Commit | Line | Data |
---|---|---|
0168c3d8 KH |
1 | /* Header for multibyte character handler. |
2 | Copyright (C) 1995, 1997, 1998 Electrotechnical Laboratory, JAPAN. | |
8f924df7 | 3 | Licensed to the Free Software Foundation. |
5df4f04c | 4 | Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011 |
0168c3d8 KH |
5 | National Institute of Advanced Industrial Science and Technology (AIST) |
6 | Registration Number H13PRO009 | |
7 | ||
8 | This file is part of GNU Emacs. | |
9 | ||
b9b1cc14 | 10 | GNU Emacs is free software: you can redistribute it and/or modify |
0168c3d8 | 11 | it under the terms of the GNU General Public License as published by |
b9b1cc14 GM |
12 | the Free Software Foundation, either version 3 of the License, or |
13 | (at your option) any later version. | |
0168c3d8 KH |
14 | |
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. | |
19 | ||
20 | You should have received a copy of the GNU General Public License | |
b9b1cc14 | 21 | along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */ |
0168c3d8 KH |
22 | |
23 | #ifndef EMACS_CHARACTER_H | |
24 | #define EMACS_CHARACTER_H | |
25 | ||
13bdea59 PE |
26 | #include <verify.h> |
27 | ||
f162bcc3 | 28 | INLINE_HEADER_BEGIN |
f162bcc3 | 29 | |
885317d8 KH |
30 | /* character code 1st byte byte sequence |
31 | -------------- -------- ------------- | |
32 | 0-7F 00..7F 0xxxxxxx | |
33 | 80-7FF C2..DF 110xxxxx 10xxxxxx | |
34 | 800-FFFF E0..EF 1110xxxx 10xxxxxx 10xxxxxx | |
35 | 10000-1FFFFF F0..F7 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx | |
36 | 200000-3FFF7F F8 11111000 1000xxxx 10xxxxxx 10xxxxxx 10xxxxxx | |
c43e85a9 KH |
37 | 3FFF80-3FFFFF C0..C1 1100000x 10xxxxxx (for eight-bit-char) |
38 | 400000-... invalid | |
0168c3d8 | 39 | |
c43e85a9 KH |
40 | invalid 1st byte 80..BF 10xxxxxx |
41 | F9..FF 11111xxx (xxx != 000) | |
0168c3d8 KH |
42 | */ |
43 | ||
885317d8 | 44 | /* Maximum character code ((1 << CHARACTERBITS) - 1). */ |
0168c3d8 KH |
45 | #define MAX_CHAR 0x3FFFFF |
46 | ||
885317d8 | 47 | /* Maximum Unicode character code. */ |
0168c3d8 KH |
48 | #define MAX_UNICODE_CHAR 0x10FFFF |
49 | ||
885317d8 | 50 | /* Maximum N-byte character codes. */ |
0168c3d8 KH |
51 | #define MAX_1_BYTE_CHAR 0x7F |
52 | #define MAX_2_BYTE_CHAR 0x7FF | |
53 | #define MAX_3_BYTE_CHAR 0xFFFF | |
54 | #define MAX_4_BYTE_CHAR 0x1FFFFF | |
55 | #define MAX_5_BYTE_CHAR 0x3FFF7F | |
56 | ||
3a0a38de KH |
57 | /* Minimum leading code of multibyte characters. */ |
58 | #define MIN_MULTIBYTE_LEADING_CODE 0xC0 | |
59 | /* Maximum leading code of multibyte characters. */ | |
60 | #define MAX_MULTIBYTE_LEADING_CODE 0xF8 | |
61 | ||
8bc28f69 KH |
62 | /* Nonzero iff C is a character that corresponds to a raw 8-bit |
63 | byte. */ | |
64 | #define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR) | |
65 | ||
885317d8 | 66 | /* Return the character code for raw 8-bit byte BYTE. */ |
0168c3d8 | 67 | #define BYTE8_TO_CHAR(byte) ((byte) + 0x3FFF00) |
885317d8 | 68 | |
4c0354d7 SM |
69 | #define UNIBYTE_TO_CHAR(byte) \ |
70 | (ASCII_BYTE_P (byte) ? (byte) : BYTE8_TO_CHAR (byte)) | |
71 | ||
885317d8 | 72 | /* Return the raw 8-bit byte for character C. */ |
8bc28f69 KH |
73 | #define CHAR_TO_BYTE8(c) \ |
74 | (CHAR_BYTE8_P (c) \ | |
75 | ? (c) - 0x3FFF00 \ | |
461c2ab9 | 76 | : multibyte_char_to_unibyte (c)) |
885317d8 | 77 | |
2afc21f5 SM |
78 | /* Return the raw 8-bit byte for character C, |
79 | or -1 if C doesn't correspond to a byte. */ | |
80 | #define CHAR_TO_BYTE_SAFE(c) \ | |
81 | (CHAR_BYTE8_P (c) \ | |
82 | ? (c) - 0x3FFF00 \ | |
455af463 | 83 | : multibyte_char_to_unibyte_safe (c)) |
2afc21f5 | 84 | |
885317d8 KH |
85 | /* Nonzero iff BYTE is the 1st byte of a multibyte form of a character |
86 | that corresponds to a raw 8-bit byte. */ | |
0168c3d8 KH |
87 | #define CHAR_BYTE8_HEAD_P(byte) ((byte) == 0xC0 || (byte) == 0xC1) |
88 | ||
43c47483 KH |
89 | /* If C is not ASCII, make it unibyte. */ |
90 | #define MAKE_CHAR_UNIBYTE(c) \ | |
91 | do { \ | |
92 | if (! ASCII_CHAR_P (c)) \ | |
93 | c = CHAR_TO_BYTE8 (c); \ | |
94 | } while (0) | |
3e411074 | 95 | |
3e411074 | 96 | |
18a2979d | 97 | /* If C is not ASCII, make it multibyte. Assumes C < 256. */ |
c0dc8f64 | 98 | #define MAKE_CHAR_MULTIBYTE(c) \ |
4c0354d7 | 99 | (eassert ((c) >= 0 && (c) < 256), (c) = UNIBYTE_TO_CHAR (c)) |
3e411074 | 100 | |
885317d8 | 101 | /* This is the maximum byte length of multibyte form. */ |
0168c3d8 KH |
102 | #define MAX_MULTIBYTE_LENGTH 5 |
103 | ||
18a2979d | 104 | /* Return a Lisp character whose character code is C. Assumes C is |
b583cead | 105 | a valid character code. */ |
0168c3d8 KH |
106 | #define make_char(c) make_number (c) |
107 | ||
108 | /* Nonzero iff C is an ASCII byte. */ | |
ea204efb | 109 | #define ASCII_BYTE_P(c) UNSIGNED_CMP (c, <, 0x80) |
0168c3d8 KH |
110 | |
111 | /* Nonzero iff X is a character. */ | |
112 | #define CHARACTERP(x) (NATNUMP (x) && XFASTINT (x) <= MAX_CHAR) | |
113 | ||
2638320e PE |
114 | /* Nonzero iff C is valid as a character code. */ |
115 | #define CHAR_VALID_P(c) UNSIGNED_CMP (c, <=, MAX_CHAR) | |
0168c3d8 KH |
116 | |
117 | /* Check if Lisp object X is a character or not. */ | |
63db3c1b MB |
118 | #define CHECK_CHARACTER(x) \ |
119 | CHECK_TYPE (CHARACTERP (x), Qcharacterp, x) | |
0168c3d8 | 120 | |
8f924df7 KH |
121 | #define CHECK_CHARACTER_CAR(x) \ |
122 | do { \ | |
123 | Lisp_Object tmp = XCAR (x); \ | |
124 | CHECK_CHARACTER (tmp); \ | |
125 | XSETCAR ((x), tmp); \ | |
126 | } while (0) | |
127 | ||
128 | #define CHECK_CHARACTER_CDR(x) \ | |
129 | do { \ | |
130 | Lisp_Object tmp = XCDR (x); \ | |
131 | CHECK_CHARACTER (tmp); \ | |
132 | XSETCDR ((x), tmp); \ | |
133 | } while (0) | |
134 | ||
0168c3d8 | 135 | /* Nonzero iff C is a character of code less than 0x100. */ |
ea204efb | 136 | #define SINGLE_BYTE_CHAR_P(c) UNSIGNED_CMP (c, <, 0x100) |
0168c3d8 KH |
137 | |
138 | /* Nonzero if character C has a printable glyph. */ | |
139 | #define CHAR_PRINTABLE_P(c) \ | |
944c7a26 AS |
140 | (((c) >= 32 && (c) < 127) \ |
141 | || ! NILP (CHAR_TABLE_REF (Vprintable_chars, (c)))) | |
0168c3d8 | 142 | |
885317d8 | 143 | /* Return byte length of multibyte form for character C. */ |
0168c3d8 KH |
144 | #define CHAR_BYTES(c) \ |
145 | ( (c) <= MAX_1_BYTE_CHAR ? 1 \ | |
146 | : (c) <= MAX_2_BYTE_CHAR ? 2 \ | |
147 | : (c) <= MAX_3_BYTE_CHAR ? 3 \ | |
148 | : (c) <= MAX_4_BYTE_CHAR ? 4 \ | |
149 | : (c) <= MAX_5_BYTE_CHAR ? 5 \ | |
150 | : 2) | |
151 | ||
43c47483 KH |
152 | |
153 | /* Return the leading code of multibyte form of C. */ | |
154 | #define CHAR_LEADING_CODE(c) \ | |
155 | ((c) <= MAX_1_BYTE_CHAR ? c \ | |
156 | : (c) <= MAX_2_BYTE_CHAR ? (0xC0 | ((c) >> 6)) \ | |
157 | : (c) <= MAX_3_BYTE_CHAR ? (0xE0 | ((c) >> 12)) \ | |
158 | : (c) <= MAX_4_BYTE_CHAR ? (0xF0 | ((c) >> 18)) \ | |
159 | : (c) <= MAX_5_BYTE_CHAR ? 0xF8 \ | |
160 | : (0xC0 | (((c) >> 6) & 0x01))) | |
161 | ||
162 | ||
885317d8 KH |
163 | /* Store multibyte form of the character C in P. The caller should |
164 | allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance. | |
165 | Returns the length of the multibyte form. */ | |
0168c3d8 KH |
166 | |
167 | #define CHAR_STRING(c, p) \ | |
ea204efb | 168 | (UNSIGNED_CMP (c, <=, MAX_1_BYTE_CHAR) \ |
0168c3d8 KH |
169 | ? ((p)[0] = (c), \ |
170 | 1) \ | |
ea204efb | 171 | : UNSIGNED_CMP (c, <=, MAX_2_BYTE_CHAR) \ |
0168c3d8 KH |
172 | ? ((p)[0] = (0xC0 | ((c) >> 6)), \ |
173 | (p)[1] = (0x80 | ((c) & 0x3F)), \ | |
174 | 2) \ | |
ea204efb | 175 | : UNSIGNED_CMP (c, <=, MAX_3_BYTE_CHAR) \ |
0168c3d8 KH |
176 | ? ((p)[0] = (0xE0 | ((c) >> 12)), \ |
177 | (p)[1] = (0x80 | (((c) >> 6) & 0x3F)), \ | |
178 | (p)[2] = (0x80 | ((c) & 0x3F)), \ | |
179 | 3) \ | |
a2a01861 | 180 | : verify_expr (sizeof (c) <= sizeof (unsigned), char_string (c, p))) |
0168c3d8 | 181 | |
eb41da4c KH |
182 | /* Store multibyte form of byte B in P. The caller should allocate at |
183 | least MAX_MULTIBYTE_LENGTH bytes area at P in advance. Returns the | |
184 | length of the multibyte form. */ | |
1106ea2b KH |
185 | |
186 | #define BYTE8_STRING(b, p) \ | |
187 | ((p)[0] = (0xC0 | (((b) >> 6) & 0x01)), \ | |
7f464917 | 188 | (p)[1] = (0x80 | ((b) & 0x3F)), \ |
1106ea2b KH |
189 | 2) |
190 | ||
0168c3d8 | 191 | |
18a2979d EZ |
192 | /* Store multibyte form of the character C in P and advance P to the |
193 | end of the multibyte form. The caller should allocate at least | |
194 | MAX_MULTIBYTE_LENGTH bytes area at P in advance. */ | |
0168c3d8 | 195 | |
eb41da4c KH |
196 | #define CHAR_STRING_ADVANCE(c, p) \ |
197 | do { \ | |
198 | if ((c) <= MAX_1_BYTE_CHAR) \ | |
199 | *(p)++ = (c); \ | |
200 | else if ((c) <= MAX_2_BYTE_CHAR) \ | |
201 | *(p)++ = (0xC0 | ((c) >> 6)), \ | |
202 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
203 | else if ((c) <= MAX_3_BYTE_CHAR) \ | |
204 | *(p)++ = (0xE0 | ((c) >> 12)), \ | |
205 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ | |
206 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
207 | else \ | |
13bdea59 PE |
208 | { \ |
209 | verify (sizeof (c) <= sizeof (unsigned)); \ | |
210 | (p) += char_string (c, p); \ | |
211 | } \ | |
885317d8 | 212 | } while (0) |
0168c3d8 | 213 | |
eb41da4c | 214 | |
0168c3d8 KH |
215 | /* Nonzero iff BYTE starts a non-ASCII character in a multibyte |
216 | form. */ | |
217 | #define LEADING_CODE_P(byte) (((byte) & 0xC0) == 0xC0) | |
218 | ||
b5c7dbe6 KH |
219 | /* Nonzero iff BYTE is a trailing code of a non-ASCII character in a |
220 | multibyte form. */ | |
221 | #define TRAILING_CODE_P(byte) (((byte) & 0xC0) == 0x80) | |
222 | ||
885317d8 KH |
223 | /* Nonzero iff BYTE starts a character in a multibyte form. |
224 | This is equivalent to: | |
225 | (ASCII_BYTE_P (byte) || LEADING_CODE_P (byte)) */ | |
226 | #define CHAR_HEAD_P(byte) (((byte) & 0xC0) != 0x80) | |
227 | ||
0168c3d8 KH |
228 | /* How many bytes a character that starts with BYTE occupies in a |
229 | multibyte form. */ | |
230 | #define BYTES_BY_CHAR_HEAD(byte) \ | |
231 | (!((byte) & 0x80) ? 1 \ | |
232 | : !((byte) & 0x20) ? 2 \ | |
233 | : !((byte) & 0x10) ? 3 \ | |
234 | : !((byte) & 0x08) ? 4 \ | |
235 | : 5) | |
236 | ||
237 | ||
0168c3d8 | 238 | /* The byte length of multibyte form at unibyte string P ending at |
18a2979d | 239 | PEND. If STR doesn't point to a valid multibyte form, return 0. */ |
0168c3d8 KH |
240 | |
241 | #define MULTIBYTE_LENGTH(p, pend) \ | |
242 | (p >= pend ? 0 \ | |
243 | : !((p)[0] & 0x80) ? 1 \ | |
244 | : ((p + 1 >= pend) || (((p)[1] & 0xC0) != 0x80)) ? 0 \ | |
245 | : ((p)[0] & 0xE0) == 0xC0 ? 2 \ | |
246 | : ((p + 2 >= pend) || (((p)[2] & 0xC0) != 0x80)) ? 0 \ | |
247 | : ((p)[0] & 0xF0) == 0xE0 ? 3 \ | |
248 | : ((p + 3 >= pend) || (((p)[3] & 0xC0) != 0x80)) ? 0 \ | |
249 | : ((p)[0] & 0xF8) == 0xF0 ? 4 \ | |
250 | : ((p + 4 >= pend) || (((p)[4] & 0xC0) != 0x80)) ? 0 \ | |
251 | : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \ | |
252 | : 0) | |
253 | ||
254 | ||
18a2979d | 255 | /* Like MULTIBYTE_LENGTH, but don't check the ending address. */ |
0168c3d8 KH |
256 | |
257 | #define MULTIBYTE_LENGTH_NO_CHECK(p) \ | |
258 | (!((p)[0] & 0x80) ? 1 \ | |
259 | : ((p)[1] & 0xC0) != 0x80 ? 0 \ | |
260 | : ((p)[0] & 0xE0) == 0xC0 ? 2 \ | |
261 | : ((p)[2] & 0xC0) != 0x80 ? 0 \ | |
262 | : ((p)[0] & 0xF0) == 0xE0 ? 3 \ | |
263 | : ((p)[3] & 0xC0) != 0x80 ? 0 \ | |
264 | : ((p)[0] & 0xF8) == 0xF0 ? 4 \ | |
265 | : ((p)[4] & 0xC0) != 0x80 ? 0 \ | |
266 | : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \ | |
267 | : 0) | |
268 | ||
18a2979d EZ |
269 | /* If P is before LIMIT, advance P to the next character boundary. |
270 | Assumes that P is already at a character boundary of the same | |
78edd3b7 | 271 | multibyte form whose end address is LIMIT. */ |
8f924df7 KH |
272 | |
273 | #define NEXT_CHAR_BOUNDARY(p, limit) \ | |
274 | do { \ | |
275 | if ((p) < (limit)) \ | |
276 | (p) += BYTES_BY_CHAR_HEAD (*(p)); \ | |
277 | } while (0) | |
278 | ||
279 | ||
280 | /* If P is after LIMIT, advance P to the previous character boundary. | |
18a2979d | 281 | Assumes that P is already at a character boundary of the same |
ce5b453a | 282 | multibyte form whose beginning address is LIMIT. */ |
8f924df7 KH |
283 | |
284 | #define PREV_CHAR_BOUNDARY(p, limit) \ | |
285 | do { \ | |
286 | if ((p) > (limit)) \ | |
287 | { \ | |
760fbc2c | 288 | const unsigned char *chp = (p); \ |
8f924df7 | 289 | do { \ |
760fbc2c PE |
290 | chp--; \ |
291 | } while (chp >= limit && ! CHAR_HEAD_P (*chp)); \ | |
292 | (p) = (BYTES_BY_CHAR_HEAD (*chp) == (p) - chp) ? chp : (p) - 1; \ | |
8f924df7 KH |
293 | } \ |
294 | } while (0) | |
0168c3d8 KH |
295 | |
296 | /* Return the character code of character whose multibyte form is at | |
2f8e16b2 EZ |
297 | P. Note that this macro unifies CJK characters whose codepoints |
298 | are in the Private Use Areas (PUAs), so it might return a different | |
299 | codepoint from the one actually stored at P. */ | |
0168c3d8 | 300 | |
62a6e103 | 301 | #define STRING_CHAR(p) \ |
0168c3d8 KH |
302 | (!((p)[0] & 0x80) \ |
303 | ? (p)[0] \ | |
304 | : ! ((p)[0] & 0x20) \ | |
305 | ? (((((p)[0] & 0x1F) << 6) \ | |
306 | | ((p)[1] & 0x3F)) \ | |
307 | + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0)) \ | |
308 | : ! ((p)[0] & 0x10) \ | |
309 | ? ((((p)[0] & 0x0F) << 12) \ | |
310 | | (((p)[1] & 0x3F) << 6) \ | |
311 | | ((p)[2] & 0x3F)) \ | |
eb41da4c | 312 | : string_char ((p), NULL, NULL)) |
0168c3d8 KH |
313 | |
314 | ||
18a2979d | 315 | /* Like STRING_CHAR, but set ACTUAL_LEN to the length of multibyte |
2f8e16b2 EZ |
316 | form. |
317 | ||
318 | Note: This macro returns the actual length of the character's | |
319 | multibyte sequence as it is stored in a buffer or string. The | |
320 | character it returns might have a different codepoint that has a | |
5ae255c7 | 321 | different multibyte sequence of a different length, due to possible |
2f8e16b2 EZ |
322 | unification of CJK characters inside string_char. Therefore do NOT |
323 | assume that the length returned by this macro is identical to the | |
324 | length of the multibyte sequence of the character it returns. */ | |
0168c3d8 | 325 | |
62a6e103 | 326 | #define STRING_CHAR_AND_LENGTH(p, actual_len) \ |
0168c3d8 KH |
327 | (!((p)[0] & 0x80) \ |
328 | ? ((actual_len) = 1, (p)[0]) \ | |
329 | : ! ((p)[0] & 0x20) \ | |
330 | ? ((actual_len) = 2, \ | |
331 | (((((p)[0] & 0x1F) << 6) \ | |
332 | | ((p)[1] & 0x3F)) \ | |
333 | + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
334 | : ! ((p)[0] & 0x10) \ | |
335 | ? ((actual_len) = 3, \ | |
336 | ((((p)[0] & 0x0F) << 12) \ | |
337 | | (((p)[1] & 0x3F) << 6) \ | |
338 | | ((p)[2] & 0x3F))) \ | |
eb41da4c | 339 | : string_char ((p), NULL, &actual_len)) |
0168c3d8 KH |
340 | |
341 | ||
18a2979d | 342 | /* Like STRING_CHAR, but advance P to the end of multibyte form. */ |
0168c3d8 KH |
343 | |
344 | #define STRING_CHAR_ADVANCE(p) \ | |
345 | (!((p)[0] & 0x80) \ | |
346 | ? *(p)++ \ | |
347 | : ! ((p)[0] & 0x20) \ | |
348 | ? ((p) += 2, \ | |
349 | ((((p)[-2] & 0x1F) << 6) \ | |
350 | | ((p)[-1] & 0x3F) \ | |
8f924df7 | 351 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ |
0168c3d8 KH |
352 | : ! ((p)[0] & 0x10) \ |
353 | ? ((p) += 3, \ | |
354 | ((((p)[-3] & 0x0F) << 12) \ | |
355 | | (((p)[-2] & 0x3F) << 6) \ | |
356 | | ((p)[-1] & 0x3F))) \ | |
eb41da4c | 357 | : string_char ((p), &(p), NULL)) |
0168c3d8 KH |
358 | |
359 | ||
360 | /* Fetch the "next" character from Lisp string STRING at byte position | |
361 | BYTEIDX, character position CHARIDX. Store it into OUTPUT. | |
362 | ||
363 | All the args must be side-effect-free. | |
364 | BYTEIDX and CHARIDX must be lvalues; | |
365 | we increment them past the character fetched. */ | |
366 | ||
367 | #define FETCH_STRING_CHAR_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 368 | do \ |
0168c3d8 KH |
369 | { \ |
370 | CHARIDX++; \ | |
371 | if (STRING_MULTIBYTE (STRING)) \ | |
372 | { \ | |
760fbc2c PE |
373 | unsigned char *chp = &SDATA (STRING)[BYTEIDX]; \ |
374 | int chlen; \ | |
0168c3d8 | 375 | \ |
760fbc2c PE |
376 | OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \ |
377 | BYTEIDX += chlen; \ | |
0168c3d8 KH |
378 | } \ |
379 | else \ | |
f1c99628 SM |
380 | { \ |
381 | OUTPUT = SREF (STRING, BYTEIDX); \ | |
382 | BYTEIDX++; \ | |
383 | } \ | |
0168c3d8 | 384 | } \ |
a1c2ac9a | 385 | while (0) |
0168c3d8 | 386 | |
18a2979d EZ |
387 | /* Like FETCH_STRING_CHAR_ADVANCE, but return a multibyte character |
388 | even if STRING is unibyte. */ | |
43c47483 KH |
389 | |
390 | #define FETCH_STRING_CHAR_AS_MULTIBYTE_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 391 | do \ |
43c47483 KH |
392 | { \ |
393 | CHARIDX++; \ | |
394 | if (STRING_MULTIBYTE (STRING)) \ | |
395 | { \ | |
760fbc2c PE |
396 | unsigned char *chp = &SDATA (STRING)[BYTEIDX]; \ |
397 | int chlen; \ | |
43c47483 | 398 | \ |
760fbc2c PE |
399 | OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \ |
400 | BYTEIDX += chlen; \ | |
43c47483 KH |
401 | } \ |
402 | else \ | |
403 | { \ | |
f1c99628 SM |
404 | OUTPUT = SREF (STRING, BYTEIDX); \ |
405 | BYTEIDX++; \ | |
43c47483 KH |
406 | MAKE_CHAR_MULTIBYTE (OUTPUT); \ |
407 | } \ | |
408 | } \ | |
a1c2ac9a | 409 | while (0) |
43c47483 | 410 | |
0168c3d8 | 411 | |
18a2979d | 412 | /* Like FETCH_STRING_CHAR_ADVANCE, but assumes STRING is multibyte. */ |
0168c3d8 KH |
413 | |
414 | #define FETCH_STRING_CHAR_ADVANCE_NO_CHECK(OUTPUT, STRING, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 415 | do \ |
0168c3d8 | 416 | { \ |
a6670b0b PE |
417 | unsigned char *fetch_ptr = &SDATA (STRING)[BYTEIDX]; \ |
418 | int fetch_len; \ | |
0168c3d8 | 419 | \ |
a6670b0b PE |
420 | OUTPUT = STRING_CHAR_AND_LENGTH (fetch_ptr, fetch_len); \ |
421 | BYTEIDX += fetch_len; \ | |
0168c3d8 KH |
422 | CHARIDX++; \ |
423 | } \ | |
a1c2ac9a | 424 | while (0) |
0168c3d8 KH |
425 | |
426 | ||
18a2979d | 427 | /* Like FETCH_STRING_CHAR_ADVANCE, but fetch character from the current |
0168c3d8 KH |
428 | buffer. */ |
429 | ||
430 | #define FETCH_CHAR_ADVANCE(OUTPUT, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 431 | do \ |
0168c3d8 KH |
432 | { \ |
433 | CHARIDX++; \ | |
4b4deea2 | 434 | if (!NILP (BVAR (current_buffer, enable_multibyte_characters))) \ |
0168c3d8 | 435 | { \ |
760fbc2c PE |
436 | unsigned char *chp = BYTE_POS_ADDR (BYTEIDX); \ |
437 | int chlen; \ | |
0168c3d8 | 438 | \ |
e8d32c7e | 439 | OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \ |
760fbc2c | 440 | BYTEIDX += chlen; \ |
0168c3d8 KH |
441 | } \ |
442 | else \ | |
443 | { \ | |
444 | OUTPUT = *(BYTE_POS_ADDR (BYTEIDX)); \ | |
445 | BYTEIDX++; \ | |
446 | } \ | |
447 | } \ | |
a1c2ac9a | 448 | while (0) |
0168c3d8 KH |
449 | |
450 | ||
18a2979d | 451 | /* Like FETCH_CHAR_ADVANCE, but assumes the current buffer is multibyte. */ |
0168c3d8 KH |
452 | |
453 | #define FETCH_CHAR_ADVANCE_NO_CHECK(OUTPUT, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 454 | do \ |
0168c3d8 | 455 | { \ |
760fbc2c PE |
456 | unsigned char *chp = BYTE_POS_ADDR (BYTEIDX); \ |
457 | int chlen; \ | |
0168c3d8 | 458 | \ |
760fbc2c PE |
459 | OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \ |
460 | BYTEIDX += chlen; \ | |
0168c3d8 KH |
461 | CHARIDX++; \ |
462 | } \ | |
a1c2ac9a | 463 | while (0) |
0168c3d8 KH |
464 | |
465 | ||
18a2979d | 466 | /* Increment the buffer byte position POS_BYTE of the current buffer to |
0168c3d8 KH |
467 | the next character boundary. No range checking of POS. */ |
468 | ||
469 | #define INC_POS(pos_byte) \ | |
470 | do { \ | |
760fbc2c PE |
471 | unsigned char *chp = BYTE_POS_ADDR (pos_byte); \ |
472 | pos_byte += BYTES_BY_CHAR_HEAD (*chp); \ | |
0168c3d8 KH |
473 | } while (0) |
474 | ||
475 | ||
18a2979d | 476 | /* Decrement the buffer byte position POS_BYTE of the current buffer to |
0168c3d8 KH |
477 | the previous character boundary. No range checking of POS. */ |
478 | ||
479 | #define DEC_POS(pos_byte) \ | |
480 | do { \ | |
760fbc2c | 481 | unsigned char *chp; \ |
0168c3d8 KH |
482 | \ |
483 | pos_byte--; \ | |
484 | if (pos_byte < GPT_BYTE) \ | |
760fbc2c | 485 | chp = BEG_ADDR + pos_byte - BEG_BYTE; \ |
0168c3d8 | 486 | else \ |
760fbc2c PE |
487 | chp = BEG_ADDR + GAP_SIZE + pos_byte - BEG_BYTE; \ |
488 | while (!CHAR_HEAD_P (*chp)) \ | |
0168c3d8 | 489 | { \ |
760fbc2c | 490 | chp--; \ |
0168c3d8 KH |
491 | pos_byte--; \ |
492 | } \ | |
493 | } while (0) | |
494 | ||
495 | /* Increment both CHARPOS and BYTEPOS, each in the appropriate way. */ | |
496 | ||
497 | #define INC_BOTH(charpos, bytepos) \ | |
498 | do \ | |
499 | { \ | |
500 | (charpos)++; \ | |
4b4deea2 | 501 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) \ |
0168c3d8 KH |
502 | (bytepos)++; \ |
503 | else \ | |
504 | INC_POS ((bytepos)); \ | |
505 | } \ | |
506 | while (0) | |
507 | ||
508 | ||
509 | /* Decrement both CHARPOS and BYTEPOS, each in the appropriate way. */ | |
510 | ||
511 | #define DEC_BOTH(charpos, bytepos) \ | |
512 | do \ | |
513 | { \ | |
514 | (charpos)--; \ | |
4b4deea2 | 515 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) \ |
0168c3d8 KH |
516 | (bytepos)--; \ |
517 | else \ | |
518 | DEC_POS ((bytepos)); \ | |
519 | } \ | |
520 | while (0) | |
521 | ||
522 | ||
18a2979d | 523 | /* Increment the buffer byte position POS_BYTE of the current buffer to |
0168c3d8 KH |
524 | the next character boundary. This macro relies on the fact that |
525 | *GPT_ADDR and *Z_ADDR are always accessible and the values are | |
526 | '\0'. No range checking of POS_BYTE. */ | |
527 | ||
528 | #define BUF_INC_POS(buf, pos_byte) \ | |
529 | do { \ | |
760fbc2c PE |
530 | unsigned char *chp = BUF_BYTE_ADDRESS (buf, pos_byte); \ |
531 | pos_byte += BYTES_BY_CHAR_HEAD (*chp); \ | |
0168c3d8 KH |
532 | } while (0) |
533 | ||
534 | ||
18a2979d | 535 | /* Decrement the buffer byte position POS_BYTE of the current buffer to |
0168c3d8 KH |
536 | the previous character boundary. No range checking of POS_BYTE. */ |
537 | ||
538 | #define BUF_DEC_POS(buf, pos_byte) \ | |
539 | do { \ | |
760fbc2c | 540 | unsigned char *chp; \ |
0168c3d8 KH |
541 | pos_byte--; \ |
542 | if (pos_byte < BUF_GPT_BYTE (buf)) \ | |
760fbc2c | 543 | chp = BUF_BEG_ADDR (buf) + pos_byte - BEG_BYTE; \ |
0168c3d8 | 544 | else \ |
760fbc2c PE |
545 | chp = BUF_BEG_ADDR (buf) + BUF_GAP_SIZE (buf) + pos_byte - BEG_BYTE;\ |
546 | while (!CHAR_HEAD_P (*chp)) \ | |
0168c3d8 | 547 | { \ |
760fbc2c | 548 | chp--; \ |
0168c3d8 KH |
549 | pos_byte--; \ |
550 | } \ | |
551 | } while (0) | |
552 | ||
553 | ||
a2271ba2 PE |
554 | /* Return a non-outlandish value for the tab width. */ |
555 | ||
5637687f PE |
556 | #define SANE_TAB_WIDTH(buf) \ |
557 | sanitize_tab_width (XFASTINT (BVAR (buf, tab_width))) | |
00382e8b | 558 | INLINE int |
5637687f | 559 | sanitize_tab_width (EMACS_INT width) |
a2271ba2 PE |
560 | { |
561 | return 0 < width && width <= 1000 ? width : 8; | |
562 | } | |
563 | ||
0168c3d8 | 564 | /* Return the width of ASCII character C. The width is measured by |
18a2979d | 565 | how many columns C will occupy on the screen when displayed in the |
0168c3d8 KH |
566 | current buffer. */ |
567 | ||
568 | #define ASCII_CHAR_WIDTH(c) \ | |
569 | (c < 0x20 \ | |
570 | ? (c == '\t' \ | |
a2271ba2 | 571 | ? SANE_TAB_WIDTH (current_buffer) \ |
4b4deea2 | 572 | : (c == '\n' ? 0 : (NILP (BVAR (current_buffer, ctl_arrow)) ? 4 : 2))) \ |
0168c3d8 KH |
573 | : (c < 0x7f \ |
574 | ? 1 \ | |
4b4deea2 | 575 | : ((NILP (BVAR (current_buffer, ctl_arrow)) ? 4 : 2)))) |
0168c3d8 | 576 | |
5637687f PE |
577 | /* Return a non-outlandish value for a character width. */ |
578 | ||
00382e8b | 579 | INLINE int |
5637687f PE |
580 | sanitize_char_width (EMACS_INT width) |
581 | { | |
582 | return 0 <= width && width <= 1000 ? width : 1000; | |
583 | } | |
584 | ||
0168c3d8 | 585 | /* Return the width of character C. The width is measured by how many |
18a2979d | 586 | columns C will occupy on the screen when displayed in the current |
0168c3d8 KH |
587 | buffer. */ |
588 | ||
589 | #define CHAR_WIDTH(c) \ | |
590 | (ASCII_CHAR_P (c) \ | |
591 | ? ASCII_CHAR_WIDTH (c) \ | |
5637687f | 592 | : sanitize_char_width (XINT (CHAR_TABLE_REF (Vchar_width_table, c)))) |
0168c3d8 | 593 | |
e1dbe924 | 594 | /* If C is a variation selector, return the index of the |
c19cab20 KH |
595 | variation selector (1..256). Otherwise, return 0. */ |
596 | ||
597 | #define CHAR_VARIATION_SELECTOR_P(c) \ | |
598 | ((c) < 0xFE00 ? 0 \ | |
599 | : (c) <= 0xFE0F ? (c) - 0xFE00 + 1 \ | |
600 | : (c) < 0xE0100 ? 0 \ | |
601 | : (c) <= 0xE01EF ? (c) - 0xE0100 + 17 \ | |
602 | : 0) | |
603 | ||
604 | /* If C is a high surrogate, return 1. If C is a low surrogate, | |
409f2919 | 605 | return 0. Otherwise, return 0. */ |
c19cab20 KH |
606 | |
607 | #define CHAR_SURROGATE_PAIR_P(c) \ | |
608 | ((c) < 0xD800 ? 0 \ | |
609 | : (c) <= 0xDBFF ? 1 \ | |
610 | : (c) <= 0xDFFF ? 2 \ | |
611 | : 0) | |
612 | ||
c805dec0 KH |
613 | /* Data type for Unicode general category. |
614 | ||
615 | The order of members must be in sync with the 8th element of the | |
616 | member of unidata-prop-alist (in admin/unidata/unidata-getn.el) for | |
617 | Unicode character property `general-category'. */ | |
618 | ||
619 | typedef enum { | |
620 | UNICODE_CATEGORY_UNKNOWN = 0, | |
621 | UNICODE_CATEGORY_Lu, | |
622 | UNICODE_CATEGORY_Ll, | |
623 | UNICODE_CATEGORY_Lt, | |
624 | UNICODE_CATEGORY_Lm, | |
625 | UNICODE_CATEGORY_Lo, | |
626 | UNICODE_CATEGORY_Mn, | |
627 | UNICODE_CATEGORY_Mc, | |
628 | UNICODE_CATEGORY_Me, | |
629 | UNICODE_CATEGORY_Nd, | |
630 | UNICODE_CATEGORY_Nl, | |
631 | UNICODE_CATEGORY_No, | |
632 | UNICODE_CATEGORY_Pc, | |
633 | UNICODE_CATEGORY_Pd, | |
634 | UNICODE_CATEGORY_Ps, | |
635 | UNICODE_CATEGORY_Pe, | |
636 | UNICODE_CATEGORY_Pi, | |
637 | UNICODE_CATEGORY_Pf, | |
638 | UNICODE_CATEGORY_Po, | |
639 | UNICODE_CATEGORY_Sm, | |
640 | UNICODE_CATEGORY_Sc, | |
641 | UNICODE_CATEGORY_Sk, | |
642 | UNICODE_CATEGORY_So, | |
643 | UNICODE_CATEGORY_Zs, | |
644 | UNICODE_CATEGORY_Zl, | |
645 | UNICODE_CATEGORY_Zp, | |
646 | UNICODE_CATEGORY_Cc, | |
647 | UNICODE_CATEGORY_Cf, | |
648 | UNICODE_CATEGORY_Cs, | |
649 | UNICODE_CATEGORY_Co, | |
650 | UNICODE_CATEGORY_Cn | |
651 | } unicode_category_t; | |
c19cab20 | 652 | |
5994c183 | 653 | extern EMACS_INT char_resolve_modifier_mask (EMACS_INT) ATTRIBUTE_CONST; |
383e0970 J |
654 | extern int char_string (unsigned, unsigned char *); |
655 | extern int string_char (const unsigned char *, | |
656 | const unsigned char **, int *); | |
657 | ||
658 | extern int translate_char (Lisp_Object, int c); | |
14162469 | 659 | extern void parse_str_as_multibyte (const unsigned char *, |
d311d28c PE |
660 | ptrdiff_t, ptrdiff_t *, ptrdiff_t *); |
661 | extern ptrdiff_t count_size_as_multibyte (const unsigned char *, ptrdiff_t); | |
662 | extern ptrdiff_t str_as_multibyte (unsigned char *, ptrdiff_t, ptrdiff_t, | |
663 | ptrdiff_t *); | |
664 | extern ptrdiff_t str_to_multibyte (unsigned char *, ptrdiff_t, ptrdiff_t); | |
665 | extern ptrdiff_t str_as_unibyte (unsigned char *, ptrdiff_t); | |
666 | extern ptrdiff_t str_to_unibyte (const unsigned char *, unsigned char *, | |
d5172d4f | 667 | ptrdiff_t); |
d311d28c PE |
668 | extern ptrdiff_t strwidth (const char *, ptrdiff_t); |
669 | extern ptrdiff_t c_string_width (const unsigned char *, ptrdiff_t, int, | |
670 | ptrdiff_t *, ptrdiff_t *); | |
671 | extern ptrdiff_t lisp_string_width (Lisp_Object, ptrdiff_t, | |
672 | ptrdiff_t *, ptrdiff_t *); | |
0168c3d8 | 673 | |
955cbe7b | 674 | extern Lisp_Object Qcharacterp; |
0168c3d8 | 675 | extern Lisp_Object Vchar_unify_table; |
383e0970 | 676 | extern Lisp_Object string_escape_byte8 (Lisp_Object); |
fac2bdc4 | 677 | |
0168c3d8 KH |
678 | /* Return a translation table of id number ID. */ |
679 | #define GET_TRANSLATION_TABLE(id) \ | |
91f2d272 | 680 | (XCDR (XVECTOR (Vtranslation_table_vector)->contents[(id)])) |
0168c3d8 | 681 | |
f162bcc3 PE |
682 | INLINE_HEADER_END |
683 | ||
0168c3d8 | 684 | #endif /* EMACS_CHARACTER_H */ |