From e5f9f4adb95233c66578e6f7ea176687af2f78ca Mon Sep 17 00:00:00 2001
From: "Miss Islington (bot)"
<31488909+miss-islington@users.noreply.github.com>
Date: Thu, 2 May 2019 09:02:35 -0700
Subject: [PATCH] bpo-36742: Fixes handling of pre-normalization characters in
urlsplit() (GH-13017) (GH-13024)
(cherry picked from commit d537ab0ff9767ef024f26246899728f0116b1ec3)
Co-authored-by: Steve Dower <steve.dower@python.org>
---
Lib/test/test_urlparse.py | 6 ++++++
Lib/urllib/parse.py | 11 +++++++----
.../Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst | 1 +
3 files changed, 14 insertions(+), 4 deletions(-)
create mode 100644 Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst
From fd1771dbdd28709716bd531580c40ae5ed814468 Mon Sep 17 00:00:00 2001
From: "Miss Islington (bot)"
<31488909+miss-islington@users.noreply.github.com>
Date: Tue, 4 Jun 2019 11:43:52 -0700
Subject: [PATCH] bpo-36742: Corrects fix to handle decomposition in usernames
(GH-13812) (GH-13814)
(cherry picked from commit 8d0ef0b5edeae52960c7ed05ae8a12388324f87e)
Co-authored-by: Steve Dower <steve.dower@python.org>
---
Lib/test/test_urlparse.py | 11 ++++++-----
Lib/urllib/parse.py | 6 +++---
2 files changed, 9 insertions(+), 8 deletions(-)
--- a/Lib/test/test_urlparse.py 2019-06-17 18:25:59.209410304 +0530
+++ b/Lib/test/test_urlparse.py 2019-06-17 18:32:10.557417721 +0530
@@ -994,12 +994,19 @@ 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)
- with self.subTest(url=url, char='{:04X}'.format(ord(c))):
- with self.assertRaises(ValueError):
- urllib.parse.urlsplit(url)
+ for netloc in ["netloc{}false.netloc", "n{}user@netloc"]:
+ for c in denorm_chars:
+ url = "{}://{}/path".format(scheme, netloc.format(c))
+ with self.subTest(url=url, char='{:04X}'.format(ord(c))):
+ with self.assertRaises(ValueError):
+ urllib.parse.urlsplit(url)
class Utility_Tests(unittest.TestCase):
"""Testcase to test the various utility functions in the urllib."""
--- a/Lib/urllib/parse.py 2019-06-17 18:27:08.097411680 +0530
+++ b/Lib/urllib/parse.py 2019-06-17 18:33:46.965419647 +0530
@@ -397,13 +397,17 @@ def _checknetloc(netloc):
# looking for characters like \u2100 that expand to 'a/c'
# IDNA uses NFKC equivalence, so normalize for this check
import unicodedata
- netloc2 = unicodedata.normalize('NFKC', netloc)
- if netloc == netloc2:
+ n = netloc.replace('@', '') # ignore characters already included
+ n = n.replace(':', '') # but not the surrounding text
+ n = n.replace('#', '')
+ 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):
--- a/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst_org 2019-06-17 18:29:26.413414442 +0530
+++ b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst 2019-06-17 18:29:39.205414698 +0530
@@ -0,0 +1 @@
+Fixes mishandling of pre-normalization characters in urlsplit().