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.c84
1 files changed, 54 insertions, 30 deletions
diff --git a/ext/pcre/pcrelib/pcre_exec.c b/ext/pcre/pcrelib/pcre_exec.c
index ca3079b0a..4fe798e6b 100644
--- a/ext/pcre/pcrelib/pcre_exec.c
+++ b/ext/pcre/pcrelib/pcre_exec.c
@@ -6,7 +6,7 @@
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
- Copyright (c) 1997-2009 University of Cambridge
+ Copyright (c) 1997-2010 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
@@ -87,7 +87,7 @@ static const char rep_max[] = { 0, 0, 0, 0, 1, 1 };
-#ifdef DEBUG
+#ifdef PCRE_DEBUG
/*************************************************
* Debugging function to print chars *
*************************************************/
@@ -139,7 +139,7 @@ match_ref(int offset, register USPTR eptr, int length, match_data *md,
{
USPTR p = md->start_subject + md->offset_vector[offset];
-#ifdef DEBUG
+#ifdef PCRE_DEBUG
if (eptr >= md->end_subject)
printf("matching subject <null>");
else
@@ -247,16 +247,16 @@ enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10,
/* These versions of the macros use the stack, as normal. There are debugging
versions and production versions. Note that the "rw" argument of RMATCH isn't
-actuall used in this definition. */
+actually used in this definition. */
#ifndef NO_RECURSE
#define REGISTER register
-#ifdef DEBUG
+#ifdef PCRE_DEBUG
#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \
{ \
printf("match() called in line %d\n", __LINE__); \
- rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1); \
+ rrc = match(ra,rb,mstart,markptr,rc,rd,re,rf,rg,rdepth+1); \
printf("to line %d\n", __LINE__); \
}
#define RRETURN(ra) \
@@ -266,7 +266,7 @@ actuall used in this definition. */
}
#else
#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \
- rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1)
+ rrc = match(ra,rb,mstart,markptr,rc,rd,re,rf,rg,rdepth+1)
#define RRETURN(ra) return ra
#endif
@@ -286,6 +286,7 @@ argument of match(), which never changes. */
newframe->Xeptr = ra;\
newframe->Xecode = rb;\
newframe->Xmstart = mstart;\
+ newframe->Xmarkptr = markptr;\
newframe->Xoffset_top = rc;\
newframe->Xims = re;\
newframe->Xeptrb = rf;\
@@ -323,6 +324,7 @@ typedef struct heapframe {
USPTR Xeptr;
const uschar *Xecode;
USPTR Xmstart;
+ USPTR Xmarkptr;
int Xoffset_top;
long int Xims;
eptrblock *Xeptrb;
@@ -430,6 +432,7 @@ Arguments:
ecode pointer to current position in compiled code
mstart pointer to the current match start position (can be modified
by encountering \K)
+ markptr pointer to the most recent MARK name, or NULL
offset_top current top pointer
md pointer to "static" info for the match
ims current /i, /m, and /s options
@@ -448,9 +451,9 @@ Returns: MATCH_MATCH if matched ) these values are >= 0
*/
static int
-match(REGISTER USPTR eptr, REGISTER const uschar *ecode, USPTR mstart,
- int offset_top, match_data *md, unsigned long int ims, eptrblock *eptrb,
- int flags, unsigned int rdepth)
+match(REGISTER USPTR eptr, REGISTER const uschar *ecode, USPTR mstart, USPTR
+ markptr, int offset_top, match_data *md, unsigned long int ims,
+ eptrblock *eptrb, int flags, unsigned int rdepth)
{
/* These variables do not need to be preserved over recursion in this function,
so they can be ordinary variables in all cases. Mark some of them with
@@ -478,6 +481,7 @@ frame->Xprevframe = NULL; /* Marks the top level */
frame->Xeptr = eptr;
frame->Xecode = ecode;
frame->Xmstart = mstart;
+frame->Xmarkptr = markptr;
frame->Xoffset_top = offset_top;
frame->Xims = ims;
frame->Xeptrb = eptrb;
@@ -493,6 +497,7 @@ HEAP_RECURSE:
#define eptr frame->Xeptr
#define ecode frame->Xecode
#define mstart frame->Xmstart
+#define markptr frame->Xmarkptr
#define offset_top frame->Xoffset_top
#define ims frame->Xims
#define eptrb frame->Xeptrb
@@ -620,7 +625,7 @@ TAIL_RECURSE:
/* OK, now we can get on with the real code of the function. Recursive calls
are specified by the macro RMATCH and RRETURN is used to return. When
NO_RECURSE is *not* defined, these just turn into a recursive call to match()
-and a "return", respectively (possibly with some debugging if DEBUG is
+and a "return", respectively (possibly with some debugging if PCRE_DEBUG is
defined). However, RMATCH isn't like a function call because it's quite a
complicated macro. It has to be used in one particular way. This shouldn't,
however, impact performance when true recursion is being used. */
@@ -711,7 +716,7 @@ for (;;)
number = GET2(ecode, 1+LINK_SIZE);
offset = number << 1;
-#ifdef DEBUG
+#ifdef PCRE_DEBUG
printf("start bracket %d\n", number);
printf("subject=");
pchars(eptr, 16, TRUE, md);
@@ -1037,7 +1042,7 @@ for (;;)
number = GET2(ecode, 1);
offset = number << 1;
-#ifdef DEBUG
+#ifdef PCRE_DEBUG
printf("end bracket %d at *ACCEPT", number);
printf("\n");
#endif
@@ -1068,7 +1073,6 @@ for (;;)
memmove(md->offset_vector, rec->offset_save,
rec->saved_max * sizeof(int));
offset_top = rec->save_offset_top;
- mstart = rec->save_start;
ims = original_ims;
ecode = rec->after_call;
break;
@@ -1112,7 +1116,11 @@ for (;;)
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0,
RM4);
- if (rrc == MATCH_MATCH) break;
+ if (rrc == MATCH_MATCH)
+ {
+ mstart = md->start_match_ptr; /* In case \K reset it */
+ break;
+ }
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
ecode += GET(ecode, 1);
}
@@ -1131,7 +1139,9 @@ for (;;)
offset_top = md->end_offset_top;
continue;
- /* Negative assertion: all branches must fail to match */
+ /* Negative assertion: all branches must fail to match. Encountering SKIP,
+ PRUNE, or COMMIT means we must assume failure without checking subsequent
+ branches. */
case OP_ASSERT_NOT:
case OP_ASSERTBACK_NOT:
@@ -1140,6 +1150,11 @@ for (;;)
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0,
RM5);
if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH);
+ if (rrc == MATCH_SKIP || rrc == MATCH_PRUNE || rrc == MATCH_COMMIT)
+ {
+ do ecode += GET(ecode,1); while (*ecode == OP_ALT);
+ break;
+ }
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
ecode += GET(ecode,1);
}
@@ -1258,9 +1273,7 @@ for (;;)
memcpy(new_recursive.offset_save, md->offset_vector,
new_recursive.saved_max * sizeof(int));
- new_recursive.save_start = mstart;
new_recursive.save_offset_top = offset_top;
- mstart = eptr;
/* OK, now we can do the recursion. For each top-level alternative we
restore the offset and recursion data. */
@@ -1307,7 +1320,8 @@ for (;;)
a move back into the brackets. Friedl calls these "atomic" subpatterns.
Check the alternative branches in turn - the matching won't pass the KET
for this kind of subpattern. If any one branch matches, we carry on as at
- the end of a normal bracket, leaving the subject pointer. */
+ the end of a normal bracket, leaving the subject pointer, but resetting
+ the start-of-match value in case it was changed by \K. */
case OP_ONCE:
prev = ecode;
@@ -1316,7 +1330,11 @@ for (;;)
do
{
RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM7);
- if (rrc == MATCH_MATCH) break;
+ if (rrc == MATCH_MATCH)
+ {
+ mstart = md->start_match_ptr;
+ break;
+ }
if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc);
ecode += GET(ecode,1);
}
@@ -1435,9 +1453,10 @@ for (;;)
}
else saved_eptr = NULL;
- /* If we are at the end of an assertion group, stop matching and return
- MATCH_MATCH, but record the current high water mark for use by positive
- assertions. Do this also for the "once" (atomic) groups. */
+ /* If we are at the end of an assertion group or an atomic group, stop
+ matching and return MATCH_MATCH, but record the current high water mark for
+ use by positive assertions. We also need to record the match start in case
+ it was changed by \K. */
if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT ||
*prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT ||
@@ -1445,6 +1464,7 @@ for (;;)
{
md->end_match_ptr = eptr; /* For ONCE */
md->end_offset_top = offset_top;
+ md->start_match_ptr = mstart;
RRETURN(MATCH_MATCH);
}
@@ -1459,7 +1479,7 @@ for (;;)
number = GET2(prev, 1+LINK_SIZE);
offset = number << 1;
-#ifdef DEBUG
+#ifdef PCRE_DEBUG
printf("end bracket %d", number);
printf("\n");
#endif
@@ -1481,7 +1501,6 @@ for (;;)
recursion_info *rec = md->recursive;
DPRINTF(("Recursion (%d) succeeded - continuing\n", number));
md->recursive = rec->prevrec;
- mstart = rec->save_start;
memcpy(md->offset_vector, rec->offset_save,
rec->saved_max * sizeof(int));
offset_top = rec->save_offset_top;
@@ -3686,8 +3705,12 @@ for (;;)
case OP_NOT_WORDCHAR:
for (i = 1; i <= min; i++)
{
- if (eptr >= md->end_subject ||
- (*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0))
+ if (eptr >= md->end_subject)
+ {
+ SCHECK_PARTIAL();
+ RRETURN(MATCH_NOMATCH);
+ }
+ if (*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0)
RRETURN(MATCH_NOMATCH);
while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80);
}
@@ -5563,7 +5586,7 @@ for(;;)
bytes to avoid spending too much time in this optimization. */
if (study != NULL && (study->flags & PCRE_STUDY_MINLEN) != 0 &&
- end_subject - start_match < study->minlength)
+ (pcre_uint32)(end_subject - start_match) < study->minlength)
{
rc = MATCH_NOMATCH;
break;
@@ -5626,7 +5649,7 @@ for(;;)
}
}
-#ifdef DEBUG /* Sigh. Some compilers never learn. */
+#ifdef PCRE_DEBUG /* Sigh. Some compilers never learn. */
printf(">>>> Match against: ");
pchars(start_match, end_subject - start_match, TRUE, md);
printf("\n");
@@ -5638,7 +5661,8 @@ for(;;)
md->start_match_ptr = start_match;
md->start_used_ptr = start_match;
md->match_call_count = 0;
- rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0);
+ rc = match(start_match, md->start_code, start_match, NULL, 2, md, ims, NULL,
+ 0, 0);
if (md->hitend && start_partial == NULL) start_partial = md->start_used_ptr;
switch(rc)
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-11 16:35:03 +0000