From ce3d003c32b156e91e85ac390fe739d32d6fde95 Mon Sep 17 00:00:00 2001
From: Charalampos Stratakis <cstratak@redhat.com>
Date: May 14 2019 05:23:31 +0000
Subject: Fix handling of pre-normalization characters in urlsplit


---

diff --git a/00320-CVE-2019-9636.patch b/00320-CVE-2019-9636.patch
index 45a2c8e..8f63675 100644
--- a/00320-CVE-2019-9636.patch
+++ b/00320-CVE-2019-9636.patch
@@ -148,3 +148,45 @@ index 000000000000..5546394157f9
 +Changes urlsplit() to raise ValueError when the URL contains characters that
 +decompose under IDNA encoding (NFKC-normalization) into characters that
 +affect how the URL is parsed.
+diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
+index 0faf2bb..d0365ec 100644
+--- 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 8b6c9b1..e2f7b69 100644
+--- 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/python3.spec b/python3.spec
index dd58233..96c9d9a 100644
--- a/python3.spec
+++ b/python3.spec
@@ -14,7 +14,7 @@ URL: https://www.python.org/
 #  WARNING  When rebasing to a new Python version,
 #           remember to update the python3-docs package as well
 Version: %{pybasever}.8
-Release: 3%{?dist}
+Release: 4%{?dist}
 License: Python
 
 
@@ -376,6 +376,9 @@ Patch317: 00317-CVE-2019-5010.patch
 # 00320 #
 # Security fix for CVE-2019-9636: Information Disclosure due to urlsplit improper NFKC normalization
 # Fixed upstream https://bugs.python.org/issue36216
+# Fix handling of pre-normalization characters in urlsplit()
+# This fixes a regression introduced by the fix for CVE-2019-9636
+# Fixed upstream: https://bugs.python.org/issue36742
 Patch320: 00320-CVE-2019-9636.patch
 
 # (New patches go here ^^^)
@@ -1590,6 +1593,9 @@ CheckPython optimized
 # ======================================================
 
 %changelog
+* Wed May 08 2019 Charalampos Stratakis <cstratak@redhat.com> - 3.6.8-4
+- Fix handling of pre-normalization characters in urlsplit
+
 * Thu Mar 14 2019 Miro Hrončok <mhroncok@redhat.com> - 3.6.8-3
 - Security fix for CVE-2019-9636 (#1688543, #1688546)