Revision: 1532
http://vcs.pcre.org/viewvc?view=rev&revision=1532
Author: ph10
Date: 2015-03-06 11:59:39 +0000 (Fri, 06 Mar 2015)
Log Message:
-----------
Fix bad compile of patterns like /[A-`]/i8 where the range contains
characters with multiple other cases and the ranges adjoin.
Modified Paths:
--------------
code/trunk/ChangeLog
code/trunk/pcre_compile.c
code/trunk/testdata/testinput6
code/trunk/testdata/testoutput6
Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog 2015-03-06 07:44:16 UTC (rev 1531)
+++ code/trunk/ChangeLog 2015-03-06 11:59:39 UTC (rev 1532)
@@ -93,7 +93,12 @@
existing and future issues, size computation is eliminated from the code,
and replaced by on-demand memory allocation.
+25. A pattern such as /(?i)[A-`]/, where characters in the other case are
+ adjacent to the end of the range, and the range contained characters with
+ more than one other case, caused incorrect behaviour when compiled in UTF
+ mode. In that example, the range a-j was left out of the class.
+
Version 8.36 26-September-2014
------------------------------
Modified: code/trunk/pcre_compile.c
===================================================================
--- code/trunk/pcre_compile.c 2015-03-06 07:44:16 UTC (rev 1531)
+++ code/trunk/pcre_compile.c 2015-03-06 11:59:39 UTC (rev 1532)
@@ -4002,7 +4002,7 @@
/* See if this recursion is on the forward reference list. If so, adjust the
reference. */
- for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset; hc < cd->hwm;
+ for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset; hc < cd->hwm;
hc += LINK_SIZE)
{
offset = (int)GET(hc, 0);
@@ -4208,7 +4208,11 @@
range. Otherwise, use a recursive call to add the additional range. */
else if (oc < start && od >= start - 1) start = oc; /* Extend downwards */
- else if (od > end && oc <= end + 1) end = od; /* Extend upwards */
+ else if (od > end && oc <= end + 1)
+ {
+ end = od; /* Extend upwards */
+ if (end > classbits_end) classbits_end = (end <= 0xff ? end : 0xff);
+ }
else n8 += add_to_class(classbits, uchardptr, options, cd, oc, od);
}
}
@@ -6052,15 +6056,15 @@
memcpy(code, previous, IN_UCHARS(len));
while (cd->hwm > cd->start_workspace + cd->workspace_size -
- WORK_SIZE_SAFETY_MARGIN -
+ WORK_SIZE_SAFETY_MARGIN -
(this_hwm_offset - save_hwm_offset))
{
*errorcodeptr = expand_workspace(cd);
if (*errorcodeptr != 0) goto FAILED;
}
- for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset;
- hc < (pcre_uchar *)cd->start_workspace + this_hwm_offset;
+ for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset;
+ hc < (pcre_uchar *)cd->start_workspace + this_hwm_offset;
hc += LINK_SIZE)
{
PUT(cd->hwm, 0, GET(hc, 0) + len);
@@ -6133,15 +6137,15 @@
copying them. */
while (cd->hwm > cd->start_workspace + cd->workspace_size -
- WORK_SIZE_SAFETY_MARGIN -
+ WORK_SIZE_SAFETY_MARGIN -
(this_hwm_offset - save_hwm_offset))
{
*errorcodeptr = expand_workspace(cd);
if (*errorcodeptr != 0) goto FAILED;
}
- for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset;
- hc < (pcre_uchar *)cd->start_workspace + this_hwm_offset;
+ for (hc = (pcre_uchar *)cd->start_workspace + save_hwm_offset;
+ hc < (pcre_uchar *)cd->start_workspace + this_hwm_offset;
hc += LINK_SIZE)
{
PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1));
Modified: code/trunk/testdata/testinput6
===================================================================
--- code/trunk/testdata/testinput6 2015-03-06 07:44:16 UTC (rev 1531)
+++ code/trunk/testdata/testinput6 2015-03-06 11:59:39 UTC (rev 1532)
@@ -1496,4 +1496,7 @@
/^s?c/mi8
scat
+/[A-`]/i8
+ abcdefghijklmno
+
/-- End of testinput6 --/
Modified: code/trunk/testdata/testoutput6
===================================================================
--- code/trunk/testdata/testoutput6 2015-03-06 07:44:16 UTC (rev 1531)
+++ code/trunk/testdata/testoutput6 2015-03-06 11:59:39 UTC (rev 1532)
@@ -2461,4 +2461,8 @@
scat
0: sc
+/[A-`]/i8
+ abcdefghijklmno
+ 0: a
+
/-- End of testinput6 --/
