bpo-22347: Update mimetypes.guess_type to allow proper parsing of URLs (GH-15522)
https://bugs.python.org/issue22347
(cherry picked from commit 87bd2071c756188b6cd577889fb1682831142ceb)
Co-authored-by: Dong-hee Na <donghee.na92@gmail.com>
diff --git a/Lib/mimetypes.py b/Lib/mimetypes.py
index 01a16fd..f38005c 100644
--- a/Lib/mimetypes.py
+++ b/Lib/mimetypes.py
@@ -114,7 +114,8 @@
but non-standard types.
"""
url = os.fspath(url)
- scheme, url = urllib.parse._splittype(url)
+ p = urllib.parse.urlparse(url)
+ scheme, url = p.scheme, p.path
if scheme == 'data':
# syntax of data URLs:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
diff --git a/Lib/test/test_mimetypes.py b/Lib/test/test_mimetypes.py
index bfd5eee..7761c3f 100644
--- a/Lib/test/test_mimetypes.py
+++ b/Lib/test/test_mimetypes.py
@@ -51,6 +51,14 @@
eq(self.db.guess_type('foo.xul', strict=False), ('text/xul', None))
eq(self.db.guess_extension('image/jpg', strict=False), '.jpg')
+ def test_url(self):
+ result = self.db.guess_type('http://host.html')
+ msg = 'URL only has a host name, not a file'
+ self.assertSequenceEqual(result, (None, None), msg)
+ result = self.db.guess_type('http://example.com/host.html')
+ msg = 'Should be text/html'
+ self.assertSequenceEqual(result, ('text/html', None), msg)
+
def test_guess_all_types(self):
eq = self.assertEqual
unless = self.assertTrue
diff --git a/Lib/test/test_urllib2.py b/Lib/test/test_urllib2.py
index c6d275e..810ee5e 100644
--- a/Lib/test/test_urllib2.py
+++ b/Lib/test/test_urllib2.py
@@ -744,7 +744,7 @@
["foo", "bar"], "", None),
("ftp://localhost/baz.gif;type=a",
"localhost", ftplib.FTP_PORT, "", "", "A",
- [], "baz.gif", None), # XXX really this should guess image/gif
+ [], "baz.gif", "image/gif"),
]:
req = Request(url)
req.timeout = None