about summary refs log tree commit diff
path: root/posix/fnmatch_loop.c
blob: 005dd99d7b10df7da7b3403eb1073fe067be8d10 (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
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
/* Copyright (C) 1991-1993, 1996-1999, 2000 Free Software Foundation, Inc.
   This file is part of the GNU C Library.

   This library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Library General Public License as
   published by the Free Software Foundation; either version 2 of the
   License, or (at your option) any later version.

   This 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
   Library General Public License for more details.

   You should have received a copy of the GNU Library General Public
   License along with this library; see the file COPYING.LIB.  If not,
   write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
   Boston, MA 02111-1307, USA.  */

/* Match STRING against the filename pattern PATTERN, returning zero if
   it matches, nonzero if not.  */
static int FCT (const CHAR *pattern, const CHAR *string,
		int no_leading_period, int flags) internal_function;

static int
internal_function
FCT (pattern, string, no_leading_period, flags)
     const CHAR *pattern;
     const CHAR *string;
     int no_leading_period;
     int flags;
{
  register const CHAR *p = pattern, *n = string;
  register UCHAR c;
#ifdef _LIBC
  const UCHAR *collseq = (const UCHAR *)
    _NL_CURRENT(LC_COLLATE, CONCAT(_NL_COLLATE_COLLSEQ,SUFFIX));
# ifdef WIDE_CHAR_VERSION
  const wint_t *names = (const wint_t *)
    _NL_CURRENT (LC_COLLATE, _NL_COLLATE_NAMES);
  size_t size = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_HASH_SIZE);
  size_t layers = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_HASH_LAYERS);
# endif
#endif

  while ((c = *p++) != L('\0'))
    {
      c = FOLD (c);

      switch (c)
	{
	case L('?'):
	  if (*n == L('\0'))
	    return FNM_NOMATCH;
	  else if (*n == L('/') && (flags & FNM_FILE_NAME))
	    return FNM_NOMATCH;
	  else if (*n == L('.') && no_leading_period
		   && (n == string
		       || (n[-1] == L('/') && (flags & FNM_FILE_NAME))))
	    return FNM_NOMATCH;
	  break;

	case L('\\'):
	  if (!(flags & FNM_NOESCAPE))
	    {
	      c = *p++;
	      if (c == L('\0'))
		/* Trailing \ loses.  */
		return FNM_NOMATCH;
	      c = FOLD (c);
	    }
	  if (FOLD ((UCHAR) *n) != c)
	    return FNM_NOMATCH;
	  break;

	case L('*'):
	  if (*n == L('.') && no_leading_period
	      && (n == string
		  || (n[-1] == L('/') && (flags & FNM_FILE_NAME))))
	    return FNM_NOMATCH;

	  for (c = *p++; c == L('?') || c == L('*'); c = *p++)
	    {
	      if (*n == L('/') && (flags & FNM_FILE_NAME))
		/* A slash does not match a wildcard under FNM_FILE_NAME.  */
		return FNM_NOMATCH;
	      else if (c == L('?'))
		{
		  /* A ? needs to match one character.  */
		  if (*n == L('\0'))
		    /* There isn't another character; no match.  */
		    return FNM_NOMATCH;
		  else
		    /* One character of the string is consumed in matching
		       this ? wildcard, so *??? won't match if there are
		       less than three characters.  */
		    ++n;
		}
	    }

	  if (c == L('\0'))
	    /* The wildcard(s) is/are the last element of the pattern.
	       If the name is a file name and contains another slash
	       this does mean it cannot match.  If the FNM_LEADING_DIR
	       flag is set and exactly one slash is following, we have
	       a match.  */
	    {
	      int result = (flags & FNM_FILE_NAME) == 0 ? 0 : FNM_NOMATCH;

	      if (flags & FNM_FILE_NAME)
		{
		  const CHAR *slashp = STRCHR (n, L('/'));

		  if (flags & FNM_LEADING_DIR)
		    {
		      if (slashp != NULL
			  && STRCHR (slashp + 1, L('/')) == NULL)
			result = 0;
		    }
		  else
		    {
		      if (slashp == NULL)
			result = 0;
		    }
		}

	      return result;
	    }
	  else
	    {
	      const CHAR *endp;

	      endp = STRCHRNUL (n, (flags & FNM_FILE_NAME) ? L('/') : L('\0'));

	      if (c == L('['))
		{
		  int flags2 = ((flags & FNM_FILE_NAME)
				? flags : (flags & ~FNM_PERIOD));

		  for (--p; n < endp; ++n)
		    if (FCT (p, n, (no_leading_period
				    && (n == string
					|| (n[-1] == L('/')
					    && (flags & FNM_FILE_NAME)))),
			     flags2) == 0)
		      return 0;
		}
	      else if (c == L('/') && (flags & FNM_FILE_NAME))
		{
		  while (*n != L('\0') && *n != L('/'))
		    ++n;
		  if (*n == L('/')
		      && (FCT (p, n + 1, flags & FNM_PERIOD, flags) == 0))
		    return 0;
		}
	      else
		{
		  int flags2 = ((flags & FNM_FILE_NAME)
				? flags : (flags & ~FNM_PERIOD));

		  if (c == L('\\') && !(flags & FNM_NOESCAPE))
		    c = *p;
		  c = FOLD (c);
		  for (--p; n < endp; ++n)
		    if (FOLD ((UCHAR) *n) == c
			&& (FCT (p, n, (no_leading_period
					&& (n == string
					    || (n[-1] == L('/')
						&& (flags & FNM_FILE_NAME)))),
				 flags2) == 0))
		      return 0;
		}
	    }

	  /* If we come here no match is possible with the wildcard.  */
	  return FNM_NOMATCH;

	case L('['):
	  {
	    static int posixly_correct;
	    /* Nonzero if the sense of the character class is inverted.  */
	    register int not;
	    CHAR cold;

	    if (posixly_correct == 0)
	      posixly_correct = getenv ("POSIXLY_CORRECT") != NULL ? 1 : -1;

	    if (*n == L('\0'))
	      return FNM_NOMATCH;

	    if (*n == L('.') && no_leading_period
		&& (n == string
		    || (n[-1] == L('/') && (flags & FNM_FILE_NAME))))
	      return FNM_NOMATCH;

	    if (*n == L('/') && (flags & FNM_FILE_NAME))
	      /* `/' cannot be matched.  */
	      return FNM_NOMATCH;

	    not = (*p == L('!') || (posixly_correct < 0 && *p == L('^')));
	    if (not)
	      ++p;

	    c = *p++;
	    for (;;)
	      {
		UCHAR fn = FOLD ((UCHAR) *n);

		if (!(flags & FNM_NOESCAPE) && c == L('\\'))
		  {
		    if (*p == L('\0'))
		      return FNM_NOMATCH;
		    c = FOLD ((UCHAR) *p);
		    ++p;

		    if (c == fn)
		      goto matched;
		  }
		else if (c == L('[') && *p == L(':'))
		  {
		    /* Leave room for the null.  */
		    CHAR str[CHAR_CLASS_MAX_LENGTH + 1];
		    size_t c1 = 0;
#if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H)
		    wctype_t wt;
#endif
		    const CHAR *startp = p;

		    for (;;)
		      {
			if (c1 == CHAR_CLASS_MAX_LENGTH)
			  /* The name is too long and therefore the pattern
			     is ill-formed.  */
			  return FNM_NOMATCH;

			c = *++p;
			if (c == L(':') && p[1] == L(']'))
			  {
			    p += 2;
			    break;
			  }
			if (c < L('a') || c >= L('z'))
			  {
			    /* This cannot possibly be a character class name.
			       Match it as a normal range.  */
			    p = startp;
			    c = L('[');
			    goto normal_bracket;
			  }
			str[c1++] = c;
		      }
		    str[c1] = L('\0');

#if defined _LIBC || (defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H)
		    wt = IS_CHAR_CLASS (str);
		    if (wt == 0)
		      /* Invalid character class name.  */
		      return FNM_NOMATCH;

		    /* The following code is glibc specific but does
		       there a good job in sppeding up the code since
		       we can avoid the btowc() call.  The
		       IS_CHAR_CLASS call will return a bit mask for
		       the 32-bit table.  We have to convert it to a
		       bitmask for the __ctype_b table.  This has to
		       be done based on the byteorder as can be seen
		       below.  In any case we will fall back on the
		       code using btowc() if the class is not one of
		       the standard classes.  */
# if defined _LIBC && ! WIDE_CHAR_VERSION
#  if __BYTE_ORDER == __LITTLE_ENDIAN
		    if ((wt & 0xf0ffff) == 0)
		      {
			wt >>= 16;
			if ((__ctype_b[(UCHAR) *n] & wt) != 0)
			  goto matched;
		      }
#  else
		    if (wt <= 0x800)
		      {
			if ((__ctype_b[(UCHAR) *n] & wt) != 0)
			  goto matched;
		      }
#  endif
		    else
# endif
		      if (ISWCTYPE (BTOWC ((UCHAR) *n), wt))
			goto matched;
#else
		    if ((STREQ (str, L("alnum")) && ISALNUM ((UCHAR) *n))
			|| (STREQ (str, L("alpha")) && ISALPHA ((UCHAR) *n))
			|| (STREQ (str, L("blank")) && ISBLANK ((UCHAR) *n))
			|| (STREQ (str, L("cntrl")) && ISCNTRL ((UCHAR) *n))
			|| (STREQ (str, L("digit")) && ISDIGIT ((UCHAR) *n))
			|| (STREQ (str, L("graph")) && ISGRAPH ((UCHAR) *n))
			|| (STREQ (str, L("lower")) && ISLOWER ((UCHAR) *n))
			|| (STREQ (str, L("print")) && ISPRINT ((UCHAR) *n))
			|| (STREQ (str, L("punct")) && ISPUNCT ((UCHAR) *n))
			|| (STREQ (str, L("space")) && ISSPACE ((UCHAR) *n))
			|| (STREQ (str, L("upper")) && ISUPPER ((UCHAR) *n))
			|| (STREQ (str, L("xdigit")) && ISXDIGIT ((UCHAR) *n)))
		      goto matched;
#endif
		    c = *p++;
		  }
#ifdef _LIBC
		else if (c == L('[') && *p == L('='))
		  {
		    UCHAR str[1];
		    uint32_t nrules =
		      _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES);
		    const CHAR *startp = p;

		    c = *++p;
		    if (c == L('\0'))
		      {
			p = startp;
			c = L('[');
			goto normal_bracket;
		      }
		    str[0] = c;

		    c = *++p;
		    if (c != L('=') || p[1] != L(']'))
		      {
			p = startp;
			c = L('[');
			goto normal_bracket;
		      }
		    p += 2;

		    if (nrules == 0)
		      {
			if ((UCHAR) *n == str[0])
			  goto matched;
		      }
		    else
		      {
			const int32_t *table;
# if WIDE_CHAR_VERSION
			const int32_t *weights;
			const int32_t *extra;
# else
			const unsigned char *weights;
			const unsigned char *extra;
# endif
			const int32_t *indirect;
			int32_t idx;
			const UCHAR *cp = (const UCHAR *) str;

			/* This #include defines a local function!  */
# if WIDE_CHAR_VERSION
#  include <locale/weightwc.h>
# else
#  include <locale/weight.h>
# endif

# if WIDE_CHAR_VERSION
			table = (const int32_t *)
			  _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEWC);
			weights = (const int32_t *)
			  _NL_CURRENT (LC_COLLATE, _NL_COLLATE_WEIGHTWC);
			extra = (const int32_t *)
			  _NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAWC);
			indirect = (const int32_t *)
			  _NL_CURRENT (LC_COLLATE, _NL_COLLATE_INDIRECTWC);
# else
			table = (const int32_t *)
			  _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB);
			weights = (const unsigned char *)
			  _NL_CURRENT (LC_COLLATE, _NL_COLLATE_WEIGHTMB);
			extra = (const unsigned char *)
			  _NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAMB);
			indirect = (const int32_t *)
			  _NL_CURRENT (LC_COLLATE, _NL_COLLATE_INDIRECTMB);
# endif

			idx = findidx (&cp);
			if (idx != 0)
			  {
			    /* We found a table entry.  Now see whether the
			       character we are currently at has the same
			       equivalance class value.  */
# if !WIDE_CHAR_VERSION
			    int len = weights[idx];
# endif
			    int32_t idx2;
			    const UCHAR *np = (const UCHAR *) n;

			    idx2 = findidx (&np);
# if !WIDE_CHAR_VERSION
			    if (idx2 != 0 && len == weights[idx2])
			      {
				int cnt = 0;

				while (cnt < len
				       && (weights[idx + 1 + cnt]
					   == weights[idx2 + 1 + cnt]))
				  ++cnt;

				if (cnt == len)
				  goto matched;
			      }
# else
			    if (idx2 != 0 && weights[idx] == weights[idx2])
			      goto matched;
# endif
			  }
		      }

		    c = *p++;
		  }
#endif
		else if (c == L('\0'))
		  /* [ (unterminated) loses.  */
		  return FNM_NOMATCH;
		else
		  {
		    c = FOLD (c);
		  normal_bracket:
		    if (c == fn)
		      goto matched;

		    cold = c;
		    c = *p++;

		    if (c == L('-') && *p != L(']'))
		      {
#if _LIBC
			/* We have to find the collation sequence
			   value for C.  Collation sequence is nothing
			   we can regularly access.  The sequence
			   value is defined by the order in which the
			   definitions of the collation values for the
			   various characters appear in the source
			   file.  A strange concept, nowhere
			   documented.  */
			int32_t fseqidx;
			int32_t lseqidx;
			UCHAR cend = *p++;
# ifdef WIDE_CHAR_VERSION
			size_t cnt;
# endif

			if (!(flags & FNM_NOESCAPE) && cend == L('\\'))
			  cend = *p++;
			if (cend == L('\0'))
			  return FNM_NOMATCH;

# ifdef WIDE_CHAR_VERSION
			/* Search in the `names' array for the characters.  */
			fseqidx = fn % size;
			cnt = 0;
			while (names[fseqidx] != fn)
			  {
			    if (++cnt == layers)
			      /* XXX We don't know anything about
				 the character we are supposed to
				 match.  This means we are failing.  */
			      goto range_not_matched;

			    fseqidx += size;
			  }
			lseqidx = cold % size;
			cnt = 0;
			while (names[lseqidx] != cold)
			  {
			    if (++cnt == layers)
			      {
				lseqidx = -1;
				break;
			      }
			    lseqidx += size;
			  }
# else
			fseqidx = fn;
			lseqidx = cold;
# endif

			/* XXX It is not entirely clear to me how to handle
			   characters which are not mentioned in the
			   collation specification.  */
			if (
# ifdef WIDE_CHAR_VERSION
			    lseqidx == -1 ||
# endif
			    collseq[lseqidx] <= collseq[fseqidx])
			  {
			    /* We have to look at the upper bound.  */
			    int32_t hseqidx;

			    cend = FOLD (cend);
# ifdef WIDE_CHAR_VERSION
			    hseqidx = cend % size;
			    cnt = 0;
			    while (names[hseqidx] != cend)
			      {
				if (++cnt == layers)
				  {
				    /* Hum, no information about the upper
				       bound.  The matching succeeds if the
				       lower bound is matched exactly.  */
				    if (lseqidx == -1 || cold != fn)
				      goto range_not_matched;

				    goto matched;
				  }
			      }
# else
			    hseqidx = cend;
# endif

			    if (
# ifdef WIDE_CHAR_VERSION
				(lseqidx == -1
				 && collseq[fseqidx] == collseq[hseqidx]) ||
# endif
				collseq[fseqidx] <= collseq[hseqidx])
			      goto matched;
			  }
# ifdef WIDE_CHAR_VERSION
		      range_not_matched:
# endif
#else
			/* We use a boring value comparison of the character
			   values.  This is better than comparing using
			   `strcoll' since the latter would have surprising
			   and sometimes fatal consequences.  */
			UCHAR cend = *p++;

			if (!(flags & FNM_NOESCAPE) && cend == L('\\'))
			  cend = *p++;
			if (cend == L('\0'))
			  return FNM_NOMATCH;

			/* It is a range.  */
			if (cold <= fc && fc <= c)
			  goto matched;
#endif

			c = *p++;
		      }
		  }

		if (c == L(']'))
		  break;
	      }

	    if (!not)
	      return FNM_NOMATCH;
	    break;

	  matched:
	    /* Skip the rest of the [...] that already matched.  */
	    do
	      {
		c = *p++;

		if (c == L('\0'))
		  /* [... (unterminated) loses.  */
		  return FNM_NOMATCH;

		if (!(flags & FNM_NOESCAPE) && c == L('\\'))
		  {
		    if (*p == L('\0'))
		      return FNM_NOMATCH;
		    /* XXX 1003.2d11 is unclear if this is right.  */
		    ++p;
		  }
		else if (c == L('[') && *p == L(':'))
		  {
		    do
		      if (*++p == L('\0'))
			return FNM_NOMATCH;
		    while (*p != L(':') || p[1] == L(']'));
		    p += 2;
		    c = *p;
		  }
	      }
	    while (c != L(']'));
	    if (not)
	      return FNM_NOMATCH;
	  }
	  break;

	default:
	  if (c != FOLD ((UCHAR) *n))
	    return FNM_NOMATCH;
	}

      ++n;
    }

  if (*n == '\0')
    return 0;

  if ((flags & FNM_LEADING_DIR) && *n == L('/'))
    /* The FNM_LEADING_DIR flag says that "foo*" matches "foobar/frobozz".  */
    return 0;

  return FNM_NOMATCH;
}

#undef FOLD
#undef CHAR
#undef UCHAR
#undef FCT
#undef STRCHR
#undef STRCHRNUL
#undef STRCOLL
#undef L
#undef BTOWC
#undef SUFFIX