commit 3f60f09eb23be3289ac5cc019391711dcdf800b3
author Senthil Kumaran <orsenthil@gmail.com> Tue Dec 28 16:05:07 2010 +0000
committer Senthil Kumaran <orsenthil@gmail.com> Tue Dec 28 16:05:07 2010 +0000
tree 25930497b54b42a4c61318d5ede15fded795d149
parent 06fdbedf81c49fd9614379ebd68d6388525bf42f

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

Lib/HTMLParser.py

diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
index 7cee47a..4fdc09a 100644
--- a/Lib/HTMLParser.py
+++ b/Lib/HTMLParser.py
@@ -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

Lib/test/test_htmlparser.py

diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index c45cf00..717585c 100644
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -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)