traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

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.
This commit is contained in:
Facundo Batista 2008-08-14 16:51:00 +00:00
parent 8401eec7fa
commit 67d1981c51
2 changed files with 21 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
Lib/test/test_urlparse.py
View File

@ -6,6 +6,7 @@ import urlparse
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 @@ class UrlParseTestCase(unittest.TestCase):
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 @@ class UrlParseTestCase(unittest.TestCase):
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'),

15
Lib/urlparse.py
View File

@ -217,9 +217,18 @@ def urljoin(base, url, allow_fragments=True):
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] == '.':