Externalized cdataElements and rcdataElements into constants.py

tbroyer · tbroyer · commit d1422286ffbd · 2007-06-08T23:43:18.000Z
--HG--
extra : convert_revision : svn%3Aacbfec75-9323-0410-a652-858a13e371e0/trunk%40683
diff --git a/src/constants.py b/src/constants.py
@@ -158,6 +158,18 @@
     "input"
 ))
 
+cdataElements = frozenset(('title', 'textarea'))
+
+rcdataElements = frozenset((
+    'style',
+    'script',
+    'xmp',
+    'iframe',
+    'noembed',
+    'noframes',
+    'noscript'
+))
+
 booleanAttributes = {
     "": frozenset(("irrelevant",)),
     "style": frozenset(("scoped",)),
diff --git a/src/html5parser.py b/src/html5parser.py
@@ -31,7 +31,8 @@
 import utils
 from constants import contentModelFlags, spaceCharacters, asciiUpper2Lower
 from constants import scopingElements, formattingElements, specialElements
-from constants import headingElements, tableInsertModeElements, voidElements
+from constants import headingElements, tableInsertModeElements
+from constants import cdataElements, rcdataElements, voidElements
 
 class HTMLParser(object):
     """HTML parser. Generates a tree structure from a stream of (possibly
@@ -86,9 +87,9 @@ def _parse(self, stream, innerHTML=False, container="div",
         if innerHTML:
             self.innerHTML = container.lower()
 
-            if self.innerHTML in ('title', 'textarea'):
+            if self.innerHTML in cdataElements:
                 self.tokenizer.contentModelFlag = tokenizer.contentModelFlags["RCDATA"]
-            elif self.innerHTML in ('style', 'script', 'xmp', 'iframe', 'noembed', 'noframes', 'noscript'):
+            elif self.innerHTML in rcdataElements:
                 self.tokenizer.contentModelFlag = tokenizer.contentModelFlags["CDATA"]
             elif self.innerHTML == 'plaintext':
                 self.tokenizer.contentModelFlag = tokenizer.contentModelFlags["PLAINTEXT"]
