summaryrefslogtreecommitdiff
path: root/Lib/urlparse.py
diff options
context:
space:
mode:
Diffstat (limited to 'Lib/urlparse.py')
-rw-r--r--Lib/urlparse.py14
1 files changed, 9 insertions, 5 deletions
diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index 54eda08..798b467 100644
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -171,14 +171,18 @@ 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.replace(u'@', u'') # ignore characters already included
+ n = n.replace(u':', u'') # but not the surrounding text
+ n = n.replace(u'#', u'')
+ n = n.replace(u'?', u'')
+ 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 " +
- "characters under NFKC normalization")
+ raise ValueError("netloc %r contains invalid characters "
+ "under NFKC normalization"
+ % netloc)
def urlsplit(url, scheme='', allow_fragments=True):
"""Parse a URL into 5 components: