Teach unquote() to handle unicode inputs
diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
index 94f0f9e..4579c47 100644
--- a/Lib/test/test_urllib.py
+++ b/Lib/test/test_urllib.py
@@ -415,6 +415,10 @@
self.assertEqual(expect, result,
"using unquote_plus(): %s != %s" % (expect, result))
+ def test_unquote_with_unicode(self):
+ r = urllib.unquote(u'br%C3%BCckner_sapporo_20050930.doc')
+ self.assertEqual(r, u'br\xc3\xbcckner_sapporo_20050930.doc')
+
class urlencode_Tests(unittest.TestCase):
"""Tests for urlencode()"""
diff --git a/Lib/urllib.py b/Lib/urllib.py
index bc16be0..f00d02f 100644
--- a/Lib/urllib.py
+++ b/Lib/urllib.py
@@ -1061,6 +1061,8 @@
res[i] = _hextochr[item[:2]] + item[2:]
except KeyError:
res[i] = '%' + item
+ except UnicodeDecodeError:
+ res[i] = unichr(int(item[:2], 16)) + item[2:]
return "".join(res)
def unquote_plus(s):