commit 164540fee1f5909364e0758bbb948ee6f7387f14
author Senthil Kumaran <orsenthil@gmail.com> Tue Dec 28 15:55:16 2010 +0000
committer Senthil Kumaran <orsenthil@gmail.com> Tue Dec 28 15:55:16 2010 +0000
tree 1b8e4bac5472f3c350384e3c6daa293dbfae17c5
parent 3b4499c5c7718a2aca8558b857dfe02cc4a80cd9

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

Lib/html/parser.py

diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index 8d275ab..21ebbc3 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -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

Lib/test/test_htmlparser.py

diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index beaf6b6..5ecd016 100644
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -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)