bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812)

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 6fd1071bf7cdec11f3e374cd01bb2d6e7b4a867f..857ed96d92fe2dec2656a80c9ed252e4967b92af 100644 (file)
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -648,12 +648,13 @@ class UrlParseTestCase(unittest.TestCase):
             urlparse.urlsplit(u'http://\u30d5\u309a\ufe1380')
 
         for scheme in [u"http", u"https", u"ftp"]:
-            for c in denorm_chars:
-                url = u"{}://netloc{}false.netloc/path".format(scheme, c)
-                if test_support.verbose:
-                    print "Checking %r" % url
-                with self.assertRaises(ValueError):
-                    urlparse.urlsplit(url)
+            for netloc in [u"netloc{}false.netloc", u"n{}user@netloc"]:
+                for c in denorm_chars:
+                    url = u"{}://{}/path".format(scheme, netloc.format(c))
+                    if test_support.verbose:
+                        print "Checking %r" % url
+                    with self.assertRaises(ValueError):
+                        urlparse.urlsplit(url)
 
 def test_main():
     test_support.run_unittest(UrlParseTestCase)

diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index f08e0fe58432cef3abfd0309ceffa5f55b40292c..6834f3c1798b093364d679777bc3bf5f491c673f 100644 (file)
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -171,17 +171,17 @@ def _checknetloc(netloc):
     # looking for characters like \u2100 that expand to 'a/c'
     # IDNA uses NFKC equivalence, so normalize for this check
     import unicodedata
-    n = netloc.rpartition('@')[2] # ignore anything to the left of '@'
-    n = n.replace(':', '')        # ignore characters already included
-    n = n.replace('#', '')        # but not the surrounding text
-    n = n.replace('?', '')
+    n = netloc.replace(u'@', u'') # ignore characters already included
+    n = n.replace(u':', u'')      # but not the surrounding text
+    n = n.replace(u'#', u'')
+    n = n.replace(u'?', u'')
     netloc2 = unicodedata.normalize('NFKC', n)
     if n == netloc2:
         return
     for c in '/?#@:':
         if c in netloc2:
-            raise ValueError("netloc '" + netloc + "' contains invalid " +
-                             "characters under NFKC normalization")
+            raise ValueError(u"netloc '" + netloc + u"' contains invalid " +
+                             u"characters under NFKC normalization")
 
 def urlsplit(url, scheme='', allow_fragments=True):
     """Parse a URL into 5 components: