coding.c 319 KB
Newer Older
Dave Love's avatar
Dave Love committed
1
/* Coding system handler (conversion, detection, etc).
2
   Copyright (C) 2001-2011 Free Software Foundation, Inc.
Kenichi Handa's avatar
Kenichi Handa committed
3
   Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
4
     2005, 2006, 2007, 2008, 2009, 2010, 2011
Kenichi Handa's avatar
Kenichi Handa committed
5 6
     National Institute of Advanced Industrial Science and Technology (AIST)
     Registration Number H14PRO021
Kenichi Handa's avatar
Kenichi Handa committed
7
   Copyright (C) 2003
Kenichi Handa's avatar
Kenichi Handa committed
8 9
     National Institute of Advanced Industrial Science and Technology (AIST)
     Registration Number H13PRO009
Karl Heuer's avatar
Karl Heuer committed
10

Karl Heuer's avatar
Karl Heuer committed
11 12
This file is part of GNU Emacs.

13
GNU Emacs is free software: you can redistribute it and/or modify
Karl Heuer's avatar
Karl Heuer committed
14
it under the terms of the GNU General Public License as published by
15 16
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Karl Heuer's avatar
Karl Heuer committed
17

Karl Heuer's avatar
Karl Heuer committed
18 19 20 21
GNU Emacs is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.
Karl Heuer's avatar
Karl Heuer committed
22

Karl Heuer's avatar
Karl Heuer committed
23
You should have received a copy of the GNU General Public License
24
along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.  */
Karl Heuer's avatar
Karl Heuer committed
25 26 27

/*** TABLE OF CONTENTS ***

28
  0. General comments
Karl Heuer's avatar
Karl Heuer committed
29
  1. Preamble
Kenichi Handa's avatar
Kenichi Handa committed
30 31 32 33 34 35 36 37 38 39 40
  2. Emacs' internal format (emacs-utf-8) handlers
  3. UTF-8 handlers
  4. UTF-16 handlers
  5. Charset-base coding systems handlers
  6. emacs-mule (old Emacs' internal format) handlers
  7. ISO2022 handlers
  8. Shift-JIS and BIG5 handlers
  9. CCL handlers
  10. C library functions
  11. Emacs Lisp library functions
  12. Postamble
Karl Heuer's avatar
Karl Heuer committed
41 42 43

*/

Kenichi Handa's avatar
Kenichi Handa committed
44
/*** 0. General comments ***
45 46


Kenichi Handa's avatar
Kenichi Handa committed
47
CODING SYSTEM
Karl Heuer's avatar
Karl Heuer committed
48

Dave Love's avatar
Dave Love committed
49 50
  A coding system is an object for an encoding mechanism that contains
  information about how to convert byte sequences to character
51 52 53 54 55
  sequences and vice versa.  When we say "decode", it means converting
  a byte sequence of a specific coding system into a character
  sequence that is represented by Emacs' internal coding system
  `emacs-utf-8', and when we say "encode", it means converting a
  character sequence of emacs-utf-8 to a byte sequence of a specific
Kenichi Handa's avatar
Kenichi Handa committed
56
  coding system.
Karl Heuer's avatar
Karl Heuer committed
57

58 59
  In Emacs Lisp, a coding system is represented by a Lisp symbol.  In
  C level, a coding system is represented by a vector of attributes
Dave Love's avatar
Dave Love committed
60
  stored in the hash table Vcharset_hash_table.  The conversion from
61 62
  coding system symbol to attributes vector is done by looking up
  Vcharset_hash_table by the symbol.
Karl Heuer's avatar
Karl Heuer committed
63

64
  Coding systems are classified into the following types depending on
Dave Love's avatar
Dave Love committed
65
  the encoding mechanism.  Here's a brief description of the types.
Karl Heuer's avatar
Karl Heuer committed
66

Kenichi Handa's avatar
Kenichi Handa committed
67 68 69 70 71 72 73
  o UTF-8

  o UTF-16

  o Charset-base coding system

  A coding system defined by one or more (coded) character sets.
Dave Love's avatar
Dave Love committed
74
  Decoding and encoding are done by a code converter defined for each
Kenichi Handa's avatar
Kenichi Handa committed
75 76
  character set.

Dave Love's avatar
Dave Love committed
77
  o Old Emacs internal format (emacs-mule)
Kenichi Handa's avatar
Kenichi Handa committed
78

Dave Love's avatar
Dave Love committed
79
  The coding system adopted by old versions of Emacs (20 and 21).
Karl Heuer's avatar
Karl Heuer committed
80

Kenichi Handa's avatar
Kenichi Handa committed
81
  o ISO2022-base coding system
Karl Heuer's avatar
Karl Heuer committed
82 83

  The most famous coding system for multiple character sets.  X's
Kenichi Handa's avatar
Kenichi Handa committed
84 85 86
  Compound Text, various EUCs (Extended Unix Code), and coding systems
  used in the Internet communication such as ISO-2022-JP are all
  variants of ISO2022.
Karl Heuer's avatar
Karl Heuer committed
87

Kenichi Handa's avatar
Kenichi Handa committed
88
  o SJIS (or Shift-JIS or MS-Kanji-Code)
89

Karl Heuer's avatar
Karl Heuer committed
90 91
  A coding system to encode character sets: ASCII, JISX0201, and
  JISX0208.  Widely used for PC's in Japan.  Details are described in
Kenichi Handa's avatar
Kenichi Handa committed
92
  section 8.
Karl Heuer's avatar
Karl Heuer committed
93

Kenichi Handa's avatar
Kenichi Handa committed
94
  o BIG5
Karl Heuer's avatar
Karl Heuer committed
95

Kenichi Handa's avatar
Kenichi Handa committed
96
  A coding system to encode character sets: ASCII and Big5.  Widely
Dave Love's avatar
Dave Love committed
97
  used for Chinese (mainly in Taiwan and Hong Kong).  Details are
Kenichi Handa's avatar
Kenichi Handa committed
98 99 100
  described in section 8.  In this file, when we write "big5" (all
  lowercase), we mean the coding system, and when we write "Big5"
  (capitalized), we mean the character set.
Karl Heuer's avatar
Karl Heuer committed
101

Kenichi Handa's avatar
Kenichi Handa committed
102
  o CCL
103

Dave Love's avatar
Dave Love committed
104
  If a user wants to decode/encode text encoded in a coding system
Kenichi Handa's avatar
Kenichi Handa committed
105 106 107
  not listed above, he can supply a decoder and an encoder for it in
  CCL (Code Conversion Language) programs.  Emacs executes the CCL
  program while decoding/encoding.
108

Kenichi Handa's avatar
Kenichi Handa committed
109
  o Raw-text
Karl Heuer's avatar
Karl Heuer committed
110

Dave Love's avatar
Dave Love committed
111
  A coding system for text containing raw eight-bit data.  Emacs
Dave Love's avatar
Dave Love committed
112
  treats each byte of source text as a character (except for
Kenichi Handa's avatar
Kenichi Handa committed
113
  end-of-line conversion).
Karl Heuer's avatar
Karl Heuer committed
114

Kenichi Handa's avatar
Kenichi Handa committed
115 116 117
  o No-conversion

  Like raw text, but don't do end-of-line conversion.
Karl Heuer's avatar
Karl Heuer committed
118 119


Kenichi Handa's avatar
Kenichi Handa committed
120
END-OF-LINE FORMAT
Karl Heuer's avatar
Karl Heuer committed
121

Dave Love's avatar
Dave Love committed
122
  How text end-of-line is encoded depends on operating system.  For
Kenichi Handa's avatar
Kenichi Handa committed
123
  instance, Unix's format is just one byte of LF (line-feed) code,
Richard M. Stallman's avatar
Richard M. Stallman committed
124
  whereas DOS's format is two-byte sequence of `carriage-return' and
125 126
  `line-feed' codes.  MacOS's format is usually one byte of
  `carriage-return'.
Karl Heuer's avatar
Karl Heuer committed
127

Dave Love's avatar
Dave Love committed
128
  Since text character encoding and end-of-line encoding are
Kenichi Handa's avatar
Kenichi Handa committed
129 130
  independent, any coding system described above can take any format
  of end-of-line (except for no-conversion).
Karl Heuer's avatar
Karl Heuer committed
131

132 133 134 135 136
STRUCT CODING_SYSTEM

  Before using a coding system for code conversion (i.e. decoding and
  encoding), we setup a structure of type `struct coding_system'.
  This structure keeps various information about a specific code
Dave Love's avatar
Dave Love committed
137
  conversion (e.g. the location of source and destination data).
Karl Heuer's avatar
Karl Heuer committed
138 139 140

*/

Kenichi Handa's avatar
Kenichi Handa committed
141 142 143
/* COMMON MACROS */


Karl Heuer's avatar
Karl Heuer committed
144 145
/*** GENERAL NOTES on `detect_coding_XXX ()' functions ***

Kenichi Handa's avatar
Kenichi Handa committed
146
  These functions check if a byte sequence specified as a source in
147 148
  CODING conforms to the format of XXX, and update the members of
  DETECT_INFO.
Kenichi Handa's avatar
Kenichi Handa committed
149

150
  Return 1 if the byte sequence conforms to XXX, otherwise return 0.
Kenichi Handa's avatar
Kenichi Handa committed
151 152 153

  Below is the template of these functions.  */

Karl Heuer's avatar
Karl Heuer committed
154
#if 0
Kenichi Handa's avatar
Kenichi Handa committed
155
static int
156 157
detect_coding_XXX (struct coding_system *coding,
		   struct coding_detection_info *detect_info)
Karl Heuer's avatar
Karl Heuer committed
158
{
159 160
  const unsigned char *src = coding->source;
  const unsigned char *src_end = coding->source + coding->src_bytes;
Kenichi Handa's avatar
Kenichi Handa committed
161
  int multibytep = coding->src_multibyte;
162
  int consumed_chars = 0;
Kenichi Handa's avatar
Kenichi Handa committed
163 164 165 166 167
  int found = 0;
  ...;

  while (1)
    {
Kenichi Handa's avatar
Kenichi Handa committed
168
      /* Get one byte from the source.  If the source is exhausted, jump
Kenichi Handa's avatar
Kenichi Handa committed
169 170
	 to no_more_source:.  */
      ONE_MORE_BYTE (c);
171 172 173 174 175

      if (! __C_conforms_to_XXX___ (c))
	break;
      if (! __C_strongly_suggests_XXX__ (c))
	found = CATEGORY_MASK_XXX;
Kenichi Handa's avatar
Kenichi Handa committed
176
    }
177 178
  /* The byte sequence is invalid for XXX.  */
  detect_info->rejected |= CATEGORY_MASK_XXX;
Kenichi Handa's avatar
Kenichi Handa committed
179
  return 0;
180

Kenichi Handa's avatar
Kenichi Handa committed
181
 no_more_source:
Kenichi Handa's avatar
Kenichi Handa committed
182
  /* The source exhausted successfully.  */
183
  detect_info->found |= found;
Kenichi Handa's avatar
Kenichi Handa committed
184
  return 1;
Karl Heuer's avatar
Karl Heuer committed
185 186 187 188 189
}
#endif

/*** GENERAL NOTES on `decode_coding_XXX ()' functions ***

Kenichi Handa's avatar
Kenichi Handa committed
190 191 192 193
  These functions decode a byte sequence specified as a source by
  CODING.  The resulting multibyte text goes to a place pointed to by
  CODING->charbuf, the length of which should not exceed
  CODING->charbuf_size;
194

Kenichi Handa's avatar
Kenichi Handa committed
195 196 197 198
  These functions set the information of original and decoded texts in
  CODING->consumed, CODING->consumed_char, and CODING->charbuf_used.
  They also set CODING->result to one of CODING_RESULT_XXX indicating
  how the decoding is finished.
199

Kenichi Handa's avatar
Kenichi Handa committed
200
  Below is the template of these functions.  */
201

Karl Heuer's avatar
Karl Heuer committed
202
#if 0
203
static void
204
decode_coding_XXXX (struct coding_system *coding)
Karl Heuer's avatar
Karl Heuer committed
205
{
206 207
  const unsigned char *src = coding->source + coding->consumed;
  const unsigned char *src_end = coding->source + coding->src_bytes;
Kenichi Handa's avatar
Kenichi Handa committed
208 209 210
  /* SRC_BASE remembers the start position in source in each loop.
     The loop will be exited when there's not enough source code, or
     when there's no room in CHARBUF for a decoded character.  */
211
  const unsigned char *src_base;
Kenichi Handa's avatar
Kenichi Handa committed
212
  /* A buffer to produce decoded characters.  */
213 214
  int *charbuf = coding->charbuf + coding->charbuf_used;
  int *charbuf_end = coding->charbuf + coding->charbuf_size;
Kenichi Handa's avatar
Kenichi Handa committed
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238
  int multibytep = coding->src_multibyte;

  while (1)
    {
      src_base = src;
      if (charbuf < charbuf_end)
	/* No more room to produce a decoded character.  */
	break;
      ONE_MORE_BYTE (c);
      /* Decode it. */
    }

 no_more_source:
  if (src_base < src_end
      && coding->mode & CODING_MODE_LAST_BLOCK)
    /* If the source ends by partial bytes to construct a character,
       treat them as eight-bit raw data.  */
    while (src_base < src_end && charbuf < charbuf_end)
      *charbuf++ = *src_base++;
  /* Remember how many bytes and characters we consumed.  If the
     source is multibyte, the bytes and chars are not identical.  */
  coding->consumed = coding->consumed_char = src_base - coding->source;
  /* Remember how many characters we produced.  */
  coding->charbuf_used = charbuf - coding->charbuf;
Karl Heuer's avatar
Karl Heuer committed
239 240 241 242 243
}
#endif

/*** GENERAL NOTES on `encode_coding_XXX ()' functions ***

Kenichi Handa's avatar
Kenichi Handa committed
244 245
  These functions encode SRC_BYTES length text at SOURCE of Emacs'
  internal multibyte format by CODING.  The resulting byte sequence
246 247
  goes to a place pointed to by DESTINATION, the length of which
  should not exceed DST_BYTES.
248

Kenichi Handa's avatar
Kenichi Handa committed
249 250 251 252
  These functions set the information of original and encoded texts in
  the members produced, produced_char, consumed, and consumed_char of
  the structure *CODING.  They also set the member result to one of
  CODING_RESULT_XXX indicating how the encoding finished.
253

Kenichi Handa's avatar
Kenichi Handa committed
254 255 256
  DST_BYTES zero means that source area and destination area are
  overlapped, which means that we can produce a encoded text until it
  reaches at the head of not-yet-encoded source text.
257

Kenichi Handa's avatar
Kenichi Handa committed
258
  Below is a template of these functions.  */
Karl Heuer's avatar
Karl Heuer committed
259
#if 0
260
static void
261
encode_coding_XXX (struct coding_system *coding)
Karl Heuer's avatar
Karl Heuer committed
262
{
Kenichi Handa's avatar
Kenichi Handa committed
263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279
  int multibytep = coding->dst_multibyte;
  int *charbuf = coding->charbuf;
  int *charbuf_end = charbuf->charbuf + coding->charbuf_used;
  unsigned char *dst = coding->destination + coding->produced;
  unsigned char *dst_end = coding->destination + coding->dst_bytes;
  unsigned char *adjusted_dst_end = dst_end - _MAX_BYTES_PRODUCED_IN_LOOP_;
  int produced_chars = 0;

  for (; charbuf < charbuf_end && dst < adjusted_dst_end; charbuf++)
    {
      int c = *charbuf;
      /* Encode C into DST, and increment DST.  */
    }
 label_no_more_destination:
  /* How many chars and bytes we produced.  */
  coding->produced_char += produced_chars;
  coding->produced = dst - coding->destination;
Karl Heuer's avatar
Karl Heuer committed
280 281 282 283 284 285
}
#endif


/*** 1. Preamble ***/

286
#include <config.h>
Karl Heuer's avatar
Karl Heuer committed
287
#include <stdio.h>
288
#include <setjmp.h>
Karl Heuer's avatar
Karl Heuer committed
289 290 291

#include "lisp.h"
#include "buffer.h"
Kenichi Handa's avatar
Kenichi Handa committed
292
#include "character.h"
Karl Heuer's avatar
Karl Heuer committed
293 294
#include "charset.h"
#include "ccl.h"
Kenichi Handa's avatar
Kenichi Handa committed
295
#include "composite.h"
Karl Heuer's avatar
Karl Heuer committed
296 297
#include "coding.h"
#include "window.h"
298 299
#include "frame.h"
#include "termhooks.h"
Karl Heuer's avatar
Karl Heuer committed
300

Kenichi Handa's avatar
Kenichi Handa committed
301
Lisp_Object Vcoding_system_hash_table;
Karl Heuer's avatar
Karl Heuer committed
302

Kenichi Handa's avatar
Kenichi Handa committed
303
Lisp_Object Qcoding_system, Qcoding_aliases, Qeol_type;
304
Lisp_Object Qunix, Qdos;
Karl Heuer's avatar
Karl Heuer committed
305 306
Lisp_Object Qbuffer_file_coding_system;
Lisp_Object Qpost_read_conversion, Qpre_write_conversion;
Kenichi Handa's avatar
Kenichi Handa committed
307
Lisp_Object Qdefault_char;
308
Lisp_Object Qno_conversion, Qundecided;
Kenichi Handa's avatar
Kenichi Handa committed
309
Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5;
310
Lisp_Object Qbig, Qlittle;
311
Lisp_Object Qcoding_system_history;
Kenichi Handa's avatar
Kenichi Handa committed
312
Lisp_Object Qvalid_codes;
313
Lisp_Object QCcategory, QCmnemonic, QCdefault_char;
Kenichi Handa's avatar
Kenichi Handa committed
314 315
Lisp_Object QCdecode_translation_table, QCencode_translation_table;
Lisp_Object QCpost_read_conversion, QCpre_write_conversion;
316
Lisp_Object QCascii_compatible_p;
Karl Heuer's avatar
Karl Heuer committed
317

Kim F. Storm's avatar
Kim F. Storm committed
318
Lisp_Object Qcall_process, Qcall_process_region;
Karl Heuer's avatar
Karl Heuer committed
319 320 321
Lisp_Object Qstart_process, Qopen_network_stream;
Lisp_Object Qtarget_idx;

322 323 324
Lisp_Object Qinsufficient_source, Qinconsistent_eol, Qinvalid_source;
Lisp_Object Qinterrupted, Qinsufficient_memory;

325 326 327 328
/* If a symbol has this property, evaluate the value to define the
   symbol as a coding system.  */
static Lisp_Object Qcoding_system_define_form;

329 330 331 332 333 334
/* Format of end-of-line decided by system.  This is Qunix on
   Unix and Mac, Qdos on DOS/Windows.
   This has an effect only for external encoding (i.e. for output to
   file and process), not for in-buffer or Lisp string encoding.  */
static Lisp_Object system_eol_type;

Karl Heuer's avatar
Karl Heuer committed
335 336
#ifdef emacs

337
Lisp_Object Qcoding_system_p, Qcoding_system_error;
Karl Heuer's avatar
Karl Heuer committed
338

339 340 341
/* Coding system emacs-mule and raw-text are for converting only
   end-of-line format.  */
Lisp_Object Qemacs_mule, Qraw_text;
Kenichi Handa's avatar
Kenichi Handa committed
342
Lisp_Object Qutf_8_emacs;
Dave Love's avatar
Dave Love committed
343

Karl Heuer's avatar
Karl Heuer committed
344 345
/* Coding-systems are handed between Emacs Lisp programs and C internal
   routines by the following three variables.  */
346 347 348 349
/* Coding system to be used to encode text for terminal display when
   terminal coding system is nil.  */
struct coding_system safe_terminal_coding;

Karl Heuer's avatar
Karl Heuer committed
350 351
#endif /* emacs */

352 353 354 355
Lisp_Object Qtranslation_table;
Lisp_Object Qtranslation_table_id;
Lisp_Object Qtranslation_table_for_decode;
Lisp_Object Qtranslation_table_for_encode;
Karl Heuer's avatar
Karl Heuer committed
356

Kenichi Handa's avatar
Kenichi Handa committed
357 358 359 360 361 362 363 364 365 366 367 368
/* Two special coding systems.  */
Lisp_Object Vsjis_coding_system;
Lisp_Object Vbig5_coding_system;

/* ISO2022 section */

#define CODING_ISO_INITIAL(coding, reg)			\
  (XINT (AREF (AREF (CODING_ID_ATTRS ((coding)->id),	\
		     coding_attr_iso_initial),		\
	       reg)))


369 370 371 372 373
#define CODING_ISO_REQUEST(coding, charset_id)		\
  (((charset_id) <= (coding)->max_charset_id		\
    ? ((coding)->safe_charsets[charset_id] != 255	\
       ? (coding)->safe_charsets[charset_id]		\
       : -1)						\
Kenichi Handa's avatar
Kenichi Handa committed
374 375 376 377 378 379 380 381 382 383 384 385 386 387 388
    : -1))


#define CODING_ISO_FLAGS(coding)	\
  ((coding)->spec.iso_2022.flags)
#define CODING_ISO_DESIGNATION(coding, reg)	\
  ((coding)->spec.iso_2022.current_designation[reg])
#define CODING_ISO_INVOCATION(coding, plane)	\
  ((coding)->spec.iso_2022.current_invocation[plane])
#define CODING_ISO_SINGLE_SHIFTING(coding)	\
  ((coding)->spec.iso_2022.single_shifting)
#define CODING_ISO_BOL(coding)	\
  ((coding)->spec.iso_2022.bol)
#define CODING_ISO_INVOKED_CHARSET(coding, plane)	\
  CODING_ISO_DESIGNATION ((coding), CODING_ISO_INVOCATION ((coding), (plane)))
389 390 391 392 393 394
#define CODING_ISO_CMP_STATUS(coding)	\
  (&(coding)->spec.iso_2022.cmp_status)
#define CODING_ISO_EXTSEGMENT_LEN(coding)	\
  ((coding)->spec.iso_2022.ctext_extended_segment_len)
#define CODING_ISO_EMBEDDED_UTF_8(coding)	\
  ((coding)->spec.iso_2022.embedded_utf_8)
Kenichi Handa's avatar
Kenichi Handa committed
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429

/* Control characters of ISO2022.  */
			/* code */	/* function */
#define ISO_CODE_LF	0x0A		/* line-feed */
#define ISO_CODE_CR	0x0D		/* carriage-return */
#define ISO_CODE_SO	0x0E		/* shift-out */
#define ISO_CODE_SI	0x0F		/* shift-in */
#define ISO_CODE_SS2_7	0x19		/* single-shift-2 for 7-bit code */
#define ISO_CODE_ESC	0x1B		/* escape */
#define ISO_CODE_SS2	0x8E		/* single-shift-2 */
#define ISO_CODE_SS3	0x8F		/* single-shift-3 */
#define ISO_CODE_CSI	0x9B		/* control-sequence-introducer */

/* All code (1-byte) of ISO2022 is classified into one of the
   followings.  */
enum iso_code_class_type
  {
    ISO_control_0,		/* Control codes in the range
				   0x00..0x1F and 0x7F, except for the
				   following 5 codes.  */
    ISO_shift_out,		/* ISO_CODE_SO (0x0E) */
    ISO_shift_in,		/* ISO_CODE_SI (0x0F) */
    ISO_single_shift_2_7,	/* ISO_CODE_SS2_7 (0x19) */
    ISO_escape,			/* ISO_CODE_SO (0x1B) */
    ISO_control_1,		/* Control codes in the range
				   0x80..0x9F, except for the
				   following 3 codes.  */
    ISO_single_shift_2,		/* ISO_CODE_SS2 (0x8E) */
    ISO_single_shift_3,		/* ISO_CODE_SS3 (0x8F) */
    ISO_control_sequence_introducer, /* ISO_CODE_CSI (0x9B) */
    ISO_0x20_or_0x7F,		/* Codes of the values 0x20 or 0x7F.  */
    ISO_graphic_plane_0,	/* Graphic codes in the range 0x21..0x7E.  */
    ISO_0xA0_or_0xFF,		/* Codes of the values 0xA0 or 0xFF.  */
    ISO_graphic_plane_1		/* Graphic codes in the range 0xA1..0xFE.  */
  };
430

Kenichi Handa's avatar
Kenichi Handa committed
431 432
/** The macros CODING_ISO_FLAG_XXX defines a flag bit of the
    `iso-flags' attribute of an iso2022 coding system.  */
433

Kenichi Handa's avatar
Kenichi Handa committed
434 435 436
/* If set, produce long-form designation sequence (e.g. ESC $ ( A)
   instead of the correct short-form sequence (e.g. ESC $ A).  */
#define CODING_ISO_FLAG_LONG_FORM	0x0001
437

Kenichi Handa's avatar
Kenichi Handa committed
438 439 440
/* If set, reset graphic planes and registers at end-of-line to the
   initial state.  */
#define CODING_ISO_FLAG_RESET_AT_EOL	0x0002
441

Kenichi Handa's avatar
Kenichi Handa committed
442 443 444
/* If set, reset graphic planes and registers before any control
   characters to the initial state.  */
#define CODING_ISO_FLAG_RESET_AT_CNTL	0x0004
445

Kenichi Handa's avatar
Kenichi Handa committed
446 447
/* If set, encode by 7-bit environment.  */
#define CODING_ISO_FLAG_SEVEN_BITS	0x0008
Karl Heuer's avatar
Karl Heuer committed
448

Kenichi Handa's avatar
Kenichi Handa committed
449 450
/* If set, use locking-shift function.  */
#define CODING_ISO_FLAG_LOCKING_SHIFT	0x0010
451

Kenichi Handa's avatar
Kenichi Handa committed
452 453 454
/* If set, use single-shift function.  Overwrite
   CODING_ISO_FLAG_LOCKING_SHIFT.  */
#define CODING_ISO_FLAG_SINGLE_SHIFT	0x0020
455

Kenichi Handa's avatar
Kenichi Handa committed
456 457
/* If set, use designation escape sequence.  */
#define CODING_ISO_FLAG_DESIGNATION	0x0040
458

Kenichi Handa's avatar
Kenichi Handa committed
459 460
/* If set, produce revision number sequence.  */
#define CODING_ISO_FLAG_REVISION	0x0080
461

Kenichi Handa's avatar
Kenichi Handa committed
462 463
/* If set, produce ISO6429's direction specifying sequence.  */
#define CODING_ISO_FLAG_DIRECTION	0x0100
Richard M. Stallman's avatar
Richard M. Stallman committed
464

Kenichi Handa's avatar
Kenichi Handa committed
465 466 467
/* If set, assume designation states are reset at beginning of line on
   output.  */
#define CODING_ISO_FLAG_INIT_AT_BOL	0x0200
Karl Heuer's avatar
Karl Heuer committed
468

Kenichi Handa's avatar
Kenichi Handa committed
469 470 471
/* If set, designation sequence should be placed at beginning of line
   on output.  */
#define CODING_ISO_FLAG_DESIGNATE_AT_BOL 0x0400
472

Kenichi Handa's avatar
Kenichi Handa committed
473
/* If set, do not encode unsafe characters on output.  */
Kenichi Handa's avatar
Kenichi Handa committed
474
#define CODING_ISO_FLAG_SAFE		0x0800
475

Kenichi Handa's avatar
Kenichi Handa committed
476 477 478
/* If set, extra latin codes (128..159) are accepted as a valid code
   on input.  */
#define CODING_ISO_FLAG_LATIN_EXTRA	0x1000
479

Kenichi Handa's avatar
Kenichi Handa committed
480
#define CODING_ISO_FLAG_COMPOSITION	0x2000
481

Kenichi Handa's avatar
Kenichi Handa committed
482
#define CODING_ISO_FLAG_EUC_TW_SHIFT	0x4000
483

484
#define CODING_ISO_FLAG_USE_ROMAN	0x8000
485

486
#define CODING_ISO_FLAG_USE_OLDJIS	0x10000
487

488
#define CODING_ISO_FLAG_FULL_SUPPORT	0x100000
489

Kenichi Handa's avatar
Kenichi Handa committed
490 491 492
/* A character to be produced on output if encoding of the original
   character is prohibited by CODING_ISO_FLAG_SAFE.  */
#define CODING_INHIBIT_CHARACTER_SUBSTITUTION  '?'
493

Kenichi Handa's avatar
Kenichi Handa committed
494 495 496
/* UTF-8 section */
#define CODING_UTF_8_BOM(coding)	\
  ((coding)->spec.utf_8_bom)
Karl Heuer's avatar
Karl Heuer committed
497

Kenichi Handa's avatar
Kenichi Handa committed
498 499 500
/* UTF-16 section */
#define CODING_UTF_16_BOM(coding)	\
  ((coding)->spec.utf_16.bom)
Karl Heuer's avatar
Karl Heuer committed
501

Kenichi Handa's avatar
Kenichi Handa committed
502 503
#define CODING_UTF_16_ENDIAN(coding)	\
  ((coding)->spec.utf_16.endian)
Karl Heuer's avatar
Karl Heuer committed
504

Kenichi Handa's avatar
Kenichi Handa committed
505 506
#define CODING_UTF_16_SURROGATE(coding)	\
  ((coding)->spec.utf_16.surrogate)
Karl Heuer's avatar
Karl Heuer committed
507 508


Kenichi Handa's avatar
Kenichi Handa committed
509 510 511 512 513 514
/* CCL section */
#define CODING_CCL_DECODER(coding)	\
  AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_decoder)
#define CODING_CCL_ENCODER(coding)	\
  AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_encoder)
#define CODING_CCL_VALIDS(coding)					   \
Kenichi Handa's avatar
Kenichi Handa committed
515
  (SDATA (AREF (CODING_ID_ATTRS ((coding)->id), coding_attr_ccl_valids)))
Karl Heuer's avatar
Karl Heuer committed
516

Dave Love's avatar
Dave Love committed
517
/* Index for each coding category in `coding_categories' */
Karl Heuer's avatar
Karl Heuer committed
518

Kenichi Handa's avatar
Kenichi Handa committed
519 520 521 522 523 524 525 526
enum coding_category
  {
    coding_category_iso_7,
    coding_category_iso_7_tight,
    coding_category_iso_8_1,
    coding_category_iso_8_2,
    coding_category_iso_7_else,
    coding_category_iso_8_else,
Kenichi Handa's avatar
Kenichi Handa committed
527 528 529
    coding_category_utf_8_auto,
    coding_category_utf_8_nosig,
    coding_category_utf_8_sig,
Kenichi Handa's avatar
Kenichi Handa committed
530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552
    coding_category_utf_16_auto,
    coding_category_utf_16_be,
    coding_category_utf_16_le,
    coding_category_utf_16_be_nosig,
    coding_category_utf_16_le_nosig,
    coding_category_charset,
    coding_category_sjis,
    coding_category_big5,
    coding_category_ccl,
    coding_category_emacs_mule,
    /* All above are targets of code detection.  */
    coding_category_raw_text,
    coding_category_undecided,
    coding_category_max
  };

/* Definitions of flag bits used in detect_coding_XXXX.  */
#define CATEGORY_MASK_ISO_7		(1 << coding_category_iso_7)
#define CATEGORY_MASK_ISO_7_TIGHT	(1 << coding_category_iso_7_tight)
#define CATEGORY_MASK_ISO_8_1		(1 << coding_category_iso_8_1)
#define CATEGORY_MASK_ISO_8_2		(1 << coding_category_iso_8_2)
#define CATEGORY_MASK_ISO_7_ELSE	(1 << coding_category_iso_7_else)
#define CATEGORY_MASK_ISO_8_ELSE	(1 << coding_category_iso_8_else)
Kenichi Handa's avatar
Kenichi Handa committed
553 554 555
#define CATEGORY_MASK_UTF_8_AUTO	(1 << coding_category_utf_8_auto)
#define CATEGORY_MASK_UTF_8_NOSIG	(1 << coding_category_utf_8_nosig)
#define CATEGORY_MASK_UTF_8_SIG		(1 << coding_category_utf_8_sig)
556
#define CATEGORY_MASK_UTF_16_AUTO	(1 << coding_category_utf_16_auto)
Kenichi Handa's avatar
Kenichi Handa committed
557 558 559 560 561 562 563 564 565
#define CATEGORY_MASK_UTF_16_BE		(1 << coding_category_utf_16_be)
#define CATEGORY_MASK_UTF_16_LE		(1 << coding_category_utf_16_le)
#define CATEGORY_MASK_UTF_16_BE_NOSIG	(1 << coding_category_utf_16_be_nosig)
#define CATEGORY_MASK_UTF_16_LE_NOSIG	(1 << coding_category_utf_16_le_nosig)
#define CATEGORY_MASK_CHARSET		(1 << coding_category_charset)
#define CATEGORY_MASK_SJIS		(1 << coding_category_sjis)
#define CATEGORY_MASK_BIG5		(1 << coding_category_big5)
#define CATEGORY_MASK_CCL		(1 << coding_category_ccl)
#define CATEGORY_MASK_EMACS_MULE	(1 << coding_category_emacs_mule)
566
#define CATEGORY_MASK_RAW_TEXT		(1 << coding_category_raw_text)
Kenichi Handa's avatar
Kenichi Handa committed
567 568 569 570 571 572 573 574 575 576

/* This value is returned if detect_coding_mask () find nothing other
   than ASCII characters.  */
#define CATEGORY_MASK_ANY		\
  (CATEGORY_MASK_ISO_7			\
   | CATEGORY_MASK_ISO_7_TIGHT		\
   | CATEGORY_MASK_ISO_8_1		\
   | CATEGORY_MASK_ISO_8_2		\
   | CATEGORY_MASK_ISO_7_ELSE		\
   | CATEGORY_MASK_ISO_8_ELSE		\
Kenichi Handa's avatar
Kenichi Handa committed
577 578 579
   | CATEGORY_MASK_UTF_8_AUTO		\
   | CATEGORY_MASK_UTF_8_NOSIG		\
   | CATEGORY_MASK_UTF_8_SIG		\
580
   | CATEGORY_MASK_UTF_16_AUTO		\
Kenichi Handa's avatar
Kenichi Handa committed
581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612
   | CATEGORY_MASK_UTF_16_BE		\
   | CATEGORY_MASK_UTF_16_LE		\
   | CATEGORY_MASK_UTF_16_BE_NOSIG	\
   | CATEGORY_MASK_UTF_16_LE_NOSIG	\
   | CATEGORY_MASK_CHARSET		\
   | CATEGORY_MASK_SJIS			\
   | CATEGORY_MASK_BIG5			\
   | CATEGORY_MASK_CCL			\
   | CATEGORY_MASK_EMACS_MULE)


#define CATEGORY_MASK_ISO_7BIT \
  (CATEGORY_MASK_ISO_7 | CATEGORY_MASK_ISO_7_TIGHT)

#define CATEGORY_MASK_ISO_8BIT \
  (CATEGORY_MASK_ISO_8_1 | CATEGORY_MASK_ISO_8_2)

#define CATEGORY_MASK_ISO_ELSE \
  (CATEGORY_MASK_ISO_7_ELSE | CATEGORY_MASK_ISO_8_ELSE)

#define CATEGORY_MASK_ISO_ESCAPE	\
  (CATEGORY_MASK_ISO_7			\
   | CATEGORY_MASK_ISO_7_TIGHT		\
   | CATEGORY_MASK_ISO_7_ELSE		\
   | CATEGORY_MASK_ISO_8_ELSE)

#define CATEGORY_MASK_ISO	\
  (  CATEGORY_MASK_ISO_7BIT	\
     | CATEGORY_MASK_ISO_8BIT	\
     | CATEGORY_MASK_ISO_ELSE)

#define CATEGORY_MASK_UTF_16		\
613 614
  (CATEGORY_MASK_UTF_16_AUTO		\
   | CATEGORY_MASK_UTF_16_BE		\
Kenichi Handa's avatar
Kenichi Handa committed
615 616 617 618
   | CATEGORY_MASK_UTF_16_LE		\
   | CATEGORY_MASK_UTF_16_BE_NOSIG	\
   | CATEGORY_MASK_UTF_16_LE_NOSIG)

Kenichi Handa's avatar
Kenichi Handa committed
619 620 621 622
#define CATEGORY_MASK_UTF_8	\
  (CATEGORY_MASK_UTF_8_AUTO	\
   | CATEGORY_MASK_UTF_8_NOSIG	\
   | CATEGORY_MASK_UTF_8_SIG)
Kenichi Handa's avatar
Kenichi Handa committed
623 624

/* Table of coding categories (Lisp symbols).  This variable is for
Kenichi Handa's avatar
Kenichi Handa committed
625
   internal use only.  */
Kenichi Handa's avatar
Kenichi Handa committed
626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
static Lisp_Object Vcoding_category_table;

/* Table of coding-categories ordered by priority.  */
static enum coding_category coding_priorities[coding_category_max];

/* Nth element is a coding context for the coding system bound to the
   Nth coding category.  */
static struct coding_system coding_categories[coding_category_max];

/*** Commonly used macros and functions ***/

#ifndef min
#define min(a, b) ((a) < (b) ? (a) : (b))
#endif
#ifndef max
#define max(a, b) ((a) > (b) ? (a) : (b))
#endif
Karl Heuer's avatar
Karl Heuer committed
643

644 645 646 647
#define CODING_GET_INFO(coding, attrs, charset_list)	\
  do {							\
    (attrs) = CODING_ID_ATTRS ((coding)->id);		\
    (charset_list) = CODING_ATTR_CHARSET_LIST (attrs);	\
Kenichi Handa's avatar
Kenichi Handa committed
648
  } while (0)
Karl Heuer's avatar
Karl Heuer committed
649 650


Kenichi Handa's avatar
Kenichi Handa committed
651 652
/* Safely get one byte from the source text pointed by SRC which ends
   at SRC_END, and set C to that byte.  If there are not enough bytes
653 654 655 656 657
   in the source, it jumps to `no_more_source'.  If multibytep is
   nonzero, and a multibyte character is found at SRC, set C to the
   negative value of the character code.  The caller should declare
   and set these variables appropriately in advance:
	src, src_end, multibytep */
658

659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
#define ONE_MORE_BYTE(c)				\
  do {							\
    if (src == src_end)					\
      {							\
	if (src_base < src)				\
	  record_conversion_result			\
	    (coding, CODING_RESULT_INSUFFICIENT_SRC);	\
	goto no_more_source;				\
      }							\
    c = *src++;						\
    if (multibytep && (c & 0x80))			\
      {							\
	if ((c & 0xFE) == 0xC0)				\
	  c = ((c & 1) << 6) | *src++;			\
	else						\
	  {						\
675 676
	    src--;					\
	    c = - string_char (src, &src, NULL);	\
677 678 679 680 681
	    record_conversion_result			\
	      (coding, CODING_RESULT_INVALID_SRC);	\
	  }						\
      }							\
    consumed_chars++;					\
682 683
  } while (0)

Kenichi Handa's avatar
Kenichi Handa committed
684
/* Safely get two bytes from the source text pointed by SRC which ends
Kenichi Handa's avatar
Kenichi Handa committed
685 686 687 688 689 690
   at SRC_END, and set C1 and C2 to those bytes while skipping the
   heading multibyte characters.  If there are not enough bytes in the
   source, it jumps to `no_more_source'.  If multibytep is nonzero and
   a multibyte character is found for C2, set C2 to the negative value
   of the character code.  The caller should declare and set these
   variables appropriately in advance:
Kenichi Handa's avatar
Kenichi Handa committed
691 692 693
	src, src_end, multibytep
   It is intended that this macro is used in detect_coding_utf_16.  */

Kenichi Handa's avatar
Kenichi Handa committed
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720
#define TWO_MORE_BYTES(c1, c2)				\
  do {							\
    do {						\
      if (src == src_end)				\
	goto no_more_source;				\
      c1 = *src++;					\
      if (multibytep && (c1 & 0x80))			\
	{						\
	  if ((c1 & 0xFE) == 0xC0)			\
	    c1 = ((c1 & 1) << 6) | *src++;		\
	  else						\
	    {						\
	      src += BYTES_BY_CHAR_HEAD (c1) - 1;	\
	      c1 = -1;					\
	    }						\
	}						\
    } while (c1 < 0);					\
    if (src == src_end)					\
      goto no_more_source;				\
    c2 = *src++;					\
    if (multibytep && (c2 & 0x80))			\
      {							\
	if ((c2 & 0xFE) == 0xC0)			\
	  c2 = ((c2 & 1) << 6) | *src++;		\
	else						\
	  c2 = -1;					\
      }							\
Kenichi Handa's avatar
Kenichi Handa committed
721 722
  } while (0)

723

724 725 726 727 728 729 730 731 732
#define ONE_MORE_BYTE_NO_CHECK(c)			\
  do {							\
    c = *src++;						\
    if (multibytep && (c & 0x80))			\
      {							\
	if ((c & 0xFE) == 0xC0)				\
	  c = ((c & 1) << 6) | *src++;			\
	else						\
	  {						\
733 734
	    src--;					\
	    c = - string_char (src, &src, NULL);	\
735 736 737 738 739
	    record_conversion_result			\
	      (coding, CODING_RESULT_INVALID_SRC);	\
	  }						\
      }							\
    consumed_chars++;					\
740 741 742
  } while (0)


Kenichi Handa's avatar
Kenichi Handa committed
743 744 745 746 747
/* Store a byte C in the place pointed by DST and increment DST to the
   next free point, and increment PRODUCED_CHARS.  The caller should
   assure that C is 0..127, and declare and set the variable `dst'
   appropriately in advance.
*/
748 749


Kenichi Handa's avatar
Kenichi Handa committed
750 751 752 753
#define EMIT_ONE_ASCII_BYTE(c)	\
  do {				\
    produced_chars++;		\
    *dst++ = (c);		\
754
  } while (0)
755 756


Kenichi Handa's avatar
Kenichi Handa committed
757
/* Like EMIT_ONE_ASCII_BYTE but store two bytes; C1 and C2.  */
758

Kenichi Handa's avatar
Kenichi Handa committed
759 760 761 762 763
#define EMIT_TWO_ASCII_BYTES(c1, c2)	\
  do {					\
    produced_chars += 2;		\
    *dst++ = (c1), *dst++ = (c2);	\
  } while (0)
764 765


Kenichi Handa's avatar
Kenichi Handa committed
766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783
/* Store a byte C in the place pointed by DST and increment DST to the
   next free point, and increment PRODUCED_CHARS.  If MULTIBYTEP is
   nonzero, store in an appropriate multibyte from.  The caller should
   declare and set the variables `dst' and `multibytep' appropriately
   in advance.  */

#define EMIT_ONE_BYTE(c)		\
  do {					\
    produced_chars++;			\
    if (multibytep)			\
      {					\
	int ch = (c);			\
	if (ch >= 0x80)			\
	  ch = BYTE8_TO_CHAR (ch);	\
	CHAR_STRING_ADVANCE (ch, dst);	\
      }					\
    else				\
      *dst++ = (c);			\
784 785 786
  } while (0)


Kenichi Handa's avatar
Kenichi Handa committed
787
/* Like EMIT_ONE_BYTE, but emit two bytes; C1 and C2.  */
788

789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809
#define EMIT_TWO_BYTES(c1, c2)		\
  do {					\
    produced_chars += 2;		\
    if (multibytep)			\
      {					\
	int ch;				\
					\
	ch = (c1);			\
	if (ch >= 0x80)			\
	  ch = BYTE8_TO_CHAR (ch);	\
	CHAR_STRING_ADVANCE (ch, dst);	\
	ch = (c2);			\
	if (ch >= 0x80)			\
	  ch = BYTE8_TO_CHAR (ch);	\
	CHAR_STRING_ADVANCE (ch, dst);	\
      }					\
    else				\
      {					\
	*dst++ = (c1);			\
	*dst++ = (c2);			\
      }					\
810 811 812
  } while (0)


Kenichi Handa's avatar
Kenichi Handa committed
813 814 815 816 817
#define EMIT_THREE_BYTES(c1, c2, c3)	\
  do {					\
    EMIT_ONE_BYTE (c1);			\
    EMIT_TWO_BYTES (c2, c3);		\
  } while (0)
818 819


Kenichi Handa's avatar
Kenichi Handa committed
820 821 822 823 824
#define EMIT_FOUR_BYTES(c1, c2, c3, c4)		\
  do {						\
    EMIT_TWO_BYTES (c1, c2);			\
    EMIT_TWO_BYTES (c3, c4);			\
  } while (0)
825 826


827
/* Prototypes for static functions.  */
828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901
static void record_conversion_result (struct coding_system *coding,
                                      enum coding_result_code result);
static int detect_coding_utf_8 (struct coding_system *,
                                struct coding_detection_info *info);
static void decode_coding_utf_8 (struct coding_system *);
static int encode_coding_utf_8 (struct coding_system *);

static int detect_coding_utf_16 (struct coding_system *,
                                 struct coding_detection_info *info);
static void decode_coding_utf_16 (struct coding_system *);
static int encode_coding_utf_16 (struct coding_system *);

static int detect_coding_iso_2022 (struct coding_system *,
                                   struct coding_detection_info *info);
static void decode_coding_iso_2022 (struct coding_system *);
static int encode_coding_iso_2022 (struct coding_system *);

static int detect_coding_emacs_mule (struct coding_system *,
                                     struct coding_detection_info *info);
static void decode_coding_emacs_mule (struct coding_system *);
static int encode_coding_emacs_mule (struct coding_system *);

static int detect_coding_sjis (struct coding_system *,
                               struct coding_detection_info *info);
static void decode_coding_sjis (struct coding_system *);
static int encode_coding_sjis (struct coding_system *);

static int detect_coding_big5 (struct coding_system *,
                               struct coding_detection_info *info);
static void decode_coding_big5 (struct coding_system *);
static int encode_coding_big5 (struct coding_system *);

static int detect_coding_ccl (struct coding_system *,
                              struct coding_detection_info *info);
static void decode_coding_ccl (struct coding_system *);
static int encode_coding_ccl (struct coding_system *);

static void decode_coding_raw_text (struct coding_system *);
static int encode_coding_raw_text (struct coding_system *);

static void coding_set_source (struct coding_system *);
static void coding_set_destination (struct coding_system *);
static void coding_alloc_by_realloc (struct coding_system *, EMACS_INT);
static void coding_alloc_by_making_gap (struct coding_system *,
                                        EMACS_INT, EMACS_INT);
static unsigned char *alloc_destination (struct coding_system *,
                                         EMACS_INT, unsigned char *);
static void setup_iso_safe_charsets (Lisp_Object);
static unsigned char *encode_designation_at_bol (struct coding_system *,
                                                 int *, int *,
                                                 unsigned char *);
static int detect_eol (const unsigned char *,
                       EMACS_INT, enum coding_category);
static Lisp_Object adjust_coding_eol_type (struct coding_system *, int);
static void decode_eol (struct coding_system *);
static Lisp_Object get_translation_table (Lisp_Object, int, int *);
static Lisp_Object get_translation (Lisp_Object, int *, int *);
static int produce_chars (struct coding_system *, Lisp_Object, int);
static INLINE void produce_charset (struct coding_system *, int *,
                                    EMACS_INT);
static void produce_annotation (struct coding_system *, EMACS_INT);
static int decode_coding (struct coding_system *);
static INLINE int *handle_composition_annotation (EMACS_INT, EMACS_INT,
                                                  struct coding_system *,
                                                  int *, EMACS_INT *);
static INLINE int *handle_charset_annotation (EMACS_INT, EMACS_INT,
                                              struct coding_system *,
                                              int *, EMACS_INT *);
static void consume_chars (struct coding_system *, Lisp_Object, int);
static int encode_coding (struct coding_system *);
static Lisp_Object make_conversion_work_buffer (int);
static Lisp_Object code_conversion_restore (Lisp_Object);
static INLINE int char_encodable_p (int, Lisp_Object);
static Lisp_Object make_subsidiaries (Lisp_Object);
902

903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924
static void
record_conversion_result (struct coding_system *coding,
			  enum coding_result_code result)
{
  coding->result = result;
  switch (result)
    {
    case CODING_RESULT_INSUFFICIENT_SRC:
      Vlast_code_conversion_error = Qinsufficient_source;
      break;
    case CODING_RESULT_INCONSISTENT_EOL:
      Vlast_code_conversion_error = Qinconsistent_eol;
      break;
    case CODING_RESULT_INVALID_SRC:
      Vlast_code_conversion_error = Qinvalid_source;
      break;
    case CODING_RESULT_INTERRUPT:
      Vlast_code_conversion_error = Qinterrupted;
      break;
    case CODING_RESULT_INSUFFICIENT_MEM:
      Vlast_code_conversion_error = Qinsufficient_memory;
      break;
925 926 927 928 929
    case CODING_RESULT_INSUFFICIENT_DST:
      /* Don't record this error in Vlast_code_conversion_error
	 because it happens just temporarily and is resolved when the
	 whole conversion is finished.  */
      break;
930 931
    case CODING_RESULT_SUCCESS:
      break;
932 933
    default:
      Vlast_code_conversion_error = intern ("Unknown error");
934 935 936
    }
}

937 938 939 940
/* This wrapper macro is used to preserve validity of pointers into
   buffer text across calls to decode_char, which could cause
   relocation of buffers if it loads a charset map, because loading a
   charset map allocates large structures.  */
Kenichi Handa's avatar
Kenichi Handa committed
941 942 943 944 945 946
#define CODING_DECODE_CHAR(coding, src, src_base, src_end, charset, code, c) \
  do {									     \
    charset_map_loaded = 0;						     \
    c = DECODE_CHAR (charset, code);					     \
    if (charset_map_loaded)						     \
      {									     \
Kenichi Handa's avatar
Kenichi Handa committed
947
	const unsigned char *orig = coding->source;			     \
Kenichi Handa's avatar
Kenichi Handa committed
948 949 950 951 952 953 954 955
	EMACS_INT offset;						     \
									     \
	coding_set_source (coding);					     \
	offset = coding->source - orig;					     \
	src += offset;							     \
	src_base += offset;						     \
	src_end += offset;						     \
      }									     \
956 957 958
  } while (0)


959 960 961 962 963
/* If there are at least BYTES length of room at dst, allocate memory
   for coding->destination and update dst and dst_end.  We don't have
   to take care of coding->source which will be relocated.  It is
   handled by calling coding_set_source in encode_coding.  */

Kenichi Handa's avatar
Kenichi Handa committed
964 965 966 967 968 969 970 971 972 973
#define ASSURE_DESTINATION(bytes)				\
  do {								\
    if (dst + (bytes) >= dst_end)				\
      {								\
	int more_bytes = charbuf_end - charbuf + (bytes);	\
								\
	dst = alloc_destination (coding, more_bytes, dst);	\
	dst_end = coding->destination + coding->dst_bytes;	\
      }								\
  } while (0)
974 975


Kenichi Handa's avatar
Kenichi Handa committed
976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035
/* Store multibyte form of the character C in P, and advance P to the
   end of the multibyte form.  This is like CHAR_STRING_ADVANCE but it
   never calls MAYBE_UNIFY_CHAR.  */

#define CHAR_STRING_ADVANCE_NO_UNIFY(c, p)	\
  do {						\
    if ((c) <= MAX_1_BYTE_CHAR)			\
      *(p)++ = (c);				\
    else if ((c) <= MAX_2_BYTE_CHAR)		\
      *(p)++ = (0xC0 | ((c) >> 6)),		\
	*(p)++ = (0x80 | ((c) & 0x3F));		\
    else if ((c) <= MAX_3_BYTE_CHAR)		\
      *(p)++ = (0xE0 | ((c) >> 12)),		\
	*(p)++ = (0x80 | (((c) >> 6) & 0x3F)),	\
	*(p)++ = (0x80 | ((c) & 0x3F));		\
    else if ((c) <= MAX_4_BYTE_CHAR)		\
      *(p)++ = (0xF0 | (c >> 18)),		\
	*(p)++ = (0x80 | ((c >> 12) & 0x3F)),	\
	*(p)++ = (0x80 | ((c >> 6) & 0x3F)),	\
	*(p)++ = (0x80 | (c & 0x3F));		\
    else if ((c) <= MAX_5_BYTE_CHAR)		\
      *(p)++ = 0xF8,				\
	*(p)++ = (0x80 | ((c >> 18) & 0x0F)),	\
	*(p)++ = (0x80 | ((c >> 12) & 0x3F)),	\
	*(p)++ = (0x80 | ((c >> 6) & 0x3F)),	\
	*(p)++ = (0x80 | (c & 0x3F));		\
    else					\
      (p) += BYTE8_STRING ((c) - 0x3FFF80, p);	\
  } while (0)


/* Return the character code of character whose multibyte form is at
   P, and advance P to the end of the multibyte form.  This is like
   STRING_CHAR_ADVANCE, but it never calls MAYBE_UNIFY_CHAR.  */

#define STRING_CHAR_ADVANCE_NO_UNIFY(p)				\
  (!((p)[0] & 0x80)						\
   ? *(p)++							\
   : ! ((p)[0] & 0x20)						\
   ? ((p) += 2,							\
      ((((p)[-2] & 0x1F) << 6)					\
       | ((p)[-1] & 0x3F)					\
       | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0)))	\
   : ! ((p)[0] & 0x10)						\
   ? ((p) += 3,							\
      ((((p)[-3] & 0x0F) << 12)					\
       | (((p)[-2] & 0x3F) << 6)				\
       | ((p)[-1] & 0x3F)))					\
   : ! ((p)[0] & 0x08)						\
   ? ((p) += 4,							\
      ((((p)[-4] & 0xF) << 18)					\
       | (((p)[-3] & 0x3F) << 12)				\
       | (((p)[-2] & 0x3F) << 6)				\
       | ((p)[-1] & 0x3F)))					\
   : ((p) += 5,							\
      ((((p)[-4] & 0x3F) << 18)					\
       | (((p)[-3] & 0x3F) << 12)				\
       | (((p)[-2] & 0x3F) << 6)				\
       | ((p)[-1] & 0x3F))))

1036

Kenichi Handa's avatar
Kenichi Handa committed
1037
static void
1038
coding_set_source (struct coding_system *coding)
1039
{
Kenichi Handa's avatar
Kenichi Handa committed
1040 1041
  if (BUFFERP (coding->src_object))
    {
1042
      struct buffer *buf = XBUFFER (coding->src_object);
1043

Kenichi Handa's avatar
Kenichi Handa committed
1044
      if (coding->src_pos < 0)
1045
	coding->source = BUF_GAP_END_ADDR (buf) + coding->src_pos_byte;
Kenichi Handa's avatar
Kenichi Handa committed
1046
      else
1047
	coding->source = BUF_BYTE_ADDRESS (buf, coding->src_pos_byte);
1048
    }
Kenichi Handa's avatar
Kenichi Handa committed
1049
  else if (STRINGP (coding->src_object))
1050
    {
Kenichi Handa's avatar
Kenichi Handa committed
1051
      coding->source = SDATA (coding->src_object) + coding->src_pos_byte;
1052
    }
Kenichi Handa's avatar
Kenichi Handa committed
1053 1054 1055 1056 1057
  else
    /* Otherwise, the source is C string and is never relocated
       automatically.  Thus we don't have to update anything.  */
    ;
}
1058

Kenichi Handa's avatar
Kenichi Handa committed
1059
static void
1060
coding_set_destination (struct coding_system *coding)
Kenichi Handa's avatar
Kenichi Handa committed
1061 1062
{
  if (BUFFERP (coding->dst_object))
1063
    {
Kenichi Handa's avatar
Kenichi Handa committed
1064
      if (coding->src_pos < 0)
1065
	{
1066
	  coding->destination = BEG_ADDR + coding->dst_pos_byte - BEG_BYTE;
1067 1068 1069
	  coding->dst_bytes = (GAP_END_ADDR
			       - (coding->src_bytes - coding->consumed)
			       - coding->destination);
1070
	}
Kenichi Handa's avatar
Kenichi Handa committed
1071
      else
1072 1073 1074 1075
	{
	  /* We are sure that coding->dst_pos_byte is before the gap
	     of the buffer. */
	  coding->destination = (BUF_BEG_ADDR (XBUFFER (coding->dst_object))
1076
				 + coding->dst_pos_byte - BEG_BYTE);
1077 1078 1079
	  coding->dst_bytes = (BUF_GAP_END_ADDR (XBUFFER (coding->dst_object))
			       - coding->destination);
	}
Kenichi Handa's avatar
Kenichi Handa committed
1080 1081 1082 1083 1084 1085 1086 1087 1088
    }
  else
    /* Otherwise, the destination is C string and is never relocated
       automatically.  Thus we don't have to update anything.  */
    ;
}


static void
1089
coding_alloc_by_realloc (struct coding_system *coding, EMACS_INT bytes)
Kenichi Handa's avatar
Kenichi Handa committed
1090 1091 1092 1093 1094 1095 1096
{
  coding->destination = (unsigned char *) xrealloc (coding->destination,
						    coding->dst_bytes + bytes);
  coding->dst_bytes += bytes;
}

static void
1097 1098
coding_alloc_by_making_gap (struct coding_system *coding,
			    EMACS_INT gap_head_used, EMACS_INT bytes)
Kenichi Handa's avatar
Kenichi Handa committed
1099
{
Kenichi Handa's avatar
Kenichi Handa committed
1100
  if (EQ (coding->src_object, coding->dst_object))
Kenichi Handa's avatar
Kenichi Handa committed
1101
    {
Kenichi Handa's avatar
Kenichi Handa committed
1102 1103 1104 1105 1106 1107 1108 1109
      /* The gap may contain the produced data at the head and not-yet
	 consumed data at the tail.  To preserve those data, we at
	 first make the gap size to zero, then increase the gap
	 size.  */
      EMACS_INT add = GAP_SIZE;

      GPT += gap_head_used, GPT_BYTE += gap_head_used;
      GAP_SIZE = 0; ZV += add; Z += add; ZV_BYTE += add; Z_BYTE += add;
Kenichi Handa's avatar
Kenichi Handa committed
1110 1111
      make_gap (bytes);
      GAP_SIZE += add; ZV -= add; Z -= add; ZV_BYTE -= add; Z_BYTE -= add;
Kenichi Handa's avatar
Kenichi Handa committed
1112
      GPT -= gap_head_used, GPT_BYTE -= gap_head_used;
Kenichi Handa's avatar
Kenichi Handa committed
1113
    }
1114
  else
Kenichi Handa's avatar
Kenichi Handa committed
1115
    {
1116 1117 1118
      Lisp_Object this_buffer;

      this_buffer = Fcurrent_buffer ();
Kenichi Handa's avatar
Kenichi Handa committed
1119 1120 1121
      set_buffer_internal (XBUFFER (coding->dst_object));
      make_gap (bytes);
      set_buffer_internal (XBUFFER (this_buffer));
1122
    }
Kenichi Handa's avatar
Kenichi Handa committed
1123
}
Kenichi Handa's avatar
Kenichi Handa committed
1124

Kenichi Handa's avatar
Kenichi Handa committed
1125 1126

static unsigned char *
1127 1128
alloc_destination (struct coding_system *coding, EMACS_INT nbytes,
		   unsigned char *dst)
Kenichi Handa's avatar
Kenichi Handa committed
1129 1130 1131 1132
{
  EMACS_INT offset = dst - coding->destination;

  if (BUFFERP (coding->dst_object))
Kenichi Handa's avatar
Kenichi Handa committed
1133 1134 1135 1136 1137
    {
      struct buffer *buf = XBUFFER (coding->dst_object);

      coding_alloc_by_making_gap (coding, dst - BUF_GPT_ADDR (buf), nbytes);
    }
1138
  else
Kenichi Handa's avatar
Kenichi Handa committed
1139 1140 1141 1142 1143
    coding_alloc_by_realloc (coding, nbytes);
  coding_set_destination (coding);
  dst = coding->destination + offset;
  return dst;
}
1144

1145 1146 1147 1148
/** Macros for annotations.  */

/* An annotation data is stored in the array coding->charbuf in this
   format:
1149
     [ -LENGTH ANNOTATION_MASK NCHARS ... ]
1150 1151
   LENGTH is the number of elements in the annotation.
   ANNOTATION_MASK is one of CODING_ANNOTATE_XXX_MASK.
1152
   NCHARS is the number of characters in the text annotated.
1153 1154 1155 1156 1157

   The format of the following elements depend on ANNOTATION_MASK.

   In the case of CODING_ANNOTATE_COMPOSITION_MASK, these elements
   follows:
1158 1159 1160 1161 1162 1163
     ... NBYTES METHOD [ COMPOSITION-COMPONENTS ... ]

   NBYTES is the number of bytes specified in the header part of
   old-style emacs-mule encoding, or 0 for the other kind of
   composition.

1164
   METHOD is one of enum composition_method.
1165

Kenichi Handa's avatar
Kenichi Handa committed
1166
   Optional COMPOSITION-COMPONENTS are characters and composition
1167 1168 1169
   rules.

   In the case of CODING_ANNOTATE_CHARSET_MASK, one element CHARSET-ID
1170 1171 1172 1173 1174 1175 1176 1177
   follows.

   If ANNOTATION_MASK is 0, this annotation is just a space holder to
   recover from an invalid annotation, and should be skipped by
   produce_annotation.  */

/* Maximum length of the header of annotation data.  */
#define MAX_ANNOTATION_LENGTH 5
1178

1179
#define ADD_ANNOTATION_DATA(buf, len, mask, nchars)	\
1180 1181 1182
  do {							\
    *(buf)++ = -(len);					\
    *(buf)++ = (mask);					\
1183
    *(buf)++ = (nchars);				\
1184 1185 1186
    coding->annotated = 1;				\
  } while (0);

1187
#define ADD_COMPOSITION_DATA(buf, nchars, nbytes, method)		    \
1188
  do {									    \
1189 1190
    ADD_ANNOTATION_DATA (buf, 5, CODING_ANNOTATE_COMPOSITION_MASK, nchars); \
    *buf++ = nbytes;							    \
1191
    *buf++ = method;							    \
1192 1193 1194
  } while (0)


1195 1196 1197 1198
#define ADD_CHARSET_DATA(buf, nchars, id)				\
  do {									\
    ADD_ANNOTATION_DATA (buf, 4, CODING_ANNOTATE_CHARSET_MASK, nchars);	\
    *buf++ = id;							\
1199 1200
  } while (0)

Kenichi Handa's avatar
Kenichi Handa committed
1201 1202 1203 1204 1205 1206 1207 1208 1209

/*** 2. Emacs' internal format (emacs-utf-8) ***/




/*** 3. UTF-8 ***/

/* See the above "GENERAL NOTES on `detect_coding_XXX ()' functions".
1210 1211
   Check if a text is encoded in UTF-8.  If it is, return 1, else
   return 0.  */
Kenichi Handa's avatar
Kenichi Handa committed
1212 1213 1214 1215 1216 1217 1218 1219

#define UTF_8_1_OCTET_P(c)         ((c) < 0x80)
#define UTF_8_EXTRA_OCTET_P(c)     (((c) & 0xC0) == 0x80)
#define UTF_8_2_OCTET_LEADING_P(c) (((c) & 0xE0) == 0xC0)
#define UTF_8_3_OCTET_LEADING_P(c) (((c) & 0xF0) == 0xE0)
#define UTF_8_4_OCTET_LEADING_P(c) (((c) & 0xF8) == 0xF0)
#define UTF_8_5_OCTET_LEADING_P(c) (((c) & 0xFC) == 0xF8)

Kenichi Handa's avatar
Kenichi Handa committed
1220 1221 1222 1223 1224
#define UTF_BOM 0xFEFF
#define UTF_8_BOM_1 0xEF
#define UTF_8_BOM_2 0xBB
#define UTF_8_BOM_3 0xBF

Kenichi Handa's avatar
Kenichi Handa committed
1225
static int
1226 1227
detect_coding_utf_8 (struct coding_system *coding,
		     struct coding_detection_info *detect_info)
Kenichi Handa's avatar
Kenichi Handa committed
1228
{
1229
  const unsigned char *src = coding->source, *src_base;
Kenichi Handa's avatar
Kenichi Handa committed
1230
  const unsigned char *src_end = coding->source + coding->src_bytes;
Kenichi Handa's avatar
Kenichi Handa committed
1231 1232
  int multibytep = coding->src_multibyte;
  int consumed_chars = 0;
Kenichi Handa's avatar
Kenichi Handa committed
1233
  int bom_found = 0;
Kenichi Handa's avatar
Kenichi Handa committed
1234 1235
  int found = 0;

1236
  detect_info->checked |= CATEGORY_MASK_UTF_8;
Kenichi Handa's avatar
Kenichi Handa committed
1237 1238 1239 1240
  /* A coding system of this category is always ASCII compatible.  */
  src += coding->head_ascii;

  while (1)
1241
    {
Kenichi Handa's avatar
Kenichi Handa committed
1242
      int c, c1, c2, c3, c4;
1243

1244
      src_base = src;
Kenichi Handa's avatar
Kenichi Handa committed
1245
      ONE_MORE_BYTE (c);
1246
      if (c < 0 || UTF_8_1_OCTET_P (c))
Kenichi Handa's avatar
Kenichi Handa committed
1247 1248
	continue;
      ONE_MORE_BYTE (c1);
1249
      if (c1 < 0 || ! UTF_8_EXTRA_OCTET_P (c1))
Kenichi Handa's avatar
Kenichi Handa committed
1250 1251
	break;
      if (UTF_8_2_OCTET_LEADING_P (c))
1252
	{
Kenichi Handa's avatar
Kenichi Handa committed
1253
	  found = 1;
Kenichi Handa's avatar
Kenichi Handa committed
1254
	  continue;
1255
	}
Kenichi Handa's avatar
Kenichi Handa committed
1256
      ONE_MORE_BYTE (c2);
1257
      if (c2 < 0 || ! UTF_8_EXTRA_OCTET_P (c2))
Kenichi Handa's avatar
Kenichi Handa committed
1258 1259
	break;
      if (UTF_8_3_OCTET_LEADING_P (c))
1260
	{
Kenichi Handa's avatar
Kenichi Handa committed
1261 1262 1263 1264
	  found = 1;
	  if (src_base == coding->source
	      && c == UTF_8_BOM_1 && c1 == UTF_8_BOM_2 && c2 == UTF_8_BOM_3)
	    bom_found = 1;
Kenichi Handa's avatar
Kenichi Handa committed
1265
	  continue;
1266
	}
Kenichi Handa's avatar
Kenichi Handa committed
1267
      ONE_MORE_BYTE (c3);
1268
      if (c3 < 0 || ! UTF_8_EXTRA_OCTET_P (c3))
Kenichi Handa's avatar
Kenichi Handa committed
1269 1270
	break;
      if (UTF_8_4_OCTET_LEADING_P (c))
1271
	{
Kenichi Handa's avatar
Kenichi Handa committed
1272
	  found = 1;
Kenichi Handa's avatar
Kenichi Handa committed
1273 1274 1275
	  continue;
	}
      ONE_MORE_BYTE (c4);
1276
      if (c4 < 0 || ! UTF_8_EXTRA_OCTET_P (c4))
Kenichi Handa's avatar
Kenichi Handa committed
1277 1278 1279
	break;
      if (UTF_8_5_OCTET_LEADING_P (c))
	{
Kenichi Handa's avatar
Kenichi Handa committed
1280
	  found = 1;
Kenichi Handa's avatar
Kenichi Handa committed
1281 1282 1283
	  continue;
	}
      break;
1284
    }
1285
  detect_info->rejected |= CATEGORY_MASK_UTF_8;
Kenichi Handa's avatar
Kenichi Handa committed
1286
  return 0;
1287

Kenichi Handa's avatar
Kenichi Handa committed
1288
 no_more_source:
1289
  if (src_base < src && coding->mode & CODING_MODE_LAST_BLOCK)
1290
    {
1291
      detect_info->rejected |= CATEGORY_MASK_UTF_8;
1292
      return 0;
1293
    }
Kenichi Handa's avatar
Kenichi Handa committed
1294 1295 1296 1297 1298 1299 1300 1301
  if (bom_found)
    {
      /* The first character 0xFFFE doesn't necessarily mean a BOM.  */
      detect_info->found |= CATEGORY_MASK_UTF_8_SIG | CATEGORY_MASK_UTF_8_NOSIG;
    }
  else
    {
      detect_info->rejected |= CATEGORY_MASK_UTF_8_SIG;
1302 1303
      if (found)
	detect_info->found |= CATEGORY_MASK_UTF_8_NOSIG;
Kenichi Handa's avatar
Kenichi Handa committed
1304
    }
1305
  return 1;
1306 1307
}

Karl Heuer's avatar
Karl Heuer committed
1308

1309
static void
1310
decode_coding_utf_8 (struct coding_system *coding)
1311
{
Kenichi Handa's avatar
Kenichi Handa committed
1312 1313 1314
  const unsigned char *src = coding->source + coding->consumed;
  const unsigned char *src_end = coding->source + coding->src_bytes;
  const unsigned char *src_base;
1315 1316
  int *charbuf = coding->charbuf + coding->charbuf_used;
  int *charbuf_end = coding->charbuf + coding->charbuf_size;
1317
  int consumed_chars = 0, consumed_chars_base = 0;
Kenichi Handa's avatar
Kenichi Handa committed
1318
  int multibytep = coding->src_multibyte;
Kenichi Handa's avatar
Kenichi Handa committed
1319
  enum utf_bom_type bom = CODING_UTF_8_BOM (coding);
1320
  Lisp_Object attr, charset_list;
1321 1322
  int eol_crlf =
    !inhibit_eol_conversion && EQ (CODING_ID_EOL_TYPE (coding->id), Qdos);
1323
  int byte_after_cr = -1;
Karl Heuer's avatar
Karl Heuer committed