4218
|
1 /* Character handling in C locale. |
|
2 |
|
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. |
|
7 |
|
8 Copyright (C) 2000-2003 Free Software Foundation, Inc. |
|
9 |
|
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 2 of the License, or |
|
13 (at your option) any later version. |
|
14 |
|
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. |
|
19 |
|
20 You should have received a copy of the GNU General Public License |
|
21 along with this program; if not, write to the Free Software |
|
22 Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ |
|
23 |
|
24 #ifndef C_CTYPE_H |
|
25 #define C_CTYPE_H |
|
26 |
|
27 #include <stdbool.h> |
|
28 |
|
29 |
4219
|
30 /* The functions defined in this file assume the "C" locale and a character |
|
31 set without diacritics (ASCII-US or EBCDIC-US or something like that). |
|
32 Even if the "C" locale on a particular system is an extension of the ASCII |
|
33 character set (like on BeOS, where it is UTF-8, or on AmigaOS, where it |
|
34 is ISO-8859-1), the functions in this file recognize only the ASCII |
|
35 characters. */ |
|
36 |
|
37 |
4218
|
38 /* Check whether the ASCII optimizations apply. */ |
|
39 |
|
40 /* ANSI C89 (and ISO C99 5.2.1.3 too) already guarantees that |
|
41 '0', '1', ..., '9' have consecutive integer values. */ |
|
42 #define C_CTYPE_CONSECUTIVE_DIGITS 1 |
|
43 |
|
44 #if ('A' <= 'Z') \ |
|
45 && ('A' + 1 == 'B') && ('B' + 1 == 'C') && ('C' + 1 == 'D') \ |
|
46 && ('D' + 1 == 'E') && ('E' + 1 == 'F') && ('F' + 1 == 'G') \ |
|
47 && ('G' + 1 == 'H') && ('H' + 1 == 'I') && ('I' + 1 == 'J') \ |
|
48 && ('J' + 1 == 'K') && ('K' + 1 == 'L') && ('L' + 1 == 'M') \ |
|
49 && ('M' + 1 == 'N') && ('N' + 1 == 'O') && ('O' + 1 == 'P') \ |
|
50 && ('P' + 1 == 'Q') && ('Q' + 1 == 'R') && ('R' + 1 == 'S') \ |
|
51 && ('S' + 1 == 'T') && ('T' + 1 == 'U') && ('U' + 1 == 'V') \ |
|
52 && ('V' + 1 == 'W') && ('W' + 1 == 'X') && ('X' + 1 == 'Y') \ |
|
53 && ('Y' + 1 == 'Z') |
|
54 #define C_CTYPE_CONSECUTIVE_UPPERCASE 1 |
|
55 #endif |
|
56 |
|
57 #if ('a' <= 'z') \ |
|
58 && ('a' + 1 == 'b') && ('b' + 1 == 'c') && ('c' + 1 == 'd') \ |
|
59 && ('d' + 1 == 'e') && ('e' + 1 == 'f') && ('f' + 1 == 'g') \ |
|
60 && ('g' + 1 == 'h') && ('h' + 1 == 'i') && ('i' + 1 == 'j') \ |
|
61 && ('j' + 1 == 'k') && ('k' + 1 == 'l') && ('l' + 1 == 'm') \ |
|
62 && ('m' + 1 == 'n') && ('n' + 1 == 'o') && ('o' + 1 == 'p') \ |
|
63 && ('p' + 1 == 'q') && ('q' + 1 == 'r') && ('r' + 1 == 's') \ |
|
64 && ('s' + 1 == 't') && ('t' + 1 == 'u') && ('u' + 1 == 'v') \ |
|
65 && ('v' + 1 == 'w') && ('w' + 1 == 'x') && ('x' + 1 == 'y') \ |
|
66 && ('y' + 1 == 'z') |
|
67 #define C_CTYPE_CONSECUTIVE_LOWERCASE 1 |
|
68 #endif |
|
69 |
|
70 #if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \ |
|
71 && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \ |
|
72 && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \ |
|
73 && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \ |
|
74 && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \ |
|
75 && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \ |
|
76 && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \ |
|
77 && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \ |
|
78 && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \ |
|
79 && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \ |
|
80 && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \ |
|
81 && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \ |
|
82 && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \ |
|
83 && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \ |
|
84 && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \ |
|
85 && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \ |
|
86 && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \ |
|
87 && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \ |
|
88 && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \ |
|
89 && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \ |
|
90 && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \ |
|
91 && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \ |
|
92 && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126) |
4219
|
93 /* The character set is ASCII or one of its variants or extensions, not EBCDIC. |
4218
|
94 Testing the value of '\n' and '\r' is not relevant. */ |
|
95 #define C_CTYPE_ASCII 1 |
|
96 #endif |
|
97 |
|
98 |
|
99 /* Function declarations. */ |
|
100 |
|
101 extern bool c_isascii (int c); /* not locale dependent */ |
|
102 |
|
103 extern bool c_isalnum (int c); |
|
104 extern bool c_isalpha (int c); |
|
105 extern bool c_isblank (int c); |
|
106 extern bool c_iscntrl (int c); |
|
107 extern bool c_isdigit (int c); |
|
108 extern bool c_islower (int c); |
|
109 extern bool c_isgraph (int c); |
|
110 extern bool c_isprint (int c); |
|
111 extern bool c_ispunct (int c); |
|
112 extern bool c_isspace (int c); |
|
113 extern bool c_isupper (int c); |
|
114 extern bool c_isxdigit (int c); |
|
115 |
|
116 extern int c_tolower (int c); |
|
117 extern int c_toupper (int c); |
|
118 |
|
119 |
|
120 #if defined __GNUC__ && defined __OPTIMIZE__ && !defined __OPTIMIZE_SIZE__ |
|
121 |
|
122 /* ASCII optimizations. */ |
|
123 |
|
124 #define c_isascii(c) \ |
|
125 ({ int __c = (c); \ |
4219
|
126 (__c >= 0x00 && __c <= 0x7f); \ |
4218
|
127 }) |
|
128 |
|
129 #if C_CTYPE_CONSECUTIVE_DIGITS \ |
|
130 && C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE |
|
131 #if C_CTYPE_ASCII |
|
132 #define c_isalnum(c) \ |
|
133 ({ int __c = (c); \ |
|
134 ((__c >= '0' && __c <= '9') \ |
|
135 || ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'Z')); \ |
|
136 }) |
|
137 #else |
|
138 #define c_isalnum(c) \ |
|
139 ({ int __c = (c); \ |
|
140 ((__c >= '0' && __c <= '9') \ |
|
141 || (__c >= 'A' && __c <= 'Z') \ |
|
142 || (__c >= 'a' && __c <= 'z')); \ |
|
143 }) |
|
144 #endif |
|
145 #endif |
|
146 |
|
147 #if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE |
|
148 #if C_CTYPE_ASCII |
|
149 #define c_isalpha(c) \ |
|
150 ({ int __c = (c); \ |
|
151 ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'Z'); \ |
|
152 }) |
|
153 #else |
|
154 #define c_isalpha(c) \ |
|
155 ({ int __c = (c); \ |
|
156 ((__c >= 'A' && __c <= 'Z') || (__c >= 'a' && __c <= 'z')); \ |
|
157 }) |
|
158 #endif |
|
159 #endif |
|
160 |
|
161 #define c_isblank(c) \ |
|
162 ({ int __c = (c); \ |
|
163 (__c == ' ' || __c == '\t'); \ |
|
164 }) |
|
165 |
|
166 #if C_CTYPE_ASCII |
|
167 #define c_iscntrl(c) \ |
|
168 ({ int __c = (c); \ |
|
169 ((__c & ~0x1f) == 0 || __c == 0x7f); \ |
|
170 }) |
|
171 #endif |
|
172 |
|
173 #if C_CTYPE_CONSECUTIVE_DIGITS |
|
174 #define c_isdigit(c) \ |
|
175 ({ int __c = (c); \ |
|
176 (__c >= '0' && __c <= '9'); \ |
|
177 }) |
|
178 #endif |
|
179 |
|
180 #if C_CTYPE_CONSECUTIVE_LOWERCASE |
|
181 #define c_islower(c) \ |
|
182 ({ int __c = (c); \ |
|
183 (__c >= 'a' && __c <= 'z'); \ |
|
184 }) |
|
185 #endif |
|
186 |
|
187 #if C_CTYPE_ASCII |
|
188 #define c_isgraph(c) \ |
|
189 ({ int __c = (c); \ |
|
190 (__c >= '!' && __c <= '~'); \ |
|
191 }) |
|
192 #endif |
|
193 |
|
194 #if C_CTYPE_ASCII |
|
195 #define c_isprint(c) \ |
|
196 ({ int __c = (c); \ |
|
197 (__c >= ' ' && __c <= '~'); \ |
|
198 }) |
|
199 #endif |
|
200 |
|
201 #if C_CTYPE_ASCII |
|
202 #define c_ispunct(c) \ |
|
203 ({ int _c = (c); \ |
|
204 (c_isgraph (_c) && ! c_isalnum (_c)); \ |
|
205 }) |
|
206 #endif |
|
207 |
|
208 #define c_isspace(c) \ |
|
209 ({ int __c = (c); \ |
|
210 (__c == ' ' || __c == '\t' \ |
|
211 || __c == '\n' || __c == '\v' || __c == '\f' || __c == '\r'); \ |
|
212 }) |
|
213 |
|
214 #if C_CTYPE_CONSECUTIVE_UPPERCASE |
|
215 #define c_isupper(c) \ |
|
216 ({ int __c = (c); \ |
|
217 (__c >= 'A' && __c <= 'Z'); \ |
|
218 }) |
|
219 #endif |
|
220 |
|
221 #if C_CTYPE_CONSECUTIVE_DIGITS \ |
|
222 && C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE |
|
223 #if C_CTYPE_ASCII |
|
224 #define c_isxdigit(c) \ |
|
225 ({ int __c = (c); \ |
|
226 ((__c >= '0' && __c <= '9') \ |
|
227 || ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'F')); \ |
|
228 }) |
|
229 #else |
|
230 #define c_isxdigit(c) \ |
|
231 ({ int __c = (c); \ |
|
232 ((__c >= '0' && __c <= '9') \ |
|
233 || (__c >= 'A' && __c <= 'F') \ |
|
234 || (__c >= 'a' && __c <= 'f')); \ |
|
235 }) |
|
236 #endif |
|
237 #endif |
|
238 |
|
239 #if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE |
|
240 #define c_tolower(c) \ |
|
241 ({ int __c = (c); \ |
|
242 (__c >= 'A' && __c <= 'Z' ? __c - 'A' + 'a' : __c); \ |
|
243 }) |
|
244 #define c_toupper(c) \ |
|
245 ({ int __c = (c); \ |
|
246 (__c >= 'a' && __c <= 'z' ? __c - 'a' + 'A' : __c); \ |
|
247 }) |
|
248 #endif |
|
249 |
|
250 #endif /* optimizing for speed */ |
|
251 |
|
252 #endif /* C_CTYPE_H */ |