1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
|
From 250b62acc59921d399f0db47db3b462cd6037e09 Mon Sep 17 00:00:00 2001
From: "Miss Islington (bot)"
<31488909+miss-islington@users.noreply.github.com>
Date: Tue, 4 Jun 2019 09:15:13 -0700
Subject: [PATCH] bpo-36742: Corrects fix to handle decomposition in usernames
(GH-13812)
(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(-)
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index c26235449461..68f633ca3a7d 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -1008,11 +1008,12 @@ def test_urlsplit_normalization(self):
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."""
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index f5b3487ea9d6..4c8e77fe3912 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -397,9 +397,9 @@ 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 = 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:
|
