Mercurial > emacs
annotate src/character.h @ 88436:29c4241b5418
*** empty log message ***
author | Kenichi Handa <handa@m17n.org> |
---|---|
date | Tue, 05 Mar 2002 01:07:22 +0000 |
parents | 5eaa8c11ab45 |
children | 2f6c9323d466 |
rev | line source |
---|---|
88363 | 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 | |
7 | |
8 This file is part of GNU Emacs. | |
9 | |
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) | |
13 any later version. | |
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 | |
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. */ | |
24 | |
25 #ifndef EMACS_CHARACTER_H | |
26 #define EMACS_CHARACTER_H | |
27 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
28 /* character code 1st byte byte sequence |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
29 -------------- -------- ------------- |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
30 0-7F 00..7F 0xxxxxxx |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
31 80-7FF C2..DF 110xxxxx 10xxxxxx |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
32 800-FFFF E0..EF 1110xxxx 10xxxxxx 10xxxxxx |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
33 10000-1FFFFF F0..F7 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
34 200000-3FFF7F F8 11111000 1000xxxx 10xxxxxx 10xxxxxx 10xxxxxx |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
35 invalid F9..FF |
88363 | 36 |
37 raw-8-bit | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
38 3FFF80-3FFFFF C0..C1 1100000x 10xxxxxx |
88363 | 39 */ |
40 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
41 /* Maximum character code ((1 << CHARACTERBITS) - 1). */ |
88363 | 42 #define MAX_CHAR 0x3FFFFF |
43 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
44 /* Maximum Unicode character code. */ |
88363 | 45 #define MAX_UNICODE_CHAR 0x10FFFF |
46 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
47 /* Maximum N-byte character codes. */ |
88363 | 48 #define MAX_1_BYTE_CHAR 0x7F |
49 #define MAX_2_BYTE_CHAR 0x7FF | |
50 #define MAX_3_BYTE_CHAR 0xFFFF | |
51 #define MAX_4_BYTE_CHAR 0x1FFFFF | |
52 #define MAX_5_BYTE_CHAR 0x3FFF7F | |
53 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
54 /* Return the character code for raw 8-bit byte BYTE. */ |
88363 | 55 #define BYTE8_TO_CHAR(byte) ((byte) + 0x3FFF00) |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
56 |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
57 /* Return the raw 8-bit byte for character C. */ |
88363 | 58 #define CHAR_TO_BYTE8(c) ((c) - 0x3FFF00) |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
59 |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
60 /* Nonzero iff C is a character that corresponds to a raw 8-bit |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
61 byte. */ |
88363 | 62 #define CHAR_BYTE8_P(c) ((c) > MAX_5_BYTE_CHAR) |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
63 |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
64 /* Nonzero iff BYTE is the 1st byte of a multibyte form of a character |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
65 that corresponds to a raw 8-bit byte. */ |
88363 | 66 #define CHAR_BYTE8_HEAD_P(byte) ((byte) == 0xC0 || (byte) == 0xC1) |
67 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
68 /* This is the maximum byte length of multibyte form. */ |
88363 | 69 #define MAX_MULTIBYTE_LENGTH 5 |
70 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
71 /* Return a Lisp character whose character code is C. */ |
88363 | 72 #define make_char(c) make_number (c) |
73 | |
74 /* Nonzero iff C is an ASCII byte. */ | |
75 #define ASCII_BYTE_P(c) ((unsigned) (c) < 0x80) | |
76 | |
77 /* Nonzero iff X is a character. */ | |
78 #define CHARACTERP(x) (NATNUMP (x) && XFASTINT (x) <= MAX_CHAR) | |
79 | |
80 /* Nozero iff C is valid as a charater code. GENERICP is not used | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
81 now. */ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
82 #define CHAR_VALID_P(c, genericp) ((unsigned) (c) <= MAX_CHAR) |
88363 | 83 |
84 /* Check if Lisp object X is a character or not. */ | |
85 #define CHECK_CHARACTER(x) \ | |
86 do { \ | |
87 if (! CHARACTERP(x)) x = wrong_type_argument (Qcharacterp, (x)); \ | |
88 } while (0) | |
89 | |
90 /* Nonzero iff C is an ASCII character. */ | |
91 #define ASCII_CHAR_P(c) ((unsigned) (c) < 0x80) | |
92 | |
93 /* Nonzero iff C is a character of code less than 0x100. */ | |
94 #define SINGLE_BYTE_CHAR_P(c) ((unsigned) (c) < 0x100) | |
95 | |
96 /* Nonzero if character C has a printable glyph. */ | |
97 #define CHAR_PRINTABLE_P(c) \ | |
98 (((c) >= 32 && ((c) < 127) \ | |
99 || ! NILP (CHAR_TABLE_REF (Vprintable_chars, (c))))) | |
100 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
101 /* Return byte length of multibyte form for character C. */ |
88363 | 102 #define CHAR_BYTES(c) \ |
103 ( (c) <= MAX_1_BYTE_CHAR ? 1 \ | |
104 : (c) <= MAX_2_BYTE_CHAR ? 2 \ | |
105 : (c) <= MAX_3_BYTE_CHAR ? 3 \ | |
106 : (c) <= MAX_4_BYTE_CHAR ? 4 \ | |
107 : (c) <= MAX_5_BYTE_CHAR ? 5 \ | |
108 : 2) | |
109 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
110 /* Store multibyte form of the character C in P. The caller should |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
111 allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance. |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
112 Returns the length of the multibyte form. */ |
88363 | 113 |
114 #define CHAR_STRING(c, p) \ | |
115 ((unsigned) (c) <= MAX_1_BYTE_CHAR \ | |
116 ? ((p)[0] = (c), \ | |
117 1) \ | |
118 : (unsigned) (c) <= MAX_2_BYTE_CHAR \ | |
119 ? ((p)[0] = (0xC0 | ((c) >> 6)), \ | |
120 (p)[1] = (0x80 | ((c) & 0x3F)), \ | |
121 2) \ | |
122 : (unsigned) (c) <= MAX_3_BYTE_CHAR \ | |
123 ? ((p)[0] = (0xE0 | ((c) >> 12)), \ | |
124 (p)[1] = (0x80 | (((c) >> 6) & 0x3F)), \ | |
125 (p)[2] = (0x80 | ((c) & 0x3F)), \ | |
126 3) \ | |
127 : (unsigned) (c) <= MAX_5_BYTE_CHAR \ | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
128 ? char_string_with_unification (c, p) \ |
88363 | 129 : ((p)[0] = (0xC0 | (((c) >> 6) & 0x01)), \ |
130 (p)[1] = (0x80 | ((c) & 0x3F)), \ | |
131 2)) | |
132 | |
133 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
134 /* Store multibyte form of the character C in P. The caller should |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
135 allocate at least MAX_MULTIBYTE_LENGTH bytes area at P in advance. |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
136 And, advance P to the end of the multibyte form. */ |
88363 | 137 |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
138 #define CHAR_STRING_ADVANCE(c, p) \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
139 do { \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
140 if ((c) <= MAX_1_BYTE_CHAR) \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
141 *(p)++ = (c); \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
142 else if ((c) <= MAX_2_BYTE_CHAR) \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
143 *(p)++ = (0xC0 | ((c) >> 6)), \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
144 *(p)++ = (0x80 | ((c) & 0x3F)); \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
145 else if ((c) <= MAX_3_BYTE_CHAR) \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
146 *(p)++ = (0xE0 | ((c) >> 12)), \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
147 *(p)++ = (0x80 | (((c) >> 6) & 0x3F)), \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
148 *(p)++ = (0x80 | ((c) & 0x3F)); \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
149 else if ((c) <= MAX_5_BYTE_CHAR) \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
150 (p) += char_string_with_unification ((c), (p)); \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
151 else \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
152 *(p)++ = (0xC0 | (((c) >> 6) & 0x01)), \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
153 *(p)++ = (0x80 | ((c) & 0x3F)); \ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
154 } while (0) |
88363 | 155 |
156 /* Nonzero iff BYTE starts a non-ASCII character in a multibyte | |
157 form. */ | |
158 #define LEADING_CODE_P(byte) (((byte) & 0xC0) == 0xC0) | |
159 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
160 /* Nonzero iff BYTE starts a character in a multibyte form. |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
161 This is equivalent to: |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
162 (ASCII_BYTE_P (byte) || LEADING_CODE_P (byte)) */ |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
163 #define CHAR_HEAD_P(byte) (((byte) & 0xC0) != 0x80) |
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
164 |
88363 | 165 /* Just kept for backward compatibility. This macro will be removed |
166 in the future. */ | |
167 #define BASE_LEADING_CODE_P LEADING_CODE_P | |
168 | |
169 /* How many bytes a character that starts with BYTE occupies in a | |
170 multibyte form. */ | |
171 #define BYTES_BY_CHAR_HEAD(byte) \ | |
172 (!((byte) & 0x80) ? 1 \ | |
173 : !((byte) & 0x20) ? 2 \ | |
174 : !((byte) & 0x10) ? 3 \ | |
175 : !((byte) & 0x08) ? 4 \ | |
176 : 5) | |
177 | |
178 | |
179 /* Return the length of the multi-byte form at string STR of length | |
180 LEN while assuming that STR points a valid multi-byte form. As | |
181 this macro isn't necessary anymore, all callers will be changed to | |
182 use BYTES_BY_CHAR_HEAD directly in the future. */ | |
183 | |
184 #define MULTIBYTE_FORM_LENGTH(str, len) \ | |
185 BYTES_BY_CHAR_HEAD (*(str)) | |
186 | |
187 /* Parse multibyte string STR of length LENGTH and set BYTES to the | |
188 byte length of a character at STR while assuming that STR points a | |
189 valid multibyte form. As this macro isn't necessary anymore, all | |
190 callers will be changed to use BYTES_BY_CHAR_HEAD directly in the | |
191 future. */ | |
192 | |
193 #define PARSE_MULTIBYTE_SEQ(str, length, bytes) \ | |
194 (bytes) = BYTES_BY_CHAR_HEAD (*(str)) | |
195 | |
196 /* The byte length of multibyte form at unibyte string P ending at | |
197 PEND. If STR doesn't point a valid multibyte form, return 0. */ | |
198 | |
199 #define MULTIBYTE_LENGTH(p, pend) \ | |
200 (p >= pend ? 0 \ | |
201 : !((p)[0] & 0x80) ? 1 \ | |
202 : ((p + 1 >= pend) || (((p)[1] & 0xC0) != 0x80)) ? 0 \ | |
203 : ((p)[0] & 0xE0) == 0xC0 ? 2 \ | |
204 : ((p + 2 >= pend) || (((p)[2] & 0xC0) != 0x80)) ? 0 \ | |
205 : ((p)[0] & 0xF0) == 0xE0 ? 3 \ | |
206 : ((p + 3 >= pend) || (((p)[3] & 0xC0) != 0x80)) ? 0 \ | |
207 : ((p)[0] & 0xF8) == 0xF0 ? 4 \ | |
208 : ((p + 4 >= pend) || (((p)[4] & 0xC0) != 0x80)) ? 0 \ | |
209 : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \ | |
210 : 0) | |
211 | |
212 | |
213 /* Like MULTIBYTE_LENGTH but don't check the ending address. */ | |
214 | |
215 #define MULTIBYTE_LENGTH_NO_CHECK(p) \ | |
216 (!((p)[0] & 0x80) ? 1 \ | |
217 : ((p)[1] & 0xC0) != 0x80 ? 0 \ | |
218 : ((p)[0] & 0xE0) == 0xC0 ? 2 \ | |
219 : ((p)[2] & 0xC0) != 0x80 ? 0 \ | |
220 : ((p)[0] & 0xF0) == 0xE0 ? 3 \ | |
221 : ((p)[3] & 0xC0) != 0x80 ? 0 \ | |
222 : ((p)[0] & 0xF8) == 0xF0 ? 4 \ | |
223 : ((p)[4] & 0xC0) != 0x80 ? 0 \ | |
224 : (p)[0] == 0xF8 && ((p)[1] & 0xF0) == 0x80 ? 5 \ | |
225 : 0) | |
226 | |
227 | |
228 /* Return the character code of character whose multibyte form is at | |
229 P. The argument LEN is ignored. It will be removed in the | |
230 future. */ | |
231 | |
232 #define STRING_CHAR(p, len) \ | |
233 (!((p)[0] & 0x80) \ | |
234 ? (p)[0] \ | |
235 : ! ((p)[0] & 0x20) \ | |
236 ? (((((p)[0] & 0x1F) << 6) \ | |
237 | ((p)[1] & 0x3F)) \ | |
238 + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0)) \ | |
239 : ! ((p)[0] & 0x10) \ | |
240 ? ((((p)[0] & 0x0F) << 12) \ | |
241 | (((p)[1] & 0x3F) << 6) \ | |
242 | ((p)[2] & 0x3F)) \ | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
243 : string_char_with_unification ((p), NULL, NULL)) |
88363 | 244 |
245 | |
246 /* Like STRING_CHAR but set ACTUAL_LEN to the length of multibyte | |
247 form. The argument LEN is ignored. It will be removed in the | |
248 future. */ | |
249 | |
250 #define STRING_CHAR_AND_LENGTH(p, len, actual_len) \ | |
251 (!((p)[0] & 0x80) \ | |
252 ? ((actual_len) = 1, (p)[0]) \ | |
253 : ! ((p)[0] & 0x20) \ | |
254 ? ((actual_len) = 2, \ | |
255 (((((p)[0] & 0x1F) << 6) \ | |
256 | ((p)[1] & 0x3F)) \ | |
257 + (((unsigned char) (p)[0]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
258 : ! ((p)[0] & 0x10) \ | |
259 ? ((actual_len) = 3, \ | |
260 ((((p)[0] & 0x0F) << 12) \ | |
261 | (((p)[1] & 0x3F) << 6) \ | |
262 | ((p)[2] & 0x3F))) \ | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
263 : string_char_with_unification ((p), NULL, &actual_len)) |
88363 | 264 |
265 | |
266 /* Like STRING_CHAR but advacen P to the end of multibyte form. */ | |
267 | |
268 #define STRING_CHAR_ADVANCE(p) \ | |
269 (!((p)[0] & 0x80) \ | |
270 ? *(p)++ \ | |
271 : ! ((p)[0] & 0x20) \ | |
272 ? ((p) += 2, \ | |
273 ((((p)[-2] & 0x1F) << 6) \ | |
274 | ((p)[-1] & 0x3F) \ | |
275 | (((unsigned char) (p)[-2]) < 0xC2 ? 0x3FFF80 : 0))) \ | |
276 : ! ((p)[0] & 0x10) \ | |
277 ? ((p) += 3, \ | |
278 ((((p)[-3] & 0x0F) << 12) \ | |
279 | (((p)[-2] & 0x3F) << 6) \ | |
280 | ((p)[-1] & 0x3F))) \ | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
281 : string_char_with_unification ((p), &(p), NULL)) |
88363 | 282 |
283 | |
284 /* Fetch the "next" character from Lisp string STRING at byte position | |
285 BYTEIDX, character position CHARIDX. Store it into OUTPUT. | |
286 | |
287 All the args must be side-effect-free. | |
288 BYTEIDX and CHARIDX must be lvalues; | |
289 we increment them past the character fetched. */ | |
290 | |
291 #define FETCH_STRING_CHAR_ADVANCE(OUTPUT, STRING, CHARIDX, BYTEIDX) \ | |
292 if (1) \ | |
293 { \ | |
294 CHARIDX++; \ | |
295 if (STRING_MULTIBYTE (STRING)) \ | |
296 { \ | |
297 unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX]; \ | |
298 int len; \ | |
299 \ | |
300 OUTPUT = STRING_CHAR_AND_LENGTH (ptr, 0, len); \ | |
301 BYTEIDX += len; \ | |
302 } \ | |
303 else \ | |
304 OUTPUT = XSTRING (STRING)->data[BYTEIDX++]; \ | |
305 } \ | |
306 else | |
307 | |
308 | |
309 /* Like FETCH_STRING_CHAR_ADVANCE but assumes STRING is multibyte. */ | |
310 | |
311 #define FETCH_STRING_CHAR_ADVANCE_NO_CHECK(OUTPUT, STRING, CHARIDX, BYTEIDX) \ | |
312 if (1) \ | |
313 { \ | |
314 unsigned char *ptr = &XSTRING (STRING)->data[BYTEIDX]; \ | |
315 int len; \ | |
316 \ | |
317 OUTPUT = STRING_CHAR_AND_LENGTH (ptr, 0, len); \ | |
318 BYTEIDX += len; \ | |
319 CHARIDX++; \ | |
320 } \ | |
321 else | |
322 | |
323 | |
324 /* Like FETCH_STRING_CHAR_ADVANCE but fetch character from the current | |
325 buffer. */ | |
326 | |
327 #define FETCH_CHAR_ADVANCE(OUTPUT, CHARIDX, BYTEIDX) \ | |
328 if (1) \ | |
329 { \ | |
330 CHARIDX++; \ | |
331 if (!NILP (current_buffer->enable_multibyte_characters)) \ | |
332 { \ | |
333 unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \ | |
334 int len; \ | |
335 \ | |
336 OUTPUT= STRING_CHAR_AND_LENGTH (ptr, 0, len); \ | |
337 BYTEIDX += len; \ | |
338 } \ | |
339 else \ | |
340 { \ | |
341 OUTPUT = *(BYTE_POS_ADDR (BYTEIDX)); \ | |
342 BYTEIDX++; \ | |
343 } \ | |
344 } \ | |
345 else | |
346 | |
347 | |
348 /* Like FETCH_CHAR_ADVANCE but assumes STRING is multibyte. */ | |
349 | |
350 #define FETCH_CHAR_ADVANCE_NO_CHECK(OUTPUT, CHARIDX, BYTEIDX) \ | |
351 if (1) \ | |
352 { \ | |
353 unsigned char *ptr = BYTE_POS_ADDR (BYTEIDX); \ | |
354 int len; \ | |
355 \ | |
356 OUTPUT= STRING_CHAR_AND_LENGTH (ptr, 0, len); \ | |
357 BYTEIDX += len; \ | |
358 CHARIDX++; \ | |
359 } \ | |
360 else | |
361 | |
362 | |
363 /* Increase the buffer byte position POS_BYTE of the current buffer to | |
364 the next character boundary. No range checking of POS. */ | |
365 | |
366 #define INC_POS(pos_byte) \ | |
367 do { \ | |
368 unsigned char *p = BYTE_POS_ADDR (pos_byte); \ | |
369 pos_byte += BYTES_BY_CHAR_HEAD (*p); \ | |
370 } while (0) | |
371 | |
372 | |
373 /* Decrease the buffer byte position POS_BYTE of the current buffer to | |
374 the previous character boundary. No range checking of POS. */ | |
375 | |
376 #define DEC_POS(pos_byte) \ | |
377 do { \ | |
378 unsigned char *p; \ | |
379 \ | |
380 pos_byte--; \ | |
381 if (pos_byte < GPT_BYTE) \ | |
382 p = BEG_ADDR + pos_byte - 1; \ | |
383 else \ | |
384 p = BEG_ADDR + GAP_SIZE + pos_byte - 1; \ | |
385 while (!CHAR_HEAD_P (*p)) \ | |
386 { \ | |
387 p--; \ | |
388 pos_byte--; \ | |
389 } \ | |
390 } while (0) | |
391 | |
392 /* Increment both CHARPOS and BYTEPOS, each in the appropriate way. */ | |
393 | |
394 #define INC_BOTH(charpos, bytepos) \ | |
395 do \ | |
396 { \ | |
397 (charpos)++; \ | |
398 if (NILP (current_buffer->enable_multibyte_characters)) \ | |
399 (bytepos)++; \ | |
400 else \ | |
401 INC_POS ((bytepos)); \ | |
402 } \ | |
403 while (0) | |
404 | |
405 | |
406 /* Decrement both CHARPOS and BYTEPOS, each in the appropriate way. */ | |
407 | |
408 #define DEC_BOTH(charpos, bytepos) \ | |
409 do \ | |
410 { \ | |
411 (charpos)--; \ | |
412 if (NILP (current_buffer->enable_multibyte_characters)) \ | |
413 (bytepos)--; \ | |
414 else \ | |
415 DEC_POS ((bytepos)); \ | |
416 } \ | |
417 while (0) | |
418 | |
419 | |
420 /* Increase the buffer byte position POS_BYTE of the current buffer to | |
421 the next character boundary. This macro relies on the fact that | |
422 *GPT_ADDR and *Z_ADDR are always accessible and the values are | |
423 '\0'. No range checking of POS_BYTE. */ | |
424 | |
425 #define BUF_INC_POS(buf, pos_byte) \ | |
426 do { \ | |
427 unsigned char *p = BUF_BYTE_ADDRESS (buf, pos_byte); \ | |
428 pos_byte += BYTES_BY_CHAR_HEAD (*p); \ | |
429 } while (0) | |
430 | |
431 | |
432 /* Decrease the buffer byte position POS_BYTE of the current buffer to | |
433 the previous character boundary. No range checking of POS_BYTE. */ | |
434 | |
435 #define BUF_DEC_POS(buf, pos_byte) \ | |
436 do { \ | |
437 unsigned char *p; \ | |
438 pos_byte--; \ | |
439 if (pos_byte < BUF_GPT_BYTE (buf)) \ | |
440 p = BUF_BEG_ADDR (buf) + pos_byte - 1; \ | |
441 else \ | |
442 p = BUF_BEG_ADDR (buf) + BUF_GAP_SIZE (buf) + pos_byte - 1; \ | |
443 while (!CHAR_HEAD_P (*p)) \ | |
444 { \ | |
445 p--; \ | |
446 pos_byte--; \ | |
447 } \ | |
448 } while (0) | |
449 | |
450 | |
451 #define MAYBE_UNIFY_CHAR(c) \ | |
452 if (CHAR_TABLE_P (Vchar_unify_table)) \ | |
453 { \ | |
454 Lisp_Object val; \ | |
455 int unified; \ | |
456 \ | |
457 val = CHAR_TABLE_REF (Vchar_unify_table, c); \ | |
458 if (SYMBOLP (val)) \ | |
459 { \ | |
460 Funify_charset (val, Qnil); \ | |
461 val = CHAR_TABLE_REF (Vchar_unify_table, c); \ | |
462 } \ | |
463 if ((unified = XINT (val)) >= 0) \ | |
464 c = unified; \ | |
465 } \ | |
466 else | |
467 | |
468 /* Return the width of ASCII character C. The width is measured by | |
469 how many columns occupied on the screen when displayed in the | |
470 current buffer. */ | |
471 | |
472 #define ASCII_CHAR_WIDTH(c) \ | |
473 (c < 0x20 \ | |
474 ? (c == '\t' \ | |
475 ? XFASTINT (current_buffer->tab_width) \ | |
476 : (c == '\n' ? 0 : (NILP (current_buffer->ctl_arrow) ? 4 : 2))) \ | |
477 : (c < 0x7f \ | |
478 ? 1 \ | |
479 : ((NILP (current_buffer->ctl_arrow) ? 4 : 2)))) | |
480 | |
481 /* Return the width of character C. The width is measured by how many | |
482 columns occupied on the screen when displayed in the current | |
483 buffer. */ | |
484 | |
485 #define CHAR_WIDTH(c) \ | |
486 (ASCII_CHAR_P (c) \ | |
487 ? ASCII_CHAR_WIDTH (c) \ | |
488 : XINT (CHAR_TABLE_REF (Vchar_width_table, c))) | |
489 | |
88428
5eaa8c11ab45
(CHAR_VALID_P): Don't call CHARACTERP.
Kenichi Handa <handa@m17n.org>
parents:
88363
diff
changeset
|
490 extern int char_string_with_unification P_ ((int, unsigned char *)); |
88363 | 491 extern int string_char_with_unification P_ ((unsigned char *, |
492 unsigned char **, int *)); | |
493 | |
494 extern int translate_char P_ ((Lisp_Object, int c)); | |
495 extern int char_printable_p P_ ((int c)); | |
496 extern void parse_str_as_multibyte P_ ((unsigned char *, int, int *, int *)); | |
497 extern int parse_str_to_multibyte P_ ((unsigned char *, int)); | |
498 extern int str_as_multibyte P_ ((unsigned char *, int, int, int *)); | |
499 extern int str_to_multibyte P_ ((unsigned char *, int, int)); | |
500 extern int str_as_unibyte P_ ((unsigned char *, int)); | |
501 extern int strwidth P_ ((unsigned char *, int)); | |
502 extern int c_string_width P_ ((unsigned char *, int, int, int *, int *)); | |
503 extern int lisp_string_width P_ ((Lisp_Object, int, int *, int *)); | |
504 | |
505 extern Lisp_Object Vprintable_chars; | |
506 | |
507 extern Lisp_Object Qcharacterp, Qauto_fill_chars; | |
508 extern Lisp_Object Vtranslation_table_vector; | |
509 extern Lisp_Object Vchar_width_table; | |
510 extern Lisp_Object Vchar_direction_table; | |
511 extern Lisp_Object Vchar_unify_table; | |
512 | |
513 /* Return a translation table of id number ID. */ | |
514 #define GET_TRANSLATION_TABLE(id) \ | |
515 (XCDR(XVECTOR(Vtranslation_table_vector)->contents[(id)])) | |
516 | |
517 /* A char-table for characters which may invoke auto-filling. */ | |
518 extern Lisp_Object Vauto_fill_chars; | |
519 | |
520 /* Copy LEN bytes from FROM to TO. This macro should be used only | |
521 when a caller knows that LEN is short and the obvious copy loop is | |
522 faster than calling bcopy which has some overhead. Copying a | |
523 multibyte sequence of a character is the typical case. */ | |
524 | |
525 #define BCOPY_SHORT(from, to, len) \ | |
526 do { \ | |
527 int i = len; \ | |
528 unsigned char *from_p = from, *to_p = to; \ | |
529 while (i--) *to_p++ = *from_p++; \ | |
530 } while (0) | |
531 | |
532 #define DEFSYM(sym, name) \ | |
533 do { (sym) = intern ((name)); staticpro (&(sym)); } while (0) | |
534 | |
535 #endif /* EMACS_CHARACTER_H */ |