summaryrefslogtreecommitdiff
path: root/lib/c-ctype.h
blob: 341c1c825a9a88d2ef10ae7f82ff14d30e2a43ec (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
/* Character handling in C locale.

   These functions work like the corresponding functions in <ctype.h>,
   except that they have the C (POSIX) locale hardwired, whereas the
   <ctype.h> functions' behaviour depends on the current locale set via
   setlocale.

   Copyright (C) 2000-2003, 2006, 2008-2016 Free Software Foundation, Inc.

   This program is free software: you can redistribute it and/or
   modify it under the terms of either:

     * the GNU Lesser General Public License as published by the Free
       Software Foundation; either version 3 of the License, or (at your
       option) any later version.

   or

     * the GNU General Public License as published by the Free
       Software Foundation; either version 2 of the License, or (at your
       option) any later version.

   or both in parallel, as here.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; if not, see <http://www.gnu.org/licenses/>.  */

#ifndef C_CTYPE_H
#define C_CTYPE_H

#include <stdbool.h>

#ifndef _GL_INLINE_HEADER_BEGIN
 #error "Please include config.h first."
#endif
_GL_INLINE_HEADER_BEGIN
#ifndef C_CTYPE_INLINE
# define C_CTYPE_INLINE _GL_INLINE
#endif

#ifdef __cplusplus
extern "C" {
#endif


/* The functions defined in this file assume the "C" locale and a character
   set without diacritics (ASCII-US or EBCDIC-US or something like that).
   Even if the "C" locale on a particular system is an extension of the ASCII
   character set (like on BeOS, where it is UTF-8, or on AmigaOS, where it
   is ISO-8859-1), the functions in this file recognize only the ASCII
   characters.  */


#if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
    && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \
    && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \
    && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \
    && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \
    && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \
    && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \
    && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \
    && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \
    && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \
    && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \
    && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \
    && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \
    && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \
    && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \
    && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \
    && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \
    && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \
    && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \
    && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \
    && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \
    && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \
    && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126)
/* The character set is ASCII or one of its variants or extensions, not EBCDIC.
   Testing the value of '\n' and '\r' is not relevant.  */
# define C_CTYPE_ASCII 1
#elif ! (' ' == '\x40' && '0' == '\xf0'                     \
         && 'A' == '\xc1' && 'J' == '\xd1' && 'S' == '\xe2' \
         && 'a' == '\x81' && 'j' == '\x91' && 's' == '\xa2')
# error "Only ASCII and EBCDIC are supported"
#endif

#if 'A' < 0
# error "EBCDIC and char is signed -- not supported"
#endif

/* Cases for control characters.  */

#define _C_CTYPE_CNTRL \
   case '\a': case '\b': case '\f': case '\n': \
   case '\r': case '\t': case '\v': \
   _C_CTYPE_OTHER_CNTRL

/* ASCII control characters other than those with \-letter escapes.  */

#if C_CTYPE_ASCII
# define _C_CTYPE_OTHER_CNTRL \
    case '\x00': case '\x01': case '\x02': case '\x03': \
    case '\x04': case '\x05': case '\x06': case '\x0e': \
    case '\x0f': case '\x10': case '\x11': case '\x12': \
    case '\x13': case '\x14': case '\x15': case '\x16': \
    case '\x17': case '\x18': case '\x19': case '\x1a': \
    case '\x1b': case '\x1c': case '\x1d': case '\x1e': \
    case '\x1f': case '\x7f'
#else
   /* Use EBCDIC code page 1047's assignments for ASCII control chars;
      assume all EBCDIC code pages agree about these assignments.  */
# define _C_CTYPE_OTHER_CNTRL \
    case '\x00': case '\x01': case '\x02': case '\x03': \
    case '\x07': case '\x0e': case '\x0f': case '\x10': \
    case '\x11': case '\x12': case '\x13': case '\x18': \
    case '\x19': case '\x1c': case '\x1d': case '\x1e': \
    case '\x1f': case '\x26': case '\x27': case '\x2d': \
    case '\x2e': case '\x32': case '\x37': case '\x3c': \
    case '\x3d': case '\x3f'
#endif

/* Cases for lowercase hex letters, and lowercase letters, all offset by N.  */

#define _C_CTYPE_LOWER_A_THRU_F_N(n) \
   case 'a' + (n): case 'b' + (n): case 'c' + (n): case 'd' + (n): \
   case 'e' + (n): case 'f' + (n)
#define _C_CTYPE_LOWER_N(n) \
   _C_CTYPE_LOWER_A_THRU_F_N(n): \
   case 'g' + (n): case 'h' + (n): case 'i' + (n): case 'j' + (n): \
   case 'k' + (n): case 'l' + (n): case 'm' + (n): case 'n' + (n): \
   case 'o' + (n): case 'p' + (n): case 'q' + (n): case 'r' + (n): \
   case 's' + (n): case 't' + (n): case 'u' + (n): case 'v' + (n): \
   case 'w' + (n): case 'x' + (n): case 'y' + (n): case 'z' + (n)

/* Cases for hex letters, digits, lower, punct, and upper.  */

#define _C_CTYPE_A_THRU_F \
   _C_CTYPE_LOWER_A_THRU_F_N (0): \
   _C_CTYPE_LOWER_A_THRU_F_N ('A' - 'a')
#define _C_CTYPE_DIGIT                     \
   case '0': case '1': case '2': case '3': \
   case '4': case '5': case '6': case '7': \
   case '8': case '9'
#define _C_CTYPE_LOWER _C_CTYPE_LOWER_N (0)
#define _C_CTYPE_PUNCT \
   case '!': case '"': case '#': case '$':  \
   case '%': case '&': case '\'': case '(': \
   case ')': case '*': case '+': case ',':  \
   case '-': case '.': case '/': case ':':  \
   case ';': case '<': case '=': case '>':  \
   case '?': case '@': case '[': case '\\': \
   case ']': case '^': case '_': case '`':  \
   case '{': case '|': case '}': case '~'
#define _C_CTYPE_UPPER _C_CTYPE_LOWER_N ('A' - 'a')


/* Function definitions.  */

/* Unlike the functions in <ctype.h>, which require an argument in the range
   of the 'unsigned char' type, the functions here operate on values that are
   in the 'unsigned char' range or in the 'char' range.  In other words,
   when you have a 'char' value, you need to cast it before using it as
   argument to a <ctype.h> function:

         const char *s = ...;
         if (isalpha ((unsigned char) *s)) ...

   but you don't need to cast it for the functions defined in this file:

         const char *s = ...;
         if (c_isalpha (*s)) ...
 */

C_CTYPE_INLINE bool
c_isalnum (int c)
{
  switch (c)
    {
    _C_CTYPE_DIGIT:
    _C_CTYPE_LOWER:
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_isalpha (int c)
{
  switch (c)
    {
    _C_CTYPE_LOWER:
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}

/* The function isascii is not locale dependent.
   Its use in EBCDIC is questionable. */
C_CTYPE_INLINE bool
c_isascii (int c)
{
  switch (c)
    {
    case ' ':
    _C_CTYPE_CNTRL:
    _C_CTYPE_DIGIT:
    _C_CTYPE_LOWER:
    _C_CTYPE_PUNCT:
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_isblank (int c)
{
  return c == ' ' || c == '\t';
}

C_CTYPE_INLINE bool
c_iscntrl (int c)
{
  switch (c)
    {
    _C_CTYPE_CNTRL:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_isdigit (int c)
{
  switch (c)
    {
    _C_CTYPE_DIGIT:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_isgraph (int c)
{
  switch (c)
    {
    _C_CTYPE_DIGIT:
    _C_CTYPE_LOWER:
    _C_CTYPE_PUNCT:
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_islower (int c)
{
  switch (c)
    {
    _C_CTYPE_LOWER:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_isprint (int c)
{
  switch (c)
    {
    case ' ':
    _C_CTYPE_DIGIT:
    _C_CTYPE_LOWER:
    _C_CTYPE_PUNCT:
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_ispunct (int c)
{
  switch (c)
    {
    _C_CTYPE_PUNCT:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_isspace (int c)
{
  switch (c)
    {
    case ' ': case '\t': case '\n': case '\v': case '\f': case '\r':
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_isupper (int c)
{
  switch (c)
    {
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_isxdigit (int c)
{
  switch (c)
    {
    _C_CTYPE_DIGIT:
    _C_CTYPE_A_THRU_F:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE int
c_tolower (int c)
{
  switch (c)
    {
    _C_CTYPE_UPPER:
      return c - 'A' + 'a';
    default:
      return c;
    }
}

C_CTYPE_INLINE int
c_toupper (int c)
{
  switch (c)
    {
    _C_CTYPE_LOWER:
      return c - 'a' + 'A';
    default:
      return c;
    }
}

#ifdef __cplusplus
}
#endif

_GL_INLINE_HEADER_END

#endif /* C_CTYPE_H */