mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-28 04:35:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

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

11
Lib/urllib/parse.py
View file

@ -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):