46 lines
2.4 KiB
Diff
46 lines
2.4 KiB
Diff
diff -uNrp a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
|
|
--- a/Lib/test/test_urlparse.py 2019-12-21 15:41:32.172000000 +0800
|
|
+++ b/Lib/test/test_urlparse.py 2019-12-21 15:44:28.316000000 +0800
|
|
@@ -641,6 +641,12 @@ class UrlParseTestCase(unittest.TestCase
|
|
self.assertIn(u'\u2100', denorm_chars)
|
|
self.assertIn(u'\uFF03', denorm_chars)
|
|
|
|
+ # bpo-36742: Verify port separators are ignored when they
|
|
+ # existed prior to decomposition
|
|
+ urlparse.urlsplit(u'http://\u30d5\u309a:80')
|
|
+ with self.assertRaises(ValueError):
|
|
+ urlparse.urlsplit(u'http://\u30d5\u309a\ufe1380')
|
|
+
|
|
for scheme in [u"http", u"https", u"ftp"]:
|
|
for c in denorm_chars:
|
|
url = u"{}://netloc{}false.netloc/path".format(scheme, c)
|
|
diff -uNrp a/Lib/urlparse.py b/Lib/urlparse.py
|
|
--- a/Lib/urlparse.py 2019-12-21 15:41:32.080000000 +0800
|
|
+++ b/Lib/urlparse.py 2019-12-21 15:46:11.480000000 +0800
|
|
@@ -171,13 +171,17 @@ 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):
|
|
diff -uNrp a/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst
|
|
--- a/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst 1970-01-01 08:00:00.000000000 +0800
|
|
+++ b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst 2019-12-21 15:53:31.188000000 +0800
|
|
@@ -0,0 +1 @@
|
|
+Fixes mishandling of pre-normalization characters in urlsplit().
|