#17802: merge with 3.3.

Lib/html/parser.py

@@ -251,6 +251,7 @@ class HTMLParser(_markupbase.ParserBase):
                         if self.strict:
                             self.error("EOF in middle of entity or char ref")
                         else:
+                            k = match.end()
                             if k <= i:
                                 k = n
                             i = self.updatepos(i, i + 1)

Lib/test/test_htmlparser.py

@@ -535,6 +535,20 @@ class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
         ]
         self._run_check(html, expected)
 
+    def test_EOF_in_charref(self):
+        # see #17802
+        # This test checks that the UnboundLocalError reported in the issue
+        # is not raised, however I'm not sure the returned values are correct.
+        # Maybe HTMLParser should use self.unescape for these
+        data = [
+            ('a&', [('data', 'a&')]),
+            ('a&b', [('data', 'ab')]),
+            ('a&b ', [('data', 'a'), ('entityref', 'b'), ('data', ' ')]),
+            ('a&b;', [('data', 'a'), ('entityref', 'b')]),
+        ]
+        for html, expected in data:
+            self._run_check(html, expected)
+
     def test_unescape_function(self):
         p = self.get_collector()
         self.assertEqual(p.unescape('&#bad;'),'&#bad;')

Misc/NEWS

@@ -62,6 +62,9 @@ Library
 
 - Issue #14679: add an __all__ (that contains only HTMLParser) to html.parser.
 
+- Issue #17802: Fix an UnboundLocalError in html.parser.  Initial tests by
+  Thomas Barlow.
+
 - Issue #17358: Modules loaded by imp.load_source() and load_compiled() (and by
   extention load_module()) now have a better chance of working when reloaded.