diff options
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/html/parser.py | 1 | ||||
| -rw-r--r-- | Lib/test/test_htmlparser.py | 14 |
2 files changed, 15 insertions, 0 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py index f8ac828..60a322a 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -249,6 +249,7 @@ 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) diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index c5d878d..b15b6fd 100644 --- a/Lib/test/test_htmlparser.py +++ b/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;') |