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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277
|
/* Copyright (C) 1991-2014 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/>. */
#include <stdint.h>
struct STRUCT
{
const CHAR *pattern;
const CHAR *string;
int no_leading_period;
};
/* Match STRING against the filename pattern PATTERN, returning zero if
it matches, nonzero if not. */
static int FCT (const CHAR *pattern, const CHAR *string,
const CHAR *string_end, int no_leading_period, int flags,
struct STRUCT *ends, size_t alloca_used)
internal_function;
static int EXT (INT opt, const CHAR *pattern, const CHAR *string,
const CHAR *string_end, int no_leading_period, int flags,
size_t alloca_used)
internal_function;
static const CHAR *END (const CHAR *patternp) internal_function;
static int
internal_function
FCT (pattern, string, string_end, no_leading_period, flags, ends, alloca_used)
const CHAR *pattern;
const CHAR *string;
const CHAR *string_end;
int no_leading_period;
int flags;
struct STRUCT *ends;
size_t alloca_used;
{
const CHAR *p = pattern, *n = string;
UCHAR c;
#ifdef _LIBC
# if WIDE_CHAR_VERSION
const char *collseq = (const char *)
_NL_CURRENT(LC_COLLATE, _NL_COLLATE_COLLSEQWC);
# else
const UCHAR *collseq = (const UCHAR *)
_NL_CURRENT(LC_COLLATE, _NL_COLLATE_COLLSEQMB);
# endif
#endif
while ((c = *p++) != L('\0'))
{
int new_no_leading_period = 0;
c = FOLD (c);
switch (c)
{
case L('?'):
if (__builtin_expect (flags & FNM_EXTMATCH, 0) && *p == '(')
{
int res = EXT (c, p, n, string_end, no_leading_period,
flags, alloca_used);
if (res != -1)
return res;
}
if (n == string_end)
return FNM_NOMATCH;
else if (*n == L('/') && (flags & FNM_FILE_NAME))
return FNM_NOMATCH;
else if (*n == L('.') && no_leading_period)
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 (n == string_end || FOLD ((UCHAR) *n) != c)
return FNM_NOMATCH;
break;
case L('*'):
if (__builtin_expect (flags & FNM_EXTMATCH, 0) && *p == '(')
{
int res = EXT (c, p, n, string_end, no_leading_period,
flags, alloca_used);
if (res != -1)
return res;
}
else if (ends != NULL)
{
ends->pattern = p - 1;
ends->string = n;
ends->no_leading_period = no_leading_period;
return 0;
}
if (n != string_end && *n == L('.') && no_leading_period)
return FNM_NOMATCH;
for (c = *p++; c == L('?') || c == L('*'); c = *p++)
{
if (*p == L('(') && (flags & FNM_EXTMATCH) != 0)
{
const CHAR *endp = END (p);
if (endp != p)
{
/* This is a pattern. Skip over it. */
p = endp;
continue;
}
}
if (c == L('?'))
{
/* A ? needs to match one character. */
if (n == string_end)
/* There isn't another character; no match. */
return FNM_NOMATCH;
else if (*n == L('/')
&& __builtin_expect (flags & FNM_FILE_NAME, 0))
/* A slash does not match a wildcard under
FNM_FILE_NAME. */
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 means it cannot match, unless the FNM_LEADING_DIR
flag is set. */
{
int result = (flags & FNM_FILE_NAME) == 0 ? 0 : FNM_NOMATCH;
if (flags & FNM_FILE_NAME)
{
if (flags & FNM_LEADING_DIR)
result = 0;
else
{
if (MEMCHR (n, L('/'), string_end - n) == NULL)
result = 0;
}
}
return result;
}
else
{
const CHAR *endp;
struct STRUCT end;
end.pattern = NULL;
endp = MEMCHR (n, (flags & FNM_FILE_NAME) ? L('/') : L('\0'),
string_end - n);
if (endp == NULL)
endp = string_end;
if (c == L('[')
|| (__builtin_expect (flags & FNM_EXTMATCH, 0) != 0
&& (c == L('@') || c == L('+') || c == L('!'))
&& *p == L('(')))
{
int flags2 = ((flags & FNM_FILE_NAME)
? flags : (flags & ~FNM_PERIOD));
for (--p; n < endp; ++n, no_leading_period = 0)
if (FCT (p, n, string_end, no_leading_period, flags2,
&end, alloca_used) == 0)
goto found;
}
else if (c == L('/') && (flags & FNM_FILE_NAME))
{
while (n < string_end && *n != L('/'))
++n;
if (n < string_end && *n == L('/')
&& (FCT (p, n + 1, string_end, flags & FNM_PERIOD, flags,
NULL, alloca_used) == 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, no_leading_period = 0)
if (FOLD ((UCHAR) *n) == c
&& (FCT (p, n, string_end, no_leading_period, flags2,
&end, alloca_used) == 0))
{
found:
if (end.pattern == NULL)
return 0;
break;
}
if (end.pattern != NULL)
{
p = end.pattern;
n = end.string;
no_leading_period = end.no_leading_period;
continue;
}
}
}
/* If we come here no match is possible with the wildcard. */
return FNM_NOMATCH;
case L('['):
{
/* Nonzero if the sense of the character class is inverted. */
const CHAR *p_init = p;
const CHAR *n_init = n;
int not;
CHAR cold;
UCHAR fn;
if (posixly_correct == 0)
posixly_correct = getenv ("POSIXLY_CORRECT") != NULL ? 1 : -1;
if (n == string_end)
return FNM_NOMATCH;
if (*n == L('.') && no_leading_period)
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;
fn = FOLD ((UCHAR) *n);
c = *p++;
for (;;)
{
if (!(flags & FNM_NOESCAPE) && c == L('\\'))
{
if (*p == L('\0'))
return FNM_NOMATCH;
c = FOLD ((UCHAR) *p);
++p;
goto normal_bracket;
}
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;
# if defined _LIBC && ! WIDE_CHAR_VERSION
/* The following code is glibc specific but does
there a good job in speeding up the code since
we can avoid the btowc() call. */
if (_ISCTYPE ((UCHAR) *n, wt))
goto matched;
# else
if (ISWCTYPE (BTOWC ((UCHAR) *n), wt))
goto matched;
# endif
#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, 1);
if (idx != 0)
{
/* We found a table entry. Now see whether the
character we are currently at has the same
equivalance class value. */
int len = weights[idx & 0xffffff];
int32_t idx2;
const UCHAR *np = (const UCHAR *) n;
idx2 = findidx (&np, string_end - n);
if (idx2 != 0
&& (idx >> 24) == (idx2 >> 24)
&& len == weights[idx2 & 0xffffff])
{
int cnt = 0;
idx &= 0xffffff;
idx2 &= 0xffffff;
while (cnt < len
&& (weights[idx + 1 + cnt]
== weights[idx2 + 1 + cnt]))
++cnt;
if (cnt == len)
goto matched;
}
}
}
c = *p++;
}
#endif
else if (c == L('\0'))
{
/* [ unterminated, treat as normal character. */
p = p_init;
n = n_init;
c = L('[');
goto normal_match;
}
else
{
int is_range = 0;
#ifdef _LIBC
int is_seqval = 0;
if (c == L('[') && *p == L('.'))
{
uint32_t nrules =
_NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES);
const CHAR *startp = p;
size_t c1 = 0;
while (1)
{
c = *++p;
if (c == L('.') && p[1] == L(']'))
{
p += 2;
break;
}
if (c == '\0')
return FNM_NOMATCH;
++c1;
}
/* We have to handling the symbols differently in
ranges since then the collation sequence is
important. */
is_range = *p == L('-') && p[1] != L('\0');
if (nrules == 0)
{
/* There are no names defined in the collation
data. Therefore we only accept the trivial
names consisting of the character itself. */
if (c1 != 1)
return FNM_NOMATCH;
if (!is_range && *n == startp[1])
goto matched;
cold = startp[1];
c = *p++;
}
else
{
int32_t table_size;
const int32_t *symb_table;
# ifdef WIDE_CHAR_VERSION
char str[c1];
unsigned int strcnt;
# else
# define str (startp + 1)
# endif
const unsigned char *extra;
int32_t idx;
int32_t elem;
int32_t second;
int32_t hash;
# ifdef WIDE_CHAR_VERSION
/* We have to convert the name to a single-byte
string. This is possible since the names
consist of ASCII characters and the internal
representation is UCS4. */
for (strcnt = 0; strcnt < c1; ++strcnt)
str[strcnt] = startp[1 + strcnt];
#endif
table_size =
_NL_CURRENT_WORD (LC_COLLATE,
_NL_COLLATE_SYMB_HASH_SIZEMB);
symb_table = (const int32_t *)
_NL_CURRENT (LC_COLLATE,
_NL_COLLATE_SYMB_TABLEMB);
extra = (const unsigned char *)
_NL_CURRENT (LC_COLLATE,
_NL_COLLATE_SYMB_EXTRAMB);
/* Locate the character in the hashing table. */
hash = elem_hash (str, c1);
idx = 0;
elem = hash % table_size;
if (symb_table[2 * elem] != 0)
{
second = hash % (table_size - 2) + 1;
do
{
/* First compare the hashing value. */
if (symb_table[2 * elem] == hash
&& (c1
== extra[symb_table[2 * elem + 1]])
&& memcmp (str,
&extra[symb_table[2 * elem
+ 1]
+ 1], c1) == 0)
{
/* Yep, this is the entry. */
idx = symb_table[2 * elem + 1];
idx += 1 + extra[idx];
break;
}
/* Next entry. */
elem += second;
}
while (symb_table[2 * elem] != 0);
}
if (symb_table[2 * elem] != 0)
{
/* Compare the byte sequence but only if
this is not part of a range. */
# ifdef WIDE_CHAR_VERSION
int32_t *wextra;
idx += 1 + extra[idx];
/* Adjust for the alignment. */
idx = (idx + 3) & ~3;
wextra = (int32_t *) &extra[idx + 4];
# endif
if (! is_range)
{
# ifdef WIDE_CHAR_VERSION
for (c1 = 0;
(int32_t) c1 < wextra[idx];
++c1)
if (n[c1] != wextra[1 + c1])
break;
if ((int32_t) c1 == wextra[idx])
goto matched;
# else
for (c1 = 0; c1 < extra[idx]; ++c1)
if (n[c1] != extra[1 + c1])
break;
if (c1 == extra[idx])
goto matched;
# endif
}
/* Get the collation sequence value. */
is_seqval = 1;
# ifdef WIDE_CHAR_VERSION
cold = wextra[1 + wextra[idx]];
# else
/* Adjust for the alignment. */
idx += 1 + extra[idx];
idx = (idx + 3) & ~4;
cold = *((int32_t *) &extra[idx]);
# endif
c = *p++;
}
else if (c1 == 1)
{
/* No valid character. Match it as a
single byte. */
if (!is_range && *n == str[0])
goto matched;
cold = str[0];
c = *p++;
}
else
return FNM_NOMATCH;
}
}
else
# undef str
#endif
{
c = FOLD (c);
normal_bracket:
/* We have to handling the symbols differently in
ranges since then the collation sequence is
important. */
is_range = (*p == L('-') && p[1] != L('\0')
&& p[1] != L(']'));
if (!is_range && c == fn)
goto matched;
/* This is needed if we goto normal_bracket; from
outside of is_seqval's scope. */
is_seqval = 0;
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. */
uint32_t fcollseq;
uint32_t lcollseq;
UCHAR cend = *p++;
# ifdef WIDE_CHAR_VERSION
/* Search in the `names' array for the characters. */
fcollseq = __collseq_table_lookup (collseq, fn);
if (fcollseq == ~((uint32_t) 0))
/* XXX We don't know anything about the character
we are supposed to match. This means we are
failing. */
goto range_not_matched;
if (is_seqval)
lcollseq = cold;
else
lcollseq = __collseq_table_lookup (collseq, cold);
# else
fcollseq = collseq[fn];
lcollseq = is_seqval ? cold : collseq[(UCHAR) cold];
# endif
is_seqval = 0;
if (cend == L('[') && *p == L('.'))
{
uint32_t nrules =
_NL_CURRENT_WORD (LC_COLLATE,
_NL_COLLATE_NRULES);
const CHAR *startp = p;
size_t c1 = 0;
while (1)
{
c = *++p;
if (c == L('.') && p[1] == L(']'))
{
p += 2;
break;
}
if (c == '\0')
return FNM_NOMATCH;
++c1;
}
if (nrules == 0)
{
/* There are no names defined in the
collation data. Therefore we only
accept the trivial names consisting
of the character itself. */
if (c1 != 1)
return FNM_NOMATCH;
cend = startp[1];
}
else
{
int32_t table_size;
const int32_t *symb_table;
# ifdef WIDE_CHAR_VERSION
char str[c1];
unsigned int strcnt;
# else
# define str (startp + 1)
# endif
const unsigned char *extra;
int32_t idx;
int32_t elem;
int32_t second;
int32_t hash;
# ifdef WIDE_CHAR_VERSION
/* We have to convert the name to a single-byte
string. This is possible since the names
consist of ASCII characters and the internal
representation is UCS4. */
for (strcnt = 0; strcnt < c1; ++strcnt)
str[strcnt] = startp[1 + strcnt];
# endif
table_size =
_NL_CURRENT_WORD (LC_COLLATE,
_NL_COLLATE_SYMB_HASH_SIZEMB);
symb_table = (const int32_t *)
_NL_CURRENT (LC_COLLATE,
_NL_COLLATE_SYMB_TABLEMB);
extra = (const unsigned char *)
_NL_CURRENT (LC_COLLATE,
_NL_COLLATE_SYMB_EXTRAMB);
/* Locate the character in the hashing
table. */
hash = elem_hash (str, c1);
idx = 0;
elem = hash % table_size;
if (symb_table[2 * elem] != 0)
{
second = hash % (table_size - 2) + 1;
do
{
/* First compare the hashing value. */
if (symb_table[2 * elem] == hash
&& (c1
== extra[symb_table[2 * elem + 1]])
&& memcmp (str,
&extra[symb_table[2 * elem + 1]
+ 1], c1) == 0)
{
/* Yep, this is the entry. */
idx = symb_table[2 * elem + 1];
idx += 1 + extra[idx];
break;
}
/* Next entry. */
elem += second;
}
while (symb_table[2 * elem] != 0);
}
if (symb_table[2 * elem] != 0)
{
/* Compare the byte sequence but only if
this is not part of a range. */
# ifdef WIDE_CHAR_VERSION
int32_t *wextra;
idx += 1 + extra[idx];
/* Adjust for the alignment. */
idx = (idx + 3) & ~4;
wextra = (int32_t *) &extra[idx + 4];
# endif
/* Get the collation sequence value. */
is_seqval = 1;
# ifdef WIDE_CHAR_VERSION
cend = wextra[1 + wextra[idx]];
# else
/* Adjust for the alignment. */
idx += 1 + extra[idx];
idx = (idx + 3) & ~4;
cend = *((int32_t *) &extra[idx]);
# endif
}
else if (symb_table[2 * elem] != 0 && c1 == 1)
{
cend = str[0];
c = *p++;
}
else
return FNM_NOMATCH;
}
# undef str
}
else
{
if (!(flags & FNM_NOESCAPE) && cend == L('\\'))
cend = *p++;
if (cend == L('\0'))
return FNM_NOMATCH;
cend = FOLD (cend);
}
/* 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
lcollseq == 0xffffffff ||
# endif
lcollseq <= fcollseq)
{
/* We have to look at the upper bound. */
uint32_t hcollseq;
if (is_seqval)
hcollseq = cend;
else
{
# ifdef WIDE_CHAR_VERSION
hcollseq =
__collseq_table_lookup (collseq, cend);
if (hcollseq == ~((uint32_t) 0))
{
/* Hum, no information about the upper
bound. The matching succeeds if the
lower bound is matched exactly. */
if (lcollseq != fcollseq)
goto range_not_matched;
goto matched;
}
# else
hcollseq = collseq[cend];
# endif
}
if (lcollseq <= hcollseq && fcollseq <= hcollseq)
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 <= fn && fn <= cend)
goto matched;
#endif
c = *p++;
}
}
if (c == L(']'))
break;
}
if (!not)
return FNM_NOMATCH;
break;
matched:
/* Skip the rest of the [...] that already matched. */
while ((c = *p++) != L (']'))
{
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(':'))
{
int c1 = 0;
const CHAR *startp = p;
while (1)
{
c = *++p;
if (++c1 == CHAR_CLASS_MAX_LENGTH)
return FNM_NOMATCH;
if (*p == L(':') && p[1] == L(']'))
break;
if (c < L('a') || c >= L('z'))
{
p = startp - 2;
break;
}
}
p += 2;
}
else if (c == L('[') && *p == L('='))
{
c = *++p;
if (c == L('\0'))
return FNM_NOMATCH;
c = *++p;
if (c != L('=') || p[1] != L(']'))
return FNM_NOMATCH;
p += 2;
}
else if (c == L('[') && *p == L('.'))
{
while (1)
{
c = *++p;
if (c == L('\0'))
return FNM_NOMATCH;
if (c == L('.') && p[1] == L(']'))
break;
}
p += 2;
}
}
if (not)
return FNM_NOMATCH;
}
break;
case L('+'):
case L('@'):
case L('!'):
if (__builtin_expect (flags & FNM_EXTMATCH, 0) && *p == '(')
{
int res = EXT (c, p, n, string_end, no_leading_period, flags,
alloca_used);
if (res != -1)
return res;
}
goto normal_match;
case L('/'):
if (NO_LEADING_PERIOD (flags))
{
if (n == string_end || c != (UCHAR) *n)
return FNM_NOMATCH;
new_no_leading_period = 1;
break;
}
/* FALLTHROUGH */
default:
normal_match:
if (n == string_end || c != FOLD ((UCHAR) *n))
return FNM_NOMATCH;
}
no_leading_period = new_no_leading_period;
++n;
}
if (n == string_end)
return 0;
if ((flags & FNM_LEADING_DIR) && n != string_end && *n == L('/'))
/* The FNM_LEADING_DIR flag says that "foo*" matches "foobar/frobozz". */
return 0;
return FNM_NOMATCH;
}
static const CHAR *
internal_function
END (const CHAR *pattern)
{
const CHAR *p = pattern;
while (1)
if (*++p == L('\0'))
/* This is an invalid pattern. */
return pattern;
else if (*p == L('['))
{
/* Handle brackets special. */
if (posixly_correct == 0)
posixly_correct = getenv ("POSIXLY_CORRECT") != NULL ? 1 : -1;
/* Skip the not sign. We have to recognize it because of a possibly
following ']'. */
if (*++p == L('!') || (posixly_correct < 0 && *p == L('^')))
++p;
/* A leading ']' is recognized as such. */
if (*p == L(']'))
++p;
/* Skip over all characters of the list. */
while (*p != L(']'))
if (*p++ == L('\0'))
/* This is no valid pattern. */
return pattern;
}
else if ((*p == L('?') || *p == L('*') || *p == L('+') || *p == L('@')
|| *p == L('!')) && p[1] == L('('))
p = END (p + 1);
else if (*p == L(')'))
break;
return p + 1;
}
static int
internal_function
EXT (INT opt, const CHAR *pattern, const CHAR *string, const CHAR *string_end,
int no_leading_period, int flags, size_t alloca_used)
{
const CHAR *startp;
int level;
struct patternlist
{
struct patternlist *next;
CHAR malloced;
CHAR str[0];
} *list = NULL;
struct patternlist **lastp = &list;
size_t pattern_len = STRLEN (pattern);
int any_malloced = 0;
const CHAR *p;
const CHAR *rs;
int retval = 0;
/* Parse the pattern. Store the individual parts in the list. */
level = 0;
for (startp = p = pattern + 1; level >= 0; ++p)
if (*p == L('\0'))
{
/* This is an invalid pattern. */
retval = -1;
goto out;
}
else if (*p == L('['))
{
/* Handle brackets special. */
if (posixly_correct == 0)
posixly_correct = getenv ("POSIXLY_CORRECT") != NULL ? 1 : -1;
/* Skip the not sign. We have to recognize it because of a possibly
following ']'. */
if (*++p == L('!') || (posixly_correct < 0 && *p == L('^')))
++p;
/* A leading ']' is recognized as such. */
if (*p == L(']'))
++p;
/* Skip over all characters of the list. */
while (*p != L(']'))
if (*p++ == L('\0'))
{
/* This is no valid pattern. */
retval = -1;
goto out;
}
}
else if ((*p == L('?') || *p == L('*') || *p == L('+') || *p == L('@')
|| *p == L('!')) && p[1] == L('('))
/* Remember the nesting level. */
++level;
else if (*p == L(')'))
{
if (level-- == 0)
{
/* This means we found the end of the pattern. */
#define NEW_PATTERN \
struct patternlist *newp; \
size_t slen = (opt == L('?') || opt == L('@') \
? pattern_len : (p - startp + 1)); \
slen = sizeof (struct patternlist) + (slen * sizeof (CHAR)); \
int malloced = ! __libc_use_alloca (alloca_used + slen); \
if (__builtin_expect (malloced, 0)) \
{ \
newp = malloc (slen); \
if (newp == NULL) \
{ \
retval = -2; \
goto out; \
} \
any_malloced = 1; \
} \
else \
newp = alloca_account (slen, alloca_used); \
newp->next = NULL; \
newp->malloced = malloced; \
*((CHAR *) MEMPCPY (newp->str, startp, p - startp)) = L('\0'); \
*lastp = newp; \
lastp = &newp->next
NEW_PATTERN;
}
}
else if (*p == L('|'))
{
if (level == 0)
{
NEW_PATTERN;
startp = p + 1;
}
}
assert (list != NULL);
assert (p[-1] == L(')'));
#undef NEW_PATTERN
switch (opt)
{
case L('*'):
if (FCT (p, string, string_end, no_leading_period, flags, NULL,
alloca_used) == 0)
goto success;
/* FALLTHROUGH */
case L('+'):
do
{
for (rs = string; rs <= string_end; ++rs)
/* First match the prefix with the current pattern with the
current pattern. */
if (FCT (list->str, string, rs, no_leading_period,
flags & FNM_FILE_NAME ? flags : flags & ~FNM_PERIOD,
NULL, alloca_used) == 0
/* This was successful. Now match the rest with the rest
of the pattern. */
&& (FCT (p, rs, string_end,
rs == string
? no_leading_period
: rs[-1] == '/' && NO_LEADING_PERIOD (flags) ? 1 : 0,
flags & FNM_FILE_NAME
? flags : flags & ~FNM_PERIOD, NULL, alloca_used) == 0
/* This didn't work. Try the whole pattern. */
|| (rs != string
&& FCT (pattern - 1, rs, string_end,
rs == string
? no_leading_period
: (rs[-1] == '/' && NO_LEADING_PERIOD (flags)
? 1 : 0),
flags & FNM_FILE_NAME
? flags : flags & ~FNM_PERIOD, NULL,
alloca_used) == 0)))
/* It worked. Signal success. */
goto success;
}
while ((list = list->next) != NULL);
/* None of the patterns lead to a match. */
retval = FNM_NOMATCH;
break;
case L('?'):
if (FCT (p, string, string_end, no_leading_period, flags, NULL,
alloca_used) == 0)
goto success;
/* FALLTHROUGH */
case L('@'):
do
/* I cannot believe it but `strcat' is actually acceptable
here. Match the entire string with the prefix from the
pattern list and the rest of the pattern following the
pattern list. */
if (FCT (STRCAT (list->str, p), string, string_end,
no_leading_period,
flags & FNM_FILE_NAME ? flags : flags & ~FNM_PERIOD,
NULL, alloca_used) == 0)
/* It worked. Signal success. */
goto success;
while ((list = list->next) != NULL);
/* None of the patterns lead to a match. */
retval = FNM_NOMATCH;
break;
case L('!'):
for (rs = string; rs <= string_end; ++rs)
{
struct patternlist *runp;
for (runp = list; runp != NULL; runp = runp->next)
if (FCT (runp->str, string, rs, no_leading_period,
flags & FNM_FILE_NAME ? flags : flags & ~FNM_PERIOD,
NULL, alloca_used) == 0)
break;
/* If none of the patterns matched see whether the rest does. */
if (runp == NULL
&& (FCT (p, rs, string_end,
rs == string
? no_leading_period
: rs[-1] == '/' && NO_LEADING_PERIOD (flags) ? 1 : 0,
flags & FNM_FILE_NAME ? flags : flags & ~FNM_PERIOD,
NULL, alloca_used) == 0))
/* This is successful. */
goto success;
}
/* None of the patterns together with the rest of the pattern
lead to a match. */
retval = FNM_NOMATCH;
break;
default:
assert (! "Invalid extended matching operator");
retval = -1;
break;
}
success:
out:
if (any_malloced)
while (list != NULL)
{
struct patternlist *old = list;
list = list->next;
if (old->malloced)
free (old);
}
return retval;
}
#undef FOLD
#undef CHAR
#undef UCHAR
#undef INT
#undef FCT
#undef EXT
#undef END
#undef STRUCT
#undef MEMPCPY
#undef MEMCHR
#undef STRCOLL
#undef STRLEN
#undef STRCAT
#undef L
#undef BTOWC
|