Teach unquote() to handle unicode inputs

Lib/test/test_urllib.py

@@ -415,6 +415,10 @@ class UnquotingTests(unittest.TestCase):
         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()"""
 

Lib/urllib.py

@@ -1061,6 +1061,8 @@ def unquote(s):
             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):