[Python-checkins] r87544 - in python/branches/release27-maint/Lib: HTMLParser.py test/test_htmlparser.py

[senthil.kumaran]

Author: senthil.kumaran
Date: Tue Dec 28 17:05:07 2010
New Revision: 87544

Log:
Fix Issue10759  - HTMLParser.unescape() to handle malform charrefs.



Modified:
   python/branches/release27-maint/Lib/HTMLParser.py
   python/branches/release27-maint/Lib/test/test_htmlparser.py

Modified: python/branches/release27-maint/Lib/HTMLParser.py
==============================================================================
--- python/branches/release27-maint/Lib/HTMLParser.py	(original)
+++ python/branches/release27-maint/Lib/HTMLParser.py	Tue Dec 28 17:05:07 2010
@@ -367,13 +367,16 @@
             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 unichr(c)
+            try:
+                if s[0] == "#":
+                    s = s[1:]
+                    if s[0] in ['x','X']:
+                        c = int(s[1:], 16)
+                    else:
+                        c = int(s)
+                    return unichr(c)
+            except ValueError:
+                return '&#'+s+';'
             else:
                 # Cannot use name2codepoint directly, because HTMLParser supports apos,
                 # which is not part of HTML 4

Modified: python/branches/release27-maint/Lib/test/test_htmlparser.py
==============================================================================
--- python/branches/release27-maint/Lib/test/test_htmlparser.py	(original)
+++ python/branches/release27-maint/Lib/test/test_htmlparser.py	Tue Dec 28 17:05:07 2010
@@ -320,6 +320,11 @@
             ("endtag", "p"),
         ])
 
+    def test_unescape_function(self):
+        parser = HTMLParser.HTMLParser()
+        self.assertEqual(parser.unescape('&#bad;'),'&#bad;')
+        self.assertEqual(parser.unescape('&'),'&')
+
 
 def test_main():
     test_support.run_unittest(HTMLParserTestCase)