summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorSteve Dower <steve.dower@python.org>2019-06-04 15:55:30 (GMT)
committerƁukasz Langa <lukasz@langa.pl>2019-06-04 15:55:29 (GMT)
commit8d0ef0b5edeae52960c7ed05ae8a12388324f87e (patch)
tree2efb997f81c7e84a3864f39157661cb0bf06f06f
parent800d78637034d77c099d49c4fe99e1fe773da700 (diff)
downloadcpython-8d0ef0b5edeae52960c7ed05ae8a12388324f87e.zip
cpython-8d0ef0b5edeae52960c7ed05ae8a12388324f87e.tar.gz
cpython-8d0ef0b5edeae52960c7ed05ae8a12388324f87e.tar.bz2
bpo-36742: Corrects fix to handle decomposition in usernames (#13812)
-rw-r--r--Lib/test/test_urlparse.py11
-rw-r--r--Lib/urllib/parse.py6
2 files changed, 9 insertions, 8 deletions
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 4344765..4ae6ed3 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -1018,11 +1018,12 @@ class UrlParseTestCase(unittest.TestCase):
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 daefb20..b660878 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -402,9 +402,9 @@ 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: