Stowage/cpython
2
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-10-31 13:41:24 +00:00
Code Issues Projects Releases Packages Wiki Activity

bpo-36742: Fixes handling of pre-normalization characters in urlsplit() (GH-13017)

Browse source
This commit is contained in:
Steve Dower 2019-04-30 12:03:02 +00:00 • committed by GitHub
parent b84cb70880
commit d537ab0ff9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 14 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
Lib/test/test_urlparse.py
View file

@ -1011,6 +1011,12 @@ def test_urlsplit_normalization(self):
self.assertIn('\u2100', denorm_chars) self.assertIn('\u2100', denorm_chars)
self.assertIn('\uFF03', 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 scheme in ["http", "https", "ftp"]:
for c in denorm_chars: for c in denorm_chars:
url = "{}://netloc{}false.netloc/path".format(scheme, c) url = "{}://netloc{}false.netloc/path".format(scheme, c)

11
Lib/urllib/parse.py
View file

@ -402,13 +402,16 @@ def _checknetloc(netloc):
# looking for characters like \u2100 that expand to 'a/c' # looking for characters like \u2100 that expand to 'a/c'
# IDNA uses NFKC equivalence, so normalize for this check # IDNA uses NFKC equivalence, so normalize for this check
import unicodedata import unicodedata
netloc2 = unicodedata.normalize('NFKC', netloc) n = netloc.rpartition('@')[2] # ignore anything to the left of '@'
if netloc == netloc2: 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 return
_, _, netloc = netloc.rpartition('@') # anything to the left of '@' is okay
for c in '/?#@:': for c in '/?#@:':
if c in netloc2: if c in netloc2:
raise ValueError("netloc '" + netloc2 + "' contains invalid " + raise ValueError("netloc '" + netloc + "' contains invalid " +
"characters under NFKC normalization") "characters under NFKC normalization")
def urlsplit(url, scheme='', allow_fragments=True): def urlsplit(url, scheme='', allow_fragments=True):

1
Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst Normal file
View file

@ -0,0 +1 @@
Fixes mishandling of pre-normalization characters in urlsplit().