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

Add options to ignore the internal encoding

Browse Source 
For both XML and HTML, the document can provide an encoding
either in XMLDecl in XML, or as a meta element in HTML head.
This adds options to ignore those encodings if the encoding
is known in advace for example if the content had been converted
before being passed to the parser.

* parser.c include/libxml/parser.h: add XML_PARSE_IGNORE_ENC option
  for XML parsing
* include/libxml/HTMLparser.h HTMLparser.c: adds the
  HTML_PARSE_IGNORE_ENC for HTML parsing
* HTMLtree.c: fix the handling of saving when an unknown encoding is
  defined in meta document header
* xmllint.c: add a --noenc option to activate the new parser options
This commit is contained in:
Daniel Veillard
2011-05-16 16:03:50 +08:00
parent 0329a1471e
commit c62efc847c
6 changed files with 39 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
HTMLparser.c
View File

@@ -3448,7 +3448,8 @@ static void
htmlCheckEncoding(htmlParserCtxtPtr ctxt, const xmlChar *attvalue) {
const xmlChar *encoding;
if ((ctxt == NULL) || (attvalue == NULL))
if ((ctxt == NULL) || (attvalue == NULL) ||
(ctxt->options & HTML_PARSE_IGNORE_ENC))
return;
/* do not change encoding */
@@ -3500,7 +3501,9 @@ htmlCheckEncoding(htmlParserCtxtPtr ctxt, const xmlChar *attvalue) {
xmlSwitchToEncoding(ctxt, handler);
ctxt->charset = XML_CHAR_ENCODING_UTF8;
} else {
ctxt->errNo = XML_ERR_UNSUPPORTED_ENCODING;
htmlParseErr(ctxt, XML_ERR_UNSUPPORTED_ENCODING,
"htmlCheckEncoding: unknown encoding %s\n",
encoding, NULL);
}
}
@@ -6537,6 +6540,10 @@ htmlCtxtUseOptions(htmlParserCtxtPtr ctxt, int options)
ctxt->options |= HTML_PARSE_NODEFDTD;
options -= HTML_PARSE_NODEFDTD;
}
if (options & HTML_PARSE_IGNORE_ENC) {
ctxt->options |= HTML_PARSE_IGNORE_ENC;
options -= HTML_PARSE_IGNORE_ENC;
}
ctxt->dictNames = 0;
return (options);
}