# HG changeset patch # Parent 0a47d0cd92e29731059972f5985cc7d073754adb diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst --- a/Doc/library/urllib.parse.rst +++ b/Doc/library/urllib.parse.rst @@ -43,16 +43,33 @@ The :mod:`urllib.parse` module defines t params='', query='', fragment='') >>> o.scheme 'http' >>> o.port 80 >>> o.geturl() 'http://www.cwi.nl:80/%7Eguido/Python.html' + If the scheme value is not specified, urlparse following the syntax + specifications from RFC 1808, expects the netloc value to start with '//', + Otherwise, it is not possible to distinguish between net_loc and path + component and would classify the indistinguishable component as path as in + a relative url. + + >>> from urlparse import urlparse + >>> urlparse('//www.cwi.nl:80/%7Eguido/Python.html') + ParseResult(scheme='', netloc='www.cwi.nl:80', path='/%7Eguido/Python.html', + params='', query='', fragment='') + >>> urlparse('www.cwi.nl:80/%7Eguido/Python.html') + ParseResult(scheme='', netloc='', path='www.cwi.nl:80/%7Eguido/Python.html', + params='', query='', fragment='') + >>> urlparse('help/Python.html') + ParseResult(scheme='', netloc='', path='help/Python.html', params='', + query='', fragment='') + If the *scheme* argument is specified, it gives the default addressing scheme, to be used only if the URL does not specify one. The default value for this argument is the empty string. If the *allow_fragments* argument is false, fragment identifiers are not allowed, even if the URL's addressing scheme normally does support them. The default value for this argument is :const:`True`. diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -456,16 +456,37 @@ class UrlParseTestCase(unittest.TestCase self.assertEqual(p.port, None) self.assertEqual(p.geturl(), uri) def test_noslash(self): # Issue 1637: http://foo.com?query is legal self.assertEqual(urllib.parse.urlparse("http://example.com?blahblah=/foo"), ('http', 'example.com', '', '', 'blahblah=/foo', '')) + def test_withoutscheme(self): + # Test urlparse without scheme + # Issue 754016: urlparse goes wrong with IP:port without scheme + # RFC 1808 specifies that netloc should start with //, urlparse expects + # the same, otherwise it classifies the portion of url as path. + self.assertEqual(urlparse.urlparse("path"), + ('','','path','','','')) + self.assertEqual(urlparse.urlparse("//www.python.org:80"), + ('','www.python.org:80','','','','')) + self.assertEqual(urlparse.urlparse("http://www.python.org:80"), + ('http','www.python.org:80','','','','')) + + def test_portseparator(self): + # Issue 754016 makes changes for port separator ':' from scheme separator + self.assertEqual(urlparse.urlparse("path:80"), + ('','','path:80','','','')) + self.assertEqual(urlparse.urlparse("http:"),('http','','','','','')) + self.assertEqual(urlparse.urlparse("https:"),('https','','','','','')) + self.assertEqual(urlparse.urlparse("http://www.python.org:80"), + ('http','www.python.org:80','','','','')) + def test_usingsys(self): # Issue 3314: sys module is used in the error self.assertRaises(TypeError, urllib.parse.urlencode, "foo") def test_anyscheme(self): # Issue 7904: s3://foo.com/stuff has netloc "foo.com". self.assertEqual(urllib.parse.urlparse("s3://foo.com/stuff"), ('s3', 'foo.com', '/stuff', '', '', '')) diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -187,21 +187,22 @@ def urlsplit(url, scheme='', allow_fragm raise ValueError("Invalid IPv6 URL") if allow_fragments and '#' in url: url, fragment = url.split('#', 1) if '?' in url: url, query = url.split('?', 1) v = SplitResult(scheme, netloc, url, query, fragment) _parse_cache[key] = v return v - for c in url[:i]: - if c not in scheme_chars: - break - else: - scheme, url = url[:i].lower(), url[i+1:] + if (len(url) == i+1) or (not url[i+1].isdigit()): + for c in url[:i]: + if c not in scheme_chars: + break + else: + scheme, url = url[:i].lower(), url[i+1:] if url[:2] == '//': netloc, url = _splitnetloc(url, 2) 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: url, fragment = url.split('#', 1) if scheme in uses_query and '?' in url: