ChangeLog fixes from M-x authors
[emacs.git] / lib / c-ctype.h
blob3a66440ae9e372bbeb2a589eec4ed900d1e7e937
1 /* Character handling in C locale.
3 These functions work like the corresponding functions in <ctype.h>,
4 except that they have the C (POSIX) locale hardwired, whereas the
5 <ctype.h> functions' behaviour depends on the current locale set via
6 setlocale.
8 Copyright (C) 2000-2003, 2006, 2008-2013 Free Software Foundation, Inc.
10 This program 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 3 of the License, or
13 (at your option) any later version.
15 This program 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 this program; if not, see <http://www.gnu.org/licenses/>. */
23 #ifndef C_CTYPE_H
24 #define C_CTYPE_H
26 #include <stdbool.h>
29 #ifdef __cplusplus
30 extern "C" {
31 #endif
34 /* The functions defined in this file assume the "C" locale and a character
35 set without diacritics (ASCII-US or EBCDIC-US or something like that).
36 Even if the "C" locale on a particular system is an extension of the ASCII
37 character set (like on BeOS, where it is UTF-8, or on AmigaOS, where it
38 is ISO-8859-1), the functions in this file recognize only the ASCII
39 characters. */
42 /* Check whether the ASCII optimizations apply. */
44 /* ANSI C89 (and ISO C99 5.2.1.3 too) already guarantees that
45 '0', '1', ..., '9' have consecutive integer values. */
46 #define C_CTYPE_CONSECUTIVE_DIGITS 1
48 #if ('A' <= 'Z') \
49 && ('A' + 1 == 'B') && ('B' + 1 == 'C') && ('C' + 1 == 'D') \
50 && ('D' + 1 == 'E') && ('E' + 1 == 'F') && ('F' + 1 == 'G') \
51 && ('G' + 1 == 'H') && ('H' + 1 == 'I') && ('I' + 1 == 'J') \
52 && ('J' + 1 == 'K') && ('K' + 1 == 'L') && ('L' + 1 == 'M') \
53 && ('M' + 1 == 'N') && ('N' + 1 == 'O') && ('O' + 1 == 'P') \
54 && ('P' + 1 == 'Q') && ('Q' + 1 == 'R') && ('R' + 1 == 'S') \
55 && ('S' + 1 == 'T') && ('T' + 1 == 'U') && ('U' + 1 == 'V') \
56 && ('V' + 1 == 'W') && ('W' + 1 == 'X') && ('X' + 1 == 'Y') \
57 && ('Y' + 1 == 'Z')
58 #define C_CTYPE_CONSECUTIVE_UPPERCASE 1
59 #endif
61 #if ('a' <= 'z') \
62 && ('a' + 1 == 'b') && ('b' + 1 == 'c') && ('c' + 1 == 'd') \
63 && ('d' + 1 == 'e') && ('e' + 1 == 'f') && ('f' + 1 == 'g') \
64 && ('g' + 1 == 'h') && ('h' + 1 == 'i') && ('i' + 1 == 'j') \
65 && ('j' + 1 == 'k') && ('k' + 1 == 'l') && ('l' + 1 == 'm') \
66 && ('m' + 1 == 'n') && ('n' + 1 == 'o') && ('o' + 1 == 'p') \
67 && ('p' + 1 == 'q') && ('q' + 1 == 'r') && ('r' + 1 == 's') \
68 && ('s' + 1 == 't') && ('t' + 1 == 'u') && ('u' + 1 == 'v') \
69 && ('v' + 1 == 'w') && ('w' + 1 == 'x') && ('x' + 1 == 'y') \
70 && ('y' + 1 == 'z')
71 #define C_CTYPE_CONSECUTIVE_LOWERCASE 1
72 #endif
74 #if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
75 && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \
76 && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \
77 && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \
78 && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \
79 && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \
80 && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \
81 && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \
82 && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \
83 && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \
84 && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \
85 && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \
86 && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \
87 && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \
88 && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \
89 && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \
90 && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \
91 && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \
92 && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \
93 && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \
94 && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \
95 && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \
96 && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126)
97 /* The character set is ASCII or one of its variants or extensions, not EBCDIC.
98 Testing the value of '\n' and '\r' is not relevant. */
99 #define C_CTYPE_ASCII 1
100 #endif
103 /* Function declarations. */
105 /* Unlike the functions in <ctype.h>, which require an argument in the range
106 of the 'unsigned char' type, the functions here operate on values that are
107 in the 'unsigned char' range or in the 'char' range. In other words,
108 when you have a 'char' value, you need to cast it before using it as
109 argument to a <ctype.h> function:
111 const char *s = ...;
112 if (isalpha ((unsigned char) *s)) ...
114 but you don't need to cast it for the functions defined in this file:
116 const char *s = ...;
117 if (c_isalpha (*s)) ...
120 extern bool c_isascii (int c) _GL_ATTRIBUTE_CONST; /* not locale dependent */
122 extern bool c_isalnum (int c) _GL_ATTRIBUTE_CONST;
123 extern bool c_isalpha (int c) _GL_ATTRIBUTE_CONST;
124 extern bool c_isblank (int c) _GL_ATTRIBUTE_CONST;
125 extern bool c_iscntrl (int c) _GL_ATTRIBUTE_CONST;
126 extern bool c_isdigit (int c) _GL_ATTRIBUTE_CONST;
127 extern bool c_islower (int c) _GL_ATTRIBUTE_CONST;
128 extern bool c_isgraph (int c) _GL_ATTRIBUTE_CONST;
129 extern bool c_isprint (int c) _GL_ATTRIBUTE_CONST;
130 extern bool c_ispunct (int c) _GL_ATTRIBUTE_CONST;
131 extern bool c_isspace (int c) _GL_ATTRIBUTE_CONST;
132 extern bool c_isupper (int c) _GL_ATTRIBUTE_CONST;
133 extern bool c_isxdigit (int c) _GL_ATTRIBUTE_CONST;
135 extern int c_tolower (int c) _GL_ATTRIBUTE_CONST;
136 extern int c_toupper (int c) _GL_ATTRIBUTE_CONST;
139 #if defined __GNUC__ && defined __OPTIMIZE__ && !defined __OPTIMIZE_SIZE__ && !defined NO_C_CTYPE_MACROS
141 /* ASCII optimizations. */
143 #undef c_isascii
144 #define c_isascii(c) \
145 ({ int __c = (c); \
146 (__c >= 0x00 && __c <= 0x7f); \
149 #if C_CTYPE_CONSECUTIVE_DIGITS \
150 && C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
151 #if C_CTYPE_ASCII
152 #undef c_isalnum
153 #define c_isalnum(c) \
154 ({ int __c = (c); \
155 ((__c >= '0' && __c <= '9') \
156 || ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'Z')); \
158 #else
159 #undef c_isalnum
160 #define c_isalnum(c) \
161 ({ int __c = (c); \
162 ((__c >= '0' && __c <= '9') \
163 || (__c >= 'A' && __c <= 'Z') \
164 || (__c >= 'a' && __c <= 'z')); \
166 #endif
167 #endif
169 #if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
170 #if C_CTYPE_ASCII
171 #undef c_isalpha
172 #define c_isalpha(c) \
173 ({ int __c = (c); \
174 ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'Z'); \
176 #else
177 #undef c_isalpha
178 #define c_isalpha(c) \
179 ({ int __c = (c); \
180 ((__c >= 'A' && __c <= 'Z') || (__c >= 'a' && __c <= 'z')); \
182 #endif
183 #endif
185 #undef c_isblank
186 #define c_isblank(c) \
187 ({ int __c = (c); \
188 (__c == ' ' || __c == '\t'); \
191 #if C_CTYPE_ASCII
192 #undef c_iscntrl
193 #define c_iscntrl(c) \
194 ({ int __c = (c); \
195 ((__c & ~0x1f) == 0 || __c == 0x7f); \
197 #endif
199 #if C_CTYPE_CONSECUTIVE_DIGITS
200 #undef c_isdigit
201 #define c_isdigit(c) \
202 ({ int __c = (c); \
203 (__c >= '0' && __c <= '9'); \
205 #endif
207 #if C_CTYPE_CONSECUTIVE_LOWERCASE
208 #undef c_islower
209 #define c_islower(c) \
210 ({ int __c = (c); \
211 (__c >= 'a' && __c <= 'z'); \
213 #endif
215 #if C_CTYPE_ASCII
216 #undef c_isgraph
217 #define c_isgraph(c) \
218 ({ int __c = (c); \
219 (__c >= '!' && __c <= '~'); \
221 #endif
223 #if C_CTYPE_ASCII
224 #undef c_isprint
225 #define c_isprint(c) \
226 ({ int __c = (c); \
227 (__c >= ' ' && __c <= '~'); \
229 #endif
231 #if C_CTYPE_ASCII
232 #undef c_ispunct
233 #define c_ispunct(c) \
234 ({ int _c = (c); \
235 (c_isgraph (_c) && ! c_isalnum (_c)); \
237 #endif
239 #undef c_isspace
240 #define c_isspace(c) \
241 ({ int __c = (c); \
242 (__c == ' ' || __c == '\t' \
243 || __c == '\n' || __c == '\v' || __c == '\f' || __c == '\r'); \
246 #if C_CTYPE_CONSECUTIVE_UPPERCASE
247 #undef c_isupper
248 #define c_isupper(c) \
249 ({ int __c = (c); \
250 (__c >= 'A' && __c <= 'Z'); \
252 #endif
254 #if C_CTYPE_CONSECUTIVE_DIGITS \
255 && C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
256 #if C_CTYPE_ASCII
257 #undef c_isxdigit
258 #define c_isxdigit(c) \
259 ({ int __c = (c); \
260 ((__c >= '0' && __c <= '9') \
261 || ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'F')); \
263 #else
264 #undef c_isxdigit
265 #define c_isxdigit(c) \
266 ({ int __c = (c); \
267 ((__c >= '0' && __c <= '9') \
268 || (__c >= 'A' && __c <= 'F') \
269 || (__c >= 'a' && __c <= 'f')); \
271 #endif
272 #endif
274 #if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
275 #undef c_tolower
276 #define c_tolower(c) \
277 ({ int __c = (c); \
278 (__c >= 'A' && __c <= 'Z' ? __c - 'A' + 'a' : __c); \
280 #undef c_toupper
281 #define c_toupper(c) \
282 ({ int __c = (c); \
283 (__c >= 'a' && __c <= 'z' ? __c - 'a' + 'A' : __c); \
285 #endif
287 #endif /* optimizing for speed */
290 #ifdef __cplusplus
292 #endif
294 #endif /* C_CTYPE_H */