[Python-checkins] r87542 - in python/branches/py3k/Lib: html/parser.py test/test_htmlparser.py

[senthil.kumaran]

Author: senthil.kumaran
Date: Tue Dec 28 16:55:16 2010
New Revision: 87542

Log:
Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax



Modified:
   python/branches/py3k/Lib/html/parser.py
   python/branches/py3k/Lib/test/test_htmlparser.py

Modified: python/branches/py3k/Lib/html/parser.py
==============================================================================
--- python/branches/py3k/Lib/html/parser.py	(original)
+++ python/branches/py3k/Lib/html/parser.py	Tue Dec 28 16:55:16 2010
@@ -434,13 +434,16 @@
             return s
         def replaceEntities(s):
             s = s.groups()[0]
-            if s[0] == "#":
-                s = s[1:]
-                if s[0] in ['x','X']:
-                    c = int(s[1:], 16)
-                else:
-                    c = int(s)
-                return chr(c)
+            try:
+                if s[0] == "#":
+                    s = s[1:]
+                    if s[0] in ['x','X']:
+                        c = int(s[1:], 16)
+                    else:
+                        c = int(s)
+                    return chr(c)
+            except ValueError:
+                return '&#'+ s +';'
             else:
                 # Cannot use name2codepoint directly, because HTMLParser
                 # supports apos, which is not part of HTML 4

Modified: python/branches/py3k/Lib/test/test_htmlparser.py
==============================================================================
--- python/branches/py3k/Lib/test/test_htmlparser.py	(original)
+++ python/branches/py3k/Lib/test/test_htmlparser.py	Tue Dec 28 16:55:16 2010
@@ -356,6 +356,11 @@
                                 [('action', 'bogus|&#()value')])],
                         collector = self.collector)
 
+    def test_unescape_function(self):
+        p = html.parser.HTMLParser()
+        self.assertEqual(p.unescape('&#bad;'),'&#bad;')
+        self.assertEqual(p.unescape('&'),'&')
+
 
 def test_main():
     support.run_unittest(HTMLParserTestCase, HTMLParserTolerantTestCase)