summaryrefslogtreecommitdiff
path: root/ext/pcre/pcrelib/pcre_exec.c
diff options
context:
space:
mode:
Diffstat (limited to 'ext/pcre/pcrelib/pcre_exec.c')
-rw-r--r--ext/pcre/pcrelib/pcre_exec.c148
1 files changed, 51 insertions, 97 deletions
diff --git a/ext/pcre/pcrelib/pcre_exec.c b/ext/pcre/pcrelib/pcre_exec.c
index eff51c7048..e28fe9ec86 100644
--- a/ext/pcre/pcrelib/pcre_exec.c
+++ b/ext/pcre/pcrelib/pcre_exec.c
@@ -156,39 +156,13 @@ printf("\n");
if (length > md->end_subject - eptr) return FALSE;
-/* Separate the caseless case for speed. In UTF-8 mode we can only do this
-properly if Unicode properties are supported. Otherwise, we can check only
-ASCII characters. */
+/* Separate the caselesss case for speed */
if ((ims & PCRE_CASELESS) != 0)
{
-#ifdef SUPPORT_UTF8
-#ifdef SUPPORT_UCP
- if (md->utf8)
- {
- USPTR endptr = eptr + length;
- while (eptr < endptr)
- {
- int c, d;
- GETCHARINC(c, eptr);
- GETCHARINC(d, p);
- if (c != d && c != UCD_OTHERCASE(d)) return FALSE;
- }
- }
- else
-#endif
-#endif
-
- /* The same code works when not in UTF-8 mode and in UTF-8 mode when there
- is no UCP support. */
-
while (length-- > 0)
- { if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; }
+ if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE;
}
-
-/* In the caseful case, we can just compare the bytes, whether or not we
-are in UTF-8 mode. */
-
else
{ while (length-- > 0) if (*p++ != *eptr++) return FALSE; }
@@ -1677,7 +1651,8 @@ for (;;)
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINCTEST(c, eptr);
{
- const ucd_record * prop = GET_UCD(c);
+ int chartype, script;
+ int category = _pcre_ucp_findprop(c, &chartype, &script);
switch(ecode[1])
{
@@ -1686,24 +1661,24 @@ for (;;)
break;
case PT_LAMP:
- if ((prop->chartype == ucp_Lu ||
- prop->chartype == ucp_Ll ||
- prop->chartype == ucp_Lt) == (op == OP_NOTPROP))
+ if ((chartype == ucp_Lu ||
+ chartype == ucp_Ll ||
+ chartype == ucp_Lt) == (op == OP_NOTPROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_GC:
- if ((ecode[2] != _pcre_ucp_gentype[prop->chartype]) == (op == OP_PROP))
+ if ((ecode[2] != category) == (op == OP_PROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_PC:
- if ((ecode[2] != prop->chartype) == (op == OP_PROP))
+ if ((ecode[2] != chartype) == (op == OP_PROP))
RRETURN(MATCH_NOMATCH);
break;
case PT_SC:
- if ((ecode[2] != prop->script) == (op == OP_PROP))
+ if ((ecode[2] != script) == (op == OP_PROP))
RRETURN(MATCH_NOMATCH);
break;
@@ -1722,7 +1697,8 @@ for (;;)
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINCTEST(c, eptr);
{
- int category = UCD_CATEGORY(c);
+ int chartype, script;
+ int category = _pcre_ucp_findprop(c, &chartype, &script);
if (category == ucp_M) RRETURN(MATCH_NOMATCH);
while (eptr < md->end_subject)
{
@@ -1731,7 +1707,7 @@ for (;;)
{
GETCHARLEN(c, eptr, len);
}
- category = UCD_CATEGORY(c);
+ category = _pcre_ucp_findprop(c, &chartype, &script);
if (category != ucp_M) break;
eptr += len;
}
@@ -2196,7 +2172,7 @@ for (;;)
if (fc != dc)
{
#ifdef SUPPORT_UCP
- if (dc != UCD_OTHERCASE(fc))
+ if (dc != _pcre_ucp_othercase(fc))
#endif
RRETURN(MATCH_NOMATCH);
}
@@ -2287,7 +2263,7 @@ for (;;)
#ifdef SUPPORT_UCP
unsigned int othercase;
if ((ims & PCRE_CASELESS) != 0 &&
- (othercase = UCD_OTHERCASE(fc)) != fc)
+ (othercase = _pcre_ucp_othercase(fc)) != NOTACHAR)
oclength = _pcre_ord2utf8(othercase, occhars);
else oclength = 0;
#endif /* SUPPORT_UCP */
@@ -2607,11 +2583,10 @@ for (;;)
{
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM28);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
- if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINC(d, eptr);
if (d < 256) d = md->lcc[d];
- if (fc == d) RRETURN(MATCH_NOMATCH);
-
+ if (fi >= max || eptr >= md->end_subject || fc == d)
+ RRETURN(MATCH_NOMATCH);
}
}
else
@@ -2717,9 +2692,9 @@ for (;;)
{
RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM32);
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
- if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINC(d, eptr);
- if (fc == d) RRETURN(MATCH_NOMATCH);
+ if (fi >= max || eptr >= md->end_subject || fc == d)
+ RRETURN(MATCH_NOMATCH);
}
}
else
@@ -2893,7 +2868,7 @@ for (;;)
{
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINCTEST(c, eptr);
- prop_chartype = UCD_CHARTYPE(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_chartype == ucp_Lu ||
prop_chartype == ucp_Ll ||
prop_chartype == ucp_Lt) == prop_fail_result)
@@ -2906,7 +2881,7 @@ for (;;)
{
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINCTEST(c, eptr);
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_category == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
@@ -2917,7 +2892,7 @@ for (;;)
{
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINCTEST(c, eptr);
- prop_chartype = UCD_CHARTYPE(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_chartype == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
@@ -2928,7 +2903,7 @@ for (;;)
{
if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINCTEST(c, eptr);
- prop_script = UCD_SCRIPT(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_script == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
@@ -2947,7 +2922,7 @@ for (;;)
for (i = 1; i <= min; i++)
{
GETCHARINCTEST(c, eptr);
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);
while (eptr < md->end_subject)
{
@@ -2956,7 +2931,7 @@ for (;;)
{
GETCHARLEN(c, eptr, len);
}
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if (prop_category != ucp_M) break;
eptr += len;
}
@@ -3372,7 +3347,7 @@ for (;;)
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINC(c, eptr);
- prop_chartype = UCD_CHARTYPE(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_chartype == ucp_Lu ||
prop_chartype == ucp_Ll ||
prop_chartype == ucp_Lt) == prop_fail_result)
@@ -3387,7 +3362,7 @@ for (;;)
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINC(c, eptr);
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_category == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
@@ -3400,7 +3375,7 @@ for (;;)
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINC(c, eptr);
- prop_chartype = UCD_CHARTYPE(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_chartype == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
@@ -3413,7 +3388,7 @@ for (;;)
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINC(c, eptr);
- prop_script = UCD_SCRIPT(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_script == prop_value) == prop_fail_result)
RRETURN(MATCH_NOMATCH);
}
@@ -3435,7 +3410,7 @@ for (;;)
if (rrc != MATCH_NOMATCH) RRETURN(rrc);
if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH);
GETCHARINCTEST(c, eptr);
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH);
while (eptr < md->end_subject)
{
@@ -3444,7 +3419,7 @@ for (;;)
{
GETCHARLEN(c, eptr, len);
}
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if (prop_category != ucp_M) break;
eptr += len;
}
@@ -3762,7 +3737,7 @@ for (;;)
int len = 1;
if (eptr >= md->end_subject) break;
GETCHARLEN(c, eptr, len);
- prop_chartype = UCD_CHARTYPE(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_chartype == ucp_Lu ||
prop_chartype == ucp_Ll ||
prop_chartype == ucp_Lt) == prop_fail_result)
@@ -3777,7 +3752,7 @@ for (;;)
int len = 1;
if (eptr >= md->end_subject) break;
GETCHARLEN(c, eptr, len);
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_category == prop_value) == prop_fail_result)
break;
eptr+= len;
@@ -3790,7 +3765,7 @@ for (;;)
int len = 1;
if (eptr >= md->end_subject) break;
GETCHARLEN(c, eptr, len);
- prop_chartype = UCD_CHARTYPE(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_chartype == prop_value) == prop_fail_result)
break;
eptr+= len;
@@ -3803,7 +3778,7 @@ for (;;)
int len = 1;
if (eptr >= md->end_subject) break;
GETCHARLEN(c, eptr, len);
- prop_script = UCD_SCRIPT(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if ((prop_script == prop_value) == prop_fail_result)
break;
eptr+= len;
@@ -3832,7 +3807,7 @@ for (;;)
{
if (eptr >= md->end_subject) break;
GETCHARINCTEST(c, eptr);
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if (prop_category == ucp_M) break;
while (eptr < md->end_subject)
{
@@ -3841,7 +3816,7 @@ for (;;)
{
GETCHARLEN(c, eptr, len);
}
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if (prop_category != ucp_M) break;
eptr += len;
}
@@ -3863,7 +3838,7 @@ for (;;)
BACKCHAR(eptr);
GETCHARLEN(c, eptr, len);
}
- prop_category = UCD_CATEGORY(c);
+ prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script);
if (prop_category != ucp_M) break;
eptr--;
}
@@ -4383,7 +4358,7 @@ Returns: > 0 => success; value is the number of elements filled in
< -1 => some kind of unexpected problem
*/
-PCRE_EXP_DEFN int PCRE_CALL_CONVENTION
+PCRE_EXP_DEFN int
pcre_exec(const pcre *argument_re, const pcre_extra *extra_data,
PCRE_SPTR subject, int length, int start_offset, int options, int *offsets,
int offsetcount)
@@ -4695,53 +4670,31 @@ for(;;)
if (firstline)
{
USPTR t = start_match;
-#ifdef SUPPORT_UTF8
- if (utf8)
- {
- while (t < md->end_subject && !IS_NEWLINE(t))
- {
- t++;
- while (t < end_subject && (*t & 0xc0) == 0x80) t++;
- }
- }
- else
-#endif
while (t < md->end_subject && !IS_NEWLINE(t)) t++;
end_subject = t;
}
- /* Now advance to a unique first byte if there is one. */
+ /* Now test for a unique first byte */
if (first_byte >= 0)
{
if (first_byte_caseless)
- while (start_match < end_subject && md->lcc[*start_match] != first_byte)
- start_match++;
+ while (start_match < end_subject &&
+ md->lcc[*start_match] != first_byte)
+ { NEXTCHAR(start_match); }
else
while (start_match < end_subject && *start_match != first_byte)
- start_match++;
+ { NEXTCHAR(start_match); }
}
- /* Or to just after a linebreak for a multiline match */
+ /* Or to just after a linebreak for a multiline match if possible */
else if (startline)
{
if (start_match > md->start_subject + start_offset)
{
-#ifdef SUPPORT_UTF8
- if (utf8)
- {
- while (start_match < end_subject && !WAS_NEWLINE(start_match))
- {
- start_match++;
- while(start_match < end_subject && (*start_match & 0xc0) == 0x80)
- start_match++;
- }
- }
- else
-#endif
- while (start_match < end_subject && !WAS_NEWLINE(start_match))
- start_match++;
+ while (start_match <= end_subject && !WAS_NEWLINE(start_match))
+ { NEXTCHAR(start_match); }
/* If we have just passed a CR and the newline option is ANY or ANYCRLF,
and we are now at a LF, advance the match position by one more character.
@@ -4755,15 +4708,16 @@ for(;;)
}
}
- /* Or to a non-unique first byte after study */
+ /* Or to a non-unique first char after study */
else if (start_bits != NULL)
{
while (start_match < end_subject)
{
register unsigned int c = *start_match;
- if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++;
- else break;
+ if ((start_bits[c/8] & (1 << (c&7))) == 0)
+ { NEXTCHAR(start_match); }
+ else break;
}
}
View Lorry Controller Status