Revert a change from d025cfbb and don't overwrite ID table entries, so
that the first attribute will be returned if there are duplicate IDs.
This requires two other changes:
- Attributes in entity content are never added to the ID table. This
seems reasonable.
- Remove the optimization to skip ID lookup when copying and the target
document has an empty ID table. This also seems more correct since the
document could have ID declarations nevertheless or we could be
copying xml:ids into the document for the first time.
Fixes#757.
Make sure that references from IDs are updated.
Note that if there are IDs with the same value in a document, the last
one will now be returned. IDs should be unique, but maybe this should be
addressed.
Work as in XML-1.0 before namespaces, and use prefix:localname
as the new element name (and no namespace of course)
Also fix 3 cases in the regression tests where the prefix: was
erroneously dropped in such case
* HTMLparser.c parser.c SAX2.c debugXML.c tree.c valid.c xmlreader.c
xmllint.c include/libxml/HTMLparser.h include/libxml/parser.h:
added a parser XML_PARSE_COMPACT option to allocate small
text nodes (less than 8 bytes on 32bits, less than 16bytes on 64bits)
directly within the node, various changes to cope with this.
* result/XPath/tests/* result/XPath/xptr/* result/xmlid/*: this
slightly change the output
Daniel
* xpath.c: relaxed id() to not check taht the name(s) passed
are actually NCName, decided this in agreement with Aleksey Sanin
since existing specs like Visa3D broke that conformance checking
and other tools seems to not implement it sigh...
* SAX2.c: check attribute decls for xml:id and the value is an
NCName.
* test/xmlid/id_err* result/xmlid/id_err*: added error testing
Daniel
