bpo-36742: Fixes handling of pre-normalization characters in urlsplit() (GH-13017)
(cherry picked from commit d537ab0ff9767ef024f26246899728f0116b1ec3)
Co-authored-by: Steve Dower <steve.dower@python.org>
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 1eec26e..f5b3487 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -397,13 +397,16 @@
# 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):