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, 2006, 2008 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 3 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 Foundation,
22: Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
23:
24: #ifndef C_CTYPE_H
25: #define C_CTYPE_H
26:
27: #include <stdbool.h>
28:
29:
30: #ifdef __cplusplus
31: extern "C" {
32: #endif
33:
34:
35: /* The functions defined in this file assume the "C" locale and a character
36: set without diacritics (ASCII-US or EBCDIC-US or something like that).
37: Even if the "C" locale on a particular system is an extension of the ASCII
38: character set (like on BeOS, where it is UTF-8, or on AmigaOS, where it
39: is ISO-8859-1), the functions in this file recognize only the ASCII
40: characters. */
41:
42:
43: /* Check whether the ASCII optimizations apply. */
44:
45: /* ANSI C89 (and ISO C99 5.2.1.3 too) already guarantees that
46: '0', '1', ..., '9' have consecutive integer values. */
47: #define C_CTYPE_CONSECUTIVE_DIGITS 1
48:
49: #if ('A' <= 'Z') \
50: && ('A' + 1 == 'B') && ('B' + 1 == 'C') && ('C' + 1 == 'D') \
51: && ('D' + 1 == 'E') && ('E' + 1 == 'F') && ('F' + 1 == 'G') \
52: && ('G' + 1 == 'H') && ('H' + 1 == 'I') && ('I' + 1 == 'J') \
53: && ('J' + 1 == 'K') && ('K' + 1 == 'L') && ('L' + 1 == 'M') \
54: && ('M' + 1 == 'N') && ('N' + 1 == 'O') && ('O' + 1 == 'P') \
55: && ('P' + 1 == 'Q') && ('Q' + 1 == 'R') && ('R' + 1 == 'S') \
56: && ('S' + 1 == 'T') && ('T' + 1 == 'U') && ('U' + 1 == 'V') \
57: && ('V' + 1 == 'W') && ('W' + 1 == 'X') && ('X' + 1 == 'Y') \
58: && ('Y' + 1 == 'Z')
59: #define C_CTYPE_CONSECUTIVE_UPPERCASE 1
60: #endif
61:
62: #if ('a' <= 'z') \
63: && ('a' + 1 == 'b') && ('b' + 1 == 'c') && ('c' + 1 == 'd') \
64: && ('d' + 1 == 'e') && ('e' + 1 == 'f') && ('f' + 1 == 'g') \
65: && ('g' + 1 == 'h') && ('h' + 1 == 'i') && ('i' + 1 == 'j') \
66: && ('j' + 1 == 'k') && ('k' + 1 == 'l') && ('l' + 1 == 'm') \
67: && ('m' + 1 == 'n') && ('n' + 1 == 'o') && ('o' + 1 == 'p') \
68: && ('p' + 1 == 'q') && ('q' + 1 == 'r') && ('r' + 1 == 's') \
69: && ('s' + 1 == 't') && ('t' + 1 == 'u') && ('u' + 1 == 'v') \
70: && ('v' + 1 == 'w') && ('w' + 1 == 'x') && ('x' + 1 == 'y') \
71: && ('y' + 1 == 'z')
72: #define C_CTYPE_CONSECUTIVE_LOWERCASE 1
73: #endif
74:
75: #if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
76: && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \
77: && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \
78: && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \
79: && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \
80: && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \
81: && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \
82: && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \
83: && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \
84: && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \
85: && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \
86: && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \
87: && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \
88: && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \
89: && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \
90: && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \
91: && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \
92: && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \
93: && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \
94: && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \
95: && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \
96: && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \
97: && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126)
98: /* The character set is ASCII or one of its variants or extensions, not EBCDIC.
99: Testing the value of '\n' and '\r' is not relevant. */
100: #define C_CTYPE_ASCII 1
101: #endif
102:
103:
104: /* Function declarations. */
105:
106: /* Unlike the functions in <ctype.h>, which require an argument in the range
107: of the 'unsigned char' type, the functions here operate on values that are
108: in the 'unsigned char' range or in the 'char' range. In other words,
109: when you have a 'char' value, you need to cast it before using it as
110: argument to a <ctype.h> function:
111:
112: const char *s = ...;
113: if (isalpha ((unsigned char) *s)) ...
114:
115: but you don't need to cast it for the functions defined in this file:
116:
117: const char *s = ...;
118: if (c_isalpha (*s)) ...
119: */
120:
121: extern bool c_isascii (int c); /* not locale dependent */
122:
123: extern bool c_isalnum (int c);
124: extern bool c_isalpha (int c);
125: extern bool c_isblank (int c);
126: extern bool c_iscntrl (int c);
127: extern bool c_isdigit (int c);
128: extern bool c_islower (int c);
129: extern bool c_isgraph (int c);
130: extern bool c_isprint (int c);
131: extern bool c_ispunct (int c);
132: extern bool c_isspace (int c);
133: extern bool c_isupper (int c);
134: extern bool c_isxdigit (int c);
135:
136: extern int c_tolower (int c);
137: extern int c_toupper (int c);
138:
139:
140: #if defined __GNUC__ && defined __OPTIMIZE__ && !defined __OPTIMIZE_SIZE__ && !defined NO_C_CTYPE_MACROS
141:
142: /* ASCII optimizations. */
143:
144: #undef c_isascii
145: #define c_isascii(c) \
146: ({ int __c = (c); \
147: (__c >= 0x00 && __c <= 0x7f); \
148: })
149:
150: #if C_CTYPE_CONSECUTIVE_DIGITS \
151: && C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
152: #if C_CTYPE_ASCII
153: #undef c_isalnum
154: #define c_isalnum(c) \
155: ({ int __c = (c); \
156: ((__c >= '0' && __c <= '9') \
157: || ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'Z')); \
158: })
159: #else
160: #undef c_isalnum
161: #define c_isalnum(c) \
162: ({ int __c = (c); \
163: ((__c >= '0' && __c <= '9') \
164: || (__c >= 'A' && __c <= 'Z') \
165: || (__c >= 'a' && __c <= 'z')); \
166: })
167: #endif
168: #endif
169:
170: #if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
171: #if C_CTYPE_ASCII
172: #undef c_isalpha
173: #define c_isalpha(c) \
174: ({ int __c = (c); \
175: ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'Z'); \
176: })
177: #else
178: #undef c_isalpha
179: #define c_isalpha(c) \
180: ({ int __c = (c); \
181: ((__c >= 'A' && __c <= 'Z') || (__c >= 'a' && __c <= 'z')); \
182: })
183: #endif
184: #endif
185:
186: #undef c_isblank
187: #define c_isblank(c) \
188: ({ int __c = (c); \
189: (__c == ' ' || __c == '\t'); \
190: })
191:
192: #if C_CTYPE_ASCII
193: #undef c_iscntrl
194: #define c_iscntrl(c) \
195: ({ int __c = (c); \
196: ((__c & ~0x1f) == 0 || __c == 0x7f); \
197: })
198: #endif
199:
200: #if C_CTYPE_CONSECUTIVE_DIGITS
201: #undef c_isdigit
202: #define c_isdigit(c) \
203: ({ int __c = (c); \
204: (__c >= '0' && __c <= '9'); \
205: })
206: #endif
207:
208: #if C_CTYPE_CONSECUTIVE_LOWERCASE
209: #undef c_islower
210: #define c_islower(c) \
211: ({ int __c = (c); \
212: (__c >= 'a' && __c <= 'z'); \
213: })
214: #endif
215:
216: #if C_CTYPE_ASCII
217: #undef c_isgraph
218: #define c_isgraph(c) \
219: ({ int __c = (c); \
220: (__c >= '!' && __c <= '~'); \
221: })
222: #endif
223:
224: #if C_CTYPE_ASCII
225: #undef c_isprint
226: #define c_isprint(c) \
227: ({ int __c = (c); \
228: (__c >= ' ' && __c <= '~'); \
229: })
230: #endif
231:
232: #if C_CTYPE_ASCII
233: #undef c_ispunct
234: #define c_ispunct(c) \
235: ({ int _c = (c); \
236: (c_isgraph (_c) && ! c_isalnum (_c)); \
237: })
238: #endif
239:
240: #undef c_isspace
241: #define c_isspace(c) \
242: ({ int __c = (c); \
243: (__c == ' ' || __c == '\t' \
244: || __c == '\n' || __c == '\v' || __c == '\f' || __c == '\r'); \
245: })
246:
247: #if C_CTYPE_CONSECUTIVE_UPPERCASE
248: #undef c_isupper
249: #define c_isupper(c) \
250: ({ int __c = (c); \
251: (__c >= 'A' && __c <= 'Z'); \
252: })
253: #endif
254:
255: #if C_CTYPE_CONSECUTIVE_DIGITS \
256: && C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
257: #if C_CTYPE_ASCII
258: #undef c_isxdigit
259: #define c_isxdigit(c) \
260: ({ int __c = (c); \
261: ((__c >= '0' && __c <= '9') \
262: || ((__c & ~0x20) >= 'A' && (__c & ~0x20) <= 'F')); \
263: })
264: #else
265: #undef c_isxdigit
266: #define c_isxdigit(c) \
267: ({ int __c = (c); \
268: ((__c >= '0' && __c <= '9') \
269: || (__c >= 'A' && __c <= 'F') \
270: || (__c >= 'a' && __c <= 'f')); \
271: })
272: #endif
273: #endif
274:
275: #if C_CTYPE_CONSECUTIVE_UPPERCASE && C_CTYPE_CONSECUTIVE_LOWERCASE
276: #undef c_tolower
277: #define c_tolower(c) \
278: ({ int __c = (c); \
279: (__c >= 'A' && __c <= 'Z' ? __c - 'A' + 'a' : __c); \
280: })
281: #undef c_toupper
282: #define c_toupper(c) \
283: ({ int __c = (c); \
284: (__c >= 'a' && __c <= 'z' ? __c - 'a' + 'A' : __c); \
285: })
286: #endif
287:
288: #endif /* optimizing for speed */
289:
290:
291: #ifdef __cplusplus
292: }
293: #endif
294:
295: #endif /* C_CTYPE_H */
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>