[svn r3819] r4487@delle: sbehnel | 2008-06-06 13:56:34 +0200

always set 'UTF-8' as document encoding if it wasn't provided - keeps the serialiser from escaping attribute values --HG-- branch : trunk
SimonSapin · Jun 6, 2008 · 5ceb85b · 5ceb85b
1 parent 8dbad3a
commit 5ceb85b
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 3 deletions.
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -57,6 +57,9 @@ Bugs fixed
 Other changes
 -------------
 
+* Non-ASCII characters in attribute values are no longer escaped on
+  serialisation.
+
 * Passing non-ASCII byte strings or invalid unicode strings as .tag,
   namespaces, etc. will result in a ValueError instead of an
   AssertionError (just like the tag well-formedness check).

diff --git a/src/lxml/parser.pxi b/src/lxml/parser.pxi
@@ -588,8 +588,11 @@ cdef xmlDoc* _handleParseResult(_ParserContext context,
             _raiseParseError(c_ctxt, filename, context._error_log)
         else:
             _raiseParseError(c_ctxt, filename, None)
-    elif result.URL is NULL and filename is not None:
-        result.URL = tree.xmlStrdup(_cstr(filename))
+    else:
+        if result.URL is NULL and filename is not None:
+            result.URL = tree.xmlStrdup(_cstr(filename))
+        if result.encoding is NULL:
+            result.encoding = tree.xmlStrdup("UTF-8")
     return result
 
 cdef int _fixHtmlDictNames(tree.xmlDict* c_dict, xmlDoc* c_doc) nogil:
@@ -1366,6 +1369,8 @@ cdef xmlDoc* _newXMLDoc() except NULL:
     result = tree.xmlNewDoc(NULL)
     if result is NULL:
         python.PyErr_NoMemory()
+    if result.encoding is NULL:
+        result.encoding = tree.xmlStrdup("UTF-8")
     __GLOBAL_PARSER_CONTEXT.initDocDict(result)
     return result
 

diff --git a/src/lxml/tests/test_etree.py b/src/lxml/tests/test_etree.py
@@ -1931,7 +1931,7 @@ def test_docinfo_empty(self):
         xml = _bytes('<html><body></body></html>')
         tree = etree.parse(BytesIO(xml))
         docinfo = tree.docinfo
-        self.assertEquals(docinfo.encoding,    None)
+        self.assertEquals(docinfo.encoding,    "UTF-8")
         self.assertEquals(docinfo.xml_version, "1.0")
         self.assertEquals(docinfo.public_id,   None)
         self.assertEquals(docinfo.system_url,  None)