Issue9374 - Generic parsing of query and fragment portion of urls for any scheme
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 39a897a..827282c 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -493,6 +493,10 @@
('s3','foo.com','/stuff','','',''))
self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff"),
('x-newscheme','foo.com','/stuff','','',''))
+ self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff?query#fragment"),
+ ('x-newscheme','foo.com','/stuff','','query','fragment'))
+ self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff?query"),
+ ('x-newscheme','foo.com','/stuff','','query',''))
def test_withoutscheme(self):
# Test urlparse without scheme
diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index b42e0f4..32eebe6 100644
--- a/Lib/urlparse.py
+++ b/Lib/urlparse.py
@@ -40,16 +40,9 @@
'imap', 'wais', 'file', 'mms', 'https', 'shttp',
'snews', 'prospero', 'rtsp', 'rtspu', 'rsync', '',
'svn', 'svn+ssh', 'sftp','nfs','git', 'git+ssh']
-non_hierarchical = ['gopher', 'hdl', 'mailto', 'news',
- 'telnet', 'wais', 'imap', 'snews', 'sip', 'sips']
uses_params = ['ftp', 'hdl', 'prospero', 'http', 'imap',
'https', 'shttp', 'rtsp', 'rtspu', 'sip', 'sips',
'mms', '', 'sftp']
-uses_query = ['http', 'wais', 'imap', 'https', 'shttp', 'mms',
- 'gopher', 'rtsp', 'rtspu', 'sip', 'sips', '']
-uses_fragment = ['ftp', 'hdl', 'http', 'gopher', 'news',
- 'nntp', 'wais', 'https', 'shttp', 'snews',
- 'file', 'prospero', '']
# Characters valid in scheme names
scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
@@ -204,9 +197,9 @@
if (('[' in netloc and ']' not in netloc) or
(']' in netloc and '[' not in netloc)):
raise ValueError("Invalid IPv6 URL")
- if allow_fragments and scheme in uses_fragment and '#' in url:
+ if allow_fragments and '#' in url:
url, fragment = url.split('#', 1)
- if scheme in uses_query and '?' in url:
+ if '?' in url:
url, query = url.split('?', 1)
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
diff --git a/Misc/NEWS b/Misc/NEWS
index 088d1e4..646b351 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -60,6 +60,9 @@
Library
-------
+- Issue #9374: Generic parsing of query and fragment portions of url for any
+ scheme. Supported both by RFC3986 and RFC2396.
+
- Issue #14798: Fix the functions in pyclbr to raise an ImportError
when the first part of a dotted name is not a package. Patch by
Xavier de Gaye.