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 | 69 | #define UNIBYTE_TO_CHAR(byte) \ |
200fc949 | 70 | (ASCII_CHAR_P (byte) ? (byte) : BYTE8_TO_CHAR (byte)) |
4c0354d7 | 71 | |
885317d8 | 72 | /* Return the raw 8-bit byte for character C. */ |
200fc949 | 73 | #define CHAR_TO_BYTE8(c) (CHAR_BYTE8_P (c) ? (c) - 0x3FFF00 : (c & 0xFF)) |
885317d8 | 74 | |
2afc21f5 SM |
75 | /* Return the raw 8-bit byte for character C, |
76 | or -1 if C doesn't correspond to a byte. */ | |
200fc949 DA |
77 | #define CHAR_TO_BYTE_SAFE(c) \ |
78 | (ASCII_CHAR_P (c) ? c : (CHAR_BYTE8_P (c) ? (c) - 0x3FFF00 : -1)) | |
2afc21f5 | 79 | |
885317d8 KH |
80 | /* Nonzero iff BYTE is the 1st byte of a multibyte form of a character |
81 | that corresponds to a raw 8-bit byte. */ | |
0168c3d8 KH |
82 | #define CHAR_BYTE8_HEAD_P(byte) ((byte) == 0xC0 || (byte) == 0xC1) |
83 | ||
43c47483 KH |
84 | /* If C is not ASCII, make it unibyte. */ |
85 | #define MAKE_CHAR_UNIBYTE(c) \ | |
86 | do { \ | |
87 | if (! ASCII_CHAR_P (c)) \ | |
88 | c = CHAR_TO_BYTE8 (c); \ | |
96c06863 | 89 | } while (false) |
3e411074 | 90 | |
3e411074 | 91 | |
18a2979d | 92 | /* If C is not ASCII, make it multibyte. Assumes C < 256. */ |
c0dc8f64 | 93 | #define MAKE_CHAR_MULTIBYTE(c) \ |
4c0354d7 | 94 | (eassert ((c) >= 0 && (c) < 256), (c) = UNIBYTE_TO_CHAR (c)) |
3e411074 | 95 | |
885317d8 | 96 | /* This is the maximum byte length of multibyte form. */ |
0168c3d8 KH |
97 | #define MAX_MULTIBYTE_LENGTH 5 |
98 | ||
0168c3d8 KH |
99 | /* Nonzero iff X is a character. */ |
100 | #define CHARACTERP(x) (NATNUMP (x) && XFASTINT (x) <= MAX_CHAR) | |
101 | ||
2638320e PE |
102 | /* Nonzero iff C is valid as a character code. */ |
103 | #define CHAR_VALID_P(c) UNSIGNED_CMP (c, <=, MAX_CHAR) | |
0168c3d8 KH |
104 | |
105 | /* Check if Lisp object X is a character or not. */ | |
63db3c1b MB |
106 | #define CHECK_CHARACTER(x) \ |
107 | CHECK_TYPE (CHARACTERP (x), Qcharacterp, x) | |
0168c3d8 | 108 | |
8f924df7 KH |
109 | #define CHECK_CHARACTER_CAR(x) \ |
110 | do { \ | |
111 | Lisp_Object tmp = XCAR (x); \ | |
112 | CHECK_CHARACTER (tmp); \ | |
113 | XSETCAR ((x), tmp); \ | |
96c06863 | 114 | } while (false) |
8f924df7 KH |
115 | |
116 | #define CHECK_CHARACTER_CDR(x) \ | |
117 | do { \ | |
118 | Lisp_Object tmp = XCDR (x); \ | |
119 | CHECK_CHARACTER (tmp); \ | |
120 | XSETCDR ((x), tmp); \ | |
96c06863 | 121 | } while (false) |
8f924df7 | 122 | |
0168c3d8 | 123 | /* Nonzero iff C is a character of code less than 0x100. */ |
ea204efb | 124 | #define SINGLE_BYTE_CHAR_P(c) UNSIGNED_CMP (c, <, 0x100) |
0168c3d8 KH |
125 | |
126 | /* Nonzero if character C has a printable glyph. */ | |
127 | #define CHAR_PRINTABLE_P(c) \ | |
944c7a26 AS |
128 | (((c) >= 32 && (c) < 127) \ |
129 | || ! NILP (CHAR_TABLE_REF (Vprintable_chars, (c)))) | |
0168c3d8 | 130 | |
885317d8 | 131 | /* Return byte length of multibyte form for character C. */ |
0168c3d8 KH |
132 | #define CHAR_BYTES(c) \ |
133 | ( (c) <= MAX_1_BYTE_CHAR ? 1 \ | |
134 | : (c) <= MAX_2_BYTE_CHAR ? 2 \ | |
135 | : (c) <= MAX_3_BYTE_CHAR ? 3 \ | |
136 | : (c) <= MAX_4_BYTE_CHAR ? 4 \ | |
137 | : (c) <= MAX_5_BYTE_CHAR ? 5 \ | |
138 | : 2) | |
139 | ||
43c47483 KH |
140 | |
141 | /* Return the leading code of multibyte form of C. */ | |
142 | #define CHAR_LEADING_CODE(c) \ | |
143 | ((c) <= MAX_1_BYTE_CHAR ? c \ | |
144 | : (c) <= MAX_2_BYTE_CHAR ? (0xC0 | ((c) >> 6)) \ | |
145 | : (c) <= MAX_3_BYTE_CHAR ? (0xE0 | ((c) >> 12)) \ | |
146 | : (c) <= MAX_4_BYTE_CHAR ? (0xF0 | ((c) >> 18)) \ | |
147 | : (c) <= MAX_5_BYTE_CHAR ? 0xF8 \ | |
148 | : (0xC0 | (((c) >> 6) & 0x01))) | |
149 | ||
150 | ||
885317d8 KH |
151 | /* Store multibyte form of the character C in P. The caller should |
152 | allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance. | |
153 | Returns the length of the multibyte form. */ | |
0168c3d8 KH |
154 | |
155 | #define CHAR_STRING(c, p) \ | |
ea204efb | 156 | (UNSIGNED_CMP (c, <=, MAX_1_BYTE_CHAR) \ |
0168c3d8 KH |
157 | ? ((p)[0] = (c), \ |
158 | 1) \ | |
ea204efb | 159 | : UNSIGNED_CMP (c, <=, MAX_2_BYTE_CHAR) \ |
0168c3d8 KH |
160 | ? ((p)[0] = (0xC0 | ((c) >> 6)), \ |
161 | (p)[1] = (0x80 | ((c) & 0x3F)), \ | |
162 | 2) \ | |
ea204efb | 163 | : UNSIGNED_CMP (c, <=, MAX_3_BYTE_CHAR) \ |
0168c3d8 KH |
164 | ? ((p)[0] = (0xE0 | ((c) >> 12)), \ |
165 | (p)[1] = (0x80 | (((c) >> 6) & 0x3F)), \ | |
166 | (p)[2] = (0x80 | ((c) & 0x3F)), \ | |
167 | 3) \ | |
a2a01861 | 168 | : verify_expr (sizeof (c) <= sizeof (unsigned), char_string (c, p))) |
0168c3d8 | 169 | |
eb41da4c KH |
170 | /* Store multibyte form of byte B in P. The caller should allocate at |
171 | least MAX_MULTIBYTE_LENGTH bytes area at P in advance. Returns the | |
172 | length of the multibyte form. */ | |
1106ea2b KH |
173 | |
174 | #define BYTE8_STRING(b, p) \ | |
175 | ((p)[0] = (0xC0 | (((b) >> 6) & 0x01)), \ | |
7f464917 | 176 | (p)[1] = (0x80 | ((b) & 0x3F)), \ |
1106ea2b KH |
177 | 2) |
178 | ||
0168c3d8 | 179 | |
18a2979d EZ |
180 | /* Store multibyte form of the character C in P and advance P to the |
181 | end of the multibyte form. The caller should allocate at least | |
182 | MAX_MULTIBYTE_LENGTH bytes area at P in advance. */ | |
0168c3d8 | 183 | |
eb41da4c KH |
184 | #define CHAR_STRING_ADVANCE(c, p) \ |
185 | do { \ | |
186 | if ((c) <= MAX_1_BYTE_CHAR) \ | |
187 | *(p)++ = (c); \ | |
188 | else if ((c) <= MAX_2_BYTE_CHAR) \ | |
189 | *(p)++ = (0xC0 | ((c) >> 6)), \ | |
190 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
191 | else if ((c) <= MAX_3_BYTE_CHAR) \ | |
192 | *(p)++ = (0xE0 | ((c) >> 12)), \ | |
193 | *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ | |
194 | *(p)++ = (0x80 | ((c) & 0x3F)); \ | |
195 | else \ | |
13bdea59 PE |
196 | { \ |
197 | verify (sizeof (c) <= sizeof (unsigned)); \ | |
198 | (p) += char_string (c, p); \ | |
199 | } \ | |
96c06863 | 200 | } while (false) |
0168c3d8 | 201 | |
eb41da4c | 202 | |
0168c3d8 KH |
203 | /* Nonzero iff BYTE starts a non-ASCII character in a multibyte |
204 | form. */ | |
205 | #define LEADING_CODE_P(byte) (((byte) & 0xC0) == 0xC0) | |
206 | ||
b5c7dbe6 KH |
207 | /* Nonzero iff BYTE is a trailing code of a non-ASCII character in a |
208 | multibyte form. */ | |
209 | #define TRAILING_CODE_P(byte) (((byte) & 0xC0) == 0x80) | |
210 | ||
885317d8 KH |
211 | /* Nonzero iff BYTE starts a character in a multibyte form. |
212 | This is equivalent to: | |
200fc949 | 213 | (ASCII_CHAR_P (byte) || LEADING_CODE_P (byte)) */ |
885317d8 KH |
214 | #define CHAR_HEAD_P(byte) (((byte) & 0xC0) != 0x80) |
215 | ||
0168c3d8 KH |
216 | /* How many bytes a character that starts with BYTE occupies in a |
217 | multibyte form. */ | |
218 | #define BYTES_BY_CHAR_HEAD(byte) \ | |
219 | (!((byte) & 0x80) ? 1 \ | |
220 | : !((byte) & 0x20) ? 2 \ | |
221 | : !((byte) & 0x10) ? 3 \ | |
222 | : !((byte) & 0x08) ? 4 \ | |
223 | : 5) | |
224 | ||
225 | ||
0168c3d8 | 226 | /* The byte length of multibyte form at unibyte string P ending at |
18a2979d | 227 | PEND. If STR doesn't point to a valid multibyte form, return 0. */ |
0168c3d8 KH |
228 | |
229 | #define MULTIBYTE_LENGTH(p, pend) \ | |
230 | (p >= pend ? 0 \ | |
231 | : !((p)[0] & 0x80) ? 1 \ | |
232 | : ((p + 1 >= pend) || (((p)[1] & 0xC0) != 0x80)) ? 0 \ | |
233 | : ((p)[0] & 0xE0) == 0xC0 ? 2 \ | |
234 | : ((p + 2 >= pend) || (((p)[2] & 0xC0) != 0x80)) ? 0 \ | |
235 | : ((p)[0] & 0xF0) == 0xE0 ? 3 \ | |
236 | : ((p + 3 >= pend) || (((p)[3] & 0xC0) != 0x80)) ? 0 \ | |
237 | : ((p)[0] & 0xF8) == 0xF0 ? 4 \ | |
238 | : ((p + 4 >= pend) || (((p)[4] & 0xC0) != 0x80)) ? 0 \ | |
239 | : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \ | |
240 | : 0) | |
241 | ||
242 | ||
18a2979d | 243 | /* Like MULTIBYTE_LENGTH, but don't check the ending address. */ |
0168c3d8 KH |
244 | |
245 | #define MULTIBYTE_LENGTH_NO_CHECK(p) \ | |
246 | (!((p)[0] & 0x80) ? 1 \ | |
247 | : ((p)[1] & 0xC0) != 0x80 ? 0 \ | |
248 | : ((p)[0] & 0xE0) == 0xC0 ? 2 \ | |
249 | : ((p)[2] & 0xC0) != 0x80 ? 0 \ | |
250 | : ((p)[0] & 0xF0) == 0xE0 ? 3 \ | |
251 | : ((p)[3] & 0xC0) != 0x80 ? 0 \ | |
252 | : ((p)[0] & 0xF8) == 0xF0 ? 4 \ | |
253 | : ((p)[4] & 0xC0) != 0x80 ? 0 \ | |
254 | : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \ | |
255 | : 0) | |
256 | ||
18a2979d EZ |
257 | /* If P is before LIMIT, advance P to the next character boundary. |
258 | Assumes that P is already at a character boundary of the same | |
78edd3b7 | 259 | multibyte form whose end address is LIMIT. */ |
8f924df7 KH |
260 | |
261 | #define NEXT_CHAR_BOUNDARY(p, limit) \ | |
262 | do { \ | |
263 | if ((p) < (limit)) \ | |
264 | (p) += BYTES_BY_CHAR_HEAD (*(p)); \ | |
96c06863 | 265 | } while (false) |
8f924df7 KH |
266 | |
267 | ||
268 | /* If P is after LIMIT, advance P to the previous character boundary. | |
18a2979d | 269 | Assumes that P is already at a character boundary of the same |
ce5b453a | 270 | multibyte form whose beginning address is LIMIT. */ |
8f924df7 KH |
271 | |
272 | #define PREV_CHAR_BOUNDARY(p, limit) \ | |
273 | do { \ | |
274 | if ((p) > (limit)) \ | |
275 | { \ | |
760fbc2c | 276 | const unsigned char *chp = (p); \ |
8f924df7 | 277 | do { \ |
760fbc2c PE |
278 | chp--; \ |
279 | } while (chp >= limit && ! CHAR_HEAD_P (*chp)); \ | |
280 | (p) = (BYTES_BY_CHAR_HEAD (*chp) == (p) - chp) ? chp : (p) - 1; \ | |
8f924df7 | 281 | } \ |
96c06863 | 282 | } while (false) |
0168c3d8 KH |
283 | |
284 | /* Return the character code of character whose multibyte form is at | |
2f8e16b2 EZ |
285 | P. Note that this macro unifies CJK characters whose codepoints |
286 | are in the Private Use Areas (PUAs), so it might return a different | |
287 | codepoint from the one actually stored at P. */ | |
0168c3d8 | 288 | |
62a6e103 | 289 | #define STRING_CHAR(p) \ |
0168c3d8 KH |
290 | (!((p)[0] & 0x80) \ |
291 | ? (p)[0] \ | |
292 | : ! ((p)[0] & 0x20) \ | |
293 | ? (((((p)[0] & 0x1F) << 6) \ | |
294 | | ((p)[1] & 0x3F)) \ | |
295 | + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0)) \ | |
296 | : ! ((p)[0] & 0x10) \ | |
297 | ? ((((p)[0] & 0x0F) << 12) \ | |
298 | | (((p)[1] & 0x3F) << 6) \ | |
299 | | ((p)[2] & 0x3F)) \ | |
eb41da4c | 300 | : string_char ((p), NULL, NULL)) |
0168c3d8 KH |
301 | |
302 | ||
18a2979d | 303 | /* Like STRING_CHAR, but set ACTUAL_LEN to the length of multibyte |
2f8e16b2 EZ |
304 | form. |
305 | ||
306 | Note: This macro returns the actual length of the character's | |
307 | multibyte sequence as it is stored in a buffer or string. The | |
308 | character it returns might have a different codepoint that has a | |
5ae255c7 | 309 | different multibyte sequence of a different length, due to possible |
2f8e16b2 EZ |
310 | unification of CJK characters inside string_char. Therefore do NOT |
311 | assume that the length returned by this macro is identical to the | |
312 | length of the multibyte sequence of the character it returns. */ | |
0168c3d8 | 313 | |
62a6e103 | 314 | #define STRING_CHAR_AND_LENGTH(p, actual_len) \ |
0168c3d8 KH |
315 | (!((p)[0] & 0x80) \ |
316 | ? ((actual_len) = 1, (p)[0]) \ | |
317 | : ! ((p)[0] & 0x20) \ | |
318 | ? ((actual_len) = 2, \ | |
319 | (((((p)[0] & 0x1F) << 6) \ | |
320 | | ((p)[1] & 0x3F)) \ | |
321 | + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
322 | : ! ((p)[0] & 0x10) \ | |
323 | ? ((actual_len) = 3, \ | |
324 | ((((p)[0] & 0x0F) << 12) \ | |
325 | | (((p)[1] & 0x3F) << 6) \ | |
326 | | ((p)[2] & 0x3F))) \ | |
eb41da4c | 327 | : string_char ((p), NULL, &actual_len)) |
0168c3d8 KH |
328 | |
329 | ||
18a2979d | 330 | /* Like STRING_CHAR, but advance P to the end of multibyte form. */ |
0168c3d8 KH |
331 | |
332 | #define STRING_CHAR_ADVANCE(p) \ | |
333 | (!((p)[0] & 0x80) \ | |
334 | ? *(p)++ \ | |
335 | : ! ((p)[0] & 0x20) \ | |
336 | ? ((p) += 2, \ | |
337 | ((((p)[-2] & 0x1F) << 6) \ | |
338 | | ((p)[-1] & 0x3F) \ | |
8f924df7 | 339 | | ((unsigned char) ((p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ |
0168c3d8 KH |
340 | : ! ((p)[0] & 0x10) \ |
341 | ? ((p) += 3, \ | |
342 | ((((p)[-3] & 0x0F) << 12) \ | |
343 | | (((p)[-2] & 0x3F) << 6) \ | |
344 | | ((p)[-1] & 0x3F))) \ | |
eb41da4c | 345 | : string_char ((p), &(p), NULL)) |
0168c3d8 KH |
346 | |
347 | ||
348 | /* Fetch the "next" character from Lisp string STRING at byte position | |
349 | BYTEIDX, character position CHARIDX. Store it into OUTPUT. | |
350 | ||
351 | All the args must be side-effect-free. | |
352 | BYTEIDX and CHARIDX must be lvalues; | |
353 | we increment them past the character fetched. */ | |
354 | ||
355 | #define FETCH_STRING_CHAR_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 356 | do \ |
0168c3d8 KH |
357 | { \ |
358 | CHARIDX++; \ | |
359 | if (STRING_MULTIBYTE (STRING)) \ | |
360 | { \ | |
760fbc2c PE |
361 | unsigned char *chp = &SDATA (STRING)[BYTEIDX]; \ |
362 | int chlen; \ | |
0168c3d8 | 363 | \ |
760fbc2c PE |
364 | OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \ |
365 | BYTEIDX += chlen; \ | |
0168c3d8 KH |
366 | } \ |
367 | else \ | |
f1c99628 SM |
368 | { \ |
369 | OUTPUT = SREF (STRING, BYTEIDX); \ | |
370 | BYTEIDX++; \ | |
371 | } \ | |
0168c3d8 | 372 | } \ |
96c06863 | 373 | while (false) |
0168c3d8 | 374 | |
18a2979d EZ |
375 | /* Like FETCH_STRING_CHAR_ADVANCE, but return a multibyte character |
376 | even if STRING is unibyte. */ | |
43c47483 KH |
377 | |
378 | #define FETCH_STRING_CHAR_AS_MULTIBYTE_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 379 | do \ |
43c47483 KH |
380 | { \ |
381 | CHARIDX++; \ | |
382 | if (STRING_MULTIBYTE (STRING)) \ | |
383 | { \ | |
760fbc2c PE |
384 | unsigned char *chp = &SDATA (STRING)[BYTEIDX]; \ |
385 | int chlen; \ | |
43c47483 | 386 | \ |
760fbc2c PE |
387 | OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \ |
388 | BYTEIDX += chlen; \ | |
43c47483 KH |
389 | } \ |
390 | else \ | |
391 | { \ | |
f1c99628 SM |
392 | OUTPUT = SREF (STRING, BYTEIDX); \ |
393 | BYTEIDX++; \ | |
43c47483 KH |
394 | MAKE_CHAR_MULTIBYTE (OUTPUT); \ |
395 | } \ | |
396 | } \ | |
96c06863 | 397 | while (false) |
43c47483 | 398 | |
0168c3d8 | 399 | |
18a2979d | 400 | /* Like FETCH_STRING_CHAR_ADVANCE, but assumes STRING is multibyte. */ |
0168c3d8 KH |
401 | |
402 | #define FETCH_STRING_CHAR_ADVANCE_NO_CHECK(OUTPUT, STRING, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 403 | do \ |
0168c3d8 | 404 | { \ |
a6670b0b PE |
405 | unsigned char *fetch_ptr = &SDATA (STRING)[BYTEIDX]; \ |
406 | int fetch_len; \ | |
0168c3d8 | 407 | \ |
a6670b0b PE |
408 | OUTPUT = STRING_CHAR_AND_LENGTH (fetch_ptr, fetch_len); \ |
409 | BYTEIDX += fetch_len; \ | |
0168c3d8 KH |
410 | CHARIDX++; \ |
411 | } \ | |
96c06863 | 412 | while (false) |
0168c3d8 KH |
413 | |
414 | ||
18a2979d | 415 | /* Like FETCH_STRING_CHAR_ADVANCE, but fetch character from the current |
0168c3d8 KH |
416 | buffer. */ |
417 | ||
418 | #define FETCH_CHAR_ADVANCE(OUTPUT, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 419 | do \ |
0168c3d8 KH |
420 | { \ |
421 | CHARIDX++; \ | |
4b4deea2 | 422 | if (!NILP (BVAR (current_buffer, enable_multibyte_characters))) \ |
0168c3d8 | 423 | { \ |
760fbc2c PE |
424 | unsigned char *chp = BYTE_POS_ADDR (BYTEIDX); \ |
425 | int chlen; \ | |
0168c3d8 | 426 | \ |
e8d32c7e | 427 | OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \ |
760fbc2c | 428 | BYTEIDX += chlen; \ |
0168c3d8 KH |
429 | } \ |
430 | else \ | |
431 | { \ | |
432 | OUTPUT = *(BYTE_POS_ADDR (BYTEIDX)); \ | |
433 | BYTEIDX++; \ | |
434 | } \ | |
435 | } \ | |
96c06863 | 436 | while (false) |
0168c3d8 KH |
437 | |
438 | ||
18a2979d | 439 | /* Like FETCH_CHAR_ADVANCE, but assumes the current buffer is multibyte. */ |
0168c3d8 KH |
440 | |
441 | #define FETCH_CHAR_ADVANCE_NO_CHECK(OUTPUT, CHARIDX, BYTEIDX) \ | |
a1c2ac9a | 442 | do \ |
0168c3d8 | 443 | { \ |
760fbc2c PE |
444 | unsigned char *chp = BYTE_POS_ADDR (BYTEIDX); \ |
445 | int chlen; \ | |
0168c3d8 | 446 | \ |
760fbc2c PE |
447 | OUTPUT = STRING_CHAR_AND_LENGTH (chp, chlen); \ |
448 | BYTEIDX += chlen; \ | |
0168c3d8 KH |
449 | CHARIDX++; \ |
450 | } \ | |
96c06863 | 451 | while (false) |
0168c3d8 KH |
452 | |
453 | ||
18a2979d | 454 | /* Increment the buffer byte position POS_BYTE of the current buffer to |
0168c3d8 KH |
455 | the next character boundary. No range checking of POS. */ |
456 | ||
457 | #define INC_POS(pos_byte) \ | |
458 | do { \ | |
760fbc2c PE |
459 | unsigned char *chp = BYTE_POS_ADDR (pos_byte); \ |
460 | pos_byte += BYTES_BY_CHAR_HEAD (*chp); \ | |
96c06863 | 461 | } while (false) |
0168c3d8 KH |
462 | |
463 | ||
18a2979d | 464 | /* Decrement the buffer byte position POS_BYTE of the current buffer to |
0168c3d8 KH |
465 | the previous character boundary. No range checking of POS. */ |
466 | ||
467 | #define DEC_POS(pos_byte) \ | |
468 | do { \ | |
760fbc2c | 469 | unsigned char *chp; \ |
0168c3d8 KH |
470 | \ |
471 | pos_byte--; \ | |
472 | if (pos_byte < GPT_BYTE) \ | |
760fbc2c | 473 | chp = BEG_ADDR + pos_byte - BEG_BYTE; \ |
0168c3d8 | 474 | else \ |
760fbc2c PE |
475 | chp = BEG_ADDR + GAP_SIZE + pos_byte - BEG_BYTE; \ |
476 | while (!CHAR_HEAD_P (*chp)) \ | |
0168c3d8 | 477 | { \ |
760fbc2c | 478 | chp--; \ |
0168c3d8 KH |
479 | pos_byte--; \ |
480 | } \ | |
96c06863 | 481 | } while (false) |
0168c3d8 KH |
482 | |
483 | /* Increment both CHARPOS and BYTEPOS, each in the appropriate way. */ | |
484 | ||
485 | #define INC_BOTH(charpos, bytepos) \ | |
486 | do \ | |
487 | { \ | |
488 | (charpos)++; \ | |
4b4deea2 | 489 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) \ |
0168c3d8 KH |
490 | (bytepos)++; \ |
491 | else \ | |
492 | INC_POS ((bytepos)); \ | |
493 | } \ | |
96c06863 | 494 | while (false) |
0168c3d8 KH |
495 | |
496 | ||
497 | /* Decrement both CHARPOS and BYTEPOS, each in the appropriate way. */ | |
498 | ||
499 | #define DEC_BOTH(charpos, bytepos) \ | |
500 | do \ | |
501 | { \ | |
502 | (charpos)--; \ | |
4b4deea2 | 503 | if (NILP (BVAR (current_buffer, enable_multibyte_characters))) \ |
0168c3d8 KH |
504 | (bytepos)--; \ |
505 | else \ | |
506 | DEC_POS ((bytepos)); \ | |
507 | } \ | |
96c06863 | 508 | while (false) |
0168c3d8 KH |
509 | |
510 | ||
18a2979d | 511 | /* Increment the buffer byte position POS_BYTE of the current buffer to |
0168c3d8 KH |
512 | the next character boundary. This macro relies on the fact that |
513 | *GPT_ADDR and *Z_ADDR are always accessible and the values are | |
514 | '\0'. No range checking of POS_BYTE. */ | |
515 | ||
516 | #define BUF_INC_POS(buf, pos_byte) \ | |
517 | do { \ | |
760fbc2c PE |
518 | unsigned char *chp = BUF_BYTE_ADDRESS (buf, pos_byte); \ |
519 | pos_byte += BYTES_BY_CHAR_HEAD (*chp); \ | |
96c06863 | 520 | } while (false) |
0168c3d8 KH |
521 | |
522 | ||
18a2979d | 523 | /* Decrement the buffer byte position POS_BYTE of the current buffer to |
0168c3d8 KH |
524 | the previous character boundary. No range checking of POS_BYTE. */ |
525 | ||
526 | #define BUF_DEC_POS(buf, pos_byte) \ | |
527 | do { \ | |
760fbc2c | 528 | unsigned char *chp; \ |
0168c3d8 KH |
529 | pos_byte--; \ |
530 | if (pos_byte < BUF_GPT_BYTE (buf)) \ | |
760fbc2c | 531 | chp = BUF_BEG_ADDR (buf) + pos_byte - BEG_BYTE; \ |
0168c3d8 | 532 | else \ |
760fbc2c PE |
533 | chp = BUF_BEG_ADDR (buf) + BUF_GAP_SIZE (buf) + pos_byte - BEG_BYTE;\ |
534 | while (!CHAR_HEAD_P (*chp)) \ | |
0168c3d8 | 535 | { \ |
760fbc2c | 536 | chp--; \ |
0168c3d8 KH |
537 | pos_byte--; \ |
538 | } \ | |
96c06863 | 539 | } while (false) |
0168c3d8 KH |
540 | |
541 | ||
a2271ba2 PE |
542 | /* Return a non-outlandish value for the tab width. */ |
543 | ||
5637687f PE |
544 | #define SANE_TAB_WIDTH(buf) \ |
545 | sanitize_tab_width (XFASTINT (BVAR (buf, tab_width))) | |
00382e8b | 546 | INLINE int |
5637687f | 547 | sanitize_tab_width (EMACS_INT width) |
a2271ba2 PE |
548 | { |
549 | return 0 < width && width <= 1000 ? width : 8; | |
550 | } | |
551 | ||
0168c3d8 | 552 | /* Return the width of ASCII character C. The width is measured by |
18a2979d | 553 | how many columns C will occupy on the screen when displayed in the |
0168c3d8 KH |
554 | current buffer. */ |
555 | ||
556 | #define ASCII_CHAR_WIDTH(c) \ | |
557 | (c < 0x20 \ | |
558 | ? (c == '\t' \ | |
a2271ba2 | 559 | ? SANE_TAB_WIDTH (current_buffer) \ |
4b4deea2 | 560 | : (c == '\n' ? 0 : (NILP (BVAR (current_buffer, ctl_arrow)) ? 4 : 2))) \ |
0168c3d8 KH |
561 | : (c < 0x7f \ |
562 | ? 1 \ | |
4b4deea2 | 563 | : ((NILP (BVAR (current_buffer, ctl_arrow)) ? 4 : 2)))) |
0168c3d8 | 564 | |
5637687f PE |
565 | /* Return a non-outlandish value for a character width. */ |
566 | ||
00382e8b | 567 | INLINE int |
5637687f PE |
568 | sanitize_char_width (EMACS_INT width) |
569 | { | |
570 | return 0 <= width && width <= 1000 ? width : 1000; | |
571 | } | |
572 | ||
0168c3d8 | 573 | /* Return the width of character C. The width is measured by how many |
18a2979d | 574 | columns C will occupy on the screen when displayed in the current |
0168c3d8 KH |
575 | buffer. */ |
576 | ||
577 | #define CHAR_WIDTH(c) \ | |
578 | (ASCII_CHAR_P (c) \ | |
579 | ? ASCII_CHAR_WIDTH (c) \ | |
5637687f | 580 | : sanitize_char_width (XINT (CHAR_TABLE_REF (Vchar_width_table, c)))) |
0168c3d8 | 581 | |
e1dbe924 | 582 | /* If C is a variation selector, return the index of the |
c19cab20 KH |
583 | variation selector (1..256). Otherwise, return 0. */ |
584 | ||
585 | #define CHAR_VARIATION_SELECTOR_P(c) \ | |
586 | ((c) < 0xFE00 ? 0 \ | |
587 | : (c) <= 0xFE0F ? (c) - 0xFE00 + 1 \ | |
588 | : (c) < 0xE0100 ? 0 \ | |
589 | : (c) <= 0xE01EF ? (c) - 0xE0100 + 17 \ | |
590 | : 0) | |
591 | ||
592 | /* If C is a high surrogate, return 1. If C is a low surrogate, | |
96c06863 | 593 | return 2. Otherwise, return 0. */ |
c19cab20 KH |
594 | |
595 | #define CHAR_SURROGATE_PAIR_P(c) \ | |
596 | ((c) < 0xD800 ? 0 \ | |
597 | : (c) <= 0xDBFF ? 1 \ | |
598 | : (c) <= 0xDFFF ? 2 \ | |
599 | : 0) | |
600 | ||
c805dec0 KH |
601 | /* Data type for Unicode general category. |
602 | ||
603 | The order of members must be in sync with the 8th element of the | |
e0cece64 | 604 | member of unidata-prop-alist (in admin/unidata/unidata-gen.el) for |
c805dec0 KH |
605 | Unicode character property `general-category'. */ |
606 | ||
607 | typedef enum { | |
608 | UNICODE_CATEGORY_UNKNOWN = 0, | |
609 | UNICODE_CATEGORY_Lu, | |
610 | UNICODE_CATEGORY_Ll, | |
611 | UNICODE_CATEGORY_Lt, | |
612 | UNICODE_CATEGORY_Lm, | |
613 | UNICODE_CATEGORY_Lo, | |
614 | UNICODE_CATEGORY_Mn, | |
615 | UNICODE_CATEGORY_Mc, | |
616 | UNICODE_CATEGORY_Me, | |
617 | UNICODE_CATEGORY_Nd, | |
618 | UNICODE_CATEGORY_Nl, | |
619 | UNICODE_CATEGORY_No, | |
620 | UNICODE_CATEGORY_Pc, | |
621 | UNICODE_CATEGORY_Pd, | |
622 | UNICODE_CATEGORY_Ps, | |
623 | UNICODE_CATEGORY_Pe, | |
624 | UNICODE_CATEGORY_Pi, | |
625 | UNICODE_CATEGORY_Pf, | |
626 | UNICODE_CATEGORY_Po, | |
627 | UNICODE_CATEGORY_Sm, | |
628 | UNICODE_CATEGORY_Sc, | |
629 | UNICODE_CATEGORY_Sk, | |
630 | UNICODE_CATEGORY_So, | |
631 | UNICODE_CATEGORY_Zs, | |
632 | UNICODE_CATEGORY_Zl, | |
633 | UNICODE_CATEGORY_Zp, | |
634 | UNICODE_CATEGORY_Cc, | |
635 | UNICODE_CATEGORY_Cf, | |
636 | UNICODE_CATEGORY_Cs, | |
637 | UNICODE_CATEGORY_Co, | |
638 | UNICODE_CATEGORY_Cn | |
639 | } unicode_category_t; | |
c19cab20 | 640 | |
5994c183 | 641 | extern EMACS_INT char_resolve_modifier_mask (EMACS_INT) ATTRIBUTE_CONST; |
383e0970 J |
642 | extern int char_string (unsigned, unsigned char *); |
643 | extern int string_char (const unsigned char *, | |
644 | const unsigned char **, int *); | |
645 | ||
646 | extern int translate_char (Lisp_Object, int c); | |
14162469 | 647 | extern void parse_str_as_multibyte (const unsigned char *, |
d311d28c PE |
648 | ptrdiff_t, ptrdiff_t *, ptrdiff_t *); |
649 | extern ptrdiff_t count_size_as_multibyte (const unsigned char *, ptrdiff_t); | |
650 | extern ptrdiff_t str_as_multibyte (unsigned char *, ptrdiff_t, ptrdiff_t, | |
651 | ptrdiff_t *); | |
652 | extern ptrdiff_t str_to_multibyte (unsigned char *, ptrdiff_t, ptrdiff_t); | |
653 | extern ptrdiff_t str_as_unibyte (unsigned char *, ptrdiff_t); | |
654 | extern ptrdiff_t str_to_unibyte (const unsigned char *, unsigned char *, | |
d5172d4f | 655 | ptrdiff_t); |
d311d28c PE |
656 | extern ptrdiff_t strwidth (const char *, ptrdiff_t); |
657 | extern ptrdiff_t c_string_width (const unsigned char *, ptrdiff_t, int, | |
658 | ptrdiff_t *, ptrdiff_t *); | |
659 | extern ptrdiff_t lisp_string_width (Lisp_Object, ptrdiff_t, | |
660 | ptrdiff_t *, ptrdiff_t *); | |
0168c3d8 | 661 | |
955cbe7b | 662 | extern Lisp_Object Qcharacterp; |
0168c3d8 | 663 | extern Lisp_Object Vchar_unify_table; |
383e0970 | 664 | extern Lisp_Object string_escape_byte8 (Lisp_Object); |
fac2bdc4 | 665 | |
0168c3d8 KH |
666 | /* Return a translation table of id number ID. */ |
667 | #define GET_TRANSLATION_TABLE(id) \ | |
91f2d272 | 668 | (XCDR (XVECTOR (Vtranslation_table_vector)->contents[(id)])) |
0168c3d8 | 669 | |
f162bcc3 PE |
670 | INLINE_HEADER_END |
671 | ||
0168c3d8 | 672 | #endif /* EMACS_CHARACTER_H */ |