Fix some lxp issues

jgraham · jgraham · commit 6437ca65c52e · 2008-04-28T22:23:20.000Z
--HG--
extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%401149
diff --git a/src/html5lib/html5parser.py b/src/html5lib/html5parser.py
@@ -306,6 +306,7 @@ def parseRCDataCData(self, name, attributes, contentType):
         element = self.tree.insertElement(name, attributes)
         self.parser.tokenizer.contentModelFlag = contentModelFlags[contentType]
         for token in self.parser.tokenizer:
+            token = self.parser.normalizeToken(token)
             if token["type"] in ("Characters", "SpaceCharacters"):
                 self.tree.insertText(token["data"])
             elif token["type"] == "ParseError":
diff --git a/src/html5lib/liberalxmlparser.py b/src/html5lib/liberalxmlparser.py
@@ -14,6 +14,8 @@
  * Selectively lowercase only XHTML, but not foreign markup
 """
 
+import sys
+
 import html5parser
 from constants import voidElements, contentModelFlags
 
@@ -25,7 +27,6 @@ class XMLParser(html5parser.HTMLParser):
 
     def __init__(self, *args, **kwargs):
         html5parser.HTMLParser.__init__(self, *args, **kwargs)
-        
         self.phases["initial"] = XmlRootPhase(self, self.tree)
 
     def normalizeToken(self, token):
@@ -68,7 +69,7 @@ class XHTMLParser(XMLParser):
     def __init__(self, *args, **kwargs):
         html5parser.HTMLParser.__init__(self, *args, **kwargs)
         self.phases["initial"] = XmlInitialPhase(self, self.tree)
-        self.phases["rootElement"] = XhmlRootPhase(self, self.tree)
+        self.phases["beforeHtml"] = XhmlRootPhase(self, self.tree)
 
     def normalizeToken(self, token):
         token = XMLParser.normalizeToken(self, token)
@@ -112,7 +113,6 @@ def processEOF(self):
         pass
 
     def processComment(self, data):
-        print repr(data)
         if not data.startswith('?xml') or not data.endswith('?'):
             html5parser.InitialPhase.processComment(self, data)
 
