summaryrefslogtreecommitdiffstats
path: root/lib/fnmatch.c
blob: 32cfb48d0f4b7a2d4d00aabf82d558e6509bbe98 (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
/* Copyright (C) 1991-2023 Free Software Foundation, Inc.
   This file is part of the GNU C Library.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library 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
   Lesser General Public License for more details.

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

#ifndef _LIBC
# include <libc-config.h>
#endif

/* Enable GNU extensions in fnmatch.h.  */
#ifndef _GNU_SOURCE
# define _GNU_SOURCE    1
#endif

#include <fnmatch.h>

#include <assert.h>
#include <errno.h>
#include <ctype.h>
#include <string.h>
#include <stdckdint.h>
#include <stdlib.h>
#if defined _LIBC || HAVE_ALLOCA
# include <alloca.h>
#endif
#include <wchar.h>
#include <wctype.h>
#include <stddef.h>

/* We need some of the locale data (the collation sequence information)
   but there is no interface to get this information in general.  Therefore
   we support a correct implementation only in glibc.  */
#ifdef _LIBC
# include "../locale/localeinfo.h"
# include "../locale/coll-lookup.h"
# include <shlib-compat.h>

# define CONCAT(a,b) __CONCAT(a,b)
# define btowc __btowc
# define iswctype __iswctype
# define mbsrtowcs __mbsrtowcs
# define mempcpy __mempcpy
# define strnlen __strnlen
# define towlower __towlower
# define wcscat __wcscat
# define wcslen __wcslen
# define wctype __wctype
# define wmemchr __wmemchr
# define wmempcpy __wmempcpy
# define fnmatch __fnmatch
extern int fnmatch (const char *pattern, const char *string, int flags);
#endif

#ifdef _LIBC
# if __glibc_has_attribute (__fallthrough__)
#  define FALLTHROUGH __attribute__ ((__fallthrough__))
# else
#  define FALLTHROUGH ((void) 0)
# endif
#else
# include "attribute.h"
#endif

#include <flexmember.h>

#ifdef _LIBC
typedef ptrdiff_t idx_t;
#else
# include "idx.h"
#endif

/* We often have to test for FNM_FILE_NAME and FNM_PERIOD being both set.  */
#define NO_LEADING_PERIOD(flags) \
  ((flags & (FNM_FILE_NAME | FNM_PERIOD)) == (FNM_FILE_NAME | FNM_PERIOD))

#ifndef _LIBC
# if HAVE_ALLOCA
/* The OS usually guarantees only one guard page at the bottom of the stack,
   and a page size can be as small as 4096 bytes.  So we cannot safely
   allocate anything larger than 4096 bytes.  Also care for the possibility
   of a few compiler-allocated temporary stack slots.  */
#  define __libc_use_alloca(n) ((n) < 4032)
# else
/* Just use malloc.  */
#  define __libc_use_alloca(n) false
#  undef alloca
#  define alloca(n) malloc (n)
# endif
# define alloca_account(size, avar) ((avar) += (size), alloca (size))
#endif

/* Provide support for user-defined character classes, based on the functions
   from ISO C 90 amendment 1.  */
#ifdef CHARCLASS_NAME_MAX
# define CHAR_CLASS_MAX_LENGTH CHARCLASS_NAME_MAX
#else
/* This shouldn't happen but some implementation might still have this
   problem.  Use a reasonable default value.  */
# define CHAR_CLASS_MAX_LENGTH 256
#endif

#define IS_CHAR_CLASS(string) wctype (string)

/* Avoid depending on library functions or files
   whose names are inconsistent.  */

/* Global variable.  */
static int posixly_correct;

/* Note that this evaluates C many times.  */
#define FOLD(c) ((flags & FNM_CASEFOLD) ? tolower (c) : (c))
#define CHAR    char
#define UCHAR   unsigned char
#define INT     int
#define FCT     internal_fnmatch
#define EXT     ext_match
#define END     end_pattern
#define STRUCT  fnmatch_struct
#define L_(CS)  CS
#define BTOWC(C) btowc (C)
#define STRLEN(S) strlen (S)
#define STRCAT(D, S) strcat (D, S)
#define MEMPCPY(D, S, N) mempcpy (D, S, N)
#define MEMCHR(S, C, N) memchr (S, C, N)
#define WIDE_CHAR_VERSION 0
#ifdef _LIBC
# include <locale/weight.h>
# define FINDIDX findidx
#endif
#include "fnmatch_loop.c"


#define FOLD(c) ((flags & FNM_CASEFOLD) ? towlower (c) : (c))
#define CHAR    wchar_t
#define UCHAR   wint_t
#define INT     wint_t
#define FCT     internal_fnwmatch
#define EXT     ext_wmatch
#define END     end_wpattern
#define L_(CS)  L##CS
#define BTOWC(C) (C)
#define STRLEN(S) wcslen (S)
#define STRCAT(D, S) wcscat (D, S)
#define MEMPCPY(D, S, N) wmempcpy (D, S, N)
#define MEMCHR(S, C, N) wmemchr (S, C, N)
#define WIDE_CHAR_VERSION 1
#ifdef _LIBC
/* Change the name the header defines so it doesn't conflict with
   the <locale/weight.h> version included above.  */
# define findidx findidxwc
# include <locale/weightwc.h>
# undef findidx
# define FINDIDX findidxwc
#endif

#undef IS_CHAR_CLASS
/* We have to convert the wide character string in a multibyte string.  But
   we know that the character class names consist of alphanumeric characters
   from the portable character set, and since the wide character encoding
   for a member of the portable character set is the same code point as
   its single-byte encoding, we can use a simplified method to convert the
   string to a multibyte character string.  */
static wctype_t
is_char_class (const wchar_t *wcs)
{
  char s[CHAR_CLASS_MAX_LENGTH + 1];
  char *cp = s;

  do
    {
      /* Test for a printable character from the portable character set.  */
#ifdef _LIBC
      if (*wcs < 0x20 || *wcs > 0x7e
          || *wcs == 0x24 || *wcs == 0x40 || *wcs == 0x60)
        return (wctype_t) 0;
#else
      switch (*wcs)
        {
        case L' ': case L'!': case L'"': case L'#': case L'%':
        case L'&': case L'\'': case L'(': case L')': case L'*':
        case L'+': case L',': case L'-': case L'.': case L'/':
        case L'0': case L'1': case L'2': case L'3': case L'4':
        case L'5': case L'6': case L'7': case L'8': case L'9':
        case L':': case L';': case L'<': case L'=': case L'>':
        case L'?':
        case L'A': case L'B': case L'C': case L'D': case L'E':
        case L'F': case L'G': case L'H': case L'I': case L'J':
        case L'K': case L'L': case L'M': case L'N': case L'O':
        case L'P': case L'Q': case L'R': case L'S': case L'T':
        case L'U': case L'V': case L'W': case L'X': case L'Y':
        case L'Z':
        case L'[': case L'\\': case L']': case L'^': case L'_':
        case L'a': case L'b': case L'c': case L'd': case L'e':
        case L'f': case L'g': case L'h': case L'i': case L'j':
        case L'k': case L'l': case L'm': case L'n': case L'o':
        case L'p': case L'q': case L'r': case L's': case L't':
        case L'u': case L'v': case L'w': case L'x': case L'y':
        case L'z': case L'{': case L'|': case L'}': case L'~':
          break;
        default:
          return (wctype_t) 0;
        }
#endif

      /* Avoid overrunning the buffer.  */
      if (cp == s + CHAR_CLASS_MAX_LENGTH)
        return (wctype_t) 0;

      *cp++ = (char) *wcs++;
    }
  while (*wcs != L'\0');

  *cp = '\0';

  return wctype (s);
}
#define IS_CHAR_CLASS(string) is_char_class (string)

#include "fnmatch_loop.c"


int
fnmatch (const char *pattern, const char *string, int flags)
{
  if (__glibc_unlikely (MB_CUR_MAX != 1))
    {
      mbstate_t ps;
      size_t n;
      const char *p;
      wchar_t *wpattern_malloc = NULL;
      wchar_t *wpattern;
      wchar_t *wstring_malloc = NULL;
      wchar_t *wstring;
      size_t alloca_used = 0;

      /* Convert the strings into wide characters.  */
      memset (&ps, '\0', sizeof (ps));
      p = pattern;
      n = strnlen (pattern, 1024);
      if (__glibc_likely (n < 1024))
        {
          wpattern = (wchar_t *) alloca_account ((n + 1) * sizeof (wchar_t),
                                                 alloca_used);
          n = mbsrtowcs (wpattern, &p, n + 1, &ps);
          if (__glibc_unlikely (n == (size_t) -1))
            /* Something wrong.
               XXX Do we have to set 'errno' to something which mbsrtows hasn't
               already done?  */
            return -1;
          if (p)
            {
              memset (&ps, '\0', sizeof (ps));
              goto prepare_wpattern;
            }
        }
      else
        {
        prepare_wpattern:
          n = mbsrtowcs (NULL, &pattern, 0, &ps);
          if (__glibc_unlikely (n == (size_t) -1))
            /* Something wrong.
               XXX Do we have to set 'errno' to something which mbsrtows hasn't
               already done?  */
            return -1;
          if (__glibc_unlikely (n >= (size_t) -1 / sizeof (wchar_t)))
            {
              __set_errno (ENOMEM);
              return -2;
            }
          wpattern_malloc = wpattern
            = (wchar_t *) malloc ((n + 1) * sizeof (wchar_t));
          assert (mbsinit (&ps));
          if (wpattern == NULL)
            return -2;
          (void) mbsrtowcs (wpattern, &pattern, n + 1, &ps);
        }

      assert (mbsinit (&ps));
      n = strnlen (string, 1024);
      p = string;
      if (__glibc_likely (n < 1024))
        {
          wstring = (wchar_t *) alloca_account ((n + 1) * sizeof (wchar_t),
                                                alloca_used);
          n = mbsrtowcs (wstring, &p, n + 1, &ps);
          if (__glibc_unlikely (n == (size_t) -1))
            {
              /* Something wrong.
                 XXX Do we have to set 'errno' to something which
                 mbsrtows hasn't already done?  */
            free_return:
              free (wpattern_malloc);
              return -1;
            }
          if (p)
            {
              memset (&ps, '\0', sizeof (ps));
              goto prepare_wstring;
            }
        }
      else
        {
        prepare_wstring:
          n = mbsrtowcs (NULL, &string, 0, &ps);
          if (__glibc_unlikely (n == (size_t) -1))
            /* Something wrong.
               XXX Do we have to set 'errno' to something which mbsrtows hasn't
               already done?  */
            goto free_return;
          if (__glibc_unlikely (n >= (size_t) -1 / sizeof (wchar_t)))
            {
              free (wpattern_malloc);
              __set_errno (ENOMEM);
              return -2;
            }

          wstring_malloc = wstring
            = (wchar_t *) malloc ((n + 1) * sizeof (wchar_t));
          if (wstring == NULL)
            {
              free (wpattern_malloc);
              return -2;
            }
          assert (mbsinit (&ps));
          (void) mbsrtowcs (wstring, &string, n + 1, &ps);
        }

      int res = internal_fnwmatch (wpattern, wstring, wstring + n,
                                   flags & FNM_PERIOD, flags, NULL,
                                   alloca_used);

      free (wstring_malloc);
      free (wpattern_malloc);

      return res;
    }

  return internal_fnmatch (pattern, string, string + strlen (string),
                           flags & FNM_PERIOD, flags, NULL, 0);
}

#undef fnmatch
versioned_symbol (libc, __fnmatch, fnmatch, GLIBC_2_2_3);
#if SHLIB_COMPAT(libc, GLIBC_2_0, GLIBC_2_2_3)
strong_alias (__fnmatch, __fnmatch_old)
compat_symbol (libc, __fnmatch_old, fnmatch, GLIBC_2_0);
#endif
libc_hidden_ver (__fnmatch, fnmatch)