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
|
/*
* Copyright (c) 1989, 1993, 1994
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Guido van Rossum.
*
* Copyright (c) 2011 The FreeBSD Foundation
* All rights reserved.
* Portions of this software were developed by David Chisnall
* under sponsorship from the FreeBSD Foundation.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 4. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#if defined(LIBC_SCCS) && !defined(lint)
static char sccsid[] = "@(#)fnmatch.c 8.2 (Berkeley) 4/16/94";
#endif /* LIBC_SCCS and not lint */
#include "winsup.h"
#include <sys/cdefs.h>
__FBSDID("$FreeBSD: head/lib/libc/gen/fnmatch.c 288309 2015-09-27 12:52:18Z jilles $");
/*
* Function fnmatch() as specified in POSIX 1003.2-1992, section B.6.
* Compares a filename or pathname to a pattern.
*/
/*
* Some notes on multibyte character support:
* 1. Patterns with illegal byte sequences match nothing.
* 2. Illegal byte sequences in the "string" argument are handled by treating
* them as single-byte characters with a value of the first byte of the
* sequence cast to wchar_t.
* 3. Multibyte conversion state objects (mbstate_t) are passed around and
* used for most, but not all, conversions. Further work will be required
* to support state-dependent encodings.
*/
#include <fnmatch.h>
#include <limits.h>
#include <string.h>
#include <wchar.h>
#include <wctype.h>
#ifdef __CYGWIN__
#include "../collate.h"
#else
#include "collate.h"
#endif
#define EOS '\0'
#define RANGE_MATCH 1
#define RANGE_NOMATCH 0
#define RANGE_ERROR (-1)
static int rangematch(const char *, wchar_t, int, char **, mbstate_t *);
static int fnmatch1(const char *, const char *, const char *, int, mbstate_t,
mbstate_t);
int
fnmatch(const char *pattern, const char *string, int flags)
{
static const mbstate_t initial;
return (fnmatch1(pattern, string, string, flags, initial, initial));
}
static int
fnmatch1(const char *pattern, const char *string, const char *stringstart,
int flags, mbstate_t patmbs, mbstate_t strmbs)
{
const char *bt_pattern, *bt_string;
mbstate_t bt_patmbs, bt_strmbs;
char *newp;
char c;
wchar_t pc, sc;
size_t pclen, sclen;
bt_pattern = bt_string = NULL;
for (;;) {
pclen = mbrtowc(&pc, pattern, MB_LEN_MAX, &patmbs);
if (pclen == (size_t)-1 || pclen == (size_t)-2)
return (FNM_NOMATCH);
pattern += pclen;
sclen = mbrtowc(&sc, string, MB_LEN_MAX, &strmbs);
if (sclen == (size_t)-1 || sclen == (size_t)-2) {
sc = (unsigned char)*string;
sclen = 1;
memset(&strmbs, 0, sizeof(strmbs));
}
switch (pc) {
case EOS:
if ((flags & FNM_LEADING_DIR) && sc == '/')
return (0);
if (sc == EOS)
return (0);
goto backtrack;
case '?':
if (sc == EOS)
return (FNM_NOMATCH);
if (sc == '/' && (flags & FNM_PATHNAME))
goto backtrack;
if (sc == '.' && (flags & FNM_PERIOD) &&
(string == stringstart ||
((flags & FNM_PATHNAME) && *(string - 1) == '/')))
goto backtrack;
string += sclen;
break;
case '*':
c = *pattern;
/* Collapse multiple stars. */
while (c == '*')
c = *++pattern;
if (sc == '.' && (flags & FNM_PERIOD) &&
(string == stringstart ||
((flags & FNM_PATHNAME) && *(string - 1) == '/')))
goto backtrack;
/* Optimize for pattern with * at end or before /. */
if (c == EOS)
if (flags & FNM_PATHNAME)
return ((flags & FNM_LEADING_DIR) ||
strchr(string, '/') == NULL ?
0 : FNM_NOMATCH);
else
return (0);
else if (c == '/' && flags & FNM_PATHNAME) {
if ((string = strchr(string, '/')) == NULL)
return (FNM_NOMATCH);
break;
}
/*
* First try the shortest match for the '*' that
* could work. We can forget any earlier '*' since
* there is no way having it match more characters
* can help us, given that we are already here.
*/
bt_pattern = pattern, bt_patmbs = patmbs;
bt_string = string, bt_strmbs = strmbs;
break;
case '[':
if (sc == EOS)
return (FNM_NOMATCH);
if (sc == '/' && (flags & FNM_PATHNAME))
goto backtrack;
if (sc == '.' && (flags & FNM_PERIOD) &&
(string == stringstart ||
((flags & FNM_PATHNAME) && *(string - 1) == '/')))
goto backtrack;
switch (rangematch(pattern, sc, flags, &newp,
&patmbs)) {
case RANGE_ERROR:
goto norm;
case RANGE_MATCH:
pattern = newp;
break;
case RANGE_NOMATCH:
goto backtrack;
}
string += sclen;
break;
case '\\':
if (!(flags & FNM_NOESCAPE)) {
pclen = mbrtowc(&pc, pattern, MB_LEN_MAX,
&patmbs);
if (pclen == (size_t)-1 || pclen == (size_t)-2)
return (FNM_NOMATCH);
pattern += pclen;
}
/* FALLTHROUGH */
default:
norm:
string += sclen;
if (pc == sc)
;
else if ((flags & FNM_CASEFOLD) &&
(towlower(pc) == towlower(sc)))
;
else {
backtrack:
/*
* If we have a mismatch (other than hitting
* the end of the string), go back to the last
* '*' seen and have it match one additional
* character.
*/
if (bt_pattern == NULL)
return (FNM_NOMATCH);
sclen = mbrtowc(&sc, bt_string, MB_LEN_MAX,
&bt_strmbs);
if (sclen == (size_t)-1 ||
sclen == (size_t)-2) {
sc = (unsigned char)*bt_string;
sclen = 1;
memset(&bt_strmbs, 0,
sizeof(bt_strmbs));
}
if (sc == EOS)
return (FNM_NOMATCH);
if (sc == '/' && flags & FNM_PATHNAME)
return (FNM_NOMATCH);
bt_string += sclen;
pattern = bt_pattern, patmbs = bt_patmbs;
string = bt_string, strmbs = bt_strmbs;
}
break;
}
}
/* NOTREACHED */
}
static int
rangematch(const char *pattern, wchar_t test, int flags, char **newp,
mbstate_t *patmbs)
{
int negate, ok;
wchar_t c, c2;
size_t pclen;
const char *origpat;
#ifndef __CYGWIN__
struct xlocale_collate *table =
(struct xlocale_collate*)__get_locale()->components[XLC_COLLATE];
#endif
/*
* A bracket expression starting with an unquoted circumflex
* character produces unspecified results (IEEE 1003.2-1992,
* 3.13.2). This implementation treats it like '!', for
* consistency with the regular expression syntax.
* J.T. Conklin (conklin@ngai.kaleida.com)
*/
if ( (negate = (*pattern == '!' || *pattern == '^')) )
++pattern;
if (flags & FNM_CASEFOLD)
test = towlower(test);
/*
* A right bracket shall lose its special meaning and represent
* itself in a bracket expression if it occurs first in the list.
* -- POSIX.2 2.8.3.2
*/
ok = 0;
origpat = pattern;
for (;;) {
if (*pattern == ']' && pattern > origpat) {
pattern++;
break;
} else if (*pattern == '\0') {
return (RANGE_ERROR);
} else if (*pattern == '/' && (flags & FNM_PATHNAME)) {
return (RANGE_NOMATCH);
} else if (*pattern == '\\' && !(flags & FNM_NOESCAPE))
pattern++;
pclen = mbrtowc(&c, pattern, MB_LEN_MAX, patmbs);
if (pclen == (size_t)-1 || pclen == (size_t)-2)
return (RANGE_NOMATCH);
pattern += pclen;
if (flags & FNM_CASEFOLD)
c = towlower(c);
if (*pattern == '-' && *(pattern + 1) != EOS &&
*(pattern + 1) != ']') {
if (*++pattern == '\\' && !(flags & FNM_NOESCAPE))
if (*pattern != EOS)
pattern++;
pclen = mbrtowc(&c2, pattern, MB_LEN_MAX, patmbs);
if (pclen == (size_t)-1 || pclen == (size_t)-2)
return (RANGE_NOMATCH);
pattern += pclen;
if (c2 == EOS)
return (RANGE_ERROR);
if (flags & FNM_CASEFOLD)
c2 = towlower(c2);
#ifdef __CYGWIN__
if (__collate_load_error ?
c <= test && test <= c2 :
__collate_range_cmp(c, test) <= 0
&& __collate_range_cmp(test, c2) <= 0
)
#else
if (table->__collate_load_error ?
c <= test && test <= c2 :
__collate_range_cmp(table, c, test) <= 0
&& __collate_range_cmp(table, test, c2) <= 0
)
#endif
ok = 1;
} else if (c == test)
ok = 1;
}
*newp = (char *)pattern;
return (ok == negate ? RANGE_NOMATCH : RANGE_MATCH);
}
|