| |
@@ -0,0 +1,42 @@
|
| |
+ diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
|
| |
+ index 77c2007..c6c54b0 100644
|
| |
+ --- a/Lib/test/test_urlparse.py
|
| |
+ +++ b/Lib/test/test_urlparse.py
|
| |
+ @@ -885,6 +885,12 @@ 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 243f470..da3a40c 100644
|
| |
+ --- a/Lib/urllib/parse.py
|
| |
+ +++ b/Lib/urllib/parse.py
|
| |
+ @@ -322,13 +322,16 @@ 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):
|
| |