1 /* Header for charset handler.
2 Copyright (C) 2001-2012 Free Software Foundation, Inc.
3 Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
4 2005, 2006, 2007, 2008, 2009, 2010, 2011
5 National Institute of Advanced Industrial Science and Technology (AIST)
6 Registration Number H14PRO021
9 National Institute of Advanced Industrial Science and Technology (AIST)
10 Registration Number H13PRO009
12 This file is part of GNU Emacs.
14 GNU Emacs is free software: you can redistribute it and/or modify
15 it under the terms of the GNU General Public License as published by
16 the Free Software Foundation, either version 3 of the License, or
17 (at your option) any later version.
19 GNU Emacs is distributed in the hope that it will be useful,
20 but WITHOUT ANY WARRANTY; without even the implied warranty of
21 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
22 GNU General Public License for more details.
24 You should have received a copy of the GNU General Public License
25 along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */
27 #ifndef EMACS_CHARSET_H
28 #define EMACS_CHARSET_H
33 #ifndef CHARSET_INLINE
34 # define CHARSET_INLINE INLINE
37 /* Index to arguments of Fdefine_charset_internal. */
39 enum define_charset_arg_index
42 charset_arg_dimension
,
43 charset_arg_code_space
,
46 charset_arg_iso_final
,
47 charset_arg_iso_revision
,
48 charset_arg_emacs_mule_id
,
49 charset_arg_ascii_compatible_p
,
50 charset_arg_supplementary_p
,
51 charset_arg_invalid_code
,
52 charset_arg_code_offset
,
56 charset_arg_unify_map
,
62 /* Indices to charset attributes vector. */
64 enum charset_attr_index
66 /* ID number of the charset. */
69 /* Name of the charset (symbol). */
72 /* Property list of the charset. */
75 /* If the method of the charset is `MAP', the value is a mapping
76 vector or a file name that contains mapping vector. Otherwise,
80 /* If the method of the charset is `MAP', the value is a vector
81 that maps code points of the charset to characters. The vector
82 is indexed by a character index. A character index is
83 calculated from a code point and the code-space table of the
87 /* If the method of the charset is `MAP', the value is a
88 char-table that maps characters of the charset to code
92 /* If the method of the charset is `SUBSET', the value is a vector
95 [ CHARSET-ID MIN-CODE MAX-CODE OFFSET ]
97 CHARSET-ID is an ID number of a parent charset. MIN-CODE and
98 MAX-CODE specify the range of characters inherited from the
99 parent. OFFSET is an integer value to add to a code point of
100 the parent charset to get the corresponding code point of this
104 /* If the method of the charset is `SUPERSET', the value is a list
105 whose elements have this form:
107 (CHARSET-ID . OFFSET)
109 CHARSET-IDs are ID numbers of parent charsets. OFFSET is an
110 integer value to add to a code point of the parent charset to
111 get the corresponding code point of this charset. */
114 /* The value is a mapping vector or a file name that contains the
115 mapping. This defines how characters in the charset should be
116 unified with Unicode. The value of the member
117 `charset_deunifier' is created from this information. */
120 /* If characters in the charset must be unified Unicode, the value
121 is a char table that maps a unified Unicode character code to
122 the non-unified character code in the charset. */
125 /* The length of the charset attribute vector. */
129 /* Methods for converting code points and characters of charsets. */
133 /* For a charset of this method, a character code is calculated
134 from a character index (which is calculated from a code point)
135 simply by adding an offset value. */
136 CHARSET_METHOD_OFFSET
,
138 /* For a charset of this method, a decoder vector and an encoder
139 char-table is used for code point <-> character code
143 /* A charset of this method is a subset of another charset. */
144 CHARSET_METHOD_SUBSET
,
146 /* A charset of this method is a superset of other charsets. */
147 CHARSET_METHOD_SUPERSET
152 /* Index to charset_table. */
155 /* Index to Vcharset_hash_table. */
156 ptrdiff_t hash_index
;
158 /* Dimension of the charset: 1, 2, 3, or 4. */
161 /* Byte code range of each dimension. <code_space>[4N] is a minimum
162 byte code of the (N+1)th dimension, <code_space>[4N+1] is a
163 maximum byte code of the (N+1)th dimension, <code_space>[4N+2] is
164 (<code_space>[4N+1] - <code_space>[4N] + 1), <code_space>[4N+3]
165 is the number of characters contained in the first through (N+1)th
166 dimensions, except that there is no <code_space>[15].
167 We get `char-index' of a `code-point' from this
171 /* If B is a byte of Nth dimension of a code-point, the (N-1)th bit
172 of code_space_mask[B] is set. This array is used to quickly
173 check if a code-point is in a valid range. */
174 unsigned char *code_space_mask
;
176 /* 1 if there's no gap in code-points. */
179 /* If the charset is treated as 94-chars in ISO-2022, the value is 0.
180 If the charset is treated as 96-chars in ISO-2022, the value is 1. */
183 /* ISO final byte of the charset: 48..127. It may be -1 if the
184 charset doesn't conform to ISO-2022. */
187 /* ISO revision number of the charset. */
190 /* If the charset is identical to what supported by Emacs 21 and the
191 priors, the identification number of the charset used in those
192 version. Otherwise, -1. */
195 /* Nonzero if the charset is compatible with ASCII. */
196 int ascii_compatible_p
;
198 /* Nonzero if the charset is supplementary. */
201 /* Nonzero if all the code points are representable by Lisp_Int. */
204 /* The method for encoding/decoding characters of the charset. */
205 enum charset_method method
;
207 /* Minimum and Maximum code points of the charset. */
208 unsigned min_code
, max_code
;
210 /* Offset value used by macros CODE_POINT_TO_INDEX and
211 INDEX_TO_CODE_POINT. . */
212 unsigned char_index_offset
;
214 /* Minimum and Maximum character codes of the charset. If the
215 charset is compatible with ASCII, min_char is a minimum non-ASCII
216 character of the charset. If the method of charset is
217 CHARSET_METHOD_OFFSET, even if the charset is unified, min_char
218 and max_char doesn't change. */
219 int min_char
, max_char
;
221 /* The code returned by ENCODE_CHAR if a character is not encodable
223 unsigned invalid_code
;
225 /* If the method of the charset is CHARSET_METHOD_MAP, this is a
226 table of bits used to quickly and roughly guess if a character
227 belongs to the charset.
229 The first 64 elements are 512 bits for characters less than
230 0x10000. Each bit corresponds to 128-character block. The last
231 126 elements are 1008 bits for the greater characters
232 (0x10000..0x3FFFFF). Each bit corresponds to 4096-character
235 If a bit is 1, at least one character in the corresponding block is
237 unsigned char fast_map
[190];
239 /* Offset value to calculate a character code from code-point, and
246 /* Hash table of charset symbols vs. the corresponding attribute
248 extern Lisp_Object Vcharset_hash_table
;
250 /* Table of struct charset. */
251 extern struct charset
*charset_table
;
253 #define CHARSET_FROM_ID(id) (charset_table + (id))
255 extern Lisp_Object Vcharset_ordered_list
;
256 extern Lisp_Object Vcharset_non_preferred_head
;
258 /* Incremented everytime we change the priority of charsets. */
259 extern unsigned short charset_ordered_list_tick
;
261 extern Lisp_Object Viso_2022_charset_list
;
262 extern Lisp_Object Vemacs_mule_charset_list
;
264 extern int emacs_mule_charset
[256];
266 /* Macros to access information about charset. */
268 /* Return the attribute vector of charset whose symbol is SYMBOL. */
269 #define CHARSET_SYMBOL_ATTRIBUTES(symbol) \
270 Fgethash ((symbol), Vcharset_hash_table, Qnil)
272 #define CHARSET_ATTR_ID(attrs) AREF ((attrs), charset_id)
273 #define CHARSET_ATTR_NAME(attrs) AREF ((attrs), charset_name)
274 #define CHARSET_ATTR_PLIST(attrs) AREF ((attrs), charset_plist)
275 #define CHARSET_ATTR_MAP(attrs) AREF ((attrs), charset_map)
276 #define CHARSET_ATTR_DECODER(attrs) AREF ((attrs), charset_decoder)
277 #define CHARSET_ATTR_ENCODER(attrs) AREF ((attrs), charset_encoder)
278 #define CHARSET_ATTR_SUBSET(attrs) AREF ((attrs), charset_subset)
279 #define CHARSET_ATTR_SUPERSET(attrs) AREF ((attrs), charset_superset)
280 #define CHARSET_ATTR_UNIFY_MAP(attrs) AREF ((attrs), charset_unify_map)
281 #define CHARSET_ATTR_DEUNIFIER(attrs) AREF ((attrs), charset_deunifier)
283 #define CHARSET_SYMBOL_ID(symbol) \
284 CHARSET_ATTR_ID (CHARSET_SYMBOL_ATTRIBUTES (symbol))
286 /* Return an index to Vcharset_hash_table of the charset whose symbol
288 #define CHARSET_SYMBOL_HASH_INDEX(symbol) \
289 hash_lookup (XHASH_TABLE (Vcharset_hash_table), symbol, NULL)
291 /* Return the attribute vector of CHARSET. */
292 #define CHARSET_ATTRIBUTES(charset) \
293 (HASH_VALUE (XHASH_TABLE (Vcharset_hash_table), (charset)->hash_index))
295 #define CHARSET_ID(charset) ((charset)->id)
296 #define CHARSET_HASH_INDEX(charset) ((charset)->hash_index)
297 #define CHARSET_DIMENSION(charset) ((charset)->dimension)
298 #define CHARSET_CODE_SPACE(charset) ((charset)->code_space)
299 #define CHARSET_CODE_LINEAR_P(charset) ((charset)->code_linear_p)
300 #define CHARSET_ISO_CHARS_96(charset) ((charset)->iso_chars_96)
301 #define CHARSET_ISO_FINAL(charset) ((charset)->iso_final)
302 #define CHARSET_ISO_PLANE(charset) ((charset)->iso_plane)
303 #define CHARSET_ISO_REVISION(charset) ((charset)->iso_revision)
304 #define CHARSET_EMACS_MULE_ID(charset) ((charset)->emacs_mule_id)
305 #define CHARSET_ASCII_COMPATIBLE_P(charset) ((charset)->ascii_compatible_p)
306 #define CHARSET_COMPACT_CODES_P(charset) ((charset)->compact_codes_p)
307 #define CHARSET_METHOD(charset) ((charset)->method)
308 #define CHARSET_MIN_CODE(charset) ((charset)->min_code)
309 #define CHARSET_MAX_CODE(charset) ((charset)->max_code)
310 #define CHARSET_INVALID_CODE(charset) ((charset)->invalid_code)
311 #define CHARSET_MIN_CHAR(charset) ((charset)->min_char)
312 #define CHARSET_MAX_CHAR(charset) ((charset)->max_char)
313 #define CHARSET_CODE_OFFSET(charset) ((charset)->code_offset)
314 #define CHARSET_UNIFIED_P(charset) ((charset)->unified_p)
316 #define CHARSET_NAME(charset) \
317 (CHARSET_ATTR_NAME (CHARSET_ATTRIBUTES (charset)))
318 #define CHARSET_MAP(charset) \
319 (CHARSET_ATTR_MAP (CHARSET_ATTRIBUTES (charset)))
320 #define CHARSET_DECODER(charset) \
321 (CHARSET_ATTR_DECODER (CHARSET_ATTRIBUTES (charset)))
322 #define CHARSET_ENCODER(charset) \
323 (CHARSET_ATTR_ENCODER (CHARSET_ATTRIBUTES (charset)))
324 #define CHARSET_SUBSET(charset) \
325 (CHARSET_ATTR_SUBSET (CHARSET_ATTRIBUTES (charset)))
326 #define CHARSET_SUPERSET(charset) \
327 (CHARSET_ATTR_SUPERSET (CHARSET_ATTRIBUTES (charset)))
328 #define CHARSET_UNIFY_MAP(charset) \
329 (CHARSET_ATTR_UNIFY_MAP (CHARSET_ATTRIBUTES (charset)))
330 #define CHARSET_DEUNIFIER(charset) \
331 (CHARSET_ATTR_DEUNIFIER (CHARSET_ATTRIBUTES (charset)))
334 set_charset_attr (struct charset
*charset
, enum charset_attr_index idx
,
337 ASET (CHARSET_ATTRIBUTES (charset
), idx
, val
);
341 /* Nonzero if OBJ is a valid charset symbol. */
342 #define CHARSETP(obj) (CHARSET_SYMBOL_HASH_INDEX (obj) >= 0)
344 /* Check if X is a valid charset symbol. If not, signal an error. */
345 #define CHECK_CHARSET(x) \
347 if (! SYMBOLP (x) || CHARSET_SYMBOL_HASH_INDEX (x) < 0) \
348 wrong_type_argument (Qcharsetp, (x)); \
352 /* Check if X is a valid charset symbol. If valid, set ID to the id
353 number of the charset. Otherwise, signal an error. */
354 #define CHECK_CHARSET_GET_ID(x, id) \
358 if (! SYMBOLP (x) || (idx = CHARSET_SYMBOL_HASH_INDEX (x)) < 0) \
359 wrong_type_argument (Qcharsetp, (x)); \
360 id = XINT (AREF (HASH_VALUE (XHASH_TABLE (Vcharset_hash_table), idx), \
365 /* Check if X is a valid charset symbol. If valid, set ATTR to the
366 attr vector of the charset. Otherwise, signal an error. */
367 #define CHECK_CHARSET_GET_ATTR(x, attr) \
369 if (!SYMBOLP (x) || NILP (attr = CHARSET_SYMBOL_ATTRIBUTES (x))) \
370 wrong_type_argument (Qcharsetp, (x)); \
374 #define CHECK_CHARSET_GET_CHARSET(x, charset) \
377 CHECK_CHARSET_GET_ID (x, csid); \
378 charset = CHARSET_FROM_ID (csid); \
382 /* Lookup Vcharset_ordered_list and return the first charset that
383 contains the character C. */
384 #define CHAR_CHARSET(c) \
385 ((c) < 0x80 ? CHARSET_FROM_ID (charset_ascii) \
386 : char_charset ((c), Qnil, NULL))
389 /* Char-table of charset-sets. Each element is a bool vector indexed
391 extern Lisp_Object Vchar_charset_set
;
393 /* Charset-bag of character C. */
394 #define CHAR_CHARSET_SET(c) \
395 CHAR_TABLE_REF (Vchar_charset_set, c)
397 /* Check if two characters C1 and C2 belong to the same charset. */
398 #define SAME_CHARSET_P(c1, c2) \
399 intersection_p (CHAR_CHARSET_SET (c1), CHAR_CHARSET_SET (c2))
404 /* Return a character corresponding to the code-point CODE of CHARSET.
405 Try some optimization before calling decode_char. */
407 #define DECODE_CHAR(charset, code) \
408 ((ASCII_BYTE_P (code) && (charset)->ascii_compatible_p) \
410 : ((code) < (charset)->min_code || (code) > (charset)->max_code) \
412 : (charset)->unified_p \
413 ? decode_char ((charset), (code)) \
414 : (charset)->method == CHARSET_METHOD_OFFSET \
415 ? ((charset)->code_linear_p \
416 ? (int) ((code) - (charset)->min_code) + (charset)->code_offset \
417 : decode_char ((charset), (code))) \
418 : (charset)->method == CHARSET_METHOD_MAP \
419 ? (((charset)->code_linear_p \
420 && VECTORP (CHARSET_DECODER (charset))) \
421 ? XINT (AREF (CHARSET_DECODER (charset), \
422 (code) - (charset)->min_code)) \
423 : decode_char ((charset), (code))) \
424 : decode_char ((charset), (code)))
426 extern Lisp_Object charset_work
;
428 /* Return a code point of CHAR in CHARSET.
429 Try some optimization before calling encode_char. */
431 #define ENCODE_CHAR(charset, c) \
433 (sizeof (c) <= sizeof (int), \
434 (ASCII_CHAR_P (c) && (charset)->ascii_compatible_p \
436 : ((charset)->unified_p \
437 || (charset)->method == CHARSET_METHOD_SUBSET \
438 || (charset)->method == CHARSET_METHOD_SUPERSET) \
439 ? encode_char (charset, c) \
440 : (c) < (charset)->min_char || (c) > (charset)->max_char \
441 ? (charset)->invalid_code \
442 : (charset)->method == CHARSET_METHOD_OFFSET \
443 ? ((charset)->code_linear_p \
444 ? (unsigned) ((c) - (charset)->code_offset) + (charset)->min_code \
445 : encode_char (charset, c)) \
446 : (charset)->method == CHARSET_METHOD_MAP \
447 ? (((charset)->compact_codes_p \
448 && CHAR_TABLE_P (CHARSET_ENCODER (charset))) \
449 ? (charset_work = CHAR_TABLE_REF (CHARSET_ENCODER (charset), c), \
450 (NILP (charset_work) \
451 ? (charset)->invalid_code \
452 : (unsigned) XFASTINT (charset_work))) \
453 : encode_char (charset, c)) \
454 : encode_char (charset, c))))
457 /* Set to 1 when a charset map is loaded to warn that a buffer text
458 and a string data may be relocated. */
459 extern int charset_map_loaded
;
462 /* Set CHARSET to the charset highest priority of C, CODE to the
463 code-point of C in CHARSET. */
464 #define SPLIT_CHAR(c, charset, code) \
465 ((charset) = char_charset ((c), Qnil, &(code)))
468 #define ISO_MAX_DIMENSION 3
469 #define ISO_MAX_CHARS 2
470 #define ISO_MAX_FINAL 0x80 /* only 0x30..0xFF are used */
472 /* Mapping table from ISO2022's charset (specified by DIMENSION,
473 CHARS, and FINAL_CHAR) to Emacs' charset ID. Should be accessed by
474 macro ISO_CHARSET_TABLE (DIMENSION, CHARS, FINAL_CHAR). */
475 extern int iso_charset_table
[ISO_MAX_DIMENSION
][ISO_MAX_CHARS
][ISO_MAX_FINAL
];
477 /* A charset of type iso2022 who has DIMENSION, CHARS, and FINAL
478 (final character). */
479 #define ISO_CHARSET_TABLE(dimension, chars_96, final) \
480 iso_charset_table[(dimension) - 1][(chars_96)][(final)]
482 /* Nonzero if the charset who has FAST_MAP may contain C. */
483 #define CHARSET_FAST_MAP_REF(c, fast_map) \
485 ? fast_map[(c) >> 10] & (1 << (((c) >> 7) & 7)) \
486 : fast_map[((c) >> 15) + 62] & (1 << (((c) >> 12) & 7)))
488 #define CHARSET_FAST_MAP_SET(c, fast_map) \
491 (fast_map)[(c) >> 10] |= 1 << (((c) >> 7) & 7); \
493 (fast_map)[((c) >> 15) + 62] |= 1 << (((c) >> 12) & 7); \
498 /* 1 if CHARSET may contain the character C. */
499 #define CHAR_CHARSET_P(c, charset) \
500 ((ASCII_CHAR_P (c) && (charset)->ascii_compatible_p) \
501 || ((CHARSET_UNIFIED_P (charset) \
502 || (charset)->method == CHARSET_METHOD_SUBSET \
503 || (charset)->method == CHARSET_METHOD_SUPERSET) \
504 ? encode_char ((charset), (c)) != (charset)->invalid_code \
505 : (CHARSET_FAST_MAP_REF ((c), (charset)->fast_map) \
506 && ((charset)->method == CHARSET_METHOD_OFFSET \
507 ? (c) >= (charset)->min_char && (c) <= (charset)->max_char \
508 : ((charset)->method == CHARSET_METHOD_MAP \
509 && (charset)->compact_codes_p \
510 && CHAR_TABLE_P (CHARSET_ENCODER (charset))) \
511 ? ! NILP (CHAR_TABLE_REF (CHARSET_ENCODER (charset), (c))) \
512 : encode_char ((charset), (c)) != (charset)->invalid_code))))
515 /* Special macros for emacs-mule encoding. */
517 /* Leading-code followed by extended leading-code. DIMENSION/COLUMN */
518 #define EMACS_MULE_LEADING_CODE_PRIVATE_11 0x9A /* 1/1 */
519 #define EMACS_MULE_LEADING_CODE_PRIVATE_12 0x9B /* 1/2 */
520 #define EMACS_MULE_LEADING_CODE_PRIVATE_21 0x9C /* 2/2 */
521 #define EMACS_MULE_LEADING_CODE_PRIVATE_22 0x9D /* 2/2 */
525 extern Lisp_Object Qcharsetp
;
527 extern Lisp_Object Qascii
;
528 extern int charset_ascii
, charset_eight_bit
;
529 extern int charset_unicode
;
530 extern int charset_jisx0201_roman
;
531 extern int charset_jisx0208_1978
;
532 extern int charset_jisx0208
;
533 extern int charset_ksc5601
;
535 extern int charset_unibyte
;
537 extern struct charset
*char_charset (int, Lisp_Object
, unsigned *);
538 extern Lisp_Object
charset_attributes (int);
540 extern int maybe_unify_char (int, Lisp_Object
);
541 extern int decode_char (struct charset
*, unsigned);
542 extern unsigned encode_char (struct charset
*, int);
543 extern int string_xstring_p (Lisp_Object
);
545 extern void map_charset_chars (void (*) (Lisp_Object
, Lisp_Object
),
546 Lisp_Object
, Lisp_Object
,
547 struct charset
*, unsigned, unsigned);
551 #endif /* EMACS_CHARSET_H */