From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Fedora Python maintainers <python-devel@lists.fedoraproject.org>
Date: Wed, 22 Jul 2020 16:38:43 +0200
Subject: [PATCH] 00320-CVE-2019-10160.patch

Security fix for CVE-2019-10160: Information Disclosure due to urlsplit improper NFKC normalization
Fixed upstream for later branches: https://bugs.python.org/issue36742
Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1718867
---
 Lib/test/test_urlparse.py |  6 ++++++
 Lib/urllib/parse.py       | 11 +++++++----
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 77c200729a2..c6c54b03c30 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -885,6 +885,12 @@ 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 243f470a289..da3a40c395c 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -322,13 +322,16 @@ 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):