#17802: Fix an UnboundLocalError in html.parser. Initial tests by Thomas Barlow.
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 @@
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 @@
]
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;')
diff --git a/Misc/NEWS b/Misc/NEWS
index 10f00a4..465ca10 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -44,6 +44,9 @@
Library
-------
+- Issue #17802: Fix an UnboundLocalError in html.parser. Initial tests by
+ Thomas Barlow.
+
- Issue #17192: Restore the patch for Issue #11729 which was ommitted in
3.3.1 when updating the bundled version of libffi used by ctypes. Update
many libffi files that were missed in 3.3.1's update to libffi-3.0.13.