diff options
| -rw-r--r-- | Doc/library/urllib.parse.rst | 5 | ||||
| -rw-r--r-- | Lib/test/test_urlparse.py | 4 | ||||
| -rw-r--r-- | Lib/urllib/parse.py | 14 |
3 files changed, 12 insertions, 11 deletions
diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst index ac05503..4900005 100644 --- a/Doc/library/urllib.parse.rst +++ b/Doc/library/urllib.parse.rst @@ -88,6 +88,9 @@ The :mod:`urllib.parse` module defines the following functions: See section :ref:`urlparse-result-object` for more information on the result object. + .. versionchanged:: 3.2 + Added IPv6 URL parsing capabilities. + .. function:: parse_qs(qs, keep_blank_values=False, strict_parsing=False) @@ -329,7 +332,7 @@ The :mod:`urllib.parse` module defines the following functions: :rfc:`3986` - Uniform Resource Identifiers This is the current standard (STD66). Any changes to urlparse module should conform to this. Certain deviations could be observed, which are - mostly due backward compatiblity purposes and for certain to de-facto + mostly due backward compatiblity purposes and for certain de-facto parsing requirements as commonly observed in major browsers. :rfc:`2732` - Format for Literal IPv6 Addresses in URL's. diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index a0b2d77..f67487d 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -273,10 +273,10 @@ class UrlParseTestCase(unittest.TestCase): for invalid_url in [ 'http://::12.34.56.78]/', 'http://[::1/foo/', + 'ftp://[::1/foo/bad]/bad', 'http://[::1/foo/bad]/bad', 'http://[::ffff:12.34.56.78']: - self.assertRaises(ValueError, lambda : urllib.parse.urlparse(invalid_url).hostname) - self.assertRaises(ValueError, lambda : urllib.parse.urlparse(invalid_url)) + self.assertRaises(ValueError, urllib.parse.urlparse, invalid_url) def test_urldefrag(self): for url, defrag, frag in [ diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index 4f48b25..3d541a7 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -181,10 +181,9 @@ def urlsplit(url, scheme='', allow_fragments=True): url = url[i+1:] if url[:2] == '//': netloc, url = _splitnetloc(url, 2) - if '[' in netloc : - if not ']' in netloc: raise ValueError("Invalid IPv6 URL") - if ']' in netloc: - if not '[' in netloc: raise ValueError("Invalid IPv6 URL") + if (('[' in netloc and ']' not in netloc) or + (']' in netloc and '[' not in netloc)): + raise ValueError("Invalid IPv6 URL") if allow_fragments and '#' in url: url, fragment = url.split('#', 1) if '?' in url: @@ -199,10 +198,9 @@ def urlsplit(url, scheme='', allow_fragments=True): scheme, url = url[:i].lower(), url[i+1:] if url[:2] == '//': netloc, url = _splitnetloc(url, 2) - if '[' in netloc: - if not ']' in netloc: raise ValueError("Invalid IPv6 URL") - if ']' in netloc: - if not '[' in netloc: raise ValueError("Invalid IPv6 URL") + 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: |