Changed HTMLTokenizer and HTMLInputStream to be old-style classes (improves overall parse performance by 15-20%).

philiptaylor · philiptaylor · commit 52121ff2e853 · 2008-12-17T00:05:47.000Z
(It seems unlikely that anyone will be depending on the new-style class semantics here.)

--HG--
extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%401235
diff --git a/src/html5lib/inputstream.py b/src/html5lib/inputstream.py
@@ -18,7 +18,7 @@
 # Cache for charsUntil()
 charsUntilRegEx = {}
 
-class HTMLInputStream(object):
+class HTMLInputStream:
     """Provides a unicode stream of characters to the HTMLTokenizer.
 
     This class takes care of character encoding and removing or replacing
diff --git a/src/html5lib/tokenizer.py b/src/html5lib/tokenizer.py
@@ -21,7 +21,7 @@
 for e in entities:
     entitiesByFirstChar.setdefault(e[0], []).append(e)
 
-class HTMLTokenizer(object):
+class HTMLTokenizer:
     """ This class takes care of tokenizing HTML.
 
     * self.currentToken
