2887 | && ! EQ (charset_list, Viso_2022_charset_list)) | |
2888 | { | |
4939150c PE |
2889 | charset_list = Viso_2022_charset_list; |
2890 | ASET (attrs, coding_attr_charset_list, charset_list); | |
df7492f9 KH |
2891 | ASET (attrs, coding_attr_safe_charsets, Qnil); |
2892 | } | |
2893 | ||
2894 | if (STRINGP (AREF (attrs, coding_attr_safe_charsets))) | |
2895 | return; | |
2896 | ||
2897 | max_charset_id = 0; | |
2898 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2899 | { | |
2900 | int id = XINT (XCAR (tail)); | |
2901 | if (max_charset_id < id) | |
2902 | max_charset_id = id; | |
2903 | } | |
d46c5b12 | 2904 | |
1b3b981b AS |
2905 | safe_charsets = make_uninit_string (max_charset_id + 1); |
2906 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
2907 | request = AREF (attrs, coding_attr_iso_request); |
2908 | reg_usage = AREF (attrs, coding_attr_iso_usage); | |
2909 | reg94 = XINT (XCAR (reg_usage)); | |
2910 | reg96 = XINT (XCDR (reg_usage)); | |
2911 | ||
2912 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
2913 | { | |
2914 | Lisp_Object id; | |
2915 | Lisp_Object reg; | |
2916 | struct charset *charset; | |
2917 | ||
2918 | id = XCAR (tail); | |
2919 | charset = CHARSET_FROM_ID (XINT (id)); | |
bf16eb23 | 2920 | reg = Fcdr (Fassq (id, request)); |
df7492f9 | 2921 | if (! NILP (reg)) |
8f924df7 | 2922 | SSET (safe_charsets, XINT (id), XINT (reg)); |
df7492f9 KH |
2923 | else if (charset->iso_chars_96) |
2924 | { | |
2925 | if (reg96 < 4) | |
8f924df7 | 2926 | SSET (safe_charsets, XINT (id), reg96); |
df7492f9 KH |
2927 | } |
2928 | else | |
2929 | { | |
2930 | if (reg94 < 4) | |
8f924df7 | 2931 | SSET (safe_charsets, XINT (id), reg94); |
df7492f9 KH |
2932 | } |
2933 | } | |
2934 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); | |
2935 | } | |
d46c5b12 | 2936 | |
b6871cc7 | 2937 | |
4ed46869 | 2938 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f PE |
2939 | Return true if a text is encoded in one of ISO-2022 based coding |
2940 | systems. */ | |
4ed46869 | 2941 | |
f10fe38f | 2942 | static bool |
cf84bb53 JB |
2943 | detect_coding_iso_2022 (struct coding_system *coding, |
2944 | struct coding_detection_info *detect_info) | |
4ed46869 | 2945 | { |
8f924df7 KH |
2946 | const unsigned char *src = coding->source, *src_base = src; |
2947 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
f10fe38f PE |
2948 | bool multibytep = coding->src_multibyte; |
2949 | bool single_shifting = 0; | |
0e48bb22 | 2950 | int id; |
df7492f9 | 2951 | int c, c1; |
d311d28c | 2952 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 2953 | int i; |
ff0dacd7 KH |
2954 | int rejected = 0; |
2955 | int found = 0; | |
cee53ed4 | 2956 | int composition_count = -1; |
ff0dacd7 KH |
2957 | |
2958 | detect_info->checked |= CATEGORY_MASK_ISO; | |
df7492f9 KH |
2959 | |
2960 | for (i = coding_category_iso_7; i <= coding_category_iso_8_else; i++) | |
2961 | { | |
2962 | struct coding_system *this = &(coding_categories[i]); | |
2963 | Lisp_Object attrs, val; | |
2964 | ||
c6b278e7 KH |
2965 | if (this->id < 0) |
2966 | continue; | |
df7492f9 KH |
2967 | attrs = CODING_ID_ATTRS (this->id); |
2968 | if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT | |
1b3b981b | 2969 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Viso_2022_charset_list)) |
df7492f9 KH |
2970 | setup_iso_safe_charsets (attrs); |
2971 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 2972 | this->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 2973 | this->safe_charsets = SDATA (val); |
df7492f9 KH |
2974 | } |
2975 | ||
2976 | /* A coding system of this category is always ASCII compatible. */ | |
2977 | src += coding->head_ascii; | |
3f003981 | 2978 | |
ff0dacd7 | 2979 | while (rejected != CATEGORY_MASK_ISO) |
4ed46869 | 2980 | { |
065e3595 | 2981 | src_base = src; |
df7492f9 | 2982 | ONE_MORE_BYTE (c); |
4ed46869 KH |
2983 | switch (c) |
2984 | { | |
2985 | case ISO_CODE_ESC: | |
74383408 KH |
2986 | if (inhibit_iso_escape_detection) |
2987 | break; | |
f46869e4 | 2988 | single_shifting = 0; |
df7492f9 | 2989 | ONE_MORE_BYTE (c); |
0e48bb22 | 2990 | if (c == 'N' || c == 'O') |
d46c5b12 | 2991 | { |
ae9ff118 | 2992 | /* ESC <Fe> for SS2 or SS3. */ |
ff0dacd7 KH |
2993 | single_shifting = 1; |
2994 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; | |
4ed46869 | 2995 | } |
cee53ed4 KH |
2996 | else if (c == '1') |
2997 | { | |
2998 | /* End of composition. */ | |
2999 | if (composition_count < 0 | |
3000 | || composition_count > MAX_COMPOSITION_COMPONENTS) | |
3001 | /* Invalid */ | |
3002 | break; | |
3003 | composition_count = -1; | |
3004 | found |= CATEGORY_MASK_ISO; | |
3005 | } | |
ec6d2bb8 KH |
3006 | else if (c >= '0' && c <= '4') |
3007 | { | |
3008 | /* ESC <Fp> for start/end composition. */ | |
cee53ed4 | 3009 | composition_count = 0; |
ec6d2bb8 | 3010 | } |
bf9cdd4e | 3011 | else |
df7492f9 | 3012 | { |
0e48bb22 AS |
3013 | if (c >= '(' && c <= '/') |
3014 | { | |
3015 | /* Designation sequence for a charset of dimension 1. */ | |
3016 | ONE_MORE_BYTE (c1); | |
3017 | if (c1 < ' ' || c1 >= 0x80 | |
3018 | || (id = iso_charset_table[0][c >= ','][c1]) < 0) | |
3019 | /* Invalid designation sequence. Just ignore. */ | |
3020 | break; | |
3021 | } | |
3022 | else if (c == '$') | |
3023 | { | |
3024 | /* Designation sequence for a charset of dimension 2. */ | |
3025 | ONE_MORE_BYTE (c); | |
3026 | if (c >= '@' && c <= 'B') | |
3027 | /* Designation for JISX0208.1978, GB2312, or JISX0208. */ | |
3028 | id = iso_charset_table[1][0][c]; | |
3029 | else if (c >= '(' && c <= '/') | |
3030 | { | |
3031 | ONE_MORE_BYTE (c1); | |
3032 | if (c1 < ' ' || c1 >= 0x80 | |
3033 | || (id = iso_charset_table[1][c >= ','][c1]) < 0) | |
3034 | /* Invalid designation sequence. Just ignore. */ | |
3035 | break; | |
3036 | } | |
3037 | else | |
3038 | /* Invalid designation sequence. Just ignore it. */ | |
3039 | break; | |
3040 | } | |
3041 | else | |
3042 | { | |
3043 | /* Invalid escape sequence. Just ignore it. */ | |
3044 | break; | |
3045 | } | |
d46c5b12 | 3046 | |
0e48bb22 AS |
3047 | /* We found a valid designation sequence for CHARSET. */ |
3048 | rejected |= CATEGORY_MASK_ISO_8BIT; | |
3049 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7], | |
3050 | id)) | |
3051 | found |= CATEGORY_MASK_ISO_7; | |
3052 | else | |
3053 | rejected |= CATEGORY_MASK_ISO_7; | |
3054 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_tight], | |
3055 | id)) | |
3056 | found |= CATEGORY_MASK_ISO_7_TIGHT; | |
3057 | else | |
3058 | rejected |= CATEGORY_MASK_ISO_7_TIGHT; | |
3059 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_7_else], | |
3060 | id)) | |
3061 | found |= CATEGORY_MASK_ISO_7_ELSE; | |
3062 | else | |
3063 | rejected |= CATEGORY_MASK_ISO_7_ELSE; | |
3064 | if (SAFE_CHARSET_P (&coding_categories[coding_category_iso_8_else], | |
3065 | id)) | |
3066 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3067 | else | |
3068 | rejected |= CATEGORY_MASK_ISO_8_ELSE; | |
3069 | } | |
4ed46869 KH |
3070 | break; |
3071 | ||
4ed46869 | 3072 | case ISO_CODE_SO: |
d46c5b12 | 3073 | case ISO_CODE_SI: |
ff0dacd7 | 3074 | /* Locking shift out/in. */ |
74383408 KH |
3075 | if (inhibit_iso_escape_detection) |
3076 | break; | |
f46869e4 | 3077 | single_shifting = 0; |
ff0dacd7 | 3078 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_8BIT; |
d46c5b12 KH |
3079 | break; |
3080 | ||
4ed46869 | 3081 | case ISO_CODE_CSI: |
ff0dacd7 | 3082 | /* Control sequence introducer. */ |
f46869e4 | 3083 | single_shifting = 0; |
ff0dacd7 KH |
3084 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3085 | found |= CATEGORY_MASK_ISO_8_ELSE; | |
3086 | goto check_extra_latin; | |
3087 | ||
4ed46869 KH |
3088 | case ISO_CODE_SS2: |
3089 | case ISO_CODE_SS3: | |
ff0dacd7 KH |
3090 | /* Single shift. */ |
3091 | if (inhibit_iso_escape_detection) | |
3092 | break; | |
75e2a253 | 3093 | single_shifting = 0; |
ff0dacd7 KH |
3094 | rejected |= CATEGORY_MASK_ISO_7BIT; |
3095 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3096 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
0e48bb22 AS |
3097 | { |
3098 | found |= CATEGORY_MASK_ISO_8_1; | |
3099 | single_shifting = 1; | |
3100 | } | |
ff0dacd7 KH |
3101 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_2]) |
3102 | & CODING_ISO_FLAG_SINGLE_SHIFT) | |
0e48bb22 AS |
3103 | { |
3104 | found |= CATEGORY_MASK_ISO_8_2; | |
3105 | single_shifting = 1; | |
3106 | } | |
75e2a253 KH |
3107 | if (single_shifting) |
3108 | break; | |
0e48bb22 AS |
3109 | check_extra_latin: |
3110 | if (! VECTORP (Vlatin_extra_code_table) | |
28be1ada | 3111 | || NILP (AREF (Vlatin_extra_code_table, c))) |
0e48bb22 AS |
3112 | { |
3113 | rejected = CATEGORY_MASK_ISO; | |
3114 | break; | |
3115 | } | |
3116 | if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1]) | |
3117 | & CODING_ISO_FLAG_LATIN_EXTRA) | |
3118 | found |= CATEGORY_MASK_ISO_8_1; | |
3119 | else | |
3120 | rejected |= CATEGORY_MASK_ISO_8_1; | |
3121 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3122 | break; | |
4ed46869 KH |
3123 | |
3124 | default: | |
065e3595 KH |
3125 | if (c < 0) |
3126 | continue; | |
4ed46869 | 3127 | if (c < 0x80) |
f46869e4 | 3128 | { |
cee53ed4 KH |
3129 | if (composition_count >= 0) |
3130 | composition_count++; | |
f46869e4 KH |
3131 | single_shifting = 0; |
3132 | break; | |
3133 | } | |
ff0dacd7 | 3134 | if (c >= 0xA0) |
c4825358 | 3135 | { |
ff0dacd7 KH |
3136 | rejected |= CATEGORY_MASK_ISO_7BIT | CATEGORY_MASK_ISO_7_ELSE; |
3137 | found |= CATEGORY_MASK_ISO_8_1; | |
f46869e4 | 3138 | /* Check the length of succeeding codes of the range |
ff0dacd7 KH |
3139 | 0xA0..0FF. If the byte length is even, we include |
3140 | CATEGORY_MASK_ISO_8_2 in `found'. We can check this | |
3141 | only when we are not single shifting. */ | |
3142 | if (! single_shifting | |
3143 | && ! (rejected & CATEGORY_MASK_ISO_8_2)) | |
f46869e4 | 3144 | { |
2735d060 | 3145 | int len = 1; |
b73bfc1c KH |
3146 | while (src < src_end) |
3147 | { | |
d12bd917 | 3148 | src_base = src; |
df7492f9 | 3149 | ONE_MORE_BYTE (c); |
b73bfc1c | 3150 | if (c < 0xA0) |
d12bd917 KH |
3151 | { |
3152 | src = src_base; | |
3153 | break; | |
3154 | } | |
2735d060 | 3155 | len++; |
b73bfc1c KH |
3156 | } |
3157 | ||
2735d060 | 3158 | if (len & 1 && src < src_end) |
cee53ed4 KH |
3159 | { |
3160 | rejected |= CATEGORY_MASK_ISO_8_2; | |
3161 | if (composition_count >= 0) | |
2735d060 | 3162 | composition_count += len; |
cee53ed4 | 3163 | } |
f46869e4 | 3164 | else |
cee53ed4 KH |
3165 | { |
3166 | found |= CATEGORY_MASK_ISO_8_2; | |
3167 | if (composition_count >= 0) | |
2735d060 | 3168 | composition_count += len / 2; |
cee53ed4 | 3169 | } |
f46869e4 | 3170 | } |
ff0dacd7 | 3171 | break; |
4ed46869 | 3172 | } |
4ed46869 KH |
3173 | } |
3174 | } | |
ff0dacd7 KH |
3175 | detect_info->rejected |= CATEGORY_MASK_ISO; |
3176 | return 0; | |
4ed46869 | 3177 | |
df7492f9 | 3178 | no_more_source: |
ff0dacd7 KH |
3179 | detect_info->rejected |= rejected; |
3180 | detect_info->found |= (found & ~rejected); | |
df7492f9 | 3181 | return 1; |
4ed46869 | 3182 | } |
ec6d2bb8 | 3183 | |
4ed46869 | 3184 | |
134b9549 KH |
3185 | /* Set designation state into CODING. Set CHARS_96 to -1 if the |
3186 | escape sequence should be kept. */ | |
df7492f9 KH |
3187 | #define DECODE_DESIGNATION(reg, dim, chars_96, final) \ |
3188 | do { \ | |
3189 | int id, prev; \ | |
3190 | \ | |
3191 | if (final < '0' || final >= 128 \ | |
3192 | || ((id = ISO_CHARSET_TABLE (dim, chars_96, final)) < 0) \ | |
3193 | || !SAFE_CHARSET_P (coding, id)) \ | |
3194 | { \ | |
3195 | CODING_ISO_DESIGNATION (coding, reg) = -2; \ | |
134b9549 KH |
3196 | chars_96 = -1; \ |
3197 | break; \ | |
df7492f9 KH |
3198 | } \ |
3199 | prev = CODING_ISO_DESIGNATION (coding, reg); \ | |
bf16eb23 KH |
3200 | if (id == charset_jisx0201_roman) \ |
3201 | { \ | |
3202 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
3203 | id = charset_ascii; \ | |
3204 | } \ | |
3205 | else if (id == charset_jisx0208_1978) \ | |
3206 | { \ | |
3207 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
3208 | id = charset_jisx0208; \ | |
3209 | } \ | |
df7492f9 KH |
3210 | CODING_ISO_DESIGNATION (coding, reg) = id; \ |
3211 | /* If there was an invalid designation to REG previously, and this \ | |
3212 | designation is ASCII to REG, we should keep this designation \ | |
3213 | sequence. */ \ | |
3214 | if (prev == -2 && id == charset_ascii) \ | |
134b9549 | 3215 | chars_96 = -1; \ |
4ed46869 KH |
3216 | } while (0) |
3217 | ||
d46c5b12 | 3218 | |
e951386e KH |
3219 | /* Handle these composition sequence (ALT: alternate char): |
3220 | ||
3221 | (1) relative composition: ESC 0 CHAR ... ESC 1 | |
3222 | (2) rulebase composition: ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
3223 | (3) altchar composition: ESC 3 ALT ... ALT ESC 0 CHAR ... ESC 1 | |
3224 | (4) alt&rule composition: ESC 4 ALT RULE ... ALT ESC 0 CHAR ... ESC 1 | |
3225 | ||
3226 | When the start sequence (ESC 0/2/3/4) is found, this annotation | |
3227 | header is produced. | |
3228 | ||
3229 | [ -LENGTH(==-5) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) 0 METHOD ] | |
3230 | ||
3231 | Then, upon reading CHAR or RULE (one or two bytes), these codes are | |
3232 | produced until the end sequence (ESC 1) is found: | |
3233 | ||
3234 | (1) CHAR ... CHAR | |
3235 | (2) CHAR -2 DECODED-RULE CHAR -2 DECODED-RULE ... CHAR | |
3236 | (3) ALT ... ALT -1 -1 CHAR ... CHAR | |
3237 | (4) ALT -2 DECODED-RULE ALT -2 DECODED-RULE ... ALT -1 -1 CHAR ... CHAR | |
3238 | ||
3239 | When the end sequence (ESC 1) is found, LENGTH and NCHARS in the | |
3240 | annotation header is updated as below: | |
3241 | ||
3242 | (1) LENGTH: unchanged, NCHARS: number of CHARs | |
3243 | (2) LENGTH: unchanged, NCHARS: number of CHARs | |
3244 | (3) LENGTH: += number of ALTs + 2, NCHARS: number of CHARs | |
3245 | (4) LENGTH: += number of ALTs * 3, NCHARS: number of CHARs | |
3246 | ||
3247 | If an error is found while composing, the annotation header is | |
3248 | changed to: | |
3249 | ||
3250 | [ ESC '0'/'2'/'3'/'4' -2 0 ] | |
3251 | ||
3252 | and the sequence [ -2 DECODED-RULE ] is changed to the original | |
3253 | byte sequence as below: | |
3254 | o the original byte sequence is B: [ B -1 ] | |
3255 | o the original byte sequence is B1 B2: [ B1 B2 ] | |
3256 | and the sequence [ -1 -1 ] is changed to the original byte | |
3257 | sequence: | |
3258 | [ ESC '0' ] | |
3259 | */ | |
3260 | ||
3261 | /* Decode a composition rule C1 and maybe one more byte from the | |
66ebf983 | 3262 | source, and set RULE to the encoded composition rule. If the rule |
d5efd1d1 | 3263 | is invalid, goto invalid_code. */ |
e951386e | 3264 | |
66ebf983 | 3265 | #define DECODE_COMPOSITION_RULE(rule) \ |
e951386e KH |
3266 | do { \ |
3267 | rule = c1 - 32; \ | |
3268 | if (rule < 0) \ | |
d5efd1d1 | 3269 | goto invalid_code; \ |
e951386e KH |
3270 | if (rule < 81) /* old format (before ver.21) */ \ |
3271 | { \ | |
3272 | int gref = (rule) / 9; \ | |
3273 | int nref = (rule) % 9; \ | |
3274 | if (gref == 4) gref = 10; \ | |
3275 | if (nref == 4) nref = 10; \ | |
3276 | rule = COMPOSITION_ENCODE_RULE (gref, nref); \ | |
e951386e KH |
3277 | } \ |
3278 | else /* new format (after ver.21) */ \ | |
3279 | { \ | |
2735d060 | 3280 | int b; \ |
e951386e | 3281 | \ |
2735d060 | 3282 | ONE_MORE_BYTE (b); \ |
d5efd1d1 PE |
3283 | if (! COMPOSITION_ENCODE_RULE_VALID (rule - 81, b - 32)) \ |
3284 | goto invalid_code; \ | |
2735d060 | 3285 | rule = COMPOSITION_ENCODE_RULE (rule - 81, b - 32); \ |
d5efd1d1 | 3286 | rule += 0x100; /* Distinguish it from the old format. */ \ |
e951386e KH |
3287 | } \ |
3288 | } while (0) | |
3289 | ||
3290 | #define ENCODE_COMPOSITION_RULE(rule) \ | |
df7492f9 | 3291 | do { \ |
e951386e KH |
3292 | int gref = (rule % 0x100) / 12, nref = (rule % 0x100) % 12; \ |
3293 | \ | |
3294 | if (rule < 0x100) /* old format */ \ | |
df7492f9 | 3295 | { \ |
e951386e KH |
3296 | if (gref == 10) gref = 4; \ |
3297 | if (nref == 10) nref = 4; \ | |
3298 | charbuf[idx] = 32 + gref * 9 + nref; \ | |
3299 | charbuf[idx + 1] = -1; \ | |
3300 | new_chars++; \ | |
df7492f9 | 3301 | } \ |
e951386e | 3302 | else /* new format */ \ |
df7492f9 | 3303 | { \ |
e951386e KH |
3304 | charbuf[idx] = 32 + 81 + gref; \ |
3305 | charbuf[idx + 1] = 32 + nref; \ | |
3306 | new_chars += 2; \ | |
df7492f9 KH |
3307 | } \ |
3308 | } while (0) | |
3309 | ||
e951386e KH |
3310 | /* Finish the current composition as invalid. */ |
3311 | ||
e951386e | 3312 | static int |
971de7fb | 3313 | finish_composition (int *charbuf, struct composition_status *cmp_status) |
e951386e KH |
3314 | { |
3315 | int idx = - cmp_status->length; | |
3316 | int new_chars; | |
3317 | ||
3318 | /* Recover the original ESC sequence */ | |
3319 | charbuf[idx++] = ISO_CODE_ESC; | |
3320 | charbuf[idx++] = (cmp_status->method == COMPOSITION_RELATIVE ? '0' | |
3321 | : cmp_status->method == COMPOSITION_WITH_RULE ? '2' | |
3322 | : cmp_status->method == COMPOSITION_WITH_ALTCHARS ? '3' | |
3323 | /* cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS */ | |
3324 | : '4'); | |
3325 | charbuf[idx++] = -2; | |
3326 | charbuf[idx++] = 0; | |
3327 | charbuf[idx++] = -1; | |
3328 | new_chars = cmp_status->nchars; | |
3329 | if (cmp_status->method >= COMPOSITION_WITH_RULE) | |
3330 | for (; idx < 0; idx++) | |
3331 | { | |
3332 | int elt = charbuf[idx]; | |
3333 | ||
3334 | if (elt == -2) | |
3335 | { | |
3336 | ENCODE_COMPOSITION_RULE (charbuf[idx + 1]); | |
3337 | idx++; | |
3338 | } | |
3339 | else if (elt == -1) | |
3340 | { | |
3341 | charbuf[idx++] = ISO_CODE_ESC; | |
3342 | charbuf[idx] = '0'; | |
3343 | new_chars += 2; | |
3344 | } | |
3345 | } | |
3346 | cmp_status->state = COMPOSING_NO; | |
3347 | return new_chars; | |
3348 | } | |
3349 | ||
ad1746f5 | 3350 | /* If characters are under composition, finish the composition. */ |
e951386e KH |
3351 | #define MAYBE_FINISH_COMPOSITION() \ |
3352 | do { \ | |
3353 | if (cmp_status->state != COMPOSING_NO) \ | |
3354 | char_offset += finish_composition (charbuf, cmp_status); \ | |
3355 | } while (0) | |
d46c5b12 | 3356 | |
aa72b389 | 3357 | /* Handle composition start sequence ESC 0, ESC 2, ESC 3, or ESC 4. |
e951386e | 3358 | |
aa72b389 KH |
3359 | ESC 0 : relative composition : ESC 0 CHAR ... ESC 1 |
3360 | ESC 2 : rulebase composition : ESC 2 CHAR RULE CHAR RULE ... CHAR ESC 1 | |
df7492f9 KH |
3361 | ESC 3 : altchar composition : ESC 3 CHAR ... ESC 0 CHAR ... ESC 1 |
3362 | ESC 4 : alt&rule composition : ESC 4 CHAR RULE ... CHAR ESC 0 CHAR ... ESC 1 | |
ec6d2bb8 | 3363 | |
e951386e KH |
3364 | Produce this annotation sequence now: |
3365 | ||
3366 | [ -LENGTH(==-4) CODING_ANNOTATE_COMPOSITION_MASK NCHARS(==0) METHOD ] | |
3367 | */ | |
3368 | ||
3369 | #define DECODE_COMPOSITION_START(c1) \ | |
3370 | do { \ | |
3371 | if (c1 == '0' \ | |
3372 | && ((cmp_status->state == COMPOSING_COMPONENT_CHAR \ | |
3373 | && cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ | |
3374 | || (cmp_status->state == COMPOSING_COMPONENT_RULE \ | |
3375 | && cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS))) \ | |
3376 | { \ | |
3377 | *charbuf++ = -1; \ | |
3378 | *charbuf++= -1; \ | |
3379 | cmp_status->state = COMPOSING_CHAR; \ | |
3380 | cmp_status->length += 2; \ | |
3381 | } \ | |
3382 | else \ | |
3383 | { \ | |
3384 | MAYBE_FINISH_COMPOSITION (); \ | |
3385 | cmp_status->method = (c1 == '0' ? COMPOSITION_RELATIVE \ | |
3386 | : c1 == '2' ? COMPOSITION_WITH_RULE \ | |
3387 | : c1 == '3' ? COMPOSITION_WITH_ALTCHARS \ | |
3388 | : COMPOSITION_WITH_RULE_ALTCHARS); \ | |
3389 | cmp_status->state \ | |
3390 | = (c1 <= '2' ? COMPOSING_CHAR : COMPOSING_COMPONENT_CHAR); \ | |
3391 | ADD_COMPOSITION_DATA (charbuf, 0, 0, cmp_status->method); \ | |
3392 | cmp_status->length = MAX_ANNOTATION_LENGTH; \ | |
3393 | cmp_status->nchars = cmp_status->ncomps = 0; \ | |
3394 | coding->annotated = 1; \ | |
3395 | } \ | |
ec6d2bb8 KH |
3396 | } while (0) |
3397 | ||
ec6d2bb8 | 3398 | |
e951386e | 3399 | /* Handle composition end sequence ESC 1. */ |
df7492f9 KH |
3400 | |
3401 | #define DECODE_COMPOSITION_END() \ | |
ec6d2bb8 | 3402 | do { \ |
e951386e KH |
3403 | if (cmp_status->nchars == 0 \ |
3404 | || ((cmp_status->state == COMPOSING_CHAR) \ | |
3405 | == (cmp_status->method == COMPOSITION_WITH_RULE))) \ | |
ec6d2bb8 | 3406 | { \ |
e951386e KH |
3407 | MAYBE_FINISH_COMPOSITION (); \ |
3408 | goto invalid_code; \ | |
ec6d2bb8 | 3409 | } \ |
e951386e KH |
3410 | if (cmp_status->method == COMPOSITION_WITH_ALTCHARS) \ |
3411 | charbuf[- cmp_status->length] -= cmp_status->ncomps + 2; \ | |
3412 | else if (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS) \ | |
3413 | charbuf[- cmp_status->length] -= cmp_status->ncomps * 3; \ | |
3414 | charbuf[- cmp_status->length + 2] = cmp_status->nchars; \ | |
3415 | char_offset += cmp_status->nchars; \ | |
3416 | cmp_status->state = COMPOSING_NO; \ | |
ec6d2bb8 KH |
3417 | } while (0) |
3418 | ||
e951386e | 3419 | /* Store a composition rule RULE in charbuf, and update cmp_status. */ |
df7492f9 | 3420 | |
e951386e KH |
3421 | #define STORE_COMPOSITION_RULE(rule) \ |
3422 | do { \ | |
3423 | *charbuf++ = -2; \ | |
3424 | *charbuf++ = rule; \ | |
3425 | cmp_status->length += 2; \ | |
3426 | cmp_status->state--; \ | |
3427 | } while (0) | |
ec6d2bb8 | 3428 | |
e951386e KH |
3429 | /* Store a composed char or a component char C in charbuf, and update |
3430 | cmp_status. */ | |
3431 | ||
3432 | #define STORE_COMPOSITION_CHAR(c) \ | |
ec6d2bb8 | 3433 | do { \ |
e951386e KH |
3434 | *charbuf++ = (c); \ |
3435 | cmp_status->length++; \ | |
3436 | if (cmp_status->state == COMPOSING_CHAR) \ | |
3437 | cmp_status->nchars++; \ | |
df7492f9 | 3438 | else \ |
e951386e KH |
3439 | cmp_status->ncomps++; \ |
3440 | if (cmp_status->method == COMPOSITION_WITH_RULE \ | |
3441 | || (cmp_status->method == COMPOSITION_WITH_RULE_ALTCHARS \ | |
3442 | && cmp_status->state == COMPOSING_COMPONENT_CHAR)) \ | |
3443 | cmp_status->state++; \ | |
ec6d2bb8 | 3444 | } while (0) |
88993dfd | 3445 | |
d46c5b12 | 3446 | |
4ed46869 KH |
3447 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
3448 | ||
b73bfc1c | 3449 | static void |
971de7fb | 3450 | decode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 3451 | { |
8f924df7 KH |
3452 | const unsigned char *src = coding->source + coding->consumed; |
3453 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
3454 | const unsigned char *src_base; | |
69a80ea3 | 3455 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 KH |
3456 | /* We may produce two annotations (charset and composition) in one |
3457 | loop and one more charset annotation at the end. */ | |
ff0dacd7 | 3458 | int *charbuf_end |
df80c7f0 | 3459 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 3); |
d311d28c | 3460 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 3461 | bool multibytep = coding->src_multibyte; |
4ed46869 | 3462 | /* Charsets invoked to graphic plane 0 and 1 respectively. */ |
df7492f9 KH |
3463 | int charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); |
3464 | int charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
134b9549 | 3465 | int charset_id_2, charset_id_3; |
df7492f9 KH |
3466 | struct charset *charset; |
3467 | int c; | |
e951386e | 3468 | struct composition_status *cmp_status = CODING_ISO_CMP_STATUS (coding); |
66ebf983 | 3469 | Lisp_Object attrs = CODING_ID_ATTRS (coding->id); |
d311d28c PE |
3470 | ptrdiff_t char_offset = coding->produced_char; |
3471 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 3472 | int last_id = charset_ascii; |
f10fe38f PE |
3473 | bool eol_dos |
3474 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 3475 | int byte_after_cr = -1; |
e951386e | 3476 | int i; |
df7492f9 | 3477 | |
df7492f9 | 3478 | setup_iso_safe_charsets (attrs); |
1b3b981b | 3479 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
b73bfc1c | 3480 | |
e951386e KH |
3481 | if (cmp_status->state != COMPOSING_NO) |
3482 | { | |
15cbd324 | 3483 | if (charbuf_end - charbuf < cmp_status->length) |
1088b922 | 3484 | emacs_abort (); |
e951386e KH |
3485 | for (i = 0; i < cmp_status->length; i++) |
3486 | *charbuf++ = cmp_status->carryover[i]; | |
3487 | coding->annotated = 1; | |
3488 | } | |
3489 | ||
b73bfc1c | 3490 | while (1) |
4ed46869 | 3491 | { |
cf299835 | 3492 | int c1, c2, c3; |
b73bfc1c KH |
3493 | |
3494 | src_base = src; | |
df7492f9 KH |
3495 | consumed_chars_base = consumed_chars; |
3496 | ||
3497 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
3498 | { |
3499 | if (byte_after_cr >= 0) | |
3500 | src_base--; | |
3501 | break; | |
3502 | } | |
df7492f9 | 3503 | |
119852e7 KH |
3504 | if (byte_after_cr >= 0) |
3505 | c1 = byte_after_cr, byte_after_cr = -1; | |
3506 | else | |
3507 | ONE_MORE_BYTE (c1); | |
065e3595 KH |
3508 | if (c1 < 0) |
3509 | goto invalid_code; | |
4ed46869 | 3510 | |
e951386e | 3511 | if (CODING_ISO_EXTSEGMENT_LEN (coding) > 0) |
4ed46869 | 3512 | { |
e951386e KH |
3513 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); |
3514 | char_offset++; | |
3515 | CODING_ISO_EXTSEGMENT_LEN (coding)--; | |
3516 | continue; | |
3517 | } | |
3518 | ||
3519 | if (CODING_ISO_EMBEDDED_UTF_8 (coding)) | |
3520 | { | |
3521 | if (c1 == ISO_CODE_ESC) | |
ec6d2bb8 | 3522 | { |
e951386e KH |
3523 | if (src + 1 >= src_end) |
3524 | goto no_more_source; | |
3525 | *charbuf++ = ISO_CODE_ESC; | |
3526 | char_offset++; | |
3527 | if (src[0] == '%' && src[1] == '@') | |
df7492f9 | 3528 | { |
e951386e KH |
3529 | src += 2; |
3530 | consumed_chars += 2; | |
3531 | char_offset += 2; | |
3532 | /* We are sure charbuf can contain two more chars. */ | |
3533 | *charbuf++ = '%'; | |
3534 | *charbuf++ = '@'; | |
3535 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
df7492f9 | 3536 | } |
4ed46869 | 3537 | } |
e951386e KH |
3538 | else |
3539 | { | |
3540 | *charbuf++ = ASCII_BYTE_P (c1) ? c1 : BYTE8_TO_CHAR (c1); | |
3541 | char_offset++; | |
3542 | } | |
3543 | continue; | |
3544 | } | |
3545 | ||
3546 | if ((cmp_status->state == COMPOSING_RULE | |
3547 | || cmp_status->state == COMPOSING_COMPONENT_RULE) | |
3548 | && c1 != ISO_CODE_ESC) | |
3549 | { | |
66ebf983 | 3550 | int rule; |
e951386e | 3551 | |
66ebf983 | 3552 | DECODE_COMPOSITION_RULE (rule); |
e951386e KH |
3553 | STORE_COMPOSITION_RULE (rule); |
3554 | continue; | |
3555 | } | |
3556 | ||
3557 | /* We produce at most one character. */ | |
3558 | switch (iso_code_class [c1]) | |
3559 | { | |
3560 | case ISO_0x20_or_0x7F: | |
df7492f9 KH |
3561 | if (charset_id_0 < 0 |
3562 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_0))) | |
781d7a48 KH |
3563 | /* This is SPACE or DEL. */ |
3564 | charset = CHARSET_FROM_ID (charset_ascii); | |
3565 | else | |
3566 | charset = CHARSET_FROM_ID (charset_id_0); | |
3567 | break; | |
4ed46869 KH |
3568 | |
3569 | case ISO_graphic_plane_0: | |
134b9549 KH |
3570 | if (charset_id_0 < 0) |
3571 | charset = CHARSET_FROM_ID (charset_ascii); | |
3572 | else | |
3573 | charset = CHARSET_FROM_ID (charset_id_0); | |
4ed46869 KH |
3574 | break; |
3575 | ||
3576 | case ISO_0xA0_or_0xFF: | |
df7492f9 KH |
3577 | if (charset_id_1 < 0 |
3578 | || ! CHARSET_ISO_CHARS_96 (CHARSET_FROM_ID (charset_id_1)) | |
3579 | || CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) | |
3580 | goto invalid_code; | |
4ed46869 KH |
3581 | /* This is a graphic character, we fall down ... */ |
3582 | ||
3583 | case ISO_graphic_plane_1: | |
df7492f9 KH |
3584 | if (charset_id_1 < 0) |
3585 | goto invalid_code; | |
3586 | charset = CHARSET_FROM_ID (charset_id_1); | |
4ed46869 KH |
3587 | break; |
3588 | ||
df7492f9 | 3589 | case ISO_control_0: |
2735d060 | 3590 | if (eol_dos && c1 == '\r') |
119852e7 | 3591 | ONE_MORE_BYTE (byte_after_cr); |
df7492f9 KH |
3592 | MAYBE_FINISH_COMPOSITION (); |
3593 | charset = CHARSET_FROM_ID (charset_ascii); | |
4ed46869 KH |
3594 | break; |
3595 | ||
df7492f9 | 3596 | case ISO_control_1: |
df7492f9 KH |
3597 | goto invalid_code; |
3598 | ||
4ed46869 | 3599 | case ISO_shift_out: |
df7492f9 KH |
3600 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3601 | || CODING_ISO_DESIGNATION (coding, 1) < 0) | |
3602 | goto invalid_code; | |
3603 | CODING_ISO_INVOCATION (coding, 0) = 1; | |
3604 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3605 | continue; |
4ed46869 KH |
3606 | |
3607 | case ISO_shift_in: | |
df7492f9 KH |
3608 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT)) |
3609 | goto invalid_code; | |
3610 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
3611 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3612 | continue; |
4ed46869 KH |
3613 | |
3614 | case ISO_single_shift_2_7: | |
a63dba42 KH |
3615 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS)) |
3616 | goto invalid_code; | |
4ed46869 | 3617 | case ISO_single_shift_2: |
df7492f9 KH |
3618 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3619 | goto invalid_code; | |
4ed46869 KH |
3620 | /* SS2 is handled as an escape sequence of ESC 'N' */ |
3621 | c1 = 'N'; | |
3622 | goto label_escape_sequence; | |
3623 | ||
3624 | case ISO_single_shift_3: | |
df7492f9 KH |
3625 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT)) |
3626 | goto invalid_code; | |
4ed46869 KH |
3627 | /* SS2 is handled as an escape sequence of ESC 'O' */ |
3628 | c1 = 'O'; | |
3629 | goto label_escape_sequence; | |
3630 | ||
3631 | case ISO_control_sequence_introducer: | |
3632 | /* CSI is handled as an escape sequence of ESC '[' ... */ | |
3633 | c1 = '['; | |
3634 | goto label_escape_sequence; | |
3635 | ||
3636 | case ISO_escape: | |
3637 | ONE_MORE_BYTE (c1); | |
3638 | label_escape_sequence: | |
df7492f9 | 3639 | /* Escape sequences handled here are invocation, |
4ed46869 KH |
3640 | designation, direction specification, and character |
3641 | composition specification. */ | |
3642 | switch (c1) | |
3643 | { | |
3644 | case '&': /* revision of following character set */ | |
3645 | ONE_MORE_BYTE (c1); | |
3646 | if (!(c1 >= '@' && c1 <= '~')) | |
df7492f9 | 3647 | goto invalid_code; |
4ed46869 KH |
3648 | ONE_MORE_BYTE (c1); |
3649 | if (c1 != ISO_CODE_ESC) | |
df7492f9 | 3650 | goto invalid_code; |
4ed46869 KH |
3651 | ONE_MORE_BYTE (c1); |
3652 | goto label_escape_sequence; | |
3653 | ||
3654 | case '$': /* designation of 2-byte character set */ | |
df7492f9 KH |
3655 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3656 | goto invalid_code; | |
134b9549 KH |
3657 | { |
3658 | int reg, chars96; | |
3659 | ||
3660 | ONE_MORE_BYTE (c1); | |
3661 | if (c1 >= '@' && c1 <= 'B') | |
3662 | { /* designation of JISX0208.1978, GB2312.1980, | |
88993dfd | 3663 | or JISX0208.1980 */ |
134b9549 KH |
3664 | reg = 0, chars96 = 0; |
3665 | } | |
3666 | else if (c1 >= 0x28 && c1 <= 0x2B) | |
3667 | { /* designation of DIMENSION2_CHARS94 character set */ | |
3668 | reg = c1 - 0x28, chars96 = 0; | |
3669 | ONE_MORE_BYTE (c1); | |
3670 | } | |
3671 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3672 | { /* designation of DIMENSION2_CHARS96 character set */ | |
3673 | reg = c1 - 0x2C, chars96 = 1; | |
3674 | ONE_MORE_BYTE (c1); | |
3675 | } | |
3676 | else | |
3677 | goto invalid_code; | |
3678 | DECODE_DESIGNATION (reg, 2, chars96, c1); | |
3679 | /* We must update these variables now. */ | |
3680 | if (reg == 0) | |
3681 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3682 | else if (reg == 1) | |
3683 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3684 | if (chars96 < 0) | |
3685 | goto invalid_code; | |
3686 | } | |
b73bfc1c | 3687 | continue; |
4ed46869 KH |
3688 | |
3689 | case 'n': /* invocation of locking-shift-2 */ | |
df7492f9 KH |
3690 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3691 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3692 | goto invalid_code; | |
3693 | CODING_ISO_INVOCATION (coding, 0) = 2; | |
3694 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3695 | continue; |
4ed46869 KH |
3696 | |
3697 | case 'o': /* invocation of locking-shift-3 */ | |
df7492f9 KH |
3698 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LOCKING_SHIFT) |
3699 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3700 | goto invalid_code; | |
3701 | CODING_ISO_INVOCATION (coding, 0) = 3; | |
3702 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
b73bfc1c | 3703 | continue; |
4ed46869 KH |
3704 | |
3705 | case 'N': /* invocation of single-shift-2 */ | |
df7492f9 KH |
3706 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3707 | || CODING_ISO_DESIGNATION (coding, 2) < 0) | |
3708 | goto invalid_code; | |
134b9549 KH |
3709 | charset_id_2 = CODING_ISO_DESIGNATION (coding, 2); |
3710 | if (charset_id_2 < 0) | |
3711 | charset = CHARSET_FROM_ID (charset_ascii); | |
3712 | else | |
3713 | charset = CHARSET_FROM_ID (charset_id_2); | |
b73bfc1c | 3714 | ONE_MORE_BYTE (c1); |
e7046a18 | 3715 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3716 | goto invalid_code; |
4ed46869 KH |
3717 | break; |
3718 | ||
3719 | case 'O': /* invocation of single-shift-3 */ | |
df7492f9 KH |
3720 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
3721 | || CODING_ISO_DESIGNATION (coding, 3) < 0) | |
3722 | goto invalid_code; | |
134b9549 KH |
3723 | charset_id_3 = CODING_ISO_DESIGNATION (coding, 3); |
3724 | if (charset_id_3 < 0) | |
3725 | charset = CHARSET_FROM_ID (charset_ascii); | |
3726 | else | |
3727 | charset = CHARSET_FROM_ID (charset_id_3); | |
b73bfc1c | 3728 | ONE_MORE_BYTE (c1); |
e7046a18 | 3729 | if (c1 < 0x20 || (c1 >= 0x80 && c1 < 0xA0)) |
df7492f9 | 3730 | goto invalid_code; |
4ed46869 KH |
3731 | break; |
3732 | ||
ec6d2bb8 | 3733 | case '0': case '2': case '3': case '4': /* start composition */ |
df7492f9 KH |
3734 | if (! (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK)) |
3735 | goto invalid_code; | |
e951386e KH |
3736 | if (last_id != charset_ascii) |
3737 | { | |
3738 | ADD_CHARSET_DATA (charbuf, char_offset- last_offset, last_id); | |
3739 | last_id = charset_ascii; | |
3740 | last_offset = char_offset; | |
3741 | } | |
ec6d2bb8 | 3742 | DECODE_COMPOSITION_START (c1); |
b73bfc1c | 3743 | continue; |
4ed46869 | 3744 | |
ec6d2bb8 | 3745 | case '1': /* end composition */ |
e951386e | 3746 | if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3747 | goto invalid_code; |
3748 | DECODE_COMPOSITION_END (); | |
b73bfc1c | 3749 | continue; |
4ed46869 KH |
3750 | |
3751 | case '[': /* specification of direction */ | |
de59072a | 3752 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DIRECTION)) |
df7492f9 | 3753 | goto invalid_code; |
4ed46869 | 3754 | /* For the moment, nested direction is not supported. |
d46c5b12 | 3755 | So, `coding->mode & CODING_MODE_DIRECTION' zero means |
ad1746f5 | 3756 | left-to-right, and nonzero means right-to-left. */ |
4ed46869 KH |
3757 | ONE_MORE_BYTE (c1); |
3758 | switch (c1) | |
3759 | { | |
3760 | case ']': /* end of the current direction */ | |
d46c5b12 | 3761 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 KH |
3762 | |
3763 | case '0': /* end of the current direction */ | |
3764 | case '1': /* start of left-to-right direction */ | |
3765 | ONE_MORE_BYTE (c1); | |
3766 | if (c1 == ']') | |
d46c5b12 | 3767 | coding->mode &= ~CODING_MODE_DIRECTION; |
4ed46869 | 3768 | else |
df7492f9 | 3769 | goto invalid_code; |
4ed46869 KH |
3770 | break; |
3771 | ||
3772 | case '2': /* start of right-to-left direction */ | |
3773 | ONE_MORE_BYTE (c1); | |
3774 | if (c1 == ']') | |
d46c5b12 | 3775 | coding->mode |= CODING_MODE_DIRECTION; |
4ed46869 | 3776 | else |
df7492f9 | 3777 | goto invalid_code; |
4ed46869 KH |
3778 | break; |
3779 | ||
3780 | default: | |
df7492f9 | 3781 | goto invalid_code; |
4ed46869 | 3782 | } |
b73bfc1c | 3783 | continue; |
4ed46869 | 3784 | |
103e0180 | 3785 | case '%': |
103e0180 KH |
3786 | ONE_MORE_BYTE (c1); |
3787 | if (c1 == '/') | |
3788 | { | |
3789 | /* CTEXT extended segment: | |
3790 | ESC % / [0-4] M L --ENCODING-NAME-- \002 --BYTES-- | |
3791 | We keep these bytes as is for the moment. | |
3792 | They may be decoded by post-read-conversion. */ | |
3793 | int dim, M, L; | |
4776e638 | 3794 | int size; |
8f924df7 | 3795 | |
103e0180 | 3796 | ONE_MORE_BYTE (dim); |
7a84eee5 | 3797 | if (dim < '0' || dim > '4') |
e951386e | 3798 | goto invalid_code; |
103e0180 | 3799 | ONE_MORE_BYTE (M); |
e951386e KH |
3800 | if (M < 128) |
3801 | goto invalid_code; | |
103e0180 | 3802 | ONE_MORE_BYTE (L); |
e951386e KH |
3803 | if (L < 128) |
3804 | goto invalid_code; | |
103e0180 | 3805 | size = ((M - 128) * 128) + (L - 128); |
e951386e | 3806 | if (charbuf + 6 > charbuf_end) |
4776e638 KH |
3807 | goto break_loop; |
3808 | *charbuf++ = ISO_CODE_ESC; | |
3809 | *charbuf++ = '%'; | |
3810 | *charbuf++ = '/'; | |
3811 | *charbuf++ = dim; | |
3812 | *charbuf++ = BYTE8_TO_CHAR (M); | |
3813 | *charbuf++ = BYTE8_TO_CHAR (L); | |
e951386e | 3814 | CODING_ISO_EXTSEGMENT_LEN (coding) = size; |
103e0180 KH |
3815 | } |
3816 | else if (c1 == 'G') | |
3817 | { | |
103e0180 KH |
3818 | /* XFree86 extension for embedding UTF-8 in CTEXT: |
3819 | ESC % G --UTF-8-BYTES-- ESC % @ | |
3820 | We keep these bytes as is for the moment. | |
3821 | They may be decoded by post-read-conversion. */ | |
e951386e | 3822 | if (charbuf + 3 > charbuf_end) |
4776e638 | 3823 | goto break_loop; |
e951386e KH |
3824 | *charbuf++ = ISO_CODE_ESC; |
3825 | *charbuf++ = '%'; | |
3826 | *charbuf++ = 'G'; | |
3827 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 1; | |
103e0180 KH |
3828 | } |
3829 | else | |
4776e638 | 3830 | goto invalid_code; |
103e0180 | 3831 | continue; |
4776e638 | 3832 | break; |
103e0180 | 3833 | |
4ed46869 | 3834 | default: |
df7492f9 KH |
3835 | if (! (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATION)) |
3836 | goto invalid_code; | |
134b9549 KH |
3837 | { |
3838 | int reg, chars96; | |
3839 | ||
3840 | if (c1 >= 0x28 && c1 <= 0x2B) | |
3841 | { /* designation of DIMENSION1_CHARS94 character set */ | |
3842 | reg = c1 - 0x28, chars96 = 0; | |
3843 | ONE_MORE_BYTE (c1); | |
3844 | } | |
3845 | else if (c1 >= 0x2C && c1 <= 0x2F) | |
3846 | { /* designation of DIMENSION1_CHARS96 character set */ | |
3847 | reg = c1 - 0x2C, chars96 = 1; | |
3848 | ONE_MORE_BYTE (c1); | |
3849 | } | |
3850 | else | |
3851 | goto invalid_code; | |
3852 | DECODE_DESIGNATION (reg, 1, chars96, c1); | |
3853 | /* We must update these variables now. */ | |
3854 | if (reg == 0) | |
3855 | charset_id_0 = CODING_ISO_INVOKED_CHARSET (coding, 0); | |
3856 | else if (reg == 1) | |
3857 | charset_id_1 = CODING_ISO_INVOKED_CHARSET (coding, 1); | |
3858 | if (chars96 < 0) | |
3859 | goto invalid_code; | |
3860 | } | |
b73bfc1c | 3861 | continue; |
4ed46869 | 3862 | } |
413bb2db PE |
3863 | break; |
3864 | ||
3865 | default: | |
1088b922 | 3866 | emacs_abort (); |
b73bfc1c | 3867 | } |
4ed46869 | 3868 | |
e951386e KH |
3869 | if (cmp_status->state == COMPOSING_NO |
3870 | && charset->id != charset_ascii | |
ff0dacd7 KH |
3871 | && last_id != charset->id) |
3872 | { | |
3873 | if (last_id != charset_ascii) | |
69a80ea3 | 3874 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
ff0dacd7 KH |
3875 | last_id = charset->id; |
3876 | last_offset = char_offset; | |
3877 | } | |
3878 | ||
b73bfc1c | 3879 | /* Now we know CHARSET and 1st position code C1 of a character. |
cf299835 KH |
3880 | Produce a decoded character while getting 2nd and 3rd |
3881 | position codes C2, C3 if necessary. */ | |
df7492f9 | 3882 | if (CHARSET_DIMENSION (charset) > 1) |
b73bfc1c KH |
3883 | { |
3884 | ONE_MORE_BYTE (c2); | |
cf299835 KH |
3885 | if (c2 < 0x20 || (c2 >= 0x80 && c2 < 0xA0) |
3886 | || ((c1 & 0x80) != (c2 & 0x80))) | |
b73bfc1c | 3887 | /* C2 is not in a valid range. */ |
df7492f9 | 3888 | goto invalid_code; |
cf299835 KH |
3889 | if (CHARSET_DIMENSION (charset) == 2) |
3890 | c1 = (c1 << 8) | c2; | |
3891 | else | |
df7492f9 | 3892 | { |
cf299835 KH |
3893 | ONE_MORE_BYTE (c3); |
3894 | if (c3 < 0x20 || (c3 >= 0x80 && c3 < 0xA0) | |
3895 | || ((c1 & 0x80) != (c3 & 0x80))) | |
3896 | /* C3 is not in a valid range. */ | |
df7492f9 | 3897 | goto invalid_code; |
cf299835 | 3898 | c1 = (c1 << 16) | (c2 << 8) | c2; |
df7492f9 KH |
3899 | } |
3900 | } | |
cf299835 | 3901 | c1 &= 0x7F7F7F; |
df7492f9 KH |
3902 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c1, c); |
3903 | if (c < 0) | |
3904 | { | |
3905 | MAYBE_FINISH_COMPOSITION (); | |
3906 | for (; src_base < src; src_base++, char_offset++) | |
3907 | { | |
3908 | if (ASCII_BYTE_P (*src_base)) | |
3909 | *charbuf++ = *src_base; | |
3910 | else | |
3911 | *charbuf++ = BYTE8_TO_CHAR (*src_base); | |
3912 | } | |
3913 | } | |
e951386e | 3914 | else if (cmp_status->state == COMPOSING_NO) |
df7492f9 KH |
3915 | { |
3916 | *charbuf++ = c; | |
3917 | char_offset++; | |
4ed46869 | 3918 | } |
e951386e KH |
3919 | else if ((cmp_status->state == COMPOSING_CHAR |
3920 | ? cmp_status->nchars | |
3921 | : cmp_status->ncomps) | |
3922 | >= MAX_COMPOSITION_COMPONENTS) | |
781d7a48 | 3923 | { |
e951386e KH |
3924 | /* Too long composition. */ |
3925 | MAYBE_FINISH_COMPOSITION (); | |
3926 | *charbuf++ = c; | |
3927 | char_offset++; | |
4ed46869 | 3928 | } |
e951386e KH |
3929 | else |
3930 | STORE_COMPOSITION_CHAR (c); | |
4ed46869 KH |
3931 | continue; |
3932 | ||
df7492f9 KH |
3933 | invalid_code: |
3934 | MAYBE_FINISH_COMPOSITION (); | |
4ed46869 | 3935 | src = src_base; |
df7492f9 KH |
3936 | consumed_chars = consumed_chars_base; |
3937 | ONE_MORE_BYTE (c); | |
065e3595 | 3938 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 3939 | char_offset++; |
df7492f9 | 3940 | coding->errors++; |
4776e638 KH |
3941 | continue; |
3942 | ||
3943 | break_loop: | |
3944 | break; | |
4ed46869 | 3945 | } |
fb88bf2d | 3946 | |
df7492f9 | 3947 | no_more_source: |
e951386e KH |
3948 | if (cmp_status->state != COMPOSING_NO) |
3949 | { | |
3950 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
3951 | MAYBE_FINISH_COMPOSITION (); | |
3952 | else | |
3953 | { | |
3954 | charbuf -= cmp_status->length; | |
3955 | for (i = 0; i < cmp_status->length; i++) | |
3956 | cmp_status->carryover[i] = charbuf[i]; | |
3957 | } | |
3958 | } | |
3959 | else if (last_id != charset_ascii) | |
69a80ea3 | 3960 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
3961 | coding->consumed_char += consumed_chars_base; |
3962 | coding->consumed = src_base - coding->source; | |
3963 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
3964 | } |
3965 | ||
b73bfc1c | 3966 | |
f4dee582 | 3967 | /* ISO2022 encoding stuff. */ |
4ed46869 KH |
3968 | |
3969 | /* | |
f4dee582 | 3970 | It is not enough to say just "ISO2022" on encoding, we have to |
df7492f9 | 3971 | specify more details. In Emacs, each coding system of ISO2022 |
4ed46869 | 3972 | variant has the following specifications: |
df7492f9 | 3973 | 1. Initial designation to G0 thru G3. |
4ed46869 KH |
3974 | 2. Allows short-form designation? |
3975 | 3. ASCII should be designated to G0 before control characters? | |
3976 | 4. ASCII should be designated to G0 at end of line? | |
3977 | 5. 7-bit environment or 8-bit environment? | |
3978 | 6. Use locking-shift? | |
3979 | 7. Use Single-shift? | |
3980 | And the following two are only for Japanese: | |
3981 | 8. Use ASCII in place of JIS0201-1976-Roman? | |
3982 | 9. Use JISX0208-1983 in place of JISX0208-1978? | |
df7492f9 KH |
3983 | These specifications are encoded in CODING_ISO_FLAGS (coding) as flag bits |
3984 | defined by macros CODING_ISO_FLAG_XXX. See `coding.h' for more | |
f4dee582 | 3985 | details. |
4ed46869 KH |
3986 | */ |
3987 | ||
3988 | /* Produce codes (escape sequence) for designating CHARSET to graphic | |
b73bfc1c KH |
3989 | register REG at DST, and increment DST. If <final-char> of CHARSET is |
3990 | '@', 'A', or 'B' and the coding system CODING allows, produce | |
3991 | designation sequence of short-form. */ | |
4ed46869 KH |
3992 | |
3993 | #define ENCODE_DESIGNATION(charset, reg, coding) \ | |
3994 | do { \ | |
df7492f9 | 3995 | unsigned char final_char = CHARSET_ISO_FINAL (charset); \ |
675e2c69 DN |
3996 | const char *intermediate_char_94 = "()*+"; \ |
3997 | const char *intermediate_char_96 = ",-./"; \ | |
df7492f9 | 3998 | int revision = -1; \ |
df7492f9 KH |
3999 | \ |
4000 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_REVISION) \ | |
c197f191 | 4001 | revision = CHARSET_ISO_REVISION (charset); \ |
df7492f9 KH |
4002 | \ |
4003 | if (revision >= 0) \ | |
70c22245 | 4004 | { \ |
df7492f9 KH |
4005 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, '&'); \ |
4006 | EMIT_ONE_BYTE ('@' + revision); \ | |
4ed46869 | 4007 | } \ |
df7492f9 | 4008 | EMIT_ONE_ASCII_BYTE (ISO_CODE_ESC); \ |
4ed46869 KH |
4009 | if (CHARSET_DIMENSION (charset) == 1) \ |
4010 | { \ | |
2735d060 | 4011 | int b; \ |
df7492f9 | 4012 | if (! CHARSET_ISO_CHARS_96 (charset)) \ |
2735d060 | 4013 | b = intermediate_char_94[reg]; \ |
4ed46869 | 4014 | else \ |
2735d060 PE |
4015 | b = intermediate_char_96[reg]; \ |
4016 | EMIT_ONE_ASCII_BYTE (b); \ | |
4ed46869 KH |
4017 | } \ |
4018 | else \ | |
4019 | { \ | |
df7492f9 KH |
4020 | EMIT_ONE_ASCII_BYTE ('$'); \ |
4021 | if (! CHARSET_ISO_CHARS_96 (charset)) \ | |
4ed46869 | 4022 | { \ |
df7492f9 | 4023 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_LONG_FORM \ |
b73bfc1c KH |
4024 | || reg != 0 \ |
4025 | || final_char < '@' || final_char > 'B') \ | |
df7492f9 | 4026 | EMIT_ONE_ASCII_BYTE (intermediate_char_94[reg]); \ |
4ed46869 KH |
4027 | } \ |
4028 | else \ | |
df7492f9 | 4029 | EMIT_ONE_ASCII_BYTE (intermediate_char_96[reg]); \ |
4ed46869 | 4030 | } \ |
df7492f9 KH |
4031 | EMIT_ONE_ASCII_BYTE (final_char); \ |
4032 | \ | |
4033 | CODING_ISO_DESIGNATION (coding, reg) = CHARSET_ID (charset); \ | |
4ed46869 KH |
4034 | } while (0) |
4035 | ||
df7492f9 | 4036 | |
4ed46869 KH |
4037 | /* The following two macros produce codes (control character or escape |
4038 | sequence) for ISO2022 single-shift functions (single-shift-2 and | |
4039 | single-shift-3). */ | |
4040 | ||
df7492f9 KH |
4041 | #define ENCODE_SINGLE_SHIFT_2 \ |
4042 | do { \ | |
4043 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4044 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'N'); \ | |
4045 | else \ | |
4046 | EMIT_ONE_BYTE (ISO_CODE_SS2); \ | |
4047 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4048 | } while (0) |
4049 | ||
df7492f9 KH |
4050 | |
4051 | #define ENCODE_SINGLE_SHIFT_3 \ | |
4052 | do { \ | |
4053 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ | |
4054 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'O'); \ | |
4055 | else \ | |
4056 | EMIT_ONE_BYTE (ISO_CODE_SS3); \ | |
4057 | CODING_ISO_SINGLE_SHIFTING (coding) = 1; \ | |
4ed46869 KH |
4058 | } while (0) |
4059 | ||
df7492f9 | 4060 | |
4ed46869 KH |
4061 | /* The following four macros produce codes (control character or |
4062 | escape sequence) for ISO2022 locking-shift functions (shift-in, | |
4063 | shift-out, locking-shift-2, and locking-shift-3). */ | |
4064 | ||
df7492f9 KH |
4065 | #define ENCODE_SHIFT_IN \ |
4066 | do { \ | |
4067 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SI); \ | |
4068 | CODING_ISO_INVOCATION (coding, 0) = 0; \ | |
4ed46869 KH |
4069 | } while (0) |
4070 | ||
df7492f9 KH |
4071 | |
4072 | #define ENCODE_SHIFT_OUT \ | |
4073 | do { \ | |
4074 | EMIT_ONE_ASCII_BYTE (ISO_CODE_SO); \ | |
4075 | CODING_ISO_INVOCATION (coding, 0) = 1; \ | |
4ed46869 KH |
4076 | } while (0) |
4077 | ||
df7492f9 KH |
4078 | |
4079 | #define ENCODE_LOCKING_SHIFT_2 \ | |
4080 | do { \ | |
4081 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4082 | CODING_ISO_INVOCATION (coding, 0) = 2; \ | |
4ed46869 KH |
4083 | } while (0) |
4084 | ||
df7492f9 KH |
4085 | |
4086 | #define ENCODE_LOCKING_SHIFT_3 \ | |
4087 | do { \ | |
4088 | EMIT_TWO_ASCII_BYTES (ISO_CODE_ESC, 'n'); \ | |
4089 | CODING_ISO_INVOCATION (coding, 0) = 3; \ | |
4ed46869 KH |
4090 | } while (0) |
4091 | ||
df7492f9 | 4092 | |
f4dee582 RS |
4093 | /* Produce codes for a DIMENSION1 character whose character set is |
4094 | CHARSET and whose position-code is C1. Designation and invocation | |
4ed46869 KH |
4095 | sequences are also produced in advance if necessary. */ |
4096 | ||
6e85d753 KH |
4097 | #define ENCODE_ISO_CHARACTER_DIMENSION1(charset, c1) \ |
4098 | do { \ | |
df7492f9 | 4099 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4100 | \ |
4101 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_ROMAN) \ | |
4102 | && id == charset_ascii) \ | |
4103 | { \ | |
4104 | id = charset_jisx0201_roman; \ | |
4105 | charset = CHARSET_FROM_ID (id); \ | |
4106 | } \ | |
4107 | \ | |
df7492f9 | 4108 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4109 | { \ |
df7492f9 KH |
4110 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4111 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ | |
6e85d753 | 4112 | else \ |
df7492f9 KH |
4113 | EMIT_ONE_BYTE (c1 | 0x80); \ |
4114 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4115 | break; \ |
4116 | } \ | |
df7492f9 | 4117 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4118 | { \ |
df7492f9 | 4119 | EMIT_ONE_ASCII_BYTE (c1 & 0x7F); \ |
6e85d753 KH |
4120 | break; \ |
4121 | } \ | |
df7492f9 | 4122 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4123 | { \ |
df7492f9 | 4124 | EMIT_ONE_BYTE (c1 | 0x80); \ |
6e85d753 KH |
4125 | break; \ |
4126 | } \ | |
6e85d753 KH |
4127 | else \ |
4128 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4129 | must invoke it, or, at first, designate it to some graphic \ | |
4130 | register. Then repeat the loop to actually produce the \ | |
4131 | character. */ \ | |
df7492f9 KH |
4132 | dst = encode_invocation_designation (charset, coding, dst, \ |
4133 | &produced_chars); \ | |
4ed46869 KH |
4134 | } while (1) |
4135 | ||
df7492f9 | 4136 | |
f4dee582 RS |
4137 | /* Produce codes for a DIMENSION2 character whose character set is |
4138 | CHARSET and whose position-codes are C1 and C2. Designation and | |
4ed46869 KH |
4139 | invocation codes are also produced in advance if necessary. */ |
4140 | ||
6e85d753 KH |
4141 | #define ENCODE_ISO_CHARACTER_DIMENSION2(charset, c1, c2) \ |
4142 | do { \ | |
df7492f9 | 4143 | int id = CHARSET_ID (charset); \ |
bf16eb23 KH |
4144 | \ |
4145 | if ((CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_USE_OLDJIS) \ | |
4146 | && id == charset_jisx0208) \ | |
4147 | { \ | |
4148 | id = charset_jisx0208_1978; \ | |
4149 | charset = CHARSET_FROM_ID (id); \ | |
4150 | } \ | |
4151 | \ | |
df7492f9 | 4152 | if (CODING_ISO_SINGLE_SHIFTING (coding)) \ |
6e85d753 | 4153 | { \ |
df7492f9 KH |
4154 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SEVEN_BITS) \ |
4155 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ | |
6e85d753 | 4156 | else \ |
df7492f9 KH |
4157 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
4158 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; \ | |
6e85d753 KH |
4159 | break; \ |
4160 | } \ | |
df7492f9 | 4161 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 0)) \ |
6e85d753 | 4162 | { \ |
df7492f9 | 4163 | EMIT_TWO_ASCII_BYTES ((c1) & 0x7F, (c2) & 0x7F); \ |
6e85d753 KH |
4164 | break; \ |
4165 | } \ | |
df7492f9 | 4166 | else if (id == CODING_ISO_INVOKED_CHARSET (coding, 1)) \ |
6e85d753 | 4167 | { \ |
df7492f9 | 4168 | EMIT_TWO_BYTES ((c1) | 0x80, (c2) | 0x80); \ |
6e85d753 KH |
4169 | break; \ |
4170 | } \ | |
6e85d753 KH |
4171 | else \ |
4172 | /* Since CHARSET is not yet invoked to any graphic planes, we \ | |
4173 | must invoke it, or, at first, designate it to some graphic \ | |
4174 | register. Then repeat the loop to actually produce the \ | |
4175 | character. */ \ | |
df7492f9 KH |
4176 | dst = encode_invocation_designation (charset, coding, dst, \ |
4177 | &produced_chars); \ | |
4ed46869 KH |
4178 | } while (1) |
4179 | ||
05e6f5dc | 4180 | |
df7492f9 KH |
4181 | #define ENCODE_ISO_CHARACTER(charset, c) \ |
4182 | do { \ | |
8f50130c | 4183 | unsigned code; \ |
5eb05ea3 | 4184 | CODING_ENCODE_CHAR (coding, dst, dst_end, (charset), (c), code); \ |
df7492f9 KH |
4185 | \ |
4186 | if (CHARSET_DIMENSION (charset) == 1) \ | |
4187 | ENCODE_ISO_CHARACTER_DIMENSION1 ((charset), code); \ | |
4188 | else \ | |
4189 | ENCODE_ISO_CHARACTER_DIMENSION2 ((charset), code >> 8, code & 0xFF); \ | |
84fbb8a0 | 4190 | } while (0) |
bdd9fb48 | 4191 | |
05e6f5dc | 4192 | |
4ed46869 | 4193 | /* Produce designation and invocation codes at a place pointed by DST |
df7492f9 | 4194 | to use CHARSET. The element `spec.iso_2022' of *CODING is updated. |
4ed46869 KH |
4195 | Return new DST. */ |
4196 | ||
e2f1bab9 | 4197 | static unsigned char * |
cf84bb53 JB |
4198 | encode_invocation_designation (struct charset *charset, |
4199 | struct coding_system *coding, | |
d311d28c | 4200 | unsigned char *dst, ptrdiff_t *p_nchars) |
4ed46869 | 4201 | { |
f10fe38f | 4202 | bool multibytep = coding->dst_multibyte; |
d311d28c | 4203 | ptrdiff_t produced_chars = *p_nchars; |
4ed46869 | 4204 | int reg; /* graphic register number */ |
df7492f9 | 4205 | int id = CHARSET_ID (charset); |
4ed46869 KH |
4206 | |
4207 | /* At first, check designations. */ | |
4208 | for (reg = 0; reg < 4; reg++) | |
df7492f9 | 4209 | if (id == CODING_ISO_DESIGNATION (coding, reg)) |
4ed46869 KH |
4210 | break; |
4211 | ||
4212 | if (reg >= 4) | |
4213 | { | |
4214 | /* CHARSET is not yet designated to any graphic registers. */ | |
4215 | /* At first check the requested designation. */ | |
df7492f9 KH |
4216 | reg = CODING_ISO_REQUEST (coding, id); |
4217 | if (reg < 0) | |
1ba9e4ab KH |
4218 | /* Since CHARSET requests no special designation, designate it |
4219 | to graphic register 0. */ | |
4ed46869 KH |
4220 | reg = 0; |
4221 | ||
4222 | ENCODE_DESIGNATION (charset, reg, coding); | |
4223 | } | |
4224 | ||
df7492f9 KH |
4225 | if (CODING_ISO_INVOCATION (coding, 0) != reg |
4226 | && CODING_ISO_INVOCATION (coding, 1) != reg) | |
4ed46869 KH |
4227 | { |
4228 | /* Since the graphic register REG is not invoked to any graphic | |
4229 | planes, invoke it to graphic plane 0. */ | |
4230 | switch (reg) | |
4231 | { | |
4232 | case 0: /* graphic register 0 */ | |
4233 | ENCODE_SHIFT_IN; | |
4234 | break; | |
4235 | ||
4236 | case 1: /* graphic register 1 */ | |
4237 | ENCODE_SHIFT_OUT; | |
4238 | break; | |
4239 | ||
4240 | case 2: /* graphic register 2 */ | |
df7492f9 | 4241 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4242 | ENCODE_SINGLE_SHIFT_2; |
4243 | else | |
4244 | ENCODE_LOCKING_SHIFT_2; | |
4245 | break; | |
4246 | ||
4247 | case 3: /* graphic register 3 */ | |
df7492f9 | 4248 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_SINGLE_SHIFT) |
4ed46869 KH |
4249 | ENCODE_SINGLE_SHIFT_3; |
4250 | else | |
4251 | ENCODE_LOCKING_SHIFT_3; | |
4252 | break; | |
4253 | } | |
4254 | } | |
b73bfc1c | 4255 | |
df7492f9 | 4256 | *p_nchars = produced_chars; |
4ed46869 KH |
4257 | return dst; |
4258 | } | |
4259 | ||
4ed46869 KH |
4260 | |
4261 | /* Produce codes for designation and invocation to reset the graphic | |
4262 | planes and registers to initial state. */ | |
df7492f9 KH |
4263 | #define ENCODE_RESET_PLANE_AND_REGISTER() \ |
4264 | do { \ | |
4265 | int reg; \ | |
4266 | struct charset *charset; \ | |
4267 | \ | |
4268 | if (CODING_ISO_INVOCATION (coding, 0) != 0) \ | |
4269 | ENCODE_SHIFT_IN; \ | |
4270 | for (reg = 0; reg < 4; reg++) \ | |
4271 | if (CODING_ISO_INITIAL (coding, reg) >= 0 \ | |
4272 | && (CODING_ISO_DESIGNATION (coding, reg) \ | |
4273 | != CODING_ISO_INITIAL (coding, reg))) \ | |
4274 | { \ | |
4275 | charset = CHARSET_FROM_ID (CODING_ISO_INITIAL (coding, reg)); \ | |
4276 | ENCODE_DESIGNATION (charset, reg, coding); \ | |
4277 | } \ | |
4ed46869 KH |
4278 | } while (0) |
4279 | ||
df7492f9 | 4280 | |
bdd9fb48 | 4281 | /* Produce designation sequences of charsets in the line started from |
5eb05ea3 KH |
4282 | CHARBUF to a place pointed by DST, and return the number of |
4283 | produced bytes. DST should not directly point a buffer text area | |
4284 | which may be relocated by char_charset call. | |
bdd9fb48 KH |
4285 | |
4286 | If the current block ends before any end-of-line, we may fail to | |
d46c5b12 KH |
4287 | find all the necessary designations. */ |
4288 | ||
6e6c82a4 | 4289 | static ptrdiff_t |
5eb05ea3 KH |
4290 | encode_designation_at_bol (struct coding_system *coding, |
4291 | int *charbuf, int *charbuf_end, | |
461c2ab9 | 4292 | unsigned char *dst) |
e0e989f6 | 4293 | { |
75a3b399 | 4294 | unsigned char *orig = dst; |
df7492f9 | 4295 | struct charset *charset; |
bdd9fb48 KH |
4296 | /* Table of charsets to be designated to each graphic register. */ |
4297 | int r[4]; | |
df7492f9 | 4298 | int c, found = 0, reg; |
d311d28c | 4299 | ptrdiff_t produced_chars = 0; |
f10fe38f | 4300 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4301 | Lisp_Object attrs; |
4302 | Lisp_Object charset_list; | |
4303 | ||
4304 | attrs = CODING_ID_ATTRS (coding->id); | |
4305 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
4306 | if (EQ (charset_list, Qiso_2022)) | |
4307 | charset_list = Viso_2022_charset_list; | |
bdd9fb48 KH |
4308 | |
4309 | for (reg = 0; reg < 4; reg++) | |
4310 | r[reg] = -1; | |
4311 | ||
5eb05ea3 | 4312 | while (charbuf < charbuf_end && found < 4) |
e0e989f6 | 4313 | { |
df7492f9 KH |
4314 | int id; |
4315 | ||
4316 | c = *charbuf++; | |
b73bfc1c KH |
4317 | if (c == '\n') |
4318 | break; | |
df7492f9 KH |
4319 | charset = char_charset (c, charset_list, NULL); |
4320 | id = CHARSET_ID (charset); | |
4321 | reg = CODING_ISO_REQUEST (coding, id); | |
4322 | if (reg >= 0 && r[reg] < 0) | |
bdd9fb48 KH |
4323 | { |
4324 | found++; | |
df7492f9 | 4325 | r[reg] = id; |
bdd9fb48 | 4326 | } |
bdd9fb48 KH |
4327 | } |
4328 | ||
4329 | if (found) | |
4330 | { | |
4331 | for (reg = 0; reg < 4; reg++) | |
4332 | if (r[reg] >= 0 | |
df7492f9 KH |
4333 | && CODING_ISO_DESIGNATION (coding, reg) != r[reg]) |
4334 | ENCODE_DESIGNATION (CHARSET_FROM_ID (r[reg]), reg, coding); | |
e0e989f6 | 4335 | } |
b73bfc1c | 4336 | |
5eb05ea3 | 4337 | return dst - orig; |
e0e989f6 KH |
4338 | } |
4339 | ||
4ed46869 KH |
4340 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". */ |
4341 | ||
f10fe38f | 4342 | static bool |
971de7fb | 4343 | encode_coding_iso_2022 (struct coding_system *coding) |
4ed46869 | 4344 | { |
f10fe38f | 4345 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4346 | int *charbuf = coding->charbuf; |
4347 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4348 | unsigned char *dst = coding->destination + coding->produced; | |
4349 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4350 | int safe_room = 16; | |
f10fe38f | 4351 | bool bol_designation |
df7492f9 KH |
4352 | = (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_DESIGNATE_AT_BOL |
4353 | && CODING_ISO_BOL (coding)); | |
d311d28c | 4354 | ptrdiff_t produced_chars = 0; |
df7492f9 | 4355 | Lisp_Object attrs, eol_type, charset_list; |
f10fe38f | 4356 | bool ascii_compatible; |
b73bfc1c | 4357 | int c; |
ff0dacd7 | 4358 | int preferred_charset_id = -1; |
05e6f5dc | 4359 | |
24a73b0a | 4360 | CODING_GET_INFO (coding, attrs, charset_list); |
0a9564cb | 4361 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
24a73b0a KH |
4362 | if (VECTORP (eol_type)) |
4363 | eol_type = Qunix; | |
4364 | ||
004068e4 | 4365 | setup_iso_safe_charsets (attrs); |
ff0dacd7 | 4366 | /* Charset list may have been changed. */ |
287c57d7 | 4367 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); |
1b3b981b | 4368 | coding->safe_charsets = SDATA (CODING_ATTR_SAFE_CHARSETS (attrs)); |
0eecad43 | 4369 | |
a552b35a KH |
4370 | ascii_compatible |
4371 | = (! NILP (CODING_ATTR_ASCII_COMPAT (attrs)) | |
4372 | && ! (CODING_ISO_FLAGS (coding) & (CODING_ISO_FLAG_DESIGNATION | |
4373 | | CODING_ISO_FLAG_LOCKING_SHIFT))); | |
bdd9fb48 | 4374 | |
df7492f9 | 4375 | while (charbuf < charbuf_end) |
4ed46869 | 4376 | { |
df7492f9 | 4377 | ASSURE_DESTINATION (safe_room); |
b73bfc1c | 4378 | |
df7492f9 | 4379 | if (bol_designation) |
b73bfc1c | 4380 | { |
bdd9fb48 | 4381 | /* We have to produce designation sequences if any now. */ |
5eb05ea3 KH |
4382 | unsigned char desig_buf[16]; |
4383 | int nbytes; | |
8f50130c | 4384 | ptrdiff_t offset; |
5eb05ea3 KH |
4385 | |
4386 | charset_map_loaded = 0; | |
4387 | nbytes = encode_designation_at_bol (coding, charbuf, charbuf_end, | |
4388 | desig_buf); | |
4389 | if (charset_map_loaded | |
c1892f11 | 4390 | && (offset = coding_change_destination (coding))) |
5eb05ea3 KH |
4391 | { |
4392 | dst += offset; | |
4393 | dst_end += offset; | |
4394 | } | |
4395 | memcpy (dst, desig_buf, nbytes); | |
4396 | dst += nbytes; | |
df7492f9 | 4397 | /* We are sure that designation sequences are all ASCII bytes. */ |
5eb05ea3 KH |
4398 | produced_chars += nbytes; |
4399 | bol_designation = 0; | |
4400 | ASSURE_DESTINATION (safe_room); | |
e0e989f6 KH |
4401 | } |
4402 | ||
df7492f9 | 4403 | c = *charbuf++; |
ec6d2bb8 | 4404 | |
ff0dacd7 KH |
4405 | if (c < 0) |
4406 | { | |
4407 | /* Handle an annotation. */ | |
4408 | switch (*charbuf) | |
ec6d2bb8 | 4409 | { |
ff0dacd7 KH |
4410 | case CODING_ANNOTATE_COMPOSITION_MASK: |
4411 | /* Not yet implemented. */ | |
4412 | break; | |
4413 | case CODING_ANNOTATE_CHARSET_MASK: | |
cf7dfdf5 | 4414 | preferred_charset_id = charbuf[2]; |
ff0dacd7 KH |
4415 | if (preferred_charset_id >= 0 |
4416 | && NILP (Fmemq (make_number (preferred_charset_id), | |
4417 | charset_list))) | |
4418 | preferred_charset_id = -1; | |
4419 | break; | |
4420 | default: | |
1088b922 | 4421 | emacs_abort (); |
4ed46869 | 4422 | } |
ff0dacd7 KH |
4423 | charbuf += -c - 1; |
4424 | continue; | |
4ed46869 | 4425 | } |
ec6d2bb8 | 4426 | |
b73bfc1c KH |
4427 | /* Now encode the character C. */ |
4428 | if (c < 0x20 || c == 0x7F) | |
4429 | { | |
df7492f9 KH |
4430 | if (c == '\n' |
4431 | || (c == '\r' && EQ (eol_type, Qmac))) | |
19a8d9e0 | 4432 | { |
df7492f9 KH |
4433 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) |
4434 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4435 | if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_INIT_AT_BOL) | |
b73bfc1c | 4436 | { |
df7492f9 KH |
4437 | int i; |
4438 | ||
4439 | for (i = 0; i < 4; i++) | |
4440 | CODING_ISO_DESIGNATION (coding, i) | |
4441 | = CODING_ISO_INITIAL (coding, i); | |
b73bfc1c | 4442 | } |
f10fe38f PE |
4443 | bol_designation = ((CODING_ISO_FLAGS (coding) |
4444 | & CODING_ISO_FLAG_DESIGNATE_AT_BOL) | |
4445 | != 0); | |
19a8d9e0 | 4446 | } |
df7492f9 KH |
4447 | else if (CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_CNTL) |
4448 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4449 | EMIT_ONE_ASCII_BYTE (c); | |
4ed46869 | 4450 | } |
df7492f9 | 4451 | else if (ASCII_CHAR_P (c)) |
88993dfd | 4452 | { |
df7492f9 KH |
4453 | if (ascii_compatible) |
4454 | EMIT_ONE_ASCII_BYTE (c); | |
93dec019 | 4455 | else |
19a8d9e0 | 4456 | { |
bf16eb23 KH |
4457 | struct charset *charset = CHARSET_FROM_ID (charset_ascii); |
4458 | ENCODE_ISO_CHARACTER (charset, c); | |
19a8d9e0 | 4459 | } |
4ed46869 | 4460 | } |
16eafb5d | 4461 | else if (CHAR_BYTE8_P (c)) |
88993dfd | 4462 | { |
16eafb5d KH |
4463 | c = CHAR_TO_BYTE8 (c); |
4464 | EMIT_ONE_BYTE (c); | |
88993dfd | 4465 | } |
b73bfc1c | 4466 | else |
df7492f9 | 4467 | { |
ff0dacd7 | 4468 | struct charset *charset; |
b73bfc1c | 4469 | |
ff0dacd7 KH |
4470 | if (preferred_charset_id >= 0) |
4471 | { | |
f10fe38f | 4472 | bool result; |
5eb05ea3 | 4473 | |
ff0dacd7 | 4474 | charset = CHARSET_FROM_ID (preferred_charset_id); |
5eb05ea3 KH |
4475 | CODING_CHAR_CHARSET_P (coding, dst, dst_end, c, charset, result); |
4476 | if (! result) | |
4477 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4478 | NULL, charset); | |
ff0dacd7 KH |
4479 | } |
4480 | else | |
5eb05ea3 KH |
4481 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
4482 | NULL, charset); | |
df7492f9 KH |
4483 | if (!charset) |
4484 | { | |
41cbe562 KH |
4485 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
4486 | { | |
4487 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
4488 | charset = CHARSET_FROM_ID (charset_ascii); | |
4489 | } | |
4490 | else | |
4491 | { | |
4492 | c = coding->default_char; | |
5eb05ea3 KH |
4493 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4494 | charset_list, NULL, charset); | |
41cbe562 | 4495 | } |
df7492f9 KH |
4496 | } |
4497 | ENCODE_ISO_CHARACTER (charset, c); | |
4498 | } | |
84fbb8a0 | 4499 | } |
b73bfc1c | 4500 | |
df7492f9 KH |
4501 | if (coding->mode & CODING_MODE_LAST_BLOCK |
4502 | && CODING_ISO_FLAGS (coding) & CODING_ISO_FLAG_RESET_AT_EOL) | |
4503 | { | |
4504 | ASSURE_DESTINATION (safe_room); | |
4505 | ENCODE_RESET_PLANE_AND_REGISTER (); | |
4506 | } | |
065e3595 | 4507 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4508 | CODING_ISO_BOL (coding) = bol_designation; |
4509 | coding->produced_char += produced_chars; | |
4510 | coding->produced = dst - coding->destination; | |
4511 | return 0; | |
4ed46869 KH |
4512 | } |
4513 | ||
4514 | \f | |
df7492f9 | 4515 | /*** 8,9. SJIS and BIG5 handlers ***/ |
4ed46869 | 4516 | |
df7492f9 | 4517 | /* Although SJIS and BIG5 are not ISO's coding system, they are used |
4ed46869 KH |
4518 | quite widely. So, for the moment, Emacs supports them in the bare |
4519 | C code. But, in the future, they may be supported only by CCL. */ | |
4520 | ||
4521 | /* SJIS is a coding system encoding three character sets: ASCII, right | |
4522 | half of JISX0201-Kana, and JISX0208. An ASCII character is encoded | |
4523 | as is. A character of charset katakana-jisx0201 is encoded by | |
4524 | "position-code + 0x80". A character of charset japanese-jisx0208 | |
4525 | is encoded in 2-byte but two position-codes are divided and shifted | |
df7492f9 | 4526 | so that it fit in the range below. |
4ed46869 KH |
4527 | |
4528 | --- CODE RANGE of SJIS --- | |
4529 | (character set) (range) | |
4530 | ASCII 0x00 .. 0x7F | |
df7492f9 | 4531 | KATAKANA-JISX0201 0xA0 .. 0xDF |
c28a9453 | 4532 | JISX0208 (1st byte) 0x81 .. 0x9F and 0xE0 .. 0xEF |
d14d03ac | 4533 | (2nd byte) 0x40 .. 0x7E and 0x80 .. 0xFC |
4ed46869 KH |
4534 | ------------------------------- |
4535 | ||
4536 | */ | |
4537 | ||
4538 | /* BIG5 is a coding system encoding two character sets: ASCII and | |
4539 | Big5. An ASCII character is encoded as is. Big5 is a two-byte | |
df7492f9 | 4540 | character set and is encoded in two-byte. |
4ed46869 KH |
4541 | |
4542 | --- CODE RANGE of BIG5 --- | |
4543 | (character set) (range) | |
4544 | ASCII 0x00 .. 0x7F | |
4545 | Big5 (1st byte) 0xA1 .. 0xFE | |
4546 | (2nd byte) 0x40 .. 0x7E and 0xA1 .. 0xFE | |
4547 | -------------------------- | |
4548 | ||
df7492f9 | 4549 | */ |
4ed46869 KH |
4550 | |
4551 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 4552 | Return true if a text is encoded in SJIS. */ |
4ed46869 | 4553 | |
f10fe38f | 4554 | static bool |
cf84bb53 JB |
4555 | detect_coding_sjis (struct coding_system *coding, |
4556 | struct coding_detection_info *detect_info) | |
4ed46869 | 4557 | { |
065e3595 | 4558 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4559 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 4560 | bool multibytep = coding->src_multibyte; |
d311d28c | 4561 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 4562 | int found = 0; |
b73bfc1c | 4563 | int c; |
f07190ca KH |
4564 | Lisp_Object attrs, charset_list; |
4565 | int max_first_byte_of_2_byte_code; | |
4566 | ||
4567 | CODING_GET_INFO (coding, attrs, charset_list); | |
4568 | max_first_byte_of_2_byte_code | |
4569 | = (XINT (Flength (charset_list)) > 3 ? 0xFC : 0xEF); | |
df7492f9 | 4570 | |
ff0dacd7 | 4571 | detect_info->checked |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4572 | /* A coding system of this category is always ASCII compatible. */ |
4573 | src += coding->head_ascii; | |
4ed46869 | 4574 | |
b73bfc1c | 4575 | while (1) |
4ed46869 | 4576 | { |
065e3595 | 4577 | src_base = src; |
df7492f9 | 4578 | ONE_MORE_BYTE (c); |
682169fe KH |
4579 | if (c < 0x80) |
4580 | continue; | |
f07190ca KH |
4581 | if ((c >= 0x81 && c <= 0x9F) |
4582 | || (c >= 0xE0 && c <= max_first_byte_of_2_byte_code)) | |
4ed46869 | 4583 | { |
df7492f9 | 4584 | ONE_MORE_BYTE (c); |
682169fe | 4585 | if (c < 0x40 || c == 0x7F || c > 0xFC) |
df7492f9 | 4586 | break; |
ff0dacd7 | 4587 | found = CATEGORY_MASK_SJIS; |
4ed46869 | 4588 | } |
df7492f9 | 4589 | else if (c >= 0xA0 && c < 0xE0) |
ff0dacd7 | 4590 | found = CATEGORY_MASK_SJIS; |
df7492f9 KH |
4591 | else |
4592 | break; | |
4ed46869 | 4593 | } |
ff0dacd7 | 4594 | detect_info->rejected |= CATEGORY_MASK_SJIS; |
df7492f9 KH |
4595 | return 0; |
4596 | ||
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_SJIS; |
89528eb3 | 4601 | return 0; |
4ed46869 | 4602 | } |
ff0dacd7 KH |
4603 | detect_info->found |= found; |
4604 | return 1; | |
4ed46869 KH |
4605 | } |
4606 | ||
4607 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f | 4608 | Return true if a text is encoded in BIG5. */ |
4ed46869 | 4609 | |
f10fe38f | 4610 | static bool |
cf84bb53 JB |
4611 | detect_coding_big5 (struct coding_system *coding, |
4612 | struct coding_detection_info *detect_info) | |
4ed46869 | 4613 | { |
065e3595 | 4614 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 4615 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 4616 | bool multibytep = coding->src_multibyte; |
d311d28c | 4617 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 4618 | int found = 0; |
b73bfc1c | 4619 | int c; |
fa42c37f | 4620 | |
ff0dacd7 | 4621 | detect_info->checked |= CATEGORY_MASK_BIG5; |
df7492f9 KH |
4622 | /* A coding system of this category is always ASCII compatible. */ |
4623 | src += coding->head_ascii; | |
fa42c37f | 4624 | |
b73bfc1c | 4625 | while (1) |
fa42c37f | 4626 | { |
065e3595 | 4627 | src_base = src; |
df7492f9 KH |
4628 | ONE_MORE_BYTE (c); |
4629 | if (c < 0x80) | |
fa42c37f | 4630 | continue; |
df7492f9 | 4631 | if (c >= 0xA1) |
fa42c37f | 4632 | { |
df7492f9 KH |
4633 | ONE_MORE_BYTE (c); |
4634 | if (c < 0x40 || (c >= 0x7F && c <= 0xA0)) | |
fa42c37f | 4635 | return 0; |
ff0dacd7 | 4636 | found = CATEGORY_MASK_BIG5; |
fa42c37f | 4637 | } |
df7492f9 KH |
4638 | else |
4639 | break; | |
fa42c37f | 4640 | } |
ff0dacd7 | 4641 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
fa42c37f | 4642 | return 0; |
fa42c37f | 4643 | |
df7492f9 | 4644 | no_more_source: |
065e3595 | 4645 | if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK) |
89528eb3 | 4646 | { |
ff0dacd7 | 4647 | detect_info->rejected |= CATEGORY_MASK_BIG5; |
89528eb3 KH |
4648 | return 0; |
4649 | } | |
ff0dacd7 KH |
4650 | detect_info->found |= found; |
4651 | return 1; | |
fa42c37f KH |
4652 | } |
4653 | ||
f10fe38f | 4654 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
fa42c37f | 4655 | |
b73bfc1c | 4656 | static void |
971de7fb | 4657 | decode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4658 | { |
8f924df7 KH |
4659 | const unsigned char *src = coding->source + coding->consumed; |
4660 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4661 | const unsigned char *src_base; | |
69a80ea3 | 4662 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4663 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4664 | the end. */ |
69a80ea3 | 4665 | int *charbuf_end |
df80c7f0 | 4666 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 4667 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 4668 | bool multibytep = coding->src_multibyte; |
df7492f9 | 4669 | struct charset *charset_roman, *charset_kanji, *charset_kana; |
57a47f8a | 4670 | struct charset *charset_kanji2; |
24a73b0a | 4671 | Lisp_Object attrs, charset_list, val; |
d311d28c PE |
4672 | ptrdiff_t char_offset = coding->produced_char; |
4673 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 4674 | int last_id = charset_ascii; |
f10fe38f PE |
4675 | bool eol_dos |
4676 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4677 | int byte_after_cr = -1; |
a5d301df | 4678 | |
24a73b0a | 4679 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4680 | |
4681 | val = charset_list; | |
4682 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
89528eb3 | 4683 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4684 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4685 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 4686 | |
b73bfc1c | 4687 | while (1) |
4ed46869 | 4688 | { |
df7492f9 | 4689 | int c, c1; |
24a73b0a | 4690 | struct charset *charset; |
fa42c37f | 4691 | |
b73bfc1c | 4692 | src_base = src; |
df7492f9 | 4693 | consumed_chars_base = consumed_chars; |
fa42c37f | 4694 | |
df7492f9 | 4695 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
4696 | { |
4697 | if (byte_after_cr >= 0) | |
4698 | src_base--; | |
4699 | break; | |
4700 | } | |
df7492f9 | 4701 | |
119852e7 KH |
4702 | if (byte_after_cr >= 0) |
4703 | c = byte_after_cr, byte_after_cr = -1; | |
4704 | else | |
4705 | ONE_MORE_BYTE (c); | |
065e3595 KH |
4706 | if (c < 0) |
4707 | goto invalid_code; | |
24a73b0a | 4708 | if (c < 0x80) |
119852e7 | 4709 | { |
2735d060 | 4710 | if (eol_dos && c == '\r') |
119852e7 KH |
4711 | ONE_MORE_BYTE (byte_after_cr); |
4712 | charset = charset_roman; | |
4713 | } | |
57a47f8a | 4714 | else if (c == 0x80 || c == 0xA0) |
8e921c4b | 4715 | goto invalid_code; |
57a47f8a KH |
4716 | else if (c >= 0xA1 && c <= 0xDF) |
4717 | { | |
4718 | /* SJIS -> JISX0201-Kana */ | |
4719 | c &= 0x7F; | |
4720 | charset = charset_kana; | |
4721 | } | |
4722 | else if (c <= 0xEF) | |
df7492f9 | 4723 | { |
57a47f8a KH |
4724 | /* SJIS -> JISX0208 */ |
4725 | ONE_MORE_BYTE (c1); | |
4726 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4727 | goto invalid_code; |
57a47f8a KH |
4728 | c = (c << 8) | c1; |
4729 | SJIS_TO_JIS (c); | |
4730 | charset = charset_kanji; | |
4731 | } | |
4732 | else if (c <= 0xFC && charset_kanji2) | |
4733 | { | |
c6876370 | 4734 | /* SJIS -> JISX0213-2 */ |
57a47f8a KH |
4735 | ONE_MORE_BYTE (c1); |
4736 | if (c1 < 0x40 || c1 == 0x7F || c1 > 0xFC) | |
24a73b0a | 4737 | goto invalid_code; |
57a47f8a KH |
4738 | c = (c << 8) | c1; |
4739 | SJIS_TO_JIS2 (c); | |
4740 | charset = charset_kanji2; | |
df7492f9 | 4741 | } |
57a47f8a KH |
4742 | else |
4743 | goto invalid_code; | |
24a73b0a KH |
4744 | if (charset->id != charset_ascii |
4745 | && last_id != charset->id) | |
4746 | { | |
4747 | if (last_id != charset_ascii) | |
69a80ea3 | 4748 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4749 | last_id = charset->id; |
4750 | last_offset = char_offset; | |
4751 | } | |
4752 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); | |
df7492f9 | 4753 | *charbuf++ = c; |
ff0dacd7 | 4754 | char_offset++; |
df7492f9 | 4755 | continue; |
b73bfc1c | 4756 | |
df7492f9 KH |
4757 | invalid_code: |
4758 | src = src_base; | |
4759 | consumed_chars = consumed_chars_base; | |
4760 | ONE_MORE_BYTE (c); | |
065e3595 | 4761 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4762 | char_offset++; |
df7492f9 KH |
4763 | coding->errors++; |
4764 | } | |
fa42c37f | 4765 | |
df7492f9 | 4766 | no_more_source: |
ff0dacd7 | 4767 | if (last_id != charset_ascii) |
69a80ea3 | 4768 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4769 | coding->consumed_char += consumed_chars_base; |
4770 | coding->consumed = src_base - coding->source; | |
4771 | coding->charbuf_used = charbuf - coding->charbuf; | |
fa42c37f KH |
4772 | } |
4773 | ||
b73bfc1c | 4774 | static void |
971de7fb | 4775 | decode_coding_big5 (struct coding_system *coding) |
4ed46869 | 4776 | { |
8f924df7 KH |
4777 | const unsigned char *src = coding->source + coding->consumed; |
4778 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
4779 | const unsigned char *src_base; | |
69a80ea3 | 4780 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 4781 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 4782 | the end. */ |
69a80ea3 | 4783 | int *charbuf_end |
df80c7f0 | 4784 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 4785 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 4786 | bool multibytep = coding->src_multibyte; |
df7492f9 | 4787 | struct charset *charset_roman, *charset_big5; |
24a73b0a | 4788 | Lisp_Object attrs, charset_list, val; |
d311d28c PE |
4789 | ptrdiff_t char_offset = coding->produced_char; |
4790 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 4791 | int last_id = charset_ascii; |
f10fe38f PE |
4792 | bool eol_dos |
4793 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 4794 | int byte_after_cr = -1; |
df7492f9 | 4795 | |
24a73b0a | 4796 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 KH |
4797 | val = charset_list; |
4798 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
4799 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4800 | |
b73bfc1c | 4801 | while (1) |
4ed46869 | 4802 | { |
df7492f9 | 4803 | int c, c1; |
24a73b0a | 4804 | struct charset *charset; |
b73bfc1c KH |
4805 | |
4806 | src_base = src; | |
df7492f9 KH |
4807 | consumed_chars_base = consumed_chars; |
4808 | ||
4809 | if (charbuf >= charbuf_end) | |
b71f6f73 KH |
4810 | { |
4811 | if (byte_after_cr >= 0) | |
4812 | src_base--; | |
4813 | break; | |
4814 | } | |
df7492f9 | 4815 | |
119852e7 | 4816 | if (byte_after_cr >= 0) |
14daee73 | 4817 | c = byte_after_cr, byte_after_cr = -1; |
119852e7 KH |
4818 | else |
4819 | ONE_MORE_BYTE (c); | |
b73bfc1c | 4820 | |
065e3595 KH |
4821 | if (c < 0) |
4822 | goto invalid_code; | |
24a73b0a | 4823 | if (c < 0x80) |
119852e7 | 4824 | { |
2735d060 | 4825 | if (eol_dos && c == '\r') |
119852e7 KH |
4826 | ONE_MORE_BYTE (byte_after_cr); |
4827 | charset = charset_roman; | |
4828 | } | |
24a73b0a | 4829 | else |
4ed46869 | 4830 | { |
24a73b0a KH |
4831 | /* BIG5 -> Big5 */ |
4832 | if (c < 0xA1 || c > 0xFE) | |
4833 | goto invalid_code; | |
4834 | ONE_MORE_BYTE (c1); | |
4835 | if (c1 < 0x40 || (c1 > 0x7E && c1 < 0xA1) || c1 > 0xFE) | |
4836 | goto invalid_code; | |
4837 | c = c << 8 | c1; | |
4838 | charset = charset_big5; | |
4ed46869 | 4839 | } |
24a73b0a KH |
4840 | if (charset->id != charset_ascii |
4841 | && last_id != charset->id) | |
df7492f9 | 4842 | { |
24a73b0a | 4843 | if (last_id != charset_ascii) |
69a80ea3 | 4844 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
4845 | last_id = charset->id; |
4846 | last_offset = char_offset; | |
4ed46869 | 4847 | } |
24a73b0a | 4848 | CODING_DECODE_CHAR (coding, src, src_base, src_end, charset, c, c); |
df7492f9 | 4849 | *charbuf++ = c; |
ff0dacd7 | 4850 | char_offset++; |
fb88bf2d KH |
4851 | continue; |
4852 | ||
df7492f9 | 4853 | invalid_code: |
4ed46869 | 4854 | src = src_base; |
df7492f9 KH |
4855 | consumed_chars = consumed_chars_base; |
4856 | ONE_MORE_BYTE (c); | |
065e3595 | 4857 | *charbuf++ = c < 0 ? -c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 4858 | char_offset++; |
df7492f9 | 4859 | coding->errors++; |
fb88bf2d | 4860 | } |
d46c5b12 | 4861 | |
df7492f9 | 4862 | no_more_source: |
ff0dacd7 | 4863 | if (last_id != charset_ascii) |
69a80ea3 | 4864 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
4865 | coding->consumed_char += consumed_chars_base; |
4866 | coding->consumed = src_base - coding->source; | |
4867 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
4868 | } |
4869 | ||
4870 | /* See the above "GENERAL NOTES on `encode_coding_XXX ()' functions". | |
b73bfc1c KH |
4871 | This function can encode charsets `ascii', `katakana-jisx0201', |
4872 | `japanese-jisx0208', `chinese-big5-1', and `chinese-big5-2'. We | |
4873 | are sure that all these charsets are registered as official charset | |
4ed46869 | 4874 | (i.e. do not have extended leading-codes). Characters of other |
f10fe38f | 4875 | charsets are produced without any encoding. */ |
4ed46869 | 4876 | |
f10fe38f | 4877 | static bool |
971de7fb | 4878 | encode_coding_sjis (struct coding_system *coding) |
4ed46869 | 4879 | { |
f10fe38f | 4880 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4881 | int *charbuf = coding->charbuf; |
4882 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4883 | unsigned char *dst = coding->destination + coding->produced; | |
4884 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4885 | int safe_room = 4; | |
d311d28c | 4886 | ptrdiff_t produced_chars = 0; |
24a73b0a | 4887 | Lisp_Object attrs, charset_list, val; |
f10fe38f | 4888 | bool ascii_compatible; |
66ebf983 | 4889 | struct charset *charset_kanji, *charset_kana; |
57a47f8a | 4890 | struct charset *charset_kanji2; |
df7492f9 | 4891 | int c; |
a5d301df | 4892 | |
24a73b0a | 4893 | CODING_GET_INFO (coding, attrs, charset_list); |
66ebf983 | 4894 | val = XCDR (charset_list); |
df7492f9 | 4895 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
57a47f8a KH |
4896 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
4897 | charset_kanji2 = NILP (val) ? NULL : CHARSET_FROM_ID (XINT (XCAR (val))); | |
4ed46869 | 4898 | |
df7492f9 | 4899 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
93dec019 | 4900 | |
df7492f9 KH |
4901 | while (charbuf < charbuf_end) |
4902 | { | |
4903 | ASSURE_DESTINATION (safe_room); | |
4904 | c = *charbuf++; | |
b73bfc1c | 4905 | /* Now encode the character C. */ |
df7492f9 KH |
4906 | if (ASCII_CHAR_P (c) && ascii_compatible) |
4907 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4908 | else if (CHAR_BYTE8_P (c)) |
4909 | { | |
4910 | c = CHAR_TO_BYTE8 (c); | |
4911 | EMIT_ONE_BYTE (c); | |
4912 | } | |
df7492f9 | 4913 | else |
b73bfc1c | 4914 | { |
df7492f9 | 4915 | unsigned code; |
5eb05ea3 KH |
4916 | struct charset *charset; |
4917 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
4918 | &code, charset); | |
df7492f9 KH |
4919 | |
4920 | if (!charset) | |
4ed46869 | 4921 | { |
41cbe562 | 4922 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 4923 | { |
41cbe562 KH |
4924 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
4925 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 4926 | } |
41cbe562 | 4927 | else |
b73bfc1c | 4928 | { |
41cbe562 | 4929 | c = coding->default_char; |
5eb05ea3 KH |
4930 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
4931 | charset_list, &code, charset); | |
b73bfc1c | 4932 | } |
b73bfc1c | 4933 | } |
df7492f9 | 4934 | if (code == CHARSET_INVALID_CODE (charset)) |
1088b922 | 4935 | emacs_abort (); |
df7492f9 KH |
4936 | if (charset == charset_kanji) |
4937 | { | |
4938 | int c1, c2; | |
4939 | JIS_TO_SJIS (code); | |
4940 | c1 = code >> 8, c2 = code & 0xFF; | |
4941 | EMIT_TWO_BYTES (c1, c2); | |
4942 | } | |
4943 | else if (charset == charset_kana) | |
4944 | EMIT_ONE_BYTE (code | 0x80); | |
57a47f8a KH |
4945 | else if (charset_kanji2 && charset == charset_kanji2) |
4946 | { | |
4947 | int c1, c2; | |
4948 | ||
4949 | c1 = code >> 8; | |
f07190ca KH |
4950 | if (c1 == 0x21 || (c1 >= 0x23 && c1 <= 0x25) |
4951 | || c1 == 0x28 | |
57a47f8a KH |
4952 | || (c1 >= 0x2C && c1 <= 0x2F) || c1 >= 0x6E) |
4953 | { | |
4954 | JIS_TO_SJIS2 (code); | |
4955 | c1 = code >> 8, c2 = code & 0xFF; | |
4956 | EMIT_TWO_BYTES (c1, c2); | |
4957 | } | |
4958 | else | |
4959 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4960 | } | |
df7492f9 KH |
4961 | else |
4962 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4963 | } | |
4964 | } | |
065e3595 | 4965 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
4966 | coding->produced_char += produced_chars; |
4967 | coding->produced = dst - coding->destination; | |
4968 | return 0; | |
4969 | } | |
4970 | ||
f10fe38f | 4971 | static bool |
971de7fb | 4972 | encode_coding_big5 (struct coding_system *coding) |
df7492f9 | 4973 | { |
f10fe38f | 4974 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
4975 | int *charbuf = coding->charbuf; |
4976 | int *charbuf_end = charbuf + coding->charbuf_used; | |
4977 | unsigned char *dst = coding->destination + coding->produced; | |
4978 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
4979 | int safe_room = 4; | |
d311d28c | 4980 | ptrdiff_t produced_chars = 0; |
24a73b0a | 4981 | Lisp_Object attrs, charset_list, val; |
f10fe38f | 4982 | bool ascii_compatible; |
66ebf983 | 4983 | struct charset *charset_big5; |
df7492f9 KH |
4984 | int c; |
4985 | ||
24a73b0a | 4986 | CODING_GET_INFO (coding, attrs, charset_list); |
66ebf983 | 4987 | val = XCDR (charset_list); |
df7492f9 KH |
4988 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); |
4989 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
4990 | ||
4991 | while (charbuf < charbuf_end) | |
4992 | { | |
4993 | ASSURE_DESTINATION (safe_room); | |
4994 | c = *charbuf++; | |
4995 | /* Now encode the character C. */ | |
4996 | if (ASCII_CHAR_P (c) && ascii_compatible) | |
4997 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d KH |
4998 | else if (CHAR_BYTE8_P (c)) |
4999 | { | |
5000 | c = CHAR_TO_BYTE8 (c); | |
5001 | EMIT_ONE_BYTE (c); | |
b73bfc1c KH |
5002 | } |
5003 | else | |
5004 | { | |
df7492f9 | 5005 | unsigned code; |
5eb05ea3 KH |
5006 | struct charset *charset; |
5007 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, | |
5008 | &code, charset); | |
df7492f9 KH |
5009 | |
5010 | if (! charset) | |
b73bfc1c | 5011 | { |
41cbe562 | 5012 | if (coding->mode & CODING_MODE_SAFE_ENCODING) |
b73bfc1c | 5013 | { |
41cbe562 KH |
5014 | code = CODING_INHIBIT_CHARACTER_SUBSTITUTION; |
5015 | charset = CHARSET_FROM_ID (charset_ascii); | |
b73bfc1c | 5016 | } |
41cbe562 | 5017 | else |
0eecad43 | 5018 | { |
41cbe562 | 5019 | c = coding->default_char; |
5eb05ea3 KH |
5020 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, |
5021 | charset_list, &code, charset); | |
0eecad43 | 5022 | } |
4ed46869 | 5023 | } |
df7492f9 | 5024 | if (code == CHARSET_INVALID_CODE (charset)) |
1088b922 | 5025 | emacs_abort (); |
df7492f9 | 5026 | if (charset == charset_big5) |
b73bfc1c | 5027 | { |
df7492f9 KH |
5028 | int c1, c2; |
5029 | ||
5030 | c1 = code >> 8, c2 = code & 0xFF; | |
5031 | EMIT_TWO_BYTES (c1, c2); | |
b73bfc1c | 5032 | } |
df7492f9 KH |
5033 | else |
5034 | EMIT_ONE_ASCII_BYTE (code & 0x7F); | |
4ed46869 | 5035 | } |
4ed46869 | 5036 | } |
065e3595 | 5037 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5038 | coding->produced_char += produced_chars; |
5039 | coding->produced = dst - coding->destination; | |
5040 | return 0; | |
4ed46869 KH |
5041 | } |
5042 | ||
5043 | \f | |
df7492f9 | 5044 | /*** 10. CCL handlers ***/ |
1397dc18 KH |
5045 | |
5046 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". | |
f10fe38f PE |
5047 | Return true if a text is encoded in a coding system of which |
5048 | encoder/decoder are written in CCL program. */ | |
1397dc18 | 5049 | |
f10fe38f | 5050 | static bool |
cf84bb53 JB |
5051 | detect_coding_ccl (struct coding_system *coding, |
5052 | struct coding_detection_info *detect_info) | |
1397dc18 | 5053 | { |
065e3595 | 5054 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5055 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 5056 | bool multibytep = coding->src_multibyte; |
d311d28c | 5057 | ptrdiff_t consumed_chars = 0; |
df7492f9 | 5058 | int found = 0; |
0e219d54 | 5059 | unsigned char *valids; |
d311d28c | 5060 | ptrdiff_t head_ascii = coding->head_ascii; |
df7492f9 KH |
5061 | Lisp_Object attrs; |
5062 | ||
ff0dacd7 KH |
5063 | detect_info->checked |= CATEGORY_MASK_CCL; |
5064 | ||
df7492f9 | 5065 | coding = &coding_categories[coding_category_ccl]; |
0e219d54 | 5066 | valids = CODING_CCL_VALIDS (coding); |
df7492f9 KH |
5067 | attrs = CODING_ID_ATTRS (coding->id); |
5068 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
5069 | src += head_ascii; | |
1397dc18 | 5070 | |
b73bfc1c | 5071 | while (1) |
1397dc18 | 5072 | { |
df7492f9 | 5073 | int c; |
065e3595 KH |
5074 | |
5075 | src_base = src; | |
df7492f9 | 5076 | ONE_MORE_BYTE (c); |
065e3595 | 5077 | if (c < 0 || ! valids[c]) |
df7492f9 | 5078 | break; |
ff0dacd7 KH |
5079 | if ((valids[c] > 1)) |
5080 | found = CATEGORY_MASK_CCL; | |
df7492f9 | 5081 | } |
ff0dacd7 | 5082 | detect_info->rejected |= CATEGORY_MASK_CCL; |
df7492f9 KH |
5083 | return 0; |
5084 | ||
5085 | no_more_source: | |
ff0dacd7 KH |
5086 | detect_info->found |= found; |
5087 | return 1; | |
df7492f9 KH |
5088 | } |
5089 | ||
5090 | static void | |
971de7fb | 5091 | decode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5092 | { |
7c78e542 | 5093 | const unsigned char *src = coding->source + coding->consumed; |
8f924df7 | 5094 | const unsigned char *src_end = coding->source + coding->src_bytes; |
69a80ea3 KH |
5095 | int *charbuf = coding->charbuf + coding->charbuf_used; |
5096 | int *charbuf_end = coding->charbuf + coding->charbuf_size; | |
d311d28c | 5097 | ptrdiff_t consumed_chars = 0; |
f10fe38f | 5098 | bool multibytep = coding->src_multibyte; |
d0396581 | 5099 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
df7492f9 | 5100 | int source_charbuf[1024]; |
fbdc1721 | 5101 | int source_byteidx[1025]; |
24a73b0a | 5102 | Lisp_Object attrs, charset_list; |
df7492f9 | 5103 | |
24a73b0a | 5104 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5105 | |
d0396581 | 5106 | while (1) |
df7492f9 | 5107 | { |
7c78e542 | 5108 | const unsigned char *p = src; |
95402d5f | 5109 | ptrdiff_t offset; |
df7492f9 KH |
5110 | int i = 0; |
5111 | ||
5112 | if (multibytep) | |
fbdc1721 KH |
5113 | { |
5114 | while (i < 1024 && p < src_end) | |
5115 | { | |
5116 | source_byteidx[i] = p - src; | |
5117 | source_charbuf[i++] = STRING_CHAR_ADVANCE (p); | |
5118 | } | |
5119 | source_byteidx[i] = p - src; | |
5120 | } | |
df7492f9 KH |
5121 | else |
5122 | while (i < 1024 && p < src_end) | |
5123 | source_charbuf[i++] = *p++; | |
8f924df7 | 5124 | |
df7492f9 | 5125 | if (p == src_end && coding->mode & CODING_MODE_LAST_BLOCK) |
d0396581 | 5126 | ccl->last_block = 1; |
95402d5f KH |
5127 | /* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */ |
5128 | charset_map_loaded = 0; | |
d0396581 KH |
5129 | ccl_driver (ccl, source_charbuf, charbuf, i, charbuf_end - charbuf, |
5130 | charset_list); | |
95402d5f KH |
5131 | if (charset_map_loaded |
5132 | && (offset = coding_change_source (coding))) | |
5133 | { | |
5134 | p += offset; | |
5135 | src += offset; | |
5136 | src_end += offset; | |
5137 | } | |
d0396581 | 5138 | charbuf += ccl->produced; |
fbdc1721 | 5139 | if (multibytep) |
d0396581 | 5140 | src += source_byteidx[ccl->consumed]; |
df7492f9 | 5141 | else |
d0396581 KH |
5142 | src += ccl->consumed; |
5143 | consumed_chars += ccl->consumed; | |
5144 | if (p == src_end || ccl->status != CCL_STAT_SUSPEND_BY_SRC) | |
df7492f9 KH |
5145 | break; |
5146 | } | |
5147 | ||
d0396581 | 5148 | switch (ccl->status) |
df7492f9 KH |
5149 | { |
5150 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5151 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5152 | break; |
5153 | case CCL_STAT_SUSPEND_BY_DST: | |
d0396581 | 5154 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5155 | break; |
5156 | case CCL_STAT_QUIT: | |
5157 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5158 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5159 | break; |
5160 | default: | |
065e3595 | 5161 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5162 | break; |
5163 | } | |
5164 | coding->consumed_char += consumed_chars; | |
5165 | coding->consumed = src - coding->source; | |
5166 | coding->charbuf_used = charbuf - coding->charbuf; | |
5167 | } | |
5168 | ||
f10fe38f | 5169 | static bool |
971de7fb | 5170 | encode_coding_ccl (struct coding_system *coding) |
df7492f9 | 5171 | { |
fb608df3 | 5172 | struct ccl_program *ccl = &coding->spec.ccl->ccl; |
f10fe38f | 5173 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5174 | int *charbuf = coding->charbuf; |
5175 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5176 | unsigned char *dst = coding->destination + coding->produced; | |
5177 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
df7492f9 | 5178 | int destination_charbuf[1024]; |
d311d28c | 5179 | ptrdiff_t produced_chars = 0; |
a53e2e89 | 5180 | int i; |
24a73b0a | 5181 | Lisp_Object attrs, charset_list; |
df7492f9 | 5182 | |
24a73b0a | 5183 | CODING_GET_INFO (coding, attrs, charset_list); |
fb608df3 KH |
5184 | if (coding->consumed_char == coding->src_chars |
5185 | && coding->mode & CODING_MODE_LAST_BLOCK) | |
5186 | ccl->last_block = 1; | |
df7492f9 | 5187 | |
76470ad1 | 5188 | do |
df7492f9 | 5189 | { |
95402d5f KH |
5190 | ptrdiff_t offset; |
5191 | ||
5192 | /* As ccl_driver calls DECODE_CHAR, buffer may be relocated. */ | |
5193 | charset_map_loaded = 0; | |
fb608df3 | 5194 | ccl_driver (ccl, charbuf, destination_charbuf, |
8cffd3e7 | 5195 | charbuf_end - charbuf, 1024, charset_list); |
95402d5f KH |
5196 | if (charset_map_loaded |
5197 | && (offset = coding_change_destination (coding))) | |
5198 | dst += offset; | |
df7492f9 | 5199 | if (multibytep) |
8cffd3e7 | 5200 | { |
fb608df3 KH |
5201 | ASSURE_DESTINATION (ccl->produced * 2); |
5202 | for (i = 0; i < ccl->produced; i++) | |
8cffd3e7 KH |
5203 | EMIT_ONE_BYTE (destination_charbuf[i] & 0xFF); |
5204 | } | |
df7492f9 KH |
5205 | else |
5206 | { | |
fb608df3 KH |
5207 | ASSURE_DESTINATION (ccl->produced); |
5208 | for (i = 0; i < ccl->produced; i++) | |
df7492f9 | 5209 | *dst++ = destination_charbuf[i] & 0xFF; |
fb608df3 | 5210 | produced_chars += ccl->produced; |
df7492f9 | 5211 | } |
fb608df3 KH |
5212 | charbuf += ccl->consumed; |
5213 | if (ccl->status == CCL_STAT_QUIT | |
5214 | || ccl->status == CCL_STAT_INVALID_CMD) | |
8cffd3e7 | 5215 | break; |
df7492f9 | 5216 | } |
76470ad1 | 5217 | while (charbuf < charbuf_end); |
df7492f9 | 5218 | |
fb608df3 | 5219 | switch (ccl->status) |
df7492f9 KH |
5220 | { |
5221 | case CCL_STAT_SUSPEND_BY_SRC: | |
065e3595 | 5222 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); |
df7492f9 KH |
5223 | break; |
5224 | case CCL_STAT_SUSPEND_BY_DST: | |
065e3595 | 5225 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_DST); |
df7492f9 KH |
5226 | break; |
5227 | case CCL_STAT_QUIT: | |
5228 | case CCL_STAT_INVALID_CMD: | |
065e3595 | 5229 | record_conversion_result (coding, CODING_RESULT_INTERRUPT); |
df7492f9 KH |
5230 | break; |
5231 | default: | |
065e3595 | 5232 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 5233 | break; |
1397dc18 | 5234 | } |
df7492f9 KH |
5235 | |
5236 | coding->produced_char += produced_chars; | |
5237 | coding->produced = dst - coding->destination; | |
5238 | return 0; | |
1397dc18 KH |
5239 | } |
5240 | ||
5241 | \f | |
df7492f9 | 5242 | /*** 10, 11. no-conversion handlers ***/ |
4ed46869 | 5243 | |
b73bfc1c | 5244 | /* See the above "GENERAL NOTES on `decode_coding_XXX ()' functions". */ |
4ed46869 | 5245 | |
b73bfc1c | 5246 | static void |
971de7fb | 5247 | decode_coding_raw_text (struct coding_system *coding) |
4ed46869 | 5248 | { |
f10fe38f PE |
5249 | bool eol_dos |
5250 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5251 | |
df7492f9 | 5252 | coding->chars_at_source = 1; |
119852e7 KH |
5253 | coding->consumed_char = coding->src_chars; |
5254 | coding->consumed = coding->src_bytes; | |
2735d060 | 5255 | if (eol_dos && coding->source[coding->src_bytes - 1] == '\r') |
119852e7 KH |
5256 | { |
5257 | coding->consumed_char--; | |
5258 | coding->consumed--; | |
5259 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_SRC); | |
5260 | } | |
5261 | else | |
5262 | record_conversion_result (coding, CODING_RESULT_SUCCESS); | |
df7492f9 | 5263 | } |
4ed46869 | 5264 | |
f10fe38f | 5265 | static bool |
971de7fb | 5266 | encode_coding_raw_text (struct coding_system *coding) |
df7492f9 | 5267 | { |
f10fe38f | 5268 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5269 | int *charbuf = coding->charbuf; |
5270 | int *charbuf_end = coding->charbuf + coding->charbuf_used; | |
5271 | unsigned char *dst = coding->destination + coding->produced; | |
5272 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c | 5273 | ptrdiff_t produced_chars = 0; |
b73bfc1c KH |
5274 | int c; |
5275 | ||
df7492f9 | 5276 | if (multibytep) |
b73bfc1c | 5277 | { |
df7492f9 | 5278 | int safe_room = MAX_MULTIBYTE_LENGTH * 2; |
4ed46869 | 5279 | |
df7492f9 KH |
5280 | if (coding->src_multibyte) |
5281 | while (charbuf < charbuf_end) | |
5282 | { | |
5283 | ASSURE_DESTINATION (safe_room); | |
5284 | c = *charbuf++; | |
5285 | if (ASCII_CHAR_P (c)) | |
5286 | EMIT_ONE_ASCII_BYTE (c); | |
5287 | else if (CHAR_BYTE8_P (c)) | |
5288 | { | |
5289 | c = CHAR_TO_BYTE8 (c); | |
5290 | EMIT_ONE_BYTE (c); | |
5291 | } | |
5292 | else | |
5293 | { | |
5294 | unsigned char str[MAX_MULTIBYTE_LENGTH], *p0 = str, *p1 = str; | |
93dec019 | 5295 | |
df7492f9 | 5296 | CHAR_STRING_ADVANCE (c, p1); |
8abc3f12 | 5297 | do |
9d123124 KH |
5298 | { |
5299 | EMIT_ONE_BYTE (*p0); | |
5300 | p0++; | |
5301 | } | |
8abc3f12 | 5302 | while (p0 < p1); |
df7492f9 KH |
5303 | } |
5304 | } | |
b73bfc1c | 5305 | else |
df7492f9 KH |
5306 | while (charbuf < charbuf_end) |
5307 | { | |
5308 | ASSURE_DESTINATION (safe_room); | |
5309 | c = *charbuf++; | |
5310 | EMIT_ONE_BYTE (c); | |
5311 | } | |
5312 | } | |
5313 | else | |
4ed46869 | 5314 | { |
df7492f9 | 5315 | if (coding->src_multibyte) |
d46c5b12 | 5316 | { |
df7492f9 KH |
5317 | int safe_room = MAX_MULTIBYTE_LENGTH; |
5318 | ||
5319 | while (charbuf < charbuf_end) | |
d46c5b12 | 5320 | { |
df7492f9 KH |
5321 | ASSURE_DESTINATION (safe_room); |
5322 | c = *charbuf++; | |
5323 | if (ASCII_CHAR_P (c)) | |
5324 | *dst++ = c; | |
5325 | else if (CHAR_BYTE8_P (c)) | |
5326 | *dst++ = CHAR_TO_BYTE8 (c); | |
b73bfc1c | 5327 | else |
df7492f9 | 5328 | CHAR_STRING_ADVANCE (c, dst); |
d46c5b12 KH |
5329 | } |
5330 | } | |
df7492f9 KH |
5331 | else |
5332 | { | |
5333 | ASSURE_DESTINATION (charbuf_end - charbuf); | |
5334 | while (charbuf < charbuf_end && dst < dst_end) | |
5335 | *dst++ = *charbuf++; | |
8f924df7 | 5336 | } |
319a3947 | 5337 | produced_chars = dst - (coding->destination + coding->produced); |
4ed46869 | 5338 | } |
065e3595 | 5339 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
a0ed9b27 | 5340 | coding->produced_char += produced_chars; |
df7492f9 KH |
5341 | coding->produced = dst - coding->destination; |
5342 | return 0; | |
4ed46869 KH |
5343 | } |
5344 | ||
ff0dacd7 | 5345 | /* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions". |
f10fe38f | 5346 | Return true if a text is encoded in a charset-based coding system. */ |
ff0dacd7 | 5347 | |
f10fe38f | 5348 | static bool |
cf84bb53 JB |
5349 | detect_coding_charset (struct coding_system *coding, |
5350 | struct coding_detection_info *detect_info) | |
1397dc18 | 5351 | { |
065e3595 | 5352 | const unsigned char *src = coding->source, *src_base; |
8f924df7 | 5353 | const unsigned char *src_end = coding->source + coding->src_bytes; |
f10fe38f | 5354 | bool multibytep = coding->src_multibyte; |
d311d28c | 5355 | ptrdiff_t consumed_chars = 0; |
07295713 | 5356 | Lisp_Object attrs, valids, name; |
584948ac | 5357 | int found = 0; |
d311d28c | 5358 | ptrdiff_t head_ascii = coding->head_ascii; |
f10fe38f | 5359 | bool check_latin_extra = 0; |
1397dc18 | 5360 | |
ff0dacd7 KH |
5361 | detect_info->checked |= CATEGORY_MASK_CHARSET; |
5362 | ||
df7492f9 KH |
5363 | coding = &coding_categories[coding_category_charset]; |
5364 | attrs = CODING_ID_ATTRS (coding->id); | |
5365 | valids = AREF (attrs, coding_attr_charset_valids); | |
07295713 | 5366 | name = CODING_ID_NAME (coding->id); |
51b59d79 | 5367 | if (strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5368 | "iso-8859-", sizeof ("iso-8859-") - 1) == 0 |
51b59d79 | 5369 | || strncmp (SSDATA (SYMBOL_NAME (name)), |
237aabf4 | 5370 | "iso-latin-", sizeof ("iso-latin-") - 1) == 0) |
07295713 | 5371 | check_latin_extra = 1; |
237aabf4 | 5372 | |
df7492f9 | 5373 | if (! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
716b3fa0 | 5374 | src += head_ascii; |
1397dc18 | 5375 | |
b73bfc1c | 5376 | while (1) |
1397dc18 | 5377 | { |
df7492f9 | 5378 | int c; |
716b3fa0 KH |
5379 | Lisp_Object val; |
5380 | struct charset *charset; | |
5381 | int dim, idx; | |
1397dc18 | 5382 | |
065e3595 | 5383 | src_base = src; |
df7492f9 | 5384 | ONE_MORE_BYTE (c); |
065e3595 KH |
5385 | if (c < 0) |
5386 | continue; | |
716b3fa0 KH |
5387 | val = AREF (valids, c); |
5388 | if (NILP (val)) | |
df7492f9 | 5389 | break; |
584948ac | 5390 | if (c >= 0x80) |
07295713 KH |
5391 | { |
5392 | if (c < 0xA0 | |
237aabf4 JR |
5393 | && check_latin_extra |
5394 | && (!VECTORP (Vlatin_extra_code_table) | |
28be1ada | 5395 | || NILP (AREF (Vlatin_extra_code_table, c)))) |
07295713 KH |
5396 | break; |
5397 | found = CATEGORY_MASK_CHARSET; | |
5398 | } | |
716b3fa0 KH |
5399 | if (INTEGERP (val)) |
5400 | { | |
5401 | charset = CHARSET_FROM_ID (XFASTINT (val)); | |
5402 | dim = CHARSET_DIMENSION (charset); | |
5403 | for (idx = 1; idx < dim; idx++) | |
5404 | { | |
5405 | if (src == src_end) | |
5406 | goto too_short; | |
5407 | ONE_MORE_BYTE (c); | |
2f9442b8 PE |
5408 | if (c < charset->code_space[(dim - 1 - idx) * 4] |
5409 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
716b3fa0 KH |
5410 | break; |
5411 | } | |
5412 | if (idx < dim) | |
5413 | break; | |
5414 | } | |
5415 | else | |
5416 | { | |
5417 | idx = 1; | |
5418 | for (; CONSP (val); val = XCDR (val)) | |
5419 | { | |
5420 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); | |
5421 | dim = CHARSET_DIMENSION (charset); | |
5422 | while (idx < dim) | |
5423 | { | |
5424 | if (src == src_end) | |
5425 | goto too_short; | |
5426 | ONE_MORE_BYTE (c); | |
5427 | if (c < charset->code_space[(dim - 1 - idx) * 4] | |
5428 | || c > charset->code_space[(dim - 1 - idx) * 4 + 1]) | |
5429 | break; | |
5430 | idx++; | |
5431 | } | |
5432 | if (idx == dim) | |
5433 | { | |
5434 | val = Qnil; | |
5435 | break; | |
5436 | } | |
5437 | } | |
5438 | if (CONSP (val)) | |
5439 | break; | |
5440 | } | |
df7492f9 | 5441 | } |
716b3fa0 | 5442 | too_short: |
ff0dacd7 | 5443 | detect_info->rejected |= CATEGORY_MASK_CHARSET; |
df7492f9 | 5444 | return 0; |
4ed46869 | 5445 | |
df7492f9 | 5446 | no_more_source: |
ff0dacd7 KH |
5447 | detect_info->found |= found; |
5448 | return 1; | |
df7492f9 | 5449 | } |
b73bfc1c | 5450 | |
b73bfc1c | 5451 | static void |
971de7fb | 5452 | decode_coding_charset (struct coding_system *coding) |
4ed46869 | 5453 | { |
8f924df7 KH |
5454 | const unsigned char *src = coding->source + coding->consumed; |
5455 | const unsigned char *src_end = coding->source + coding->src_bytes; | |
5456 | const unsigned char *src_base; | |
69a80ea3 | 5457 | int *charbuf = coding->charbuf + coding->charbuf_used; |
ad1746f5 | 5458 | /* We may produce one charset annotation in one loop and one more at |
df80c7f0 | 5459 | the end. */ |
69a80ea3 | 5460 | int *charbuf_end |
df80c7f0 | 5461 | = coding->charbuf + coding->charbuf_size - (MAX_ANNOTATION_LENGTH * 2); |
d311d28c | 5462 | ptrdiff_t consumed_chars = 0, consumed_chars_base; |
f10fe38f | 5463 | bool multibytep = coding->src_multibyte; |
66ebf983 PE |
5464 | Lisp_Object attrs = CODING_ID_ATTRS (coding->id); |
5465 | Lisp_Object valids; | |
d311d28c PE |
5466 | ptrdiff_t char_offset = coding->produced_char; |
5467 | ptrdiff_t last_offset = char_offset; | |
ff0dacd7 | 5468 | int last_id = charset_ascii; |
f10fe38f PE |
5469 | bool eol_dos |
5470 | = !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos); | |
119852e7 | 5471 | int byte_after_cr = -1; |
df7492f9 | 5472 | |
4eb6d3f1 | 5473 | valids = AREF (attrs, coding_attr_charset_valids); |
b73bfc1c | 5474 | |
df7492f9 | 5475 | while (1) |
4ed46869 | 5476 | { |
4eb6d3f1 | 5477 | int c; |
24a73b0a KH |
5478 | Lisp_Object val; |
5479 | struct charset *charset; | |
5480 | int dim; | |
5481 | int len = 1; | |
5482 | unsigned code; | |
df7492f9 KH |
5483 | |
5484 | src_base = src; | |
5485 | consumed_chars_base = consumed_chars; | |
b73bfc1c | 5486 | |
df7492f9 | 5487 | if (charbuf >= charbuf_end) |
b71f6f73 KH |
5488 | { |
5489 | if (byte_after_cr >= 0) | |
5490 | src_base--; | |
5491 | break; | |
5492 | } | |
df7492f9 | 5493 | |
119852e7 KH |
5494 | if (byte_after_cr >= 0) |
5495 | { | |
5496 | c = byte_after_cr; | |
5497 | byte_after_cr = -1; | |
5498 | } | |
5499 | else | |
5500 | { | |
5501 | ONE_MORE_BYTE (c); | |
2735d060 | 5502 | if (eol_dos && c == '\r') |
119852e7 KH |
5503 | ONE_MORE_BYTE (byte_after_cr); |
5504 | } | |
065e3595 KH |
5505 | if (c < 0) |
5506 | goto invalid_code; | |
24a73b0a KH |
5507 | code = c; |
5508 | ||
5509 | val = AREF (valids, c); | |
1b17adfd | 5510 | if (! INTEGERP (val) && ! CONSP (val)) |
24a73b0a KH |
5511 | goto invalid_code; |
5512 | if (INTEGERP (val)) | |
d46c5b12 | 5513 | { |
24a73b0a KH |
5514 | charset = CHARSET_FROM_ID (XFASTINT (val)); |
5515 | dim = CHARSET_DIMENSION (charset); | |
5516 | while (len < dim) | |
b73bfc1c | 5517 | { |
24a73b0a KH |
5518 | ONE_MORE_BYTE (c); |
5519 | code = (code << 8) | c; | |
5520 | len++; | |
b73bfc1c | 5521 | } |
24a73b0a KH |
5522 | CODING_DECODE_CHAR (coding, src, src_base, src_end, |
5523 | charset, code, c); | |
d46c5b12 | 5524 | } |
df7492f9 | 5525 | else |
d46c5b12 | 5526 | { |
24a73b0a KH |
5527 | /* VAL is a list of charset IDs. It is assured that the |
5528 | list is sorted by charset dimensions (smaller one | |
5529 | comes first). */ | |
5530 | while (CONSP (val)) | |
4eb6d3f1 | 5531 | { |
24a73b0a | 5532 | charset = CHARSET_FROM_ID (XFASTINT (XCAR (val))); |
c7c66a95 | 5533 | dim = CHARSET_DIMENSION (charset); |
f9d71dcd | 5534 | while (len < dim) |
4eb6d3f1 | 5535 | { |
acb2a965 KH |
5536 | ONE_MORE_BYTE (c); |
5537 | code = (code << 8) | c; | |
f9d71dcd | 5538 | len++; |
4eb6d3f1 | 5539 | } |
24a73b0a KH |
5540 | CODING_DECODE_CHAR (coding, src, src_base, |
5541 | src_end, charset, code, c); | |
5542 | if (c >= 0) | |
5543 | break; | |
5544 | val = XCDR (val); | |
ff0dacd7 | 5545 | } |
d46c5b12 | 5546 | } |
24a73b0a KH |
5547 | if (c < 0) |
5548 | goto invalid_code; | |
5549 | if (charset->id != charset_ascii | |
5550 | && last_id != charset->id) | |
5551 | { | |
5552 | if (last_id != charset_ascii) | |
69a80ea3 | 5553 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
24a73b0a KH |
5554 | last_id = charset->id; |
5555 | last_offset = char_offset; | |
5556 | } | |
5557 | ||
df7492f9 | 5558 | *charbuf++ = c; |
ff0dacd7 | 5559 | char_offset++; |
df7492f9 KH |
5560 | continue; |
5561 | ||
5562 | invalid_code: | |
5563 | src = src_base; | |
5564 | consumed_chars = consumed_chars_base; | |
5565 | ONE_MORE_BYTE (c); | |
065e3595 | 5566 | *charbuf++ = c < 0 ? -c : ASCII_BYTE_P (c) ? c : BYTE8_TO_CHAR (c); |
ff0dacd7 | 5567 | char_offset++; |
df7492f9 | 5568 | coding->errors++; |
4ed46869 KH |
5569 | } |
5570 | ||
df7492f9 | 5571 | no_more_source: |
ff0dacd7 | 5572 | if (last_id != charset_ascii) |
69a80ea3 | 5573 | ADD_CHARSET_DATA (charbuf, char_offset - last_offset, last_id); |
df7492f9 KH |
5574 | coding->consumed_char += consumed_chars_base; |
5575 | coding->consumed = src_base - coding->source; | |
5576 | coding->charbuf_used = charbuf - coding->charbuf; | |
4ed46869 KH |
5577 | } |
5578 | ||
f10fe38f | 5579 | static bool |
971de7fb | 5580 | encode_coding_charset (struct coding_system *coding) |
4ed46869 | 5581 | { |
f10fe38f | 5582 | bool multibytep = coding->dst_multibyte; |
df7492f9 KH |
5583 | int *charbuf = coding->charbuf; |
5584 | int *charbuf_end = charbuf + coding->charbuf_used; | |
5585 | unsigned char *dst = coding->destination + coding->produced; | |
5586 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
5587 | int safe_room = MAX_MULTIBYTE_LENGTH; | |
d311d28c | 5588 | ptrdiff_t produced_chars = 0; |
24a73b0a | 5589 | Lisp_Object attrs, charset_list; |
f10fe38f | 5590 | bool ascii_compatible; |
b73bfc1c | 5591 | int c; |
b73bfc1c | 5592 | |
24a73b0a | 5593 | CODING_GET_INFO (coding, attrs, charset_list); |
df7492f9 | 5594 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); |
fb88bf2d | 5595 | |
df7492f9 | 5596 | while (charbuf < charbuf_end) |
4ed46869 | 5597 | { |
4eb6d3f1 | 5598 | struct charset *charset; |
df7492f9 | 5599 | unsigned code; |
8f924df7 | 5600 | |
df7492f9 KH |
5601 | ASSURE_DESTINATION (safe_room); |
5602 | c = *charbuf++; | |
5603 | if (ascii_compatible && ASCII_CHAR_P (c)) | |
5604 | EMIT_ONE_ASCII_BYTE (c); | |
16eafb5d | 5605 | else if (CHAR_BYTE8_P (c)) |
4ed46869 | 5606 | { |
16eafb5d KH |
5607 | c = CHAR_TO_BYTE8 (c); |
5608 | EMIT_ONE_BYTE (c); | |
d46c5b12 | 5609 | } |
d46c5b12 | 5610 | else |
b73bfc1c | 5611 | { |
5eb05ea3 KH |
5612 | CODING_CHAR_CHARSET (coding, dst, dst_end, c, charset_list, |
5613 | &code, charset); | |
5614 | ||
4eb6d3f1 KH |
5615 | if (charset) |
5616 | { | |
5617 | if (CHARSET_DIMENSION (charset) == 1) | |
5618 | EMIT_ONE_BYTE (code); | |
5619 | else if (CHARSET_DIMENSION (charset) == 2) | |
5620 | EMIT_TWO_BYTES (code >> 8, code & 0xFF); | |
5621 | else if (CHARSET_DIMENSION (charset) == 3) | |
5622 | EMIT_THREE_BYTES (code >> 16, (code >> 8) & 0xFF, code & 0xFF); | |
5623 | else | |
5624 | EMIT_FOUR_BYTES (code >> 24, (code >> 16) & 0xFF, | |
5625 | (code >> 8) & 0xFF, code & 0xFF); | |
5626 | } | |
5627 | else | |
41cbe562 KH |
5628 | { |
5629 | if (coding->mode & CODING_MODE_SAFE_ENCODING) | |
5630 | c = CODING_INHIBIT_CHARACTER_SUBSTITUTION; | |
5631 | else | |
5632 | c = coding->default_char; | |
5633 | EMIT_ONE_BYTE (c); | |
5634 | } | |
4ed46869 | 5635 | } |
4ed46869 KH |
5636 | } |
5637 | ||
065e3595 | 5638 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 KH |
5639 | coding->produced_char += produced_chars; |
5640 | coding->produced = dst - coding->destination; | |
5641 | return 0; | |
4ed46869 KH |
5642 | } |
5643 | ||
5644 | \f | |
1397dc18 | 5645 | /*** 7. C library functions ***/ |
4ed46869 | 5646 | |
df7492f9 KH |
5647 | /* Setup coding context CODING from information about CODING_SYSTEM. |
5648 | If CODING_SYSTEM is nil, `no-conversion' is assumed. If | |
5649 | CODING_SYSTEM is invalid, signal an error. */ | |
4ed46869 | 5650 | |
ec6d2bb8 | 5651 | void |
971de7fb | 5652 | setup_coding_system (Lisp_Object coding_system, struct coding_system *coding) |
4ed46869 | 5653 | { |
df7492f9 KH |
5654 | Lisp_Object attrs; |
5655 | Lisp_Object eol_type; | |
5656 | Lisp_Object coding_type; | |
4608c386 | 5657 | Lisp_Object val; |
4ed46869 | 5658 | |
df7492f9 | 5659 | if (NILP (coding_system)) |
ae6f73fa | 5660 | coding_system = Qundecided; |
c07c8e12 | 5661 | |
df7492f9 | 5662 | CHECK_CODING_SYSTEM_GET_ID (coding_system, coding->id); |
1f5dbf34 | 5663 | |
df7492f9 | 5664 | attrs = CODING_ID_ATTRS (coding->id); |
0a9564cb | 5665 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
1f5dbf34 | 5666 | |
df7492f9 KH |
5667 | coding->mode = 0; |
5668 | coding->head_ascii = -1; | |
4a015c45 KH |
5669 | if (VECTORP (eol_type)) |
5670 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5671 | | CODING_REQUIRE_DETECTION_MASK); | |
5672 | else if (! EQ (eol_type, Qunix)) | |
5673 | coding->common_flags = (CODING_REQUIRE_DECODING_MASK | |
5674 | | CODING_REQUIRE_ENCODING_MASK); | |
5675 | else | |
5676 | coding->common_flags = 0; | |
5e5c78be KH |
5677 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
5678 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5679 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) | |
5680 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
8f924df7 KH |
5681 | if (! NILP (CODING_ATTR_FOR_UNIBYTE (attrs))) |
5682 | coding->common_flags |= CODING_FOR_UNIBYTE_MASK; | |
1f5dbf34 | 5683 | |
df7492f9 | 5684 | val = CODING_ATTR_SAFE_CHARSETS (attrs); |
8f924df7 | 5685 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5686 | coding->safe_charsets = SDATA (val); |
df7492f9 | 5687 | coding->default_char = XINT (CODING_ATTR_DEFAULT_CHAR (attrs)); |
624bda09 | 5688 | coding->carryover_bytes = 0; |
4608c386 | 5689 | |
df7492f9 KH |
5690 | coding_type = CODING_ATTR_TYPE (attrs); |
5691 | if (EQ (coding_type, Qundecided)) | |
d46c5b12 | 5692 | { |
df7492f9 KH |
5693 | coding->detector = NULL; |
5694 | coding->decoder = decode_coding_raw_text; | |
5695 | coding->encoder = encode_coding_raw_text; | |
5696 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
d46c5b12 | 5697 | } |
df7492f9 | 5698 | else if (EQ (coding_type, Qiso_2022)) |
d46c5b12 | 5699 | { |
df7492f9 KH |
5700 | int i; |
5701 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5702 | ||
5703 | /* Invoke graphic register 0 to plane 0. */ | |
5704 | CODING_ISO_INVOCATION (coding, 0) = 0; | |
5705 | /* Invoke graphic register 1 to plane 1 if we can use 8-bit. */ | |
5706 | CODING_ISO_INVOCATION (coding, 1) | |
5707 | = (flags & CODING_ISO_FLAG_SEVEN_BITS ? -1 : 1); | |
5708 | /* Setup the initial status of designation. */ | |
5709 | for (i = 0; i < 4; i++) | |
5710 | CODING_ISO_DESIGNATION (coding, i) = CODING_ISO_INITIAL (coding, i); | |
5711 | /* Not single shifting initially. */ | |
5712 | CODING_ISO_SINGLE_SHIFTING (coding) = 0; | |
5713 | /* Beginning of buffer should also be regarded as bol. */ | |
5714 | CODING_ISO_BOL (coding) = 1; | |
5715 | coding->detector = detect_coding_iso_2022; | |
5716 | coding->decoder = decode_coding_iso_2022; | |
5717 | coding->encoder = encode_coding_iso_2022; | |
5718 | if (flags & CODING_ISO_FLAG_SAFE) | |
5719 | coding->mode |= CODING_MODE_SAFE_ENCODING; | |
d46c5b12 | 5720 | coding->common_flags |
df7492f9 KH |
5721 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5722 | | CODING_REQUIRE_FLUSHING_MASK); | |
5723 | if (flags & CODING_ISO_FLAG_COMPOSITION) | |
5724 | coding->common_flags |= CODING_ANNOTATE_COMPOSITION_MASK; | |
ff0dacd7 KH |
5725 | if (flags & CODING_ISO_FLAG_DESIGNATION) |
5726 | coding->common_flags |= CODING_ANNOTATE_CHARSET_MASK; | |
df7492f9 KH |
5727 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) |
5728 | { | |
5729 | setup_iso_safe_charsets (attrs); | |
5730 | val = CODING_ATTR_SAFE_CHARSETS (attrs); | |
8f924df7 | 5731 | coding->max_charset_id = SCHARS (val) - 1; |
1b3b981b | 5732 | coding->safe_charsets = SDATA (val); |
df7492f9 KH |
5733 | } |
5734 | CODING_ISO_FLAGS (coding) = flags; | |
e951386e KH |
5735 | CODING_ISO_CMP_STATUS (coding)->state = COMPOSING_NO; |
5736 | CODING_ISO_CMP_STATUS (coding)->method = COMPOSITION_NO; | |
5737 | CODING_ISO_EXTSEGMENT_LEN (coding) = 0; | |
5738 | CODING_ISO_EMBEDDED_UTF_8 (coding) = 0; | |
d46c5b12 | 5739 | } |
df7492f9 | 5740 | else if (EQ (coding_type, Qcharset)) |
d46c5b12 | 5741 | { |
df7492f9 KH |
5742 | coding->detector = detect_coding_charset; |
5743 | coding->decoder = decode_coding_charset; | |
5744 | coding->encoder = encode_coding_charset; | |
d46c5b12 | 5745 | coding->common_flags |
df7492f9 | 5746 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
d46c5b12 | 5747 | } |
df7492f9 | 5748 | else if (EQ (coding_type, Qutf_8)) |
d46c5b12 | 5749 | { |
a470d443 KH |
5750 | val = AREF (attrs, coding_attr_utf_bom); |
5751 | CODING_UTF_8_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5752 | : EQ (val, Qt) ? utf_with_bom | |
5753 | : utf_without_bom); | |
df7492f9 KH |
5754 | coding->detector = detect_coding_utf_8; |
5755 | coding->decoder = decode_coding_utf_8; | |
5756 | coding->encoder = encode_coding_utf_8; | |
5757 | coding->common_flags | |
5758 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 KH |
5759 | if (CODING_UTF_8_BOM (coding) == utf_detect_bom) |
5760 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; | |
df7492f9 KH |
5761 | } |
5762 | else if (EQ (coding_type, Qutf_16)) | |
5763 | { | |
a470d443 KH |
5764 | val = AREF (attrs, coding_attr_utf_bom); |
5765 | CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_detect_bom | |
5766 | : EQ (val, Qt) ? utf_with_bom | |
5767 | : utf_without_bom); | |
df7492f9 | 5768 | val = AREF (attrs, coding_attr_utf_16_endian); |
b49a1807 | 5769 | CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian |
df7492f9 | 5770 | : utf_16_little_endian); |
e19c3639 | 5771 | CODING_UTF_16_SURROGATE (coding) = 0; |
df7492f9 KH |
5772 | coding->detector = detect_coding_utf_16; |
5773 | coding->decoder = decode_coding_utf_16; | |
5774 | coding->encoder = encode_coding_utf_16; | |
5775 | coding->common_flags | |
5776 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); | |
a470d443 | 5777 | if (CODING_UTF_16_BOM (coding) == utf_detect_bom) |
b49a1807 | 5778 | coding->common_flags |= CODING_REQUIRE_DETECTION_MASK; |
d46c5b12 | 5779 | } |
df7492f9 | 5780 | else if (EQ (coding_type, Qccl)) |
4ed46869 | 5781 | { |
df7492f9 KH |
5782 | coding->detector = detect_coding_ccl; |
5783 | coding->decoder = decode_coding_ccl; | |
5784 | coding->encoder = encode_coding_ccl; | |
c952af22 | 5785 | coding->common_flags |
df7492f9 KH |
5786 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK |
5787 | | CODING_REQUIRE_FLUSHING_MASK); | |
5788 | } | |
5789 | else if (EQ (coding_type, Qemacs_mule)) | |
5790 | { | |
5791 | coding->detector = detect_coding_emacs_mule; | |
5792 | coding->decoder = decode_coding_emacs_mule; | |
5793 | coding->encoder = encode_coding_emacs_mule; | |
c952af22 | 5794 | coding->common_flags |
df7492f9 KH |
5795 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5796 | if (! NILP (AREF (attrs, coding_attr_emacs_mule_full)) | |
5797 | && ! EQ (CODING_ATTR_CHARSET_LIST (attrs), Vemacs_mule_charset_list)) | |
5798 | { | |
5799 | Lisp_Object tail, safe_charsets; | |
5800 | int max_charset_id = 0; | |
5801 | ||
5802 | for (tail = Vemacs_mule_charset_list; CONSP (tail); | |
5803 | tail = XCDR (tail)) | |
5804 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
5805 | max_charset_id = XFASTINT (XCAR (tail)); | |
1b3b981b AS |
5806 | safe_charsets = make_uninit_string (max_charset_id + 1); |
5807 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 KH |
5808 | for (tail = Vemacs_mule_charset_list; CONSP (tail); |
5809 | tail = XCDR (tail)) | |
8f924df7 | 5810 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
df7492f9 | 5811 | coding->max_charset_id = max_charset_id; |
1b3b981b | 5812 | coding->safe_charsets = SDATA (safe_charsets); |
df7492f9 | 5813 | } |
e951386e KH |
5814 | coding->spec.emacs_mule.cmp_status.state = COMPOSING_NO; |
5815 | coding->spec.emacs_mule.cmp_status.method = COMPOSITION_NO; | |
df7492f9 KH |
5816 | } |
5817 | else if (EQ (coding_type, Qshift_jis)) | |
5818 | { | |
5819 | coding->detector = detect_coding_sjis; | |
5820 | coding->decoder = decode_coding_sjis; | |
5821 | coding->encoder = encode_coding_sjis; | |
c952af22 | 5822 | coding->common_flags |
df7492f9 KH |
5823 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5824 | } | |
5825 | else if (EQ (coding_type, Qbig5)) | |
5826 | { | |
5827 | coding->detector = detect_coding_big5; | |
5828 | coding->decoder = decode_coding_big5; | |
5829 | coding->encoder = encode_coding_big5; | |
c952af22 | 5830 | coding->common_flags |
df7492f9 KH |
5831 | |= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK); |
5832 | } | |
5833 | else /* EQ (coding_type, Qraw_text) */ | |
ec6d2bb8 | 5834 | { |
df7492f9 KH |
5835 | coding->detector = NULL; |
5836 | coding->decoder = decode_coding_raw_text; | |
5837 | coding->encoder = encode_coding_raw_text; | |
ea29edf2 KH |
5838 | if (! EQ (eol_type, Qunix)) |
5839 | { | |
5840 | coding->common_flags |= CODING_REQUIRE_DECODING_MASK; | |
5841 | if (! VECTORP (eol_type)) | |
5842 | coding->common_flags |= CODING_REQUIRE_ENCODING_MASK; | |
5843 | } | |
5844 | ||
4ed46869 | 5845 | } |
4ed46869 | 5846 | |
df7492f9 | 5847 | return; |
4ed46869 KH |
5848 | } |
5849 | ||
0ff61e78 KH |
5850 | /* Return a list of charsets supported by CODING. */ |
5851 | ||
5852 | Lisp_Object | |
971de7fb | 5853 | coding_charset_list (struct coding_system *coding) |
0ff61e78 | 5854 | { |
35befdaa | 5855 | Lisp_Object attrs, charset_list; |
0ff61e78 KH |
5856 | |
5857 | CODING_GET_INFO (coding, attrs, charset_list); | |
5858 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5859 | { | |
5860 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5861 | ||
5862 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5863 | charset_list = Viso_2022_charset_list; | |
5864 | } | |
5865 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5866 | { | |
5867 | charset_list = Vemacs_mule_charset_list; | |
5868 | } | |
5869 | return charset_list; | |
5870 | } | |
5871 | ||
5872 | ||
e9f91ece KH |
5873 | /* Return a list of charsets supported by CODING-SYSTEM. */ |
5874 | ||
5875 | Lisp_Object | |
971de7fb | 5876 | coding_system_charset_list (Lisp_Object coding_system) |
e9f91ece | 5877 | { |
d3411f89 | 5878 | ptrdiff_t id; |
e9f91ece KH |
5879 | Lisp_Object attrs, charset_list; |
5880 | ||
5881 | CHECK_CODING_SYSTEM_GET_ID (coding_system, id); | |
5882 | attrs = CODING_ID_ATTRS (id); | |
5883 | ||
5884 | if (EQ (CODING_ATTR_TYPE (attrs), Qiso_2022)) | |
5885 | { | |
5886 | int flags = XINT (AREF (attrs, coding_attr_iso_flags)); | |
5887 | ||
5888 | if (flags & CODING_ISO_FLAG_FULL_SUPPORT) | |
5889 | charset_list = Viso_2022_charset_list; | |
5890 | else | |
5891 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5892 | } | |
5893 | else if (EQ (CODING_ATTR_TYPE (attrs), Qemacs_mule)) | |
5894 | { | |
5895 | charset_list = Vemacs_mule_charset_list; | |
5896 | } | |
5897 | else | |
5898 | { | |
5899 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
5900 | } | |
5901 | return charset_list; | |
5902 | } | |
5903 | ||
5904 | ||
df7492f9 KH |
5905 | /* Return raw-text or one of its subsidiaries that has the same |
5906 | eol_type as CODING-SYSTEM. */ | |
ec6d2bb8 | 5907 | |
df7492f9 | 5908 | Lisp_Object |
971de7fb | 5909 | raw_text_coding_system (Lisp_Object coding_system) |
ec6d2bb8 | 5910 | { |
0be8721c | 5911 | Lisp_Object spec, attrs; |
df7492f9 | 5912 | Lisp_Object eol_type, raw_text_eol_type; |
ec6d2bb8 | 5913 | |
d3e4cb56 KH |
5914 | if (NILP (coding_system)) |
5915 | return Qraw_text; | |
df7492f9 KH |
5916 | spec = CODING_SYSTEM_SPEC (coding_system); |
5917 | attrs = AREF (spec, 0); | |
ec6d2bb8 | 5918 | |
df7492f9 KH |
5919 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) |
5920 | return coding_system; | |
ec6d2bb8 | 5921 | |
df7492f9 KH |
5922 | eol_type = AREF (spec, 2); |
5923 | if (VECTORP (eol_type)) | |
5924 | return Qraw_text; | |
5925 | spec = CODING_SYSTEM_SPEC (Qraw_text); | |
5926 | raw_text_eol_type = AREF (spec, 2); | |
5927 | return (EQ (eol_type, Qunix) ? AREF (raw_text_eol_type, 0) | |
5928 | : EQ (eol_type, Qdos) ? AREF (raw_text_eol_type, 1) | |
5929 | : AREF (raw_text_eol_type, 2)); | |
ec6d2bb8 KH |
5930 | } |
5931 | ||
54f78171 | 5932 | |
1911a33b KH |
5933 | /* If CODING_SYSTEM doesn't specify end-of-line format, return one of |
5934 | the subsidiary that has the same eol-spec as PARENT (if it is not | |
5935 | nil and specifies end-of-line format) or the system's setting | |
fcbcfb64 | 5936 | (system_eol_type). */ |
df7492f9 KH |
5937 | |
5938 | Lisp_Object | |
971de7fb | 5939 | coding_inherit_eol_type (Lisp_Object coding_system, Lisp_Object parent) |
54f78171 | 5940 | { |
3e139625 | 5941 | Lisp_Object spec, eol_type; |
54f78171 | 5942 | |
d3e4cb56 KH |
5943 | if (NILP (coding_system)) |
5944 | coding_system = Qraw_text; | |
df7492f9 | 5945 | spec = CODING_SYSTEM_SPEC (coding_system); |
df7492f9 | 5946 | eol_type = AREF (spec, 2); |
fcbcfb64 | 5947 | if (VECTORP (eol_type)) |
df7492f9 | 5948 | { |
df7492f9 KH |
5949 | Lisp_Object parent_eol_type; |
5950 | ||
fcbcfb64 KH |
5951 | if (! NILP (parent)) |
5952 | { | |
5953 | Lisp_Object parent_spec; | |
5954 | ||
4a015c45 | 5955 | parent_spec = CODING_SYSTEM_SPEC (parent); |
fcbcfb64 | 5956 | parent_eol_type = AREF (parent_spec, 2); |
1911a33b | 5957 | if (VECTORP (parent_eol_type)) |
4628bef1 | 5958 | parent_eol_type = system_eol_type; |
fcbcfb64 KH |
5959 | } |
5960 | else | |
5961 | parent_eol_type = system_eol_type; | |
df7492f9 KH |
5962 | if (EQ (parent_eol_type, Qunix)) |
5963 | coding_system = AREF (eol_type, 0); | |
5964 | else if (EQ (parent_eol_type, Qdos)) | |
5965 | coding_system = AREF (eol_type, 1); | |
5966 | else if (EQ (parent_eol_type, Qmac)) | |
5967 | coding_system = AREF (eol_type, 2); | |
54f78171 | 5968 | } |
df7492f9 | 5969 | return coding_system; |
54f78171 KH |
5970 | } |
5971 | ||
fcaf8878 KH |
5972 | |
5973 | /* Check if text-conversion and eol-conversion of CODING_SYSTEM are | |
5974 | decided for writing to a process. If not, complement them, and | |
5975 | return a new coding system. */ | |
5976 | ||
5977 | Lisp_Object | |
4628bef1 | 5978 | complement_process_encoding_system (Lisp_Object coding_system) |
fcaf8878 | 5979 | { |
5886ec9c KH |
5980 | Lisp_Object coding_base = Qnil, eol_base = Qnil; |
5981 | Lisp_Object spec, attrs; | |
93d50df8 | 5982 | int i; |
fcaf8878 | 5983 | |
93d50df8 | 5984 | for (i = 0; i < 3; i++) |
fcaf8878 | 5985 | { |
93d50df8 KH |
5986 | if (i == 1) |
5987 | coding_system = CDR_SAFE (Vdefault_process_coding_system); | |
5988 | else if (i == 2) | |
5989 | coding_system = preferred_coding_system (); | |
5990 | spec = CODING_SYSTEM_SPEC (coding_system); | |
5991 | if (NILP (spec)) | |
5992 | continue; | |
5993 | attrs = AREF (spec, 0); | |
5994 | if (NILP (coding_base) && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
5995 | coding_base = CODING_ATTR_BASE_NAME (attrs); | |
5996 | if (NILP (eol_base) && ! VECTORP (AREF (spec, 2))) | |
5997 | eol_base = coding_system; | |
5998 | if (! NILP (coding_base) && ! NILP (eol_base)) | |
5999 | break; | |
fcaf8878 | 6000 | } |
fcaf8878 | 6001 | |
93d50df8 KH |
6002 | if (i > 0) |
6003 | /* The original CODING_SYSTEM didn't specify text-conversion or | |
6004 | eol-conversion. Be sure that we return a fully complemented | |
6005 | coding system. */ | |
6006 | coding_system = coding_inherit_eol_type (coding_base, eol_base); | |
6007 | return coding_system; | |
fcaf8878 KH |
6008 | } |
6009 | ||
6010 | ||
4ed46869 KH |
6011 | /* Emacs has a mechanism to automatically detect a coding system if it |
6012 | is one of Emacs' internal format, ISO2022, SJIS, and BIG5. But, | |
6013 | it's impossible to distinguish some coding systems accurately | |
6014 | because they use the same range of codes. So, at first, coding | |
6015 | systems are categorized into 7, those are: | |
6016 | ||
0ef69138 | 6017 | o coding-category-emacs-mule |
4ed46869 KH |
6018 | |
6019 | The category for a coding system which has the same code range | |
6020 | as Emacs' internal format. Assigned the coding-system (Lisp | |
0ef69138 | 6021 | symbol) `emacs-mule' by default. |
4ed46869 KH |
6022 | |
6023 | o coding-category-sjis | |
6024 | ||
6025 | The category for a coding system which has the same code range | |
6026 | as SJIS. Assigned the coding-system (Lisp | |
7717c392 | 6027 | symbol) `japanese-shift-jis' by default. |
4ed46869 KH |
6028 | |
6029 | o coding-category-iso-7 | |
6030 | ||
6031 | The category for a coding system which has the same code range | |
7717c392 | 6032 | as ISO2022 of 7-bit environment. This doesn't use any locking |
d46c5b12 KH |
6033 | shift and single shift functions. This can encode/decode all |
6034 | charsets. Assigned the coding-system (Lisp symbol) | |
6035 | `iso-2022-7bit' by default. | |
6036 | ||
6037 | o coding-category-iso-7-tight | |
6038 | ||
6039 | Same as coding-category-iso-7 except that this can | |
6040 | encode/decode only the specified charsets. | |
4ed46869 KH |
6041 | |
6042 | o coding-category-iso-8-1 | |
6043 | ||
6044 | The category for a coding system which has the same code range | |
6045 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6046 | for DIMENSION1 charset. This doesn't use any locking shift |
6047 | and single shift functions. Assigned the coding-system (Lisp | |
6048 | symbol) `iso-latin-1' by default. | |
4ed46869 KH |
6049 | |
6050 | o coding-category-iso-8-2 | |
6051 | ||
6052 | The category for a coding system which has the same code range | |
6053 | as ISO2022 of 8-bit environment and graphic plane 1 used only | |
7717c392 KH |
6054 | for DIMENSION2 charset. This doesn't use any locking shift |
6055 | and single shift functions. Assigned the coding-system (Lisp | |
6056 | symbol) `japanese-iso-8bit' by default. | |
4ed46869 | 6057 | |
7717c392 | 6058 | o coding-category-iso-7-else |
4ed46869 KH |
6059 | |
6060 | The category for a coding system which has the same code range | |
ad1746f5 | 6061 | as ISO2022 of 7-bit environment but uses locking shift or |
7717c392 KH |
6062 | single shift functions. Assigned the coding-system (Lisp |
6063 | symbol) `iso-2022-7bit-lock' by default. | |
6064 | ||
6065 | o coding-category-iso-8-else | |
6066 | ||
6067 | The category for a coding system which has the same code range | |
ad1746f5 | 6068 | as ISO2022 of 8-bit environment but uses locking shift or |
7717c392 KH |
6069 | single shift functions. Assigned the coding-system (Lisp |
6070 | symbol) `iso-2022-8bit-ss2' by default. | |
4ed46869 KH |
6071 | |
6072 | o coding-category-big5 | |
6073 | ||
6074 | The category for a coding system which has the same code range | |
6075 | as BIG5. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6076 | `cn-big5' by default. |
4ed46869 | 6077 | |
fa42c37f KH |
6078 | o coding-category-utf-8 |
6079 | ||
6080 | The category for a coding system which has the same code range | |
6e76ae91 | 6081 | as UTF-8 (cf. RFC3629). Assigned the coding-system (Lisp |
fa42c37f KH |
6082 | symbol) `utf-8' by default. |
6083 | ||
6084 | o coding-category-utf-16-be | |
6085 | ||
6086 | The category for a coding system in which a text has an | |
6087 | Unicode signature (cf. Unicode Standard) in the order of BIG | |
6088 | endian at the head. Assigned the coding-system (Lisp symbol) | |
6089 | `utf-16-be' by default. | |
6090 | ||
6091 | o coding-category-utf-16-le | |
6092 | ||
6093 | The category for a coding system in which a text has an | |
6094 | Unicode signature (cf. Unicode Standard) in the order of | |
6095 | LITTLE endian at the head. Assigned the coding-system (Lisp | |
6096 | symbol) `utf-16-le' by default. | |
6097 | ||
1397dc18 KH |
6098 | o coding-category-ccl |
6099 | ||
6100 | The category for a coding system of which encoder/decoder is | |
6101 | written in CCL programs. The default value is nil, i.e., no | |
6102 | coding system is assigned. | |
6103 | ||
4ed46869 KH |
6104 | o coding-category-binary |
6105 | ||
6106 | The category for a coding system not categorized in any of the | |
6107 | above. Assigned the coding-system (Lisp symbol) | |
e0e989f6 | 6108 | `no-conversion' by default. |
4ed46869 KH |
6109 | |
6110 | Each of them is a Lisp symbol and the value is an actual | |
df7492f9 | 6111 | `coding-system's (this is also a Lisp symbol) assigned by a user. |
4ed46869 KH |
6112 | What Emacs does actually is to detect a category of coding system. |
6113 | Then, it uses a `coding-system' assigned to it. If Emacs can't | |
df7492f9 | 6114 | decide only one possible category, it selects a category of the |
4ed46869 KH |
6115 | highest priority. Priorities of categories are also specified by a |
6116 | user in a Lisp variable `coding-category-list'. | |
6117 | ||
6118 | */ | |
6119 | ||
df7492f9 KH |
6120 | #define EOL_SEEN_NONE 0 |
6121 | #define EOL_SEEN_LF 1 | |
6122 | #define EOL_SEEN_CR 2 | |
6123 | #define EOL_SEEN_CRLF 4 | |
66cfb530 | 6124 | |
ff0dacd7 KH |
6125 | /* Detect how end-of-line of a text of length SRC_BYTES pointed by |
6126 | SOURCE is encoded. If CATEGORY is one of | |
6127 | coding_category_utf_16_XXXX, assume that CR and LF are encoded by | |
6128 | two-byte, else they are encoded by one-byte. | |
6129 | ||
6130 | Return one of EOL_SEEN_XXX. */ | |
4ed46869 | 6131 | |
bc4bc72a | 6132 | #define MAX_EOL_CHECK_COUNT 3 |
d46c5b12 KH |
6133 | |
6134 | static int | |
d311d28c | 6135 | detect_eol (const unsigned char *source, ptrdiff_t src_bytes, |
cf84bb53 | 6136 | enum coding_category category) |
4ed46869 | 6137 | { |
f6cbaf43 | 6138 | const unsigned char *src = source, *src_end = src + src_bytes; |
4ed46869 | 6139 | unsigned char c; |
df7492f9 KH |
6140 | int total = 0; |
6141 | int eol_seen = EOL_SEEN_NONE; | |
4ed46869 | 6142 | |
89528eb3 | 6143 | if ((1 << category) & CATEGORY_MASK_UTF_16) |
4ed46869 | 6144 | { |
f10fe38f PE |
6145 | bool msb = category == (coding_category_utf_16_le |
6146 | | coding_category_utf_16_le_nosig); | |
6147 | bool lsb = !msb; | |
fa42c37f | 6148 | |
df7492f9 | 6149 | while (src + 1 < src_end) |
fa42c37f | 6150 | { |
df7492f9 KH |
6151 | c = src[lsb]; |
6152 | if (src[msb] == 0 && (c == '\n' || c == '\r')) | |
fa42c37f | 6153 | { |
df7492f9 KH |
6154 | int this_eol; |
6155 | ||
6156 | if (c == '\n') | |
6157 | this_eol = EOL_SEEN_LF; | |
6158 | else if (src + 3 >= src_end | |
6159 | || src[msb + 2] != 0 | |
6160 | || src[lsb + 2] != '\n') | |
6161 | this_eol = EOL_SEEN_CR; | |
fa42c37f | 6162 | else |
75f4f1ac EZ |
6163 | { |
6164 | this_eol = EOL_SEEN_CRLF; | |
6165 | src += 2; | |
6166 | } | |
df7492f9 KH |
6167 | |
6168 | if (eol_seen == EOL_SEEN_NONE) | |
6169 | /* This is the first end-of-line. */ | |
6170 | eol_seen = this_eol; | |
6171 | else if (eol_seen != this_eol) | |
fa42c37f | 6172 | { |
75f4f1ac EZ |
6173 | /* The found type is different from what found before. |
6174 | Allow for stray ^M characters in DOS EOL files. */ | |
ef1b0ba7 SM |
6175 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) |
6176 | || (eol_seen == EOL_SEEN_CRLF | |
6177 | && this_eol == EOL_SEEN_CR)) | |
75f4f1ac EZ |
6178 | eol_seen = EOL_SEEN_CRLF; |
6179 | else | |
6180 | { | |
6181 | eol_seen = EOL_SEEN_LF; | |
6182 | break; | |
6183 | } | |
fa42c37f | 6184 | } |
df7492f9 KH |
6185 | if (++total == MAX_EOL_CHECK_COUNT) |
6186 | break; | |
fa42c37f | 6187 | } |
df7492f9 | 6188 | src += 2; |
fa42c37f | 6189 | } |
bcf26d6a | 6190 | } |
d46c5b12 | 6191 | else |
ef1b0ba7 SM |
6192 | while (src < src_end) |
6193 | { | |
6194 | c = *src++; | |
6195 | if (c == '\n' || c == '\r') | |
6196 | { | |
6197 | int this_eol; | |
d46c5b12 | 6198 | |
ef1b0ba7 SM |
6199 | if (c == '\n') |
6200 | this_eol = EOL_SEEN_LF; | |
6201 | else if (src >= src_end || *src != '\n') | |
6202 | this_eol = EOL_SEEN_CR; | |
6203 | else | |
6204 | this_eol = EOL_SEEN_CRLF, src++; | |
d46c5b12 | 6205 | |
ef1b0ba7 SM |
6206 | if (eol_seen == EOL_SEEN_NONE) |
6207 | /* This is the first end-of-line. */ | |
6208 | eol_seen = this_eol; | |
6209 | else if (eol_seen != this_eol) | |
6210 | { | |
6211 | /* The found type is different from what found before. | |
6212 | Allow for stray ^M characters in DOS EOL files. */ | |
6213 | if ((eol_seen == EOL_SEEN_CR && this_eol == EOL_SEEN_CRLF) | |
6214 | || (eol_seen == EOL_SEEN_CRLF && this_eol == EOL_SEEN_CR)) | |
6215 | eol_seen = EOL_SEEN_CRLF; | |
6216 | else | |
6217 | { | |
6218 | eol_seen = EOL_SEEN_LF; | |
6219 | break; | |
6220 | } | |
6221 | } | |
6222 | if (++total == MAX_EOL_CHECK_COUNT) | |
6223 | break; | |
6224 | } | |
6225 | } | |
df7492f9 | 6226 | return eol_seen; |
73be902c KH |
6227 | } |
6228 | ||
df7492f9 | 6229 | |
24a73b0a | 6230 | static Lisp_Object |
971de7fb | 6231 | adjust_coding_eol_type (struct coding_system *coding, int eol_seen) |
73be902c | 6232 | { |
0be8721c | 6233 | Lisp_Object eol_type; |
8f924df7 | 6234 | |
df7492f9 KH |
6235 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
6236 | if (eol_seen & EOL_SEEN_LF) | |
24a73b0a KH |
6237 | { |
6238 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 0)); | |
6239 | eol_type = Qunix; | |
6240 | } | |
6f197c07 | 6241 | else if (eol_seen & EOL_SEEN_CRLF) |
24a73b0a KH |
6242 | { |
6243 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 1)); | |
6244 | eol_type = Qdos; | |
6245 | } | |
6f197c07 | 6246 | else if (eol_seen & EOL_SEEN_CR) |
24a73b0a KH |
6247 | { |
6248 | coding->id = CODING_SYSTEM_ID (AREF (eol_type, 2)); | |
6249 | eol_type = Qmac; | |
6250 | } | |
6251 | return eol_type; | |
d46c5b12 | 6252 | } |
4ed46869 | 6253 | |
df7492f9 KH |
6254 | /* Detect how a text specified in CODING is encoded. If a coding |
6255 | system is detected, update fields of CODING by the detected coding | |
6256 | system. */ | |
0a28aafb | 6257 | |
74ab6df5 | 6258 | static void |
971de7fb | 6259 | detect_coding (struct coding_system *coding) |
d46c5b12 | 6260 | { |
8f924df7 | 6261 | const unsigned char *src, *src_end; |
f10fe38f | 6262 | unsigned int saved_mode = coding->mode; |
d46c5b12 | 6263 | |
df7492f9 KH |
6264 | coding->consumed = coding->consumed_char = 0; |
6265 | coding->produced = coding->produced_char = 0; | |
6266 | coding_set_source (coding); | |
1c3478b0 | 6267 | |
df7492f9 | 6268 | src_end = coding->source + coding->src_bytes; |
c0e16b14 | 6269 | coding->head_ascii = 0; |
1c3478b0 | 6270 | |
df7492f9 KH |
6271 | /* If we have not yet decided the text encoding type, detect it |
6272 | now. */ | |
6273 | if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qundecided)) | |
b73bfc1c | 6274 | { |
df7492f9 | 6275 | int c, i; |
6cb21a4f | 6276 | struct coding_detection_info detect_info; |
f10fe38f | 6277 | bool null_byte_found = 0, eight_bit_found = 0; |
df7492f9 | 6278 | |
6cb21a4f | 6279 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
2f3cbb32 | 6280 | for (src = coding->source; src < src_end; src++) |
d46c5b12 | 6281 | { |
df7492f9 | 6282 | c = *src; |
6cb21a4f | 6283 | if (c & 0x80) |
6cb21a4f | 6284 | { |
2f3cbb32 | 6285 | eight_bit_found = 1; |
2f3cbb32 KH |
6286 | if (null_byte_found) |
6287 | break; | |
6288 | } | |
6289 | else if (c < 0x20) | |
6290 | { | |
6291 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
6292 | && ! inhibit_iso_escape_detection | |
6293 | && ! detect_info.checked) | |
6cb21a4f | 6294 | { |
2f3cbb32 KH |
6295 | if (detect_coding_iso_2022 (coding, &detect_info)) |
6296 | { | |
6297 | /* We have scanned the whole data. */ | |
6298 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
6299 | { |
6300 | /* We didn't find an 8-bit code. We may | |
6301 | have found a null-byte, but it's very | |
ce5b453a | 6302 | rare that a binary file conforms to |
c0e16b14 KH |
6303 | ISO-2022. */ |
6304 | src = src_end; | |
6305 | coding->head_ascii = src - coding->source; | |
6306 | } | |
6307 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
6308 | break; |
6309 | } | |
6310 | } | |
97b1b294 | 6311 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
6312 | { |
6313 | null_byte_found = 1; | |
6314 | if (eight_bit_found) | |
6315 | break; | |
6cb21a4f | 6316 | } |
c006c0c8 KH |
6317 | if (! eight_bit_found) |
6318 | coding->head_ascii++; | |
6cb21a4f | 6319 | } |
c006c0c8 | 6320 | else if (! eight_bit_found) |
c0e16b14 | 6321 | coding->head_ascii++; |
d46c5b12 | 6322 | } |
df7492f9 | 6323 | |
2f3cbb32 KH |
6324 | if (null_byte_found || eight_bit_found |
6325 | || coding->head_ascii < coding->src_bytes | |
6cb21a4f | 6326 | || detect_info.found) |
d46c5b12 | 6327 | { |
ff0dacd7 KH |
6328 | enum coding_category category; |
6329 | struct coding_system *this; | |
df7492f9 | 6330 | |
6cb21a4f KH |
6331 | if (coding->head_ascii == coding->src_bytes) |
6332 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ | |
6333 | for (i = 0; i < coding_category_raw_text; i++) | |
6334 | { | |
6335 | category = coding_priorities[i]; | |
6336 | this = coding_categories + category; | |
6337 | if (detect_info.found & (1 << category)) | |
24a73b0a | 6338 | break; |
6cb21a4f KH |
6339 | } |
6340 | else | |
2f3cbb32 KH |
6341 | { |
6342 | if (null_byte_found) | |
ff0dacd7 | 6343 | { |
2f3cbb32 KH |
6344 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; |
6345 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
ff0dacd7 | 6346 | } |
2f3cbb32 KH |
6347 | for (i = 0; i < coding_category_raw_text; i++) |
6348 | { | |
6349 | category = coding_priorities[i]; | |
6350 | this = coding_categories + category; | |
6351 | if (this->id < 0) | |
6352 | { | |
6353 | /* No coding system of this category is defined. */ | |
6354 | detect_info.rejected |= (1 << category); | |
6355 | } | |
6356 | else if (category >= coding_category_raw_text) | |
6357 | continue; | |
6358 | else if (detect_info.checked & (1 << category)) | |
6359 | { | |
6360 | if (detect_info.found & (1 << category)) | |
6361 | break; | |
6362 | } | |
6363 | else if ((*(this->detector)) (coding, &detect_info) | |
6364 | && detect_info.found & (1 << category)) | |
6365 | { | |
6366 | if (category == coding_category_utf_16_auto) | |
6367 | { | |
6368 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6369 | category = coding_category_utf_16_le; | |
6370 | else | |
6371 | category = coding_category_utf_16_be; | |
6372 | } | |
6373 | break; | |
6374 | } | |
6375 | } | |
2f3cbb32 | 6376 | } |
c0e16b14 KH |
6377 | |
6378 | if (i < coding_category_raw_text) | |
6379 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6380 | else if (null_byte_found) | |
6381 | setup_coding_system (Qno_conversion, coding); | |
6382 | else if ((detect_info.rejected & CATEGORY_MASK_ANY) | |
6383 | == CATEGORY_MASK_ANY) | |
6384 | setup_coding_system (Qraw_text, coding); | |
6385 | else if (detect_info.rejected) | |
6386 | for (i = 0; i < coding_category_raw_text; i++) | |
6387 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
6388 | { | |
6389 | this = coding_categories + coding_priorities[i]; | |
6390 | setup_coding_system (CODING_ID_NAME (this->id), coding); | |
6391 | break; | |
6392 | } | |
d46c5b12 | 6393 | } |
b73bfc1c | 6394 | } |
a470d443 KH |
6395 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6396 | == coding_category_utf_8_auto) | |
6397 | { | |
6398 | Lisp_Object coding_systems; | |
6399 | struct coding_detection_info detect_info; | |
6400 | ||
6401 | coding_systems | |
6402 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); | |
6403 | detect_info.found = detect_info.rejected = 0; | |
6404 | coding->head_ascii = 0; | |
6405 | if (CONSP (coding_systems) | |
6406 | && detect_coding_utf_8 (coding, &detect_info)) | |
6407 | { | |
6408 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
6409 | setup_coding_system (XCAR (coding_systems), coding); | |
6410 | else | |
6411 | setup_coding_system (XCDR (coding_systems), coding); | |
6412 | } | |
6413 | } | |
24a73b0a KH |
6414 | else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id))) |
6415 | == coding_category_utf_16_auto) | |
b49a1807 KH |
6416 | { |
6417 | Lisp_Object coding_systems; | |
6418 | struct coding_detection_info detect_info; | |
6419 | ||
6420 | coding_systems | |
a470d443 | 6421 | = AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_bom); |
b49a1807 | 6422 | detect_info.found = detect_info.rejected = 0; |
a470d443 | 6423 | coding->head_ascii = 0; |
b49a1807 | 6424 | if (CONSP (coding_systems) |
24a73b0a | 6425 | && detect_coding_utf_16 (coding, &detect_info)) |
b49a1807 KH |
6426 | { |
6427 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
6428 | setup_coding_system (XCAR (coding_systems), coding); | |
24a73b0a | 6429 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) |
b49a1807 KH |
6430 | setup_coding_system (XCDR (coding_systems), coding); |
6431 | } | |
6432 | } | |
73cce38d | 6433 | coding->mode = saved_mode; |
4ed46869 | 6434 | } |
4ed46869 | 6435 | |
d46c5b12 | 6436 | |
aaaf0b1e | 6437 | static void |
971de7fb | 6438 | decode_eol (struct coding_system *coding) |
aaaf0b1e | 6439 | { |
24a73b0a KH |
6440 | Lisp_Object eol_type; |
6441 | unsigned char *p, *pbeg, *pend; | |
3ed051d4 | 6442 | |
24a73b0a | 6443 | eol_type = CODING_ID_EOL_TYPE (coding->id); |
0a9564cb | 6444 | if (EQ (eol_type, Qunix) || inhibit_eol_conversion) |
24a73b0a KH |
6445 | return; |
6446 | ||
6447 | if (NILP (coding->dst_object)) | |
6448 | pbeg = coding->destination; | |
6449 | else | |
6450 | pbeg = BYTE_POS_ADDR (coding->dst_pos_byte); | |
6451 | pend = pbeg + coding->produced; | |
6452 | ||
6453 | if (VECTORP (eol_type)) | |
aaaf0b1e | 6454 | { |
df7492f9 | 6455 | int eol_seen = EOL_SEEN_NONE; |
4ed46869 | 6456 | |
24a73b0a | 6457 | for (p = pbeg; p < pend; p++) |
aaaf0b1e | 6458 | { |
df7492f9 KH |
6459 | if (*p == '\n') |
6460 | eol_seen |= EOL_SEEN_LF; | |
6461 | else if (*p == '\r') | |
aaaf0b1e | 6462 | { |
df7492f9 | 6463 | if (p + 1 < pend && *(p + 1) == '\n') |
aaaf0b1e | 6464 | { |
df7492f9 KH |
6465 | eol_seen |= EOL_SEEN_CRLF; |
6466 | p++; | |
aaaf0b1e | 6467 | } |
aaaf0b1e | 6468 | else |
df7492f9 | 6469 | eol_seen |= EOL_SEEN_CR; |
aaaf0b1e | 6470 | } |
aaaf0b1e | 6471 | } |
75f4f1ac EZ |
6472 | /* Handle DOS-style EOLs in a file with stray ^M characters. */ |
6473 | if ((eol_seen & EOL_SEEN_CRLF) != 0 | |
6474 | && (eol_seen & EOL_SEEN_CR) != 0 | |
6475 | && (eol_seen & EOL_SEEN_LF) == 0) | |
6476 | eol_seen = EOL_SEEN_CRLF; | |
6477 | else if (eol_seen != EOL_SEEN_NONE | |
24a73b0a KH |
6478 | && eol_seen != EOL_SEEN_LF |
6479 | && eol_seen != EOL_SEEN_CRLF | |
6480 | && eol_seen != EOL_SEEN_CR) | |
6481 | eol_seen = EOL_SEEN_LF; | |
df7492f9 | 6482 | if (eol_seen != EOL_SEEN_NONE) |
24a73b0a | 6483 | eol_type = adjust_coding_eol_type (coding, eol_seen); |
aaaf0b1e | 6484 | } |
d46c5b12 | 6485 | |
24a73b0a | 6486 | if (EQ (eol_type, Qmac)) |
27901516 | 6487 | { |
24a73b0a | 6488 | for (p = pbeg; p < pend; p++) |
df7492f9 KH |
6489 | if (*p == '\r') |
6490 | *p = '\n'; | |
4ed46869 | 6491 | } |
24a73b0a | 6492 | else if (EQ (eol_type, Qdos)) |
df7492f9 | 6493 | { |
d311d28c | 6494 | ptrdiff_t n = 0; |
b73bfc1c | 6495 | |
24a73b0a KH |
6496 | if (NILP (coding->dst_object)) |
6497 | { | |
4347441b KH |
6498 | /* Start deleting '\r' from the tail to minimize the memory |
6499 | movement. */ | |
24a73b0a KH |
6500 | for (p = pend - 2; p >= pbeg; p--) |
6501 | if (*p == '\r') | |
6502 | { | |
72af86bd | 6503 | memmove (p, p + 1, pend-- - p - 1); |
24a73b0a KH |
6504 | n++; |
6505 | } | |
6506 | } | |
6507 | else | |
6508 | { | |
d311d28c PE |
6509 | ptrdiff_t pos_byte = coding->dst_pos_byte; |
6510 | ptrdiff_t pos = coding->dst_pos; | |
6511 | ptrdiff_t pos_end = pos + coding->produced_char - 1; | |
4347441b KH |
6512 | |
6513 | while (pos < pos_end) | |
6514 | { | |
6515 | p = BYTE_POS_ADDR (pos_byte); | |
6516 | if (*p == '\r' && p[1] == '\n') | |
6517 | { | |
6518 | del_range_2 (pos, pos_byte, pos + 1, pos_byte + 1, 0); | |
6519 | n++; | |
6520 | pos_end--; | |
6521 | } | |
6522 | pos++; | |
69b8522d KH |
6523 | if (coding->dst_multibyte) |
6524 | pos_byte += BYTES_BY_CHAR_HEAD (*p); | |
6525 | else | |
6526 | pos_byte++; | |
4347441b | 6527 | } |
24a73b0a KH |
6528 | } |
6529 | coding->produced -= n; | |
6530 | coding->produced_char -= n; | |
aaaf0b1e | 6531 | } |
4ed46869 KH |
6532 | } |
6533 | ||
7d64c6ad | 6534 | |
a6f87d34 | 6535 | /* Return a translation table (or list of them) from coding system |
f10fe38f PE |
6536 | attribute vector ATTRS for encoding (if ENCODEP) or decoding (if |
6537 | not ENCODEP). */ | |
7d64c6ad | 6538 | |
e6a54062 | 6539 | static Lisp_Object |
f10fe38f | 6540 | get_translation_table (Lisp_Object attrs, bool encodep, int *max_lookup) |
7d64c6ad KH |
6541 | { |
6542 | Lisp_Object standard, translation_table; | |
09ee6fdd | 6543 | Lisp_Object val; |
7d64c6ad | 6544 | |
4bed5909 CY |
6545 | if (NILP (Venable_character_translation)) |
6546 | { | |
6547 | if (max_lookup) | |
6548 | *max_lookup = 0; | |
6549 | return Qnil; | |
6550 | } | |
7d64c6ad KH |
6551 | if (encodep) |
6552 | translation_table = CODING_ATTR_ENCODE_TBL (attrs), | |
6553 | standard = Vstandard_translation_table_for_encode; | |
6554 | else | |
6555 | translation_table = CODING_ATTR_DECODE_TBL (attrs), | |
6556 | standard = Vstandard_translation_table_for_decode; | |
7d64c6ad | 6557 | if (NILP (translation_table)) |
09ee6fdd KH |
6558 | translation_table = standard; |
6559 | else | |
a6f87d34 | 6560 | { |
09ee6fdd KH |
6561 | if (SYMBOLP (translation_table)) |
6562 | translation_table = Fget (translation_table, Qtranslation_table); | |
6563 | else if (CONSP (translation_table)) | |
6564 | { | |
6565 | translation_table = Fcopy_sequence (translation_table); | |
6566 | for (val = translation_table; CONSP (val); val = XCDR (val)) | |
6567 | if (SYMBOLP (XCAR (val))) | |
6568 | XSETCAR (val, Fget (XCAR (val), Qtranslation_table)); | |
6569 | } | |
6570 | if (CHAR_TABLE_P (standard)) | |
6571 | { | |
6572 | if (CONSP (translation_table)) | |
6573 | translation_table = nconc2 (translation_table, | |
6574 | Fcons (standard, Qnil)); | |
6575 | else | |
6576 | translation_table = Fcons (translation_table, | |
6577 | Fcons (standard, Qnil)); | |
6578 | } | |
a6f87d34 | 6579 | } |
2170c8f0 KH |
6580 | |
6581 | if (max_lookup) | |
09ee6fdd | 6582 | { |
2170c8f0 KH |
6583 | *max_lookup = 1; |
6584 | if (CHAR_TABLE_P (translation_table) | |
6585 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (translation_table)) > 1) | |
6586 | { | |
6587 | val = XCHAR_TABLE (translation_table)->extras[1]; | |
6588 | if (NATNUMP (val) && *max_lookup < XFASTINT (val)) | |
6589 | *max_lookup = XFASTINT (val); | |
6590 | } | |
6591 | else if (CONSP (translation_table)) | |
6592 | { | |
2735d060 | 6593 | Lisp_Object tail; |
09ee6fdd | 6594 | |
2170c8f0 KH |
6595 | for (tail = translation_table; CONSP (tail); tail = XCDR (tail)) |
6596 | if (CHAR_TABLE_P (XCAR (tail)) | |
6597 | && CHAR_TABLE_EXTRA_SLOTS (XCHAR_TABLE (XCAR (tail))) > 1) | |
6598 | { | |
2735d060 PE |
6599 | Lisp_Object tailval = XCHAR_TABLE (XCAR (tail))->extras[1]; |
6600 | if (NATNUMP (tailval) && *max_lookup < XFASTINT (tailval)) | |
6601 | *max_lookup = XFASTINT (tailval); | |
2170c8f0 KH |
6602 | } |
6603 | } | |
a6f87d34 | 6604 | } |
7d64c6ad KH |
6605 | return translation_table; |
6606 | } | |
6607 | ||
09ee6fdd KH |
6608 | #define LOOKUP_TRANSLATION_TABLE(table, c, trans) \ |
6609 | do { \ | |
6610 | trans = Qnil; \ | |
6611 | if (CHAR_TABLE_P (table)) \ | |
6612 | { \ | |
6613 | trans = CHAR_TABLE_REF (table, c); \ | |
6614 | if (CHARACTERP (trans)) \ | |
6615 | c = XFASTINT (trans), trans = Qnil; \ | |
6616 | } \ | |
6617 | else if (CONSP (table)) \ | |
6618 | { \ | |
6619 | Lisp_Object tail; \ | |
6620 | \ | |
6621 | for (tail = table; CONSP (tail); tail = XCDR (tail)) \ | |
6622 | if (CHAR_TABLE_P (XCAR (tail))) \ | |
6623 | { \ | |
6624 | trans = CHAR_TABLE_REF (XCAR (tail), c); \ | |
6625 | if (CHARACTERP (trans)) \ | |
6626 | c = XFASTINT (trans), trans = Qnil; \ | |
6627 | else if (! NILP (trans)) \ | |
6628 | break; \ | |
6629 | } \ | |
6630 | } \ | |
e6a54062 KH |
6631 | } while (0) |
6632 | ||
7d64c6ad | 6633 | |
e951386e KH |
6634 | /* Return a translation of character(s) at BUF according to TRANS. |
6635 | TRANS is TO-CHAR or ((FROM . TO) ...) where | |
6636 | FROM = [FROM-CHAR ...], TO is TO-CHAR or [TO-CHAR ...]. | |
6637 | The return value is TO-CHAR or ([FROM-CHAR ...] . TO) if a | |
6638 | translation is found, and Qnil if not found.. | |
6639 | If BUF is too short to lookup characters in FROM, return Qt. */ | |
6640 | ||
69a80ea3 | 6641 | static Lisp_Object |
971de7fb | 6642 | get_translation (Lisp_Object trans, int *buf, int *buf_end) |
69a80ea3 | 6643 | { |
e951386e KH |
6644 | |
6645 | if (INTEGERP (trans)) | |
6646 | return trans; | |
6647 | for (; CONSP (trans); trans = XCDR (trans)) | |
69a80ea3 | 6648 | { |
e951386e KH |
6649 | Lisp_Object val = XCAR (trans); |
6650 | Lisp_Object from = XCAR (val); | |
2c6a9faa PE |
6651 | ptrdiff_t len = ASIZE (from); |
6652 | ptrdiff_t i; | |
69a80ea3 | 6653 | |
e951386e | 6654 | for (i = 0; i < len; i++) |
69a80ea3 | 6655 | { |
e951386e KH |
6656 | if (buf + i == buf_end) |
6657 | return Qt; | |
6658 | if (XINT (AREF (from, i)) != buf[i]) | |
6659 | break; | |
69a80ea3 | 6660 | } |
e951386e KH |
6661 | if (i == len) |
6662 | return val; | |
69a80ea3 | 6663 | } |
e951386e | 6664 | return Qnil; |
69a80ea3 KH |
6665 | } |
6666 | ||
6667 | ||
d46c5b12 | 6668 | static int |
cf84bb53 | 6669 | produce_chars (struct coding_system *coding, Lisp_Object translation_table, |
f10fe38f | 6670 | bool last_block) |
4ed46869 | 6671 | { |
df7492f9 KH |
6672 | unsigned char *dst = coding->destination + coding->produced; |
6673 | unsigned char *dst_end = coding->destination + coding->dst_bytes; | |
d311d28c PE |
6674 | ptrdiff_t produced; |
6675 | ptrdiff_t produced_chars = 0; | |
69a80ea3 | 6676 | int carryover = 0; |
4ed46869 | 6677 | |
df7492f9 | 6678 | if (! coding->chars_at_source) |
4ed46869 | 6679 | { |
119852e7 | 6680 | /* Source characters are in coding->charbuf. */ |
fba4576f AS |
6681 | int *buf = coding->charbuf; |
6682 | int *buf_end = buf + coding->charbuf_used; | |
4ed46869 | 6683 | |
db274c7a KH |
6684 | if (EQ (coding->src_object, coding->dst_object)) |
6685 | { | |
6686 | coding_set_source (coding); | |
6687 | dst_end = ((unsigned char *) coding->source) + coding->consumed; | |
6688 | } | |
4ed46869 | 6689 | |
df7492f9 | 6690 | while (buf < buf_end) |
4ed46869 | 6691 | { |
27bb1ca4 PE |
6692 | int c = *buf; |
6693 | ptrdiff_t i; | |
bc4bc72a | 6694 | |
df7492f9 KH |
6695 | if (c >= 0) |
6696 | { | |
d311d28c | 6697 | ptrdiff_t from_nchars = 1, to_nchars = 1; |
69a80ea3 KH |
6698 | Lisp_Object trans = Qnil; |
6699 | ||
09ee6fdd | 6700 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 6701 | if (! NILP (trans)) |
69a80ea3 | 6702 | { |
e951386e KH |
6703 | trans = get_translation (trans, buf, buf_end); |
6704 | if (INTEGERP (trans)) | |
6705 | c = XINT (trans); | |
6706 | else if (CONSP (trans)) | |
6707 | { | |
6708 | from_nchars = ASIZE (XCAR (trans)); | |
6709 | trans = XCDR (trans); | |
6710 | if (INTEGERP (trans)) | |
6711 | c = XINT (trans); | |
6712 | else | |
6713 | { | |
6714 | to_nchars = ASIZE (trans); | |
6715 | c = XINT (AREF (trans, 0)); | |
6716 | } | |
6717 | } | |
6718 | else if (EQ (trans, Qt) && ! last_block) | |
69a80ea3 | 6719 | break; |
69a80ea3 KH |
6720 | } |
6721 | ||
5d009b3a | 6722 | if ((dst_end - dst) / MAX_MULTIBYTE_LENGTH < to_nchars) |
69a80ea3 | 6723 | { |
5d009b3a PE |
6724 | if (((min (PTRDIFF_MAX, SIZE_MAX) - (buf_end - buf)) |
6725 | / MAX_MULTIBYTE_LENGTH) | |
6726 | < to_nchars) | |
6727 | memory_full (SIZE_MAX); | |
69a80ea3 KH |
6728 | dst = alloc_destination (coding, |
6729 | buf_end - buf | |
6730 | + MAX_MULTIBYTE_LENGTH * to_nchars, | |
6731 | dst); | |
db274c7a KH |
6732 | if (EQ (coding->src_object, coding->dst_object)) |
6733 | { | |
6734 | coding_set_source (coding); | |
e951386e KH |
6735 | dst_end = (((unsigned char *) coding->source) |
6736 | + coding->consumed); | |
db274c7a KH |
6737 | } |
6738 | else | |
6739 | dst_end = coding->destination + coding->dst_bytes; | |
69a80ea3 KH |
6740 | } |
6741 | ||
433f7f87 | 6742 | for (i = 0; i < to_nchars; i++) |
69a80ea3 | 6743 | { |
433f7f87 KH |
6744 | if (i > 0) |
6745 | c = XINT (AREF (trans, i)); | |
69a80ea3 KH |
6746 | if (coding->dst_multibyte |
6747 | || ! CHAR_BYTE8_P (c)) | |
db274c7a | 6748 | CHAR_STRING_ADVANCE_NO_UNIFY (c, dst); |
69a80ea3 KH |
6749 | else |
6750 | *dst++ = CHAR_TO_BYTE8 (c); | |
6751 | } | |
6752 | produced_chars += to_nchars; | |
e951386e | 6753 | buf += from_nchars; |
d46c5b12 | 6754 | } |
df7492f9 | 6755 | else |
69a80ea3 KH |
6756 | /* This is an annotation datum. (-C) is the length. */ |
6757 | buf += -c; | |
4ed46869 | 6758 | } |
69a80ea3 | 6759 | carryover = buf_end - buf; |
4ed46869 | 6760 | } |
fa42c37f | 6761 | else |
fa42c37f | 6762 | { |
119852e7 | 6763 | /* Source characters are at coding->source. */ |
8f924df7 | 6764 | const unsigned char *src = coding->source; |
119852e7 | 6765 | const unsigned char *src_end = src + coding->consumed; |
4ed46869 | 6766 | |
db274c7a KH |
6767 | if (EQ (coding->dst_object, coding->src_object)) |
6768 | dst_end = (unsigned char *) src; | |
df7492f9 | 6769 | if (coding->src_multibyte != coding->dst_multibyte) |
fa42c37f | 6770 | { |
df7492f9 | 6771 | if (coding->src_multibyte) |
fa42c37f | 6772 | { |
f10fe38f | 6773 | bool multibytep = 1; |
d311d28c | 6774 | ptrdiff_t consumed_chars = 0; |
d46c5b12 | 6775 | |
df7492f9 KH |
6776 | while (1) |
6777 | { | |
8f924df7 | 6778 | const unsigned char *src_base = src; |
df7492f9 | 6779 | int c; |
b73bfc1c | 6780 | |
df7492f9 | 6781 | ONE_MORE_BYTE (c); |
119852e7 | 6782 | if (dst == dst_end) |
df7492f9 | 6783 | { |
119852e7 KH |
6784 | if (EQ (coding->src_object, coding->dst_object)) |
6785 | dst_end = (unsigned char *) src; | |
6786 | if (dst == dst_end) | |
df7492f9 | 6787 | { |
d311d28c | 6788 | ptrdiff_t offset = src - coding->source; |
119852e7 KH |
6789 | |
6790 | dst = alloc_destination (coding, src_end - src + 1, | |
6791 | dst); | |
6792 | dst_end = coding->destination + coding->dst_bytes; | |
6793 | coding_set_source (coding); | |
6794 | src = coding->source + offset; | |
5c1ca13d | 6795 | src_end = coding->source + coding->consumed; |
db274c7a KH |
6796 | if (EQ (coding->src_object, coding->dst_object)) |
6797 | dst_end = (unsigned char *) src; | |
df7492f9 | 6798 | } |
df7492f9 KH |
6799 | } |
6800 | *dst++ = c; | |
6801 | produced_chars++; | |
6802 | } | |
6803 | no_more_source: | |
6804 | ; | |
fa42c37f KH |
6805 | } |
6806 | else | |
df7492f9 KH |
6807 | while (src < src_end) |
6808 | { | |
f10fe38f | 6809 | bool multibytep = 1; |
df7492f9 | 6810 | int c = *src++; |
b73bfc1c | 6811 | |
df7492f9 KH |
6812 | if (dst >= dst_end - 1) |
6813 | { | |
2c78b7e1 | 6814 | if (EQ (coding->src_object, coding->dst_object)) |
8f924df7 | 6815 | dst_end = (unsigned char *) src; |
2c78b7e1 KH |
6816 | if (dst >= dst_end - 1) |
6817 | { | |
d311d28c PE |
6818 | ptrdiff_t offset = src - coding->source; |
6819 | ptrdiff_t more_bytes; | |
119852e7 | 6820 | |
db274c7a KH |
6821 | if (EQ (coding->src_object, coding->dst_object)) |
6822 | more_bytes = ((src_end - src) / 2) + 2; | |
6823 | else | |
6824 | more_bytes = src_end - src + 2; | |
6825 | dst = alloc_destination (coding, more_bytes, dst); | |
2c78b7e1 KH |
6826 | dst_end = coding->destination + coding->dst_bytes; |
6827 | coding_set_source (coding); | |
119852e7 | 6828 | src = coding->source + offset; |
5c1ca13d | 6829 | src_end = coding->source + coding->consumed; |
db274c7a KH |
6830 | if (EQ (coding->src_object, coding->dst_object)) |
6831 | dst_end = (unsigned char *) src; | |
2c78b7e1 | 6832 | } |
df7492f9 KH |
6833 | } |
6834 | EMIT_ONE_BYTE (c); | |
6835 | } | |
d46c5b12 | 6836 | } |
df7492f9 KH |
6837 | else |
6838 | { | |
6839 | if (!EQ (coding->src_object, coding->dst_object)) | |
fa42c37f | 6840 | { |
d311d28c | 6841 | ptrdiff_t require = coding->src_bytes - coding->dst_bytes; |
4ed46869 | 6842 | |
df7492f9 | 6843 | if (require > 0) |
fa42c37f | 6844 | { |
d311d28c | 6845 | ptrdiff_t offset = src - coding->source; |
df7492f9 KH |
6846 | |
6847 | dst = alloc_destination (coding, require, dst); | |
6848 | coding_set_source (coding); | |
6849 | src = coding->source + offset; | |
5c1ca13d | 6850 | src_end = coding->source + coding->consumed; |
fa42c37f KH |
6851 | } |
6852 | } | |
119852e7 | 6853 | produced_chars = coding->consumed_char; |
df7492f9 | 6854 | while (src < src_end) |
14daee73 | 6855 | *dst++ = *src++; |
fa42c37f KH |
6856 | } |
6857 | } | |
6858 | ||
df7492f9 | 6859 | produced = dst - (coding->destination + coding->produced); |
284201e4 | 6860 | if (BUFFERP (coding->dst_object) && produced_chars > 0) |
df7492f9 KH |
6861 | insert_from_gap (produced_chars, produced); |
6862 | coding->produced += produced; | |
6863 | coding->produced_char += produced_chars; | |
69a80ea3 | 6864 | return carryover; |
fa42c37f KH |
6865 | } |
6866 | ||
ff0dacd7 KH |
6867 | /* Compose text in CODING->object according to the annotation data at |
6868 | CHARBUF. CHARBUF is an array: | |
e951386e | 6869 | [ -LENGTH ANNOTATION_MASK NCHARS NBYTES METHOD [ COMPONENTS... ] ] |
df7492f9 | 6870 | */ |
4ed46869 | 6871 | |
55d4c1b2 | 6872 | static inline void |
d311d28c | 6873 | produce_composition (struct coding_system *coding, int *charbuf, ptrdiff_t pos) |
4ed46869 | 6874 | { |
df7492f9 | 6875 | int len; |
d311d28c | 6876 | ptrdiff_t to; |
df7492f9 | 6877 | enum composition_method method; |
df7492f9 | 6878 | Lisp_Object components; |
fa42c37f | 6879 | |
e951386e | 6880 | len = -charbuf[0] - MAX_ANNOTATION_LENGTH; |
69a80ea3 | 6881 | to = pos + charbuf[2]; |
e951386e | 6882 | method = (enum composition_method) (charbuf[4]); |
d46c5b12 | 6883 | |
df7492f9 KH |
6884 | if (method == COMPOSITION_RELATIVE) |
6885 | components = Qnil; | |
e951386e | 6886 | else |
d46c5b12 | 6887 | { |
df7492f9 | 6888 | Lisp_Object args[MAX_COMPOSITION_COMPONENTS * 2 - 1]; |
e951386e | 6889 | int i, j; |
b73bfc1c | 6890 | |
e951386e KH |
6891 | if (method == COMPOSITION_WITH_RULE) |
6892 | len = charbuf[2] * 3 - 2; | |
6893 | charbuf += MAX_ANNOTATION_LENGTH; | |
6894 | /* charbuf = [ CHRA ... CHAR] or [ CHAR -2 RULE ... CHAR ] */ | |
6895 | for (i = j = 0; i < len && charbuf[i] != -1; i++, j++) | |
9ffd559c | 6896 | { |
e951386e KH |
6897 | if (charbuf[i] >= 0) |
6898 | args[j] = make_number (charbuf[i]); | |
6899 | else | |
6900 | { | |
6901 | i++; | |
6902 | args[j] = make_number (charbuf[i] % 0x100); | |
6903 | } | |
9ffd559c | 6904 | } |
e951386e | 6905 | components = (i == j ? Fstring (j, args) : Fvector (j, args)); |
d46c5b12 | 6906 | } |
69a80ea3 | 6907 | compose_text (pos, to, components, Qnil, coding->dst_object); |
d46c5b12 KH |
6908 | } |
6909 | ||
d46c5b12 | 6910 | |
ff0dacd7 KH |
6911 | /* Put `charset' property on text in CODING->object according to |
6912 | the annotation data at CHARBUF. CHARBUF is an array: | |
69a80ea3 | 6913 | [ -LENGTH ANNOTATION_MASK NCHARS CHARSET-ID ] |
ff0dacd7 | 6914 | */ |
d46c5b12 | 6915 | |
55d4c1b2 | 6916 | static inline void |
d311d28c | 6917 | produce_charset (struct coding_system *coding, int *charbuf, ptrdiff_t pos) |
d46c5b12 | 6918 | { |
d311d28c | 6919 | ptrdiff_t from = pos - charbuf[2]; |
69a80ea3 | 6920 | struct charset *charset = CHARSET_FROM_ID (charbuf[3]); |
b73bfc1c | 6921 | |
69a80ea3 | 6922 | Fput_text_property (make_number (from), make_number (pos), |
ff0dacd7 KH |
6923 | Qcharset, CHARSET_NAME (charset), |
6924 | coding->dst_object); | |
d46c5b12 KH |
6925 | } |
6926 | ||
d46c5b12 | 6927 | |
df7492f9 KH |
6928 | #define CHARBUF_SIZE 0x4000 |
6929 | ||
6930 | #define ALLOC_CONVERSION_WORK_AREA(coding) \ | |
6931 | do { \ | |
8510724d | 6932 | int size = CHARBUF_SIZE; \ |
df7492f9 KH |
6933 | \ |
6934 | coding->charbuf = NULL; \ | |
6935 | while (size > 1024) \ | |
6936 | { \ | |
38182d90 | 6937 | coding->charbuf = alloca (sizeof (int) * size); \ |
df7492f9 KH |
6938 | if (coding->charbuf) \ |
6939 | break; \ | |
6940 | size >>= 1; \ | |
6941 | } \ | |
6942 | if (! coding->charbuf) \ | |
6943 | { \ | |
065e3595 | 6944 | record_conversion_result (coding, CODING_RESULT_INSUFFICIENT_MEM); \ |
f10fe38f | 6945 | return; \ |
df7492f9 KH |
6946 | } \ |
6947 | coding->charbuf_size = size; \ | |
6948 | } while (0) | |
4ed46869 | 6949 | |
d46c5b12 KH |
6950 | |
6951 | static void | |
d311d28c | 6952 | produce_annotation (struct coding_system *coding, ptrdiff_t pos) |
d46c5b12 | 6953 | { |
df7492f9 KH |
6954 | int *charbuf = coding->charbuf; |
6955 | int *charbuf_end = charbuf + coding->charbuf_used; | |
d46c5b12 | 6956 | |
ff0dacd7 KH |
6957 | if (NILP (coding->dst_object)) |
6958 | return; | |
d46c5b12 | 6959 | |
df7492f9 | 6960 | while (charbuf < charbuf_end) |
a84f1519 | 6961 | { |
df7492f9 | 6962 | if (*charbuf >= 0) |
e951386e | 6963 | pos++, charbuf++; |
d46c5b12 | 6964 | else |
d46c5b12 | 6965 | { |
df7492f9 | 6966 | int len = -*charbuf; |
e951386e KH |
6967 | |
6968 | if (len > 2) | |
6969 | switch (charbuf[1]) | |
6970 | { | |
6971 | case CODING_ANNOTATE_COMPOSITION_MASK: | |
6972 | produce_composition (coding, charbuf, pos); | |
6973 | break; | |
6974 | case CODING_ANNOTATE_CHARSET_MASK: | |
6975 | produce_charset (coding, charbuf, pos); | |
6976 | break; | |
6977 | } | |
df7492f9 | 6978 | charbuf += len; |
d46c5b12 | 6979 | } |
a84f1519 | 6980 | } |
d46c5b12 KH |
6981 | } |
6982 | ||
df7492f9 KH |
6983 | /* Decode the data at CODING->src_object into CODING->dst_object. |
6984 | CODING->src_object is a buffer, a string, or nil. | |
6985 | CODING->dst_object is a buffer. | |
d46c5b12 | 6986 | |
df7492f9 KH |
6987 | If CODING->src_object is a buffer, it must be the current buffer. |
6988 | In this case, if CODING->src_pos is positive, it is a position of | |
6989 | the source text in the buffer, otherwise, the source text is in the | |
6990 | gap area of the buffer, and CODING->src_pos specifies the offset of | |
6991 | the text from GPT (which must be the same as PT). If this is the | |
6992 | same buffer as CODING->dst_object, CODING->src_pos must be | |
6993 | negative. | |
d46c5b12 | 6994 | |
b6828792 | 6995 | If CODING->src_object is a string, CODING->src_pos is an index to |
df7492f9 | 6996 | that string. |
d46c5b12 | 6997 | |
df7492f9 KH |
6998 | If CODING->src_object is nil, CODING->source must already point to |
6999 | the non-relocatable memory area. In this case, CODING->src_pos is | |
7000 | an offset from CODING->source. | |
73be902c | 7001 | |
df7492f9 KH |
7002 | The decoded data is inserted at the current point of the buffer |
7003 | CODING->dst_object. | |
7004 | */ | |
d46c5b12 | 7005 | |
f10fe38f | 7006 | static void |
971de7fb | 7007 | decode_coding (struct coding_system *coding) |
d46c5b12 | 7008 | { |
df7492f9 | 7009 | Lisp_Object attrs; |
24a73b0a | 7010 | Lisp_Object undo_list; |
7d64c6ad | 7011 | Lisp_Object translation_table; |
d0396581 | 7012 | struct ccl_spec cclspec; |
69a80ea3 KH |
7013 | int carryover; |
7014 | int i; | |
d46c5b12 | 7015 | |
df7492f9 KH |
7016 | if (BUFFERP (coding->src_object) |
7017 | && coding->src_pos > 0 | |
7018 | && coding->src_pos < GPT | |
7019 | && coding->src_pos + coding->src_chars > GPT) | |
7020 | move_gap_both (coding->src_pos, coding->src_pos_byte); | |
d46c5b12 | 7021 | |
24a73b0a | 7022 | undo_list = Qt; |
df7492f9 | 7023 | if (BUFFERP (coding->dst_object)) |
1c3478b0 | 7024 | { |
a3d794a1 | 7025 | set_buffer_internal (XBUFFER (coding->dst_object)); |
df7492f9 KH |
7026 | if (GPT != PT) |
7027 | move_gap_both (PT, PT_BYTE); | |
f48b82fd GR |
7028 | |
7029 | /* We must disable undo_list in order to record the whole insert | |
7030 | transaction via record_insert at the end. But doing so also | |
7031 | disables the recording of the first change to the undo_list. | |
7032 | Therefore we check for first change here and record it via | |
7033 | record_first_change if needed. */ | |
7034 | if (MODIFF <= SAVE_MODIFF) | |
7035 | record_first_change (); | |
7036 | ||
4b4deea2 | 7037 | undo_list = BVAR (current_buffer, undo_list); |
39eb03f1 | 7038 | bset_undo_list (current_buffer, Qt); |
1c3478b0 KH |
7039 | } |
7040 | ||
df7492f9 KH |
7041 | coding->consumed = coding->consumed_char = 0; |
7042 | coding->produced = coding->produced_char = 0; | |
7043 | coding->chars_at_source = 0; | |
065e3595 | 7044 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
df7492f9 | 7045 | coding->errors = 0; |
1c3478b0 | 7046 | |
df7492f9 KH |
7047 | ALLOC_CONVERSION_WORK_AREA (coding); |
7048 | ||
7049 | attrs = CODING_ID_ATTRS (coding->id); | |
2170c8f0 | 7050 | translation_table = get_translation_table (attrs, 0, NULL); |
df7492f9 | 7051 | |
69a80ea3 | 7052 | carryover = 0; |
d0396581 KH |
7053 | if (coding->decoder == decode_coding_ccl) |
7054 | { | |
7055 | coding->spec.ccl = &cclspec; | |
7056 | setup_ccl_program (&cclspec.ccl, CODING_CCL_DECODER (coding)); | |
7057 | } | |
df7492f9 | 7058 | do |
b73bfc1c | 7059 | { |
d311d28c | 7060 | ptrdiff_t pos = coding->dst_pos + coding->produced_char; |
69a80ea3 | 7061 | |
df7492f9 KH |
7062 | coding_set_source (coding); |
7063 | coding->annotated = 0; | |
69a80ea3 | 7064 | coding->charbuf_used = carryover; |
df7492f9 | 7065 | (*(coding->decoder)) (coding); |
df7492f9 | 7066 | coding_set_destination (coding); |
69a80ea3 | 7067 | carryover = produce_chars (coding, translation_table, 0); |
df7492f9 | 7068 | if (coding->annotated) |
69a80ea3 KH |
7069 | produce_annotation (coding, pos); |
7070 | for (i = 0; i < carryover; i++) | |
7071 | coding->charbuf[i] | |
7072 | = coding->charbuf[coding->charbuf_used - carryover + i]; | |
d46c5b12 | 7073 | } |
d0396581 KH |
7074 | while (coding->result == CODING_RESULT_INSUFFICIENT_DST |
7075 | || (coding->consumed < coding->src_bytes | |
7076 | && (coding->result == CODING_RESULT_SUCCESS | |
7077 | || coding->result == CODING_RESULT_INVALID_SRC))); | |
d46c5b12 | 7078 | |
69a80ea3 KH |
7079 | if (carryover > 0) |
7080 | { | |
7081 | coding_set_destination (coding); | |
7082 | coding->charbuf_used = carryover; | |
7083 | produce_chars (coding, translation_table, 1); | |
7084 | } | |
7085 | ||
df7492f9 KH |
7086 | coding->carryover_bytes = 0; |
7087 | if (coding->consumed < coding->src_bytes) | |
d46c5b12 | 7088 | { |
df7492f9 | 7089 | int nbytes = coding->src_bytes - coding->consumed; |
8f924df7 | 7090 | const unsigned char *src; |
df7492f9 KH |
7091 | |
7092 | coding_set_source (coding); | |
7093 | coding_set_destination (coding); | |
7094 | src = coding->source + coding->consumed; | |
7095 | ||
7096 | if (coding->mode & CODING_MODE_LAST_BLOCK) | |
1c3478b0 | 7097 | { |
df7492f9 KH |
7098 | /* Flush out unprocessed data as binary chars. We are sure |
7099 | that the number of data is less than the size of | |
7100 | coding->charbuf. */ | |
065e3595 | 7101 | coding->charbuf_used = 0; |
b2dab6c8 JR |
7102 | coding->chars_at_source = 0; |
7103 | ||
df7492f9 | 7104 | while (nbytes-- > 0) |
1c3478b0 | 7105 | { |
df7492f9 | 7106 | int c = *src++; |
98725083 | 7107 | |
1c91457d KH |
7108 | if (c & 0x80) |
7109 | c = BYTE8_TO_CHAR (c); | |
7110 | coding->charbuf[coding->charbuf_used++] = c; | |
1c3478b0 | 7111 | } |
f6cbaf43 | 7112 | produce_chars (coding, Qnil, 1); |
d46c5b12 | 7113 | } |
d46c5b12 | 7114 | else |
df7492f9 KH |
7115 | { |
7116 | /* Record unprocessed bytes in coding->carryover. We are | |
7117 | sure that the number of data is less than the size of | |
7118 | coding->carryover. */ | |
7119 | unsigned char *p = coding->carryover; | |
7120 | ||
f289d375 KH |
7121 | if (nbytes > sizeof coding->carryover) |
7122 | nbytes = sizeof coding->carryover; | |
df7492f9 KH |
7123 | coding->carryover_bytes = nbytes; |
7124 | while (nbytes-- > 0) | |
7125 | *p++ = *src++; | |
1c3478b0 | 7126 | } |
df7492f9 | 7127 | coding->consumed = coding->src_bytes; |
b73bfc1c | 7128 | } |
69f76525 | 7129 | |
0a9564cb EZ |
7130 | if (! EQ (CODING_ID_EOL_TYPE (coding->id), Qunix) |
7131 | && !inhibit_eol_conversion) | |
4347441b | 7132 | decode_eol (coding); |
24a73b0a KH |
7133 | if (BUFFERP (coding->dst_object)) |
7134 | { | |
39eb03f1 | 7135 | bset_undo_list (current_buffer, undo_list); |
24a73b0a KH |
7136 | record_insert (coding->dst_pos, coding->produced_char); |
7137 | } | |
4ed46869 KH |
7138 | } |
7139 | ||
aaaf0b1e | 7140 | |
e1c23804 | 7141 | /* Extract an annotation datum from a composition starting at POS and |
ff0dacd7 KH |
7142 | ending before LIMIT of CODING->src_object (buffer or string), store |
7143 | the data in BUF, set *STOP to a starting position of the next | |
7144 | composition (if any) or to LIMIT, and return the address of the | |
7145 | next element of BUF. | |
7146 | ||
7147 | If such an annotation is not found, set *STOP to a starting | |
7148 | position of a composition after POS (if any) or to LIMIT, and | |
7149 | return BUF. */ | |
7150 | ||
55d4c1b2 | 7151 | static inline int * |
d311d28c | 7152 | handle_composition_annotation (ptrdiff_t pos, ptrdiff_t limit, |
cf84bb53 | 7153 | struct coding_system *coding, int *buf, |
d311d28c | 7154 | ptrdiff_t *stop) |
aaaf0b1e | 7155 | { |
d311d28c | 7156 | ptrdiff_t start, end; |
ff0dacd7 | 7157 | Lisp_Object prop; |
aaaf0b1e | 7158 | |
ff0dacd7 KH |
7159 | if (! find_composition (pos, limit, &start, &end, &prop, coding->src_object) |
7160 | || end > limit) | |
7161 | *stop = limit; | |
7162 | else if (start > pos) | |
7163 | *stop = start; | |
7164 | else | |
aaaf0b1e | 7165 | { |
ff0dacd7 | 7166 | if (start == pos) |
aaaf0b1e | 7167 | { |
ff0dacd7 KH |
7168 | /* We found a composition. Store the corresponding |
7169 | annotation data in BUF. */ | |
7170 | int *head = buf; | |
7171 | enum composition_method method = COMPOSITION_METHOD (prop); | |
7172 | int nchars = COMPOSITION_LENGTH (prop); | |
7173 | ||
e951386e | 7174 | ADD_COMPOSITION_DATA (buf, nchars, 0, method); |
ff0dacd7 | 7175 | if (method != COMPOSITION_RELATIVE) |
aaaf0b1e | 7176 | { |
ff0dacd7 | 7177 | Lisp_Object components; |
2c6a9faa | 7178 | ptrdiff_t i, len, i_byte; |
ff0dacd7 KH |
7179 | |
7180 | components = COMPOSITION_COMPONENTS (prop); | |
7181 | if (VECTORP (components)) | |
aaaf0b1e | 7182 | { |
77b37c05 | 7183 | len = ASIZE (components); |
ff0dacd7 KH |
7184 | for (i = 0; i < len; i++) |
7185 | *buf++ = XINT (AREF (components, i)); | |
aaaf0b1e | 7186 | } |
ff0dacd7 | 7187 | else if (STRINGP (components)) |
aaaf0b1e | 7188 | { |
8f924df7 | 7189 | len = SCHARS (components); |
ff0dacd7 KH |
7190 | i = i_byte = 0; |
7191 | while (i < len) | |
7192 | { | |
7193 | FETCH_STRING_CHAR_ADVANCE (*buf, components, i, i_byte); | |
7194 | buf++; | |
7195 | } | |
7196 | } | |
7197 | else if (INTEGERP (components)) | |
7198 | { | |
7199 | len = 1; | |
7200 | *buf++ = XINT (components); | |
7201 | } | |
7202 | else if (CONSP (components)) | |
7203 | { | |
7204 | for (len = 0; CONSP (components); | |
7205 | len++, components = XCDR (components)) | |
7206 | *buf++ = XINT (XCAR (components)); | |
aaaf0b1e | 7207 | } |
aaaf0b1e | 7208 | else |
1088b922 | 7209 | emacs_abort (); |
ff0dacd7 | 7210 | *head -= len; |
aaaf0b1e | 7211 | } |
aaaf0b1e | 7212 | } |
ff0dacd7 KH |
7213 | |
7214 | if (find_composition (end, limit, &start, &end, &prop, | |
7215 | coding->src_object) | |
7216 | && end <= limit) | |
7217 | *stop = start; | |
7218 | else | |
7219 | *stop = limit; | |
aaaf0b1e | 7220 | } |
ff0dacd7 KH |
7221 | return buf; |
7222 | } | |
7223 | ||
7224 | ||
e1c23804 | 7225 | /* Extract an annotation datum from a text property `charset' at POS of |
ff0dacd7 KH |
7226 | CODING->src_object (buffer of string), store the data in BUF, set |
7227 | *STOP to the position where the value of `charset' property changes | |
7228 | (limiting by LIMIT), and return the address of the next element of | |
7229 | BUF. | |
7230 | ||
7231 | If the property value is nil, set *STOP to the position where the | |
7232 | property value is non-nil (limiting by LIMIT), and return BUF. */ | |
7233 | ||
55d4c1b2 | 7234 | static inline int * |
d311d28c | 7235 | handle_charset_annotation (ptrdiff_t pos, ptrdiff_t limit, |
cf84bb53 | 7236 | struct coding_system *coding, int *buf, |
d311d28c | 7237 | ptrdiff_t *stop) |
ff0dacd7 KH |
7238 | { |
7239 | Lisp_Object val, next; | |
7240 | int id; | |
7241 | ||
7242 | val = Fget_text_property (make_number (pos), Qcharset, coding->src_object); | |
7243 | if (! NILP (val) && CHARSETP (val)) | |
7244 | id = XINT (CHARSET_SYMBOL_ID (val)); | |
7245 | else | |
7246 | id = -1; | |
69a80ea3 | 7247 | ADD_CHARSET_DATA (buf, 0, id); |
ff0dacd7 KH |
7248 | next = Fnext_single_property_change (make_number (pos), Qcharset, |
7249 | coding->src_object, | |
7250 | make_number (limit)); | |
7251 | *stop = XINT (next); | |
7252 | return buf; | |
7253 | } | |
7254 | ||
7255 | ||
df7492f9 | 7256 | static void |
cf84bb53 JB |
7257 | consume_chars (struct coding_system *coding, Lisp_Object translation_table, |
7258 | int max_lookup) | |
df7492f9 KH |
7259 | { |
7260 | int *buf = coding->charbuf; | |
ff0dacd7 | 7261 | int *buf_end = coding->charbuf + coding->charbuf_size; |
7c78e542 | 7262 | const unsigned char *src = coding->source + coding->consumed; |
4776e638 | 7263 | const unsigned char *src_end = coding->source + coding->src_bytes; |
d311d28c PE |
7264 | ptrdiff_t pos = coding->src_pos + coding->consumed_char; |
7265 | ptrdiff_t end_pos = coding->src_pos + coding->src_chars; | |
f10fe38f | 7266 | bool multibytep = coding->src_multibyte; |
df7492f9 KH |
7267 | Lisp_Object eol_type; |
7268 | int c; | |
d311d28c | 7269 | ptrdiff_t stop, stop_composition, stop_charset; |
09ee6fdd | 7270 | int *lookup_buf = NULL; |
433f7f87 KH |
7271 | |
7272 | if (! NILP (translation_table)) | |
09ee6fdd | 7273 | lookup_buf = alloca (sizeof (int) * max_lookup); |
88993dfd | 7274 | |
0a9564cb | 7275 | eol_type = inhibit_eol_conversion ? Qunix : CODING_ID_EOL_TYPE (coding->id); |
df7492f9 KH |
7276 | if (VECTORP (eol_type)) |
7277 | eol_type = Qunix; | |
88993dfd | 7278 | |
df7492f9 KH |
7279 | /* Note: composition handling is not yet implemented. */ |
7280 | coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
ec6d2bb8 | 7281 | |
0b5670c9 KH |
7282 | if (NILP (coding->src_object)) |
7283 | stop = stop_composition = stop_charset = end_pos; | |
ff0dacd7 | 7284 | else |
0b5670c9 KH |
7285 | { |
7286 | if (coding->common_flags & CODING_ANNOTATE_COMPOSITION_MASK) | |
7287 | stop = stop_composition = pos; | |
7288 | else | |
7289 | stop = stop_composition = end_pos; | |
7290 | if (coding->common_flags & CODING_ANNOTATE_CHARSET_MASK) | |
7291 | stop = stop_charset = pos; | |
7292 | else | |
7293 | stop_charset = end_pos; | |
7294 | } | |
ec6d2bb8 | 7295 | |
24a73b0a | 7296 | /* Compensate for CRLF and conversion. */ |
ff0dacd7 | 7297 | buf_end -= 1 + MAX_ANNOTATION_LENGTH; |
df7492f9 | 7298 | while (buf < buf_end) |
aaaf0b1e | 7299 | { |
433f7f87 KH |
7300 | Lisp_Object trans; |
7301 | ||
df7492f9 | 7302 | if (pos == stop) |
ec6d2bb8 | 7303 | { |
df7492f9 KH |
7304 | if (pos == end_pos) |
7305 | break; | |
ff0dacd7 KH |
7306 | if (pos == stop_composition) |
7307 | buf = handle_composition_annotation (pos, end_pos, coding, | |
7308 | buf, &stop_composition); | |
7309 | if (pos == stop_charset) | |
7310 | buf = handle_charset_annotation (pos, end_pos, coding, | |
7311 | buf, &stop_charset); | |
7312 | stop = (stop_composition < stop_charset | |
7313 | ? stop_composition : stop_charset); | |
df7492f9 KH |
7314 | } |
7315 | ||
7316 | if (! multibytep) | |
4776e638 | 7317 | { |
d311d28c | 7318 | int bytes; |
aaaf0b1e | 7319 | |
4d1e6632 KH |
7320 | if (coding->encoder == encode_coding_raw_text |
7321 | || coding->encoder == encode_coding_ccl) | |
ea29edf2 KH |
7322 | c = *src++, pos++; |
7323 | else if ((bytes = MULTIBYTE_LENGTH (src, src_end)) > 0) | |
db274c7a | 7324 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos += bytes; |
4776e638 | 7325 | else |
f03caae0 | 7326 | c = BYTE8_TO_CHAR (*src), src++, pos++; |
4776e638 | 7327 | } |
df7492f9 | 7328 | else |
db274c7a | 7329 | c = STRING_CHAR_ADVANCE_NO_UNIFY (src), pos++; |
df7492f9 KH |
7330 | if ((c == '\r') && (coding->mode & CODING_MODE_SELECTIVE_DISPLAY)) |
7331 | c = '\n'; | |
7332 | if (! EQ (eol_type, Qunix)) | |
aaaf0b1e | 7333 | { |
df7492f9 | 7334 | if (c == '\n') |
aaaf0b1e | 7335 | { |
df7492f9 KH |
7336 | if (EQ (eol_type, Qdos)) |
7337 | *buf++ = '\r'; | |
7338 | else | |
7339 | c = '\r'; | |
aaaf0b1e KH |
7340 | } |
7341 | } | |
433f7f87 | 7342 | |
e6a54062 | 7343 | trans = Qnil; |
09ee6fdd | 7344 | LOOKUP_TRANSLATION_TABLE (translation_table, c, trans); |
e6a54062 | 7345 | if (NILP (trans)) |
433f7f87 KH |
7346 | *buf++ = c; |
7347 | else | |
7348 | { | |
2c6a9faa | 7349 | ptrdiff_t from_nchars = 1, to_nchars = 1; |
433f7f87 KH |
7350 | int *lookup_buf_end; |
7351 | const unsigned char *p = src; | |
7352 | int i; | |
7353 | ||
7354 | lookup_buf[0] = c; | |
7355 | for (i = 1; i < max_lookup && p < src_end; i++) | |
7356 | lookup_buf[i] = STRING_CHAR_ADVANCE (p); | |
7357 | lookup_buf_end = lookup_buf + i; | |
e951386e KH |
7358 | trans = get_translation (trans, lookup_buf, lookup_buf_end); |
7359 | if (INTEGERP (trans)) | |
7360 | c = XINT (trans); | |
7361 | else if (CONSP (trans)) | |
7362 | { | |
7363 | from_nchars = ASIZE (XCAR (trans)); | |
7364 | trans = XCDR (trans); | |
7365 | if (INTEGERP (trans)) | |
7366 | c = XINT (trans); | |
7367 | else | |
7368 | { | |
7369 | to_nchars = ASIZE (trans); | |
2c6a9faa | 7370 | if (buf_end - buf < to_nchars) |
e951386e KH |
7371 | break; |
7372 | c = XINT (AREF (trans, 0)); | |
7373 | } | |
7374 | } | |
7375 | else | |
433f7f87 | 7376 | break; |
e951386e | 7377 | *buf++ = c; |
433f7f87 KH |
7378 | for (i = 1; i < to_nchars; i++) |
7379 | *buf++ = XINT (AREF (trans, i)); | |
7380 | for (i = 1; i < from_nchars; i++, pos++) | |
7381 | src += MULTIBYTE_LENGTH_NO_CHECK (src); | |
7382 | } | |
aaaf0b1e | 7383 | } |
ec6d2bb8 | 7384 | |
df7492f9 KH |
7385 | coding->consumed = src - coding->source; |
7386 | coding->consumed_char = pos - coding->src_pos; | |
7387 | coding->charbuf_used = buf - coding->charbuf; | |
7388 | coding->chars_at_source = 0; | |
aaaf0b1e KH |
7389 | } |
7390 | ||
4ed46869 | 7391 | |
df7492f9 KH |
7392 | /* Encode the text at CODING->src_object into CODING->dst_object. |
7393 | CODING->src_object is a buffer or a string. | |
7394 | CODING->dst_object is a buffer or nil. | |
7395 | ||
7396 | If CODING->src_object is a buffer, it must be the current buffer. | |
7397 | In this case, if CODING->src_pos is positive, it is a position of | |
7398 | the source text in the buffer, otherwise. the source text is in the | |
7399 | gap area of the buffer, and coding->src_pos specifies the offset of | |
7400 | the text from GPT (which must be the same as PT). If this is the | |
7401 | same buffer as CODING->dst_object, CODING->src_pos must be | |
7402 | negative and CODING should not have `pre-write-conversion'. | |
7403 | ||
7404 | If CODING->src_object is a string, CODING should not have | |
7405 | `pre-write-conversion'. | |
7406 | ||
7407 | If CODING->dst_object is a buffer, the encoded data is inserted at | |
7408 | the current point of that buffer. | |
7409 | ||
7410 | If CODING->dst_object is nil, the encoded data is placed at the | |
7411 | memory area specified by CODING->destination. */ | |
7412 | ||
f10fe38f | 7413 | static void |
971de7fb | 7414 | encode_coding (struct coding_system *coding) |
4ed46869 | 7415 | { |
df7492f9 | 7416 | Lisp_Object attrs; |
7d64c6ad | 7417 | Lisp_Object translation_table; |
09ee6fdd | 7418 | int max_lookup; |
fb608df3 | 7419 | struct ccl_spec cclspec; |
9861e777 | 7420 | |
df7492f9 | 7421 | attrs = CODING_ID_ATTRS (coding->id); |
ea29edf2 KH |
7422 | if (coding->encoder == encode_coding_raw_text) |
7423 | translation_table = Qnil, max_lookup = 0; | |
7424 | else | |
7425 | translation_table = get_translation_table (attrs, 1, &max_lookup); | |
4ed46869 | 7426 | |
df7492f9 | 7427 | if (BUFFERP (coding->dst_object)) |
8844fa83 | 7428 | { |
df7492f9 KH |
7429 | set_buffer_internal (XBUFFER (coding->dst_object)); |
7430 | coding->dst_multibyte | |
4b4deea2 | 7431 | = ! NILP (BVAR (current_buffer, enable_multibyte_characters)); |
8844fa83 | 7432 | } |
4ed46869 | 7433 | |
b73bfc1c | 7434 | coding->consumed = coding->consumed_char = 0; |
df7492f9 | 7435 | coding->produced = coding->produced_char = 0; |
065e3595 | 7436 | record_conversion_result (coding, CODING_RESULT_SUCCESS); |
b73bfc1c | 7437 | coding->errors = 0; |
b73bfc1c | 7438 | |
df7492f9 | 7439 | ALLOC_CONVERSION_WORK_AREA (coding); |
4ed46869 | 7440 | |
fb608df3 KH |
7441 | if (coding->encoder == encode_coding_ccl) |
7442 | { | |
7443 | coding->spec.ccl = &cclspec; | |
7444 | setup_ccl_program (&cclspec.ccl, CODING_CCL_ENCODER (coding)); | |
7445 | } | |
df7492f9 KH |
7446 | do { |
7447 | coding_set_source (coding); | |
09ee6fdd | 7448 | consume_chars (coding, translation_table, max_lookup); |
df7492f9 KH |
7449 | coding_set_destination (coding); |
7450 | (*(coding->encoder)) (coding); | |
7451 | } while (coding->consumed_char < coding->src_chars); | |
7452 | ||
284201e4 | 7453 | if (BUFFERP (coding->dst_object) && coding->produced_char > 0) |
df7492f9 | 7454 | insert_from_gap (coding->produced_char, coding->produced); |
ec6d2bb8 KH |
7455 | } |
7456 | ||
fb88bf2d | 7457 | |
24a73b0a KH |
7458 | /* Name (or base name) of work buffer for code conversion. */ |
7459 | static Lisp_Object Vcode_conversion_workbuf_name; | |
d46c5b12 | 7460 | |
24a73b0a KH |
7461 | /* A working buffer used by the top level conversion. Once it is |
7462 | created, it is never destroyed. It has the name | |
7463 | Vcode_conversion_workbuf_name. The other working buffers are | |
7464 | destroyed after the use is finished, and their names are modified | |
7465 | versions of Vcode_conversion_workbuf_name. */ | |
7466 | static Lisp_Object Vcode_conversion_reused_workbuf; | |
b73bfc1c | 7467 | |
f10fe38f PE |
7468 | /* True iff Vcode_conversion_reused_workbuf is already in use. */ |
7469 | static bool reused_workbuf_in_use; | |
4ed46869 | 7470 | |
24a73b0a | 7471 | |
ad1746f5 | 7472 | /* Return a working buffer of code conversion. MULTIBYTE specifies the |
24a73b0a | 7473 | multibyteness of returning buffer. */ |
b73bfc1c | 7474 | |
f6cbaf43 | 7475 | static Lisp_Object |
f10fe38f | 7476 | make_conversion_work_buffer (bool multibyte) |
df7492f9 | 7477 | { |
24a73b0a KH |
7478 | Lisp_Object name, workbuf; |
7479 | struct buffer *current; | |
4ed46869 | 7480 | |
f10fe38f | 7481 | if (reused_workbuf_in_use) |
065e3595 KH |
7482 | { |
7483 | name = Fgenerate_new_buffer_name (Vcode_conversion_workbuf_name, Qnil); | |
7484 | workbuf = Fget_buffer_create (name); | |
7485 | } | |
df7492f9 | 7486 | else |
065e3595 | 7487 | { |
f10fe38f | 7488 | reused_workbuf_in_use = 1; |
159bd5a2 | 7489 | if (NILP (Fbuffer_live_p (Vcode_conversion_reused_workbuf))) |
a993c7a1 KH |
7490 | Vcode_conversion_reused_workbuf |
7491 | = Fget_buffer_create (Vcode_conversion_workbuf_name); | |
7492 | workbuf = Vcode_conversion_reused_workbuf; | |
065e3595 | 7493 | } |
24a73b0a KH |
7494 | current = current_buffer; |
7495 | set_buffer_internal (XBUFFER (workbuf)); | |
df36ff1f CY |
7496 | /* We can't allow modification hooks to run in the work buffer. For |
7497 | instance, directory_files_internal assumes that file decoding | |
7498 | doesn't compile new regexps. */ | |
7499 | Fset (Fmake_local_variable (Qinhibit_modification_hooks), Qt); | |
3ed051d4 | 7500 | Ferase_buffer (); |
39eb03f1 PE |
7501 | bset_undo_list (current_buffer, Qt); |
7502 | bset_enable_multibyte_characters (current_buffer, multibyte ? Qt : Qnil); | |
df7492f9 | 7503 | set_buffer_internal (current); |
24a73b0a | 7504 | return workbuf; |
df7492f9 | 7505 | } |
d46c5b12 | 7506 | |
24a73b0a | 7507 | |
4776e638 | 7508 | static Lisp_Object |
971de7fb | 7509 | code_conversion_restore (Lisp_Object arg) |
4776e638 | 7510 | { |
24a73b0a | 7511 | Lisp_Object current, workbuf; |
948bdcf3 | 7512 | struct gcpro gcpro1; |
24a73b0a | 7513 | |
948bdcf3 | 7514 | GCPRO1 (arg); |
24a73b0a KH |
7515 | current = XCAR (arg); |
7516 | workbuf = XCDR (arg); | |
7517 | if (! NILP (workbuf)) | |
7518 | { | |
7519 | if (EQ (workbuf, Vcode_conversion_reused_workbuf)) | |
7520 | reused_workbuf_in_use = 0; | |
d17337e5 | 7521 | else |
24a73b0a KH |
7522 | Fkill_buffer (workbuf); |
7523 | } | |
7524 | set_buffer_internal (XBUFFER (current)); | |
948bdcf3 | 7525 | UNGCPRO; |
4776e638 KH |
7526 | return Qnil; |
7527 | } | |
b73bfc1c | 7528 | |
24a73b0a | 7529 | Lisp_Object |
f10fe38f | 7530 | code_conversion_save (bool with_work_buf, bool multibyte) |
df7492f9 | 7531 | { |
24a73b0a | 7532 | Lisp_Object workbuf = Qnil; |
b73bfc1c | 7533 | |
4776e638 | 7534 | if (with_work_buf) |
24a73b0a KH |
7535 | workbuf = make_conversion_work_buffer (multibyte); |
7536 | record_unwind_protect (code_conversion_restore, | |
7537 | Fcons (Fcurrent_buffer (), workbuf)); | |
4776e638 | 7538 | return workbuf; |
df7492f9 | 7539 | } |
d46c5b12 | 7540 | |
f10fe38f | 7541 | void |
cf84bb53 | 7542 | decode_coding_gap (struct coding_system *coding, |
d311d28c | 7543 | ptrdiff_t chars, ptrdiff_t bytes) |
df7492f9 | 7544 | { |
d311d28c | 7545 | ptrdiff_t count = SPECPDL_INDEX (); |
5e5c78be | 7546 | Lisp_Object attrs; |
fb88bf2d | 7547 | |
24a73b0a | 7548 | code_conversion_save (0, 0); |
ec6d2bb8 | 7549 | |
24a73b0a | 7550 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7551 | coding->src_chars = chars; |
7552 | coding->src_bytes = bytes; | |
7553 | coding->src_pos = -chars; | |
7554 | coding->src_pos_byte = -bytes; | |
7555 | coding->src_multibyte = chars < bytes; | |
24a73b0a | 7556 | coding->dst_object = coding->src_object; |
df7492f9 KH |
7557 | coding->dst_pos = PT; |
7558 | coding->dst_pos_byte = PT_BYTE; | |
4b4deea2 | 7559 | coding->dst_multibyte = ! NILP (BVAR (current_buffer, enable_multibyte_characters)); |
4ed46869 | 7560 | |
df7492f9 KH |
7561 | if (CODING_REQUIRE_DETECTION (coding)) |
7562 | detect_coding (coding); | |
8f924df7 | 7563 | |
9286b333 | 7564 | coding->mode |= CODING_MODE_LAST_BLOCK; |
287c57d7 | 7565 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 | 7566 | decode_coding (coding); |
287c57d7 | 7567 | current_buffer->text->inhibit_shrinking = 0; |
d46c5b12 | 7568 | |
5e5c78be KH |
7569 | attrs = CODING_ID_ATTRS (coding->id); |
7570 | if (! NILP (CODING_ATTR_POST_READ (attrs))) | |
b73bfc1c | 7571 | { |
d311d28c | 7572 | ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
5e5c78be KH |
7573 | Lisp_Object val; |
7574 | ||
7575 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); | |
5e5c78be KH |
7576 | val = call1 (CODING_ATTR_POST_READ (attrs), |
7577 | make_number (coding->produced_char)); | |
5e5c78be KH |
7578 | CHECK_NATNUM (val); |
7579 | coding->produced_char += Z - prev_Z; | |
7580 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
b73bfc1c | 7581 | } |
4ed46869 | 7582 | |
df7492f9 | 7583 | unbind_to (count, Qnil); |
b73bfc1c | 7584 | } |
52d41803 | 7585 | |
d46c5b12 | 7586 | |
df7492f9 KH |
7587 | /* Decode the text in the range FROM/FROM_BYTE and TO/TO_BYTE in |
7588 | SRC_OBJECT into DST_OBJECT by coding context CODING. | |
b73bfc1c | 7589 | |
df7492f9 | 7590 | SRC_OBJECT is a buffer, a string, or Qnil. |
b73bfc1c | 7591 | |
df7492f9 KH |
7592 | If it is a buffer, the text is at point of the buffer. FROM and TO |
7593 | are positions in the buffer. | |
b73bfc1c | 7594 | |
df7492f9 KH |
7595 | If it is a string, the text is at the beginning of the string. |
7596 | FROM and TO are indices to the string. | |
4ed46869 | 7597 | |
df7492f9 KH |
7598 | If it is nil, the text is at coding->source. FROM and TO are |
7599 | indices to coding->source. | |
bb10be8b | 7600 | |
df7492f9 | 7601 | DST_OBJECT is a buffer, Qt, or Qnil. |
4ed46869 | 7602 | |
df7492f9 KH |
7603 | If it is a buffer, the decoded text is inserted at point of the |
7604 | buffer. If the buffer is the same as SRC_OBJECT, the source text | |
7605 | is deleted. | |
4ed46869 | 7606 | |
df7492f9 KH |
7607 | If it is Qt, a string is made from the decoded text, and |
7608 | set in CODING->dst_object. | |
d46c5b12 | 7609 | |
df7492f9 | 7610 | If it is Qnil, the decoded text is stored at CODING->destination. |
2cb26057 | 7611 | The caller must allocate CODING->dst_bytes bytes at |
df7492f9 KH |
7612 | CODING->destination by xmalloc. If the decoded text is longer than |
7613 | CODING->dst_bytes, CODING->destination is relocated by xrealloc. | |
7614 | */ | |
d46c5b12 | 7615 | |
df7492f9 | 7616 | void |
cf84bb53 JB |
7617 | decode_coding_object (struct coding_system *coding, |
7618 | Lisp_Object src_object, | |
d311d28c PE |
7619 | ptrdiff_t from, ptrdiff_t from_byte, |
7620 | ptrdiff_t to, ptrdiff_t to_byte, | |
cf84bb53 | 7621 | Lisp_Object dst_object) |
d46c5b12 | 7622 | { |
d311d28c | 7623 | ptrdiff_t count = SPECPDL_INDEX (); |
c4a63b12 | 7624 | unsigned char *destination IF_LINT (= NULL); |
d311d28c PE |
7625 | ptrdiff_t dst_bytes IF_LINT (= 0); |
7626 | ptrdiff_t chars = to - from; | |
7627 | ptrdiff_t bytes = to_byte - from_byte; | |
df7492f9 | 7628 | Lisp_Object attrs; |
f10fe38f PE |
7629 | ptrdiff_t saved_pt = -1, saved_pt_byte IF_LINT (= 0); |
7630 | bool need_marker_adjustment = 0; | |
b3bfad50 | 7631 | Lisp_Object old_deactivate_mark; |
d46c5b12 | 7632 | |
b3bfad50 | 7633 | old_deactivate_mark = Vdeactivate_mark; |
93dec019 | 7634 | |
df7492f9 | 7635 | if (NILP (dst_object)) |
d46c5b12 | 7636 | { |
df7492f9 KH |
7637 | destination = coding->destination; |
7638 | dst_bytes = coding->dst_bytes; | |
d46c5b12 | 7639 | } |
93dec019 | 7640 | |
df7492f9 KH |
7641 | coding->src_object = src_object; |
7642 | coding->src_chars = chars; | |
7643 | coding->src_bytes = bytes; | |
7644 | coding->src_multibyte = chars < bytes; | |
70ad9fc4 | 7645 | |
df7492f9 | 7646 | if (STRINGP (src_object)) |
d46c5b12 | 7647 | { |
df7492f9 KH |
7648 | coding->src_pos = from; |
7649 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7650 | } |
df7492f9 | 7651 | else if (BUFFERP (src_object)) |
88993dfd | 7652 | { |
df7492f9 KH |
7653 | set_buffer_internal (XBUFFER (src_object)); |
7654 | if (from != GPT) | |
7655 | move_gap_both (from, from_byte); | |
7656 | if (EQ (src_object, dst_object)) | |
fb88bf2d | 7657 | { |
64cedb0c KH |
7658 | struct Lisp_Marker *tail; |
7659 | ||
7660 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7661 | { | |
7662 | tail->need_adjustment | |
7663 | = tail->charpos == (tail->insertion_type ? from : to); | |
7664 | need_marker_adjustment |= tail->need_adjustment; | |
7665 | } | |
4776e638 | 7666 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 | 7667 | TEMP_SET_PT_BOTH (from, from_byte); |
f4a3cc44 | 7668 | current_buffer->text->inhibit_shrinking = 1; |
df7492f9 KH |
7669 | del_range_both (from, from_byte, to, to_byte, 1); |
7670 | coding->src_pos = -chars; | |
7671 | coding->src_pos_byte = -bytes; | |
fb88bf2d | 7672 | } |
df7492f9 | 7673 | else |
fb88bf2d | 7674 | { |
df7492f9 KH |
7675 | coding->src_pos = from; |
7676 | coding->src_pos_byte = from_byte; | |
fb88bf2d | 7677 | } |
88993dfd KH |
7678 | } |
7679 | ||
df7492f9 KH |
7680 | if (CODING_REQUIRE_DETECTION (coding)) |
7681 | detect_coding (coding); | |
7682 | attrs = CODING_ID_ATTRS (coding->id); | |
d46c5b12 | 7683 | |
2cb26057 KH |
7684 | if (EQ (dst_object, Qt) |
7685 | || (! NILP (CODING_ATTR_POST_READ (attrs)) | |
7686 | && NILP (dst_object))) | |
b73bfc1c | 7687 | { |
a1567c45 SM |
7688 | coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding); |
7689 | coding->dst_object = code_conversion_save (1, coding->dst_multibyte); | |
df7492f9 KH |
7690 | coding->dst_pos = BEG; |
7691 | coding->dst_pos_byte = BEG_BYTE; | |
b73bfc1c | 7692 | } |
df7492f9 | 7693 | else if (BUFFERP (dst_object)) |
d46c5b12 | 7694 | { |
24a73b0a | 7695 | code_conversion_save (0, 0); |
df7492f9 KH |
7696 | coding->dst_object = dst_object; |
7697 | coding->dst_pos = BUF_PT (XBUFFER (dst_object)); | |
7698 | coding->dst_pos_byte = BUF_PT_BYTE (XBUFFER (dst_object)); | |
7699 | coding->dst_multibyte | |
4b4deea2 | 7700 | = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters)); |
d46c5b12 KH |
7701 | } |
7702 | else | |
7703 | { | |
24a73b0a | 7704 | code_conversion_save (0, 0); |
df7492f9 | 7705 | coding->dst_object = Qnil; |
0154725e SM |
7706 | /* Most callers presume this will return a multibyte result, and they |
7707 | won't use `binary' or `raw-text' anyway, so let's not worry about | |
7708 | CODING_FOR_UNIBYTE. */ | |
bb555731 | 7709 | coding->dst_multibyte = 1; |
d46c5b12 KH |
7710 | } |
7711 | ||
df7492f9 | 7712 | decode_coding (coding); |
fa46990e | 7713 | |
df7492f9 KH |
7714 | if (BUFFERP (coding->dst_object)) |
7715 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
d46c5b12 | 7716 | |
df7492f9 | 7717 | if (! NILP (CODING_ATTR_POST_READ (attrs))) |
d46c5b12 | 7718 | { |
b3bfad50 | 7719 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d311d28c | 7720 | ptrdiff_t prev_Z = Z, prev_Z_BYTE = Z_BYTE; |
2b4f9037 | 7721 | Lisp_Object val; |
d46c5b12 | 7722 | |
c0cc7f7f | 7723 | TEMP_SET_PT_BOTH (coding->dst_pos, coding->dst_pos_byte); |
b3bfad50 KH |
7724 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7725 | old_deactivate_mark); | |
d4850d67 KH |
7726 | val = safe_call1 (CODING_ATTR_POST_READ (attrs), |
7727 | make_number (coding->produced_char)); | |
df7492f9 KH |
7728 | UNGCPRO; |
7729 | CHECK_NATNUM (val); | |
7730 | coding->produced_char += Z - prev_Z; | |
7731 | coding->produced += Z_BYTE - prev_Z_BYTE; | |
d46c5b12 | 7732 | } |
de79a6a5 | 7733 | |
df7492f9 | 7734 | if (EQ (dst_object, Qt)) |
ec6d2bb8 | 7735 | { |
df7492f9 KH |
7736 | coding->dst_object = Fbuffer_string (); |
7737 | } | |
7738 | else if (NILP (dst_object) && BUFFERP (coding->dst_object)) | |
7739 | { | |
7740 | set_buffer_internal (XBUFFER (coding->dst_object)); | |
7741 | if (dst_bytes < coding->produced) | |
7742 | { | |
b3bfad50 | 7743 | destination = xrealloc (destination, coding->produced); |
df7492f9 KH |
7744 | if (! destination) |
7745 | { | |
065e3595 | 7746 | record_conversion_result (coding, |
ebaf11b6 | 7747 | CODING_RESULT_INSUFFICIENT_MEM); |
df7492f9 KH |
7748 | unbind_to (count, Qnil); |
7749 | return; | |
7750 | } | |
7751 | if (BEGV < GPT && GPT < BEGV + coding->produced_char) | |
7752 | move_gap_both (BEGV, BEGV_BYTE); | |
72af86bd | 7753 | memcpy (destination, BEGV_ADDR, coding->produced); |
df7492f9 | 7754 | coding->destination = destination; |
d46c5b12 | 7755 | } |
ec6d2bb8 | 7756 | } |
b73bfc1c | 7757 | |
4776e638 KH |
7758 | if (saved_pt >= 0) |
7759 | { | |
7760 | /* This is the case of: | |
7761 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7762 | As we have moved PT while replacing the original buffer | |
7763 | contents, we must recover it now. */ | |
7764 | set_buffer_internal (XBUFFER (src_object)); | |
f4a3cc44 | 7765 | current_buffer->text->inhibit_shrinking = 0; |
4776e638 KH |
7766 | if (saved_pt < from) |
7767 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7768 | else if (saved_pt < from + chars) | |
7769 | TEMP_SET_PT_BOTH (from, from_byte); | |
4b4deea2 | 7770 | else if (! NILP (BVAR (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
7771 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
7772 | saved_pt_byte + (coding->produced - bytes)); | |
7773 | else | |
7774 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), | |
7775 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7776 | |
7777 | if (need_marker_adjustment) | |
7778 | { | |
7779 | struct Lisp_Marker *tail; | |
7780 | ||
7781 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7782 | if (tail->need_adjustment) | |
7783 | { | |
7784 | tail->need_adjustment = 0; | |
7785 | if (tail->insertion_type) | |
7786 | { | |
7787 | tail->bytepos = from_byte; | |
7788 | tail->charpos = from; | |
7789 | } | |
7790 | else | |
7791 | { | |
7792 | tail->bytepos = from_byte + coding->produced; | |
7793 | tail->charpos | |
4b4deea2 | 7794 | = (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
7795 | ? tail->bytepos : from + coding->produced_char); |
7796 | } | |
7797 | } | |
7798 | } | |
d46c5b12 | 7799 | } |
4776e638 | 7800 | |
b3bfad50 | 7801 | Vdeactivate_mark = old_deactivate_mark; |
065e3595 | 7802 | unbind_to (count, coding->dst_object); |
d46c5b12 KH |
7803 | } |
7804 | ||
d46c5b12 | 7805 | |
df7492f9 | 7806 | void |
cf84bb53 JB |
7807 | encode_coding_object (struct coding_system *coding, |
7808 | Lisp_Object src_object, | |
d311d28c PE |
7809 | ptrdiff_t from, ptrdiff_t from_byte, |
7810 | ptrdiff_t to, ptrdiff_t to_byte, | |
cf84bb53 | 7811 | Lisp_Object dst_object) |
d46c5b12 | 7812 | { |
d311d28c PE |
7813 | ptrdiff_t count = SPECPDL_INDEX (); |
7814 | ptrdiff_t chars = to - from; | |
7815 | ptrdiff_t bytes = to_byte - from_byte; | |
df7492f9 | 7816 | Lisp_Object attrs; |
f10fe38f PE |
7817 | ptrdiff_t saved_pt = -1, saved_pt_byte IF_LINT (= 0); |
7818 | bool need_marker_adjustment = 0; | |
7819 | bool kill_src_buffer = 0; | |
b3bfad50 | 7820 | Lisp_Object old_deactivate_mark; |
df7492f9 | 7821 | |
b3bfad50 | 7822 | old_deactivate_mark = Vdeactivate_mark; |
df7492f9 KH |
7823 | |
7824 | coding->src_object = src_object; | |
7825 | coding->src_chars = chars; | |
7826 | coding->src_bytes = bytes; | |
7827 | coding->src_multibyte = chars < bytes; | |
7828 | ||
7829 | attrs = CODING_ID_ATTRS (coding->id); | |
7830 | ||
64cedb0c KH |
7831 | if (EQ (src_object, dst_object)) |
7832 | { | |
7833 | struct Lisp_Marker *tail; | |
7834 | ||
7835 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7836 | { | |
7837 | tail->need_adjustment | |
7838 | = tail->charpos == (tail->insertion_type ? from : to); | |
7839 | need_marker_adjustment |= tail->need_adjustment; | |
7840 | } | |
7841 | } | |
7842 | ||
df7492f9 | 7843 | if (! NILP (CODING_ATTR_PRE_WRITE (attrs))) |
6bac5b12 | 7844 | { |
24a73b0a | 7845 | coding->src_object = code_conversion_save (1, coding->src_multibyte); |
df7492f9 KH |
7846 | set_buffer_internal (XBUFFER (coding->src_object)); |
7847 | if (STRINGP (src_object)) | |
7848 | insert_from_string (src_object, from, from_byte, chars, bytes, 0); | |
7849 | else if (BUFFERP (src_object)) | |
7850 | insert_from_buffer (XBUFFER (src_object), from, chars, 0); | |
7851 | else | |
b68864e5 | 7852 | insert_1_both ((char *) coding->source + from, chars, bytes, 0, 0, 0); |
d46c5b12 | 7853 | |
df7492f9 KH |
7854 | if (EQ (src_object, dst_object)) |
7855 | { | |
7856 | set_buffer_internal (XBUFFER (src_object)); | |
4776e638 | 7857 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
df7492f9 KH |
7858 | del_range_both (from, from_byte, to, to_byte, 1); |
7859 | set_buffer_internal (XBUFFER (coding->src_object)); | |
7860 | } | |
7861 | ||
d4850d67 | 7862 | { |
b3bfad50 | 7863 | struct gcpro gcpro1, gcpro2, gcpro3, gcpro4, gcpro5; |
d4850d67 | 7864 | |
b3bfad50 KH |
7865 | GCPRO5 (coding->src_object, coding->dst_object, src_object, dst_object, |
7866 | old_deactivate_mark); | |
6cd7a139 DA |
7867 | safe_call2 (CODING_ATTR_PRE_WRITE (attrs), |
7868 | make_number (BEG), make_number (Z)); | |
b3bfad50 | 7869 | UNGCPRO; |
d4850d67 | 7870 | } |
c02d943b KH |
7871 | if (XBUFFER (coding->src_object) != current_buffer) |
7872 | kill_src_buffer = 1; | |
ac87bbef | 7873 | coding->src_object = Fcurrent_buffer (); |
df7492f9 KH |
7874 | if (BEG != GPT) |
7875 | move_gap_both (BEG, BEG_BYTE); | |
7876 | coding->src_chars = Z - BEG; | |
7877 | coding->src_bytes = Z_BYTE - BEG_BYTE; | |
7878 | coding->src_pos = BEG; | |
7879 | coding->src_pos_byte = BEG_BYTE; | |
7880 | coding->src_multibyte = Z < Z_BYTE; | |
7881 | } | |
7882 | else if (STRINGP (src_object)) | |
d46c5b12 | 7883 | { |
24a73b0a | 7884 | code_conversion_save (0, 0); |
df7492f9 KH |
7885 | coding->src_pos = from; |
7886 | coding->src_pos_byte = from_byte; | |
b73bfc1c | 7887 | } |
df7492f9 | 7888 | else if (BUFFERP (src_object)) |
b73bfc1c | 7889 | { |
24a73b0a | 7890 | code_conversion_save (0, 0); |
df7492f9 | 7891 | set_buffer_internal (XBUFFER (src_object)); |
df7492f9 | 7892 | if (EQ (src_object, dst_object)) |
d46c5b12 | 7893 | { |
4776e638 | 7894 | saved_pt = PT, saved_pt_byte = PT_BYTE; |
ff0dacd7 KH |
7895 | coding->src_object = del_range_1 (from, to, 1, 1); |
7896 | coding->src_pos = 0; | |
7897 | coding->src_pos_byte = 0; | |
d46c5b12 | 7898 | } |
df7492f9 | 7899 | else |
d46c5b12 | 7900 | { |
ff0dacd7 KH |
7901 | if (from < GPT && to >= GPT) |
7902 | move_gap_both (from, from_byte); | |
df7492f9 KH |
7903 | coding->src_pos = from; |
7904 | coding->src_pos_byte = from_byte; | |
d46c5b12 | 7905 | } |
d46c5b12 | 7906 | } |
4776e638 | 7907 | else |
24a73b0a | 7908 | code_conversion_save (0, 0); |
d46c5b12 | 7909 | |
df7492f9 | 7910 | if (BUFFERP (dst_object)) |
88993dfd | 7911 | { |
df7492f9 | 7912 | coding->dst_object = dst_object; |
28f67a95 KH |
7913 | if (EQ (src_object, dst_object)) |
7914 | { | |
7915 | coding->dst_pos = from; | |
7916 | coding->dst_pos_byte = from_byte; | |
7917 | } | |
7918 | else | |
7919 | { | |
319a3947 KH |
7920 | struct buffer *current = current_buffer; |
7921 | ||
7922 | set_buffer_temp (XBUFFER (dst_object)); | |
7923 | coding->dst_pos = PT; | |
7924 | coding->dst_pos_byte = PT_BYTE; | |
7925 | move_gap_both (coding->dst_pos, coding->dst_pos_byte); | |
7926 | set_buffer_temp (current); | |
28f67a95 | 7927 | } |
df7492f9 | 7928 | coding->dst_multibyte |
4b4deea2 | 7929 | = ! NILP (BVAR (XBUFFER (dst_object), enable_multibyte_characters)); |
88993dfd | 7930 | } |
df7492f9 | 7931 | else if (EQ (dst_object, Qt)) |
d46c5b12 | 7932 | { |
5d009b3a | 7933 | ptrdiff_t dst_bytes = max (1, coding->src_chars); |
df7492f9 | 7934 | coding->dst_object = Qnil; |
23f86fce | 7935 | coding->destination = xmalloc (dst_bytes); |
5d009b3a | 7936 | coding->dst_bytes = dst_bytes; |
df7492f9 | 7937 | coding->dst_multibyte = 0; |
d46c5b12 KH |
7938 | } |
7939 | else | |
7940 | { | |
df7492f9 KH |
7941 | coding->dst_object = Qnil; |
7942 | coding->dst_multibyte = 0; | |
d46c5b12 KH |
7943 | } |
7944 | ||
df7492f9 | 7945 | encode_coding (coding); |
d46c5b12 | 7946 | |
df7492f9 | 7947 | if (EQ (dst_object, Qt)) |
d46c5b12 | 7948 | { |
df7492f9 KH |
7949 | if (BUFFERP (coding->dst_object)) |
7950 | coding->dst_object = Fbuffer_string (); | |
7951 | else | |
d46c5b12 | 7952 | { |
df7492f9 KH |
7953 | coding->dst_object |
7954 | = make_unibyte_string ((char *) coding->destination, | |
7955 | coding->produced); | |
7956 | xfree (coding->destination); | |
d46c5b12 | 7957 | } |
4ed46869 | 7958 | } |
d46c5b12 | 7959 | |
4776e638 KH |
7960 | if (saved_pt >= 0) |
7961 | { | |
7962 | /* This is the case of: | |
7963 | (BUFFERP (src_object) && EQ (src_object, dst_object)) | |
7964 | As we have moved PT while replacing the original buffer | |
7965 | contents, we must recover it now. */ | |
7966 | set_buffer_internal (XBUFFER (src_object)); | |
7967 | if (saved_pt < from) | |
7968 | TEMP_SET_PT_BOTH (saved_pt, saved_pt_byte); | |
7969 | else if (saved_pt < from + chars) | |
7970 | TEMP_SET_PT_BOTH (from, from_byte); | |
4b4deea2 | 7971 | else if (! NILP (BVAR (current_buffer, enable_multibyte_characters))) |
4776e638 KH |
7972 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced_char - chars), |
7973 | saved_pt_byte + (coding->produced - bytes)); | |
d46c5b12 | 7974 | else |
4776e638 KH |
7975 | TEMP_SET_PT_BOTH (saved_pt + (coding->produced - bytes), |
7976 | saved_pt_byte + (coding->produced - bytes)); | |
64cedb0c KH |
7977 | |
7978 | if (need_marker_adjustment) | |
7979 | { | |
7980 | struct Lisp_Marker *tail; | |
7981 | ||
7982 | for (tail = BUF_MARKERS (current_buffer); tail; tail = tail->next) | |
7983 | if (tail->need_adjustment) | |
7984 | { | |
7985 | tail->need_adjustment = 0; | |
7986 | if (tail->insertion_type) | |
7987 | { | |
7988 | tail->bytepos = from_byte; | |
7989 | tail->charpos = from; | |
7990 | } | |
7991 | else | |
7992 | { | |
7993 | tail->bytepos = from_byte + coding->produced; | |
7994 | tail->charpos | |
4b4deea2 | 7995 | = (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
64cedb0c KH |
7996 | ? tail->bytepos : from + coding->produced_char); |
7997 | } | |
7998 | } | |
7999 | } | |
4776e638 KH |
8000 | } |
8001 | ||
c02d943b KH |
8002 | if (kill_src_buffer) |
8003 | Fkill_buffer (coding->src_object); | |
b3bfad50 KH |
8004 | |
8005 | Vdeactivate_mark = old_deactivate_mark; | |
df7492f9 | 8006 | unbind_to (count, Qnil); |
b73bfc1c KH |
8007 | } |
8008 | ||
df7492f9 | 8009 | |
b73bfc1c | 8010 | Lisp_Object |
971de7fb | 8011 | preferred_coding_system (void) |
b73bfc1c | 8012 | { |
df7492f9 | 8013 | int id = coding_categories[coding_priorities[0]].id; |
2391eaa4 | 8014 | |
df7492f9 | 8015 | return CODING_ID_NAME (id); |
4ed46869 KH |
8016 | } |
8017 | ||
8018 | \f | |
8019 | #ifdef emacs | |
1397dc18 | 8020 | /*** 8. Emacs Lisp library functions ***/ |
4ed46869 | 8021 | |
a7ca3326 | 8022 | DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0, |
48b0f3ae | 8023 | doc: /* Return t if OBJECT is nil or a coding-system. |
df7492f9 | 8024 | See the documentation of `define-coding-system' for information |
48b0f3ae | 8025 | about coding-system objects. */) |
5842a27b | 8026 | (Lisp_Object object) |
4ed46869 | 8027 | { |
d4a1d553 JB |
8028 | if (NILP (object) |
8029 | || CODING_SYSTEM_ID (object) >= 0) | |
44e8490d | 8030 | return Qt; |
d4a1d553 JB |
8031 | if (! SYMBOLP (object) |
8032 | || NILP (Fget (object, Qcoding_system_define_form))) | |
44e8490d KH |
8033 | return Qnil; |
8034 | return Qt; | |
4ed46869 KH |
8035 | } |
8036 | ||
a7ca3326 | 8037 | DEFUN ("read-non-nil-coding-system", Fread_non_nil_coding_system, |
9d991de8 | 8038 | Sread_non_nil_coding_system, 1, 1, 0, |
48b0f3ae | 8039 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. */) |
5842a27b | 8040 | (Lisp_Object prompt) |
4ed46869 | 8041 | { |
e0e989f6 | 8042 | Lisp_Object val; |
9d991de8 RS |
8043 | do |
8044 | { | |
4608c386 KH |
8045 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
8046 | Qt, Qnil, Qcoding_system_history, Qnil, Qnil); | |
9d991de8 | 8047 | } |
8f924df7 | 8048 | while (SCHARS (val) == 0); |
e0e989f6 | 8049 | return (Fintern (val, Qnil)); |
4ed46869 KH |
8050 | } |
8051 | ||
a7ca3326 | 8052 | DEFUN ("read-coding-system", Fread_coding_system, Sread_coding_system, 1, 2, 0, |
48b0f3ae | 8053 | doc: /* Read a coding system from the minibuffer, prompting with string PROMPT. |
c7183fb8 GM |
8054 | If the user enters null input, return second argument DEFAULT-CODING-SYSTEM. |
8055 | Ignores case when completing coding systems (all Emacs coding systems | |
8056 | are lower-case). */) | |
5842a27b | 8057 | (Lisp_Object prompt, Lisp_Object default_coding_system) |
4ed46869 | 8058 | { |
f44d27ce | 8059 | Lisp_Object val; |
d311d28c | 8060 | ptrdiff_t count = SPECPDL_INDEX (); |
c7183fb8 | 8061 | |
9b787f3e | 8062 | if (SYMBOLP (default_coding_system)) |
57d25e6f | 8063 | default_coding_system = SYMBOL_NAME (default_coding_system); |
c7183fb8 | 8064 | specbind (Qcompletion_ignore_case, Qt); |
4608c386 | 8065 | val = Fcompleting_read (prompt, Vcoding_system_alist, Qnil, |
9b787f3e RS |
8066 | Qt, Qnil, Qcoding_system_history, |
8067 | default_coding_system, Qnil); | |
c7183fb8 | 8068 | unbind_to (count, Qnil); |
8f924df7 | 8069 | return (SCHARS (val) == 0 ? Qnil : Fintern (val, Qnil)); |
4ed46869 KH |
8070 | } |
8071 | ||
a7ca3326 | 8072 | DEFUN ("check-coding-system", Fcheck_coding_system, Scheck_coding_system, |
4ed46869 | 8073 | 1, 1, 0, |
48b0f3ae | 8074 | doc: /* Check validity of CODING-SYSTEM. |
9ffd559c KH |
8075 | If valid, return CODING-SYSTEM, else signal a `coding-system-error' error. |
8076 | It is valid if it is nil or a symbol defined as a coding system by the | |
8077 | function `define-coding-system'. */) | |
5842a27b | 8078 | (Lisp_Object coding_system) |
4ed46869 | 8079 | { |
44e8490d KH |
8080 | Lisp_Object define_form; |
8081 | ||
8082 | define_form = Fget (coding_system, Qcoding_system_define_form); | |
8083 | if (! NILP (define_form)) | |
8084 | { | |
8085 | Fput (coding_system, Qcoding_system_define_form, Qnil); | |
8086 | safe_eval (define_form); | |
8087 | } | |
4ed46869 KH |
8088 | if (!NILP (Fcoding_system_p (coding_system))) |
8089 | return coding_system; | |
fcad4ec4 | 8090 | xsignal1 (Qcoding_system_error, coding_system); |
4ed46869 | 8091 | } |
df7492f9 | 8092 | |
3a73fa5d | 8093 | \f |
89528eb3 | 8094 | /* Detect how the bytes at SRC of length SRC_BYTES are encoded. If |
f10fe38f | 8095 | HIGHEST, return the coding system of the highest |
ad1746f5 | 8096 | priority among the detected coding systems. Otherwise return a |
89528eb3 | 8097 | list of detected coding systems sorted by their priorities. If |
f10fe38f | 8098 | MULTIBYTEP, it is assumed that the bytes are in correct |
89528eb3 KH |
8099 | multibyte form but contains only ASCII and eight-bit chars. |
8100 | Otherwise, the bytes are raw bytes. | |
8101 | ||
8102 | CODING-SYSTEM controls the detection as below: | |
8103 | ||
8104 | If it is nil, detect both text-format and eol-format. If the | |
8105 | text-format part of CODING-SYSTEM is already specified | |
8106 | (e.g. `iso-latin-1'), detect only eol-format. If the eol-format | |
8107 | part of CODING-SYSTEM is already specified (e.g. `undecided-unix'), | |
8108 | detect only text-format. */ | |
8109 | ||
d46c5b12 | 8110 | Lisp_Object |
cf84bb53 | 8111 | detect_coding_system (const unsigned char *src, |
d311d28c | 8112 | ptrdiff_t src_chars, ptrdiff_t src_bytes, |
f10fe38f | 8113 | bool highest, bool multibytep, |
cf84bb53 | 8114 | Lisp_Object coding_system) |
4ed46869 | 8115 | { |
8f924df7 | 8116 | const unsigned char *src_end = src + src_bytes; |
df7492f9 | 8117 | Lisp_Object attrs, eol_type; |
4533845d | 8118 | Lisp_Object val = Qnil; |
df7492f9 | 8119 | struct coding_system coding; |
d3411f89 | 8120 | ptrdiff_t id; |
ff0dacd7 | 8121 | struct coding_detection_info detect_info; |
24a73b0a | 8122 | enum coding_category base_category; |
f10fe38f | 8123 | bool null_byte_found = 0, eight_bit_found = 0; |
b73bfc1c | 8124 | |
df7492f9 KH |
8125 | if (NILP (coding_system)) |
8126 | coding_system = Qundecided; | |
8127 | setup_coding_system (coding_system, &coding); | |
8128 | attrs = CODING_ID_ATTRS (coding.id); | |
8129 | eol_type = CODING_ID_EOL_TYPE (coding.id); | |
89528eb3 | 8130 | coding_system = CODING_ATTR_BASE_NAME (attrs); |
4ed46869 | 8131 | |
df7492f9 | 8132 | coding.source = src; |
24a73b0a | 8133 | coding.src_chars = src_chars; |
df7492f9 KH |
8134 | coding.src_bytes = src_bytes; |
8135 | coding.src_multibyte = multibytep; | |
8136 | coding.consumed = 0; | |
89528eb3 | 8137 | coding.mode |= CODING_MODE_LAST_BLOCK; |
c0e16b14 | 8138 | coding.head_ascii = 0; |
d46c5b12 | 8139 | |
ff0dacd7 | 8140 | detect_info.checked = detect_info.found = detect_info.rejected = 0; |
d46c5b12 | 8141 | |
89528eb3 | 8142 | /* At first, detect text-format if necessary. */ |
24a73b0a KH |
8143 | base_category = XINT (CODING_ATTR_CATEGORY (attrs)); |
8144 | if (base_category == coding_category_undecided) | |
4ed46869 | 8145 | { |
c4a63b12 PE |
8146 | enum coding_category category IF_LINT (= 0); |
8147 | struct coding_system *this IF_LINT (= NULL); | |
ff0dacd7 | 8148 | int c, i; |
88993dfd | 8149 | |
24a73b0a | 8150 | /* Skip all ASCII bytes except for a few ISO2022 controls. */ |
2f3cbb32 | 8151 | for (; src < src_end; src++) |
4ed46869 | 8152 | { |
df7492f9 | 8153 | c = *src; |
6cb21a4f | 8154 | if (c & 0x80) |
6cb21a4f | 8155 | { |
2f3cbb32 | 8156 | eight_bit_found = 1; |
2f3cbb32 KH |
8157 | if (null_byte_found) |
8158 | break; | |
8159 | } | |
c0e16b14 | 8160 | else if (c < 0x20) |
2f3cbb32 KH |
8161 | { |
8162 | if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO) | |
8163 | && ! inhibit_iso_escape_detection | |
8164 | && ! detect_info.checked) | |
6cb21a4f | 8165 | { |
2f3cbb32 KH |
8166 | if (detect_coding_iso_2022 (&coding, &detect_info)) |
8167 | { | |
8168 | /* We have scanned the whole data. */ | |
8169 | if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE)) | |
c0e16b14 KH |
8170 | { |
8171 | /* We didn't find an 8-bit code. We may | |
8172 | have found a null-byte, but it's very | |
8173 | rare that a binary file confirm to | |
8174 | ISO-2022. */ | |
8175 | src = src_end; | |
8176 | coding.head_ascii = src - coding.source; | |
8177 | } | |
8178 | detect_info.rejected |= ~CATEGORY_MASK_ISO_ESCAPE; | |
2f3cbb32 KH |
8179 | break; |
8180 | } | |
8181 | } | |
97b1b294 | 8182 | else if (! c && !inhibit_null_byte_detection) |
2f3cbb32 KH |
8183 | { |
8184 | null_byte_found = 1; | |
8185 | if (eight_bit_found) | |
8186 | break; | |
6cb21a4f | 8187 | } |
c006c0c8 KH |
8188 | if (! eight_bit_found) |
8189 | coding.head_ascii++; | |
6cb21a4f | 8190 | } |
c006c0c8 | 8191 | else if (! eight_bit_found) |
c0e16b14 | 8192 | coding.head_ascii++; |
4ed46869 | 8193 | } |
88993dfd | 8194 | |
2f3cbb32 KH |
8195 | if (null_byte_found || eight_bit_found |
8196 | || coding.head_ascii < coding.src_bytes | |
6cb21a4f KH |
8197 | || detect_info.found) |
8198 | { | |
2f3cbb32 | 8199 | if (coding.head_ascii == coding.src_bytes) |
6cb21a4f KH |
8200 | /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings. */ |
8201 | for (i = 0; i < coding_category_raw_text; i++) | |
ff0dacd7 | 8202 | { |
6cb21a4f | 8203 | category = coding_priorities[i]; |
c7266f4a | 8204 | this = coding_categories + category; |
6cb21a4f | 8205 | if (detect_info.found & (1 << category)) |
ff0dacd7 KH |
8206 | break; |
8207 | } | |
6cb21a4f | 8208 | else |
2f3cbb32 KH |
8209 | { |
8210 | if (null_byte_found) | |
8211 | { | |
8212 | detect_info.checked |= ~CATEGORY_MASK_UTF_16; | |
8213 | detect_info.rejected |= ~CATEGORY_MASK_UTF_16; | |
8214 | } | |
8215 | for (i = 0; i < coding_category_raw_text; i++) | |
8216 | { | |
8217 | category = coding_priorities[i]; | |
8218 | this = coding_categories + category; | |
6cb21a4f | 8219 | |
2f3cbb32 KH |
8220 | if (this->id < 0) |
8221 | { | |
8222 | /* No coding system of this category is defined. */ | |
8223 | detect_info.rejected |= (1 << category); | |
8224 | } | |
8225 | else if (category >= coding_category_raw_text) | |
8226 | continue; | |
8227 | else if (detect_info.checked & (1 << category)) | |
8228 | { | |
8229 | if (highest | |
8230 | && (detect_info.found & (1 << category))) | |
6cb21a4f | 8231 | break; |
2f3cbb32 KH |
8232 | } |
8233 | else if ((*(this->detector)) (&coding, &detect_info) | |
8234 | && highest | |
8235 | && (detect_info.found & (1 << category))) | |
8236 | { | |
8237 | if (category == coding_category_utf_16_auto) | |
8238 | { | |
8239 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8240 | category = coding_category_utf_16_le; | |
8241 | else | |
8242 | category = coding_category_utf_16_be; | |
8243 | } | |
8244 | break; | |
8245 | } | |
8246 | } | |
8247 | } | |
6cb21a4f | 8248 | } |
ec6d2bb8 | 8249 | |
4cddb209 KH |
8250 | if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY |
8251 | || null_byte_found) | |
ec6d2bb8 | 8252 | { |
ff0dacd7 | 8253 | detect_info.found = CATEGORY_MASK_RAW_TEXT; |
4cddb209 | 8254 | id = CODING_SYSTEM_ID (Qno_conversion); |
89528eb3 KH |
8255 | val = Fcons (make_number (id), Qnil); |
8256 | } | |
ff0dacd7 | 8257 | else if (! detect_info.rejected && ! detect_info.found) |
89528eb3 | 8258 | { |
ff0dacd7 | 8259 | detect_info.found = CATEGORY_MASK_ANY; |
89528eb3 KH |
8260 | id = coding_categories[coding_category_undecided].id; |
8261 | val = Fcons (make_number (id), Qnil); | |
8262 | } | |
8263 | else if (highest) | |
8264 | { | |
ff0dacd7 | 8265 | if (detect_info.found) |
ec6d2bb8 | 8266 | { |
ff0dacd7 KH |
8267 | detect_info.found = 1 << category; |
8268 | val = Fcons (make_number (this->id), Qnil); | |
8269 | } | |
8270 | else | |
8271 | for (i = 0; i < coding_category_raw_text; i++) | |
8272 | if (! (detect_info.rejected & (1 << coding_priorities[i]))) | |
8273 | { | |
8274 | detect_info.found = 1 << coding_priorities[i]; | |
8275 | id = coding_categories[coding_priorities[i]].id; | |
8276 | val = Fcons (make_number (id), Qnil); | |
8277 | break; | |
8278 | } | |
8279 | } | |
89528eb3 KH |
8280 | else |
8281 | { | |
ff0dacd7 KH |
8282 | int mask = detect_info.rejected | detect_info.found; |
8283 | int found = 0; | |
ec6d2bb8 | 8284 | |
89528eb3 | 8285 | for (i = coding_category_raw_text - 1; i >= 0; i--) |
ff0dacd7 KH |
8286 | { |
8287 | category = coding_priorities[i]; | |
8288 | if (! (mask & (1 << category))) | |
ec6d2bb8 | 8289 | { |
ff0dacd7 KH |
8290 | found |= 1 << category; |
8291 | id = coding_categories[category].id; | |
c7266f4a KH |
8292 | if (id >= 0) |
8293 | val = Fcons (make_number (id), val); | |
ff0dacd7 KH |
8294 | } |
8295 | } | |
8296 | for (i = coding_category_raw_text - 1; i >= 0; i--) | |
8297 | { | |
8298 | category = coding_priorities[i]; | |
8299 | if (detect_info.found & (1 << category)) | |
8300 | { | |
8301 | id = coding_categories[category].id; | |
8302 | val = Fcons (make_number (id), val); | |
ec6d2bb8 | 8303 | } |
ec6d2bb8 | 8304 | } |
ff0dacd7 | 8305 | detect_info.found |= found; |
ec6d2bb8 | 8306 | } |
ec6d2bb8 | 8307 | } |
a470d443 KH |
8308 | else if (base_category == coding_category_utf_8_auto) |
8309 | { | |
8310 | if (detect_coding_utf_8 (&coding, &detect_info)) | |
8311 | { | |
8312 | struct coding_system *this; | |
8313 | ||
8314 | if (detect_info.found & CATEGORY_MASK_UTF_8_SIG) | |
8315 | this = coding_categories + coding_category_utf_8_sig; | |
8316 | else | |
8317 | this = coding_categories + coding_category_utf_8_nosig; | |
8318 | val = Fcons (make_number (this->id), Qnil); | |
8319 | } | |
8320 | } | |
24a73b0a KH |
8321 | else if (base_category == coding_category_utf_16_auto) |
8322 | { | |
8323 | if (detect_coding_utf_16 (&coding, &detect_info)) | |
8324 | { | |
24a73b0a KH |
8325 | struct coding_system *this; |
8326 | ||
8327 | if (detect_info.found & CATEGORY_MASK_UTF_16_LE) | |
8328 | this = coding_categories + coding_category_utf_16_le; | |
8329 | else if (detect_info.found & CATEGORY_MASK_UTF_16_BE) | |
8330 | this = coding_categories + coding_category_utf_16_be; | |
8331 | else if (detect_info.rejected & CATEGORY_MASK_UTF_16_LE_NOSIG) | |
8332 | this = coding_categories + coding_category_utf_16_be_nosig; | |
8333 | else | |
8334 | this = coding_categories + coding_category_utf_16_le_nosig; | |
8335 | val = Fcons (make_number (this->id), Qnil); | |
8336 | } | |
8337 | } | |
df7492f9 KH |
8338 | else |
8339 | { | |
ff0dacd7 | 8340 | detect_info.found = 1 << XINT (CODING_ATTR_CATEGORY (attrs)); |
89528eb3 | 8341 | val = Fcons (make_number (coding.id), Qnil); |
4ed46869 | 8342 | } |
df7492f9 | 8343 | |
89528eb3 | 8344 | /* Then, detect eol-format if necessary. */ |
df7492f9 | 8345 | { |
4533845d | 8346 | int normal_eol = -1, utf_16_be_eol = -1, utf_16_le_eol = -1; |
df7492f9 KH |
8347 | Lisp_Object tail; |
8348 | ||
89528eb3 KH |
8349 | if (VECTORP (eol_type)) |
8350 | { | |
ff0dacd7 | 8351 | if (detect_info.found & ~CATEGORY_MASK_UTF_16) |
2f3cbb32 KH |
8352 | { |
8353 | if (null_byte_found) | |
8354 | normal_eol = EOL_SEEN_LF; | |
8355 | else | |
8356 | normal_eol = detect_eol (coding.source, src_bytes, | |
8357 | coding_category_raw_text); | |
8358 | } | |
ff0dacd7 KH |
8359 | if (detect_info.found & (CATEGORY_MASK_UTF_16_BE |
8360 | | CATEGORY_MASK_UTF_16_BE_NOSIG)) | |
89528eb3 KH |
8361 | utf_16_be_eol = detect_eol (coding.source, src_bytes, |
8362 | coding_category_utf_16_be); | |
ff0dacd7 KH |
8363 | if (detect_info.found & (CATEGORY_MASK_UTF_16_LE |
8364 | | CATEGORY_MASK_UTF_16_LE_NOSIG)) | |
89528eb3 KH |
8365 | utf_16_le_eol = detect_eol (coding.source, src_bytes, |
8366 | coding_category_utf_16_le); | |
8367 | } | |
8368 | else | |
8369 | { | |
8370 | if (EQ (eol_type, Qunix)) | |
8371 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_LF; | |
8372 | else if (EQ (eol_type, Qdos)) | |
8373 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CRLF; | |
8374 | else | |
8375 | normal_eol = utf_16_be_eol = utf_16_le_eol = EOL_SEEN_CR; | |
8376 | } | |
8377 | ||
df7492f9 KH |
8378 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
8379 | { | |
89528eb3 | 8380 | enum coding_category category; |
df7492f9 | 8381 | int this_eol; |
89528eb3 KH |
8382 | |
8383 | id = XINT (XCAR (tail)); | |
8384 | attrs = CODING_ID_ATTRS (id); | |
8385 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
8386 | eol_type = CODING_ID_EOL_TYPE (id); | |
df7492f9 KH |
8387 | if (VECTORP (eol_type)) |
8388 | { | |
89528eb3 KH |
8389 | if (category == coding_category_utf_16_be |
8390 | || category == coding_category_utf_16_be_nosig) | |
8391 | this_eol = utf_16_be_eol; | |
8392 | else if (category == coding_category_utf_16_le | |
8393 | || category == coding_category_utf_16_le_nosig) | |
8394 | this_eol = utf_16_le_eol; | |
df7492f9 | 8395 | else |
89528eb3 KH |
8396 | this_eol = normal_eol; |
8397 | ||
df7492f9 KH |
8398 | if (this_eol == EOL_SEEN_LF) |
8399 | XSETCAR (tail, AREF (eol_type, 0)); | |
8400 | else if (this_eol == EOL_SEEN_CRLF) | |
8401 | XSETCAR (tail, AREF (eol_type, 1)); | |
8402 | else if (this_eol == EOL_SEEN_CR) | |
8403 | XSETCAR (tail, AREF (eol_type, 2)); | |
89528eb3 KH |
8404 | else |
8405 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 | 8406 | } |
89528eb3 KH |
8407 | else |
8408 | XSETCAR (tail, CODING_ID_NAME (id)); | |
df7492f9 KH |
8409 | } |
8410 | } | |
ec6d2bb8 | 8411 | |
4533845d | 8412 | return (highest ? (CONSP (val) ? XCAR (val) : Qnil) : val); |
ec6d2bb8 KH |
8413 | } |
8414 | ||
ec6d2bb8 | 8415 | |
d46c5b12 KH |
8416 | DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region, |
8417 | 2, 3, 0, | |
48b0f3ae PJ |
8418 | doc: /* Detect coding system of the text in the region between START and END. |
8419 | Return a list of possible coding systems ordered by priority. | |
b811c52b KH |
8420 | The coding systems to try and their priorities follows what |
8421 | the function `coding-system-priority-list' (which see) returns. | |
ec6d2bb8 | 8422 | |
12e0131a | 8423 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8424 | characters as ESC), it returns a list of single element `undecided' |
8425 | or its subsidiary coding system according to a detected end-of-line | |
8426 | format. | |
ec6d2bb8 | 8427 | |
48b0f3ae PJ |
8428 | If optional argument HIGHEST is non-nil, return the coding system of |
8429 | highest priority. */) | |
5842a27b | 8430 | (Lisp_Object start, Lisp_Object end, Lisp_Object highest) |
d46c5b12 | 8431 | { |
d311d28c PE |
8432 | ptrdiff_t from, to; |
8433 | ptrdiff_t from_byte, to_byte; | |
ec6d2bb8 | 8434 | |
b7826503 PJ |
8435 | CHECK_NUMBER_COERCE_MARKER (start); |
8436 | CHECK_NUMBER_COERCE_MARKER (end); | |
ec6d2bb8 | 8437 | |
d46c5b12 KH |
8438 | validate_region (&start, &end); |
8439 | from = XINT (start), to = XINT (end); | |
8440 | from_byte = CHAR_TO_BYTE (from); | |
8441 | to_byte = CHAR_TO_BYTE (to); | |
ec6d2bb8 | 8442 | |
d46c5b12 KH |
8443 | if (from < GPT && to >= GPT) |
8444 | move_gap_both (to, to_byte); | |
c210f766 | 8445 | |
d46c5b12 | 8446 | return detect_coding_system (BYTE_POS_ADDR (from_byte), |
24a73b0a | 8447 | to - from, to_byte - from_byte, |
0a28aafb | 8448 | !NILP (highest), |
4b4deea2 | 8449 | !NILP (BVAR (current_buffer |
5d8ea120 | 8450 | , enable_multibyte_characters)), |
df7492f9 | 8451 | Qnil); |
ec6d2bb8 KH |
8452 | } |
8453 | ||
d46c5b12 KH |
8454 | DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string, |
8455 | 1, 2, 0, | |
48b0f3ae PJ |
8456 | doc: /* Detect coding system of the text in STRING. |
8457 | Return a list of possible coding systems ordered by priority. | |
67ceab9d KH |
8458 | The coding systems to try and their priorities follows what |
8459 | the function `coding-system-priority-list' (which see) returns. | |
fb88bf2d | 8460 | |
12e0131a | 8461 | If only ASCII characters are found (except for such ISO-2022 control |
d4a1d553 JB |
8462 | characters as ESC), it returns a list of single element `undecided' |
8463 | or its subsidiary coding system according to a detected end-of-line | |
8464 | format. | |
d46c5b12 | 8465 | |
48b0f3ae PJ |
8466 | If optional argument HIGHEST is non-nil, return the coding system of |
8467 | highest priority. */) | |
5842a27b | 8468 | (Lisp_Object string, Lisp_Object highest) |
d46c5b12 | 8469 | { |
b7826503 | 8470 | CHECK_STRING (string); |
b73bfc1c | 8471 | |
24a73b0a KH |
8472 | return detect_coding_system (SDATA (string), |
8473 | SCHARS (string), SBYTES (string), | |
8f924df7 | 8474 | !NILP (highest), STRING_MULTIBYTE (string), |
df7492f9 | 8475 | Qnil); |
4ed46869 | 8476 | } |
4ed46869 | 8477 | |
b73bfc1c | 8478 | |
f10fe38f | 8479 | static inline bool |
971de7fb | 8480 | char_encodable_p (int c, Lisp_Object attrs) |
05e6f5dc | 8481 | { |
df7492f9 | 8482 | Lisp_Object tail; |
df7492f9 | 8483 | struct charset *charset; |
7d64c6ad | 8484 | Lisp_Object translation_table; |
d46c5b12 | 8485 | |
7d64c6ad | 8486 | translation_table = CODING_ATTR_TRANS_TBL (attrs); |
a6f87d34 | 8487 | if (! NILP (translation_table)) |
7d64c6ad | 8488 | c = translate_char (translation_table, c); |
df7492f9 KH |
8489 | for (tail = CODING_ATTR_CHARSET_LIST (attrs); |
8490 | CONSP (tail); tail = XCDR (tail)) | |
e133c8fa | 8491 | { |
df7492f9 KH |
8492 | charset = CHARSET_FROM_ID (XINT (XCAR (tail))); |
8493 | if (CHAR_CHARSET_P (c, charset)) | |
8494 | break; | |
e133c8fa | 8495 | } |
df7492f9 | 8496 | return (! NILP (tail)); |
05e6f5dc | 8497 | } |
83fa074f | 8498 | |
fb88bf2d | 8499 | |
df7492f9 KH |
8500 | /* Return a list of coding systems that safely encode the text between |
8501 | START and END. If EXCLUDE is non-nil, it is a list of coding | |
8502 | systems not to check. The returned list doesn't contain any such | |
48468dac | 8503 | coding systems. In any case, if the text contains only ASCII or is |
df7492f9 | 8504 | unibyte, return t. */ |
e077cc80 | 8505 | |
df7492f9 KH |
8506 | DEFUN ("find-coding-systems-region-internal", |
8507 | Ffind_coding_systems_region_internal, | |
8508 | Sfind_coding_systems_region_internal, 2, 3, 0, | |
8509 | doc: /* Internal use only. */) | |
5842a27b | 8510 | (Lisp_Object start, Lisp_Object end, Lisp_Object exclude) |
df7492f9 KH |
8511 | { |
8512 | Lisp_Object coding_attrs_list, safe_codings; | |
d311d28c | 8513 | ptrdiff_t start_byte, end_byte; |
7c78e542 | 8514 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8515 | int c; |
0e727afa | 8516 | Lisp_Object tail, elt, work_table; |
d46c5b12 | 8517 | |
df7492f9 KH |
8518 | if (STRINGP (start)) |
8519 | { | |
8520 | if (!STRING_MULTIBYTE (start) | |
8f924df7 | 8521 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8522 | return Qt; |
8523 | start_byte = 0; | |
8f924df7 | 8524 | end_byte = SBYTES (start); |
df7492f9 KH |
8525 | } |
8526 | else | |
d46c5b12 | 8527 | { |
df7492f9 KH |
8528 | CHECK_NUMBER_COERCE_MARKER (start); |
8529 | CHECK_NUMBER_COERCE_MARKER (end); | |
8530 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) | |
8531 | args_out_of_range (start, end); | |
4b4deea2 | 8532 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8533 | return Qt; |
8534 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8535 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8536 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
8537 | return Qt; | |
d46c5b12 | 8538 | |
e1c23804 | 8539 | if (XINT (start) < GPT && XINT (end) > GPT) |
d46c5b12 | 8540 | { |
e1c23804 DL |
8541 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8542 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8543 | else |
e1c23804 | 8544 | move_gap_both (XINT (end), end_byte); |
d46c5b12 KH |
8545 | } |
8546 | } | |
8547 | ||
df7492f9 KH |
8548 | coding_attrs_list = Qnil; |
8549 | for (tail = Vcoding_system_list; CONSP (tail); tail = XCDR (tail)) | |
8550 | if (NILP (exclude) | |
8551 | || NILP (Fmemq (XCAR (tail), exclude))) | |
8552 | { | |
8553 | Lisp_Object attrs; | |
d46c5b12 | 8554 | |
df7492f9 KH |
8555 | attrs = AREF (CODING_SYSTEM_SPEC (XCAR (tail)), 0); |
8556 | if (EQ (XCAR (tail), CODING_ATTR_BASE_NAME (attrs)) | |
8557 | && ! EQ (CODING_ATTR_TYPE (attrs), Qundecided)) | |
7d64c6ad KH |
8558 | { |
8559 | ASET (attrs, coding_attr_trans_tbl, | |
2170c8f0 | 8560 | get_translation_table (attrs, 1, NULL)); |
7d64c6ad KH |
8561 | coding_attrs_list = Fcons (attrs, coding_attrs_list); |
8562 | } | |
df7492f9 | 8563 | } |
d46c5b12 | 8564 | |
df7492f9 | 8565 | if (STRINGP (start)) |
8f924df7 | 8566 | p = pbeg = SDATA (start); |
df7492f9 KH |
8567 | else |
8568 | p = pbeg = BYTE_POS_ADDR (start_byte); | |
8569 | pend = p + (end_byte - start_byte); | |
b843d1ae | 8570 | |
df7492f9 KH |
8571 | while (p < pend && ASCII_BYTE_P (*p)) p++; |
8572 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
d46c5b12 | 8573 | |
0e727afa | 8574 | work_table = Fmake_char_table (Qnil, Qnil); |
05e6f5dc | 8575 | while (p < pend) |
72d1a715 | 8576 | { |
df7492f9 KH |
8577 | if (ASCII_BYTE_P (*p)) |
8578 | p++; | |
72d1a715 RS |
8579 | else |
8580 | { | |
df7492f9 | 8581 | c = STRING_CHAR_ADVANCE (p); |
0e727afa YM |
8582 | if (!NILP (char_table_ref (work_table, c))) |
8583 | /* This character was already checked. Ignore it. */ | |
8584 | continue; | |
12410ef1 | 8585 | |
df7492f9 KH |
8586 | charset_map_loaded = 0; |
8587 | for (tail = coding_attrs_list; CONSP (tail);) | |
8588 | { | |
8589 | elt = XCAR (tail); | |
8590 | if (NILP (elt)) | |
8591 | tail = XCDR (tail); | |
8592 | else if (char_encodable_p (c, elt)) | |
8593 | tail = XCDR (tail); | |
8594 | else if (CONSP (XCDR (tail))) | |
8595 | { | |
8596 | XSETCAR (tail, XCAR (XCDR (tail))); | |
8597 | XSETCDR (tail, XCDR (XCDR (tail))); | |
8598 | } | |
8599 | else | |
8600 | { | |
8601 | XSETCAR (tail, Qnil); | |
8602 | tail = XCDR (tail); | |
8603 | } | |
8604 | } | |
8605 | if (charset_map_loaded) | |
8606 | { | |
d311d28c | 8607 | ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg; |
05e6f5dc | 8608 | |
df7492f9 | 8609 | if (STRINGP (start)) |
8f924df7 | 8610 | pbeg = SDATA (start); |
df7492f9 KH |
8611 | else |
8612 | pbeg = BYTE_POS_ADDR (start_byte); | |
8613 | p = pbeg + p_offset; | |
8614 | pend = pbeg + pend_offset; | |
8615 | } | |
0e727afa | 8616 | char_table_set (work_table, c, Qt); |
df7492f9 | 8617 | } |
ec6d2bb8 | 8618 | } |
fb88bf2d | 8619 | |
988b3759 | 8620 | safe_codings = list2 (Qraw_text, Qno_conversion); |
df7492f9 KH |
8621 | for (tail = coding_attrs_list; CONSP (tail); tail = XCDR (tail)) |
8622 | if (! NILP (XCAR (tail))) | |
8623 | safe_codings = Fcons (CODING_ATTR_BASE_NAME (XCAR (tail)), safe_codings); | |
ec6d2bb8 | 8624 | |
05e6f5dc KH |
8625 | return safe_codings; |
8626 | } | |
4956c225 | 8627 | |
d46c5b12 | 8628 | |
8f924df7 KH |
8629 | DEFUN ("unencodable-char-position", Funencodable_char_position, |
8630 | Sunencodable_char_position, 3, 5, 0, | |
8631 | doc: /* | |
8632 | Return position of first un-encodable character in a region. | |
d4a1d553 | 8633 | START and END specify the region and CODING-SYSTEM specifies the |
8f924df7 | 8634 | encoding to check. Return nil if CODING-SYSTEM does encode the region. |
d46c5b12 | 8635 | |
8f924df7 KH |
8636 | If optional 4th argument COUNT is non-nil, it specifies at most how |
8637 | many un-encodable characters to search. In this case, the value is a | |
8638 | list of positions. | |
d46c5b12 | 8639 | |
8f924df7 KH |
8640 | If optional 5th argument STRING is non-nil, it is a string to search |
8641 | for un-encodable characters. In that case, START and END are indexes | |
8642 | to the string. */) | |
5842a27b | 8643 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object count, Lisp_Object string) |
8f924df7 | 8644 | { |
d311d28c | 8645 | EMACS_INT n; |
8f924df7 | 8646 | struct coding_system coding; |
7d64c6ad | 8647 | Lisp_Object attrs, charset_list, translation_table; |
8f924df7 | 8648 | Lisp_Object positions; |
d311d28c | 8649 | ptrdiff_t from, to; |
8f924df7 | 8650 | const unsigned char *p, *stop, *pend; |
f10fe38f | 8651 | bool ascii_compatible; |
fb88bf2d | 8652 | |
8f924df7 KH |
8653 | setup_coding_system (Fcheck_coding_system (coding_system), &coding); |
8654 | attrs = CODING_ID_ATTRS (coding.id); | |
8655 | if (EQ (CODING_ATTR_TYPE (attrs), Qraw_text)) | |
8656 | return Qnil; | |
8657 | ascii_compatible = ! NILP (CODING_ATTR_ASCII_COMPAT (attrs)); | |
8658 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
2170c8f0 | 8659 | translation_table = get_translation_table (attrs, 1, NULL); |
fb88bf2d | 8660 | |
8f924df7 KH |
8661 | if (NILP (string)) |
8662 | { | |
8663 | validate_region (&start, &end); | |
8664 | from = XINT (start); | |
8665 | to = XINT (end); | |
4b4deea2 | 8666 | if (NILP (BVAR (current_buffer, enable_multibyte_characters)) |
8f924df7 KH |
8667 | || (ascii_compatible |
8668 | && (to - from) == (CHAR_TO_BYTE (to) - (CHAR_TO_BYTE (from))))) | |
8669 | return Qnil; | |
8670 | p = CHAR_POS_ADDR (from); | |
8671 | pend = CHAR_POS_ADDR (to); | |
8672 | if (from < GPT && to >= GPT) | |
8673 | stop = GPT_ADDR; | |
8674 | else | |
8675 | stop = pend; | |
8676 | } | |
8677 | else | |
8678 | { | |
8679 | CHECK_STRING (string); | |
8680 | CHECK_NATNUM (start); | |
8681 | CHECK_NATNUM (end); | |
d311d28c PE |
8682 | if (! (XINT (start) <= XINT (end) && XINT (end) <= SCHARS (string))) |
8683 | args_out_of_range_3 (string, start, end); | |
8f924df7 KH |
8684 | from = XINT (start); |
8685 | to = XINT (end); | |
8f924df7 KH |
8686 | if (! STRING_MULTIBYTE (string)) |
8687 | return Qnil; | |
8688 | p = SDATA (string) + string_char_to_byte (string, from); | |
8689 | stop = pend = SDATA (string) + string_char_to_byte (string, to); | |
8690 | if (ascii_compatible && (to - from) == (pend - p)) | |
8691 | return Qnil; | |
8692 | } | |
f2558efd | 8693 | |
8f924df7 KH |
8694 | if (NILP (count)) |
8695 | n = 1; | |
8696 | else | |
b73bfc1c | 8697 | { |
8f924df7 KH |
8698 | CHECK_NATNUM (count); |
8699 | n = XINT (count); | |
b73bfc1c KH |
8700 | } |
8701 | ||
8f924df7 | 8702 | positions = Qnil; |
3633e3aa | 8703 | charset_map_loaded = 0; |
8f924df7 | 8704 | while (1) |
d46c5b12 | 8705 | { |
8f924df7 | 8706 | int c; |
ec6d2bb8 | 8707 | |
8f924df7 KH |
8708 | if (ascii_compatible) |
8709 | while (p < stop && ASCII_BYTE_P (*p)) | |
8710 | p++, from++; | |
8711 | if (p >= stop) | |
0e79d667 | 8712 | { |
8f924df7 KH |
8713 | if (p >= pend) |
8714 | break; | |
8715 | stop = pend; | |
8716 | p = GAP_END_ADDR; | |
0e79d667 | 8717 | } |
ec6d2bb8 | 8718 | |
8f924df7 KH |
8719 | c = STRING_CHAR_ADVANCE (p); |
8720 | if (! (ASCII_CHAR_P (c) && ascii_compatible) | |
7d64c6ad KH |
8721 | && ! char_charset (translate_char (translation_table, c), |
8722 | charset_list, NULL)) | |
ec6d2bb8 | 8723 | { |
8f924df7 KH |
8724 | positions = Fcons (make_number (from), positions); |
8725 | n--; | |
8726 | if (n == 0) | |
8727 | break; | |
ec6d2bb8 KH |
8728 | } |
8729 | ||
8f924df7 | 8730 | from++; |
3633e3aa KH |
8731 | if (charset_map_loaded && NILP (string)) |
8732 | { | |
8733 | p = CHAR_POS_ADDR (from); | |
8734 | pend = CHAR_POS_ADDR (to); | |
8735 | if (from < GPT && to >= GPT) | |
8736 | stop = GPT_ADDR; | |
8737 | else | |
8738 | stop = pend; | |
8739 | charset_map_loaded = 0; | |
8740 | } | |
8f924df7 | 8741 | } |
d46c5b12 | 8742 | |
8f924df7 KH |
8743 | return (NILP (count) ? Fcar (positions) : Fnreverse (positions)); |
8744 | } | |
d46c5b12 | 8745 | |
d46c5b12 | 8746 | |
df7492f9 KH |
8747 | DEFUN ("check-coding-systems-region", Fcheck_coding_systems_region, |
8748 | Scheck_coding_systems_region, 3, 3, 0, | |
8749 | doc: /* Check if the region is encodable by coding systems. | |
d46c5b12 | 8750 | |
df7492f9 KH |
8751 | START and END are buffer positions specifying the region. |
8752 | CODING-SYSTEM-LIST is a list of coding systems to check. | |
d46c5b12 | 8753 | |
df7492f9 | 8754 | The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where |
d4a1d553 | 8755 | CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the |
df7492f9 KH |
8756 | whole region, POS0, POS1, ... are buffer positions where non-encodable |
8757 | characters are found. | |
93dec019 | 8758 | |
df7492f9 KH |
8759 | If all coding systems in CODING-SYSTEM-LIST can encode the region, the |
8760 | value is nil. | |
93dec019 | 8761 | |
df7492f9 KH |
8762 | START may be a string. In that case, check if the string is |
8763 | encodable, and the value contains indices to the string instead of | |
5704f39a KH |
8764 | buffer positions. END is ignored. |
8765 | ||
4c1958f4 | 8766 | If the current buffer (or START if it is a string) is unibyte, the value |
5704f39a | 8767 | is nil. */) |
5842a27b | 8768 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system_list) |
05e6f5dc | 8769 | { |
df7492f9 | 8770 | Lisp_Object list; |
d311d28c PE |
8771 | ptrdiff_t start_byte, end_byte; |
8772 | ptrdiff_t pos; | |
7c78e542 | 8773 | const unsigned char *p, *pbeg, *pend; |
df7492f9 | 8774 | int c; |
7d64c6ad | 8775 | Lisp_Object tail, elt, attrs; |
70ad9fc4 | 8776 | |
05e6f5dc KH |
8777 | if (STRINGP (start)) |
8778 | { | |
df7492f9 | 8779 | if (!STRING_MULTIBYTE (start) |
4c1958f4 | 8780 | || SCHARS (start) == SBYTES (start)) |
df7492f9 KH |
8781 | return Qnil; |
8782 | start_byte = 0; | |
8f924df7 | 8783 | end_byte = SBYTES (start); |
df7492f9 | 8784 | pos = 0; |
d46c5b12 | 8785 | } |
05e6f5dc | 8786 | else |
b73bfc1c | 8787 | { |
b7826503 PJ |
8788 | CHECK_NUMBER_COERCE_MARKER (start); |
8789 | CHECK_NUMBER_COERCE_MARKER (end); | |
05e6f5dc KH |
8790 | if (XINT (start) < BEG || XINT (end) > Z || XINT (start) > XINT (end)) |
8791 | args_out_of_range (start, end); | |
4b4deea2 | 8792 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) |
df7492f9 KH |
8793 | return Qnil; |
8794 | start_byte = CHAR_TO_BYTE (XINT (start)); | |
8795 | end_byte = CHAR_TO_BYTE (XINT (end)); | |
8796 | if (XINT (end) - XINT (start) == end_byte - start_byte) | |
5704f39a | 8797 | return Qnil; |
df7492f9 | 8798 | |
e1c23804 | 8799 | if (XINT (start) < GPT && XINT (end) > GPT) |
b73bfc1c | 8800 | { |
e1c23804 DL |
8801 | if ((GPT - XINT (start)) < (XINT (end) - GPT)) |
8802 | move_gap_both (XINT (start), start_byte); | |
df7492f9 | 8803 | else |
e1c23804 | 8804 | move_gap_both (XINT (end), end_byte); |
b73bfc1c | 8805 | } |
e1c23804 | 8806 | pos = XINT (start); |
b73bfc1c | 8807 | } |
7553d0e1 | 8808 | |
df7492f9 KH |
8809 | list = Qnil; |
8810 | for (tail = coding_system_list; CONSP (tail); tail = XCDR (tail)) | |
12410ef1 | 8811 | { |
df7492f9 | 8812 | elt = XCAR (tail); |
7d64c6ad | 8813 | attrs = AREF (CODING_SYSTEM_SPEC (elt), 0); |
2170c8f0 KH |
8814 | ASET (attrs, coding_attr_trans_tbl, |
8815 | get_translation_table (attrs, 1, NULL)); | |
7d64c6ad | 8816 | list = Fcons (Fcons (elt, Fcons (attrs, Qnil)), list); |
12410ef1 KH |
8817 | } |
8818 | ||
df7492f9 | 8819 | if (STRINGP (start)) |
8f924df7 | 8820 | p = pbeg = SDATA (start); |
72d1a715 | 8821 | else |
df7492f9 KH |
8822 | p = pbeg = BYTE_POS_ADDR (start_byte); |
8823 | pend = p + (end_byte - start_byte); | |
4ed46869 | 8824 | |
df7492f9 KH |
8825 | while (p < pend && ASCII_BYTE_P (*p)) p++, pos++; |
8826 | while (p < pend && ASCII_BYTE_P (*(pend - 1))) pend--; | |
ec6d2bb8 | 8827 | |
df7492f9 | 8828 | while (p < pend) |
d46c5b12 | 8829 | { |
df7492f9 KH |
8830 | if (ASCII_BYTE_P (*p)) |
8831 | p++; | |
e133c8fa | 8832 | else |
05e6f5dc | 8833 | { |
df7492f9 KH |
8834 | c = STRING_CHAR_ADVANCE (p); |
8835 | ||
8836 | charset_map_loaded = 0; | |
8837 | for (tail = list; CONSP (tail); tail = XCDR (tail)) | |
8838 | { | |
8839 | elt = XCDR (XCAR (tail)); | |
8840 | if (! char_encodable_p (c, XCAR (elt))) | |
8841 | XSETCDR (elt, Fcons (make_number (pos), XCDR (elt))); | |
8842 | } | |
8843 | if (charset_map_loaded) | |
8844 | { | |
d311d28c | 8845 | ptrdiff_t p_offset = p - pbeg, pend_offset = pend - pbeg; |
df7492f9 KH |
8846 | |
8847 | if (STRINGP (start)) | |
8f924df7 | 8848 | pbeg = SDATA (start); |
df7492f9 KH |
8849 | else |
8850 | pbeg = BYTE_POS_ADDR (start_byte); | |
8851 | p = pbeg + p_offset; | |
8852 | pend = pbeg + pend_offset; | |
8853 | } | |
05e6f5dc | 8854 | } |
df7492f9 | 8855 | pos++; |
d46c5b12 | 8856 | } |
4ed46869 | 8857 | |
df7492f9 KH |
8858 | tail = list; |
8859 | list = Qnil; | |
8860 | for (; CONSP (tail); tail = XCDR (tail)) | |
ec6d2bb8 | 8861 | { |
df7492f9 KH |
8862 | elt = XCAR (tail); |
8863 | if (CONSP (XCDR (XCDR (elt)))) | |
8864 | list = Fcons (Fcons (XCAR (elt), Fnreverse (XCDR (XCDR (elt)))), | |
8865 | list); | |
ec6d2bb8 | 8866 | } |
2b4f9037 | 8867 | |
df7492f9 | 8868 | return list; |
d46c5b12 KH |
8869 | } |
8870 | ||
3fd9494b | 8871 | |
74ab6df5 | 8872 | static Lisp_Object |
cf84bb53 JB |
8873 | code_convert_region (Lisp_Object start, Lisp_Object end, |
8874 | Lisp_Object coding_system, Lisp_Object dst_object, | |
f10fe38f | 8875 | bool encodep, bool norecord) |
4ed46869 | 8876 | { |
3a73fa5d | 8877 | struct coding_system coding; |
d311d28c | 8878 | ptrdiff_t from, from_byte, to, to_byte; |
df7492f9 | 8879 | Lisp_Object src_object; |
4ed46869 | 8880 | |
b7826503 PJ |
8881 | CHECK_NUMBER_COERCE_MARKER (start); |
8882 | CHECK_NUMBER_COERCE_MARKER (end); | |
df7492f9 KH |
8883 | if (NILP (coding_system)) |
8884 | coding_system = Qno_conversion; | |
8885 | else | |
8886 | CHECK_CODING_SYSTEM (coding_system); | |
8887 | src_object = Fcurrent_buffer (); | |
8888 | if (NILP (dst_object)) | |
8889 | dst_object = src_object; | |
8890 | else if (! EQ (dst_object, Qt)) | |
8891 | CHECK_BUFFER (dst_object); | |
3a73fa5d | 8892 | |
d46c5b12 KH |
8893 | validate_region (&start, &end); |
8894 | from = XFASTINT (start); | |
df7492f9 | 8895 | from_byte = CHAR_TO_BYTE (from); |
d46c5b12 | 8896 | to = XFASTINT (end); |
df7492f9 | 8897 | to_byte = CHAR_TO_BYTE (to); |
764ca8da | 8898 | |
df7492f9 KH |
8899 | setup_coding_system (coding_system, &coding); |
8900 | coding.mode |= CODING_MODE_LAST_BLOCK; | |
ec6d2bb8 | 8901 | |
df7492f9 KH |
8902 | if (encodep) |
8903 | encode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8904 | dst_object); | |
8905 | else | |
8906 | decode_coding_object (&coding, src_object, from, from_byte, to, to_byte, | |
8907 | dst_object); | |
8908 | if (! norecord) | |
8909 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
ec6d2bb8 | 8910 | |
df7492f9 KH |
8911 | return (BUFFERP (dst_object) |
8912 | ? make_number (coding.produced_char) | |
8913 | : coding.dst_object); | |
4031e2bf | 8914 | } |
78108bcd | 8915 | |
4ed46869 | 8916 | |
4031e2bf | 8917 | DEFUN ("decode-coding-region", Fdecode_coding_region, Sdecode_coding_region, |
df7492f9 | 8918 | 3, 4, "r\nzCoding system: ", |
48b0f3ae | 8919 | doc: /* Decode the current region from the specified coding system. |
df7492f9 KH |
8920 | When called from a program, takes four arguments: |
8921 | START, END, CODING-SYSTEM, and DESTINATION. | |
8922 | START and END are buffer positions. | |
8844fa83 | 8923 | |
df7492f9 | 8924 | Optional 4th arguments DESTINATION specifies where the decoded text goes. |
2354b80b | 8925 | If nil, the region between START and END is replaced by the decoded text. |
1560f91a EZ |
8926 | If buffer, the decoded text is inserted in that buffer after point (point |
8927 | does not move). | |
446dcd75 | 8928 | In those cases, the length of the decoded text is returned. |
319a3947 | 8929 | If DESTINATION is t, the decoded text is returned. |
8844fa83 | 8930 | |
48b0f3ae PJ |
8931 | This function sets `last-coding-system-used' to the precise coding system |
8932 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8933 | not fully specified.) */) |
5842a27b | 8934 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
4031e2bf | 8935 | { |
df7492f9 | 8936 | return code_convert_region (start, end, coding_system, destination, 0, 0); |
3a73fa5d | 8937 | } |
8844fa83 | 8938 | |
3a73fa5d | 8939 | DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region, |
df7492f9 KH |
8940 | 3, 4, "r\nzCoding system: ", |
8941 | doc: /* Encode the current region by specified coding system. | |
d4a1d553 JB |
8942 | When called from a program, takes four arguments: |
8943 | START, END, CODING-SYSTEM and DESTINATION. | |
8944 | START and END are buffer positions. | |
d46c5b12 | 8945 | |
df7492f9 KH |
8946 | Optional 4th arguments DESTINATION specifies where the encoded text goes. |
8947 | If nil, the region between START and END is replace by the encoded text. | |
1560f91a EZ |
8948 | If buffer, the encoded text is inserted in that buffer after point (point |
8949 | does not move). | |
446dcd75 | 8950 | In those cases, the length of the encoded text is returned. |
319a3947 | 8951 | If DESTINATION is t, the encoded text is returned. |
2391eaa4 | 8952 | |
48b0f3ae PJ |
8953 | This function sets `last-coding-system-used' to the precise coding system |
8954 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
319a3947 | 8955 | not fully specified.) */) |
5842a27b | 8956 | (Lisp_Object start, Lisp_Object end, Lisp_Object coding_system, Lisp_Object destination) |
3a73fa5d | 8957 | { |
df7492f9 | 8958 | return code_convert_region (start, end, coding_system, destination, 1, 0); |
b73bfc1c KH |
8959 | } |
8960 | ||
8961 | Lisp_Object | |
6f704c76 | 8962 | code_convert_string (Lisp_Object string, Lisp_Object coding_system, |
f10fe38f PE |
8963 | Lisp_Object dst_object, bool encodep, bool nocopy, |
8964 | bool norecord) | |
b73bfc1c | 8965 | { |
4031e2bf | 8966 | struct coding_system coding; |
d311d28c | 8967 | ptrdiff_t chars, bytes; |
ec6d2bb8 | 8968 | |
b7826503 | 8969 | CHECK_STRING (string); |
d46c5b12 | 8970 | if (NILP (coding_system)) |
4956c225 | 8971 | { |
df7492f9 KH |
8972 | if (! norecord) |
8973 | Vlast_coding_system_used = Qno_conversion; | |
8974 | if (NILP (dst_object)) | |
8975 | return (nocopy ? Fcopy_sequence (string) : string); | |
4956c225 | 8976 | } |
b73bfc1c | 8977 | |
df7492f9 KH |
8978 | if (NILP (coding_system)) |
8979 | coding_system = Qno_conversion; | |
8980 | else | |
8981 | CHECK_CODING_SYSTEM (coding_system); | |
8982 | if (NILP (dst_object)) | |
8983 | dst_object = Qt; | |
8984 | else if (! EQ (dst_object, Qt)) | |
8985 | CHECK_BUFFER (dst_object); | |
73be902c | 8986 | |
df7492f9 | 8987 | setup_coding_system (coding_system, &coding); |
d46c5b12 | 8988 | coding.mode |= CODING_MODE_LAST_BLOCK; |
8f924df7 KH |
8989 | chars = SCHARS (string); |
8990 | bytes = SBYTES (string); | |
df7492f9 KH |
8991 | if (encodep) |
8992 | encode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
8993 | else | |
8994 | decode_coding_object (&coding, string, 0, 0, chars, bytes, dst_object); | |
8995 | if (! norecord) | |
8996 | Vlast_coding_system_used = CODING_ID_NAME (coding.id); | |
73be902c | 8997 | |
df7492f9 KH |
8998 | return (BUFFERP (dst_object) |
8999 | ? make_number (coding.produced_char) | |
9000 | : coding.dst_object); | |
4ed46869 | 9001 | } |
73be902c | 9002 | |
b73bfc1c | 9003 | |
ecec61c1 | 9004 | /* Encode or decode STRING according to CODING_SYSTEM. |
ec6d2bb8 | 9005 | Do not set Vlast_coding_system_used. |
4ed46869 | 9006 | |
ec6d2bb8 KH |
9007 | This function is called only from macros DECODE_FILE and |
9008 | ENCODE_FILE, thus we ignore character composition. */ | |
4ed46869 | 9009 | |
ecec61c1 | 9010 | Lisp_Object |
cf84bb53 | 9011 | code_convert_string_norecord (Lisp_Object string, Lisp_Object coding_system, |
f10fe38f | 9012 | bool encodep) |
4ed46869 | 9013 | { |
0be8721c | 9014 | return code_convert_string (string, coding_system, Qt, encodep, 0, 1); |
4ed46869 KH |
9015 | } |
9016 | ||
4ed46869 | 9017 | |
a7ca3326 | 9018 | DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string, |
df7492f9 KH |
9019 | 2, 4, 0, |
9020 | doc: /* Decode STRING which is encoded in CODING-SYSTEM, and return the result. | |
9021 | ||
9022 | Optional third arg NOCOPY non-nil means it is OK to return STRING itself | |
9023 | if the decoding operation is trivial. | |
ecec61c1 | 9024 | |
d4a1d553 | 9025 | Optional fourth arg BUFFER non-nil means that the decoded text is |
1560f91a EZ |
9026 | inserted in that buffer after point (point does not move). In this |
9027 | case, the return value is the length of the decoded text. | |
ecec61c1 | 9028 | |
df7492f9 KH |
9029 | This function sets `last-coding-system-used' to the precise coding system |
9030 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
d4a1d553 | 9031 | not fully specified.) */) |
5842a27b | 9032 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9033 | { |
df7492f9 KH |
9034 | return code_convert_string (string, coding_system, buffer, |
9035 | 0, ! NILP (nocopy), 0); | |
4ed46869 KH |
9036 | } |
9037 | ||
df7492f9 KH |
9038 | DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string, |
9039 | 2, 4, 0, | |
9040 | doc: /* Encode STRING to CODING-SYSTEM, and return the result. | |
9041 | ||
9042 | Optional third arg NOCOPY non-nil means it is OK to return STRING | |
9043 | itself if the encoding operation is trivial. | |
9044 | ||
d4a1d553 | 9045 | Optional fourth arg BUFFER non-nil means that the encoded text is |
1560f91a EZ |
9046 | inserted in that buffer after point (point does not move). In this |
9047 | case, the return value is the length of the encoded text. | |
df7492f9 KH |
9048 | |
9049 | This function sets `last-coding-system-used' to the precise coding system | |
9050 | used (which may be different from CODING-SYSTEM if CODING-SYSTEM is | |
9051 | not fully specified.) */) | |
5842a27b | 9052 | (Lisp_Object string, Lisp_Object coding_system, Lisp_Object nocopy, Lisp_Object buffer) |
4ed46869 | 9053 | { |
df7492f9 | 9054 | return code_convert_string (string, coding_system, buffer, |
4550efdf | 9055 | 1, ! NILP (nocopy), 0); |
4ed46869 | 9056 | } |
df7492f9 | 9057 | |
3a73fa5d | 9058 | \f |
4ed46869 | 9059 | DEFUN ("decode-sjis-char", Fdecode_sjis_char, Sdecode_sjis_char, 1, 1, 0, |
48b0f3ae PJ |
9060 | doc: /* Decode a Japanese character which has CODE in shift_jis encoding. |
9061 | Return the corresponding character. */) | |
5842a27b | 9062 | (Lisp_Object code) |
4ed46869 | 9063 | { |
df7492f9 KH |
9064 | Lisp_Object spec, attrs, val; |
9065 | struct charset *charset_roman, *charset_kanji, *charset_kana, *charset; | |
5fdb398c PE |
9066 | EMACS_INT ch; |
9067 | int c; | |
4ed46869 | 9068 | |
df7492f9 | 9069 | CHECK_NATNUM (code); |
5fdb398c | 9070 | ch = XFASTINT (code); |
df7492f9 KH |
9071 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); |
9072 | attrs = AREF (spec, 0); | |
4ed46869 | 9073 | |
5fdb398c | 9074 | if (ASCII_BYTE_P (ch) |
df7492f9 KH |
9075 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
9076 | return code; | |
4ed46869 | 9077 | |
df7492f9 KH |
9078 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9079 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
004068e4 KH |
9080 | charset_kana = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); |
9081 | charset_kanji = CHARSET_FROM_ID (XINT (XCAR (val))); | |
fa42c37f | 9082 | |
5fdb398c PE |
9083 | if (ch <= 0x7F) |
9084 | { | |
9085 | c = ch; | |
9086 | charset = charset_roman; | |
9087 | } | |
9088 | else if (ch >= 0xA0 && ch < 0xDF) | |
55ab7be3 | 9089 | { |
5fdb398c | 9090 | c = ch - 0x80; |
df7492f9 | 9091 | charset = charset_kana; |
4ed46869 | 9092 | } |
55ab7be3 | 9093 | else |
4ed46869 | 9094 | { |
5fdb398c PE |
9095 | EMACS_INT c1 = ch >> 8; |
9096 | int c2 = ch & 0xFF; | |
df7492f9 | 9097 | |
2735d060 PE |
9098 | if (c1 < 0x81 || (c1 > 0x9F && c1 < 0xE0) || c1 > 0xEF |
9099 | || c2 < 0x40 || c2 == 0x7F || c2 > 0xFC) | |
c2982e87 | 9100 | error ("Invalid code: %"pI"d", ch); |
5fdb398c | 9101 | c = ch; |
df7492f9 KH |
9102 | SJIS_TO_JIS (c); |
9103 | charset = charset_kanji; | |
4ed46869 | 9104 | } |
df7492f9 KH |
9105 | c = DECODE_CHAR (charset, c); |
9106 | if (c < 0) | |
c2982e87 | 9107 | error ("Invalid code: %"pI"d", ch); |
df7492f9 | 9108 | return make_number (c); |
93dec019 | 9109 | } |
4ed46869 | 9110 | |
48b0f3ae | 9111 | |
4ed46869 | 9112 | DEFUN ("encode-sjis-char", Fencode_sjis_char, Sencode_sjis_char, 1, 1, 0, |
8acf0c0e | 9113 | doc: /* Encode a Japanese character CH to shift_jis encoding. |
48b0f3ae | 9114 | Return the corresponding code in SJIS. */) |
5842a27b | 9115 | (Lisp_Object ch) |
4ed46869 | 9116 | { |
df7492f9 KH |
9117 | Lisp_Object spec, attrs, charset_list; |
9118 | int c; | |
9119 | struct charset *charset; | |
9120 | unsigned code; | |
48b0f3ae | 9121 | |
df7492f9 KH |
9122 | CHECK_CHARACTER (ch); |
9123 | c = XFASTINT (ch); | |
9124 | CHECK_CODING_SYSTEM_GET_SPEC (Vsjis_coding_system, spec); | |
9125 | attrs = AREF (spec, 0); | |
9126 | ||
9127 | if (ASCII_CHAR_P (c) | |
9128 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9129 | return ch; | |
9130 | ||
9131 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9132 | charset = char_charset (c, charset_list, &code); | |
9133 | if (code == CHARSET_INVALID_CODE (charset)) | |
e6c3da20 | 9134 | error ("Can't encode by shift_jis encoding: %c", c); |
df7492f9 KH |
9135 | JIS_TO_SJIS (code); |
9136 | ||
9137 | return make_number (code); | |
4ed46869 KH |
9138 | } |
9139 | ||
9140 | DEFUN ("decode-big5-char", Fdecode_big5_char, Sdecode_big5_char, 1, 1, 0, | |
48b0f3ae PJ |
9141 | doc: /* Decode a Big5 character which has CODE in BIG5 coding system. |
9142 | Return the corresponding character. */) | |
5842a27b | 9143 | (Lisp_Object code) |
d46c5b12 | 9144 | { |
df7492f9 KH |
9145 | Lisp_Object spec, attrs, val; |
9146 | struct charset *charset_roman, *charset_big5, *charset; | |
5fdb398c | 9147 | EMACS_INT ch; |
df7492f9 | 9148 | int c; |
6289dd10 | 9149 | |
df7492f9 | 9150 | CHECK_NATNUM (code); |
5fdb398c | 9151 | ch = XFASTINT (code); |
df7492f9 KH |
9152 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); |
9153 | attrs = AREF (spec, 0); | |
4ed46869 | 9154 | |
5fdb398c | 9155 | if (ASCII_BYTE_P (ch) |
df7492f9 KH |
9156 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) |
9157 | return code; | |
6289dd10 | 9158 | |
df7492f9 KH |
9159 | val = CODING_ATTR_CHARSET_LIST (attrs); |
9160 | charset_roman = CHARSET_FROM_ID (XINT (XCAR (val))), val = XCDR (val); | |
9161 | charset_big5 = CHARSET_FROM_ID (XINT (XCAR (val))); | |
c210f766 | 9162 | |
5fdb398c PE |
9163 | if (ch <= 0x7F) |
9164 | { | |
9165 | c = ch; | |
9166 | charset = charset_roman; | |
9167 | } | |
c28a9453 KH |
9168 | else |
9169 | { | |
5fdb398c PE |
9170 | EMACS_INT b1 = ch >> 8; |
9171 | int b2 = ch & 0x7F; | |
df7492f9 KH |
9172 | if (b1 < 0xA1 || b1 > 0xFE |
9173 | || b2 < 0x40 || (b2 > 0x7E && b2 < 0xA1) || b2 > 0xFE) | |
c2982e87 | 9174 | error ("Invalid code: %"pI"d", ch); |
5fdb398c | 9175 | c = ch; |
df7492f9 | 9176 | charset = charset_big5; |
c28a9453 | 9177 | } |
5fdb398c | 9178 | c = DECODE_CHAR (charset, c); |
df7492f9 | 9179 | if (c < 0) |
c2982e87 | 9180 | error ("Invalid code: %"pI"d", ch); |
df7492f9 | 9181 | return make_number (c); |
d46c5b12 | 9182 | } |
6289dd10 | 9183 | |
4ed46869 | 9184 | DEFUN ("encode-big5-char", Fencode_big5_char, Sencode_big5_char, 1, 1, 0, |
8acf0c0e | 9185 | doc: /* Encode the Big5 character CH to BIG5 coding system. |
48b0f3ae | 9186 | Return the corresponding character code in Big5. */) |
5842a27b | 9187 | (Lisp_Object ch) |
4ed46869 | 9188 | { |
df7492f9 KH |
9189 | Lisp_Object spec, attrs, charset_list; |
9190 | struct charset *charset; | |
9191 | int c; | |
9192 | unsigned code; | |
9193 | ||
9194 | CHECK_CHARACTER (ch); | |
9195 | c = XFASTINT (ch); | |
9196 | CHECK_CODING_SYSTEM_GET_SPEC (Vbig5_coding_system, spec); | |
9197 | attrs = AREF (spec, 0); | |
9198 | if (ASCII_CHAR_P (c) | |
9199 | && ! NILP (CODING_ATTR_ASCII_COMPAT (attrs))) | |
9200 | return ch; | |
9201 | ||
9202 | charset_list = CODING_ATTR_CHARSET_LIST (attrs); | |
9203 | charset = char_charset (c, charset_list, &code); | |
9204 | if (code == CHARSET_INVALID_CODE (charset)) | |
e6c3da20 | 9205 | error ("Can't encode by Big5 encoding: %c", c); |
df7492f9 KH |
9206 | |
9207 | return make_number (code); | |
4ed46869 | 9208 | } |
48b0f3ae | 9209 | |
3a73fa5d | 9210 | \f |
002fdb44 | 9211 | DEFUN ("set-terminal-coding-system-internal", Fset_terminal_coding_system_internal, |
68bba4e4 | 9212 | Sset_terminal_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9213 | doc: /* Internal use only. */) |
5842a27b | 9214 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9215 | { |
b18fad6d KH |
9216 | struct terminal *term = get_terminal (terminal, 1); |
9217 | struct coding_system *terminal_coding = TERMINAL_TERMINAL_CODING (term); | |
b7826503 | 9218 | CHECK_SYMBOL (coding_system); |
b8299c66 | 9219 | setup_coding_system (Fcheck_coding_system (coding_system), terminal_coding); |
70c22245 | 9220 | /* We had better not send unsafe characters to terminal. */ |
c73bd236 | 9221 | terminal_coding->mode |= CODING_MODE_SAFE_ENCODING; |
ad1746f5 | 9222 | /* Character composition should be disabled. */ |
c73bd236 | 9223 | terminal_coding->common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b8299c66 KL |
9224 | terminal_coding->src_multibyte = 1; |
9225 | terminal_coding->dst_multibyte = 0; | |
3f22b86f PE |
9226 | tset_charset_list |
9227 | (term, (terminal_coding->common_flags & CODING_REQUIRE_ENCODING_MASK | |
9228 | ? coding_charset_list (terminal_coding) | |
9229 | : Fcons (make_number (charset_ascii), Qnil))); | |
4ed46869 KH |
9230 | return Qnil; |
9231 | } | |
9232 | ||
c4825358 KH |
9233 | DEFUN ("set-safe-terminal-coding-system-internal", |
9234 | Fset_safe_terminal_coding_system_internal, | |
48b0f3ae | 9235 | Sset_safe_terminal_coding_system_internal, 1, 1, 0, |
ddb67bdc | 9236 | doc: /* Internal use only. */) |
5842a27b | 9237 | (Lisp_Object coding_system) |
d46c5b12 | 9238 | { |
b7826503 | 9239 | CHECK_SYMBOL (coding_system); |
c4825358 KH |
9240 | setup_coding_system (Fcheck_coding_system (coding_system), |
9241 | &safe_terminal_coding); | |
ad1746f5 | 9242 | /* Character composition should be disabled. */ |
df7492f9 | 9243 | safe_terminal_coding.common_flags &= ~CODING_ANNOTATE_COMPOSITION_MASK; |
b73bfc1c KH |
9244 | safe_terminal_coding.src_multibyte = 1; |
9245 | safe_terminal_coding.dst_multibyte = 0; | |
c4825358 KH |
9246 | return Qnil; |
9247 | } | |
4ed46869 | 9248 | |
002fdb44 | 9249 | DEFUN ("terminal-coding-system", Fterminal_coding_system, |
68bba4e4 | 9250 | Sterminal_coding_system, 0, 1, 0, |
6ed8eeff | 9251 | doc: /* Return coding system specified for terminal output on the given terminal. |
708e05dc | 9252 | TERMINAL may be a terminal object, a frame, or nil for the selected |
6ed8eeff | 9253 | frame's terminal device. */) |
5842a27b | 9254 | (Lisp_Object terminal) |
4ed46869 | 9255 | { |
985773c9 MB |
9256 | struct coding_system *terminal_coding |
9257 | = TERMINAL_TERMINAL_CODING (get_terminal (terminal, 1)); | |
9258 | Lisp_Object coding_system = CODING_ID_NAME (terminal_coding->id); | |
ae6f73fa | 9259 | |
6d5eb5b0 | 9260 | /* For backward compatibility, return nil if it is `undecided'. */ |
f75c90a9 | 9261 | return (! EQ (coding_system, Qundecided) ? coding_system : Qnil); |
4ed46869 KH |
9262 | } |
9263 | ||
002fdb44 | 9264 | DEFUN ("set-keyboard-coding-system-internal", Fset_keyboard_coding_system_internal, |
68bba4e4 | 9265 | Sset_keyboard_coding_system_internal, 1, 2, 0, |
48b0f3ae | 9266 | doc: /* Internal use only. */) |
5842a27b | 9267 | (Lisp_Object coding_system, Lisp_Object terminal) |
4ed46869 | 9268 | { |
6ed8eeff | 9269 | struct terminal *t = get_terminal (terminal, 1); |
b7826503 | 9270 | CHECK_SYMBOL (coding_system); |
624bda09 KH |
9271 | if (NILP (coding_system)) |
9272 | coding_system = Qno_conversion; | |
9273 | else | |
9274 | Fcheck_coding_system (coding_system); | |
9275 | setup_coding_system (coding_system, TERMINAL_KEYBOARD_CODING (t)); | |
ad1746f5 | 9276 | /* Character composition should be disabled. */ |
c73bd236 MB |
9277 | TERMINAL_KEYBOARD_CODING (t)->common_flags |
9278 | &= ~CODING_ANNOTATE_COMPOSITION_MASK; | |
4ed46869 KH |
9279 | return Qnil; |
9280 | } | |
9281 | ||
9282 | DEFUN ("keyboard-coding-system", | |
985773c9 | 9283 | Fkeyboard_coding_system, Skeyboard_coding_system, 0, 1, 0, |
48b0f3ae | 9284 | doc: /* Return coding system specified for decoding keyboard input. */) |
5842a27b | 9285 | (Lisp_Object terminal) |
4ed46869 | 9286 | { |
985773c9 MB |
9287 | return CODING_ID_NAME (TERMINAL_KEYBOARD_CODING |
9288 | (get_terminal (terminal, 1))->id); | |
4ed46869 KH |
9289 | } |
9290 | ||
4ed46869 | 9291 | \f |
a7ca3326 | 9292 | DEFUN ("find-operation-coding-system", Ffind_operation_coding_system, |
a5d301df | 9293 | Sfind_operation_coding_system, 1, MANY, 0, |
48b0f3ae PJ |
9294 | doc: /* Choose a coding system for an operation based on the target name. |
9295 | The value names a pair of coding systems: (DECODING-SYSTEM . ENCODING-SYSTEM). | |
9296 | DECODING-SYSTEM is the coding system to use for decoding | |
9297 | \(in case OPERATION does decoding), and ENCODING-SYSTEM is the coding system | |
9298 | for encoding (in case OPERATION does encoding). | |
05e6f5dc | 9299 | |
48b0f3ae PJ |
9300 | The first argument OPERATION specifies an I/O primitive: |
9301 | For file I/O, `insert-file-contents' or `write-region'. | |
9302 | For process I/O, `call-process', `call-process-region', or `start-process'. | |
9303 | For network I/O, `open-network-stream'. | |
05e6f5dc | 9304 | |
48b0f3ae PJ |
9305 | The remaining arguments should be the same arguments that were passed |
9306 | to the primitive. Depending on which primitive, one of those arguments | |
9307 | is selected as the TARGET. For example, if OPERATION does file I/O, | |
9308 | whichever argument specifies the file name is TARGET. | |
05e6f5dc | 9309 | |
48b0f3ae | 9310 | TARGET has a meaning which depends on OPERATION: |
b883cdb2 | 9311 | For file I/O, TARGET is a file name (except for the special case below). |
48b0f3ae | 9312 | For process I/O, TARGET is a process name. |
d4a1d553 | 9313 | For network I/O, TARGET is a service name or a port number. |
05e6f5dc | 9314 | |
d4a1d553 | 9315 | This function looks up what is specified for TARGET in |
48b0f3ae PJ |
9316 | `file-coding-system-alist', `process-coding-system-alist', |
9317 | or `network-coding-system-alist' depending on OPERATION. | |
9318 | They may specify a coding system, a cons of coding systems, | |
9319 | or a function symbol to call. | |
9320 | In the last case, we call the function with one argument, | |
9321 | which is a list of all the arguments given to this function. | |
1011c487 MB |
9322 | If the function can't decide a coding system, it can return |
9323 | `undecided' so that the normal code-detection is performed. | |
48b0f3ae | 9324 | |
b883cdb2 MB |
9325 | If OPERATION is `insert-file-contents', the argument corresponding to |
9326 | TARGET may be a cons (FILENAME . BUFFER). In that case, FILENAME is a | |
9327 | file name to look up, and BUFFER is a buffer that contains the file's | |
9328 | contents (not yet decoded). If `file-coding-system-alist' specifies a | |
9329 | function to call for FILENAME, that function should examine the | |
9330 | contents of BUFFER instead of reading the file. | |
9331 | ||
d918f936 | 9332 | usage: (find-operation-coding-system OPERATION ARGUMENTS...) */) |
f66c7cf8 | 9333 | (ptrdiff_t nargs, Lisp_Object *args) |
6b89e3aa | 9334 | { |
4ed46869 KH |
9335 | Lisp_Object operation, target_idx, target, val; |
9336 | register Lisp_Object chain; | |
177c0ea7 | 9337 | |
4ed46869 KH |
9338 | if (nargs < 2) |
9339 | error ("Too few arguments"); | |
9340 | operation = args[0]; | |
9341 | if (!SYMBOLP (operation) | |
d311d28c | 9342 | || (target_idx = Fget (operation, Qtarget_idx), !NATNUMP (target_idx))) |
3ed051d4 | 9343 | error ("Invalid first argument"); |
7b09a37a | 9344 | if (nargs <= 1 + XFASTINT (target_idx)) |
94dcfacf | 9345 | error ("Too few arguments for operation `%s'", |
8f924df7 | 9346 | SDATA (SYMBOL_NAME (operation))); |
c5101a77 | 9347 | target = args[XFASTINT (target_idx) + 1]; |
4ed46869 | 9348 | if (!(STRINGP (target) |
091a0ff0 KH |
9349 | || (EQ (operation, Qinsert_file_contents) && CONSP (target) |
9350 | && STRINGP (XCAR (target)) && BUFFERP (XCDR (target))) | |
4ed46869 | 9351 | || (EQ (operation, Qopen_network_stream) && INTEGERP (target)))) |
94dcfacf EZ |
9352 | error ("Invalid argument %"pI"d of operation `%s'", |
9353 | XFASTINT (target_idx) + 1, SDATA (SYMBOL_NAME (operation))); | |
091a0ff0 KH |
9354 | if (CONSP (target)) |
9355 | target = XCAR (target); | |
4ed46869 | 9356 | |
2e34157c RS |
9357 | chain = ((EQ (operation, Qinsert_file_contents) |
9358 | || EQ (operation, Qwrite_region)) | |
02ba4723 | 9359 | ? Vfile_coding_system_alist |
2e34157c | 9360 | : (EQ (operation, Qopen_network_stream) |
02ba4723 KH |
9361 | ? Vnetwork_coding_system_alist |
9362 | : Vprocess_coding_system_alist)); | |
4ed46869 KH |
9363 | if (NILP (chain)) |
9364 | return Qnil; | |
9365 | ||
03699b14 | 9366 | for (; CONSP (chain); chain = XCDR (chain)) |
6b89e3aa | 9367 | { |
f44d27ce | 9368 | Lisp_Object elt; |
6b89e3aa | 9369 | |
df7492f9 | 9370 | elt = XCAR (chain); |
4ed46869 KH |
9371 | if (CONSP (elt) |
9372 | && ((STRINGP (target) | |
03699b14 KR |
9373 | && STRINGP (XCAR (elt)) |
9374 | && fast_string_match (XCAR (elt), target) >= 0) | |
9375 | || (INTEGERP (target) && EQ (target, XCAR (elt))))) | |
6b89e3aa | 9376 | { |
03699b14 | 9377 | val = XCDR (elt); |
b19fd4c5 KH |
9378 | /* Here, if VAL is both a valid coding system and a valid |
9379 | function symbol, we return VAL as a coding system. */ | |
02ba4723 KH |
9380 | if (CONSP (val)) |
9381 | return val; | |
9382 | if (! SYMBOLP (val)) | |
9383 | return Qnil; | |
9384 | if (! NILP (Fcoding_system_p (val))) | |
9385 | return Fcons (val, val); | |
b19fd4c5 | 9386 | if (! NILP (Ffboundp (val))) |
6b89e3aa | 9387 | { |
e2b97060 MB |
9388 | /* We use call1 rather than safe_call1 |
9389 | so as to get bug reports about functions called here | |
9390 | which don't handle the current interface. */ | |
9391 | val = call1 (val, Flist (nargs, args)); | |
b19fd4c5 KH |
9392 | if (CONSP (val)) |
9393 | return val; | |
9394 | if (SYMBOLP (val) && ! NILP (Fcoding_system_p (val))) | |
9395 | return Fcons (val, val); | |
6b89e3aa | 9396 | } |
02ba4723 | 9397 | return Qnil; |
6b89e3aa KH |
9398 | } |
9399 | } | |
4ed46869 | 9400 | return Qnil; |
6b89e3aa KH |
9401 | } |
9402 | ||
df7492f9 | 9403 | DEFUN ("set-coding-system-priority", Fset_coding_system_priority, |
a3f6ee6d | 9404 | Sset_coding_system_priority, 0, MANY, 0, |
da7db224 | 9405 | doc: /* Assign higher priority to the coding systems given as arguments. |
d4a1d553 | 9406 | If multiple coding systems belong to the same category, |
a3181084 DL |
9407 | all but the first one are ignored. |
9408 | ||
d4a1d553 | 9409 | usage: (set-coding-system-priority &rest coding-systems) */) |
f66c7cf8 | 9410 | (ptrdiff_t nargs, Lisp_Object *args) |
df7492f9 | 9411 | { |
f66c7cf8 | 9412 | ptrdiff_t i, j; |
f10fe38f | 9413 | bool changed[coding_category_max]; |
df7492f9 KH |
9414 | enum coding_category priorities[coding_category_max]; |
9415 | ||
72af86bd | 9416 | memset (changed, 0, sizeof changed); |
6b89e3aa | 9417 | |
df7492f9 | 9418 | for (i = j = 0; i < nargs; i++) |
6b89e3aa | 9419 | { |
df7492f9 KH |
9420 | enum coding_category category; |
9421 | Lisp_Object spec, attrs; | |
6b89e3aa | 9422 | |
df7492f9 KH |
9423 | CHECK_CODING_SYSTEM_GET_SPEC (args[i], spec); |
9424 | attrs = AREF (spec, 0); | |
9425 | category = XINT (CODING_ATTR_CATEGORY (attrs)); | |
9426 | if (changed[category]) | |
9427 | /* Ignore this coding system because a coding system of the | |
9428 | same category already had a higher priority. */ | |
9429 | continue; | |
9430 | changed[category] = 1; | |
9431 | priorities[j++] = category; | |
9432 | if (coding_categories[category].id >= 0 | |
9433 | && ! EQ (args[i], CODING_ID_NAME (coding_categories[category].id))) | |
9434 | setup_coding_system (args[i], &coding_categories[category]); | |
ff563fce | 9435 | Fset (AREF (Vcoding_category_table, category), args[i]); |
df7492f9 | 9436 | } |
6b89e3aa | 9437 | |
df7492f9 KH |
9438 | /* Now we have decided top J priorities. Reflect the order of the |
9439 | original priorities to the remaining priorities. */ | |
6b89e3aa | 9440 | |
df7492f9 | 9441 | for (i = j, j = 0; i < coding_category_max; i++, j++) |
6b89e3aa | 9442 | { |
df7492f9 KH |
9443 | while (j < coding_category_max |
9444 | && changed[coding_priorities[j]]) | |
9445 | j++; | |
9446 | if (j == coding_category_max) | |
1088b922 | 9447 | emacs_abort (); |
df7492f9 KH |
9448 | priorities[i] = coding_priorities[j]; |
9449 | } | |
6b89e3aa | 9450 | |
72af86bd | 9451 | memcpy (coding_priorities, priorities, sizeof priorities); |
177c0ea7 | 9452 | |
ff563fce KH |
9453 | /* Update `coding-category-list'. */ |
9454 | Vcoding_category_list = Qnil; | |
c5101a77 | 9455 | for (i = coding_category_max; i-- > 0; ) |
ff563fce KH |
9456 | Vcoding_category_list |
9457 | = Fcons (AREF (Vcoding_category_table, priorities[i]), | |
9458 | Vcoding_category_list); | |
6b89e3aa | 9459 | |
df7492f9 | 9460 | return Qnil; |
6b89e3aa KH |
9461 | } |
9462 | ||
df7492f9 KH |
9463 | DEFUN ("coding-system-priority-list", Fcoding_system_priority_list, |
9464 | Scoding_system_priority_list, 0, 1, 0, | |
da7db224 | 9465 | doc: /* Return a list of coding systems ordered by their priorities. |
b811c52b KH |
9466 | The list contains a subset of coding systems; i.e. coding systems |
9467 | assigned to each coding category (see `coding-category-list'). | |
9468 | ||
da7db224 | 9469 | HIGHESTP non-nil means just return the highest priority one. */) |
5842a27b | 9470 | (Lisp_Object highestp) |
d46c5b12 KH |
9471 | { |
9472 | int i; | |
df7492f9 | 9473 | Lisp_Object val; |
6b89e3aa | 9474 | |
df7492f9 | 9475 | for (i = 0, val = Qnil; i < coding_category_max; i++) |
d46c5b12 | 9476 | { |
df7492f9 KH |
9477 | enum coding_category category = coding_priorities[i]; |
9478 | int id = coding_categories[category].id; | |
9479 | Lisp_Object attrs; | |
068a9dbd | 9480 | |
df7492f9 KH |
9481 | if (id < 0) |
9482 | continue; | |
9483 | attrs = CODING_ID_ATTRS (id); | |
9484 | if (! NILP (highestp)) | |
9485 | return CODING_ATTR_BASE_NAME (attrs); | |
9486 | val = Fcons (CODING_ATTR_BASE_NAME (attrs), val); | |
9487 | } | |
9488 | return Fnreverse (val); | |
9489 | } | |
068a9dbd | 9490 | |
91433552 | 9491 | static const char *const suffixes[] = { "-unix", "-dos", "-mac" }; |
068a9dbd KH |
9492 | |
9493 | static Lisp_Object | |
971de7fb | 9494 | make_subsidiaries (Lisp_Object base) |
068a9dbd | 9495 | { |
df7492f9 | 9496 | Lisp_Object subsidiaries; |
1bfdaf10 | 9497 | ptrdiff_t base_name_len = SBYTES (SYMBOL_NAME (base)); |
38182d90 | 9498 | char *buf = alloca (base_name_len + 6); |
df7492f9 | 9499 | int i; |
068a9dbd | 9500 | |
72af86bd | 9501 | memcpy (buf, SDATA (SYMBOL_NAME (base)), base_name_len); |
df7492f9 KH |
9502 | subsidiaries = Fmake_vector (make_number (3), Qnil); |
9503 | for (i = 0; i < 3; i++) | |
068a9dbd | 9504 | { |
1bfdaf10 | 9505 | strcpy (buf + base_name_len, suffixes[i]); |
df7492f9 | 9506 | ASET (subsidiaries, i, intern (buf)); |
068a9dbd | 9507 | } |
df7492f9 | 9508 | return subsidiaries; |
068a9dbd KH |
9509 | } |
9510 | ||
9511 | ||
df7492f9 KH |
9512 | DEFUN ("define-coding-system-internal", Fdefine_coding_system_internal, |
9513 | Sdefine_coding_system_internal, coding_arg_max, MANY, 0, | |
1fcd6c8b DL |
9514 | doc: /* For internal use only. |
9515 | usage: (define-coding-system-internal ...) */) | |
f66c7cf8 | 9516 | (ptrdiff_t nargs, Lisp_Object *args) |
068a9dbd | 9517 | { |
df7492f9 KH |
9518 | Lisp_Object name; |
9519 | Lisp_Object spec_vec; /* [ ATTRS ALIASE EOL_TYPE ] */ | |
9520 | Lisp_Object attrs; /* Vector of attributes. */ | |
9521 | Lisp_Object eol_type; | |
9522 | Lisp_Object aliases; | |
9523 | Lisp_Object coding_type, charset_list, safe_charsets; | |
9524 | enum coding_category category; | |
9525 | Lisp_Object tail, val; | |
9526 | int max_charset_id = 0; | |
9527 | int i; | |
068a9dbd | 9528 | |
df7492f9 KH |
9529 | if (nargs < coding_arg_max) |
9530 | goto short_args; | |
068a9dbd | 9531 | |
df7492f9 | 9532 | attrs = Fmake_vector (make_number (coding_attr_last_index), Qnil); |
068a9dbd | 9533 | |
df7492f9 KH |
9534 | name = args[coding_arg_name]; |
9535 | CHECK_SYMBOL (name); | |
4939150c | 9536 | ASET (attrs, coding_attr_base_name, name); |
068a9dbd | 9537 | |
df7492f9 KH |
9538 | val = args[coding_arg_mnemonic]; |
9539 | if (! STRINGP (val)) | |
9540 | CHECK_CHARACTER (val); | |
4939150c | 9541 | ASET (attrs, coding_attr_mnemonic, val); |
068a9dbd | 9542 | |
df7492f9 KH |
9543 | coding_type = args[coding_arg_coding_type]; |
9544 | CHECK_SYMBOL (coding_type); | |
4939150c | 9545 | ASET (attrs, coding_attr_type, coding_type); |
068a9dbd | 9546 | |
df7492f9 KH |
9547 | charset_list = args[coding_arg_charset_list]; |
9548 | if (SYMBOLP (charset_list)) | |
9549 | { | |
9550 | if (EQ (charset_list, Qiso_2022)) | |
9551 | { | |
9552 | if (! EQ (coding_type, Qiso_2022)) | |
9553 | error ("Invalid charset-list"); | |
9554 | charset_list = Viso_2022_charset_list; | |
9555 | } | |
9556 | else if (EQ (charset_list, Qemacs_mule)) | |
9557 | { | |
9558 | if (! EQ (coding_type, Qemacs_mule)) | |
9559 | error ("Invalid charset-list"); | |
9560 | charset_list = Vemacs_mule_charset_list; | |
9561 | } | |
9562 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) | |
d311d28c PE |
9563 | { |
9564 | if (! RANGED_INTEGERP (0, XCAR (tail), INT_MAX - 1)) | |
9565 | error ("Invalid charset-list"); | |
9566 | if (max_charset_id < XFASTINT (XCAR (tail))) | |
9567 | max_charset_id = XFASTINT (XCAR (tail)); | |
9568 | } | |
df7492f9 | 9569 | } |
068a9dbd KH |
9570 | else |
9571 | { | |
df7492f9 | 9572 | charset_list = Fcopy_sequence (charset_list); |
985773c9 | 9573 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
068a9dbd | 9574 | { |
df7492f9 KH |
9575 | struct charset *charset; |
9576 | ||
985773c9 | 9577 | val = XCAR (tail); |
df7492f9 KH |
9578 | CHECK_CHARSET_GET_CHARSET (val, charset); |
9579 | if (EQ (coding_type, Qiso_2022) | |
9580 | ? CHARSET_ISO_FINAL (charset) < 0 | |
9581 | : EQ (coding_type, Qemacs_mule) | |
9582 | ? CHARSET_EMACS_MULE_ID (charset) < 0 | |
9583 | : 0) | |
9584 | error ("Can't handle charset `%s'", | |
8f924df7 | 9585 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 | 9586 | |
8f924df7 | 9587 | XSETCAR (tail, make_number (charset->id)); |
df7492f9 KH |
9588 | if (max_charset_id < charset->id) |
9589 | max_charset_id = charset->id; | |
068a9dbd KH |
9590 | } |
9591 | } | |
4939150c | 9592 | ASET (attrs, coding_attr_charset_list, charset_list); |
068a9dbd | 9593 | |
1b3b981b AS |
9594 | safe_charsets = make_uninit_string (max_charset_id + 1); |
9595 | memset (SDATA (safe_charsets), 255, max_charset_id + 1); | |
df7492f9 | 9596 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
8f924df7 | 9597 | SSET (safe_charsets, XFASTINT (XCAR (tail)), 0); |
4939150c | 9598 | ASET (attrs, coding_attr_safe_charsets, safe_charsets); |
068a9dbd | 9599 | |
4939150c | 9600 | ASET (attrs, coding_attr_ascii_compat, args[coding_arg_ascii_compatible_p]); |
3a73fa5d | 9601 | |
df7492f9 | 9602 | val = args[coding_arg_decode_translation_table]; |
a6f87d34 | 9603 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9604 | CHECK_SYMBOL (val); |
4939150c | 9605 | ASET (attrs, coding_attr_decode_tbl, val); |
3a73fa5d | 9606 | |
df7492f9 | 9607 | val = args[coding_arg_encode_translation_table]; |
a6f87d34 | 9608 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) |
7d64c6ad | 9609 | CHECK_SYMBOL (val); |
4939150c | 9610 | ASET (attrs, coding_attr_encode_tbl, val); |
d46c5b12 | 9611 | |
df7492f9 KH |
9612 | val = args[coding_arg_post_read_conversion]; |
9613 | CHECK_SYMBOL (val); | |
4939150c | 9614 | ASET (attrs, coding_attr_post_read, val); |
d46c5b12 | 9615 | |
df7492f9 KH |
9616 | val = args[coding_arg_pre_write_conversion]; |
9617 | CHECK_SYMBOL (val); | |
4939150c | 9618 | ASET (attrs, coding_attr_pre_write, val); |
3a73fa5d | 9619 | |
df7492f9 KH |
9620 | val = args[coding_arg_default_char]; |
9621 | if (NILP (val)) | |
4939150c | 9622 | ASET (attrs, coding_attr_default_char, make_number (' ')); |
df7492f9 KH |
9623 | else |
9624 | { | |
8f924df7 | 9625 | CHECK_CHARACTER (val); |
4939150c | 9626 | ASET (attrs, coding_attr_default_char, val); |
df7492f9 | 9627 | } |
4031e2bf | 9628 | |
8f924df7 | 9629 | val = args[coding_arg_for_unibyte]; |
4939150c | 9630 | ASET (attrs, coding_attr_for_unibyte, NILP (val) ? Qnil : Qt); |
3a73fa5d | 9631 | |
df7492f9 KH |
9632 | val = args[coding_arg_plist]; |
9633 | CHECK_LIST (val); | |
4939150c | 9634 | ASET (attrs, coding_attr_plist, val); |
3a73fa5d | 9635 | |
df7492f9 KH |
9636 | if (EQ (coding_type, Qcharset)) |
9637 | { | |
c7c66a95 KH |
9638 | /* Generate a lisp vector of 256 elements. Each element is nil, |
9639 | integer, or a list of charset IDs. | |
3a73fa5d | 9640 | |
c7c66a95 KH |
9641 | If Nth element is nil, the byte code N is invalid in this |
9642 | coding system. | |
4ed46869 | 9643 | |
c7c66a95 KH |
9644 | If Nth element is a number NUM, N is the first byte of a |
9645 | charset whose ID is NUM. | |
4ed46869 | 9646 | |
c7c66a95 KH |
9647 | If Nth element is a list of charset IDs, N is the first byte |
9648 | of one of them. The list is sorted by dimensions of the | |
ad1746f5 | 9649 | charsets. A charset of smaller dimension comes first. */ |
df7492f9 | 9650 | val = Fmake_vector (make_number (256), Qnil); |
4ed46869 | 9651 | |
5c99c2e6 | 9652 | for (tail = charset_list; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9653 | { |
c7c66a95 KH |
9654 | struct charset *charset = CHARSET_FROM_ID (XFASTINT (XCAR (tail))); |
9655 | int dim = CHARSET_DIMENSION (charset); | |
9656 | int idx = (dim - 1) * 4; | |
4ed46869 | 9657 | |
5c99c2e6 | 9658 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9659 | ASET (attrs, coding_attr_ascii_compat, Qt); |
4031e2bf | 9660 | |
15d143f7 KH |
9661 | for (i = charset->code_space[idx]; |
9662 | i <= charset->code_space[idx + 1]; i++) | |
9663 | { | |
c7c66a95 KH |
9664 | Lisp_Object tmp, tmp2; |
9665 | int dim2; | |
ec6d2bb8 | 9666 | |
c7c66a95 KH |
9667 | tmp = AREF (val, i); |
9668 | if (NILP (tmp)) | |
9669 | tmp = XCAR (tail); | |
9670 | else if (NUMBERP (tmp)) | |
9671 | { | |
9672 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (tmp))); | |
9673 | if (dim < dim2) | |
c7c66a95 | 9674 | tmp = Fcons (XCAR (tail), Fcons (tmp, Qnil)); |
f9d71dcd KH |
9675 | else |
9676 | tmp = Fcons (tmp, Fcons (XCAR (tail), Qnil)); | |
c7c66a95 | 9677 | } |
15d143f7 | 9678 | else |
c7c66a95 KH |
9679 | { |
9680 | for (tmp2 = tmp; CONSP (tmp2); tmp2 = XCDR (tmp2)) | |
9681 | { | |
9682 | dim2 = CHARSET_DIMENSION (CHARSET_FROM_ID (XFASTINT (XCAR (tmp2)))); | |
9683 | if (dim < dim2) | |
9684 | break; | |
9685 | } | |
9686 | if (NILP (tmp2)) | |
9687 | tmp = nconc2 (tmp, Fcons (XCAR (tail), Qnil)); | |
9688 | else | |
9689 | { | |
9690 | XSETCDR (tmp2, Fcons (XCAR (tmp2), XCDR (tmp2))); | |
9691 | XSETCAR (tmp2, XCAR (tail)); | |
9692 | } | |
9693 | } | |
9694 | ASET (val, i, tmp); | |
15d143f7 | 9695 | } |
df7492f9 KH |
9696 | } |
9697 | ASET (attrs, coding_attr_charset_valids, val); | |
9698 | category = coding_category_charset; | |
9699 | } | |
9700 | else if (EQ (coding_type, Qccl)) | |
9701 | { | |
9702 | Lisp_Object valids; | |
ecec61c1 | 9703 | |
df7492f9 KH |
9704 | if (nargs < coding_arg_ccl_max) |
9705 | goto short_args; | |
ecec61c1 | 9706 | |
df7492f9 KH |
9707 | val = args[coding_arg_ccl_decoder]; |
9708 | CHECK_CCL_PROGRAM (val); | |
9709 | if (VECTORP (val)) | |
9710 | val = Fcopy_sequence (val); | |
9711 | ASET (attrs, coding_attr_ccl_decoder, val); | |
ecec61c1 | 9712 | |
df7492f9 KH |
9713 | val = args[coding_arg_ccl_encoder]; |
9714 | CHECK_CCL_PROGRAM (val); | |
9715 | if (VECTORP (val)) | |
9716 | val = Fcopy_sequence (val); | |
9717 | ASET (attrs, coding_attr_ccl_encoder, val); | |
ecec61c1 | 9718 | |
df7492f9 KH |
9719 | val = args[coding_arg_ccl_valids]; |
9720 | valids = Fmake_string (make_number (256), make_number (0)); | |
7d7bbefd | 9721 | for (tail = val; CONSP (tail); tail = XCDR (tail)) |
df7492f9 | 9722 | { |
8dcbea82 | 9723 | int from, to; |
ecec61c1 | 9724 | |
34348bd4 | 9725 | val = XCAR (tail); |
df7492f9 | 9726 | if (INTEGERP (val)) |
8dcbea82 | 9727 | { |
d311d28c | 9728 | if (! (0 <= XINT (val) && XINT (val) <= 255)) |
8dcbea82 | 9729 | args_out_of_range_3 (val, make_number (0), make_number (255)); |
d311d28c | 9730 | from = to = XINT (val); |
8dcbea82 | 9731 | } |
df7492f9 KH |
9732 | else |
9733 | { | |
df7492f9 | 9734 | CHECK_CONS (val); |
8f924df7 | 9735 | CHECK_NATNUM_CAR (val); |
d311d28c PE |
9736 | CHECK_NUMBER_CDR (val); |
9737 | if (XINT (XCAR (val)) > 255) | |
8dcbea82 KH |
9738 | args_out_of_range_3 (XCAR (val), |
9739 | make_number (0), make_number (255)); | |
d311d28c PE |
9740 | from = XINT (XCAR (val)); |
9741 | if (! (from <= XINT (XCDR (val)) && XINT (XCDR (val)) <= 255)) | |
8dcbea82 KH |
9742 | args_out_of_range_3 (XCDR (val), |
9743 | XCAR (val), make_number (255)); | |
d311d28c | 9744 | to = XINT (XCDR (val)); |
df7492f9 | 9745 | } |
8dcbea82 | 9746 | for (i = from; i <= to; i++) |
8f924df7 | 9747 | SSET (valids, i, 1); |
df7492f9 KH |
9748 | } |
9749 | ASET (attrs, coding_attr_ccl_valids, valids); | |
4ed46869 | 9750 | |
df7492f9 | 9751 | category = coding_category_ccl; |
55ab7be3 | 9752 | } |
df7492f9 | 9753 | else if (EQ (coding_type, Qutf_16)) |
55ab7be3 | 9754 | { |
df7492f9 | 9755 | Lisp_Object bom, endian; |
4ed46869 | 9756 | |
4939150c | 9757 | ASET (attrs, coding_attr_ascii_compat, Qnil); |
4ed46869 | 9758 | |
df7492f9 KH |
9759 | if (nargs < coding_arg_utf16_max) |
9760 | goto short_args; | |
4ed46869 | 9761 | |
df7492f9 KH |
9762 | bom = args[coding_arg_utf16_bom]; |
9763 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9764 | { | |
9765 | CHECK_CONS (bom); | |
8f924df7 KH |
9766 | val = XCAR (bom); |
9767 | CHECK_CODING_SYSTEM (val); | |
9768 | val = XCDR (bom); | |
9769 | CHECK_CODING_SYSTEM (val); | |
df7492f9 | 9770 | } |
a470d443 | 9771 | ASET (attrs, coding_attr_utf_bom, bom); |
df7492f9 KH |
9772 | |
9773 | endian = args[coding_arg_utf16_endian]; | |
b49a1807 KH |
9774 | CHECK_SYMBOL (endian); |
9775 | if (NILP (endian)) | |
9776 | endian = Qbig; | |
9777 | else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle)) | |
8f924df7 | 9778 | error ("Invalid endian: %s", SDATA (SYMBOL_NAME (endian))); |
df7492f9 KH |
9779 | ASET (attrs, coding_attr_utf_16_endian, endian); |
9780 | ||
9781 | category = (CONSP (bom) | |
9782 | ? coding_category_utf_16_auto | |
9783 | : NILP (bom) | |
b49a1807 | 9784 | ? (EQ (endian, Qbig) |
df7492f9 KH |
9785 | ? coding_category_utf_16_be_nosig |
9786 | : coding_category_utf_16_le_nosig) | |
b49a1807 | 9787 | : (EQ (endian, Qbig) |
df7492f9 KH |
9788 | ? coding_category_utf_16_be |
9789 | : coding_category_utf_16_le)); | |
9790 | } | |
9791 | else if (EQ (coding_type, Qiso_2022)) | |
9792 | { | |
9793 | Lisp_Object initial, reg_usage, request, flags; | |
1397dc18 | 9794 | |
df7492f9 KH |
9795 | if (nargs < coding_arg_iso2022_max) |
9796 | goto short_args; | |
9797 | ||
9798 | initial = Fcopy_sequence (args[coding_arg_iso2022_initial]); | |
9799 | CHECK_VECTOR (initial); | |
9800 | for (i = 0; i < 4; i++) | |
9801 | { | |
9802 | val = Faref (initial, make_number (i)); | |
9803 | if (! NILP (val)) | |
9804 | { | |
584948ac KH |
9805 | struct charset *charset; |
9806 | ||
9807 | CHECK_CHARSET_GET_CHARSET (val, charset); | |
9808 | ASET (initial, i, make_number (CHARSET_ID (charset))); | |
9809 | if (i == 0 && CHARSET_ASCII_COMPATIBLE_P (charset)) | |
4939150c | 9810 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9811 | } |
9812 | else | |
9813 | ASET (initial, i, make_number (-1)); | |
9814 | } | |
9815 | ||
9816 | reg_usage = args[coding_arg_iso2022_reg_usage]; | |
9817 | CHECK_CONS (reg_usage); | |
8f924df7 KH |
9818 | CHECK_NUMBER_CAR (reg_usage); |
9819 | CHECK_NUMBER_CDR (reg_usage); | |
df7492f9 KH |
9820 | |
9821 | request = Fcopy_sequence (args[coding_arg_iso2022_request]); | |
7d7bbefd | 9822 | for (tail = request; CONSP (tail); tail = XCDR (tail)) |
1397dc18 | 9823 | { |
df7492f9 | 9824 | int id; |
2735d060 | 9825 | Lisp_Object tmp1; |
df7492f9 | 9826 | |
34348bd4 | 9827 | val = XCAR (tail); |
df7492f9 | 9828 | CHECK_CONS (val); |
2735d060 PE |
9829 | tmp1 = XCAR (val); |
9830 | CHECK_CHARSET_GET_ID (tmp1, id); | |
8f924df7 | 9831 | CHECK_NATNUM_CDR (val); |
df7492f9 | 9832 | if (XINT (XCDR (val)) >= 4) |
c2982e87 | 9833 | error ("Invalid graphic register number: %"pI"d", XINT (XCDR (val))); |
8f924df7 | 9834 | XSETCAR (val, make_number (id)); |
1397dc18 | 9835 | } |
4ed46869 | 9836 | |
df7492f9 KH |
9837 | flags = args[coding_arg_iso2022_flags]; |
9838 | CHECK_NATNUM (flags); | |
d311d28c | 9839 | i = XINT (flags) & INT_MAX; |
df7492f9 | 9840 | if (EQ (args[coding_arg_charset_list], Qiso_2022)) |
d311d28c PE |
9841 | i |= CODING_ISO_FLAG_FULL_SUPPORT; |
9842 | flags = make_number (i); | |
df7492f9 KH |
9843 | |
9844 | ASET (attrs, coding_attr_iso_initial, initial); | |
9845 | ASET (attrs, coding_attr_iso_usage, reg_usage); | |
9846 | ASET (attrs, coding_attr_iso_request, request); | |
9847 | ASET (attrs, coding_attr_iso_flags, flags); | |
9848 | setup_iso_safe_charsets (attrs); | |
9849 | ||
9850 | if (i & CODING_ISO_FLAG_SEVEN_BITS) | |
9851 | category = ((i & (CODING_ISO_FLAG_LOCKING_SHIFT | |
9852 | | CODING_ISO_FLAG_SINGLE_SHIFT)) | |
9853 | ? coding_category_iso_7_else | |
9854 | : EQ (args[coding_arg_charset_list], Qiso_2022) | |
9855 | ? coding_category_iso_7 | |
9856 | : coding_category_iso_7_tight); | |
9857 | else | |
9858 | { | |
9859 | int id = XINT (AREF (initial, 1)); | |
9860 | ||
c6fb6e98 | 9861 | category = (((i & CODING_ISO_FLAG_LOCKING_SHIFT) |
df7492f9 KH |
9862 | || EQ (args[coding_arg_charset_list], Qiso_2022) |
9863 | || id < 0) | |
9864 | ? coding_category_iso_8_else | |
9865 | : (CHARSET_DIMENSION (CHARSET_FROM_ID (id)) == 1) | |
9866 | ? coding_category_iso_8_1 | |
9867 | : coding_category_iso_8_2); | |
9868 | } | |
0ce7886f KH |
9869 | if (category != coding_category_iso_8_1 |
9870 | && category != coding_category_iso_8_2) | |
4939150c | 9871 | ASET (attrs, coding_attr_ascii_compat, Qnil); |
df7492f9 KH |
9872 | } |
9873 | else if (EQ (coding_type, Qemacs_mule)) | |
c28a9453 | 9874 | { |
df7492f9 KH |
9875 | if (EQ (args[coding_arg_charset_list], Qemacs_mule)) |
9876 | ASET (attrs, coding_attr_emacs_mule_full, Qt); | |
4939150c | 9877 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 | 9878 | category = coding_category_emacs_mule; |
c28a9453 | 9879 | } |
df7492f9 | 9880 | else if (EQ (coding_type, Qshift_jis)) |
c28a9453 | 9881 | { |
df7492f9 KH |
9882 | |
9883 | struct charset *charset; | |
9884 | ||
7d64c6ad | 9885 | if (XINT (Flength (charset_list)) != 3 |
6e07c25f | 9886 | && XINT (Flength (charset_list)) != 4) |
7d64c6ad | 9887 | error ("There should be three or four charsets"); |
df7492f9 KH |
9888 | |
9889 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9890 | if (CHARSET_DIMENSION (charset) != 1) | |
9891 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9892 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac | 9893 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9894 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9895 | |
9896 | charset_list = XCDR (charset_list); | |
9897 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9898 | if (CHARSET_DIMENSION (charset) != 1) | |
9899 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9900 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
df7492f9 KH |
9901 | |
9902 | charset_list = XCDR (charset_list); | |
9903 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9904 | if (CHARSET_DIMENSION (charset) != 2) | |
7d64c6ad KH |
9905 | error ("Dimension of charset %s is not two", |
9906 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9907 | ||
9908 | charset_list = XCDR (charset_list); | |
2b917a06 KH |
9909 | if (! NILP (charset_list)) |
9910 | { | |
9911 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9912 | if (CHARSET_DIMENSION (charset) != 2) | |
9913 | error ("Dimension of charset %s is not two", | |
9914 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); | |
9915 | } | |
df7492f9 KH |
9916 | |
9917 | category = coding_category_sjis; | |
9918 | Vsjis_coding_system = name; | |
c28a9453 | 9919 | } |
df7492f9 KH |
9920 | else if (EQ (coding_type, Qbig5)) |
9921 | { | |
9922 | struct charset *charset; | |
4ed46869 | 9923 | |
df7492f9 KH |
9924 | if (XINT (Flength (charset_list)) != 2) |
9925 | error ("There should be just two charsets"); | |
9926 | ||
9927 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9928 | if (CHARSET_DIMENSION (charset) != 1) | |
9929 | error ("Dimension of charset %s is not one", | |
8f924df7 | 9930 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
584948ac | 9931 | if (CHARSET_ASCII_COMPATIBLE_P (charset)) |
4939150c | 9932 | ASET (attrs, coding_attr_ascii_compat, Qt); |
df7492f9 KH |
9933 | |
9934 | charset_list = XCDR (charset_list); | |
9935 | charset = CHARSET_FROM_ID (XINT (XCAR (charset_list))); | |
9936 | if (CHARSET_DIMENSION (charset) != 2) | |
9937 | error ("Dimension of charset %s is not two", | |
8f924df7 | 9938 | SDATA (SYMBOL_NAME (CHARSET_NAME (charset)))); |
4ed46869 | 9939 | |
df7492f9 KH |
9940 | category = coding_category_big5; |
9941 | Vbig5_coding_system = name; | |
9942 | } | |
9943 | else if (EQ (coding_type, Qraw_text)) | |
c28a9453 | 9944 | { |
584948ac | 9945 | category = coding_category_raw_text; |
4939150c | 9946 | ASET (attrs, coding_attr_ascii_compat, Qt); |
c28a9453 | 9947 | } |
df7492f9 | 9948 | else if (EQ (coding_type, Qutf_8)) |
4ed46869 | 9949 | { |
a470d443 KH |
9950 | Lisp_Object bom; |
9951 | ||
a470d443 KH |
9952 | if (nargs < coding_arg_utf8_max) |
9953 | goto short_args; | |
9954 | ||
9955 | bom = args[coding_arg_utf8_bom]; | |
9956 | if (! NILP (bom) && ! EQ (bom, Qt)) | |
9957 | { | |
9958 | CHECK_CONS (bom); | |
9959 | val = XCAR (bom); | |
9960 | CHECK_CODING_SYSTEM (val); | |
9961 | val = XCDR (bom); | |
9962 | CHECK_CODING_SYSTEM (val); | |
9963 | } | |
9964 | ASET (attrs, coding_attr_utf_bom, bom); | |
0e5317f7 | 9965 | if (NILP (bom)) |
4939150c | 9966 | ASET (attrs, coding_attr_ascii_compat, Qt); |
a470d443 KH |
9967 | |
9968 | category = (CONSP (bom) ? coding_category_utf_8_auto | |
9969 | : NILP (bom) ? coding_category_utf_8_nosig | |
9970 | : coding_category_utf_8_sig); | |
4ed46869 | 9971 | } |
df7492f9 KH |
9972 | else if (EQ (coding_type, Qundecided)) |
9973 | category = coding_category_undecided; | |
4ed46869 | 9974 | else |
df7492f9 | 9975 | error ("Invalid coding system type: %s", |
8f924df7 | 9976 | SDATA (SYMBOL_NAME (coding_type))); |
4ed46869 | 9977 | |
4939150c PE |
9978 | ASET (attrs, coding_attr_category, make_number (category)); |
9979 | ASET (attrs, coding_attr_plist, | |
9980 | Fcons (QCcategory, | |
9981 | Fcons (AREF (Vcoding_category_table, category), | |
9982 | CODING_ATTR_PLIST (attrs)))); | |
9983 | ASET (attrs, coding_attr_plist, | |
9984 | Fcons (QCascii_compatible_p, | |
9985 | Fcons (CODING_ATTR_ASCII_COMPAT (attrs), | |
9986 | CODING_ATTR_PLIST (attrs)))); | |
c4825358 | 9987 | |
df7492f9 KH |
9988 | eol_type = args[coding_arg_eol_type]; |
9989 | if (! NILP (eol_type) | |
9990 | && ! EQ (eol_type, Qunix) | |
9991 | && ! EQ (eol_type, Qdos) | |
9992 | && ! EQ (eol_type, Qmac)) | |
9993 | error ("Invalid eol-type"); | |
4ed46869 | 9994 | |
df7492f9 | 9995 | aliases = Fcons (name, Qnil); |
4ed46869 | 9996 | |
df7492f9 KH |
9997 | if (NILP (eol_type)) |
9998 | { | |
9999 | eol_type = make_subsidiaries (name); | |
10000 | for (i = 0; i < 3; i++) | |
1397dc18 | 10001 | { |
df7492f9 KH |
10002 | Lisp_Object this_spec, this_name, this_aliases, this_eol_type; |
10003 | ||
10004 | this_name = AREF (eol_type, i); | |
10005 | this_aliases = Fcons (this_name, Qnil); | |
10006 | this_eol_type = (i == 0 ? Qunix : i == 1 ? Qdos : Qmac); | |
10007 | this_spec = Fmake_vector (make_number (3), attrs); | |
10008 | ASET (this_spec, 1, this_aliases); | |
10009 | ASET (this_spec, 2, this_eol_type); | |
10010 | Fputhash (this_name, this_spec, Vcoding_system_hash_table); | |
10011 | Vcoding_system_list = Fcons (this_name, Vcoding_system_list); | |
583f71ca KH |
10012 | val = Fassoc (Fsymbol_name (this_name), Vcoding_system_alist); |
10013 | if (NILP (val)) | |
10014 | Vcoding_system_alist | |
10015 | = Fcons (Fcons (Fsymbol_name (this_name), Qnil), | |
10016 | Vcoding_system_alist); | |
1397dc18 | 10017 | } |
d46c5b12 | 10018 | } |
4ed46869 | 10019 | |
df7492f9 KH |
10020 | spec_vec = Fmake_vector (make_number (3), attrs); |
10021 | ASET (spec_vec, 1, aliases); | |
10022 | ASET (spec_vec, 2, eol_type); | |
48b0f3ae | 10023 | |
df7492f9 KH |
10024 | Fputhash (name, spec_vec, Vcoding_system_hash_table); |
10025 | Vcoding_system_list = Fcons (name, Vcoding_system_list); | |
583f71ca KH |
10026 | val = Fassoc (Fsymbol_name (name), Vcoding_system_alist); |
10027 | if (NILP (val)) | |
10028 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (name), Qnil), | |
10029 | Vcoding_system_alist); | |
48b0f3ae | 10030 | |
df7492f9 KH |
10031 | { |
10032 | int id = coding_categories[category].id; | |
48b0f3ae | 10033 | |
df7492f9 KH |
10034 | if (id < 0 || EQ (name, CODING_ID_NAME (id))) |
10035 | setup_coding_system (name, &coding_categories[category]); | |
10036 | } | |
48b0f3ae | 10037 | |
d46c5b12 | 10038 | return Qnil; |
48b0f3ae | 10039 | |
df7492f9 KH |
10040 | short_args: |
10041 | return Fsignal (Qwrong_number_of_arguments, | |
10042 | Fcons (intern ("define-coding-system-internal"), | |
10043 | make_number (nargs))); | |
d46c5b12 | 10044 | } |
4ed46869 | 10045 | |
d6925f38 | 10046 | |
a6f87d34 KH |
10047 | DEFUN ("coding-system-put", Fcoding_system_put, Scoding_system_put, |
10048 | 3, 3, 0, | |
10049 | doc: /* Change value in CODING-SYSTEM's property list PROP to VAL. */) | |
5842a27b | 10050 | (Lisp_Object coding_system, Lisp_Object prop, Lisp_Object val) |
a6f87d34 | 10051 | { |
3dbe7859 | 10052 | Lisp_Object spec, attrs; |
a6f87d34 KH |
10053 | |
10054 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10055 | attrs = AREF (spec, 0); | |
10056 | if (EQ (prop, QCmnemonic)) | |
10057 | { | |
10058 | if (! STRINGP (val)) | |
10059 | CHECK_CHARACTER (val); | |
4939150c | 10060 | ASET (attrs, coding_attr_mnemonic, val); |
a6f87d34 | 10061 | } |
2133e2d1 | 10062 | else if (EQ (prop, QCdefault_char)) |
a6f87d34 KH |
10063 | { |
10064 | if (NILP (val)) | |
10065 | val = make_number (' '); | |
10066 | else | |
10067 | CHECK_CHARACTER (val); | |
4939150c | 10068 | ASET (attrs, coding_attr_default_char, val); |
a6f87d34 KH |
10069 | } |
10070 | else if (EQ (prop, QCdecode_translation_table)) | |
10071 | { | |
10072 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10073 | CHECK_SYMBOL (val); | |
4939150c | 10074 | ASET (attrs, coding_attr_decode_tbl, val); |
a6f87d34 KH |
10075 | } |
10076 | else if (EQ (prop, QCencode_translation_table)) | |
10077 | { | |
10078 | if (! CHAR_TABLE_P (val) && ! CONSP (val)) | |
10079 | CHECK_SYMBOL (val); | |
4939150c | 10080 | ASET (attrs, coding_attr_encode_tbl, val); |
a6f87d34 KH |
10081 | } |
10082 | else if (EQ (prop, QCpost_read_conversion)) | |
10083 | { | |
10084 | CHECK_SYMBOL (val); | |
4939150c | 10085 | ASET (attrs, coding_attr_post_read, val); |
a6f87d34 KH |
10086 | } |
10087 | else if (EQ (prop, QCpre_write_conversion)) | |
10088 | { | |
10089 | CHECK_SYMBOL (val); | |
4939150c | 10090 | ASET (attrs, coding_attr_pre_write, val); |
a6f87d34 | 10091 | } |
35befdaa KH |
10092 | else if (EQ (prop, QCascii_compatible_p)) |
10093 | { | |
4939150c | 10094 | ASET (attrs, coding_attr_ascii_compat, val); |
35befdaa | 10095 | } |
a6f87d34 | 10096 | |
4939150c PE |
10097 | ASET (attrs, coding_attr_plist, |
10098 | Fplist_put (CODING_ATTR_PLIST (attrs), prop, val)); | |
a6f87d34 KH |
10099 | return val; |
10100 | } | |
10101 | ||
10102 | ||
df7492f9 KH |
10103 | DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias, |
10104 | Sdefine_coding_system_alias, 2, 2, 0, | |
10105 | doc: /* Define ALIAS as an alias for CODING-SYSTEM. */) | |
5842a27b | 10106 | (Lisp_Object alias, Lisp_Object coding_system) |
66cfb530 | 10107 | { |
583f71ca | 10108 | Lisp_Object spec, aliases, eol_type, val; |
4ed46869 | 10109 | |
df7492f9 KH |
10110 | CHECK_SYMBOL (alias); |
10111 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10112 | aliases = AREF (spec, 1); | |
d4a1d553 | 10113 | /* ALIASES should be a list of length more than zero, and the first |
d6925f38 KH |
10114 | element is a base coding system. Append ALIAS at the tail of the |
10115 | list. */ | |
df7492f9 KH |
10116 | while (!NILP (XCDR (aliases))) |
10117 | aliases = XCDR (aliases); | |
8f924df7 | 10118 | XSETCDR (aliases, Fcons (alias, Qnil)); |
4ed46869 | 10119 | |
df7492f9 KH |
10120 | eol_type = AREF (spec, 2); |
10121 | if (VECTORP (eol_type)) | |
4ed46869 | 10122 | { |
df7492f9 KH |
10123 | Lisp_Object subsidiaries; |
10124 | int i; | |
4ed46869 | 10125 | |
df7492f9 KH |
10126 | subsidiaries = make_subsidiaries (alias); |
10127 | for (i = 0; i < 3; i++) | |
10128 | Fdefine_coding_system_alias (AREF (subsidiaries, i), | |
10129 | AREF (eol_type, i)); | |
4ed46869 | 10130 | } |
df7492f9 KH |
10131 | |
10132 | Fputhash (alias, spec, Vcoding_system_hash_table); | |
d6925f38 | 10133 | Vcoding_system_list = Fcons (alias, Vcoding_system_list); |
583f71ca KH |
10134 | val = Fassoc (Fsymbol_name (alias), Vcoding_system_alist); |
10135 | if (NILP (val)) | |
10136 | Vcoding_system_alist = Fcons (Fcons (Fsymbol_name (alias), Qnil), | |
10137 | Vcoding_system_alist); | |
66cfb530 | 10138 | |
4ed46869 KH |
10139 | return Qnil; |
10140 | } | |
10141 | ||
a7ca3326 | 10142 | DEFUN ("coding-system-base", Fcoding_system_base, Scoding_system_base, |
df7492f9 KH |
10143 | 1, 1, 0, |
10144 | doc: /* Return the base of CODING-SYSTEM. | |
da7db224 | 10145 | Any alias or subsidiary coding system is not a base coding system. */) |
5842a27b | 10146 | (Lisp_Object coding_system) |
d46c5b12 | 10147 | { |
df7492f9 | 10148 | Lisp_Object spec, attrs; |
d46c5b12 | 10149 | |
df7492f9 KH |
10150 | if (NILP (coding_system)) |
10151 | return (Qno_conversion); | |
10152 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10153 | attrs = AREF (spec, 0); | |
10154 | return CODING_ATTR_BASE_NAME (attrs); | |
10155 | } | |
1397dc18 | 10156 | |
df7492f9 KH |
10157 | DEFUN ("coding-system-plist", Fcoding_system_plist, Scoding_system_plist, |
10158 | 1, 1, 0, | |
10159 | doc: "Return the property list of CODING-SYSTEM.") | |
5842a27b | 10160 | (Lisp_Object coding_system) |
df7492f9 KH |
10161 | { |
10162 | Lisp_Object spec, attrs; | |
1397dc18 | 10163 | |
df7492f9 KH |
10164 | if (NILP (coding_system)) |
10165 | coding_system = Qno_conversion; | |
10166 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
10167 | attrs = AREF (spec, 0); | |
10168 | return CODING_ATTR_PLIST (attrs); | |
d46c5b12 KH |
10169 | } |
10170 | ||
df7492f9 KH |
10171 | |
10172 | DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases, | |
10173 | 1, 1, 0, | |
da7db224 | 10174 | doc: /* Return the list of aliases of CODING-SYSTEM. */) |
5842a27b | 10175 | (Lisp_Object coding_system) |
66cfb530 | 10176 | { |
df7492f9 | 10177 | Lisp_Object spec; |
84d60297 | 10178 | |
df7492f9 KH |
10179 | if (NILP (coding_system)) |
10180 | coding_system = Qno_conversion; | |
10181 | CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec); | |
da7db224 | 10182 | return AREF (spec, 1); |
df7492f9 | 10183 | } |
66cfb530 | 10184 | |
a7ca3326 | 10185 | DEFUN ("coding-system-eol-type", Fcoding_system_eol_type, |
df7492f9 KH |
10186 | Scoding_system_eol_type, 1, 1, 0, |
10187 | doc: /* Return eol-type of CODING-SYSTEM. | |
d4a1d553 | 10188 | An eol-type is an integer 0, 1, 2, or a vector of coding systems. |
66cfb530 | 10189 | |
df7492f9 KH |
10190 | Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF, |
10191 | and CR respectively. | |
66cfb530 | 10192 | |
df7492f9 KH |
10193 | A vector value indicates that a format of end-of-line should be |
10194 | detected automatically. Nth element of the vector is the subsidiary | |
10195 | coding system whose eol-type is N. */) | |
5842a27b | 10196 | (Lisp_Object coding_system) |
6b89e3aa | 10197 | { |
df7492f9 KH |
10198 | Lisp_Object spec, eol_type; |
10199 | int n; | |
6b89e3aa | 10200 | |
df7492f9 KH |
10201 | if (NILP (coding_system)) |
10202 | coding_system = Qno_conversion; | |
10203 | if (! CODING_SYSTEM_P (coding_system)) | |
10204 | return Qnil; | |
10205 | spec = CODING_SYSTEM_SPEC (coding_system); | |
10206 | eol_type = AREF (spec, 2); | |
10207 | if (VECTORP (eol_type)) | |
10208 | return Fcopy_sequence (eol_type); | |
10209 | n = EQ (eol_type, Qunix) ? 0 : EQ (eol_type, Qdos) ? 1 : 2; | |
10210 | return make_number (n); | |
6b89e3aa KH |
10211 | } |
10212 | ||
4ed46869 KH |
10213 | #endif /* emacs */ |
10214 | ||
10215 | \f | |
1397dc18 | 10216 | /*** 9. Post-amble ***/ |
4ed46869 | 10217 | |
dfcf069d | 10218 | void |
971de7fb | 10219 | init_coding_once (void) |
4ed46869 KH |
10220 | { |
10221 | int i; | |
10222 | ||
df7492f9 KH |
10223 | for (i = 0; i < coding_category_max; i++) |
10224 | { | |
10225 | coding_categories[i].id = -1; | |
10226 | coding_priorities[i] = i; | |
10227 | } | |
4ed46869 KH |
10228 | |
10229 | /* ISO2022 specific initialize routine. */ | |
10230 | for (i = 0; i < 0x20; i++) | |
b73bfc1c | 10231 | iso_code_class[i] = ISO_control_0; |
4ed46869 KH |
10232 | for (i = 0x21; i < 0x7F; i++) |
10233 | iso_code_class[i] = ISO_graphic_plane_0; | |
10234 | for (i = 0x80; i < 0xA0; i++) | |
b73bfc1c | 10235 | iso_code_class[i] = ISO_control_1; |
4ed46869 KH |
10236 | for (i = 0xA1; i < 0xFF; i++) |
10237 | iso_code_class[i] = ISO_graphic_plane_1; | |
10238 | iso_code_class[0x20] = iso_code_class[0x7F] = ISO_0x20_or_0x7F; | |
10239 | iso_code_class[0xA0] = iso_code_class[0xFF] = ISO_0xA0_or_0xFF; | |
4ed46869 KH |
10240 | iso_code_class[ISO_CODE_SO] = ISO_shift_out; |
10241 | iso_code_class[ISO_CODE_SI] = ISO_shift_in; | |
10242 | iso_code_class[ISO_CODE_SS2_7] = ISO_single_shift_2_7; | |
10243 | iso_code_class[ISO_CODE_ESC] = ISO_escape; | |
10244 | iso_code_class[ISO_CODE_SS2] = ISO_single_shift_2; | |
10245 | iso_code_class[ISO_CODE_SS3] = ISO_single_shift_3; | |
10246 | iso_code_class[ISO_CODE_CSI] = ISO_control_sequence_introducer; | |
10247 | ||
df7492f9 KH |
10248 | for (i = 0; i < 256; i++) |
10249 | { | |
10250 | emacs_mule_bytes[i] = 1; | |
10251 | } | |
7c78e542 KH |
10252 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_11] = 3; |
10253 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_12] = 3; | |
10254 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_21] = 4; | |
10255 | emacs_mule_bytes[EMACS_MULE_LEADING_CODE_PRIVATE_22] = 4; | |
e0e989f6 KH |
10256 | } |
10257 | ||
10258 | #ifdef emacs | |
10259 | ||
dfcf069d | 10260 | void |
971de7fb | 10261 | syms_of_coding (void) |
e0e989f6 | 10262 | { |
df7492f9 | 10263 | staticpro (&Vcoding_system_hash_table); |
8f924df7 KH |
10264 | { |
10265 | Lisp_Object args[2]; | |
10266 | args[0] = QCtest; | |
10267 | args[1] = Qeq; | |
10268 | Vcoding_system_hash_table = Fmake_hash_table (2, args); | |
10269 | } | |
df7492f9 KH |
10270 | |
10271 | staticpro (&Vsjis_coding_system); | |
10272 | Vsjis_coding_system = Qnil; | |
e0e989f6 | 10273 | |
df7492f9 KH |
10274 | staticpro (&Vbig5_coding_system); |
10275 | Vbig5_coding_system = Qnil; | |
10276 | ||
24a73b0a KH |
10277 | staticpro (&Vcode_conversion_reused_workbuf); |
10278 | Vcode_conversion_reused_workbuf = Qnil; | |
10279 | ||
10280 | staticpro (&Vcode_conversion_workbuf_name); | |
2a0213a6 | 10281 | Vcode_conversion_workbuf_name = build_pure_c_string (" *code-conversion-work*"); |
e0e989f6 | 10282 | |
24a73b0a | 10283 | reused_workbuf_in_use = 0; |
df7492f9 KH |
10284 | |
10285 | DEFSYM (Qcharset, "charset"); | |
10286 | DEFSYM (Qtarget_idx, "target-idx"); | |
10287 | DEFSYM (Qcoding_system_history, "coding-system-history"); | |
bb0115a2 RS |
10288 | Fset (Qcoding_system_history, Qnil); |
10289 | ||
9ce27fde | 10290 | /* Target FILENAME is the first argument. */ |
e0e989f6 | 10291 | Fput (Qinsert_file_contents, Qtarget_idx, make_number (0)); |
9ce27fde | 10292 | /* Target FILENAME is the third argument. */ |
e0e989f6 KH |
10293 | Fput (Qwrite_region, Qtarget_idx, make_number (2)); |
10294 | ||
df7492f9 | 10295 | DEFSYM (Qcall_process, "call-process"); |
9ce27fde | 10296 | /* Target PROGRAM is the first argument. */ |
e0e989f6 KH |
10297 | Fput (Qcall_process, Qtarget_idx, make_number (0)); |
10298 | ||
df7492f9 | 10299 | DEFSYM (Qcall_process_region, "call-process-region"); |
9ce27fde | 10300 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10301 | Fput (Qcall_process_region, Qtarget_idx, make_number (2)); |
10302 | ||
df7492f9 | 10303 | DEFSYM (Qstart_process, "start-process"); |
9ce27fde | 10304 | /* Target PROGRAM is the third argument. */ |
e0e989f6 KH |
10305 | Fput (Qstart_process, Qtarget_idx, make_number (2)); |
10306 | ||
df7492f9 | 10307 | DEFSYM (Qopen_network_stream, "open-network-stream"); |
9ce27fde | 10308 | /* Target SERVICE is the fourth argument. */ |
e0e989f6 KH |
10309 | Fput (Qopen_network_stream, Qtarget_idx, make_number (3)); |
10310 | ||
df7492f9 KH |
10311 | DEFSYM (Qcoding_system, "coding-system"); |
10312 | DEFSYM (Qcoding_aliases, "coding-aliases"); | |
4ed46869 | 10313 | |
df7492f9 KH |
10314 | DEFSYM (Qeol_type, "eol-type"); |
10315 | DEFSYM (Qunix, "unix"); | |
10316 | DEFSYM (Qdos, "dos"); | |
4ed46869 | 10317 | |
df7492f9 KH |
10318 | DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system"); |
10319 | DEFSYM (Qpost_read_conversion, "post-read-conversion"); | |
10320 | DEFSYM (Qpre_write_conversion, "pre-write-conversion"); | |
10321 | DEFSYM (Qdefault_char, "default-char"); | |
10322 | DEFSYM (Qundecided, "undecided"); | |
10323 | DEFSYM (Qno_conversion, "no-conversion"); | |
10324 | DEFSYM (Qraw_text, "raw-text"); | |
4ed46869 | 10325 | |
df7492f9 | 10326 | DEFSYM (Qiso_2022, "iso-2022"); |
4ed46869 | 10327 | |
df7492f9 | 10328 | DEFSYM (Qutf_8, "utf-8"); |
8f924df7 | 10329 | DEFSYM (Qutf_8_emacs, "utf-8-emacs"); |
27901516 | 10330 | |
df7492f9 | 10331 | DEFSYM (Qutf_16, "utf-16"); |
df7492f9 KH |
10332 | DEFSYM (Qbig, "big"); |
10333 | DEFSYM (Qlittle, "little"); | |
27901516 | 10334 | |
df7492f9 KH |
10335 | DEFSYM (Qshift_jis, "shift-jis"); |
10336 | DEFSYM (Qbig5, "big5"); | |
4ed46869 | 10337 | |
df7492f9 | 10338 | DEFSYM (Qcoding_system_p, "coding-system-p"); |
4ed46869 | 10339 | |
df7492f9 | 10340 | DEFSYM (Qcoding_system_error, "coding-system-error"); |
4ed46869 | 10341 | Fput (Qcoding_system_error, Qerror_conditions, |
3438fe21 | 10342 | listn (CONSTYPE_PURE, 2, Qcoding_system_error, Qerror)); |
4ed46869 | 10343 | Fput (Qcoding_system_error, Qerror_message, |
2a0213a6 | 10344 | build_pure_c_string ("Invalid coding system")); |
4ed46869 | 10345 | |
05e6f5dc KH |
10346 | /* Intern this now in case it isn't already done. |
10347 | Setting this variable twice is harmless. | |
10348 | But don't staticpro it here--that is done in alloc.c. */ | |
d67b4f80 | 10349 | Qchar_table_extra_slots = intern_c_string ("char-table-extra-slots"); |
70c22245 | 10350 | |
df7492f9 | 10351 | DEFSYM (Qtranslation_table, "translation-table"); |
433f7f87 | 10352 | Fput (Qtranslation_table, Qchar_table_extra_slots, make_number (2)); |
df7492f9 KH |
10353 | DEFSYM (Qtranslation_table_id, "translation-table-id"); |
10354 | DEFSYM (Qtranslation_table_for_decode, "translation-table-for-decode"); | |
10355 | DEFSYM (Qtranslation_table_for_encode, "translation-table-for-encode"); | |
1397dc18 | 10356 | |
df7492f9 | 10357 | DEFSYM (Qvalid_codes, "valid-codes"); |
9ce27fde | 10358 | |
df7492f9 | 10359 | DEFSYM (Qemacs_mule, "emacs-mule"); |
d46c5b12 | 10360 | |
01378f49 | 10361 | DEFSYM (QCcategory, ":category"); |
a6f87d34 | 10362 | DEFSYM (QCmnemonic, ":mnemonic"); |
2133e2d1 | 10363 | DEFSYM (QCdefault_char, ":default-char"); |
a6f87d34 KH |
10364 | DEFSYM (QCdecode_translation_table, ":decode-translation-table"); |
10365 | DEFSYM (QCencode_translation_table, ":encode-translation-table"); | |
10366 | DEFSYM (QCpost_read_conversion, ":post-read-conversion"); | |
10367 | DEFSYM (QCpre_write_conversion, ":pre-write-conversion"); | |
35befdaa | 10368 | DEFSYM (QCascii_compatible_p, ":ascii-compatible-p"); |
01378f49 | 10369 | |
df7492f9 KH |
10370 | Vcoding_category_table |
10371 | = Fmake_vector (make_number (coding_category_max), Qnil); | |
10372 | staticpro (&Vcoding_category_table); | |
10373 | /* Followings are target of code detection. */ | |
10374 | ASET (Vcoding_category_table, coding_category_iso_7, | |
d67b4f80 | 10375 | intern_c_string ("coding-category-iso-7")); |
df7492f9 | 10376 | ASET (Vcoding_category_table, coding_category_iso_7_tight, |
d67b4f80 | 10377 | intern_c_string ("coding-category-iso-7-tight")); |
df7492f9 | 10378 | ASET (Vcoding_category_table, coding_category_iso_8_1, |
d67b4f80 | 10379 | intern_c_string ("coding-category-iso-8-1")); |
df7492f9 | 10380 | ASET (Vcoding_category_table, coding_category_iso_8_2, |
d67b4f80 | 10381 | intern_c_string ("coding-category-iso-8-2")); |
df7492f9 | 10382 | ASET (Vcoding_category_table, coding_category_iso_7_else, |
d67b4f80 | 10383 | intern_c_string ("coding-category-iso-7-else")); |
df7492f9 | 10384 | ASET (Vcoding_category_table, coding_category_iso_8_else, |
d67b4f80 | 10385 | intern_c_string ("coding-category-iso-8-else")); |
a470d443 | 10386 | ASET (Vcoding_category_table, coding_category_utf_8_auto, |
d67b4f80 | 10387 | intern_c_string ("coding-category-utf-8-auto")); |
a470d443 | 10388 | ASET (Vcoding_category_table, coding_category_utf_8_nosig, |
d67b4f80 | 10389 | intern_c_string ("coding-category-utf-8")); |
a470d443 | 10390 | ASET (Vcoding_category_table, coding_category_utf_8_sig, |
d67b4f80 | 10391 | intern_c_string ("coding-category-utf-8-sig")); |
df7492f9 | 10392 | ASET (Vcoding_category_table, coding_category_utf_16_be, |
d67b4f80 | 10393 | intern_c_string ("coding-category-utf-16-be")); |
ff563fce | 10394 | ASET (Vcoding_category_table, coding_category_utf_16_auto, |
d67b4f80 | 10395 | intern_c_string ("coding-category-utf-16-auto")); |
df7492f9 | 10396 | ASET (Vcoding_category_table, coding_category_utf_16_le, |
d67b4f80 | 10397 | intern_c_string ("coding-category-utf-16-le")); |
df7492f9 | 10398 | ASET (Vcoding_category_table, coding_category_utf_16_be_nosig, |
d67b4f80 | 10399 | intern_c_string ("coding-category-utf-16-be-nosig")); |
df7492f9 | 10400 | ASET (Vcoding_category_table, coding_category_utf_16_le_nosig, |
d67b4f80 | 10401 | intern_c_string ("coding-category-utf-16-le-nosig")); |
df7492f9 | 10402 | ASET (Vcoding_category_table, coding_category_charset, |
d67b4f80 | 10403 | intern_c_string ("coding-category-charset")); |
df7492f9 | 10404 | ASET (Vcoding_category_table, coding_category_sjis, |
d67b4f80 | 10405 | intern_c_string ("coding-category-sjis")); |
df7492f9 | 10406 | ASET (Vcoding_category_table, coding_category_big5, |
d67b4f80 | 10407 | intern_c_string ("coding-category-big5")); |
df7492f9 | 10408 | ASET (Vcoding_category_table, coding_category_ccl, |
d67b4f80 | 10409 | intern_c_string ("coding-category-ccl")); |
df7492f9 | 10410 | ASET (Vcoding_category_table, coding_category_emacs_mule, |
d67b4f80 | 10411 | intern_c_string ("coding-category-emacs-mule")); |
df7492f9 KH |
10412 | /* Followings are NOT target of code detection. */ |
10413 | ASET (Vcoding_category_table, coding_category_raw_text, | |
d67b4f80 | 10414 | intern_c_string ("coding-category-raw-text")); |
df7492f9 | 10415 | ASET (Vcoding_category_table, coding_category_undecided, |
d67b4f80 | 10416 | intern_c_string ("coding-category-undecided")); |
ecf488bc | 10417 | |
065e3595 KH |
10418 | DEFSYM (Qinsufficient_source, "insufficient-source"); |
10419 | DEFSYM (Qinconsistent_eol, "inconsistent-eol"); | |
10420 | DEFSYM (Qinvalid_source, "invalid-source"); | |
10421 | DEFSYM (Qinterrupted, "interrupted"); | |
10422 | DEFSYM (Qinsufficient_memory, "insufficient-memory"); | |
44e8490d | 10423 | DEFSYM (Qcoding_system_define_form, "coding-system-define-form"); |
065e3595 | 10424 | |
4ed46869 KH |
10425 | defsubr (&Scoding_system_p); |
10426 | defsubr (&Sread_coding_system); | |
10427 | defsubr (&Sread_non_nil_coding_system); | |
10428 | defsubr (&Scheck_coding_system); | |
10429 | defsubr (&Sdetect_coding_region); | |
d46c5b12 | 10430 | defsubr (&Sdetect_coding_string); |
05e6f5dc | 10431 | defsubr (&Sfind_coding_systems_region_internal); |
068a9dbd | 10432 | defsubr (&Sunencodable_char_position); |
df7492f9 | 10433 | defsubr (&Scheck_coding_systems_region); |
4ed46869 KH |
10434 | defsubr (&Sdecode_coding_region); |
10435 | defsubr (&Sencode_coding_region); | |
10436 | defsubr (&Sdecode_coding_string); | |
10437 | defsubr (&Sencode_coding_string); | |
10438 | defsubr (&Sdecode_sjis_char); | |
10439 | defsubr (&Sencode_sjis_char); | |
10440 | defsubr (&Sdecode_big5_char); | |
10441 | defsubr (&Sencode_big5_char); | |
1ba9e4ab | 10442 | defsubr (&Sset_terminal_coding_system_internal); |
c4825358 | 10443 | defsubr (&Sset_safe_terminal_coding_system_internal); |
4ed46869 | 10444 | defsubr (&Sterminal_coding_system); |
1ba9e4ab | 10445 | defsubr (&Sset_keyboard_coding_system_internal); |
4ed46869 | 10446 | defsubr (&Skeyboard_coding_system); |
a5d301df | 10447 | defsubr (&Sfind_operation_coding_system); |
df7492f9 | 10448 | defsubr (&Sset_coding_system_priority); |
6b89e3aa | 10449 | defsubr (&Sdefine_coding_system_internal); |
df7492f9 | 10450 | defsubr (&Sdefine_coding_system_alias); |
a6f87d34 | 10451 | defsubr (&Scoding_system_put); |
df7492f9 KH |
10452 | defsubr (&Scoding_system_base); |
10453 | defsubr (&Scoding_system_plist); | |
10454 | defsubr (&Scoding_system_aliases); | |
10455 | defsubr (&Scoding_system_eol_type); | |
10456 | defsubr (&Scoding_system_priority_list); | |
4ed46869 | 10457 | |
29208e82 | 10458 | DEFVAR_LISP ("coding-system-list", Vcoding_system_list, |
48b0f3ae PJ |
10459 | doc: /* List of coding systems. |
10460 | ||
10461 | Do not alter the value of this variable manually. This variable should be | |
df7492f9 | 10462 | updated by the functions `define-coding-system' and |
48b0f3ae | 10463 | `define-coding-system-alias'. */); |
4608c386 KH |
10464 | Vcoding_system_list = Qnil; |
10465 | ||
29208e82 | 10466 | DEFVAR_LISP ("coding-system-alist", Vcoding_system_alist, |
48b0f3ae PJ |
10467 | doc: /* Alist of coding system names. |
10468 | Each element is one element list of coding system name. | |
446dcd75 | 10469 | This variable is given to `completing-read' as COLLECTION argument. |
48b0f3ae PJ |
10470 | |
10471 | Do not alter the value of this variable manually. This variable should be | |
10472 | updated by the functions `make-coding-system' and | |
10473 | `define-coding-system-alias'. */); | |
4608c386 KH |
10474 | Vcoding_system_alist = Qnil; |
10475 | ||
29208e82 | 10476 | DEFVAR_LISP ("coding-category-list", Vcoding_category_list, |
48b0f3ae PJ |
10477 | doc: /* List of coding-categories (symbols) ordered by priority. |
10478 | ||
10479 | On detecting a coding system, Emacs tries code detection algorithms | |
10480 | associated with each coding-category one by one in this order. When | |
10481 | one algorithm agrees with a byte sequence of source text, the coding | |
0ec31faf KH |
10482 | system bound to the corresponding coding-category is selected. |
10483 | ||
448e17d6 | 10484 | Don't modify this variable directly, but use `set-coding-system-priority'. */); |
4ed46869 KH |
10485 | { |
10486 | int i; | |
10487 | ||
10488 | Vcoding_category_list = Qnil; | |
df7492f9 | 10489 | for (i = coding_category_max - 1; i >= 0; i--) |
4ed46869 | 10490 | Vcoding_category_list |
28be1ada | 10491 | = Fcons (AREF (Vcoding_category_table, i), |
d46c5b12 | 10492 | Vcoding_category_list); |
4ed46869 KH |
10493 | } |
10494 | ||
29208e82 | 10495 | DEFVAR_LISP ("coding-system-for-read", Vcoding_system_for_read, |
48b0f3ae PJ |
10496 | doc: /* Specify the coding system for read operations. |
10497 | It is useful to bind this variable with `let', but do not set it globally. | |
10498 | If the value is a coding system, it is used for decoding on read operation. | |
446dcd75 JB |
10499 | If not, an appropriate element is used from one of the coding system alists. |
10500 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae | 10501 | `process-coding-system-alist', and `network-coding-system-alist'. */); |
4ed46869 KH |
10502 | Vcoding_system_for_read = Qnil; |
10503 | ||
29208e82 | 10504 | DEFVAR_LISP ("coding-system-for-write", Vcoding_system_for_write, |
48b0f3ae PJ |
10505 | doc: /* Specify the coding system for write operations. |
10506 | Programs bind this variable with `let', but you should not set it globally. | |
10507 | If the value is a coding system, it is used for encoding of output, | |
10508 | when writing it to a file and when sending it to a file or subprocess. | |
10509 | ||
10510 | If this does not specify a coding system, an appropriate element | |
446dcd75 JB |
10511 | is used from one of the coding system alists. |
10512 | There are three such tables: `file-coding-system-alist', | |
48b0f3ae PJ |
10513 | `process-coding-system-alist', and `network-coding-system-alist'. |
10514 | For output to files, if the above procedure does not specify a coding system, | |
10515 | the value of `buffer-file-coding-system' is used. */); | |
4ed46869 KH |
10516 | Vcoding_system_for_write = Qnil; |
10517 | ||
29208e82 | 10518 | DEFVAR_LISP ("last-coding-system-used", Vlast_coding_system_used, |
df7492f9 KH |
10519 | doc: /* |
10520 | Coding system used in the latest file or process I/O. */); | |
4ed46869 KH |
10521 | Vlast_coding_system_used = Qnil; |
10522 | ||
29208e82 | 10523 | DEFVAR_LISP ("last-code-conversion-error", Vlast_code_conversion_error, |
065e3595 KH |
10524 | doc: /* |
10525 | Error status of the last code conversion. | |
10526 | ||
10527 | When an error was detected in the last code conversion, this variable | |
10528 | is set to one of the following symbols. | |
10529 | `insufficient-source' | |
10530 | `inconsistent-eol' | |
10531 | `invalid-source' | |
10532 | `interrupted' | |
10533 | `insufficient-memory' | |
10534 | When no error was detected, the value doesn't change. So, to check | |
10535 | the error status of a code conversion by this variable, you must | |
10536 | explicitly set this variable to nil before performing code | |
10537 | conversion. */); | |
10538 | Vlast_code_conversion_error = Qnil; | |
10539 | ||
29208e82 | 10540 | DEFVAR_BOOL ("inhibit-eol-conversion", inhibit_eol_conversion, |
df7492f9 KH |
10541 | doc: /* |
10542 | *Non-nil means always inhibit code conversion of end-of-line format. | |
48b0f3ae PJ |
10543 | See info node `Coding Systems' and info node `Text and Binary' concerning |
10544 | such conversion. */); | |
9ce27fde KH |
10545 | inhibit_eol_conversion = 0; |
10546 | ||
29208e82 | 10547 | DEFVAR_BOOL ("inherit-process-coding-system", inherit_process_coding_system, |
df7492f9 KH |
10548 | doc: /* |
10549 | Non-nil means process buffer inherits coding system of process output. | |
48b0f3ae PJ |
10550 | Bind it to t if the process output is to be treated as if it were a file |
10551 | read from some filesystem. */); | |
ed29121d EZ |
10552 | inherit_process_coding_system = 0; |
10553 | ||
29208e82 | 10554 | DEFVAR_LISP ("file-coding-system-alist", Vfile_coding_system_alist, |
df7492f9 KH |
10555 | doc: /* |
10556 | Alist to decide a coding system to use for a file I/O operation. | |
48b0f3ae PJ |
10557 | The format is ((PATTERN . VAL) ...), |
10558 | where PATTERN is a regular expression matching a file name, | |
10559 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10560 | If VAL is a coding system, it is used for both decoding and encoding | |
10561 | the file contents. | |
10562 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10563 | and the cdr part is used for encoding. | |
10564 | If VAL is a function symbol, the function must return a coding system | |
2c53e699 KH |
10565 | or a cons of coding systems which are used as above. The function is |
10566 | called with an argument that is a list of the arguments with which | |
5a0bbd9a KH |
10567 | `find-operation-coding-system' was called. If the function can't decide |
10568 | a coding system, it can return `undecided' so that the normal | |
10569 | code-detection is performed. | |
48b0f3ae PJ |
10570 | |
10571 | See also the function `find-operation-coding-system' | |
10572 | and the variable `auto-coding-alist'. */); | |
02ba4723 KH |
10573 | Vfile_coding_system_alist = Qnil; |
10574 | ||
29208e82 | 10575 | DEFVAR_LISP ("process-coding-system-alist", Vprocess_coding_system_alist, |
df7492f9 KH |
10576 | doc: /* |
10577 | Alist to decide a coding system to use for a process I/O operation. | |
48b0f3ae PJ |
10578 | The format is ((PATTERN . VAL) ...), |
10579 | where PATTERN is a regular expression matching a program name, | |
10580 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10581 | If VAL is a coding system, it is used for both decoding what received | |
10582 | from the program and encoding what sent to the program. | |
10583 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10584 | and the cdr part is used for encoding. | |
10585 | If VAL is a function symbol, the function must return a coding system | |
10586 | or a cons of coding systems which are used as above. | |
10587 | ||
10588 | See also the function `find-operation-coding-system'. */); | |
02ba4723 KH |
10589 | Vprocess_coding_system_alist = Qnil; |
10590 | ||
29208e82 | 10591 | DEFVAR_LISP ("network-coding-system-alist", Vnetwork_coding_system_alist, |
df7492f9 KH |
10592 | doc: /* |
10593 | Alist to decide a coding system to use for a network I/O operation. | |
48b0f3ae PJ |
10594 | The format is ((PATTERN . VAL) ...), |
10595 | where PATTERN is a regular expression matching a network service name | |
10596 | or is a port number to connect to, | |
10597 | VAL is a coding system, a cons of coding systems, or a function symbol. | |
10598 | If VAL is a coding system, it is used for both decoding what received | |
10599 | from the network stream and encoding what sent to the network stream. | |
10600 | If VAL is a cons of coding systems, the car part is used for decoding, | |
10601 | and the cdr part is used for encoding. | |
10602 | If VAL is a function symbol, the function must return a coding system | |
10603 | or a cons of coding systems which are used as above. | |
10604 | ||
10605 | See also the function `find-operation-coding-system'. */); | |
02ba4723 | 10606 | Vnetwork_coding_system_alist = Qnil; |
4ed46869 | 10607 | |
29208e82 | 10608 | DEFVAR_LISP ("locale-coding-system", Vlocale_coding_system, |
75205970 RS |
10609 | doc: /* Coding system to use with system messages. |
10610 | Also used for decoding keyboard input on X Window system. */); | |
68c45bf0 PE |
10611 | Vlocale_coding_system = Qnil; |
10612 | ||
005f0d35 | 10613 | /* The eol mnemonics are reset in startup.el system-dependently. */ |
29208e82 | 10614 | DEFVAR_LISP ("eol-mnemonic-unix", eol_mnemonic_unix, |
df7492f9 KH |
10615 | doc: /* |
10616 | *String displayed in mode line for UNIX-like (LF) end-of-line format. */); | |
2a0213a6 | 10617 | eol_mnemonic_unix = build_pure_c_string (":"); |
4ed46869 | 10618 | |
29208e82 | 10619 | DEFVAR_LISP ("eol-mnemonic-dos", eol_mnemonic_dos, |
df7492f9 KH |
10620 | doc: /* |
10621 | *String displayed in mode line for DOS-like (CRLF) end-of-line format. */); | |
2a0213a6 | 10622 | eol_mnemonic_dos = build_pure_c_string ("\\"); |
4ed46869 | 10623 | |
29208e82 | 10624 | DEFVAR_LISP ("eol-mnemonic-mac", eol_mnemonic_mac, |
df7492f9 KH |
10625 | doc: /* |
10626 | *String displayed in mode line for MAC-like (CR) end-of-line format. */); | |
2a0213a6 | 10627 | eol_mnemonic_mac = build_pure_c_string ("/"); |
4ed46869 | 10628 | |
29208e82 | 10629 | DEFVAR_LISP ("eol-mnemonic-undecided", eol_mnemonic_undecided, |
df7492f9 KH |
10630 | doc: /* |
10631 | *String displayed in mode line when end-of-line format is not yet determined. */); | |
2a0213a6 | 10632 | eol_mnemonic_undecided = build_pure_c_string (":"); |
4ed46869 | 10633 | |
29208e82 | 10634 | DEFVAR_LISP ("enable-character-translation", Venable_character_translation, |
df7492f9 KH |
10635 | doc: /* |
10636 | *Non-nil enables character translation while encoding and decoding. */); | |
84fbb8a0 | 10637 | Venable_character_translation = Qt; |
bdd9fb48 | 10638 | |
f967223b | 10639 | DEFVAR_LISP ("standard-translation-table-for-decode", |
29208e82 | 10640 | Vstandard_translation_table_for_decode, |
48b0f3ae | 10641 | doc: /* Table for translating characters while decoding. */); |
f967223b | 10642 | Vstandard_translation_table_for_decode = Qnil; |
bdd9fb48 | 10643 | |
f967223b | 10644 | DEFVAR_LISP ("standard-translation-table-for-encode", |
29208e82 | 10645 | Vstandard_translation_table_for_encode, |
48b0f3ae | 10646 | doc: /* Table for translating characters while encoding. */); |
f967223b | 10647 | Vstandard_translation_table_for_encode = Qnil; |
4ed46869 | 10648 | |
29208e82 | 10649 | DEFVAR_LISP ("charset-revision-table", Vcharset_revision_table, |
48b0f3ae PJ |
10650 | doc: /* Alist of charsets vs revision numbers. |
10651 | While encoding, if a charset (car part of an element) is found, | |
df7492f9 KH |
10652 | designate it with the escape sequence identifying revision (cdr part |
10653 | of the element). */); | |
10654 | Vcharset_revision_table = Qnil; | |
02ba4723 KH |
10655 | |
10656 | DEFVAR_LISP ("default-process-coding-system", | |
29208e82 | 10657 | Vdefault_process_coding_system, |
48b0f3ae PJ |
10658 | doc: /* Cons of coding systems used for process I/O by default. |
10659 | The car part is used for decoding a process output, | |
10660 | the cdr part is used for encoding a text to be sent to a process. */); | |
02ba4723 | 10661 | Vdefault_process_coding_system = Qnil; |
c4825358 | 10662 | |
29208e82 | 10663 | DEFVAR_LISP ("latin-extra-code-table", Vlatin_extra_code_table, |
df7492f9 KH |
10664 | doc: /* |
10665 | Table of extra Latin codes in the range 128..159 (inclusive). | |
48b0f3ae PJ |
10666 | This is a vector of length 256. |
10667 | If Nth element is non-nil, the existence of code N in a file | |
10668 | \(or output of subprocess) doesn't prevent it to be detected as | |
10669 | a coding system of ISO 2022 variant which has a flag | |
10670 | `accept-latin-extra-code' t (e.g. iso-latin-1) on reading a file | |
10671 | or reading output of a subprocess. | |
446dcd75 | 10672 | Only 128th through 159th elements have a meaning. */); |
3f003981 | 10673 | Vlatin_extra_code_table = Fmake_vector (make_number (256), Qnil); |
d46c5b12 KH |
10674 | |
10675 | DEFVAR_LISP ("select-safe-coding-system-function", | |
29208e82 | 10676 | Vselect_safe_coding_system_function, |
df7492f9 KH |
10677 | doc: /* |
10678 | Function to call to select safe coding system for encoding a text. | |
48b0f3ae PJ |
10679 | |
10680 | If set, this function is called to force a user to select a proper | |
10681 | coding system which can encode the text in the case that a default | |
fdecf907 GM |
10682 | coding system used in each operation can't encode the text. The |
10683 | function should take care that the buffer is not modified while | |
10684 | the coding system is being selected. | |
48b0f3ae PJ |
10685 | |
10686 | The default value is `select-safe-coding-system' (which see). */); | |
d46c5b12 KH |
10687 | Vselect_safe_coding_system_function = Qnil; |
10688 | ||
5d5bf4d8 | 10689 | DEFVAR_BOOL ("coding-system-require-warning", |
29208e82 | 10690 | coding_system_require_warning, |
5d5bf4d8 | 10691 | doc: /* Internal use only. |
6b89e3aa KH |
10692 | If non-nil, on writing a file, `select-safe-coding-system-function' is |
10693 | called even if `coding-system-for-write' is non-nil. The command | |
10694 | `universal-coding-system-argument' binds this variable to t temporarily. */); | |
5d5bf4d8 KH |
10695 | coding_system_require_warning = 0; |
10696 | ||
10697 | ||
22ab2303 | 10698 | DEFVAR_BOOL ("inhibit-iso-escape-detection", |
29208e82 | 10699 | inhibit_iso_escape_detection, |
df7492f9 | 10700 | doc: /* |
97b1b294 | 10701 | If non-nil, Emacs ignores ISO-2022 escape sequences during code detection. |
48b0f3ae | 10702 | |
97b1b294 EZ |
10703 | When Emacs reads text, it tries to detect how the text is encoded. |
10704 | This code detection is sensitive to escape sequences. If Emacs sees | |
10705 | a valid ISO-2022 escape sequence, it assumes the text is encoded in one | |
10706 | of the ISO2022 encodings, and decodes text by the corresponding coding | |
10707 | system (e.g. `iso-2022-7bit'). | |
48b0f3ae PJ |
10708 | |
10709 | However, there may be a case that you want to read escape sequences in | |
10710 | a file as is. In such a case, you can set this variable to non-nil. | |
97b1b294 EZ |
10711 | Then the code detection will ignore any escape sequences, and no text is |
10712 | detected as encoded in some ISO-2022 encoding. The result is that all | |
48b0f3ae PJ |
10713 | escape sequences become visible in a buffer. |
10714 | ||
10715 | The default value is nil, and it is strongly recommended not to change | |
10716 | it. That is because many Emacs Lisp source files that contain | |
10717 | non-ASCII characters are encoded by the coding system `iso-2022-7bit' | |
10718 | in Emacs's distribution, and they won't be decoded correctly on | |
10719 | reading if you suppress escape sequence detection. | |
10720 | ||
10721 | The other way to read escape sequences in a file without decoding is | |
97b1b294 | 10722 | to explicitly specify some coding system that doesn't use ISO-2022 |
48b0f3ae | 10723 | escape sequence (e.g `latin-1') on reading by \\[universal-coding-system-argument]. */); |
74383408 | 10724 | inhibit_iso_escape_detection = 0; |
002fdb44 | 10725 | |
97b1b294 | 10726 | DEFVAR_BOOL ("inhibit-null-byte-detection", |
29208e82 | 10727 | inhibit_null_byte_detection, |
97b1b294 EZ |
10728 | doc: /* If non-nil, Emacs ignores null bytes on code detection. |
10729 | By default, Emacs treats it as binary data, and does not attempt to | |
10730 | decode it. The effect is as if you specified `no-conversion' for | |
10731 | reading that text. | |
10732 | ||
10733 | Set this to non-nil when a regular text happens to include null bytes. | |
10734 | Examples are Index nodes of Info files and null-byte delimited output | |
10735 | from GNU Find and GNU Grep. Emacs will then ignore the null bytes and | |
10736 | decode text as usual. */); | |
10737 | inhibit_null_byte_detection = 0; | |
10738 | ||
29208e82 | 10739 | DEFVAR_LISP ("translation-table-for-input", Vtranslation_table_for_input, |
15c8f9d1 | 10740 | doc: /* Char table for translating self-inserting characters. |
446dcd75 | 10741 | This is applied to the result of input methods, not their input. |
8434d0b8 EZ |
10742 | See also `keyboard-translate-table'. |
10743 | ||
10744 | Use of this variable for character code unification was rendered | |
10745 | obsolete in Emacs 23.1 and later, since Unicode is now the basis of | |
10746 | internal character representation. */); | |
002fdb44 | 10747 | Vtranslation_table_for_input = Qnil; |
8f924df7 | 10748 | |
2c78b7e1 KH |
10749 | { |
10750 | Lisp_Object args[coding_arg_max]; | |
8f924df7 | 10751 | Lisp_Object plist[16]; |
2c78b7e1 KH |
10752 | int i; |
10753 | ||
10754 | for (i = 0; i < coding_arg_max; i++) | |
10755 | args[i] = Qnil; | |
10756 | ||
d67b4f80 | 10757 | plist[0] = intern_c_string (":name"); |
2c78b7e1 | 10758 | plist[1] = args[coding_arg_name] = Qno_conversion; |
d67b4f80 | 10759 | plist[2] = intern_c_string (":mnemonic"); |
2c78b7e1 | 10760 | plist[3] = args[coding_arg_mnemonic] = make_number ('='); |
d67b4f80 | 10761 | plist[4] = intern_c_string (":coding-type"); |
2c78b7e1 | 10762 | plist[5] = args[coding_arg_coding_type] = Qraw_text; |
d67b4f80 | 10763 | plist[6] = intern_c_string (":ascii-compatible-p"); |
2c78b7e1 | 10764 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; |
d67b4f80 | 10765 | plist[8] = intern_c_string (":default-char"); |
2c78b7e1 | 10766 | plist[9] = args[coding_arg_default_char] = make_number (0); |
d67b4f80 | 10767 | plist[10] = intern_c_string (":for-unibyte"); |
8f924df7 | 10768 | plist[11] = args[coding_arg_for_unibyte] = Qt; |
d67b4f80 | 10769 | plist[12] = intern_c_string (":docstring"); |
2a0213a6 | 10770 | plist[13] = build_pure_c_string ("Do no conversion.\n\ |
2c78b7e1 KH |
10771 | \n\ |
10772 | When you visit a file with this coding, the file is read into a\n\ | |
10773 | unibyte buffer as is, thus each byte of a file is treated as a\n\ | |
10774 | character."); | |
d67b4f80 | 10775 | plist[14] = intern_c_string (":eol-type"); |
8f924df7 KH |
10776 | plist[15] = args[coding_arg_eol_type] = Qunix; |
10777 | args[coding_arg_plist] = Flist (16, plist); | |
2c78b7e1 | 10778 | Fdefine_coding_system_internal (coding_arg_max, args); |
ae6f73fa KH |
10779 | |
10780 | plist[1] = args[coding_arg_name] = Qundecided; | |
10781 | plist[3] = args[coding_arg_mnemonic] = make_number ('-'); | |
10782 | plist[5] = args[coding_arg_coding_type] = Qundecided; | |
10783 | /* This is already set. | |
35befdaa | 10784 | plist[7] = args[coding_arg_ascii_compatible_p] = Qt; */ |
d67b4f80 | 10785 | plist[8] = intern_c_string (":charset-list"); |
ae6f73fa KH |
10786 | plist[9] = args[coding_arg_charset_list] = Fcons (Qascii, Qnil); |
10787 | plist[11] = args[coding_arg_for_unibyte] = Qnil; | |
2a0213a6 | 10788 | plist[13] = build_pure_c_string ("No conversion on encoding, automatic conversion on decoding."); |
ae6f73fa KH |
10789 | plist[15] = args[coding_arg_eol_type] = Qnil; |
10790 | args[coding_arg_plist] = Flist (16, plist); | |
10791 | Fdefine_coding_system_internal (coding_arg_max, args); | |
2c78b7e1 KH |
10792 | } |
10793 | ||
2c78b7e1 | 10794 | setup_coding_system (Qno_conversion, &safe_terminal_coding); |
ff563fce KH |
10795 | |
10796 | { | |
10797 | int i; | |
10798 | ||
10799 | for (i = 0; i < coding_category_max; i++) | |
10800 | Fset (AREF (Vcoding_category_table, i), Qno_conversion); | |
10801 | } | |
1a4990fb | 10802 | #if defined (DOS_NT) |
fcbcfb64 KH |
10803 | system_eol_type = Qdos; |
10804 | #else | |
10805 | system_eol_type = Qunix; | |
10806 | #endif | |
10807 | staticpro (&system_eol_type); | |
4ed46869 KH |
10808 | } |
10809 | ||
68c45bf0 | 10810 | char * |
971de7fb | 10811 | emacs_strerror (int error_number) |
68c45bf0 PE |
10812 | { |
10813 | char *str; | |
10814 | ||
ca9c0567 | 10815 | synchronize_system_messages_locale (); |
68c45bf0 PE |
10816 | str = strerror (error_number); |
10817 | ||
10818 | if (! NILP (Vlocale_coding_system)) | |
10819 | { | |
10820 | Lisp_Object dec = code_convert_string_norecord (build_string (str), | |
10821 | Vlocale_coding_system, | |
10822 | 0); | |
51b59d79 | 10823 | str = SSDATA (dec); |
68c45bf0 PE |
10824 | } |
10825 | ||
10826 | return str; | |
10827 | } | |
10828 | ||
4ed46869 | 10829 | #endif /* emacs */ |