2 Commits

Author	SHA1	Message	Date
Hugh Davenport	beca86e8c8	Detect change of encoding when parsing HTML names ... From https://bugzilla.gnome.org/show_bug.cgi?id=758518 Happens when a file has a name getting parsed, but no valid encoding set, so libxml has to guess what the encoding is. This patch detects when the buffer location changes, and if it does, restarts the parsing of the name. This slightly change a couple of regression tests output	2016-05-23 15:01:07 +08:00
Pranjal Jumde	a820dbeac2	Bug 758605: Heap-based buffer overread in xmlDictAddString <https://bugzilla.gnome.org/show_bug.cgi?id=758605> ... Reviewed by David Kilzer. * HTMLparser.c: (htmlParseName): Add bounds check. (htmlParseNameComplex): Ditto. * result/HTML/758605.html: Added. * result/HTML/758605.html.err: Added. * result/HTML/758605.html.sax: Added. * runtest.c: (pushParseTest): The input for the new test case was so small (4 bytes) that htmlParseChunk() was never called after htmlCreatePushParserCtxt(), thereby creating a false positive test failure. Fixed by using a do-while loop so we always call htmlParseChunk() at least once. * test/HTML/758605.html: Added.	2016-05-23 15:01:07 +08:00