| 6 |
and semantics are as close as possible to those of the Perl 5 language. |
and semantics are as close as possible to those of the Perl 5 language. |
| 7 |
|
|
| 8 |
Written by Philip Hazel |
Written by Philip Hazel |
| 9 |
Copyright (c) 1997-2007 University of Cambridge |
Copyright (c) 1997-2008 University of Cambridge |
| 10 |
|
|
| 11 |
----------------------------------------------------------------------------- |
----------------------------------------------------------------------------- |
| 12 |
Redistribution and use in source and binary forms, with or without |
Redistribution and use in source and binary forms, with or without |
| 42 |
pattern matching using an NFA algorithm, trying to mimic Perl as closely as |
pattern matching using an NFA algorithm, trying to mimic Perl as closely as |
| 43 |
possible. There are also some static supporting functions. */ |
possible. There are also some static supporting functions. */ |
| 44 |
|
|
| 45 |
#ifdef HAVE_CONFIG_H |
#ifdef HAVE_CONFIG_H |
| 46 |
#include <config.h> |
#include "config.h" |
| 47 |
#endif |
#endif |
| 48 |
|
|
| 49 |
#define NLBLOCK md /* Block containing newline information */ |
#define NLBLOCK md /* Block containing newline information */ |
| 50 |
#define PSSTART start_subject /* Field containing processed string start */ |
#define PSSTART start_subject /* Field containing processed string start */ |
| 68 |
#define MATCH_MATCH 1 |
#define MATCH_MATCH 1 |
| 69 |
#define MATCH_NOMATCH 0 |
#define MATCH_NOMATCH 0 |
| 70 |
|
|
| 71 |
|
/* Special internal returns from the match() function. Make them sufficiently |
| 72 |
|
negative to avoid the external error codes. */ |
| 73 |
|
|
| 74 |
|
#define MATCH_COMMIT (-999) |
| 75 |
|
#define MATCH_PRUNE (-998) |
| 76 |
|
#define MATCH_SKIP (-997) |
| 77 |
|
#define MATCH_THEN (-996) |
| 78 |
|
|
| 79 |
/* Maximum number of ints of offset to save on the stack for recursive calls. |
/* Maximum number of ints of offset to save on the stack for recursive calls. |
| 80 |
If the offset vector is bigger, malloc is used. This should be a multiple of 3, |
If the offset vector is bigger, malloc is used. This should be a multiple of 3, |
| 81 |
because the offset vector is always a multiple of 3 long. */ |
because the offset vector is always a multiple of 3 long. */ |
| 158 |
|
|
| 159 |
if (length > md->end_subject - eptr) return FALSE; |
if (length > md->end_subject - eptr) return FALSE; |
| 160 |
|
|
| 161 |
/* Separate the caselesss case for speed */ |
/* Separate the caseless case for speed. In UTF-8 mode we can only do this |
| 162 |
|
properly if Unicode properties are supported. Otherwise, we can check only |
| 163 |
|
ASCII characters. */ |
| 164 |
|
|
| 165 |
if ((ims & PCRE_CASELESS) != 0) |
if ((ims & PCRE_CASELESS) != 0) |
| 166 |
{ |
{ |
| 167 |
|
#ifdef SUPPORT_UTF8 |
| 168 |
|
#ifdef SUPPORT_UCP |
| 169 |
|
if (md->utf8) |
| 170 |
|
{ |
| 171 |
|
USPTR endptr = eptr + length; |
| 172 |
|
while (eptr < endptr) |
| 173 |
|
{ |
| 174 |
|
int c, d; |
| 175 |
|
GETCHARINC(c, eptr); |
| 176 |
|
GETCHARINC(d, p); |
| 177 |
|
if (c != d && c != UCD_OTHERCASE(d)) return FALSE; |
| 178 |
|
} |
| 179 |
|
} |
| 180 |
|
else |
| 181 |
|
#endif |
| 182 |
|
#endif |
| 183 |
|
|
| 184 |
|
/* The same code works when not in UTF-8 mode and in UTF-8 mode when there |
| 185 |
|
is no UCP support. */ |
| 186 |
|
|
| 187 |
while (length-- > 0) |
while (length-- > 0) |
| 188 |
if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; |
{ if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; } |
| 189 |
} |
} |
| 190 |
|
|
| 191 |
|
/* In the caseful case, we can just compare the bytes, whether or not we |
| 192 |
|
are in UTF-8 mode. */ |
| 193 |
|
|
| 194 |
else |
else |
| 195 |
{ while (length-- > 0) if (*p++ != *eptr++) return FALSE; } |
{ while (length-- > 0) if (*p++ != *eptr++) return FALSE; } |
| 196 |
|
|
| 237 |
**************************************************************************** |
**************************************************************************** |
| 238 |
***************************************************************************/ |
***************************************************************************/ |
| 239 |
|
|
| 240 |
|
/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN |
| 241 |
/* Numbers for RMATCH calls */ |
below must be updated in sync. */ |
| 242 |
|
|
| 243 |
enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, |
enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, |
| 244 |
RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, |
RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, |
| 245 |
RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, |
RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, |
| 246 |
RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, |
RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, |
| 247 |
RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50 }; |
RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50, |
| 248 |
|
RM51, RM52, RM53, RM54 }; |
| 249 |
|
|
| 250 |
/* These versions of the macros use the stack, as normal. There are debugging |
/* These versions of the macros use the stack, as normal. There are debugging |
| 251 |
versions and production versions. Note that the "rw" argument of RMATCH isn't |
versions and production versions. Note that the "rw" argument of RMATCH isn't |
| 646 |
|
|
| 647 |
switch(op) |
switch(op) |
| 648 |
{ |
{ |
| 649 |
|
case OP_FAIL: |
| 650 |
|
RRETURN(MATCH_NOMATCH); |
| 651 |
|
|
| 652 |
|
case OP_PRUNE: |
| 653 |
|
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, |
| 654 |
|
ims, eptrb, flags, RM51); |
| 655 |
|
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 656 |
|
RRETURN(MATCH_PRUNE); |
| 657 |
|
|
| 658 |
|
case OP_COMMIT: |
| 659 |
|
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, |
| 660 |
|
ims, eptrb, flags, RM52); |
| 661 |
|
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 662 |
|
RRETURN(MATCH_COMMIT); |
| 663 |
|
|
| 664 |
|
case OP_SKIP: |
| 665 |
|
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, |
| 666 |
|
ims, eptrb, flags, RM53); |
| 667 |
|
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 668 |
|
md->start_match_ptr = eptr; /* Pass back current position */ |
| 669 |
|
RRETURN(MATCH_SKIP); |
| 670 |
|
|
| 671 |
|
case OP_THEN: |
| 672 |
|
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, |
| 673 |
|
ims, eptrb, flags, RM54); |
| 674 |
|
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 675 |
|
RRETURN(MATCH_THEN); |
| 676 |
|
|
| 677 |
/* Handle a capturing bracket. If there is space in the offset vector, save |
/* Handle a capturing bracket. If there is space in the offset vector, save |
| 678 |
the current subject position in the working slot at the top of the vector. |
the current subject position in the working slot at the top of the vector. |
| 679 |
We mustn't change the current values of the data slot, because they may be |
We mustn't change the current values of the data slot, because they may be |
| 715 |
{ |
{ |
| 716 |
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, |
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, |
| 717 |
ims, eptrb, flags, RM1); |
ims, eptrb, flags, RM1); |
| 718 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); |
| 719 |
md->capture_last = save_capture_last; |
md->capture_last = save_capture_last; |
| 720 |
ecode += GET(ecode, 1); |
ecode += GET(ecode, 1); |
| 721 |
} |
} |
| 774 |
|
|
| 775 |
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, |
RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, |
| 776 |
eptrb, flags, RM2); |
eptrb, flags, RM2); |
| 777 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); |
| 778 |
ecode += GET(ecode, 1); |
ecode += GET(ecode, 1); |
| 779 |
} |
} |
| 780 |
/* Control never reaches here. */ |
/* Control never reaches here. */ |
| 822 |
ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2); |
ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2); |
| 823 |
while (*ecode == OP_ALT) ecode += GET(ecode, 1); |
while (*ecode == OP_ALT) ecode += GET(ecode, 1); |
| 824 |
} |
} |
| 825 |
else if (rrc != MATCH_NOMATCH) |
else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) |
| 826 |
{ |
{ |
| 827 |
RRETURN(rrc); /* Need braces because of following else */ |
RRETURN(rrc); /* Need braces because of following else */ |
| 828 |
} |
} |
| 859 |
break; |
break; |
| 860 |
|
|
| 861 |
|
|
| 862 |
/* End of the pattern. If we are in a top-level recursion, we should |
/* End of the pattern, either real or forced. If we are in a top-level |
| 863 |
restore the offsets appropriately and continue from after the call. */ |
recursion, we should restore the offsets appropriately and continue from |
| 864 |
|
after the call. */ |
| 865 |
|
|
| 866 |
|
case OP_ACCEPT: |
| 867 |
case OP_END: |
case OP_END: |
| 868 |
if (md->recursive != NULL && md->recursive->group_num == 0) |
if (md->recursive != NULL && md->recursive->group_num == 0) |
| 869 |
{ |
{ |
| 884 |
if (md->notempty && eptr == mstart) RRETURN(MATCH_NOMATCH); |
if (md->notempty && eptr == mstart) RRETURN(MATCH_NOMATCH); |
| 885 |
md->end_match_ptr = eptr; /* Record where we ended */ |
md->end_match_ptr = eptr; /* Record where we ended */ |
| 886 |
md->end_offset_top = offset_top; /* and how many extracts were taken */ |
md->end_offset_top = offset_top; /* and how many extracts were taken */ |
| 887 |
md->start_match_ptr = mstart; /* and the start (\K can modify) */ |
md->start_match_ptr = mstart; /* and the start (\K can modify) */ |
| 888 |
RRETURN(MATCH_MATCH); |
RRETURN(MATCH_MATCH); |
| 889 |
|
|
| 890 |
/* Change option settings */ |
/* Change option settings */ |
| 908 |
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, |
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, |
| 909 |
RM4); |
RM4); |
| 910 |
if (rrc == MATCH_MATCH) break; |
if (rrc == MATCH_MATCH) break; |
| 911 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); |
| 912 |
ecode += GET(ecode, 1); |
ecode += GET(ecode, 1); |
| 913 |
} |
} |
| 914 |
while (*ecode == OP_ALT); |
while (*ecode == OP_ALT); |
| 935 |
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, |
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, |
| 936 |
RM5); |
RM5); |
| 937 |
if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); |
if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); |
| 938 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); |
| 939 |
ecode += GET(ecode,1); |
ecode += GET(ecode,1); |
| 940 |
} |
} |
| 941 |
while (*ecode == OP_ALT); |
while (*ecode == OP_ALT); |
| 959 |
{ |
{ |
| 960 |
eptr--; |
eptr--; |
| 961 |
if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); |
if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); |
| 962 |
BACKCHAR(eptr) |
BACKCHAR(eptr); |
| 963 |
} |
} |
| 964 |
} |
} |
| 965 |
else |
else |
| 1072 |
(pcre_free)(new_recursive.offset_save); |
(pcre_free)(new_recursive.offset_save); |
| 1073 |
RRETURN(MATCH_MATCH); |
RRETURN(MATCH_MATCH); |
| 1074 |
} |
} |
| 1075 |
else if (rrc != MATCH_NOMATCH) |
else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) |
| 1076 |
{ |
{ |
| 1077 |
DPRINTF(("Recursion gave error %d\n", rrc)); |
DPRINTF(("Recursion gave error %d\n", rrc)); |
| 1078 |
RRETURN(rrc); |
RRETURN(rrc); |
| 1108 |
{ |
{ |
| 1109 |
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM7); |
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM7); |
| 1110 |
if (rrc == MATCH_MATCH) break; |
if (rrc == MATCH_MATCH) break; |
| 1111 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); |
| 1112 |
ecode += GET(ecode,1); |
ecode += GET(ecode,1); |
| 1113 |
} |
} |
| 1114 |
while (*ecode == OP_ALT); |
while (*ecode == OP_ALT); |
| 1174 |
do ecode += GET(ecode,1); while (*ecode == OP_ALT); |
do ecode += GET(ecode,1); while (*ecode == OP_ALT); |
| 1175 |
break; |
break; |
| 1176 |
|
|
| 1177 |
/* BRAZERO and BRAMINZERO occur just before a bracket group, indicating |
/* BRAZERO, BRAMINZERO and SKIPZERO occur just before a bracket group, |
| 1178 |
that it may occur zero times. It may repeat infinitely, or not at all - |
indicating that it may occur zero times. It may repeat infinitely, or not |
| 1179 |
i.e. it could be ()* or ()? in the pattern. Brackets with fixed upper |
at all - i.e. it could be ()* or ()? or even (){0} in the pattern. Brackets |
| 1180 |
repeat limits are compiled as a number of copies, with the optional ones |
with fixed upper repeat limits are compiled as a number of copies, with the |
| 1181 |
preceded by BRAZERO or BRAMINZERO. */ |
optional ones preceded by BRAZERO or BRAMINZERO. */ |
| 1182 |
|
|
| 1183 |
case OP_BRAZERO: |
case OP_BRAZERO: |
| 1184 |
{ |
{ |
| 1200 |
} |
} |
| 1201 |
break; |
break; |
| 1202 |
|
|
| 1203 |
|
case OP_SKIPZERO: |
| 1204 |
|
{ |
| 1205 |
|
next = ecode+1; |
| 1206 |
|
do next += GET(next,1); while (*next == OP_ALT); |
| 1207 |
|
ecode = next + 1 + LINK_SIZE; |
| 1208 |
|
} |
| 1209 |
|
break; |
| 1210 |
|
|
| 1211 |
/* End of a group, repeated or non-repeating. */ |
/* End of a group, repeated or non-repeating. */ |
| 1212 |
|
|
| 1213 |
case OP_KET: |
case OP_KET: |
| 1455 |
/* Match a single character type; inline for speed */ |
/* Match a single character type; inline for speed */ |
| 1456 |
|
|
| 1457 |
case OP_ANY: |
case OP_ANY: |
| 1458 |
if ((ims & PCRE_DOTALL) == 0) |
if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); |
| 1459 |
{ |
/* Fall through */ |
| 1460 |
if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); |
|
| 1461 |
} |
case OP_ALLANY: |
| 1462 |
if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 1463 |
if (utf8) |
if (utf8) while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
|
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
|
| 1464 |
ecode++; |
ecode++; |
| 1465 |
break; |
break; |
| 1466 |
|
|
| 1559 |
case 0x000d: |
case 0x000d: |
| 1560 |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
| 1561 |
break; |
break; |
| 1562 |
|
|
| 1563 |
case 0x000a: |
case 0x000a: |
| 1564 |
|
break; |
| 1565 |
|
|
| 1566 |
case 0x000b: |
case 0x000b: |
| 1567 |
case 0x000c: |
case 0x000c: |
| 1568 |
case 0x0085: |
case 0x0085: |
| 1569 |
case 0x2028: |
case 0x2028: |
| 1570 |
case 0x2029: |
case 0x2029: |
| 1571 |
|
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); |
| 1572 |
break; |
break; |
| 1573 |
} |
} |
| 1574 |
ecode++; |
ecode++; |
| 1679 |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 1680 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 1681 |
{ |
{ |
| 1682 |
int chartype, script; |
const ucd_record * prop = GET_UCD(c); |
|
int category = _pcre_ucp_findprop(c, &chartype, &script); |
|
| 1683 |
|
|
| 1684 |
switch(ecode[1]) |
switch(ecode[1]) |
| 1685 |
{ |
{ |
| 1688 |
break; |
break; |
| 1689 |
|
|
| 1690 |
case PT_LAMP: |
case PT_LAMP: |
| 1691 |
if ((chartype == ucp_Lu || |
if ((prop->chartype == ucp_Lu || |
| 1692 |
chartype == ucp_Ll || |
prop->chartype == ucp_Ll || |
| 1693 |
chartype == ucp_Lt) == (op == OP_NOTPROP)) |
prop->chartype == ucp_Lt) == (op == OP_NOTPROP)) |
| 1694 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 1695 |
break; |
break; |
| 1696 |
|
|
| 1697 |
case PT_GC: |
case PT_GC: |
| 1698 |
if ((ecode[2] != category) == (op == OP_PROP)) |
if ((ecode[2] != _pcre_ucp_gentype[prop->chartype]) == (op == OP_PROP)) |
| 1699 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 1700 |
break; |
break; |
| 1701 |
|
|
| 1702 |
case PT_PC: |
case PT_PC: |
| 1703 |
if ((ecode[2] != chartype) == (op == OP_PROP)) |
if ((ecode[2] != prop->chartype) == (op == OP_PROP)) |
| 1704 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 1705 |
break; |
break; |
| 1706 |
|
|
| 1707 |
case PT_SC: |
case PT_SC: |
| 1708 |
if ((ecode[2] != script) == (op == OP_PROP)) |
if ((ecode[2] != prop->script) == (op == OP_PROP)) |
| 1709 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 1710 |
break; |
break; |
| 1711 |
|
|
| 1724 |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 1725 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 1726 |
{ |
{ |
| 1727 |
int chartype, script; |
int category = UCD_CATEGORY(c); |
|
int category = _pcre_ucp_findprop(c, &chartype, &script); |
|
| 1728 |
if (category == ucp_M) RRETURN(MATCH_NOMATCH); |
if (category == ucp_M) RRETURN(MATCH_NOMATCH); |
| 1729 |
while (eptr < md->end_subject) |
while (eptr < md->end_subject) |
| 1730 |
{ |
{ |
| 1733 |
{ |
{ |
| 1734 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 1735 |
} |
} |
| 1736 |
category = _pcre_ucp_findprop(c, &chartype, &script); |
category = UCD_CATEGORY(c); |
| 1737 |
if (category != ucp_M) break; |
if (category != ucp_M) break; |
| 1738 |
eptr += len; |
eptr += len; |
| 1739 |
} |
} |
| 1754 |
case OP_REF: |
case OP_REF: |
| 1755 |
{ |
{ |
| 1756 |
offset = GET2(ecode, 1) << 1; /* Doubled ref number */ |
offset = GET2(ecode, 1) << 1; /* Doubled ref number */ |
| 1757 |
ecode += 3; /* Advance past item */ |
ecode += 3; |
| 1758 |
|
|
| 1759 |
|
/* If the reference is unset, there are two possibilities: |
| 1760 |
|
|
| 1761 |
|
(a) In the default, Perl-compatible state, set the length to be longer |
| 1762 |
|
than the amount of subject left; this ensures that every attempt at a |
| 1763 |
|
match fails. We can't just fail here, because of the possibility of |
| 1764 |
|
quantifiers with zero minima. |
| 1765 |
|
|
| 1766 |
|
(b) If the JavaScript compatibility flag is set, set the length to zero |
| 1767 |
|
so that the back reference matches an empty string. |
| 1768 |
|
|
| 1769 |
|
Otherwise, set the length to the length of what was matched by the |
| 1770 |
|
referenced subpattern. */ |
| 1771 |
|
|
| 1772 |
/* If the reference is unset, set the length to be longer than the amount |
if (offset >= offset_top || md->offset_vector[offset] < 0) |
| 1773 |
of subject left; this ensures that every attempt at a match fails. We |
length = (md->jscript_compat)? 0 : md->end_subject - eptr + 1; |
| 1774 |
can't just fail here, because of the possibility of quantifiers with zero |
else |
| 1775 |
minima. */ |
length = md->offset_vector[offset+1] - md->offset_vector[offset]; |
|
|
|
|
length = (offset >= offset_top || md->offset_vector[offset] < 0)? |
|
|
md->end_subject - eptr + 1 : |
|
|
md->offset_vector[offset+1] - md->offset_vector[offset]; |
|
| 1776 |
|
|
| 1777 |
/* Set up for repetition, or handle the non-repeated case */ |
/* Set up for repetition, or handle the non-repeated case */ |
| 1778 |
|
|
| 2132 |
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21); |
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21); |
| 2133 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 2134 |
if (eptr-- == pp) break; /* Stop if tried at original pos */ |
if (eptr-- == pp) break; /* Stop if tried at original pos */ |
| 2135 |
BACKCHAR(eptr) |
if (utf8) BACKCHAR(eptr); |
| 2136 |
} |
} |
| 2137 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 2138 |
} |
} |
| 2198 |
if (fc != dc) |
if (fc != dc) |
| 2199 |
{ |
{ |
| 2200 |
#ifdef SUPPORT_UCP |
#ifdef SUPPORT_UCP |
| 2201 |
if (dc != _pcre_ucp_othercase(fc)) |
if (dc != UCD_OTHERCASE(fc)) |
| 2202 |
#endif |
#endif |
| 2203 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 2204 |
} |
} |
| 2289 |
#ifdef SUPPORT_UCP |
#ifdef SUPPORT_UCP |
| 2290 |
unsigned int othercase; |
unsigned int othercase; |
| 2291 |
if ((ims & PCRE_CASELESS) != 0 && |
if ((ims & PCRE_CASELESS) != 0 && |
| 2292 |
(othercase = _pcre_ucp_othercase(fc)) != NOTACHAR) |
(othercase = UCD_OTHERCASE(fc)) != fc) |
| 2293 |
oclength = _pcre_ord2utf8(othercase, occhars); |
oclength = _pcre_ord2utf8(othercase, occhars); |
| 2294 |
else oclength = 0; |
else oclength = 0; |
| 2295 |
#endif /* SUPPORT_UCP */ |
#endif /* SUPPORT_UCP */ |
| 2894 |
{ |
{ |
| 2895 |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 2896 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 2897 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_chartype = UCD_CHARTYPE(c); |
| 2898 |
if ((prop_chartype == ucp_Lu || |
if ((prop_chartype == ucp_Lu || |
| 2899 |
prop_chartype == ucp_Ll || |
prop_chartype == ucp_Ll || |
| 2900 |
prop_chartype == ucp_Lt) == prop_fail_result) |
prop_chartype == ucp_Lt) == prop_fail_result) |
| 2907 |
{ |
{ |
| 2908 |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 2909 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 2910 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 2911 |
if ((prop_category == prop_value) == prop_fail_result) |
if ((prop_category == prop_value) == prop_fail_result) |
| 2912 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 2913 |
} |
} |
| 2918 |
{ |
{ |
| 2919 |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 2920 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 2921 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_chartype = UCD_CHARTYPE(c); |
| 2922 |
if ((prop_chartype == prop_value) == prop_fail_result) |
if ((prop_chartype == prop_value) == prop_fail_result) |
| 2923 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 2924 |
} |
} |
| 2929 |
{ |
{ |
| 2930 |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 2931 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 2932 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_script = UCD_SCRIPT(c); |
| 2933 |
if ((prop_script == prop_value) == prop_fail_result) |
if ((prop_script == prop_value) == prop_fail_result) |
| 2934 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 2935 |
} |
} |
| 2948 |
for (i = 1; i <= min; i++) |
for (i = 1; i <= min; i++) |
| 2949 |
{ |
{ |
| 2950 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 2951 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 2952 |
if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); |
if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); |
| 2953 |
while (eptr < md->end_subject) |
while (eptr < md->end_subject) |
| 2954 |
{ |
{ |
| 2957 |
{ |
{ |
| 2958 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 2959 |
} |
} |
| 2960 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 2961 |
if (prop_category != ucp_M) break; |
if (prop_category != ucp_M) break; |
| 2962 |
eptr += len; |
eptr += len; |
| 2963 |
} |
} |
| 2975 |
case OP_ANY: |
case OP_ANY: |
| 2976 |
for (i = 1; i <= min; i++) |
for (i = 1; i <= min; i++) |
| 2977 |
{ |
{ |
| 2978 |
if (eptr >= md->end_subject || |
if (eptr >= md->end_subject || IS_NEWLINE(eptr)) |
|
((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr))) |
|
| 2979 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 2980 |
eptr++; |
eptr++; |
| 2981 |
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
| 2982 |
} |
} |
| 2983 |
break; |
break; |
| 2984 |
|
|
| 2985 |
|
case OP_ALLANY: |
| 2986 |
|
for (i = 1; i <= min; i++) |
| 2987 |
|
{ |
| 2988 |
|
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 2989 |
|
eptr++; |
| 2990 |
|
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
| 2991 |
|
} |
| 2992 |
|
break; |
| 2993 |
|
|
| 2994 |
case OP_ANYBYTE: |
case OP_ANYBYTE: |
| 2995 |
eptr += min; |
eptr += min; |
| 2996 |
break; |
break; |
| 3006 |
case 0x000d: |
case 0x000d: |
| 3007 |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
| 3008 |
break; |
break; |
| 3009 |
|
|
| 3010 |
case 0x000a: |
case 0x000a: |
| 3011 |
|
break; |
| 3012 |
|
|
| 3013 |
case 0x000b: |
case 0x000b: |
| 3014 |
case 0x000c: |
case 0x000c: |
| 3015 |
case 0x0085: |
case 0x0085: |
| 3016 |
case 0x2028: |
case 0x2028: |
| 3017 |
case 0x2029: |
case 0x2029: |
| 3018 |
|
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); |
| 3019 |
break; |
break; |
| 3020 |
} |
} |
| 3021 |
} |
} |
| 3149 |
for (i = 1; i <= min; i++) |
for (i = 1; i <= min; i++) |
| 3150 |
{ |
{ |
| 3151 |
if (eptr >= md->end_subject || |
if (eptr >= md->end_subject || |
| 3152 |
(*eptr < 128 && (md->ctypes[*eptr++] & ctype_space) != 0)) |
(*eptr < 128 && (md->ctypes[*eptr] & ctype_space) != 0)) |
| 3153 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 3154 |
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80); |
| 3155 |
} |
} |
| 3156 |
break; |
break; |
| 3157 |
|
|
| 3169 |
for (i = 1; i <= min; i++) |
for (i = 1; i <= min; i++) |
| 3170 |
{ |
{ |
| 3171 |
if (eptr >= md->end_subject || |
if (eptr >= md->end_subject || |
| 3172 |
(*eptr < 128 && (md->ctypes[*eptr++] & ctype_word) != 0)) |
(*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0)) |
| 3173 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 3174 |
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80); |
| 3175 |
} |
} |
| 3176 |
break; |
break; |
| 3177 |
|
|
| 3199 |
switch(ctype) |
switch(ctype) |
| 3200 |
{ |
{ |
| 3201 |
case OP_ANY: |
case OP_ANY: |
| 3202 |
if ((ims & PCRE_DOTALL) == 0) |
for (i = 1; i <= min; i++) |
| 3203 |
{ |
{ |
| 3204 |
for (i = 1; i <= min; i++) |
if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); |
| 3205 |
{ |
eptr++; |
|
if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); |
|
|
eptr++; |
|
|
} |
|
| 3206 |
} |
} |
| 3207 |
else eptr += min; |
break; |
| 3208 |
|
|
| 3209 |
|
case OP_ALLANY: |
| 3210 |
|
eptr += min; |
| 3211 |
break; |
break; |
| 3212 |
|
|
| 3213 |
case OP_ANYBYTE: |
case OP_ANYBYTE: |
| 3228 |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
| 3229 |
break; |
break; |
| 3230 |
case 0x000a: |
case 0x000a: |
| 3231 |
|
break; |
| 3232 |
|
|
| 3233 |
case 0x000b: |
case 0x000b: |
| 3234 |
case 0x000c: |
case 0x000c: |
| 3235 |
case 0x0085: |
case 0x0085: |
| 3236 |
|
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); |
| 3237 |
break; |
break; |
| 3238 |
} |
} |
| 3239 |
} |
} |
| 3373 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 3374 |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 3375 |
GETCHARINC(c, eptr); |
GETCHARINC(c, eptr); |
| 3376 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_chartype = UCD_CHARTYPE(c); |
| 3377 |
if ((prop_chartype == ucp_Lu || |
if ((prop_chartype == ucp_Lu || |
| 3378 |
prop_chartype == ucp_Ll || |
prop_chartype == ucp_Ll || |
| 3379 |
prop_chartype == ucp_Lt) == prop_fail_result) |
prop_chartype == ucp_Lt) == prop_fail_result) |
| 3388 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 3389 |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 3390 |
GETCHARINC(c, eptr); |
GETCHARINC(c, eptr); |
| 3391 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 3392 |
if ((prop_category == prop_value) == prop_fail_result) |
if ((prop_category == prop_value) == prop_fail_result) |
| 3393 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 3394 |
} |
} |
| 3401 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 3402 |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 3403 |
GETCHARINC(c, eptr); |
GETCHARINC(c, eptr); |
| 3404 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_chartype = UCD_CHARTYPE(c); |
| 3405 |
if ((prop_chartype == prop_value) == prop_fail_result) |
if ((prop_chartype == prop_value) == prop_fail_result) |
| 3406 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 3407 |
} |
} |
| 3414 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 3415 |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 3416 |
GETCHARINC(c, eptr); |
GETCHARINC(c, eptr); |
| 3417 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_script = UCD_SCRIPT(c); |
| 3418 |
if ((prop_script == prop_value) == prop_fail_result) |
if ((prop_script == prop_value) == prop_fail_result) |
| 3419 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 3420 |
} |
} |
| 3436 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 3437 |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); |
| 3438 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 3439 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 3440 |
if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); |
if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); |
| 3441 |
while (eptr < md->end_subject) |
while (eptr < md->end_subject) |
| 3442 |
{ |
{ |
| 3445 |
{ |
{ |
| 3446 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 3447 |
} |
} |
| 3448 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 3449 |
if (prop_category != ucp_M) break; |
if (prop_category != ucp_M) break; |
| 3450 |
eptr += len; |
eptr += len; |
| 3451 |
} |
} |
| 3464 |
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42); |
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42); |
| 3465 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 3466 |
if (fi >= max || eptr >= md->end_subject || |
if (fi >= max || eptr >= md->end_subject || |
| 3467 |
(ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 && |
(ctype == OP_ANY && IS_NEWLINE(eptr))) |
|
IS_NEWLINE(eptr))) |
|
| 3468 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 3469 |
|
|
| 3470 |
GETCHARINC(c, eptr); |
GETCHARINC(c, eptr); |
| 3471 |
switch(ctype) |
switch(ctype) |
| 3472 |
{ |
{ |
| 3473 |
case OP_ANY: /* This is the DOTALL case */ |
case OP_ANY: /* This is the non-NL case */ |
| 3474 |
break; |
case OP_ALLANY: |
|
|
|
| 3475 |
case OP_ANYBYTE: |
case OP_ANYBYTE: |
| 3476 |
break; |
break; |
| 3477 |
|
|
| 3483 |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
| 3484 |
break; |
break; |
| 3485 |
case 0x000a: |
case 0x000a: |
| 3486 |
|
break; |
| 3487 |
|
|
| 3488 |
case 0x000b: |
case 0x000b: |
| 3489 |
case 0x000c: |
case 0x000c: |
| 3490 |
case 0x0085: |
case 0x0085: |
| 3491 |
case 0x2028: |
case 0x2028: |
| 3492 |
case 0x2029: |
case 0x2029: |
| 3493 |
|
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); |
| 3494 |
break; |
break; |
| 3495 |
} |
} |
| 3496 |
break; |
break; |
| 3623 |
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43); |
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43); |
| 3624 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 3625 |
if (fi >= max || eptr >= md->end_subject || |
if (fi >= max || eptr >= md->end_subject || |
| 3626 |
((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr))) |
(ctype == OP_ANY && IS_NEWLINE(eptr))) |
| 3627 |
RRETURN(MATCH_NOMATCH); |
RRETURN(MATCH_NOMATCH); |
| 3628 |
|
|
| 3629 |
c = *eptr++; |
c = *eptr++; |
| 3630 |
switch(ctype) |
switch(ctype) |
| 3631 |
{ |
{ |
| 3632 |
case OP_ANY: /* This is the DOTALL case */ |
case OP_ANY: /* This is the non-NL case */ |
| 3633 |
break; |
case OP_ALLANY: |
|
|
|
| 3634 |
case OP_ANYBYTE: |
case OP_ANYBYTE: |
| 3635 |
break; |
break; |
| 3636 |
|
|
| 3641 |
case 0x000d: |
case 0x000d: |
| 3642 |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
if (eptr < md->end_subject && *eptr == 0x0a) eptr++; |
| 3643 |
break; |
break; |
| 3644 |
|
|
| 3645 |
case 0x000a: |
case 0x000a: |
| 3646 |
|
break; |
| 3647 |
|
|
| 3648 |
case 0x000b: |
case 0x000b: |
| 3649 |
case 0x000c: |
case 0x000c: |
| 3650 |
case 0x0085: |
case 0x0085: |
| 3651 |
|
if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); |
| 3652 |
break; |
break; |
| 3653 |
} |
} |
| 3654 |
break; |
break; |
| 3763 |
int len = 1; |
int len = 1; |
| 3764 |
if (eptr >= md->end_subject) break; |
if (eptr >= md->end_subject) break; |
| 3765 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 3766 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_chartype = UCD_CHARTYPE(c); |
| 3767 |
if ((prop_chartype == ucp_Lu || |
if ((prop_chartype == ucp_Lu || |
| 3768 |
prop_chartype == ucp_Ll || |
prop_chartype == ucp_Ll || |
| 3769 |
prop_chartype == ucp_Lt) == prop_fail_result) |
prop_chartype == ucp_Lt) == prop_fail_result) |
| 3778 |
int len = 1; |
int len = 1; |
| 3779 |
if (eptr >= md->end_subject) break; |
if (eptr >= md->end_subject) break; |
| 3780 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 3781 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 3782 |
if ((prop_category == prop_value) == prop_fail_result) |
if ((prop_category == prop_value) == prop_fail_result) |
| 3783 |
break; |
break; |
| 3784 |
eptr+= len; |
eptr+= len; |
| 3791 |
int len = 1; |
int len = 1; |
| 3792 |
if (eptr >= md->end_subject) break; |
if (eptr >= md->end_subject) break; |
| 3793 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 3794 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_chartype = UCD_CHARTYPE(c); |
| 3795 |
if ((prop_chartype == prop_value) == prop_fail_result) |
if ((prop_chartype == prop_value) == prop_fail_result) |
| 3796 |
break; |
break; |
| 3797 |
eptr+= len; |
eptr+= len; |
| 3804 |
int len = 1; |
int len = 1; |
| 3805 |
if (eptr >= md->end_subject) break; |
if (eptr >= md->end_subject) break; |
| 3806 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 3807 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_script = UCD_SCRIPT(c); |
| 3808 |
if ((prop_script == prop_value) == prop_fail_result) |
if ((prop_script == prop_value) == prop_fail_result) |
| 3809 |
break; |
break; |
| 3810 |
eptr+= len; |
eptr+= len; |
| 3820 |
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM44); |
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM44); |
| 3821 |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
if (rrc != MATCH_NOMATCH) RRETURN(rrc); |
| 3822 |
if (eptr-- == pp) break; /* Stop if tried at original pos */ |
if (eptr-- == pp) break; /* Stop if tried at original pos */ |
| 3823 |
BACKCHAR(eptr); |
if (utf8) BACKCHAR(eptr); |
| 3824 |
} |
} |
| 3825 |
} |
} |
| 3826 |
|
|
| 3833 |
{ |
{ |
| 3834 |
if (eptr >= md->end_subject) break; |
if (eptr >= md->end_subject) break; |
| 3835 |
GETCHARINCTEST(c, eptr); |
GETCHARINCTEST(c, eptr); |
| 3836 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 3837 |
if (prop_category == ucp_M) break; |
if (prop_category == ucp_M) break; |
| 3838 |
while (eptr < md->end_subject) |
while (eptr < md->end_subject) |
| 3839 |
{ |
{ |
| 3842 |
{ |
{ |
| 3843 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 3844 |
} |
} |
| 3845 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 3846 |
if (prop_category != ucp_M) break; |
if (prop_category != ucp_M) break; |
| 3847 |
eptr += len; |
eptr += len; |
| 3848 |
} |
} |
| 3859 |
for (;;) /* Move back over one extended */ |
for (;;) /* Move back over one extended */ |
| 3860 |
{ |
{ |
| 3861 |
int len = 1; |
int len = 1; |
|
BACKCHAR(eptr); |
|
| 3862 |
if (!utf8) c = *eptr; else |
if (!utf8) c = *eptr; else |
| 3863 |
{ |
{ |
| 3864 |
|
BACKCHAR(eptr); |
| 3865 |
GETCHARLEN(c, eptr, len); |
GETCHARLEN(c, eptr, len); |
| 3866 |
} |
} |
| 3867 |
prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); |
prop_category = UCD_CATEGORY(c); |
| 3868 |
if (prop_category != ucp_M) break; |
if (prop_category != ucp_M) break; |
| 3869 |
eptr--; |
eptr--; |
| 3870 |
} |
} |
| 3884 |
case OP_ANY: |
case OP_ANY: |
| 3885 |
if (max < INT_MAX) |
if (max < INT_MAX) |
| 3886 |
{ |
{ |
| 3887 |
if ((ims & PCRE_DOTALL) == 0) |
for (i = min; i < max; i++) |
|
{ |
|
|
for (i = min; i < max; i++) |
|
|
{ |
|
|
if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; |
|
|
eptr++; |
|
|
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
|
|
} |
|
|
} |
|
|
else |
|
| 3888 |
{ |
{ |
| 3889 |
for (i = min; i < max; i++) |
if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; |
| 3890 |
{ |
eptr++; |
| 3891 |
if (eptr >= md->end_subject) break; |
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
|
eptr++; |
|
|
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
|
|
} |
|
| 3892 |
} |
} |
| 3893 |
} |
} |
| 3894 |
|
|
| 3896 |
|
|
| 3897 |
else |
else |
| 3898 |
{ |
{ |
| 3899 |
if ((ims & PCRE_DOTALL) == 0) |
for (i = min; i < max; i++) |
| 3900 |
{ |
{ |
| 3901 |
for (i = min; i < max; i++) |
if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; |
| 3902 |
{ |
eptr++; |
| 3903 |
if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; |
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
|
eptr++; |
|
|
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
|
|
} |
|
| 3904 |
} |
} |
| 3905 |
else |
} |
| 3906 |
|
break; |
| 3907 |
|
|
| 3908 |
|
case OP_ALLANY: |
| 3909 |
|
if (max < INT_MAX) |
| 3910 |
|
{ |
| 3911 |
|
for (i = min; i < max; i++) |
| 3912 |
{ |
{ |
| 3913 |
eptr = md->end_subject; |
if (eptr >= md->end_subject) break; |
| 3914 |
|
eptr++; |
| 3915 |
|
while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; |
| 3916 |
} |
} |
| 3917 |
} |
} |
| 3918 |
|
else eptr = md->end_subject; /* Unlimited UTF-8 repeat */ |
| 3919 |
break; |
break; |
| 3920 |
|
|
| 3921 |
/* The byte case is the same as non-UTF8 */ |
/* The byte case is the same as non-UTF8 */ |
| 3940 |
} |
} |
| 3941 |
else |
else |
| 3942 |
{ |
{ |
| 3943 |
if (c != 0x000a && c != 0x000b && c != 0x000c && |
if (c != 0x000a && |
| 3944 |
c != 0x0085 && c != 0x2028 && c != 0x2029) |
(md->bsr_anycrlf || |
| 3945 |
|
(c != 0x000b && c != 0x000c && |
| 3946 |
|
c != 0x0085 && c != 0x2028 && c != 0x2029))) |
| 3947 |
break; |
break; |
| 3948 |
eptr += len; |
eptr += len; |
| 3949 |
} |
} |
| 4096 |
} |
} |
| 4097 |
} |
} |
| 4098 |
else |
else |
| 4099 |
#endif |
#endif /* SUPPORT_UTF8 */ |
| 4100 |
|
|
| 4101 |
/* Not UTF-8 mode */ |
/* Not UTF-8 mode */ |
| 4102 |
{ |
{ |
| 4103 |
switch(ctype) |
switch(ctype) |
| 4104 |
{ |
{ |
| 4105 |
case OP_ANY: |
case OP_ANY: |
| 4106 |
if ((ims & PCRE_DOTALL) == 0) |
for (i = min; i < max; i++) |
| 4107 |
{ |
{ |
| 4108 |
for (i = min; i < max; i++) |
if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; |
| 4109 |
{ |
eptr++; |
|
if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; |
|
|
eptr++; |
|
|
} |
|
|
break; |
|
| 4110 |
} |
} |
| 4111 |
/* For DOTALL case, fall through and treat as \C */ |
break; |
| 4112 |
|
|
| 4113 |
|
case OP_ALLANY: |
| 4114 |
case OP_ANYBYTE: |
case OP_ANYBYTE: |
| 4115 |
c = max - min; |
c = max - min; |
| 4116 |
if (c > (unsigned int)(md->end_subject - eptr)) |
if (c > (unsigned int)(md->end_subject - eptr)) |
| 4130 |
} |
} |
| 4131 |
else |
else |
| 4132 |
{ |
{ |
| 4133 |
if (c != 0x000a && c != 0x000b && c != 0x000c && c != 0x0085) |
if (c != 0x000a && |
| 4134 |
|
(md->bsr_anycrlf || |
| 4135 |
|
(c != 0x000b && c != 0x000c && c != 0x0085))) |
| 4136 |
break; |
break; |
| 4137 |
eptr++; |
eptr++; |
| 4138 |
} |
} |
| 4282 |
switch (frame->Xwhere) |
switch (frame->Xwhere) |
| 4283 |
{ |
{ |
| 4284 |
LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) |
LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) |
| 4285 |
LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(16) |
LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17) |
| 4286 |
LBL(17) LBL(18) LBL(19) LBL(20) LBL(21) LBL(22) LBL(23) LBL(24) |
LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33) |
| 4287 |
LBL(25) LBL(26) LBL(27) LBL(28) LBL(29) LBL(30) LBL(31) LBL(32) |
LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52) |
| 4288 |
LBL(33) LBL(34) LBL(35) LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) |
LBL(53) LBL(54) |
| 4289 |
LBL(41) LBL(42) LBL(43) LBL(44) LBL(45) LBL(46) LBL(47) |
#ifdef SUPPORT_UTF8 |
| 4290 |
|
LBL(16) LBL(18) LBL(20) LBL(21) LBL(22) LBL(23) LBL(28) LBL(30) |
| 4291 |
|
LBL(32) LBL(34) LBL(42) LBL(46) |
| 4292 |
|
#ifdef SUPPORT_UCP |
| 4293 |
|
LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45) |
| 4294 |
|
#endif /* SUPPORT_UCP */ |
| 4295 |
|
#endif /* SUPPORT_UTF8 */ |
| 4296 |
default: |
default: |
| 4297 |
DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); |
DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); |
| 4298 |
return PCRE_ERROR_INTERNAL; |
return PCRE_ERROR_INTERNAL; |
| 4384 |
< -1 => some kind of unexpected problem |
< -1 => some kind of unexpected problem |
| 4385 |
*/ |
*/ |
| 4386 |
|
|
| 4387 |
PCRE_EXP_DEFN int |
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION |
| 4388 |
pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, |
pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, |
| 4389 |
PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, |
PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, |
| 4390 |
int offsetcount) |
int offsetcount) |
| 4471 |
/* Set up other data */ |
/* Set up other data */ |
| 4472 |
|
|
| 4473 |
anchored = ((re->options | options) & PCRE_ANCHORED) != 0; |
anchored = ((re->options | options) & PCRE_ANCHORED) != 0; |
| 4474 |
startline = (re->options & PCRE_STARTLINE) != 0; |
startline = (re->flags & PCRE_STARTLINE) != 0; |
| 4475 |
firstline = (re->options & PCRE_FIRSTLINE) != 0; |
firstline = (re->options & PCRE_FIRSTLINE) != 0; |
| 4476 |
|
|
| 4477 |
/* The code starts after the real_pcre block and the capture name table. */ |
/* The code starts after the real_pcre block and the capture name table. */ |
| 4486 |
|
|
| 4487 |
md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; |
md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; |
| 4488 |
utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0; |
utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0; |
| 4489 |
|
md->jscript_compat = (re->options & PCRE_JAVASCRIPT_COMPAT) != 0; |
| 4490 |
|
|
| 4491 |
md->notbol = (options & PCRE_NOTBOL) != 0; |
md->notbol = (options & PCRE_NOTBOL) != 0; |
| 4492 |
md->noteol = (options & PCRE_NOTEOL) != 0; |
md->noteol = (options & PCRE_NOTEOL) != 0; |
| 4499 |
md->lcc = tables + lcc_offset; |
md->lcc = tables + lcc_offset; |
| 4500 |
md->ctypes = tables + ctypes_offset; |
md->ctypes = tables + ctypes_offset; |
| 4501 |
|
|
| 4502 |
|
/* Handle different \R options. */ |
| 4503 |
|
|
| 4504 |
|
switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) |
| 4505 |
|
{ |
| 4506 |
|
case 0: |
| 4507 |
|
if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) |
| 4508 |
|
md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0; |
| 4509 |
|
else |
| 4510 |
|
#ifdef BSR_ANYCRLF |
| 4511 |
|
md->bsr_anycrlf = TRUE; |
| 4512 |
|
#else |
| 4513 |
|
md->bsr_anycrlf = FALSE; |
| 4514 |
|
#endif |
| 4515 |
|
break; |
| 4516 |
|
|
| 4517 |
|
case PCRE_BSR_ANYCRLF: |
| 4518 |
|
md->bsr_anycrlf = TRUE; |
| 4519 |
|
break; |
| 4520 |
|
|
| 4521 |
|
case PCRE_BSR_UNICODE: |
| 4522 |
|
md->bsr_anycrlf = FALSE; |
| 4523 |
|
break; |
| 4524 |
|
|
| 4525 |
|
default: return PCRE_ERROR_BADNEWLINE; |
| 4526 |
|
} |
| 4527 |
|
|
| 4528 |
/* Handle different types of newline. The three bits give eight cases. If |
/* Handle different types of newline. The three bits give eight cases. If |
| 4529 |
nothing is set at run time, whatever was used at compile time applies. */ |
nothing is set at run time, whatever was used at compile time applies. */ |
| 4530 |
|
|
| 4531 |
switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : (pcre_uint32)options) & |
switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : |
| 4532 |
PCRE_NEWLINE_BITS) |
(pcre_uint32)options) & PCRE_NEWLINE_BITS) |
| 4533 |
{ |
{ |
| 4534 |
case 0: newline = NEWLINE; break; /* Compile-time default */ |
case 0: newline = NEWLINE; break; /* Compile-time default */ |
| 4535 |
case PCRE_NEWLINE_CR: newline = '\r'; break; |
case PCRE_NEWLINE_CR: newline = '\r'; break; |
| 4568 |
/* Partial matching is supported only for a restricted set of regexes at the |
/* Partial matching is supported only for a restricted set of regexes at the |
| 4569 |
moment. */ |
moment. */ |
| 4570 |
|
|
| 4571 |
if (md->partial && (re->options & PCRE_NOPARTIAL) != 0) |
if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0) |
| 4572 |
return PCRE_ERROR_BADPARTIAL; |
return PCRE_ERROR_BADPARTIAL; |
| 4573 |
|
|
| 4574 |
/* Check a UTF-8 string if required. Unfortunately there's no way of passing |
/* Check a UTF-8 string if required. Unfortunately there's no way of passing |
| 4645 |
|
|
| 4646 |
if (!anchored) |
if (!anchored) |
| 4647 |
{ |
{ |
| 4648 |
if ((re->options & PCRE_FIRSTSET) != 0) |
if ((re->flags & PCRE_FIRSTSET) != 0) |
| 4649 |
{ |
{ |
| 4650 |
first_byte = re->first_byte & 255; |
first_byte = re->first_byte & 255; |
| 4651 |
if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) |
if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) |
| 4660 |
/* For anchored or unanchored matches, there may be a "last known required |
/* For anchored or unanchored matches, there may be a "last known required |
| 4661 |
character" set. */ |
character" set. */ |
| 4662 |
|
|
| 4663 |
if ((re->options & PCRE_REQCHSET) != 0) |
if ((re->flags & PCRE_REQCHSET) != 0) |
| 4664 |
{ |
{ |
| 4665 |
req_byte = re->req_byte & 255; |
req_byte = re->req_byte & 255; |
| 4666 |
req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; |
req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; |
| 4676 |
for(;;) |
for(;;) |
| 4677 |
{ |
{ |
| 4678 |
USPTR save_end_subject = end_subject; |
USPTR save_end_subject = end_subject; |
| 4679 |
|
USPTR new_start_match; |
| 4680 |
|
|
| 4681 |
/* Reset the maximum number of extractions we might see. */ |
/* Reset the maximum number of extractions we might see. */ |
| 4682 |
|
|
| 4696 |
if (firstline) |
if (firstline) |
| 4697 |
{ |
{ |
| 4698 |
USPTR t = start_match; |
USPTR t = start_match; |
| 4699 |
|
#ifdef SUPPORT_UTF8 |
| 4700 |
|
if (utf8) |
| 4701 |
|
{ |
| 4702 |
|
while (t < md->end_subject && !IS_NEWLINE(t)) |
| 4703 |
|
{ |
| 4704 |
|
t++; |
| 4705 |
|
while (t < end_subject && (*t & 0xc0) == 0x80) t++; |
| 4706 |
|
} |
| 4707 |
|
} |
| 4708 |
|
else |
| 4709 |
|
#endif |
| 4710 |
while (t < md->end_subject && !IS_NEWLINE(t)) t++; |
while (t < md->end_subject && !IS_NEWLINE(t)) t++; |
| 4711 |
end_subject = t; |
end_subject = t; |
| 4712 |
} |
} |
| 4713 |
|
|
| 4714 |
/* Now test for a unique first byte */ |
/* Now advance to a unique first byte if there is one. */ |
| 4715 |
|
|
| 4716 |
if (first_byte >= 0) |
if (first_byte >= 0) |
| 4717 |
{ |
{ |
| 4718 |
if (first_byte_caseless) |
if (first_byte_caseless) |
| 4719 |
while (start_match < end_subject && |
while (start_match < end_subject && md->lcc[*start_match] != first_byte) |
|
md->lcc[*start_match] != first_byte) |
|
| 4720 |
start_match++; |
start_match++; |
| 4721 |
else |
else |
| 4722 |
while (start_match < end_subject && *start_match != first_byte) |
while (start_match < end_subject && *start_match != first_byte) |
| 4723 |
start_match++; |
start_match++; |
| 4724 |
} |
} |
| 4725 |
|
|
| 4726 |
/* Or to just after a linebreak for a multiline match if possible */ |
/* Or to just after a linebreak for a multiline match */ |
| 4727 |
|
|
| 4728 |
else if (startline) |
else if (startline) |
| 4729 |
{ |
{ |
| 4730 |
if (start_match > md->start_subject + start_offset) |
if (start_match > md->start_subject + start_offset) |
| 4731 |
{ |
{ |
| 4732 |
while (start_match <= end_subject && !WAS_NEWLINE(start_match)) |
#ifdef SUPPORT_UTF8 |
| 4733 |
|
if (utf8) |
| 4734 |
|
{ |
| 4735 |
|
while (start_match < end_subject && !WAS_NEWLINE(start_match)) |
| 4736 |
|
{ |
| 4737 |
|
start_match++; |
| 4738 |
|
while(start_match < end_subject && (*start_match & 0xc0) == 0x80) |
| 4739 |
|
start_match++; |
| 4740 |
|
} |
| 4741 |
|
} |
| 4742 |
|
else |
| 4743 |
|
#endif |
| 4744 |
|
while (start_match < end_subject && !WAS_NEWLINE(start_match)) |
| 4745 |
start_match++; |
start_match++; |
| 4746 |
|
|
| 4747 |
/* If we have just passed a CR and the newline option is ANY or ANYCRLF, |
/* If we have just passed a CR and the newline option is ANY or ANYCRLF, |
| 4748 |
and we are now at a LF, advance the match position by one more character. |
and we are now at a LF, advance the match position by one more character. |
| 4749 |
*/ |
*/ |
| 4756 |
} |
} |
| 4757 |
} |
} |
| 4758 |
|
|
| 4759 |
/* Or to a non-unique first char after study */ |
/* Or to a non-unique first byte after study */ |
| 4760 |
|
|
| 4761 |
else if (start_bits != NULL) |
else if (start_bits != NULL) |
| 4762 |
{ |
{ |
| 4763 |
while (start_match < end_subject) |
while (start_match < end_subject) |
| 4764 |
{ |
{ |
| 4765 |
register unsigned int c = *start_match; |
register unsigned int c = *start_match; |
| 4766 |
if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break; |
if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; |
| 4767 |
|
else break; |
| 4768 |
} |
} |
| 4769 |
} |
} |
| 4770 |
|
|
| 4839 |
} |
} |
| 4840 |
|
|
| 4841 |
/* OK, we can now run the match. */ |
/* OK, we can now run the match. */ |
| 4842 |
|
|
| 4843 |
md->start_match_ptr = start_match; /* Insurance */ |
md->start_match_ptr = start_match; |
| 4844 |
md->match_call_count = 0; |
md->match_call_count = 0; |
| 4845 |
rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0); |
rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0); |
| 4846 |
|
|
| 4847 |
/* Any return other than MATCH_NOMATCH breaks the loop. */ |
switch(rc) |
| 4848 |
|
{ |
| 4849 |
|
/* NOMATCH and PRUNE advance by one character. THEN at this level acts |
| 4850 |
|
exactly like PRUNE. */ |
| 4851 |
|
|
| 4852 |
|
case MATCH_NOMATCH: |
| 4853 |
|
case MATCH_PRUNE: |
| 4854 |
|
case MATCH_THEN: |
| 4855 |
|
new_start_match = start_match + 1; |
| 4856 |
|
#ifdef SUPPORT_UTF8 |
| 4857 |
|
if (utf8) |
| 4858 |
|
while(new_start_match < end_subject && (*new_start_match & 0xc0) == 0x80) |
| 4859 |
|
new_start_match++; |
| 4860 |
|
#endif |
| 4861 |
|
break; |
| 4862 |
|
|
| 4863 |
|
/* SKIP passes back the next starting point explicitly. */ |
| 4864 |
|
|
| 4865 |
|
case MATCH_SKIP: |
| 4866 |
|
new_start_match = md->start_match_ptr; |
| 4867 |
|
break; |
| 4868 |
|
|
| 4869 |
|
/* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */ |
| 4870 |
|
|
| 4871 |
if (rc != MATCH_NOMATCH) break; |
case MATCH_COMMIT: |
| 4872 |
|
rc = MATCH_NOMATCH; |
| 4873 |
|
goto ENDLOOP; |
| 4874 |
|
|
| 4875 |
|
/* Any other return is some kind of error. */ |
| 4876 |
|
|
| 4877 |
|
default: |
| 4878 |
|
goto ENDLOOP; |
| 4879 |
|
} |
| 4880 |
|
|
| 4881 |
|
/* Control reaches here for the various types of "no match at this point" |
| 4882 |
|
result. Reset the code to MATCH_NOMATCH for subsequent checking. */ |
| 4883 |
|
|
| 4884 |
|
rc = MATCH_NOMATCH; |
| 4885 |
|
|
| 4886 |
/* If PCRE_FIRSTLINE is set, the match must happen before or at the first |
/* If PCRE_FIRSTLINE is set, the match must happen before or at the first |
| 4887 |
newline in the subject (though it may continue over the newline). Therefore, |
newline in the subject (though it may continue over the newline). Therefore, |
| 4889 |
|
|
| 4890 |
if (firstline && IS_NEWLINE(start_match)) break; |
if (firstline && IS_NEWLINE(start_match)) break; |
| 4891 |
|
|
| 4892 |
/* Advance the match position by one character. */ |
/* Advance to new matching position */ |
| 4893 |
|
|
| 4894 |
start_match++; |
start_match = new_start_match; |
|
#ifdef SUPPORT_UTF8 |
|
|
if (utf8) |
|
|
while(start_match < end_subject && (*start_match & 0xc0) == 0x80) |
|
|
start_match++; |
|
|
#endif |
|
| 4895 |
|
|
| 4896 |
/* Break the loop if the pattern is anchored or if we have passed the end of |
/* Break the loop if the pattern is anchored or if we have passed the end of |
| 4897 |
the subject. */ |
the subject. */ |
| 4898 |
|
|
| 4899 |
if (anchored || start_match > end_subject) break; |
if (anchored || start_match > end_subject) break; |
| 4900 |
|
|
| 4901 |
/* If we have just passed a CR and the newline option is CRLF or ANY or |
/* If we have just passed a CR and we are now at a LF, and the pattern does |
| 4902 |
ANYCRLF, and we are now at a LF, advance the match position by one more |
not contain any explicit matches for \r or \n, and the newline option is CRLF |
| 4903 |
character. */ |
or ANY or ANYCRLF, advance the match position by one more character. */ |
| 4904 |
|
|
| 4905 |
if (start_match[-1] == '\r' && |
if (start_match[-1] == '\r' && |
| 4906 |
(md->nltype == NLTYPE_ANY || |
start_match < end_subject && |
| 4907 |
md->nltype == NLTYPE_ANYCRLF || |
*start_match == '\n' && |
| 4908 |
md->nllen == 2) && |
(re->flags & PCRE_HASCRORLF) == 0 && |
| 4909 |
start_match < end_subject && |
(md->nltype == NLTYPE_ANY || |
| 4910 |
*start_match == '\n') |
md->nltype == NLTYPE_ANYCRLF || |
| 4911 |
|
md->nllen == 2)) |
| 4912 |
start_match++; |
start_match++; |
| 4913 |
|
|
| 4914 |
} /* End of for(;;) "bumpalong" loop */ |
} /* End of for(;;) "bumpalong" loop */ |
| 4918 |
/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping |
/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping |
| 4919 |
conditions is true: |
conditions is true: |
| 4920 |
|
|
| 4921 |
(1) The pattern is anchored; |
(1) The pattern is anchored or the match was failed by (*COMMIT); |
| 4922 |
|
|
| 4923 |
(2) We are past the end of the subject; |
(2) We are past the end of the subject; |
| 4924 |
|
|
| 4933 |
certain parts of the pattern were not used, even though there are more |
certain parts of the pattern were not used, even though there are more |
| 4934 |
capturing parentheses than vector slots. */ |
capturing parentheses than vector slots. */ |
| 4935 |
|
|
| 4936 |
|
ENDLOOP: |
| 4937 |
|
|
| 4938 |
if (rc == MATCH_MATCH) |
if (rc == MATCH_MATCH) |
| 4939 |
{ |
{ |
| 4940 |
if (using_temporary_offsets) |
if (using_temporary_offsets) |