version 1.1.1.3, 2012/10/09 09:19:17
|
version 1.1.1.4, 2013/07/22 08:25:55
|
Line 7 and semantics are as close as possible to those of the
|
Line 7 and semantics are as close as possible to those of the
|
below for why this module is different). |
below for why this module is different). |
|
|
Written by Philip Hazel |
Written by Philip Hazel |
Copyright (c) 1997-2012 University of Cambridge | Copyright (c) 1997-2013 University of Cambridge |
|
|
----------------------------------------------------------------------------- |
----------------------------------------------------------------------------- |
Redistribution and use in source and binary forms, with or without |
Redistribution and use in source and binary forms, with or without |
Line 302 Returns: nothing
|
Line 302 Returns: nothing
|
static void |
static void |
pchars(const pcre_uchar *p, int length, FILE *f) |
pchars(const pcre_uchar *p, int length, FILE *f) |
{ |
{ |
int c; | pcre_uint32 c; |
while (length-- > 0) |
while (length-- > 0) |
{ |
{ |
if (isprint(c = *(p++))) |
if (isprint(c = *(p++))) |
fprintf(f, "%c", c); |
fprintf(f, "%c", c); |
else |
else |
fprintf(f, "\\x%02x", c); | fprintf(f, "\\x{%02x}", c); |
} |
} |
} |
} |
#endif |
#endif |
Line 571 for (;;)
|
Line 571 for (;;)
|
{ |
{ |
int i, j; |
int i, j; |
int clen, dlen; |
int clen, dlen; |
unsigned int c, d; | pcre_uint32 c, d; |
int forced_fail = 0; |
int forced_fail = 0; |
BOOL partial_newline = FALSE; |
BOOL partial_newline = FALSE; |
BOOL could_continue = reset_could_continue; |
BOOL could_continue = reset_could_continue; |
Line 613 for (;;)
|
Line 613 for (;;)
|
{ |
{ |
clen = 1; /* Number of data items in the character */ |
clen = 1; /* Number of data items in the character */ |
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
if (utf) { GETCHARLEN(c, ptr, clen); } else | GETCHARLENTEST(c, ptr, clen); |
#endif /* SUPPORT_UTF */ | #else |
c = *ptr; |
c = *ptr; |
|
#endif /* SUPPORT_UTF */ |
} |
} |
else |
else |
{ |
{ |
Line 634 for (;;)
|
Line 635 for (;;)
|
BOOL caseless = FALSE; |
BOOL caseless = FALSE; |
const pcre_uchar *code; |
const pcre_uchar *code; |
int state_offset = current_state->offset; |
int state_offset = current_state->offset; |
int count, codevalue, rrc; | int codevalue, rrc; |
| int count; |
|
|
#ifdef PCRE_DEBUG |
#ifdef PCRE_DEBUG |
printf ("%.*sProcessing state %d c=", rlevel*2-2, SP, state_offset); |
printf ("%.*sProcessing state %d c=", rlevel*2-2, SP, state_offset); |
Line 1007 for (;;)
|
Line 1009 for (;;)
|
{ |
{ |
const pcre_uchar *temp = ptr - 1; |
const pcre_uchar *temp = ptr - 1; |
if (temp < md->start_used_ptr) md->start_used_ptr = temp; |
if (temp < md->start_used_ptr) md->start_used_ptr = temp; |
#ifdef SUPPORT_UTF | #if defined SUPPORT_UTF && !defined COMPILE_PCRE32 |
if (utf) { BACKCHAR(temp); } |
if (utf) { BACKCHAR(temp); } |
#endif |
#endif |
GETCHARTEST(d, temp); |
GETCHARTEST(d, temp); |
Line 1060 for (;;)
|
Line 1062 for (;;)
|
if (clen > 0) |
if (clen > 0) |
{ |
{ |
BOOL OK; |
BOOL OK; |
|
const pcre_uint32 *cp; |
const ucd_record * prop = GET_UCD(c); |
const ucd_record * prop = GET_UCD(c); |
switch(code[1]) |
switch(code[1]) |
{ |
{ |
Line 1108 for (;;)
|
Line 1111 for (;;)
|
c == CHAR_UNDERSCORE; |
c == CHAR_UNDERSCORE; |
break; |
break; |
|
|
|
case PT_CLIST: |
|
cp = PRIV(ucd_caseless_sets) + code[2]; |
|
for (;;) |
|
{ |
|
if (c < *cp) { OK = FALSE; break; } |
|
if (c == *cp++) { OK = TRUE; break; } |
|
} |
|
break; |
|
|
|
case PT_UCNC: |
|
OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || |
|
c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || |
|
c >= 0xe000; |
|
break; |
|
|
/* Should never occur, but keep compilers from grumbling. */ |
/* Should never occur, but keep compilers from grumbling. */ |
|
|
default: |
default: |
Line 1237 for (;;)
|
Line 1255 for (;;)
|
(d != OP_ANY || !IS_NEWLINE(ptr)) && |
(d != OP_ANY || !IS_NEWLINE(ptr)) && |
((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) |
((ctypes[c] & toptable1[d]) ^ toptable2[d]) != 0)) |
{ |
{ |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW(state_offset + 1 + IMM2_SIZE + 1, 0); } |
{ ADD_NEW(state_offset + 1 + IMM2_SIZE + 1, 0); } |
else |
else |
{ ADD_NEW(state_offset, count); } |
{ ADD_NEW(state_offset, count); } |
Line 1271 for (;;)
|
Line 1289 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW(state_offset + 2 + IMM2_SIZE, 0); } |
{ ADD_NEW(state_offset + 2 + IMM2_SIZE, 0); } |
else |
else |
{ ADD_NEW(state_offset, count); } |
{ ADD_NEW(state_offset, count); } |
Line 1294 for (;;)
|
Line 1312 for (;;)
|
if (clen > 0) |
if (clen > 0) |
{ |
{ |
BOOL OK; |
BOOL OK; |
|
const pcre_uint32 *cp; |
const ucd_record * prop = GET_UCD(c); |
const ucd_record * prop = GET_UCD(c); |
switch(code[2]) |
switch(code[2]) |
{ |
{ |
Line 1342 for (;;)
|
Line 1361 for (;;)
|
c == CHAR_UNDERSCORE; |
c == CHAR_UNDERSCORE; |
break; |
break; |
|
|
|
case PT_CLIST: |
|
cp = PRIV(ucd_caseless_sets) + code[3]; |
|
for (;;) |
|
{ |
|
if (c < *cp) { OK = FALSE; break; } |
|
if (c == *cp++) { OK = TRUE; break; } |
|
} |
|
break; |
|
|
|
case PT_UCNC: |
|
OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || |
|
c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || |
|
c >= 0xe000; |
|
break; |
|
|
/* Should never occur, but keep compilers from grumbling. */ |
/* Should never occur, but keep compilers from grumbling. */ |
|
|
default: |
default: |
Line 1368 for (;;)
|
Line 1402 for (;;)
|
case OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS: |
case OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS: |
count = current_state->count; /* Already matched */ |
count = current_state->count; /* Already matched */ |
if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } |
if (count > 0) { ADD_ACTIVE(state_offset + 2, 0); } |
if (clen > 0 && UCD_CATEGORY(c) != ucp_M) | if (clen > 0) |
{ |
{ |
|
int lgb, rgb; |
const pcre_uchar *nptr = ptr + clen; |
const pcre_uchar *nptr = ptr + clen; |
int ncount = 0; |
int ncount = 0; |
if (count > 0 && codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS) |
if (count > 0 && codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSPLUS) |
Line 1377 for (;;)
|
Line 1412 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
|
lgb = UCD_GRAPHBREAK(c); |
while (nptr < end_subject) |
while (nptr < end_subject) |
{ |
{ |
int nd; | dlen = 1; |
int ndlen = 1; | if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } |
GETCHARLEN(nd, nptr, ndlen); | rgb = UCD_GRAPHBREAK(d); |
if (UCD_CATEGORY(nd) != ucp_M) break; | if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; |
ncount++; |
ncount++; |
nptr += ndlen; | lgb = rgb; |
| nptr += dlen; |
} |
} |
count++; |
count++; |
ADD_NEW_DATA(-state_offset, count, ncount); |
ADD_NEW_DATA(-state_offset, count, ncount); |
Line 1403 for (;;)
|
Line 1440 for (;;)
|
int ncount = 0; |
int ncount = 0; |
switch (c) |
switch (c) |
{ |
{ |
case 0x000b: | case CHAR_VT: |
case 0x000c: | case CHAR_FF: |
case 0x0085: | case CHAR_NEL: |
| #ifndef EBCDIC |
case 0x2028: |
case 0x2028: |
case 0x2029: |
case 0x2029: |
|
#endif /* Not EBCDIC */ |
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; |
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; |
goto ANYNL01; |
goto ANYNL01; |
|
|
case 0x000d: | case CHAR_CR: |
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; | if (ptr + 1 < end_subject && RAWUCHARTEST(ptr + 1) == CHAR_LF) ncount = 1; |
/* Fall through */ |
/* Fall through */ |
|
|
ANYNL01: |
ANYNL01: |
case 0x000a: | case CHAR_LF: |
if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS) |
if (count > 0 && codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSPLUS) |
{ |
{ |
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
Line 1443 for (;;)
|
Line 1482 for (;;)
|
BOOL OK; |
BOOL OK; |
switch (c) |
switch (c) |
{ |
{ |
case 0x000a: | VSPACE_CASES: |
case 0x000b: | |
case 0x000c: | |
case 0x000d: | |
case 0x0085: | |
case 0x2028: | |
case 0x2029: | |
OK = TRUE; |
OK = TRUE; |
break; |
break; |
|
|
Line 1482 for (;;)
|
Line 1515 for (;;)
|
BOOL OK; |
BOOL OK; |
switch (c) |
switch (c) |
{ |
{ |
case 0x09: /* HT */ | HSPACE_CASES: |
case 0x20: /* SPACE */ | |
case 0xa0: /* NBSP */ | |
case 0x1680: /* OGHAM SPACE MARK */ | |
case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ | |
case 0x2000: /* EN QUAD */ | |
case 0x2001: /* EM QUAD */ | |
case 0x2002: /* EN SPACE */ | |
case 0x2003: /* EM SPACE */ | |
case 0x2004: /* THREE-PER-EM SPACE */ | |
case 0x2005: /* FOUR-PER-EM SPACE */ | |
case 0x2006: /* SIX-PER-EM SPACE */ | |
case 0x2007: /* FIGURE SPACE */ | |
case 0x2008: /* PUNCTUATION SPACE */ | |
case 0x2009: /* THIN SPACE */ | |
case 0x200A: /* HAIR SPACE */ | |
case 0x202f: /* NARROW NO-BREAK SPACE */ | |
case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ | |
case 0x3000: /* IDEOGRAPHIC SPACE */ | |
OK = TRUE; |
OK = TRUE; |
break; |
break; |
|
|
Line 1541 for (;;)
|
Line 1556 for (;;)
|
if (clen > 0) |
if (clen > 0) |
{ |
{ |
BOOL OK; |
BOOL OK; |
|
const pcre_uint32 *cp; |
const ucd_record * prop = GET_UCD(c); |
const ucd_record * prop = GET_UCD(c); |
switch(code[2]) |
switch(code[2]) |
{ |
{ |
Line 1589 for (;;)
|
Line 1605 for (;;)
|
c == CHAR_UNDERSCORE; |
c == CHAR_UNDERSCORE; |
break; |
break; |
|
|
|
case PT_CLIST: |
|
cp = PRIV(ucd_caseless_sets) + code[3]; |
|
for (;;) |
|
{ |
|
if (c < *cp) { OK = FALSE; break; } |
|
if (c == *cp++) { OK = TRUE; break; } |
|
} |
|
break; |
|
|
|
case PT_UCNC: |
|
OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || |
|
c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || |
|
c >= 0xe000; |
|
break; |
|
|
/* Should never occur, but keep compilers from grumbling. */ |
/* Should never occur, but keep compilers from grumbling. */ |
|
|
default: |
default: |
Line 1624 for (;;)
|
Line 1655 for (;;)
|
QS2: |
QS2: |
|
|
ADD_ACTIVE(state_offset + 2, 0); |
ADD_ACTIVE(state_offset + 2, 0); |
if (clen > 0 && UCD_CATEGORY(c) != ucp_M) | if (clen > 0) |
{ |
{ |
|
int lgb, rgb; |
const pcre_uchar *nptr = ptr + clen; |
const pcre_uchar *nptr = ptr + clen; |
int ncount = 0; |
int ncount = 0; |
if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR || |
if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSSTAR || |
Line 1634 for (;;)
|
Line 1666 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
|
lgb = UCD_GRAPHBREAK(c); |
while (nptr < end_subject) |
while (nptr < end_subject) |
{ |
{ |
int nd; | dlen = 1; |
int ndlen = 1; | if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } |
GETCHARLEN(nd, nptr, ndlen); | rgb = UCD_GRAPHBREAK(d); |
if (UCD_CATEGORY(nd) != ucp_M) break; | if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; |
ncount++; |
ncount++; |
nptr += ndlen; | lgb = rgb; |
| nptr += dlen; |
} |
} |
ADD_NEW_DATA(-(state_offset + count), 0, ncount); |
ADD_NEW_DATA(-(state_offset + count), 0, ncount); |
} |
} |
Line 1667 for (;;)
|
Line 1701 for (;;)
|
int ncount = 0; |
int ncount = 0; |
switch (c) |
switch (c) |
{ |
{ |
case 0x000b: | case CHAR_VT: |
case 0x000c: | case CHAR_FF: |
case 0x0085: | case CHAR_NEL: |
| #ifndef EBCDIC |
case 0x2028: |
case 0x2028: |
case 0x2029: |
case 0x2029: |
|
#endif /* Not EBCDIC */ |
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; |
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; |
goto ANYNL02; |
goto ANYNL02; |
|
|
case 0x000d: | case CHAR_CR: |
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; | if (ptr + 1 < end_subject && RAWUCHARTEST(ptr + 1) == CHAR_LF) ncount = 1; |
/* Fall through */ |
/* Fall through */ |
|
|
ANYNL02: |
ANYNL02: |
case 0x000a: | case CHAR_LF: |
if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR || |
if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSSTAR || |
codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY) |
codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSQUERY) |
{ |
{ |
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
ADD_NEW_DATA(-(state_offset + count), 0, ncount); | ADD_NEW_DATA(-(state_offset + (int)count), 0, ncount); |
break; |
break; |
|
|
default: |
default: |
Line 1715 for (;;)
|
Line 1751 for (;;)
|
BOOL OK; |
BOOL OK; |
switch (c) |
switch (c) |
{ |
{ |
case 0x000a: | VSPACE_CASES: |
case 0x000b: | |
case 0x000c: | |
case 0x000d: | |
case 0x0085: | |
case 0x2028: | |
case 0x2029: | |
OK = TRUE; |
OK = TRUE; |
break; |
break; |
|
|
Line 1737 for (;;)
|
Line 1767 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
ADD_NEW_DATA(-(state_offset + count), 0, 0); | ADD_NEW_DATA(-(state_offset + (int)count), 0, 0); |
} |
} |
} |
} |
break; |
break; |
Line 1761 for (;;)
|
Line 1791 for (;;)
|
BOOL OK; |
BOOL OK; |
switch (c) |
switch (c) |
{ |
{ |
case 0x09: /* HT */ | HSPACE_CASES: |
case 0x20: /* SPACE */ | |
case 0xa0: /* NBSP */ | |
case 0x1680: /* OGHAM SPACE MARK */ | |
case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ | |
case 0x2000: /* EN QUAD */ | |
case 0x2001: /* EM QUAD */ | |
case 0x2002: /* EN SPACE */ | |
case 0x2003: /* EM SPACE */ | |
case 0x2004: /* THREE-PER-EM SPACE */ | |
case 0x2005: /* FOUR-PER-EM SPACE */ | |
case 0x2006: /* SIX-PER-EM SPACE */ | |
case 0x2007: /* FIGURE SPACE */ | |
case 0x2008: /* PUNCTUATION SPACE */ | |
case 0x2009: /* THIN SPACE */ | |
case 0x200A: /* HAIR SPACE */ | |
case 0x202f: /* NARROW NO-BREAK SPACE */ | |
case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ | |
case 0x3000: /* IDEOGRAPHIC SPACE */ | |
OK = TRUE; |
OK = TRUE; |
break; |
break; |
|
|
Line 1796 for (;;)
|
Line 1808 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
ADD_NEW_DATA(-(state_offset + count), 0, 0); | ADD_NEW_DATA(-(state_offset + (int)count), 0, 0); |
} |
} |
} |
} |
break; |
break; |
Line 1813 for (;;)
|
Line 1825 for (;;)
|
if (clen > 0) |
if (clen > 0) |
{ |
{ |
BOOL OK; |
BOOL OK; |
|
const pcre_uint32 *cp; |
const ucd_record * prop = GET_UCD(c); |
const ucd_record * prop = GET_UCD(c); |
switch(code[1 + IMM2_SIZE + 1]) |
switch(code[1 + IMM2_SIZE + 1]) |
{ |
{ |
Line 1861 for (;;)
|
Line 1874 for (;;)
|
c == CHAR_UNDERSCORE; |
c == CHAR_UNDERSCORE; |
break; |
break; |
|
|
|
case PT_CLIST: |
|
cp = PRIV(ucd_caseless_sets) + code[1 + IMM2_SIZE + 2]; |
|
for (;;) |
|
{ |
|
if (c < *cp) { OK = FALSE; break; } |
|
if (c == *cp++) { OK = TRUE; break; } |
|
} |
|
break; |
|
|
|
case PT_UCNC: |
|
OK = c == CHAR_DOLLAR_SIGN || c == CHAR_COMMERCIAL_AT || |
|
c == CHAR_GRAVE_ACCENT || (c >= 0xa0 && c <= 0xd7ff) || |
|
c >= 0xe000; |
|
break; |
|
|
/* Should never occur, but keep compilers from grumbling. */ |
/* Should never occur, but keep compilers from grumbling. */ |
|
|
default: |
default: |
Line 1875 for (;;)
|
Line 1903 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW(state_offset + 1 + IMM2_SIZE + 3, 0); } |
{ ADD_NEW(state_offset + 1 + IMM2_SIZE + 3, 0); } |
else |
else |
{ ADD_NEW(state_offset, count); } |
{ ADD_NEW(state_offset, count); } |
Line 1891 for (;;)
|
Line 1919 for (;;)
|
if (codevalue != OP_EXTUNI_EXTRA + OP_TYPEEXACT) |
if (codevalue != OP_EXTUNI_EXTRA + OP_TYPEEXACT) |
{ ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } |
{ ADD_ACTIVE(state_offset + 2 + IMM2_SIZE, 0); } |
count = current_state->count; /* Number already matched */ |
count = current_state->count; /* Number already matched */ |
if (clen > 0 && UCD_CATEGORY(c) != ucp_M) | if (clen > 0) |
{ |
{ |
|
int lgb, rgb; |
const pcre_uchar *nptr = ptr + clen; |
const pcre_uchar *nptr = ptr + clen; |
int ncount = 0; |
int ncount = 0; |
if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO) |
if (codevalue == OP_EXTUNI_EXTRA + OP_TYPEPOSUPTO) |
Line 1900 for (;;)
|
Line 1929 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
|
lgb = UCD_GRAPHBREAK(c); |
while (nptr < end_subject) |
while (nptr < end_subject) |
{ |
{ |
int nd; | dlen = 1; |
int ndlen = 1; | if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } |
GETCHARLEN(nd, nptr, ndlen); | rgb = UCD_GRAPHBREAK(d); |
if (UCD_CATEGORY(nd) != ucp_M) break; | if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; |
ncount++; |
ncount++; |
nptr += ndlen; | lgb = rgb; |
| nptr += dlen; |
} |
} |
if (nptr >= end_subject && (md->moptions & PCRE_PARTIAL_HARD) != 0) |
if (nptr >= end_subject && (md->moptions & PCRE_PARTIAL_HARD) != 0) |
reset_could_continue = TRUE; |
reset_could_continue = TRUE; |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, ncount); } |
{ ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, ncount); } |
else |
else |
{ ADD_NEW_DATA(-state_offset, count, ncount); } |
{ ADD_NEW_DATA(-state_offset, count, ncount); } |
Line 1932 for (;;)
|
Line 1963 for (;;)
|
int ncount = 0; |
int ncount = 0; |
switch (c) |
switch (c) |
{ |
{ |
case 0x000b: | case CHAR_VT: |
case 0x000c: | case CHAR_FF: |
case 0x0085: | case CHAR_NEL: |
| #ifndef EBCDIC |
case 0x2028: |
case 0x2028: |
case 0x2029: |
case 0x2029: |
|
#endif /* Not EBCDIC */ |
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; |
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; |
goto ANYNL03; |
goto ANYNL03; |
|
|
case 0x000d: | case CHAR_CR: |
if (ptr + 1 < end_subject && ptr[1] == 0x0a) ncount = 1; | if (ptr + 1 < end_subject && RAWUCHARTEST(ptr + 1) == CHAR_LF) ncount = 1; |
/* Fall through */ |
/* Fall through */ |
|
|
ANYNL03: |
ANYNL03: |
case 0x000a: | case CHAR_LF: |
if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO) |
if (codevalue == OP_ANYNL_EXTRA + OP_TYPEPOSUPTO) |
{ |
{ |
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, ncount); } |
{ ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, ncount); } |
else |
else |
{ ADD_NEW_DATA(-state_offset, count, ncount); } |
{ ADD_NEW_DATA(-state_offset, count, ncount); } |
Line 1976 for (;;)
|
Line 2009 for (;;)
|
BOOL OK; |
BOOL OK; |
switch (c) |
switch (c) |
{ |
{ |
case 0x000a: | VSPACE_CASES: |
case 0x000b: | |
case 0x000c: | |
case 0x000d: | |
case 0x0085: | |
case 0x2028: | |
case 0x2029: | |
OK = TRUE; |
OK = TRUE; |
break; |
break; |
|
|
Line 1997 for (;;)
|
Line 2024 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, 0); } |
{ ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, 0); } |
else |
else |
{ ADD_NEW_DATA(-state_offset, count, 0); } |
{ ADD_NEW_DATA(-state_offset, count, 0); } |
Line 2018 for (;;)
|
Line 2045 for (;;)
|
BOOL OK; |
BOOL OK; |
switch (c) |
switch (c) |
{ |
{ |
case 0x09: /* HT */ | HSPACE_CASES: |
case 0x20: /* SPACE */ | |
case 0xa0: /* NBSP */ | |
case 0x1680: /* OGHAM SPACE MARK */ | |
case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ | |
case 0x2000: /* EN QUAD */ | |
case 0x2001: /* EM QUAD */ | |
case 0x2002: /* EN SPACE */ | |
case 0x2003: /* EM SPACE */ | |
case 0x2004: /* THREE-PER-EM SPACE */ | |
case 0x2005: /* FOUR-PER-EM SPACE */ | |
case 0x2006: /* SIX-PER-EM SPACE */ | |
case 0x2007: /* FIGURE SPACE */ | |
case 0x2008: /* PUNCTUATION SPACE */ | |
case 0x2009: /* THIN SPACE */ | |
case 0x200A: /* HAIR SPACE */ | |
case 0x202f: /* NARROW NO-BREAK SPACE */ | |
case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ | |
case 0x3000: /* IDEOGRAPHIC SPACE */ | |
OK = TRUE; |
OK = TRUE; |
break; |
break; |
|
|
Line 2052 for (;;)
|
Line 2061 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, 0); } |
{ ADD_NEW_DATA(-(state_offset + 2 + IMM2_SIZE), 0, 0); } |
else |
else |
{ ADD_NEW_DATA(-state_offset, count, 0); } |
{ ADD_NEW_DATA(-state_offset, count, 0); } |
Line 2112 for (;;)
|
Line 2121 for (;;)
|
to wait for them to pass before continuing. */ |
to wait for them to pass before continuing. */ |
|
|
case OP_EXTUNI: |
case OP_EXTUNI: |
if (clen > 0 && UCD_CATEGORY(c) != ucp_M) | if (clen > 0) |
{ |
{ |
|
int lgb, rgb; |
const pcre_uchar *nptr = ptr + clen; |
const pcre_uchar *nptr = ptr + clen; |
int ncount = 0; |
int ncount = 0; |
|
lgb = UCD_GRAPHBREAK(c); |
while (nptr < end_subject) |
while (nptr < end_subject) |
{ |
{ |
int nclen = 1; | dlen = 1; |
GETCHARLEN(c, nptr, nclen); | if (!utf) d = *nptr; else { GETCHARLEN(d, nptr, dlen); } |
if (UCD_CATEGORY(c) != ucp_M) break; | rgb = UCD_GRAPHBREAK(d); |
| if ((PRIV(ucp_gbtable)[lgb] & (1 << rgb)) == 0) break; |
ncount++; |
ncount++; |
nptr += nclen; | lgb = rgb; |
| nptr += dlen; |
} |
} |
if (nptr >= end_subject && (md->moptions & PCRE_PARTIAL_HARD) != 0) |
if (nptr >= end_subject && (md->moptions & PCRE_PARTIAL_HARD) != 0) |
reset_could_continue = TRUE; |
reset_could_continue = TRUE; |
Line 2139 for (;;)
|
Line 2152 for (;;)
|
case OP_ANYNL: |
case OP_ANYNL: |
if (clen > 0) switch(c) |
if (clen > 0) switch(c) |
{ |
{ |
case 0x000b: | case CHAR_VT: |
case 0x000c: | case CHAR_FF: |
case 0x0085: | case CHAR_NEL: |
| #ifndef EBCDIC |
case 0x2028: |
case 0x2028: |
case 0x2029: |
case 0x2029: |
|
#endif /* Not EBCDIC */ |
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; |
if ((md->moptions & PCRE_BSR_ANYCRLF) != 0) break; |
|
|
case 0x000a: | case CHAR_LF: |
ADD_NEW(state_offset + 1, 0); |
ADD_NEW(state_offset + 1, 0); |
break; |
break; |
|
|
case 0x000d: | case CHAR_CR: |
if (ptr + 1 >= end_subject) |
if (ptr + 1 >= end_subject) |
{ |
{ |
ADD_NEW(state_offset + 1, 0); |
ADD_NEW(state_offset + 1, 0); |
if ((md->moptions & PCRE_PARTIAL_HARD) != 0) |
if ((md->moptions & PCRE_PARTIAL_HARD) != 0) |
reset_could_continue = TRUE; |
reset_could_continue = TRUE; |
} |
} |
else if (ptr[1] == 0x0a) | else if (RAWUCHARTEST(ptr + 1) == CHAR_LF) |
{ |
{ |
ADD_NEW_DATA(-(state_offset + 1), 0, 1); |
ADD_NEW_DATA(-(state_offset + 1), 0, 1); |
} |
} |
Line 2173 for (;;)
|
Line 2188 for (;;)
|
case OP_NOT_VSPACE: |
case OP_NOT_VSPACE: |
if (clen > 0) switch(c) |
if (clen > 0) switch(c) |
{ |
{ |
case 0x000a: | VSPACE_CASES: |
case 0x000b: | |
case 0x000c: | |
case 0x000d: | |
case 0x0085: | |
case 0x2028: | |
case 0x2029: | |
break; |
break; |
|
|
default: |
default: |
Line 2192 for (;;)
|
Line 2201 for (;;)
|
case OP_VSPACE: |
case OP_VSPACE: |
if (clen > 0) switch(c) |
if (clen > 0) switch(c) |
{ |
{ |
case 0x000a: | VSPACE_CASES: |
case 0x000b: | |
case 0x000c: | |
case 0x000d: | |
case 0x0085: | |
case 0x2028: | |
case 0x2029: | |
ADD_NEW(state_offset + 1, 0); |
ADD_NEW(state_offset + 1, 0); |
break; |
break; |
|
|
default: break; | default: |
| break; |
} |
} |
break; |
break; |
|
|
Line 2210 for (;;)
|
Line 2214 for (;;)
|
case OP_NOT_HSPACE: |
case OP_NOT_HSPACE: |
if (clen > 0) switch(c) |
if (clen > 0) switch(c) |
{ |
{ |
case 0x09: /* HT */ | HSPACE_CASES: |
case 0x20: /* SPACE */ | |
case 0xa0: /* NBSP */ | |
case 0x1680: /* OGHAM SPACE MARK */ | |
case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ | |
case 0x2000: /* EN QUAD */ | |
case 0x2001: /* EM QUAD */ | |
case 0x2002: /* EN SPACE */ | |
case 0x2003: /* EM SPACE */ | |
case 0x2004: /* THREE-PER-EM SPACE */ | |
case 0x2005: /* FOUR-PER-EM SPACE */ | |
case 0x2006: /* SIX-PER-EM SPACE */ | |
case 0x2007: /* FIGURE SPACE */ | |
case 0x2008: /* PUNCTUATION SPACE */ | |
case 0x2009: /* THIN SPACE */ | |
case 0x200A: /* HAIR SPACE */ | |
case 0x202f: /* NARROW NO-BREAK SPACE */ | |
case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ | |
case 0x3000: /* IDEOGRAPHIC SPACE */ | |
break; |
break; |
|
|
default: |
default: |
Line 2241 for (;;)
|
Line 2227 for (;;)
|
case OP_HSPACE: |
case OP_HSPACE: |
if (clen > 0) switch(c) |
if (clen > 0) switch(c) |
{ |
{ |
case 0x09: /* HT */ | HSPACE_CASES: |
case 0x20: /* SPACE */ | |
case 0xa0: /* NBSP */ | |
case 0x1680: /* OGHAM SPACE MARK */ | |
case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ | |
case 0x2000: /* EN QUAD */ | |
case 0x2001: /* EM QUAD */ | |
case 0x2002: /* EN SPACE */ | |
case 0x2003: /* EM SPACE */ | |
case 0x2004: /* THREE-PER-EM SPACE */ | |
case 0x2005: /* FOUR-PER-EM SPACE */ | |
case 0x2006: /* SIX-PER-EM SPACE */ | |
case 0x2007: /* FIGURE SPACE */ | |
case 0x2008: /* PUNCTUATION SPACE */ | |
case 0x2009: /* THIN SPACE */ | |
case 0x200A: /* HAIR SPACE */ | |
case 0x202f: /* NARROW NO-BREAK SPACE */ | |
case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ | |
case 0x3000: /* IDEOGRAPHIC SPACE */ | |
ADD_NEW(state_offset + 1, 0); |
ADD_NEW(state_offset + 1, 0); |
break; |
break; |
|
|
|
default: |
|
break; |
} |
} |
break; |
break; |
|
|
Line 2315 for (;;)
|
Line 2286 for (;;)
|
if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); } |
if (count > 0) { ADD_ACTIVE(state_offset + dlen + 1, 0); } |
if (clen > 0) |
if (clen > 0) |
{ |
{ |
unsigned int otherd = NOTACHAR; | pcre_uint32 otherd = NOTACHAR; |
if (caseless) |
if (caseless) |
{ |
{ |
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
Line 2362 for (;;)
|
Line 2333 for (;;)
|
ADD_ACTIVE(state_offset + dlen + 1, 0); |
ADD_ACTIVE(state_offset + dlen + 1, 0); |
if (clen > 0) |
if (clen > 0) |
{ |
{ |
unsigned int otherd = NOTACHAR; | pcre_uint32 otherd = NOTACHAR; |
if (caseless) |
if (caseless) |
{ |
{ |
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
Line 2407 for (;;)
|
Line 2378 for (;;)
|
ADD_ACTIVE(state_offset + dlen + 1, 0); |
ADD_ACTIVE(state_offset + dlen + 1, 0); |
if (clen > 0) |
if (clen > 0) |
{ |
{ |
unsigned int otherd = NOTACHAR; | pcre_uint32 otherd = NOTACHAR; |
if (caseless) |
if (caseless) |
{ |
{ |
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
Line 2444 for (;;)
|
Line 2415 for (;;)
|
count = current_state->count; /* Number already matched */ |
count = current_state->count; /* Number already matched */ |
if (clen > 0) |
if (clen > 0) |
{ |
{ |
unsigned int otherd = NOTACHAR; | pcre_uint32 otherd = NOTACHAR; |
if (caseless) |
if (caseless) |
{ |
{ |
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
Line 2460 for (;;)
|
Line 2431 for (;;)
|
} |
} |
if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) |
if ((c == d || c == otherd) == (codevalue < OP_NOTSTAR)) |
{ |
{ |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW(state_offset + dlen + 1 + IMM2_SIZE, 0); } |
{ ADD_NEW(state_offset + dlen + 1 + IMM2_SIZE, 0); } |
else |
else |
{ ADD_NEW(state_offset, count); } |
{ ADD_NEW(state_offset, count); } |
Line 2488 for (;;)
|
Line 2459 for (;;)
|
count = current_state->count; /* Number already matched */ |
count = current_state->count; /* Number already matched */ |
if (clen > 0) |
if (clen > 0) |
{ |
{ |
unsigned int otherd = NOTACHAR; | pcre_uint32 otherd = NOTACHAR; |
if (caseless) |
if (caseless) |
{ |
{ |
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
Line 2509 for (;;)
|
Line 2480 for (;;)
|
active_count--; /* Remove non-match possibility */ |
active_count--; /* Remove non-match possibility */ |
next_active_state--; |
next_active_state--; |
} |
} |
if (++count >= GET2(code, 1)) | if (++count >= (int)GET2(code, 1)) |
{ ADD_NEW(state_offset + dlen + 1 + IMM2_SIZE, 0); } |
{ ADD_NEW(state_offset + dlen + 1 + IMM2_SIZE, 0); } |
else |
else |
{ ADD_NEW(state_offset, count); } |
{ ADD_NEW(state_offset, count); } |
Line 2582 for (;;)
|
Line 2553 for (;;)
|
case OP_CRRANGE: |
case OP_CRRANGE: |
case OP_CRMINRANGE: |
case OP_CRMINRANGE: |
count = current_state->count; /* Already matched */ |
count = current_state->count; /* Already matched */ |
if (count >= GET2(ecode, 1)) | if (count >= (int)GET2(ecode, 1)) |
{ ADD_ACTIVE(next_state_offset + 1 + 2 * IMM2_SIZE, 0); } |
{ ADD_ACTIVE(next_state_offset + 1 + 2 * IMM2_SIZE, 0); } |
if (isinclass) |
if (isinclass) |
{ |
{ |
int max = GET2(ecode, 1 + IMM2_SIZE); | int max = (int)GET2(ecode, 1 + IMM2_SIZE); |
if (++count >= max && max != 0) /* Max 0 => no limit */ |
if (++count >= max && max != 0) /* Max 0 => no limit */ |
{ ADD_NEW(next_state_offset + 1 + 2 * IMM2_SIZE, 0); } |
{ ADD_NEW(next_state_offset + 1 + 2 * IMM2_SIZE, 0); } |
else |
else |
Line 2662 for (;;)
|
Line 2633 for (;;)
|
cb.version = 1; /* Version 1 of the callout block */ |
cb.version = 1; /* Version 1 of the callout block */ |
cb.callout_number = code[LINK_SIZE+2]; |
cb.callout_number = code[LINK_SIZE+2]; |
cb.offset_vector = offsets; |
cb.offset_vector = offsets; |
#ifdef COMPILE_PCRE8 | #if defined COMPILE_PCRE8 |
cb.subject = (PCRE_SPTR)start_subject; |
cb.subject = (PCRE_SPTR)start_subject; |
#else | #elif defined COMPILE_PCRE16 |
cb.subject = (PCRE_SPTR16)start_subject; |
cb.subject = (PCRE_SPTR16)start_subject; |
|
#elif defined COMPILE_PCRE32 |
|
cb.subject = (PCRE_SPTR32)start_subject; |
#endif |
#endif |
cb.subject_length = (int)(end_subject - start_subject); |
cb.subject_length = (int)(end_subject - start_subject); |
cb.start_match = (int)(current_subject - start_subject); |
cb.start_match = (int)(current_subject - start_subject); |
Line 2796 for (;;)
|
Line 2769 for (;;)
|
for (rc = rc*2 - 2; rc >= 0; rc -= 2) |
for (rc = rc*2 - 2; rc >= 0; rc -= 2) |
{ |
{ |
int charcount = local_offsets[rc+1] - local_offsets[rc]; |
int charcount = local_offsets[rc+1] - local_offsets[rc]; |
#ifdef SUPPORT_UTF | #if defined SUPPORT_UTF && !defined COMPILE_PCRE32 |
if (utf) |
if (utf) |
{ |
{ |
const pcre_uchar *p = start_subject + local_offsets[rc]; |
const pcre_uchar *p = start_subject + local_offsets[rc]; |
Line 2900 for (;;)
|
Line 2873 for (;;)
|
const pcre_uchar *p = ptr; |
const pcre_uchar *p = ptr; |
const pcre_uchar *pp = local_ptr; |
const pcre_uchar *pp = local_ptr; |
charcount = (int)(pp - p); |
charcount = (int)(pp - p); |
#ifdef SUPPORT_UTF | #if defined SUPPORT_UTF && !defined COMPILE_PCRE32 |
if (utf) while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--; |
if (utf) while (p < pp) if (NOT_FIRSTCHAR(*p++)) charcount--; |
#endif |
#endif |
ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1)); |
ADD_NEW_DATA(-next_state_offset, 0, (charcount - 1)); |
Line 2982 for (;;)
|
Line 2955 for (;;)
|
} |
} |
else |
else |
{ |
{ |
#ifdef SUPPORT_UTF | #if defined SUPPORT_UTF && !defined COMPILE_PCRE32 |
if (utf) |
if (utf) |
{ |
{ |
const pcre_uchar *p = start_subject + local_offsets[0]; |
const pcre_uchar *p = start_subject + local_offsets[0]; |
Line 3011 for (;;)
|
Line 2984 for (;;)
|
cb.version = 1; /* Version 1 of the callout block */ |
cb.version = 1; /* Version 1 of the callout block */ |
cb.callout_number = code[1]; |
cb.callout_number = code[1]; |
cb.offset_vector = offsets; |
cb.offset_vector = offsets; |
#ifdef COMPILE_PCRE8 | #if defined COMPILE_PCRE8 |
cb.subject = (PCRE_SPTR)start_subject; |
cb.subject = (PCRE_SPTR)start_subject; |
#else | #elif defined COMPILE_PCRE16 |
cb.subject = (PCRE_SPTR16)start_subject; |
cb.subject = (PCRE_SPTR16)start_subject; |
|
#elif defined COMPILE_PCRE32 |
|
cb.subject = (PCRE_SPTR32)start_subject; |
#endif |
#endif |
cb.subject_length = (int)(end_subject - start_subject); |
cb.subject_length = (int)(end_subject - start_subject); |
cb.start_match = (int)(current_subject - start_subject); |
cb.start_match = (int)(current_subject - start_subject); |
Line 3072 for (;;)
|
Line 3047 for (;;)
|
ptr > md->start_used_ptr) /* Inspected non-empty string */ |
ptr > md->start_used_ptr) /* Inspected non-empty string */ |
) |
) |
) |
) |
{ |
|
if (offsetcount >= 2) |
|
{ |
|
offsets[0] = (int)(md->start_used_ptr - start_subject); |
|
offsets[1] = (int)(end_subject - start_subject); |
|
} |
|
match_count = PCRE_ERROR_PARTIAL; |
match_count = PCRE_ERROR_PARTIAL; |
} |
|
|
|
DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" |
DPRINTF(("%.*sEnd of internal_dfa_exec %d: returning %d\n" |
"%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, match_count, |
"%.*s---------------------\n\n", rlevel*2-2, SP, rlevel, match_count, |
rlevel*2-2, SP)); |
rlevel*2-2, SP)); |
Line 3130 Returns: > 0 => number of match offset pairs
|
Line 3097 Returns: > 0 => number of match offset pairs
|
< -1 => some kind of unexpected problem |
< -1 => some kind of unexpected problem |
*/ |
*/ |
|
|
#ifdef COMPILE_PCRE8 | #if defined COMPILE_PCRE8 |
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION |
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION |
pcre_dfa_exec(const pcre *argument_re, const pcre_extra *extra_data, |
pcre_dfa_exec(const pcre *argument_re, const pcre_extra *extra_data, |
const char *subject, int length, int start_offset, int options, int *offsets, |
const char *subject, int length, int start_offset, int options, int *offsets, |
int offsetcount, int *workspace, int wscount) |
int offsetcount, int *workspace, int wscount) |
#else | #elif defined COMPILE_PCRE16 |
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION |
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION |
pcre16_dfa_exec(const pcre16 *argument_re, const pcre16_extra *extra_data, |
pcre16_dfa_exec(const pcre16 *argument_re, const pcre16_extra *extra_data, |
PCRE_SPTR16 subject, int length, int start_offset, int options, int *offsets, |
PCRE_SPTR16 subject, int length, int start_offset, int options, int *offsets, |
int offsetcount, int *workspace, int wscount) |
int offsetcount, int *workspace, int wscount) |
|
#elif defined COMPILE_PCRE32 |
|
PCRE_EXP_DEFN int PCRE_CALL_CONVENTION |
|
pcre32_dfa_exec(const pcre32 *argument_re, const pcre32_extra *extra_data, |
|
PCRE_SPTR32 subject, int length, int start_offset, int options, int *offsets, |
|
int offsetcount, int *workspace, int wscount) |
#endif |
#endif |
{ |
{ |
REAL_PCRE *re = (REAL_PCRE *)argument_re; |
REAL_PCRE *re = (REAL_PCRE *)argument_re; |
Line 3166 if (re == NULL || subject == NULL || workspace == NULL
|
Line 3138 if (re == NULL || subject == NULL || workspace == NULL
|
(offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; |
(offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; |
if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; |
if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; |
if (wscount < 20) return PCRE_ERROR_DFA_WSSIZE; |
if (wscount < 20) return PCRE_ERROR_DFA_WSSIZE; |
|
if (length < 0) return PCRE_ERROR_BADLENGTH; |
if (start_offset < 0 || start_offset > length) return PCRE_ERROR_BADOFFSET; |
if (start_offset < 0 || start_offset > length) return PCRE_ERROR_BADOFFSET; |
|
|
/* Check that the first field in the block is the magic number. If it is not, |
/* Check that the first field in the block is the magic number. If it is not, |
Line 3214 end_subject = (const pcre_uchar *)subject + length;
|
Line 3187 end_subject = (const pcre_uchar *)subject + length;
|
req_char_ptr = current_subject - 1; |
req_char_ptr = current_subject - 1; |
|
|
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
/* PCRE_UTF16 has the same value as PCRE_UTF8. */ | /* PCRE_UTF(16|32) have the same value as PCRE_UTF8. */ |
utf = (re->options & PCRE_UTF8) != 0; |
utf = (re->options & PCRE_UTF8) != 0; |
#else |
#else |
utf = FALSE; |
utf = FALSE; |
Line 3300 if (utf && (options & PCRE_NO_UTF8_CHECK) == 0)
|
Line 3273 if (utf && (options & PCRE_NO_UTF8_CHECK) == 0)
|
offsets[0] = erroroffset; |
offsets[0] = erroroffset; |
offsets[1] = errorcode; |
offsets[1] = errorcode; |
} |
} |
return (errorcode <= PCRE_UTF8_ERR5 && (options & PCRE_PARTIAL_HARD) != 0)? | #if defined COMPILE_PCRE8 |
| return (errorcode <= PCRE_UTF8_ERR5 && (options & PCRE_PARTIAL_HARD) != 0) ? |
PCRE_ERROR_SHORTUTF8 : PCRE_ERROR_BADUTF8; |
PCRE_ERROR_SHORTUTF8 : PCRE_ERROR_BADUTF8; |
|
#elif defined COMPILE_PCRE16 |
|
return (errorcode <= PCRE_UTF16_ERR1 && (options & PCRE_PARTIAL_HARD) != 0) ? |
|
PCRE_ERROR_SHORTUTF16 : PCRE_ERROR_BADUTF16; |
|
#elif defined COMPILE_PCRE32 |
|
return PCRE_ERROR_BADUTF32; |
|
#endif |
} |
} |
|
#if defined COMPILE_PCRE8 || defined COMPILE_PCRE16 |
if (start_offset > 0 && start_offset < length && |
if (start_offset > 0 && start_offset < length && |
NOT_FIRSTCHAR(((PCRE_PUCHAR)subject)[start_offset])) |
NOT_FIRSTCHAR(((PCRE_PUCHAR)subject)[start_offset])) |
return PCRE_ERROR_BADUTF8_OFFSET; |
return PCRE_ERROR_BADUTF8_OFFSET; |
|
#endif |
} |
} |
#endif |
#endif |
|
|
Line 3415 for (;;)
|
Line 3397 for (;;)
|
if (has_first_char) |
if (has_first_char) |
{ |
{ |
if (first_char != first_char2) |
if (first_char != first_char2) |
|
{ |
|
pcre_uchar csc; |
while (current_subject < end_subject && |
while (current_subject < end_subject && |
*current_subject != first_char && *current_subject != first_char2) | (csc = RAWUCHARTEST(current_subject)) != first_char && csc != first_char2) |
current_subject++; |
current_subject++; |
|
} |
else |
else |
while (current_subject < end_subject && |
while (current_subject < end_subject && |
*current_subject != first_char) | RAWUCHARTEST(current_subject) != first_char) |
current_subject++; |
current_subject++; |
} |
} |
|
|
Line 3450 for (;;)
|
Line 3435 for (;;)
|
ANYCRLF, and we are now at a LF, advance the match position by one |
ANYCRLF, and we are now at a LF, advance the match position by one |
more character. */ |
more character. */ |
|
|
if (current_subject[-1] == CHAR_CR && | if (RAWUCHARTEST(current_subject - 1) == CHAR_CR && |
(md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && |
(md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && |
current_subject < end_subject && |
current_subject < end_subject && |
*current_subject == CHAR_NL) | RAWUCHARTEST(current_subject) == CHAR_NL) |
current_subject++; |
current_subject++; |
} |
} |
} |
} |
Line 3464 for (;;)
|
Line 3449 for (;;)
|
{ |
{ |
while (current_subject < end_subject) |
while (current_subject < end_subject) |
{ |
{ |
register unsigned int c = *current_subject; | register pcre_uint32 c = RAWUCHARTEST(current_subject); |
#ifndef COMPILE_PCRE8 |
#ifndef COMPILE_PCRE8 |
if (c > 255) c = 255; |
if (c > 255) c = 255; |
#endif |
#endif |
Line 3530 for (;;)
|
Line 3515 for (;;)
|
{ |
{ |
while (p < end_subject) |
while (p < end_subject) |
{ |
{ |
register int pp = *p++; | register pcre_uint32 pp = RAWUCHARINCTEST(p); |
if (pp == req_char || pp == req_char2) { p--; break; } |
if (pp == req_char || pp == req_char2) { p--; break; } |
} |
} |
} |
} |
Line 3538 for (;;)
|
Line 3523 for (;;)
|
{ |
{ |
while (p < end_subject) |
while (p < end_subject) |
{ |
{ |
if (*p++ == req_char) { p--; break; } | if (RAWUCHARINCTEST(p) == req_char) { p--; break; } |
} |
} |
} |
} |
|
|
Line 3576 for (;;)
|
Line 3561 for (;;)
|
/* Anything other than "no match" means we are done, always; otherwise, carry |
/* Anything other than "no match" means we are done, always; otherwise, carry |
on only if not anchored. */ |
on only if not anchored. */ |
|
|
if (rc != PCRE_ERROR_NOMATCH || anchored) return rc; | if (rc != PCRE_ERROR_NOMATCH || anchored) |
| { |
| if (rc == PCRE_ERROR_PARTIAL && offsetcount >= 2) |
| { |
| offsets[0] = (int)(md->start_used_ptr - (PCRE_PUCHAR)subject); |
| offsets[1] = (int)(end_subject - (PCRE_PUCHAR)subject); |
| if (offsetcount > 2) |
| offsets[2] = (int)(current_subject - (PCRE_PUCHAR)subject); |
| } |
| return rc; |
| } |
|
|
/* Advance to the next subject character unless we are at the end of a line |
/* Advance to the next subject character unless we are at the end of a line |
and firstline is set. */ |
and firstline is set. */ |
Line 3596 for (;;)
|
Line 3591 for (;;)
|
not contain any explicit matches for \r or \n, and the newline option is CRLF |
not contain any explicit matches for \r or \n, and the newline option is CRLF |
or ANY or ANYCRLF, advance the match position by one more character. */ |
or ANY or ANYCRLF, advance the match position by one more character. */ |
|
|
if (current_subject[-1] == CHAR_CR && | if (RAWUCHARTEST(current_subject - 1) == CHAR_CR && |
current_subject < end_subject && |
current_subject < end_subject && |
*current_subject == CHAR_NL && | RAWUCHARTEST(current_subject) == CHAR_NL && |
(re->flags & PCRE_HASCRORLF) == 0 && |
(re->flags & PCRE_HASCRORLF) == 0 && |
(md->nltype == NLTYPE_ANY || |
(md->nltype == NLTYPE_ANY || |
md->nltype == NLTYPE_ANYCRLF || |
md->nltype == NLTYPE_ANYCRLF || |