summary refs log tree commit diff
path: root/posix/fnmatch.c
blob: 7b225cf2bace55c19ece2fa67e8ee9ed09528cad (plain) (blame)
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
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
/* Copyright (C) 1991-2019 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
   <http://www.gnu.org/licenses/>.  */

#if HAVE_CONFIG_H
# include <config.h>
#endif

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

#include <assert.h>
#include <errno.h>
#include <fnmatch.h>
#include <ctype.h>
#include <string.h>

#if defined STDC_HEADERS || defined _LIBC
# include <stdlib.h>
#endif

#ifdef _LIBC
# include <alloca.h>
#else
# define alloca_account(size., var) alloca (size)
#endif

/* For platform which support the ISO C amendement 1 functionality we
   support user defined character classes.  */
#if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H)
/* Solaris 2.5 has a bug: <wchar.h> must be included before <wctype.h>.  */
# include <wchar.h>
# include <wctype.h>
#endif

/* 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/elem-hash.h"
# include "../locale/coll-lookup.h"
# include <shlib-compat.h>

# define CONCAT(a,b) __CONCAT(a,b)
# define mbsrtowcs __mbsrtowcs
# define fnmatch __fnmatch
extern int fnmatch (const char *pattern, const char *string, int flags);
#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))

/* Comment out all this code if we are using the GNU C Library, and are not
   actually compiling the library itself.  This code is part of the GNU C
   Library, but also included in many other GNU distributions.  Compiling
   and linking in this code is a waste when using the GNU C library
   (especially if it is a shared library).  Rather than having every GNU
   program understand `configure --with-gnu-libc' and omit the object files,
   it is simpler to just do this in the source for each such file.  */

#if defined _LIBC || !defined __GNU_LIBRARY__


# if defined STDC_HEADERS || !defined isascii
#  define ISASCII(c) 1
# else
#  define ISASCII(c) isascii(c)
# endif

# ifdef isblank
#  define ISBLANK(c) (ISASCII (c) && isblank (c))
# else
#  define ISBLANK(c) ((c) == ' ' || (c) == '\t')
# endif
# ifdef isgraph
#  define ISGRAPH(c) (ISASCII (c) && isgraph (c))
# else
#  define ISGRAPH(c) (ISASCII (c) && isprint (c) && !isspace (c))
# endif

# define ISPRINT(c) (ISASCII (c) && isprint (c))
# define ISDIGIT(c) (ISASCII (c) && isdigit (c))
# define ISALNUM(c) (ISASCII (c) && isalnum (c))
# define ISALPHA(c) (ISASCII (c) && isalpha (c))
# define ISCNTRL(c) (ISASCII (c) && iscntrl (c))
# define ISLOWER(c) (ISASCII (c) && islower (c))
# define ISPUNCT(c) (ISASCII (c) && ispunct (c))
# define ISSPACE(c) (ISASCII (c) && isspace (c))
# define ISUPPER(c) (ISASCII (c) && isupper (c))
# define ISXDIGIT(c) (ISASCII (c) && isxdigit (c))

# define STREQ(s1, s2) ((strcmp (s1, s2) == 0))

# if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H)
/* The GNU C library provides support for user-defined character classes
   and the functions from ISO C amendement 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

#  ifdef _LIBC
#   define IS_CHAR_CLASS(string) __wctype (string)
#  else
#   define IS_CHAR_CLASS(string) wctype (string)
#  endif

#  ifdef _LIBC
#   define ISWCTYPE(WC, WT)	__iswctype (WC, WT)
#  else
#   define ISWCTYPE(WC, WT)	iswctype (WC, WT)
#  endif

#  if (HAVE_MBSTATE_T && HAVE_MBSRTOWCS) || _LIBC
/* In this case we are implementing the multibyte character handling.  */
#   define HANDLE_MULTIBYTE	1
#  endif

# else
#  define CHAR_CLASS_MAX_LENGTH  6 /* Namely, `xdigit'.  */

#  define IS_CHAR_CLASS(string)						      \
   (STREQ (string, "alpha") || STREQ (string, "upper")			      \
    || STREQ (string, "lower") || STREQ (string, "digit")		      \
    || STREQ (string, "alnum") || STREQ (string, "xdigit")		      \
    || STREQ (string, "space") || STREQ (string, "print")		      \
    || STREQ (string, "punct") || STREQ (string, "graph")		      \
    || STREQ (string, "cntrl") || STREQ (string, "blank"))
# endif

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

# if !defined _LIBC && !defined getenv
extern char *getenv ();
# endif

# ifndef errno
extern int errno;
# endif

/* Global variable.  */
static int posixly_correct;

/* This function doesn't exist on most systems.  */

# if !defined HAVE___STRCHRNUL && !defined _LIBC
static char *
__strchrnul (const char *s, int c)
{
  char *result = strchr (s, c);
  if (result == NULL)
    result = strchr (s, '\0');
  return result;
}
# endif

# if HANDLE_MULTIBYTE && !defined HAVE___STRCHRNUL && !defined _LIBC
static wchar_t *
__wcschrnul (const wchar_t *s, wint_t c)
{
  wchar_t *result = wcschr (s, c);
  if (result == NULL)
    result = wcschr (s, '\0');
  return result;
}
# endif

/* Note that this evaluates C many times.  */
# ifdef _LIBC
#  define FOLD(c) ((flags & FNM_CASEFOLD) ? tolower (c) : (c))
# else
#  define FOLD(c) ((flags & FNM_CASEFOLD) && ISUPPER (c) ? tolower (c) : (c))
# endif
# 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
# ifdef _LIBC
#  define BTOWC(C)	__btowc (C)
# else
#  define BTOWC(C)	btowc (C)
# endif
# 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 STRCOLL(S1, S2) strcoll (S1, S2)
# define WIDE_CHAR_VERSION 0
# include <locale/weight.h>
# define FINDIDX findidx
# include "fnmatch_loop.c"


# if HANDLE_MULTIBYTE
/* Note that this evaluates C many times.  */
#  ifdef _LIBC
#   define FOLD(c) ((flags & FNM_CASEFOLD) ? __towlower (c) : (c))
#  else
#   define FOLD(c) ((flags & FNM_CASEFOLD) && ISUPPER (c) ? towlower (c) : (c))
#  endif
#  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 STRUCT fnwmatch_struct
#  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 STRCOLL(S1, S2) wcscoll (S1, S2)
#  define WIDE_CHAR_VERSION 1
/* 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

#  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';

#  ifdef _LIBC
  return __wctype (s);
#  else
  return wctype (s);
#  endif
}
#  define IS_CHAR_CLASS(string) is_char_class (string)

#  include "fnmatch_loop.c"
# endif


int
fnmatch (const char *pattern, const char *string, int flags)
{
# if HANDLE_MULTIBYTE
  if (__builtin_expect (MB_CUR_MAX, 1) != 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;
#ifdef _LIBC
      n = __strnlen (pattern, 1024);
#else
      n = strlen (pattern);
#endif
      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));
#ifdef _LIBC
      n = __strnlen (string, 1024);
#else
      n = strlen (string);
#endif
      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;
    }
# endif  /* mbstate_t and mbsrtowcs or _LIBC.  */

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

# ifdef _LIBC
#  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)
# endif

#endif	/* _LIBC or not __GNU_LIBRARY__.  */