1 /* Header for multibyte character handler.
2 Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN.
3 Licensed to the Free Software Foundation.
4 Copyright (C) 2001, 2002
5 National Institute of Advanced Industrial Science and Technology (AIST)
6 Registration Number H13PRO009
8 This file is part of GNU Emacs.
10 GNU Emacs is free software; you can redistribute it and/or modify
11 it under the terms of the GNU General Public License as published by
12 the Free Software Foundation; either version 2, or (at your option)
15 GNU Emacs is distributed in the hope that it will be useful,
16 but WITHOUT ANY WARRANTY; without even the implied warranty of
17 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18 GNU General Public License for more details.
20 You should have received a copy of the GNU General Public License
21 along with GNU Emacs; see the file COPYING. If not, write to
22 the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23 Boston, MA 02111-1307, USA. */
25 #ifndef EMACS_CHARACTER_H
26 #define EMACS_CHARACTER_H
30 80-7FF 110xxxxx 10xxxxxx
32 800-FFFF 1110xxxx 10xxxxxx 10xxxxxx
34 10000-1FFFFF 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
35 F0..F7 80..BF 80..BF 80..BF
36 200000-3FFF7F 11111000 1000xxxx 10xxxxxx 10xxxxxx 10xxxxxx
37 F8 80..8F 80..BF 80..BF 80..BF
46 3FFF80-3FFFFF 1100000x 10xxxxxx
51 /* This is the maximum character code ((1 << CHARACTERBITS) - 1). */
52 #define MAX_CHAR 0x3FFFFF
54 #define MAX_UNICODE_CHAR 0x10FFFF
56 #define MAX_1_BYTE_CHAR 0x7F
57 #define MAX_2_BYTE_CHAR 0x7FF
58 #define MAX_3_BYTE_CHAR 0xFFFF
59 #define MAX_4_BYTE_CHAR 0x1FFFFF
60 #define MAX_5_BYTE_CHAR 0x3FFF7F
62 #define BYTE8_TO_CHAR(byte) ((byte) + 0x3FFF00)
63 #define CHAR_TO_BYTE8(c) ((c) - 0x3FFF00)
64 #define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR)
65 #define CHAR_BYTE8_HEAD_P(byte) ((byte) == 0xC0 || (byte) == 0xC1)
67 /* This is the maximum byte length of multi-byte sequence. */
68 #define MAX_MULTIBYTE_LENGTH 5
70 /* Return a Lisp character whose code is C. */
71 #define make_char(c) make_number (c)
73 /* Nonzero iff C is an ASCII byte. */
74 #define ASCII_BYTE_P(c) ((unsigned) (c) < 0x80)
76 /* Nonzero iff X is a character. */
77 #define CHARACTERP(x) (NATNUMP (x) && XFASTINT (x) <= MAX_CHAR)
79 /* Nozero iff C is valid as a charater code. GENERICP is not used
80 now. It will be removed in the future. */
81 #define CHAR_VALID_P(c, genericp) CHARACTERP (c)
83 /* Check if Lisp object X is a character or not. */
84 #define CHECK_CHARACTER(x) \
86 if (! CHARACTERP(x)) x = wrong_type_argument (Qcharacterp, (x)); \
89 /* Nonzero iff C is an ASCII character. */
90 #define ASCII_CHAR_P(c) ((unsigned) (c) < 0x80)
92 /* Nonzero iff C is a character of code less than 0x100. */
93 #define SINGLE_BYTE_CHAR_P(c) ((unsigned) (c) < 0x100)
95 /* Nonzero if character C has a printable glyph. */
96 #define CHAR_PRINTABLE_P(c) \
97 (((c) >= 32 && ((c) < 127) \
98 || ! NILP (CHAR_TABLE_REF (Vprintable_chars, (c)))))
100 /* How many bytes C occupies in a multibyte buffer. */
101 #define CHAR_BYTES(c) \
102 ( (c) <= MAX_1_BYTE_CHAR ? 1 \
103 : (c) <= MAX_2_BYTE_CHAR ? 2 \
104 : (c) <= MAX_3_BYTE_CHAR ? 3 \
105 : (c) <= MAX_4_BYTE_CHAR ? 4 \
106 : (c) <= MAX_5_BYTE_CHAR ? 5 \
109 /* Store multibyte form of the character C in STR. The caller should
110 allocate at least MAX_MULTIBYTE_LENGTH bytes area at STR in
111 advance. Returns the length of the multibyte form. */
113 #define CHAR_STRING(c, p) \
114 ((unsigned) (c) <= MAX_1_BYTE_CHAR \
117 : (unsigned) (c) <= MAX_2_BYTE_CHAR \
118 ? ((p)[0] = (0xC0 | ((c) >> 6)), \
119 (p)[1] = (0x80 | ((c) & 0x3F)), \
121 : (unsigned) (c) <= MAX_3_BYTE_CHAR \
122 ? ((p)[0] = (0xE0 | ((c) >> 12)), \
123 (p)[1] = (0x80 | (((c) >> 6) & 0x3F)), \
124 (p)[2] = (0x80 | ((c) & 0x3F)), \
126 : (unsigned) (c) <= MAX_5_BYTE_CHAR \
127 ? char_string_with_unification (c, p, NULL) \
128 : ((p)[0] = (0xC0 | (((c) >> 6) & 0x01)), \
129 (p)[1] = (0x80 | ((c) & 0x3F)), \
133 /* Like CHAR_STRING, but advance P to the end of the multibyte
136 #define CHAR_STRING_ADVANCE(c, p) \
137 ((unsigned) (c) <= MAX_1_BYTE_CHAR \
139 : (unsigned) (c) <= MAX_2_BYTE_CHAR \
140 ? (*(p)++ = (0xC0 | ((c) >> 6)), \
141 *(p)++ = (0x80 | ((c) & 0x3F))) \
142 : (unsigned) (c) <= MAX_3_BYTE_CHAR \
143 ? (*(p)++ = (0xE0 | ((c) >> 12)), \
144 *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \
145 *(p)++ = (0x80 | ((c) & 0x3F))) \
146 : (unsigned) (c) <= MAX_5_BYTE_CHAR \
147 ? char_string_with_unification (c, p, &p) \
148 : (*(p)++ = (0xC0 | (((c) >> 6) & 0x01)), \
149 *(p)++ = (0x80 | ((c) & 0x3F))))
152 /* Nonzero iff BYTE starts a character in a multibyte form. */
153 #define CHAR_HEAD_P(byte) (((byte) & 0xC0) != 0x80)
155 /* Nonzero iff BYTE starts a non-ASCII character in a multibyte
157 #define LEADING_CODE_P(byte) (((byte) & 0xC0) == 0xC0)
159 /* Just kept for backward compatibility. This macro will be removed
161 #define BASE_LEADING_CODE_P LEADING_CODE_P
163 /* How many bytes a character that starts with BYTE occupies in a
165 #define BYTES_BY_CHAR_HEAD(byte) \
166 (!((byte) & 0x80) ? 1 \
167 : !((byte) & 0x20) ? 2 \
168 : !((byte) & 0x10) ? 3 \
169 : !((byte) & 0x08) ? 4 \
173 /* Return the length of the multi-byte form at string STR of length
174 LEN while assuming that STR points a valid multi-byte form. As
175 this macro isn't necessary anymore, all callers will be changed to
176 use BYTES_BY_CHAR_HEAD directly in the future. */
178 #define MULTIBYTE_FORM_LENGTH(str, len) \
179 BYTES_BY_CHAR_HEAD (*(str))
181 /* Parse multibyte string STR of length LENGTH and set BYTES to the
182 byte length of a character at STR while assuming that STR points a
183 valid multibyte form. As this macro isn't necessary anymore, all
184 callers will be changed to use BYTES_BY_CHAR_HEAD directly in the
187 #define PARSE_MULTIBYTE_SEQ(str, length, bytes) \
188 (bytes) = BYTES_BY_CHAR_HEAD (*(str))
190 /* The byte length of multibyte form at unibyte string P ending at
191 PEND. If STR doesn't point a valid multibyte form, return 0. */
193 #define MULTIBYTE_LENGTH(p, pend) \
195 : !((p)[0] & 0x80) ? 1 \
196 : ((p + 1 >= pend) || (((p)[1] & 0xC0) != 0x80)) ? 0 \
197 : ((p)[0] & 0xE0) == 0xC0 ? 2 \
198 : ((p + 2 >= pend) || (((p)[2] & 0xC0) != 0x80)) ? 0 \
199 : ((p)[0] & 0xF0) == 0xE0 ? 3 \
200 : ((p + 3 >= pend) || (((p)[3] & 0xC0) != 0x80)) ? 0 \
201 : ((p)[0] & 0xF8) == 0xF0 ? 4 \
202 : ((p + 4 >= pend) || (((p)[4] & 0xC0) != 0x80)) ? 0 \
203 : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \
207 /* Like MULTIBYTE_LENGTH but don't check the ending address. */
209 #define MULTIBYTE_LENGTH_NO_CHECK(p) \
210 (!((p)[0] & 0x80) ? 1 \
211 : ((p)[1] & 0xC0) != 0x80 ? 0 \
212 : ((p)[0] & 0xE0) == 0xC0 ? 2 \
213 : ((p)[2] & 0xC0) != 0x80 ? 0 \
214 : ((p)[0] & 0xF0) == 0xE0 ? 3 \
215 : ((p)[3] & 0xC0) != 0x80 ? 0 \
216 : ((p)[0] & 0xF8) == 0xF0 ? 4 \
217 : ((p)[4] & 0xC0) != 0x80 ? 0 \
218 : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \
222 /* Return the character code of character whose multibyte form is at
223 P. The argument LEN is ignored. It will be removed in the
226 #define STRING_CHAR(p, len) \
229 : ! ((p)[0] & 0x20) \
230 ? (((((p)[0] & 0x1F) << 6) \
232 + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0)) \
233 : ! ((p)[0] & 0x10) \
234 ? ((((p)[0] & 0x0F) << 12) \
235 | (((p)[1] & 0x3F) << 6) \
237 : string_char_with_unification (p, NULL, NULL))
240 /* Like STRING_CHAR but set ACTUAL_LEN to the length of multibyte
241 form. The argument LEN is ignored. It will be removed in the
244 #define STRING_CHAR_AND_LENGTH(p, len, actual_len) \
246 ? ((actual_len) = 1, (p)[0]) \
247 : ! ((p)[0] & 0x20) \
248 ? ((actual_len) = 2, \
249 (((((p)[0] & 0x1F) << 6) \
251 + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0))) \
252 : ! ((p)[0] & 0x10) \
253 ? ((actual_len) = 3, \
254 ((((p)[0] & 0x0F) << 12) \
255 | (((p)[1] & 0x3F) << 6) \
256 | ((p)[2] & 0x3F))) \
257 : string_char_with_unification (p, NULL, &actual_len))
260 /* Like STRING_CHAR but advacen P to the end of multibyte form. */
262 #define STRING_CHAR_ADVANCE(p) \
265 : ! ((p)[0] & 0x20) \
267 ((((p)[-2] & 0x1F) << 6) \
269 | (((unsigned char) (p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \
270 : ! ((p)[0] & 0x10) \
272 ((((p)[-3] & 0x0F) << 12) \
273 | (((p)[-2] & 0x3F) << 6) \
274 | ((p)[-1] & 0x3F))) \
275 : string_char_with_unification (p, &p, NULL))
278 /* Fetch the "next" character from Lisp string STRING at byte position
279 BYTEIDX, character position CHARIDX. Store it into OUTPUT.
281 All the args must be side-effect-free.
282 BYTEIDX and CHARIDX must be lvalues;
283 we increment them past the character fetched. */
285 #define FETCH_STRING_CHAR_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \
289 if (STRING_MULTIBYTE (STRING)) \
291 unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX]; \
294 OUTPUT = STRING_CHAR_AND_LENGTH (ptr, 0, len); \
298 OUTPUT = XSTRING (STRING)->data[BYTEIDX++]; \
303 /* Like FETCH_STRING_CHAR_ADVANCE but assumes STRING is multibyte. */
305 #define FETCH_STRING_CHAR_ADVANCE_NO_CHECK(OUTPUT, STRING, CHARIDX, BYTEIDX) \
308 unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX]; \
311 OUTPUT = STRING_CHAR_AND_LENGTH (ptr, 0, len); \
318 /* Like FETCH_STRING_CHAR_ADVANCE but fetch character from the current
321 #define FETCH_CHAR_ADVANCE(OUTPUT, CHARIDX, BYTEIDX) \
325 if (!NILP (current_buffer->enable_multibyte_characters)) \
327 unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \
330 OUTPUT= STRING_CHAR_AND_LENGTH (ptr, 0, len); \
335 OUTPUT = *(BYTE_POS_ADDR (BYTEIDX)); \
342 /* Like FETCH_CHAR_ADVANCE but assumes STRING is multibyte. */
344 #define FETCH_CHAR_ADVANCE_NO_CHECK(OUTPUT, CHARIDX, BYTEIDX) \
347 unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \
350 OUTPUT= STRING_CHAR_AND_LENGTH (ptr, 0, len); \
357 /* Increase the buffer byte position POS_BYTE of the current buffer to
358 the next character boundary. No range checking of POS. */
360 #define INC_POS(pos_byte) \
362 unsigned char *p = BYTE_POS_ADDR (pos_byte); \
363 pos_byte += BYTES_BY_CHAR_HEAD (*p); \
367 /* Decrease the buffer byte position POS_BYTE of the current buffer to
368 the previous character boundary. No range checking of POS. */
370 #define DEC_POS(pos_byte) \
375 if (pos_byte < GPT_BYTE) \
376 p = BEG_ADDR + pos_byte - 1; \
378 p = BEG_ADDR + GAP_SIZE + pos_byte - 1; \
379 while (!CHAR_HEAD_P (*p)) \
386 /* Increment both CHARPOS and BYTEPOS, each in the appropriate way. */
388 #define INC_BOTH(charpos, bytepos) \
392 if (NILP (current_buffer->enable_multibyte_characters)) \
395 INC_POS ((bytepos)); \
400 /* Decrement both CHARPOS and BYTEPOS, each in the appropriate way. */
402 #define DEC_BOTH(charpos, bytepos) \
406 if (NILP (current_buffer->enable_multibyte_characters)) \
409 DEC_POS ((bytepos)); \
414 /* Increase the buffer byte position POS_BYTE of the current buffer to
415 the next character boundary. This macro relies on the fact that
416 *GPT_ADDR and *Z_ADDR are always accessible and the values are
417 '\0'. No range checking of POS_BYTE. */
419 #define BUF_INC_POS(buf, pos_byte) \
421 unsigned char *p = BUF_BYTE_ADDRESS (buf, pos_byte); \
422 pos_byte += BYTES_BY_CHAR_HEAD (*p); \
426 /* Decrease the buffer byte position POS_BYTE of the current buffer to
427 the previous character boundary. No range checking of POS_BYTE. */
429 #define BUF_DEC_POS(buf, pos_byte) \
433 if (pos_byte < BUF_GPT_BYTE (buf)) \
434 p = BUF_BEG_ADDR (buf) + pos_byte - 1; \
436 p = BUF_BEG_ADDR (buf) + BUF_GAP_SIZE (buf) + pos_byte - 1; \
437 while (!CHAR_HEAD_P (*p)) \
445 #define MAYBE_UNIFY_CHAR(c) \
446 if (CHAR_TABLE_P (Vchar_unify_table)) \
451 val = CHAR_TABLE_REF (Vchar_unify_table, c); \
454 Funify_charset (val, Qnil); \
455 val = CHAR_TABLE_REF (Vchar_unify_table, c); \
457 if ((unified = XINT (val)) >= 0) \
462 /* Return the width of ASCII character C. The width is measured by
463 how many columns occupied on the screen when displayed in the
466 #define ASCII_CHAR_WIDTH(c) \
469 ? XFASTINT (current_buffer->tab_width) \
470 : (c == '\n' ? 0 : (NILP (current_buffer->ctl_arrow) ? 4 : 2))) \
473 : ((NILP (current_buffer->ctl_arrow) ? 4 : 2))))
475 /* Return the width of character C. The width is measured by how many
476 columns occupied on the screen when displayed in the current
479 #define CHAR_WIDTH(c) \
481 ? ASCII_CHAR_WIDTH (c) \
482 : XINT (CHAR_TABLE_REF (Vchar_width_table, c)))
484 extern int char_string_with_unification
P_ ((int, unsigned char *,
486 extern int string_char_with_unification
P_ ((unsigned char *,
487 unsigned char **, int *));
489 extern int translate_char
P_ ((Lisp_Object
, int c
));
490 extern int char_printable_p
P_ ((int c
));
491 extern void parse_str_as_multibyte
P_ ((unsigned char *, int, int *, int *));
492 extern int parse_str_to_multibyte
P_ ((unsigned char *, int));
493 extern int str_as_multibyte
P_ ((unsigned char *, int, int, int *));
494 extern int str_to_multibyte
P_ ((unsigned char *, int, int));
495 extern int str_as_unibyte
P_ ((unsigned char *, int));
496 extern int strwidth
P_ ((unsigned char *, int));
497 extern int c_string_width
P_ ((unsigned char *, int, int, int *, int *));
498 extern int lisp_string_width
P_ ((Lisp_Object
, int, int *, int *));
500 extern Lisp_Object Vprintable_chars
;
502 extern Lisp_Object Qcharacterp
, Qauto_fill_chars
;
503 extern Lisp_Object Vtranslation_table_vector
;
504 extern Lisp_Object Vchar_width_table
;
505 extern Lisp_Object Vchar_direction_table
;
506 extern Lisp_Object Vchar_unify_table
;
508 /* Return a translation table of id number ID. */
509 #define GET_TRANSLATION_TABLE(id) \
510 (XCDR(XVECTOR(Vtranslation_table_vector)->contents[(id)]))
512 /* A char-table for characters which may invoke auto-filling. */
513 extern Lisp_Object Vauto_fill_chars
;
515 /* Copy LEN bytes from FROM to TO. This macro should be used only
516 when a caller knows that LEN is short and the obvious copy loop is
517 faster than calling bcopy which has some overhead. Copying a
518 multibyte sequence of a character is the typical case. */
520 #define BCOPY_SHORT(from, to, len) \
523 unsigned char *from_p = from, *to_p = to; \
524 while (i--) *to_p++ = *from_p++; \
527 #define DEFSYM(sym, name) \
528 do { (sym) = intern ((name)); staticpro (&(sym)); } while (0)
530 #endif /* EMACS_CHARACTER_H */