c/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2 synced 2025-03-28 21:33:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Detect change of encoding when parsing HTML names

Browse Source 
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
This commit is contained in:
Hugh Davenport 2016-05-04 11:23:49 +08:00 committed by Daniel Veillard
parent b1d34de46a
commit beca86e8c8
4 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
HTMLparser.c
View File

@ -2492,6 +2492,7 @@ htmlParseNameComplex(xmlParserCtxtPtr ctxt) {
int len = 0, l;
int c;
int count = 0;
const xmlChar *base = ctxt->input->base;
/*
* Handler for more complex cases
@ -2517,6 +2518,13 @@ htmlParseNameComplex(xmlParserCtxtPtr ctxt) {
len += l;
NEXTL(l);
c = CUR_CHAR(l);
if (ctxt->input->base != base) {
/*
* We changed encoding from an unknown encoding
* Input buffer changed location, so we better start again
*/
return(htmlParseNameComplex(ctxt));
}
}
if (ctxt->input->base > ctxt->input->cur - len)

2
result/HTML/758605.html
View File

@ -1,3 +1,3 @@
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd">
<html><body><p>&amp;
<html><body><p>&amp;&ecirc;
</p></body></html>

2
result/HTML/758605.html.err
View File

@ -1,3 +1,3 @@
./test/HTML/758605.html:1: HTML parser error : htmlParseEntityRef: no name
./test/HTML/758605.html:1: HTML parser error : htmlParseEntityRef: expecting ';'
ê
^

3
result/HTML/758605.html.sax
View File

@ -1,10 +1,11 @@
SAX.setDocumentLocator()
SAX.startDocument()
SAX.error: htmlParseEntityRef: no name
SAX.error: htmlParseEntityRef: expecting ';'
SAX.startElement(html)
SAX.startElement(body)
SAX.startElement(p)
SAX.characters(&amp;, 1)
SAX.characters(&ecirc;, 2)
SAX.ignorableWhitespace(
, 1)
SAX.endElement(p)