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

Lib/html/parser.py

@@ -434,6 +434,7 @@ class HTMLParser(_markupbase.ParserBase):
             return s
         def replaceEntities(s):
             s = s.groups()[0]
+            try:
                 if s[0] == "#":
                     s = s[1:]
                     if s[0] in ['x','X']:
@@ -441,6 +442,8 @@ class HTMLParser(_markupbase.ParserBase):
                     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

@@ -356,6 +356,11 @@ class HTMLParserTolerantTestCase(TestCaseBase):
                                 [('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)