python3/00320-fix-pre-normalization-chars-in-urlsplit.patch
2019-05-07 15:46:35 +00:00

43 lines
1.9 KiB
Diff

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 0faf2bb..d0365ec 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -1011,6 +1011,12 @@ class UrlParseTestCase(unittest.TestCase):
self.assertIn('\u2100', 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 c in denorm_chars:
url = "{}://netloc{}false.netloc/path".format(scheme, c)
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 8b6c9b1..e2f7b69 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -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):