Revision: 1544
http://vcs.pcre.org/viewvc?view=rev&revision=1544
Author: ph10
Date: 2015-04-07 17:19:03 +0100 (Tue, 07 Apr 2015)
Log Message:
-----------
Fix pcretest loop for \K in lookbehind assertion.
Modified Paths:
--------------
code/trunk/ChangeLog
code/trunk/pcretest.c
code/trunk/testdata/testinput2
code/trunk/testdata/testinput5
code/trunk/testdata/testoutput2
code/trunk/testdata/testoutput5
Modified: code/trunk/ChangeLog
===================================================================
--- code/trunk/ChangeLog 2015-04-07 15:52:11 UTC (rev 1543)
+++ code/trunk/ChangeLog 2015-04-07 16:19:03 UTC (rev 1544)
@@ -149,7 +149,9 @@
36. The use of \K in a positive lookbehind assertion in a non-anchored pattern
(e.g. /(?<=\Ka)/) could make pcregrep loop.
+37. There was a similar problem to 36 in pcretest for global matches.
+
Version 8.36 26-September-2014
------------------------------
Modified: code/trunk/pcretest.c
===================================================================
--- code/trunk/pcretest.c 2015-04-07 15:52:11 UTC (rev 1543)
+++ code/trunk/pcretest.c 2015-04-07 16:19:03 UTC (rev 1544)
@@ -5627,9 +5627,33 @@
g_notempty = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED;
}
- /* For /g, update the start offset, leaving the rest alone */
+ /* For /g, update the start offset, leaving the rest alone. There is a
+ tricky case when \K is used in a positive lookbehind assertion. This can
+ cause the end of the match to be less than or equal to the start offset.
+ In this case we restart at one past the start offset. This may return the
+ same match if the original start offset was bumped along during the
+ match, but eventually the new start offset will hit the actual start
+ offset. (In PCRE2 the true start offset is available, and this can be
+ done better. It is not worth doing more than making sure we do not loop
+ at this stage in the life of PCRE1.) */
- if (do_g) start_offset = use_offsets[1];
+ if (do_g)
+ {
+ if (g_notempty == 0 && use_offsets[1] <= start_offset)
+ {
+ if (start_offset >= len) break; /* End of subject */
+ start_offset++;
+ if (use_utf)
+ {
+ while (start_offset < len)
+ {
+ if ((bptr[start_offset] & 0xc0) != 0x80) break;
+ start_offset++;
+ }
+ }
+ }
+ else start_offset = use_offsets[1];
+ }
/* For /G, update the pointer and length */
Modified: code/trunk/testdata/testinput2
===================================================================
--- code/trunk/testdata/testinput2 2015-04-07 15:52:11 UTC (rev 1543)
+++ code/trunk/testdata/testinput2 2015-04-07 16:19:03 UTC (rev 1544)
@@ -4144,4 +4144,10 @@
"(?<=((?2))((?1)))"
+/(?<=\Ka)/g+
+ aaaaa
+
+/(?<=\Ka)/G+
+ aaaaa
+
/-- End of testinput2 --/
Modified: code/trunk/testdata/testinput5
===================================================================
--- code/trunk/testdata/testinput5 2015-04-07 15:52:11 UTC (rev 1543)
+++ code/trunk/testdata/testinput5 2015-04-07 16:19:03 UTC (rev 1544)
@@ -794,4 +794,10 @@
/[^\xff]*PRUNE:\x{100}abc(xyz(?1))/8DZ
+/(?<=\K\x{17f})/8g+
+ \x{17f}\x{17f}\x{17f}\x{17f}\x{17f}
+
+/(?<=\K\x{17f})/8G+
+ \x{17f}\x{17f}\x{17f}\x{17f}\x{17f}
+
/-- End of testinput5 --/
Modified: code/trunk/testdata/testoutput2
===================================================================
--- code/trunk/testdata/testoutput2 2015-04-07 15:52:11 UTC (rev 1543)
+++ code/trunk/testdata/testoutput2 2015-04-07 16:19:03 UTC (rev 1544)
@@ -14393,4 +14393,32 @@
"(?<=((?2))((?1)))"
Failed: lookbehind assertion is not fixed length at offset 17
+/(?<=\Ka)/g+
+ aaaaa
+ 0: a
+ 0+ aaaa
+ 0: a
+ 0+ aaaa
+ 0: a
+ 0+ aaa
+ 0: a
+ 0+ aa
+ 0: a
+ 0+ a
+ 0: a
+ 0+
+
+/(?<=\Ka)/G+
+ aaaaa
+ 0: a
+ 0+ aaaa
+ 0: a
+ 0+ aaa
+ 0: a
+ 0+ aa
+ 0: a
+ 0+ a
+ 0: a
+ 0+
+
/-- End of testinput2 --/
Modified: code/trunk/testdata/testoutput5
===================================================================
--- code/trunk/testdata/testoutput5 2015-04-07 15:52:11 UTC (rev 1543)
+++ code/trunk/testdata/testoutput5 2015-04-07 16:19:03 UTC (rev 1544)
@@ -1916,4 +1916,32 @@
No first char
Need char = 'z'
+/(?<=\K\x{17f})/8g+
+ \x{17f}\x{17f}\x{17f}\x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}\x{17f}\x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}\x{17f}\x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}\x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}
+ 0: \x{17f}
+ 0+
+
+/(?<=\K\x{17f})/8G+
+ \x{17f}\x{17f}\x{17f}\x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}\x{17f}\x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}\x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}\x{17f}
+ 0: \x{17f}
+ 0+ \x{17f}
+ 0: \x{17f}
+ 0+
+
/-- End of testinput5 --/
