1 /* Header for code conversion stuff
2 Copyright (C) 1991, 1995 Free Software Foundation, Inc.
3 Copyright (C) 1995 Sun Microsystems, Inc.
4 Copyright (C) 1999,2000,2002,2005 MORIOKA Tomohiko
6 This file is part of XEmacs.
8 XEmacs is free software; you can redistribute it and/or modify it
9 under the terms of the GNU General Public License as published by the
10 Free Software Foundation; either version 2, or (at your option) any
13 XEmacs is distributed in the hope that it will be useful, but WITHOUT
14 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
15 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
18 You should have received a copy of the GNU General Public License
19 along with XEmacs; see the file COPYING. If not, write to
20 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
21 Boston, MA 02111-1307, USA. */
23 /* Synched up with: Mule 2.3. Not in FSF. */
25 /* 91.10.09 written by K.Handa <handa@etl.go.jp> */
26 /* Rewritten by Ben Wing <ben@xemacs.org>. */
28 #ifndef INCLUDED_file_coding_h_
29 #define INCLUDED_file_coding_h_
31 struct decoding_stream;
32 struct encoding_stream;
34 /* Coding system types. These go into the TYPE field of a
35 Lisp_Coding_System. */
37 enum coding_system_type
39 CODESYS_AUTODETECT, /* Automatic conversion. */
41 CODESYS_SHIFT_JIS, /* Shift-JIS; Hankaku (half-width) KANA
43 CODESYS_ISO2022, /* Any ISO2022-compliant coding system.
44 Includes JIS, EUC, CTEXT */
45 CODESYS_BIG5, /* BIG5 (used for Taiwanese). */
46 CODESYS_UCS4, /* ISO 10646 UCS-4 */
47 CODESYS_UTF8, /* ISO 10646 UTF-8 */
49 CODESYS_UTF16, /* ISO 10646 UTF-16 */
51 CODESYS_CCL, /* Converter written in CCL. */
53 CODESYS_NO_CONVERSION /* "No conversion"; used for binary files.
54 We use quotes because there really
55 is some conversion being applied,
56 but it appears to the user as if
57 the text is read in without conversion. */
59 ,CODESYS_INTERNAL /* Raw (internally-formatted) data. */
70 typedef enum eol_type eol_type_t;
73 typedef struct charset_conversion_spec charset_conversion_spec;
74 struct charset_conversion_spec
76 Lisp_Object from_charset;
77 Lisp_Object to_charset;
82 Dynarr_declare (charset_conversion_spec);
83 } charset_conversion_spec_dynarr;
86 struct Lisp_Coding_System
88 struct lcrecord_header header;
90 /* Name and doc string of this coding system. */
92 Lisp_Object doc_string;
94 /* This is the major type of the coding system -- one of Big5, ISO2022,
95 Shift-JIS, etc. See the constants above. */
96 enum coding_system_type type;
98 /* Mnemonic string displayed in the modeline when this coding
99 system is active for a particular buffer. */
100 Lisp_Object mnemonic;
102 Lisp_Object post_read_conversion;
103 Lisp_Object pre_write_conversion;
107 /* Subsidiary coding systems that specify a particular type of EOL
108 marking, rather than autodetecting it. These will only be non-nil
109 if (eol_type == EOL_AUTODETECT). */
111 Lisp_Object eol_crlf;
116 /* What are the charsets to be initially designated to G0, G1,
117 G2, G3? If t, no charset is initially designated. If nil,
118 no charset is initially designated and no charset is allowed
120 Lisp_Object initial_charset[4];
122 /* If true, a designation escape sequence needs to be sent on output
123 for the charset in G[0-3] before that charset is used. */
124 unsigned char force_charset_on_output[4];
126 charset_conversion_spec_dynarr *input_conv;
127 charset_conversion_spec_dynarr *output_conv;
129 unsigned int shoort :1; /* C makes you speak Dutch */
130 unsigned int no_ascii_eol :1;
131 unsigned int no_ascii_cntl :1;
132 unsigned int seven :1;
133 unsigned int lock_shift :1;
134 unsigned int no_iso6429 :1;
135 unsigned int escape_quoted :1;
139 /* For a CCL coding system, these specify the CCL programs used for
140 decoding (input) and encoding (output). */
146 unsigned int disable_composition :1;
147 unsigned int use_entity_reference :1;
148 Lisp_Object ccs_priority_list;
151 typedef struct Lisp_Coding_System Lisp_Coding_System;
153 DECLARE_LRECORD (coding_system, Lisp_Coding_System);
154 #define XCODING_SYSTEM(x) XRECORD (x, coding_system, Lisp_Coding_System)
155 #define XSETCODING_SYSTEM(x, p) XSETRECORD (x, p, coding_system)
156 #define CODING_SYSTEMP(x) RECORDP (x, coding_system)
157 #define CHECK_CODING_SYSTEM(x) CHECK_RECORD (x, coding_system)
158 #define CONCHECK_CODING_SYSTEM(x) CONCHECK_RECORD (x, coding_system)
160 #define CODING_SYSTEM_NAME(codesys) ((codesys)->name)
161 #define CODING_SYSTEM_DOC_STRING(codesys) ((codesys)->doc_string)
162 #define CODING_SYSTEM_TYPE(codesys) ((codesys)->type)
163 #define CODING_SYSTEM_MNEMONIC(codesys) ((codesys)->mnemonic)
164 #define CODING_SYSTEM_POST_READ_CONVERSION(codesys) \
165 ((codesys)->post_read_conversion)
166 #define CODING_SYSTEM_PRE_WRITE_CONVERSION(codesys) \
167 ((codesys)->pre_write_conversion)
168 #define CODING_SYSTEM_EOL_TYPE(codesys) ((codesys)->eol_type)
169 #define CODING_SYSTEM_EOL_LF(codesys) ((codesys)->eol_lf)
170 #define CODING_SYSTEM_EOL_CRLF(codesys) ((codesys)->eol_crlf)
171 #define CODING_SYSTEM_EOL_CR(codesys) ((codesys)->eol_cr)
174 #define CODING_SYSTEM_ISO2022_INITIAL_CHARSET(codesys, g) \
175 ((codesys)->iso2022.initial_charset[g])
176 #define CODING_SYSTEM_ISO2022_FORCE_CHARSET_ON_OUTPUT(codesys, g) \
177 ((codesys)->iso2022.force_charset_on_output[g])
178 #define CODING_SYSTEM_ISO2022_SHORT(codesys) ((codesys)->iso2022.shoort)
179 #define CODING_SYSTEM_ISO2022_NO_ASCII_EOL(codesys) \
180 ((codesys)->iso2022.no_ascii_eol)
181 #define CODING_SYSTEM_ISO2022_NO_ASCII_CNTL(codesys) \
182 ((codesys)->iso2022.no_ascii_cntl)
183 #define CODING_SYSTEM_ISO2022_SEVEN(codesys) ((codesys)->iso2022.seven)
184 #define CODING_SYSTEM_ISO2022_LOCK_SHIFT(codesys) \
185 ((codesys)->iso2022.lock_shift)
186 #define CODING_SYSTEM_ISO2022_NO_ISO6429(codesys) \
187 ((codesys)->iso2022.no_iso6429)
188 #define CODING_SYSTEM_ISO2022_ESCAPE_QUOTED(codesys) \
189 ((codesys)->iso2022.escape_quoted)
190 #define CODING_SYSTEM_CCL_DECODE(codesys) ((codesys)->ccl.decode)
191 #define CODING_SYSTEM_CCL_ENCODE(codesys) ((codesys)->ccl.encode)
194 #define CODING_SYSTEM_DISABLE_COMPOSITION(codesys) \
195 ((codesys)->disable_composition)
196 #define CODING_SYSTEM_USE_ENTITY_REFERENCE(codesys) \
197 ((codesys)->use_entity_reference)
198 #define CODING_SYSTEM_CCS_PRIORITY_LIST(codesys) \
199 ((codesys)->ccs_priority_list)
202 #define XCODING_SYSTEM_NAME(codesys) \
203 CODING_SYSTEM_NAME (XCODING_SYSTEM (codesys))
204 #define XCODING_SYSTEM_DOC_STRING(codesys) \
205 CODING_SYSTEM_DOC_STRING (XCODING_SYSTEM (codesys))
206 #define XCODING_SYSTEM_TYPE(codesys) \
207 CODING_SYSTEM_TYPE (XCODING_SYSTEM (codesys))
208 #define XCODING_SYSTEM_MNEMONIC(codesys) \
209 CODING_SYSTEM_MNEMONIC (XCODING_SYSTEM (codesys))
210 #define XCODING_SYSTEM_POST_READ_CONVERSION(codesys) \
211 CODING_SYSTEM_POST_READ_CONVERSION (XCODING_SYSTEM (codesys))
212 #define XCODING_SYSTEM_PRE_WRITE_CONVERSION(codesys) \
213 CODING_SYSTEM_PRE_WRITE_CONVERSION (XCODING_SYSTEM (codesys))
214 #define XCODING_SYSTEM_EOL_TYPE(codesys) \
215 CODING_SYSTEM_EOL_TYPE (XCODING_SYSTEM (codesys))
216 #define XCODING_SYSTEM_EOL_LF(codesys) \
217 CODING_SYSTEM_EOL_LF (XCODING_SYSTEM (codesys))
218 #define XCODING_SYSTEM_EOL_CRLF(codesys) \
219 CODING_SYSTEM_EOL_CRLF (XCODING_SYSTEM (codesys))
220 #define XCODING_SYSTEM_EOL_CR(codesys) \
221 CODING_SYSTEM_EOL_CR (XCODING_SYSTEM (codesys))
224 #define XCODING_SYSTEM_ISO2022_INITIAL_CHARSET(codesys, g) \
225 CODING_SYSTEM_ISO2022_INITIAL_CHARSET (XCODING_SYSTEM (codesys), g)
226 #define XCODING_SYSTEM_ISO2022_FORCE_CHARSET_ON_OUTPUT(codesys, g) \
227 CODING_SYSTEM_ISO2022_FORCE_CHARSET_ON_OUTPUT (XCODING_SYSTEM (codesys), g)
228 #define XCODING_SYSTEM_ISO2022_SHORT(codesys) \
229 CODING_SYSTEM_ISO2022_SHORT (XCODING_SYSTEM (codesys))
230 #define XCODING_SYSTEM_ISO2022_NO_ASCII_EOL(codesys) \
231 CODING_SYSTEM_ISO2022_NO_ASCII_EOL (XCODING_SYSTEM (codesys))
232 #define XCODING_SYSTEM_ISO2022_NO_ASCII_CNTL(codesys) \
233 CODING_SYSTEM_ISO2022_NO_ASCII_CNTL (XCODING_SYSTEM (codesys))
234 #define XCODING_SYSTEM_ISO2022_SEVEN(codesys) \
235 CODING_SYSTEM_ISO2022_SEVEN (XCODING_SYSTEM (codesys))
236 #define XCODING_SYSTEM_ISO2022_LOCK_SHIFT(codesys) \
237 CODING_SYSTEM_ISO2022_LOCK_SHIFT (XCODING_SYSTEM (codesys))
238 #define XCODING_SYSTEM_ISO2022_NO_ISO6429(codesys) \
239 CODING_SYSTEM_ISO2022_NO_ISO6429 (XCODING_SYSTEM (codesys))
240 #define XCODING_SYSTEM_ISO2022_ESCAPE_QUOTED(codesys) \
241 CODING_SYSTEM_ISO2022_ESCAPE_QUOTED (XCODING_SYSTEM (codesys))
242 #define XCODING_SYSTEM_CCL_DECODE(codesys) \
243 CODING_SYSTEM_CCL_DECODE (XCODING_SYSTEM (codesys))
244 #define XCODING_SYSTEM_CCL_ENCODE(codesys) \
245 CODING_SYSTEM_CCL_ENCODE (XCODING_SYSTEM (codesys))
248 #define XCODING_SYSTEM_DISABLE_COMPOSITION(codesys) \
249 CODING_SYSTEM_DISABLE_COMPOSITION (XCODING_SYSTEM (codesys))
250 #define XCODING_SYSTEM_USE_ENTITY_REFERENCE(codesys) \
251 CODING_SYSTEM_USE_ENTITY_REFERENCE (XCODING_SYSTEM (codesys))
252 #define XCODING_SYSTEM_CCS_PRIORITY_LIST(codesys) \
253 CODING_SYSTEM_CCS_PRIORITY_LIST (XCODING_SYSTEM (codesys))
256 EXFUN (Fcoding_category_list, 0);
257 EXFUN (Fcoding_category_system, 1);
258 EXFUN (Fcoding_priority_list, 0);
259 EXFUN (Fcoding_system_charset, 2);
260 EXFUN (Fcoding_system_doc_string, 1);
261 EXFUN (Fcoding_system_list, 0);
262 EXFUN (Fcoding_system_name, 1);
263 EXFUN (Fcoding_system_p, 1);
264 EXFUN (Fcoding_system_property, 2);
265 EXFUN (Fcoding_system_type, 1);
266 EXFUN (Fcopy_coding_system, 2);
267 EXFUN (Fdecode_big5_char, 1);
268 EXFUN (Fdecode_coding_region, 4);
269 EXFUN (Fdecode_shift_jis_char, 1);
270 EXFUN (Fdetect_coding_region, 3);
271 EXFUN (Fencode_big5_char, 1);
272 EXFUN (Fencode_coding_region, 4);
273 EXFUN (Fencode_shift_jis_char, 1);
274 EXFUN (Ffind_coding_system, 1);
275 EXFUN (Fget_coding_system, 1);
276 EXFUN (Fmake_coding_system, 4);
277 EXFUN (Fset_coding_category_system, 2);
278 EXFUN (Fset_coding_priority_list, 1);
279 EXFUN (Fsubsidiary_coding_system, 2);
281 extern Lisp_Object Qucs4, Qutf8;
282 extern Lisp_Object Qbig5, Qccl, Qcharset_g0;
283 extern Lisp_Object Qcharset_g1, Qcharset_g2, Qcharset_g3, Qcoding_system_error;
284 extern Lisp_Object Qcoding_systemp, Qcr, Qcrlf, Qdecode, Qencode;
285 extern Lisp_Object Qeol_cr, Qeol_crlf, Qeol_lf, Qeol_type, Qescape_quoted;
286 extern Lisp_Object Qforce_g0_on_output, Qforce_g1_on_output;
287 extern Lisp_Object Qforce_g2_on_output, Qforce_g3_on_output;
288 extern Lisp_Object Qinput_charset_conversion, Qiso2022, Qlf, Qlock_shift;
289 extern Lisp_Object Qmnemonic, Qno_ascii_cntl, Qno_ascii_eol, Qno_conversion;
290 extern Lisp_Object Qraw_text;
291 extern Lisp_Object Qno_iso6429, Qoutput_charset_conversion;
292 extern Lisp_Object Qpost_read_conversion, Qpre_write_conversion, Qseven;
293 extern Lisp_Object Qshift_jis, Qshort, Vcoding_system_for_read;
294 extern Lisp_Object Vcoding_system_for_write, Vcoding_system_hash_table;
295 extern Lisp_Object Vfile_name_coding_system, Vkeyboard_coding_system;
296 extern Lisp_Object Vterminal_coding_system;
298 /* Flags indicating current state while converting code. */
300 /* Used by everyone. */
302 #define CODING_STATE_END (1 << 0) /* If set, this is the last chunk of
303 data being processed. When this
304 is finished, output any necessary
305 terminating control characters,
306 escape sequences, etc. */
307 #define CODING_STATE_CR (1 << 1) /* If set, we just saw a CR. */
310 /* Used by Big 5 on output. */
312 #define CODING_STATE_BIG5_1 (1 << 2) /* If set, we just encountered
313 LEADING_BYTE_BIG5_1. */
314 #define CODING_STATE_BIG5_2 (1 << 3) /* If set, we just encountered
315 LEADING_BYTE_BIG5_2. */
318 /* Used by ISO2022 on input and output. */
320 #define CODING_STATE_R2L (1 << 4) /* If set, the current
321 directionality is right-to-left.
322 Otherwise, it's left-to-right. */
325 /* Used by ISO2022 on input. */
327 #define CODING_STATE_ESCAPE (1 << 5) /* If set, we're currently parsing
328 an escape sequence and the upper
329 16 bits should be looked at to
330 indicate what partial escape
331 sequence we've seen so far.
332 Otherwise, we're running
333 through actual text. */
334 #define CODING_STATE_SS2 (1 << 6) /* If set, G2 is invoked into GL, but
335 only for the next character. */
336 #define CODING_STATE_SS3 (1 << 7) /* If set, G3 is invoked into GL,
337 but only for the next character.
338 If both CODING_STATE_SS2 and
339 CODING_STATE_SS3 are set,
340 CODING_STATE_SS2 overrides; but
341 this probably indicates an error
342 in the text encoding. */
343 #ifdef ENABLE_COMPOSITE_CHARS
344 #define CODING_STATE_COMPOSITE (1 << 8) /* If set, we're currently processing
345 a composite character (i.e. a
346 character constructed by
347 overstriking two or more
349 #endif /* ENABLE_COMPOSITE_CHARS */
352 /* CODING_STATE_ISO2022_LOCK is the mask of flags that remain on until
353 explicitly turned off when in the ISO2022 encoder/decoder. Other flags are
354 turned off at the end of processing each character or escape sequence. */
355 #ifdef ENABLE_COMPOSITE_CHARS
356 # define CODING_STATE_ISO2022_LOCK \
357 (CODING_STATE_END | CODING_STATE_COMPOSITE | CODING_STATE_R2L)
359 # define CODING_STATE_ISO2022_LOCK (CODING_STATE_END | CODING_STATE_R2L)
362 #define CODING_STATE_BIG5_LOCK CODING_STATE_END
364 /* Flags indicating what we've seen so far when parsing an
365 ISO2022 escape sequence. */
368 /* Partial sequences */
369 ISO_ESC_NOTHING, /* Nothing has been seen. */
370 ISO_ESC, /* We've seen ESC. */
371 ISO_ESC_2_4, /* We've seen ESC $. This indicates
372 that we're designating a multi-byte, rather
373 than a single-byte, character set. */
374 ISO_ESC_2_8, /* We've seen ESC 0x28, i.e. ESC (.
375 This means designate a 94-character
376 character set into G0. */
377 ISO_ESC_2_9, /* We've seen ESC 0x29 -- designate a
378 94-character character set into G1. */
379 ISO_ESC_2_10, /* We've seen ESC 0x2A. */
380 ISO_ESC_2_11, /* We've seen ESC 0x2B. */
381 ISO_ESC_2_12, /* We've seen ESC 0x2C -- designate a
382 96-character character set into G0.
383 (This is not ISO2022-standard.
384 The following 96-character
385 control sequences are standard,
387 ISO_ESC_2_13, /* We've seen ESC 0x2D -- designate a
388 96-character character set into G1.
390 ISO_ESC_2_14, /* We've seen ESC 0x2E. */
391 ISO_ESC_2_15, /* We've seen ESC 0x2F. */
392 ISO_ESC_2_4_8, /* We've seen ESC $ 0x28 -- designate
393 a 94^N character set into G0. */
394 ISO_ESC_2_4_9, /* We've seen ESC $ 0x29. */
395 ISO_ESC_2_4_10, /* We've seen ESC $ 0x2A. */
396 ISO_ESC_2_4_11, /* We've seen ESC $ 0x2B. */
397 ISO_ESC_2_4_12, /* We've seen ESC $ 0x2C. */
398 ISO_ESC_2_4_13, /* We've seen ESC $ 0x2D. */
399 ISO_ESC_2_4_14, /* We've seen ESC $ 0x2E. */
400 ISO_ESC_2_4_15, /* We've seen ESC $ 0x2F. */
401 ISO_ESC_5_11, /* We've seen ESC [ or 0x9B. This
402 starts a directionality-control
403 sequence. The next character
404 must be 0, 1, 2, or ]. */
405 ISO_ESC_5_11_0, /* We've seen 0x9B 0. The next character must be ]. */
406 ISO_ESC_5_11_1, /* We've seen 0x9B 1. The next character must be ]. */
407 ISO_ESC_5_11_2, /* We've seen 0x9B 2. The next character must be ]. */
409 /* Full sequences. */
410 #ifdef ENABLE_COMPOSITE_CHARS
411 ISO_ESC_START_COMPOSITE, /* Private usage for START COMPOSING */
412 ISO_ESC_END_COMPOSITE, /* Private usage for END COMPOSING */
413 #endif /* ENABLE_COMPOSITE_CHARS */
414 ISO_ESC_SINGLE_SHIFT, /* We've seen a complete single-shift sequence. */
415 ISO_ESC_LOCKING_SHIFT,/* We've seen a complete locking-shift sequence. */
416 ISO_ESC_DESIGNATE, /* We've seen a complete designation sequence. */
417 ISO_ESC_DIRECTIONALITY,/* We've seen a complete ISO6429 directionality
419 ISO_ESC_LITERAL /* We've seen a literal character ala
423 /* Macros to define code of control characters for ISO2022's functions. */
424 /* code */ /* function */
425 #define ISO_CODE_LF 0x0A /* line-feed */
426 #define ISO_CODE_CR 0x0D /* carriage-return */
427 #define ISO_CODE_SO 0x0E /* shift-out */
428 #define ISO_CODE_SI 0x0F /* shift-in */
429 #define ISO_CODE_ESC 0x1B /* escape */
430 #define ISO_CODE_DEL 0x7F /* delete */
431 #define ISO_CODE_SS2 0x8E /* single-shift-2 */
432 #define ISO_CODE_SS3 0x8F /* single-shift-3 */
433 #define ISO_CODE_CSI 0x9B /* control-sequence-introduce */
436 /* Distinguishable categories of encodings.
438 This list determines the initial priority of the categories.
440 For better or worse, currently Mule files are encoded in 7-bit ISO 2022.
441 For this reason, under Mule ISO_7 gets highest priority.
443 Putting NO_CONVERSION second prevents "binary corruption" in the
444 default case in all but the (presumably) extremely rare case of a
445 binary file which contains redundant escape sequences but no 8-bit
448 The remaining priorities are based on perceived "internationalization
449 political correctness." An exception is UCS-4 at the bottom, since
450 basically everything is compatible with UCS-4, but it is likely to
451 be very rare as an external encoding. */
453 enum coding_category_type
455 /* must be a contiguous range of values 0 -- CODING_CATEGORY_LAST - 1 */
457 CODING_CATEGORY_ISO_7, /* ISO2022 system using only seven-bit bytes,
459 CODING_CATEGORY_NO_CONVERSION,
460 CODING_CATEGORY_UTF8,
461 CODING_CATEGORY_ISO_8_1, /* ISO2022 system using eight-bit bytes,
462 no locking shift, no designation sequences,
463 one-dimension characters in the upper half. */
464 CODING_CATEGORY_ISO_8_2, /* ISO2022 system using eight-bit bytes,
465 no locking shift, no designation sequences,
466 two-dimension characters in the upper half. */
467 CODING_CATEGORY_ISO_8_DESIGNATE, /* ISO2022 system using eight-bit bytes,
468 no locking shift, no single shift,
469 using designation to switch charsets */
470 CODING_CATEGORY_ISO_LOCK_SHIFT, /* ISO2022 system using locking shift */
471 CODING_CATEGORY_SHIFT_JIS,
472 CODING_CATEGORY_BIG5,
473 CODING_CATEGORY_UTF16,
474 CODING_CATEGORY_UCS4,
476 CODING_CATEGORY_NO_CONVERSION,
478 CODING_CATEGORY_LAST /* not a real coding category */
482 #define CODING_CATEGORY_SHIFT_JIS_MASK \
483 (1 << CODING_CATEGORY_SHIFT_JIS)
484 #define CODING_CATEGORY_ISO_7_MASK \
485 (1 << CODING_CATEGORY_ISO_7)
486 #define CODING_CATEGORY_ISO_8_DESIGNATE_MASK \
487 (1 << CODING_CATEGORY_ISO_8_DESIGNATE)
488 #define CODING_CATEGORY_ISO_8_1_MASK \
489 (1 << CODING_CATEGORY_ISO_8_1)
490 #define CODING_CATEGORY_ISO_8_2_MASK \
491 (1 << CODING_CATEGORY_ISO_8_2)
492 #define CODING_CATEGORY_ISO_LOCK_SHIFT_MASK \
493 (1 << CODING_CATEGORY_ISO_LOCK_SHIFT)
494 #define CODING_CATEGORY_BIG5_MASK \
495 (1 << CODING_CATEGORY_BIG5)
496 #define CODING_CATEGORY_UCS4_MASK \
497 (1 << CODING_CATEGORY_UCS4)
498 #define CODING_CATEGORY_UTF16_MASK \
499 (1 << CODING_CATEGORY_UTF16)
500 #define CODING_CATEGORY_UTF8_MASK \
501 (1 << CODING_CATEGORY_UTF8)
503 #define CODING_CATEGORY_NO_CONVERSION_MASK \
504 (1 << CODING_CATEGORY_NO_CONVERSION)
505 #define CODING_CATEGORY_NOT_FINISHED_MASK \
509 /* Convert shift-JIS code (sj1, sj2) into internal string
510 representation (c1, c2). (The leading byte is assumed.) */
512 #define DECODE_SJIS(sj1, sj2, c1, c2) \
514 int I1 = sj1, I2 = sj2; \
516 c1 = (I1 << 1) - ((I1 >= 0xe0) ? 0xe0 : 0x60), \
519 c1 = (I1 << 1) - ((I1 >= 0xe0) ? 0xe1 : 0x61), \
520 c2 = I2 + ((I2 >= 0x7f) ? 0x60 : 0x61); \
523 /* Convert the internal string representation of a Shift-JIS character
524 (c1, c2) into Shift-JIS code (sj1, sj2). The leading byte is
527 #define ENCODE_SJIS(c1, c2, sj1, sj2) \
529 int I1 = c1, I2 = c2; \
531 sj1 = (I1 >> 1) + ((I1 < 0xdf) ? 0x31 : 0x71), \
532 sj2 = I2 - ((I2 >= 0xe0) ? 0x60 : 0x61); \
534 sj1 = (I1 >> 1) + ((I1 < 0xdf) ? 0x30 : 0x70), \
539 Lisp_Object make_decoding_input_stream (Lstream *stream,
540 Lisp_Object codesys);
541 Lisp_Object make_encoding_input_stream (Lstream *stream,
542 Lisp_Object codesys);
543 Lisp_Object make_decoding_output_stream (Lstream *stream,
544 Lisp_Object codesys);
545 Lisp_Object make_encoding_output_stream (Lstream *stream,
546 Lisp_Object codesys);
547 Lisp_Object decoding_stream_coding_system (Lstream *stream);
548 Lisp_Object encoding_stream_coding_system (Lstream *stream);
549 void set_decoding_stream_coding_system (Lstream *stream,
550 Lisp_Object codesys);
551 void set_encoding_stream_coding_system (Lstream *stream,
552 Lisp_Object codesys);
553 void determine_real_coding_system (Lstream *stream, Lisp_Object *codesys_in_out,
554 eol_type_t *eol_type_in_out);
558 #define MIN_LEADING_BYTE 0x80
559 /* These need special treatment in a string and/or character */
560 #ifdef ENABLE_COMPOSITE_CHARS
561 #define LEADING_BYTE_COMPOSITE 0x80 /* for a composite character */
563 #define LEADING_BYTE_CONTROL_1 0x8F /* represent normal 80-9F */
564 #define LEADING_BYTE_LATIN_ISO8859_1 0x81 /* Right half of ISO 8859-1 */
565 #define BYTE_C1_P(c) ((unsigned int) ((unsigned int) (c) - 0x80) < 0x20)
566 #define BUFBYTE_FIRST_BYTE_P(c) ((c) < 0xA0)
567 #define BUFBYTE_LEADING_BYTE_P(c) BYTE_C1_P (c)
568 #endif /* not MULE */
570 #endif /* INCLUDED_file_coding_h_ */