[Python-3000-checkins] r65680 - in python/branches/py3k/Lib: test/test_urlparse.py urllib/parse.py

[facundo.batista]

Author: facundo.batista
Date: Thu Aug 14 18:55:14 2008
New Revision: 65680

Log:

Issue 1432. Fixes a bug caused because of the evolution
of the RFC that describes the behaviour. Note that we now
have the same behaviour than the current browsers.


Modified:
python/branches/py3k/Lib/test/test_urlparse.py
python/branches/py3k/Lib/urllib/parse.py

Modified: python/branches/py3k/Lib/test/test_urlparse.py
==============================================================================
--- python/branches/py3k/Lib/test/test_urlparse.py (original)
+++ python/branches/py3k/Lib/test/test_urlparse.py Thu Aug 14 18:55:14 2008
@@ -6,6 +6,7 @@

RFC1808_BASE = "http://a/b/c/d;p?q#f"
RFC2396_BASE = "http://a/b/c/d;p?q"
+RFC3986_BASE = "http://a/b/c/d;p?q"

class UrlParseTestCase(unittest.TestCase):

@@ -167,8 +168,6 @@
def test_RFC2396(self):
# cases from RFC 2396

- self.checkJoin(RFC2396_BASE, '?y', 'http://a/b/c/?y')
- self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x')

self.checkJoin(RFC2396_BASE, 'g:h', 'g:h')
self.checkJoin(RFC2396_BASE, 'g', 'http://a/b/c/g')
@@ -210,6 +209,14 @@
self.checkJoin(RFC2396_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x')
self.checkJoin(RFC2396_BASE, 'g#s/../x', 'http://a/b/c/g#s/../x')

+ #The following scenarios have been updated in RFC3986
+ #self.checkJoin(RFC2396_BASE, '?y', 'http://a/b/c/?y')
+ #self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x')
+
+ def test_RFC3986(self):
+ self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y')
+ self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x')
+
def test_urldefrag(self):
for url, defrag, frag in [
('http://python.org#frag', 'http://python.org', 'frag'),

Modified: python/branches/py3k/Lib/urllib/parse.py
==============================================================================
--- python/branches/py3k/Lib/urllib/parse.py (original)
+++ python/branches/py3k/Lib/urllib/parse.py Thu Aug 14 18:55:14 2008
@@ -219,9 +219,18 @@
if path[:1] == '/':
return urlunparse((scheme, netloc, path,
params, query, fragment))
- if not (path or params or query):
- return urlunparse((scheme, netloc, bpath,
- bparams, bquery, fragment))
+ if not path:
+ path = bpath
+ if not params:
+ params = bparams
+ else:
+ path = path[:-1]
+ return urlunparse((scheme, netloc, path,
+ params, query, fragment))
+ if not query:
+ query = bquery
+ return urlunparse((scheme, netloc, path,
+ params, query, fragment))
segments = bpath.split('/')[:-1] + path.split('/')
# XXX The stuff below is bogus in various ways...
if segments[-1] == '.':