lib/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2.git synced 2025-10-24 13:33:01 +03:00
Code Activity

html: Reenable buggy detection of XML declarations

Browse Source 
Switch to UTF-8 if a document starts with '<?xm' to match old behavior.
Also enable this check in the push parser.

Fixes #637.
This commit is contained in:
Nick Wellnhofer
2023-11-30 16:15:46 +01:00
parent e2ce828c9b
commit e395946194
5 changed files with 43 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
HTMLparser.c
View File

@@ -4851,6 +4851,14 @@ htmlParseDocument(htmlParserCtxtPtr ctxt) {
xmlDetectEncoding(ctxt);
/*
* This is wrong but matches long-standing behavior. In most cases,
* a document starting with an XML declaration will specify UTF-8.
*/
if (((ctxt->input->flags & XML_INPUT_HAS_ENCODING) == 0) &&
(xmlStrncmp(ctxt->input->cur, BAD_CAST "<?xm", 4) == 0))
xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_UTF8);
/*
* Wipe out everything which is before the first '<'
*/
@@ -5408,6 +5416,16 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
*/
goto done;
case XML_PARSER_START:
/*
* This is wrong but matches long-standing behavior. In most
* cases, a document starting with an XML declaration will
* specify UTF-8.
*/
if (((ctxt->input->flags & XML_INPUT_HAS_ENCODING) == 0) &&
(xmlStrncmp(ctxt->input->cur, BAD_CAST "<?xm", 4) == 0)) {
xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_UTF8);
}
/*
* Very first chars read from the document flow.
*/