On Tuesday 14 April 2015 17:50:51 you wrote:
> If anything like this does get put in, it should only be if it is a
> configurable option that is disabled by default - an xml parser should
> only accept a strictly-conforming document by default. Adding support for
> ‘broken’ html because other (weak) parsers allow it is not a good plan as
> it causes divergence from the standard.
There you go; you find the updated patch attached. It now requires
HTML_PARSE_RECOVER option to be set for recovering from stand-alone less-than
characters.
Best regards,
Christian Schoenebeck
diff -u libxml2-2.9.1+dfsg1.orig/HTMLparser.c libxml2-2.9.1+dfsg1/HTMLparser.c
--- libxml2-2.9.1+dfsg1.orig/HTMLparser.c 2015-04-14 13:05:01.000000000 +0200
+++ libxml2-2.9.1+dfsg1/HTMLparser.c 2015-04-14 18:22:41.143973776 +0200
@@ -2948,8 +2948,10 @@
/**
- * htmlParseCharData:
+ * htmlParseCharDataInternal:
* @ctxt: an HTML parser context
+ * @prep: optional character to be prepended to text, 0 if no character
+ * shall be prepended
*
* parse a CharData section.
* if we are within a CDATA section ']]>' marks an end of section.
@@ -2958,12 +2960,15 @@
*/
static void
-htmlParseCharData(htmlParserCtxtPtr ctxt) {
- xmlChar buf[HTML_PARSER_BIG_BUFFER_SIZE + 5];
+htmlParseCharDataInternal(htmlParserCtxtPtr ctxt, char prep) {
+ xmlChar buf[HTML_PARSER_BIG_BUFFER_SIZE + 6];
int nbchar = 0;
int cur, l;
int chunk = 0;
+ if (prep)
+ buf[nbchar++] = prep;
+
SHRINK;
cur = CUR_CHAR(l);
while (((cur != '<') || (ctxt->token == '<')) &&
@@ -3043,6 +3048,21 @@
}
/**
+ * htmlParseCharData:
+ * @ctxt: an HTML parser context
+ *
+ * parse a CharData section.
+ * if we are within a CDATA section ']]>' marks an end of section.
+ *
+ * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
+ */
+
+static void
+htmlParseCharData(htmlParserCtxtPtr ctxt) {
+ htmlParseCharDataInternal(ctxt, 0);
+}
+
+/**
* htmlParseExternalID:
* @ctxt: an HTML parser context
* @publicID: a xmlChar** receiving PubidLiteral
@@ -4157,14 +4177,24 @@
}
/*
- * Third case : a sub-element.
+ * Third case : (unescaped) stand-alone less-than character.
+ * Only if HTML_PARSE_RECOVER option is set.
+ */
+ else if (ctxt->recovery && (CUR == '<') &&
+ (IS_BLANK_CH(NXT(1)) || (NXT(1) == '='))) {
+ NEXT;
+ htmlParseCharDataInternal(ctxt, '<');
+ }
+
+ /*
+ * Fourth case : a sub-element.
*/
else if (CUR == '<') {
htmlParseElement(ctxt);
}
/*
- * Fourth case : a reference. If if has not been resolved,
+ * Fifth case : a reference. If if has not been resolved,
* parsing returns it's Name, create the node
*/
else if (CUR == '&') {
@@ -4172,7 +4202,7 @@
}
/*
- * Fifth case : end of the resource
+ * Sixth case : end of the resource
*/
else if (CUR == 0) {
htmlAutoCloseOnEnd(ctxt);
@@ -4567,7 +4597,17 @@
}
/*
- * Third case : a sub-element.
+ * Third case : (unescaped) stand-alone less-than character.
+ * Only if HTML_PARSE_RECOVER option is set.
+ */
+ else if (ctxt->recovery && (CUR == '<') &&
+ (IS_BLANK_CH(NXT(1)) || (NXT(1) == '='))) {
+ NEXT;
+ htmlParseCharDataInternal(ctxt, '<');
+ }
+
+ /*
+ * Fourth case : a sub-element.
*/
else if (CUR == '<') {
htmlParseElementInternal(ctxt);
@@ -4578,7 +4618,7 @@
}
/*
- * Fourth case : a reference. If if has not been resolved,
+ * Fifth case : a reference. If if has not been resolved,
* parsing returns it's Name, create the node
*/
else if (CUR == '&') {
@@ -4586,7 +4626,7 @@
}
/*
- * Fifth case : end of the resource
+ * Sixth case : end of the resource
*/
else if (CUR == 0) {
htmlAutoCloseOnEnd(ctxt);
_______________________________________________
xml mailing list, project page http://xmlsoft.org/
xml@gnome.org
https://mail.gnome.org/mailman/listinfo/xml
