c-ctype.h 9.26 KB
Newer Older
1 2 3 4 5 6 7
/* 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.

Paul Eggert's avatar
Paul Eggert committed
8
   Copyright (C) 2000-2003, 2006, 2008-2019 Free Software Foundation, Inc.
9 10 11 12 13 14 15 16 17 18 19 20

This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.

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
Paul Eggert's avatar
Paul Eggert committed
21
along with this program; if not, see <https://www.gnu.org/licenses/>.  */
22 23 24 25 26 27

#ifndef C_CTYPE_H
#define C_CTYPE_H

#include <stdbool.h>

Paul Eggert's avatar
Paul Eggert committed
28 29 30 31 32 33 34
#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
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

#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.  */
Paul Eggert's avatar
Paul Eggert committed
74 75 76 77 78 79 80
# 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

Paul Eggert's avatar
Paul Eggert committed
81 82 83 84 85 86 87 88 89 90 91 92
#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.  */
Paul Eggert's avatar
Paul Eggert committed
93 94

#if C_CTYPE_ASCII
Paul Eggert's avatar
Paul Eggert committed
95
# define _C_CTYPE_OTHER_CNTRL \
Paul Eggert's avatar
Paul Eggert committed
96
    case '\x00': case '\x01': case '\x02': case '\x03': \
Paul Eggert's avatar
Paul Eggert committed
97 98 99 100 101 102
    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'
Paul Eggert's avatar
Paul Eggert committed
103 104 105
#else
   /* Use EBCDIC code page 1047's assignments for ASCII control chars;
      assume all EBCDIC code pages agree about these assignments.  */
Paul Eggert's avatar
Paul Eggert committed
106
# define _C_CTYPE_OTHER_CNTRL \
Paul Eggert's avatar
Paul Eggert committed
107
    case '\x00': case '\x01': case '\x02': case '\x03': \
Paul Eggert's avatar
Paul Eggert committed
108 109 110 111 112 113
    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'
114 115
#endif

Paul Eggert's avatar
Paul Eggert committed
116
/* Cases for lowercase hex letters, and lowercase letters, all offset by N.  */
Paul Eggert's avatar
Paul Eggert committed
117

Paul Eggert's avatar
Paul Eggert committed
118 119 120 121 122 123 124 125 126 127
#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)
Paul Eggert's avatar
Paul Eggert committed
128 129 130 131 132 133 134 135 136 137 138 139

/* 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 \
Paul Eggert's avatar
Paul Eggert committed
140 141 142 143 144 145 146 147
   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 '~'
Paul Eggert's avatar
Paul Eggert committed
148 149
#define _C_CTYPE_UPPER _C_CTYPE_LOWER_N ('A' - 'a')

Paul Eggert's avatar
Paul Eggert committed
150 151

/* Function definitions.  */
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167

/* 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)) ...
 */

Paul Eggert's avatar
Paul Eggert committed
168 169 170 171 172 173 174 175 176 177 178 179 180
C_CTYPE_INLINE bool
c_isalnum (int c)
{
  switch (c)
    {
    _C_CTYPE_DIGIT:
    _C_CTYPE_LOWER:
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}
181

Paul Eggert's avatar
Paul Eggert committed
182 183 184 185 186 187 188 189 190 191 192 193
C_CTYPE_INLINE bool
c_isalpha (int c)
{
  switch (c)
    {
    _C_CTYPE_LOWER:
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}
194

Paul Eggert's avatar
Paul Eggert committed
195 196 197 198 199 200 201 202 203 204 205
/* 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:
Paul Eggert's avatar
Paul Eggert committed
206
    _C_CTYPE_PUNCT:
Paul Eggert's avatar
Paul Eggert committed
207 208 209 210 211 212
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}
213

Paul Eggert's avatar
Paul Eggert committed
214 215 216 217 218
C_CTYPE_INLINE bool
c_isblank (int c)
{
  return c == ' ' || c == '\t';
}
219

Paul Eggert's avatar
Paul Eggert committed
220 221 222 223 224 225 226 227 228 229 230
C_CTYPE_INLINE bool
c_iscntrl (int c)
{
  switch (c)
    {
    _C_CTYPE_CNTRL:
      return true;
    default:
      return false;
    }
}
231

Paul Eggert's avatar
Paul Eggert committed
232 233 234 235 236 237 238 239 240 241 242
C_CTYPE_INLINE bool
c_isdigit (int c)
{
  switch (c)
    {
    _C_CTYPE_DIGIT:
      return true;
    default:
      return false;
    }
}
243

Paul Eggert's avatar
Paul Eggert committed
244 245 246 247 248 249 250
C_CTYPE_INLINE bool
c_isgraph (int c)
{
  switch (c)
    {
    _C_CTYPE_DIGIT:
    _C_CTYPE_LOWER:
Paul Eggert's avatar
Paul Eggert committed
251
    _C_CTYPE_PUNCT:
Paul Eggert's avatar
Paul Eggert committed
252 253 254 255 256 257
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}
258

Paul Eggert's avatar
Paul Eggert committed
259 260 261 262 263 264 265 266 267 268 269
C_CTYPE_INLINE bool
c_islower (int c)
{
  switch (c)
    {
    _C_CTYPE_LOWER:
      return true;
    default:
      return false;
    }
}
270

Paul Eggert's avatar
Paul Eggert committed
271 272 273 274 275 276 277 278
C_CTYPE_INLINE bool
c_isprint (int c)
{
  switch (c)
    {
    case ' ':
    _C_CTYPE_DIGIT:
    _C_CTYPE_LOWER:
Paul Eggert's avatar
Paul Eggert committed
279
    _C_CTYPE_PUNCT:
Paul Eggert's avatar
Paul Eggert committed
280 281 282 283 284 285 286 287 288 289 290 291
    _C_CTYPE_UPPER:
      return true;
    default:
      return false;
    }
}

C_CTYPE_INLINE bool
c_ispunct (int c)
{
  switch (c)
    {
Paul Eggert's avatar
Paul Eggert committed
292
    _C_CTYPE_PUNCT:
Paul Eggert's avatar
Paul Eggert committed
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
      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)
    {
Paul Eggert's avatar
Paul Eggert committed
341
    _C_CTYPE_UPPER:
Paul Eggert's avatar
Paul Eggert committed
342 343 344 345 346
      return c - 'A' + 'a';
    default:
      return c;
    }
}
347

Paul Eggert's avatar
Paul Eggert committed
348 349 350 351 352
C_CTYPE_INLINE int
c_toupper (int c)
{
  switch (c)
    {
Paul Eggert's avatar
Paul Eggert committed
353
    _C_CTYPE_LOWER:
Paul Eggert's avatar
Paul Eggert committed
354 355 356 357 358
      return c - 'a' + 'A';
    default:
      return c;
    }
}
359 360 361 362 363

#ifdef __cplusplus
}
#endif

Paul Eggert's avatar
Paul Eggert committed
364 365
_GL_INLINE_HEADER_END

366
#endif /* C_CTYPE_H */