bpo-36742: Fixes handling of pre-normalization characters in urlsplit() (GH-13017)

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 0faf2bbb645924d276bb79dd48e6268878347766..d0365ecab72ccb188e7aa70a280f2eb4e91ffb09 100644 (file)
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -1011,6 +1011,12 @@ class UrlParseTestCase(unittest.TestCase):
         self.assertIn('\u2100', denorm_chars)
         self.assertIn('\uFF03', denorm_chars)
 
+        # bpo-36742: Verify port separators are ignored when they
+        # existed prior to decomposition
+        urllib.parse.urlsplit('http://\u30d5\u309a:80')
+        with self.assertRaises(ValueError):
+            urllib.parse.urlsplit('http://\u30d5\u309a\ufe1380')
+
         for scheme in ["http", "https", "ftp"]:
             for c in denorm_chars:
                 url = "{}://netloc{}false.netloc/path".format(scheme, c)

diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index fb518a97749ccb937e0c3ddec0d095bc1a48e173..dfba704144e9b4bd05e75ec0159e853ac5231d97 100644 (file)
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -402,13 +402,16 @@ def _checknetloc(netloc):
     # looking for characters like \u2100 that expand to 'a/c'
     # IDNA uses NFKC equivalence, so normalize for this check
     import unicodedata
-    netloc2 = unicodedata.normalize('NFKC', netloc)
-    if netloc == netloc2:
+    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('?', '')
+    netloc2 = unicodedata.normalize('NFKC', n)
+    if n == netloc2:
         return
-    _, _, netloc = netloc.rpartition('@') # anything to the left of '@' is okay
     for c in '/?#@:':
         if c in netloc2:
-            raise ValueError("netloc '" + netloc2 + "' contains invalid " +
+            raise ValueError("netloc '" + netloc + "' contains invalid " +
                              "characters under NFKC normalization")
 
 def urlsplit(url, scheme='', allow_fragments=True):

diff --git a/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst
new file mode 100644 (file)
index 0000000..d729ed2
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst
@@ -0,0 +1 @@
+Fixes mishandling of pre-normalization characters in urlsplit().