fix some bugs with the doctype identifiers

annevk · annevk · commit 046c791ff230 · 2007-06-18T16:24:32.000Z
--HG--
extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%40751
diff --git a/src/tokenizer.py b/src/tokenizer.py
@@ -735,8 +735,8 @@ def afterDoctypeNameState(self):
             self.tokenQueue.append(self.currentToken)
             self.state = self.states["data"]
         else:
-            charStack = []
-            for x in xrange(6):
+            charStack = [data]  
+            for x in xrange(5):
                 charStack.append(self.stream.char())
             if EOF not in charStack and\
               "".join(charStack).translate(asciiUpper2Lower) == "public":
@@ -816,7 +816,7 @@ def afterDoctypePublicIdentifierState(self):
             self.state = self.states["doctypeSystemIdentifierDoubleQuoted"]
         elif data == "'":
             self.currentToken["systemId"] = ""
-            self.state = self.states["doctypeSystemIdentifierSinglequoted"]
+            self.state = self.states["doctypeSystemIdentifierSingleQuoted"]
         elif data == ">":
             self.tokenQueue.append(self.currentToken)
             self.state = self.states["data"]
@@ -833,14 +833,15 @@ def afterDoctypePublicIdentifierState(self):
         return True
     
     def beforeDoctypeSystemIdentifierState(self):
+        data = self.stream.char()
         if data in spaceCharacters:
             pass
         elif data == "\"":
             self.currentToken["systemId"] = ""
             self.state = self.states["doctypeSystemIdentifierDoubleQuoted"]
         elif data == "'":
             self.currentToken["systemId"] = ""
-            self.state = self.states["doctypeSystemIdentifierSinglequoted"]
+            self.state = self.states["doctypeSystemIdentifierSingleQuoted"]
         elif data == ">":
             self.tokenQueue.append({"type": "ParseError", "data":
               _("Unexpected character in DOCTYPE.")})
