diff options
Diffstat (limited to 'Lib/test/test_urlparse.py')
| -rw-r--r-- | Lib/test/test_urlparse.py | 138 |
1 files changed, 120 insertions, 18 deletions
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index 1775ef3..71abc14 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -17,7 +17,6 @@ parse_qsl_test_cases = [ ("=a", [('', 'a')]), ("a", [('a', '')]), ("a=", [('a', '')]), - ("a=", [('a', '')]), ("&a=b", [('a', 'b')]), ("a=a+b&b=b+c", [('a', 'a b'), ('b', 'b c')]), ("a=1&a=2", [('a', '1'), ('a', '2')]), @@ -28,10 +27,52 @@ parse_qsl_test_cases = [ (b"=a", [(b'', b'a')]), (b"a", [(b'a', b'')]), (b"a=", [(b'a', b'')]), - (b"a=", [(b'a', b'')]), (b"&a=b", [(b'a', b'b')]), (b"a=a+b&b=b+c", [(b'a', b'a b'), (b'b', b'b c')]), (b"a=1&a=2", [(b'a', b'1'), (b'a', b'2')]), + (";", []), + (";;", []), + (";a=b", [('a', 'b')]), + ("a=a+b;b=b+c", [('a', 'a b'), ('b', 'b c')]), + ("a=1;a=2", [('a', '1'), ('a', '2')]), + (b";", []), + (b";;", []), + (b";a=b", [(b'a', b'b')]), + (b"a=a+b;b=b+c", [(b'a', b'a b'), (b'b', b'b c')]), + (b"a=1;a=2", [(b'a', b'1'), (b'a', b'2')]), +] + +parse_qs_test_cases = [ + ("", {}), + ("&", {}), + ("&&", {}), + ("=", {'': ['']}), + ("=a", {'': ['a']}), + ("a", {'a': ['']}), + ("a=", {'a': ['']}), + ("&a=b", {'a': ['b']}), + ("a=a+b&b=b+c", {'a': ['a b'], 'b': ['b c']}), + ("a=1&a=2", {'a': ['1', '2']}), + (b"", {}), + (b"&", {}), + (b"&&", {}), + (b"=", {b'': [b'']}), + (b"=a", {b'': [b'a']}), + (b"a", {b'a': [b'']}), + (b"a=", {b'a': [b'']}), + (b"&a=b", {b'a': [b'b']}), + (b"a=a+b&b=b+c", {b'a': [b'a b'], b'b': [b'b c']}), + (b"a=1&a=2", {b'a': [b'1', b'2']}), + (";", {}), + (";;", {}), + (";a=b", {'a': ['b']}), + ("a=a+b;b=b+c", {'a': ['a b'], 'b': ['b c']}), + ("a=1;a=2", {'a': ['1', '2']}), + (b";", {}), + (b";;", {}), + (b";a=b", {b'a': [b'b']}), + (b"a=a+b;b=b+c", {b'a': [b'a b'], b'b': [b'b c']}), + (b"a=1;a=2", {b'a': [b'1', b'2']}), ] class UrlParseTestCase(unittest.TestCase): @@ -96,6 +137,16 @@ class UrlParseTestCase(unittest.TestCase): self.assertEqual(result, expect_without_blanks, "Error parsing %r" % orig) + def test_qs(self): + for orig, expect in parse_qs_test_cases: + result = urllib.parse.parse_qs(orig, keep_blank_values=True) + self.assertEqual(result, expect, "Error parsing %r" % orig) + expect_without_blanks = {v: expect[v] + for v in expect if len(expect[v][0])} + result = urllib.parse.parse_qs(orig, keep_blank_values=False) + self.assertEqual(result, expect_without_blanks, + "Error parsing %r" % orig) + def test_roundtrips(self): str_cases = [ ('file:///tmp/junk.txt', @@ -210,10 +261,6 @@ class UrlParseTestCase(unittest.TestCase): # "abnormal" cases from RFC 1808: self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f') - self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g') - self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g') - self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g') - self.checkJoin(RFC1808_BASE, '/../g', 'http://a/../g') self.checkJoin(RFC1808_BASE, 'g.', 'http://a/b/c/g.') self.checkJoin(RFC1808_BASE, '.g', 'http://a/b/c/.g') self.checkJoin(RFC1808_BASE, 'g..', 'http://a/b/c/g..') @@ -228,6 +275,13 @@ class UrlParseTestCase(unittest.TestCase): #self.checkJoin(RFC1808_BASE, 'http:g', 'http:g') #self.checkJoin(RFC1808_BASE, 'http:', 'http:') + # XXX: The following tests are no longer compatible with RFC3986 + # self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g') + # self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g') + # self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g') + # self.checkJoin(RFC1808_BASE, '/../g', 'http://a/../g') + + def test_RFC2368(self): # Issue 11467: path that starts with a number is not parsed correctly self.assertEqual(urllib.parse.urlparse('mailto:1337@example.org'), @@ -258,10 +312,6 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin(RFC2396_BASE, '../../', 'http://a/') self.checkJoin(RFC2396_BASE, '../../g', 'http://a/g') self.checkJoin(RFC2396_BASE, '', RFC2396_BASE) - self.checkJoin(RFC2396_BASE, '../../../g', 'http://a/../g') - self.checkJoin(RFC2396_BASE, '../../../../g', 'http://a/../../g') - self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g') - self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g') self.checkJoin(RFC2396_BASE, 'g.', 'http://a/b/c/g.') self.checkJoin(RFC2396_BASE, '.g', 'http://a/b/c/.g') self.checkJoin(RFC2396_BASE, 'g..', 'http://a/b/c/g..') @@ -277,10 +327,17 @@ 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') + # XXX: The following tests are no longer compatible with RFC3986 + # self.checkJoin(RFC2396_BASE, '../../../g', 'http://a/../g') + # self.checkJoin(RFC2396_BASE, '../../../../g', 'http://a/../../g') + # self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g') + # self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g') + + def test_RFC3986(self): # Test cases from RFC3986 self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y') - self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x') + self.checkJoin(RFC3986_BASE, ';x', 'http://a/b/c/;x') self.checkJoin(RFC3986_BASE, 'g:h','g:h') self.checkJoin(RFC3986_BASE, 'g','http://a/b/c/g') self.checkJoin(RFC3986_BASE, './g','http://a/b/c/g') @@ -304,17 +361,17 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin(RFC3986_BASE, '../..','http://a/') self.checkJoin(RFC3986_BASE, '../../','http://a/') self.checkJoin(RFC3986_BASE, '../../g','http://a/g') + self.checkJoin(RFC3986_BASE, '../../../g', 'http://a/g') #Abnormal Examples # The 'abnormal scenarios' are incompatible with RFC2986 parsing # Tests are here for reference. - #self.checkJoin(RFC3986_BASE, '../../../g','http://a/g') - #self.checkJoin(RFC3986_BASE, '../../../../g','http://a/g') - #self.checkJoin(RFC3986_BASE, '/./g','http://a/g') - #self.checkJoin(RFC3986_BASE, '/../g','http://a/g') - + self.checkJoin(RFC3986_BASE, '../../../g','http://a/g') + self.checkJoin(RFC3986_BASE, '../../../../g','http://a/g') + self.checkJoin(RFC3986_BASE, '/./g','http://a/g') + self.checkJoin(RFC3986_BASE, '/../g','http://a/g') self.checkJoin(RFC3986_BASE, 'g.','http://a/b/c/g.') self.checkJoin(RFC3986_BASE, '.g','http://a/b/c/.g') self.checkJoin(RFC3986_BASE, 'g..','http://a/b/c/g..') @@ -354,10 +411,8 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin(SIMPLE_BASE, '../g','http://a/b/g') self.checkJoin(SIMPLE_BASE, '../..','http://a/') self.checkJoin(SIMPLE_BASE, '../../g','http://a/g') - self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g') self.checkJoin(SIMPLE_BASE, './../g','http://a/b/g') self.checkJoin(SIMPLE_BASE, './g/.','http://a/b/c/g/') - self.checkJoin(SIMPLE_BASE, '/./g','http://a/./g') self.checkJoin(SIMPLE_BASE, 'g/./h','http://a/b/c/g/h') self.checkJoin(SIMPLE_BASE, 'g/../h','http://a/b/c/h') self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g') @@ -370,6 +425,27 @@ class UrlParseTestCase(unittest.TestCase): self.checkJoin('', 'http://a/./g', 'http://a/./g') self.checkJoin('svn://pathtorepo/dir1', 'dir2', 'svn://pathtorepo/dir2') self.checkJoin('svn+ssh://pathtorepo/dir1', 'dir2', 'svn+ssh://pathtorepo/dir2') + self.checkJoin('ws://a/b','g','ws://a/g') + self.checkJoin('wss://a/b','g','wss://a/g') + + # XXX: The following tests are no longer compatible with RFC3986 + # self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g') + # self.checkJoin(SIMPLE_BASE, '/./g','http://a/./g') + + # test for issue22118 duplicate slashes + self.checkJoin(SIMPLE_BASE + '/', 'foo', SIMPLE_BASE + '/foo') + + # Non-RFC-defined tests, covering variations of base and trailing + # slashes + self.checkJoin('http://a/b/c/d/e/', '../../f/g/', 'http://a/b/c/f/g/') + self.checkJoin('http://a/b/c/d/e', '../../f/g/', 'http://a/b/f/g/') + self.checkJoin('http://a/b/c/d/e/', '/../../f/g/', 'http://a/f/g/') + self.checkJoin('http://a/b/c/d/e', '/../../f/g/', 'http://a/f/g/') + self.checkJoin('http://a/b/c/d/e/', '../../f/g', 'http://a/b/c/f/g') + self.checkJoin('http://a/b/', '../../f/g/', 'http://a/f/g/') + + # issue 23703: don't duplicate filename + self.checkJoin('a', 'b', 'b') def test_RFC2732(self): str_cases = [ @@ -803,6 +879,16 @@ class UrlParseTestCase(unittest.TestCase): result = urllib.parse.urlencode({'a': Trivial()}, True) self.assertEqual(result, 'a=trivial') + def test_urlencode_quote_via(self): + result = urllib.parse.urlencode({'a': 'some value'}) + self.assertEqual(result, "a=some+value") + result = urllib.parse.urlencode({'a': 'some value/another'}, + quote_via=urllib.parse.quote) + self.assertEqual(result, "a=some%20value%2Fanother") + result = urllib.parse.urlencode({'a': 'some value/another'}, + safe='/', quote_via=urllib.parse.quote) + self.assertEqual(result, "a=some%20value/another") + def test_quote_from_bytes(self): self.assertRaises(TypeError, urllib.parse.quote_from_bytes, 'foo') result = urllib.parse.quote_from_bytes(b'archaeological arcana') @@ -861,6 +947,22 @@ class UrlParseTestCase(unittest.TestCase): quoter = urllib.parse.Quoter(urllib.parse._ALWAYS_SAFE) self.assertIn('Quoter', repr(quoter)) + def test_all(self): + expected = [] + undocumented = { + 'splitattr', 'splithost', 'splitnport', 'splitpasswd', + 'splitport', 'splitquery', 'splittag', 'splittype', 'splituser', + 'splitvalue', + 'Quoter', 'ResultBase', 'clear_cache', 'to_bytes', 'unwrap', + } + for name in dir(urllib.parse): + if name.startswith('_') or name in undocumented: + continue + object = getattr(urllib.parse, name) + if getattr(object, '__module__', None) == 'urllib.parse': + expected.append(name) + self.assertCountEqual(urllib.parse.__all__, expected) + class Utility_Tests(unittest.TestCase): """Testcase to test the various utility functions in the urllib.""" |