[2.7] bpo-36742: Fix urlparse.urlsplit() error message for Unicode URL (GH-13937)

If urlparse.urlsplit() detects an invalid netloc according to NFKC
normalization, the error message type is now str rather than unicode,
and use repr() to format the URL, to prevent <exception str() failed>
when display the error message.

1 files changed, 9 insertions, 0 deletions

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 857ed96..86c4a05 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -656,6 +656,15 @@ class UrlParseTestCase(unittest.TestCase):
                     with self.assertRaises(ValueError):
                         urlparse.urlsplit(url)
 
+        # check error message: invalid netloc must be formated with repr()
+        # to get an ASCII error message
+        with self.assertRaises(ValueError) as cm:
+            urlparse.urlsplit(u'http://example.com\uFF03@bing.com')
+        self.assertEqual(str(cm.exception),
+                         "netloc u'example.com\\uff03@bing.com' contains invalid characters "
+                         "under NFKC normalization")
+        self.assertIsInstance(cm.exception.args[0], str)
+
 def test_main():
     test_support.run_unittest(UrlParseTestCase)