Add options to ignore the internal encoding
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
diff --git a/HTMLparser.c b/HTMLparser.c
index 4d43b93..1a4d80d 100644
--- a/HTMLparser.c
+++ b/HTMLparser.c
@@ -3448,7 +3448,8 @@
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 @@
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 @@
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);
}