| 1 | n/a | import unittest |
|---|
| 2 | n/a | import urllib.parse |
|---|
| 3 | n/a | |
|---|
| 4 | n/a | RFC1808_BASE = "http://a/b/c/d;p?q#f" |
|---|
| 5 | n/a | RFC2396_BASE = "http://a/b/c/d;p?q" |
|---|
| 6 | n/a | RFC3986_BASE = 'http://a/b/c/d;p?q' |
|---|
| 7 | n/a | SIMPLE_BASE = 'http://a/b/c/d' |
|---|
| 8 | n/a | |
|---|
| 9 | n/a | # A list of test cases. Each test case is a two-tuple that contains |
|---|
| 10 | n/a | # a string with the query and a dictionary with the expected result. |
|---|
| 11 | n/a | |
|---|
| 12 | n/a | parse_qsl_test_cases = [ |
|---|
| 13 | n/a | ("", []), |
|---|
| 14 | n/a | ("&", []), |
|---|
| 15 | n/a | ("&&", []), |
|---|
| 16 | n/a | ("=", [('', '')]), |
|---|
| 17 | n/a | ("=a", [('', 'a')]), |
|---|
| 18 | n/a | ("a", [('a', '')]), |
|---|
| 19 | n/a | ("a=", [('a', '')]), |
|---|
| 20 | n/a | ("&a=b", [('a', 'b')]), |
|---|
| 21 | n/a | ("a=a+b&b=b+c", [('a', 'a b'), ('b', 'b c')]), |
|---|
| 22 | n/a | ("a=1&a=2", [('a', '1'), ('a', '2')]), |
|---|
| 23 | n/a | (b"", []), |
|---|
| 24 | n/a | (b"&", []), |
|---|
| 25 | n/a | (b"&&", []), |
|---|
| 26 | n/a | (b"=", [(b'', b'')]), |
|---|
| 27 | n/a | (b"=a", [(b'', b'a')]), |
|---|
| 28 | n/a | (b"a", [(b'a', b'')]), |
|---|
| 29 | n/a | (b"a=", [(b'a', b'')]), |
|---|
| 30 | n/a | (b"&a=b", [(b'a', b'b')]), |
|---|
| 31 | n/a | (b"a=a+b&b=b+c", [(b'a', b'a b'), (b'b', b'b c')]), |
|---|
| 32 | n/a | (b"a=1&a=2", [(b'a', b'1'), (b'a', b'2')]), |
|---|
| 33 | n/a | (";", []), |
|---|
| 34 | n/a | (";;", []), |
|---|
| 35 | n/a | (";a=b", [('a', 'b')]), |
|---|
| 36 | n/a | ("a=a+b;b=b+c", [('a', 'a b'), ('b', 'b c')]), |
|---|
| 37 | n/a | ("a=1;a=2", [('a', '1'), ('a', '2')]), |
|---|
| 38 | n/a | (b";", []), |
|---|
| 39 | n/a | (b";;", []), |
|---|
| 40 | n/a | (b";a=b", [(b'a', b'b')]), |
|---|
| 41 | n/a | (b"a=a+b;b=b+c", [(b'a', b'a b'), (b'b', b'b c')]), |
|---|
| 42 | n/a | (b"a=1;a=2", [(b'a', b'1'), (b'a', b'2')]), |
|---|
| 43 | n/a | ] |
|---|
| 44 | n/a | |
|---|
| 45 | n/a | parse_qs_test_cases = [ |
|---|
| 46 | n/a | ("", {}), |
|---|
| 47 | n/a | ("&", {}), |
|---|
| 48 | n/a | ("&&", {}), |
|---|
| 49 | n/a | ("=", {'': ['']}), |
|---|
| 50 | n/a | ("=a", {'': ['a']}), |
|---|
| 51 | n/a | ("a", {'a': ['']}), |
|---|
| 52 | n/a | ("a=", {'a': ['']}), |
|---|
| 53 | n/a | ("&a=b", {'a': ['b']}), |
|---|
| 54 | n/a | ("a=a+b&b=b+c", {'a': ['a b'], 'b': ['b c']}), |
|---|
| 55 | n/a | ("a=1&a=2", {'a': ['1', '2']}), |
|---|
| 56 | n/a | (b"", {}), |
|---|
| 57 | n/a | (b"&", {}), |
|---|
| 58 | n/a | (b"&&", {}), |
|---|
| 59 | n/a | (b"=", {b'': [b'']}), |
|---|
| 60 | n/a | (b"=a", {b'': [b'a']}), |
|---|
| 61 | n/a | (b"a", {b'a': [b'']}), |
|---|
| 62 | n/a | (b"a=", {b'a': [b'']}), |
|---|
| 63 | n/a | (b"&a=b", {b'a': [b'b']}), |
|---|
| 64 | n/a | (b"a=a+b&b=b+c", {b'a': [b'a b'], b'b': [b'b c']}), |
|---|
| 65 | n/a | (b"a=1&a=2", {b'a': [b'1', b'2']}), |
|---|
| 66 | n/a | (";", {}), |
|---|
| 67 | n/a | (";;", {}), |
|---|
| 68 | n/a | (";a=b", {'a': ['b']}), |
|---|
| 69 | n/a | ("a=a+b;b=b+c", {'a': ['a b'], 'b': ['b c']}), |
|---|
| 70 | n/a | ("a=1;a=2", {'a': ['1', '2']}), |
|---|
| 71 | n/a | (b";", {}), |
|---|
| 72 | n/a | (b";;", {}), |
|---|
| 73 | n/a | (b";a=b", {b'a': [b'b']}), |
|---|
| 74 | n/a | (b"a=a+b;b=b+c", {b'a': [b'a b'], b'b': [b'b c']}), |
|---|
| 75 | n/a | (b"a=1;a=2", {b'a': [b'1', b'2']}), |
|---|
| 76 | n/a | ] |
|---|
| 77 | n/a | |
|---|
| 78 | n/a | class UrlParseTestCase(unittest.TestCase): |
|---|
| 79 | n/a | |
|---|
| 80 | n/a | def checkRoundtrips(self, url, parsed, split): |
|---|
| 81 | n/a | result = urllib.parse.urlparse(url) |
|---|
| 82 | n/a | self.assertEqual(result, parsed) |
|---|
| 83 | n/a | t = (result.scheme, result.netloc, result.path, |
|---|
| 84 | n/a | result.params, result.query, result.fragment) |
|---|
| 85 | n/a | self.assertEqual(t, parsed) |
|---|
| 86 | n/a | # put it back together and it should be the same |
|---|
| 87 | n/a | result2 = urllib.parse.urlunparse(result) |
|---|
| 88 | n/a | self.assertEqual(result2, url) |
|---|
| 89 | n/a | self.assertEqual(result2, result.geturl()) |
|---|
| 90 | n/a | |
|---|
| 91 | n/a | # the result of geturl() is a fixpoint; we can always parse it |
|---|
| 92 | n/a | # again to get the same result: |
|---|
| 93 | n/a | result3 = urllib.parse.urlparse(result.geturl()) |
|---|
| 94 | n/a | self.assertEqual(result3.geturl(), result.geturl()) |
|---|
| 95 | n/a | self.assertEqual(result3, result) |
|---|
| 96 | n/a | self.assertEqual(result3.scheme, result.scheme) |
|---|
| 97 | n/a | self.assertEqual(result3.netloc, result.netloc) |
|---|
| 98 | n/a | self.assertEqual(result3.path, result.path) |
|---|
| 99 | n/a | self.assertEqual(result3.params, result.params) |
|---|
| 100 | n/a | self.assertEqual(result3.query, result.query) |
|---|
| 101 | n/a | self.assertEqual(result3.fragment, result.fragment) |
|---|
| 102 | n/a | self.assertEqual(result3.username, result.username) |
|---|
| 103 | n/a | self.assertEqual(result3.password, result.password) |
|---|
| 104 | n/a | self.assertEqual(result3.hostname, result.hostname) |
|---|
| 105 | n/a | self.assertEqual(result3.port, result.port) |
|---|
| 106 | n/a | |
|---|
| 107 | n/a | # check the roundtrip using urlsplit() as well |
|---|
| 108 | n/a | result = urllib.parse.urlsplit(url) |
|---|
| 109 | n/a | self.assertEqual(result, split) |
|---|
| 110 | n/a | t = (result.scheme, result.netloc, result.path, |
|---|
| 111 | n/a | result.query, result.fragment) |
|---|
| 112 | n/a | self.assertEqual(t, split) |
|---|
| 113 | n/a | result2 = urllib.parse.urlunsplit(result) |
|---|
| 114 | n/a | self.assertEqual(result2, url) |
|---|
| 115 | n/a | self.assertEqual(result2, result.geturl()) |
|---|
| 116 | n/a | |
|---|
| 117 | n/a | # check the fixpoint property of re-parsing the result of geturl() |
|---|
| 118 | n/a | result3 = urllib.parse.urlsplit(result.geturl()) |
|---|
| 119 | n/a | self.assertEqual(result3.geturl(), result.geturl()) |
|---|
| 120 | n/a | self.assertEqual(result3, result) |
|---|
| 121 | n/a | self.assertEqual(result3.scheme, result.scheme) |
|---|
| 122 | n/a | self.assertEqual(result3.netloc, result.netloc) |
|---|
| 123 | n/a | self.assertEqual(result3.path, result.path) |
|---|
| 124 | n/a | self.assertEqual(result3.query, result.query) |
|---|
| 125 | n/a | self.assertEqual(result3.fragment, result.fragment) |
|---|
| 126 | n/a | self.assertEqual(result3.username, result.username) |
|---|
| 127 | n/a | self.assertEqual(result3.password, result.password) |
|---|
| 128 | n/a | self.assertEqual(result3.hostname, result.hostname) |
|---|
| 129 | n/a | self.assertEqual(result3.port, result.port) |
|---|
| 130 | n/a | |
|---|
| 131 | n/a | def test_qsl(self): |
|---|
| 132 | n/a | for orig, expect in parse_qsl_test_cases: |
|---|
| 133 | n/a | result = urllib.parse.parse_qsl(orig, keep_blank_values=True) |
|---|
| 134 | n/a | self.assertEqual(result, expect, "Error parsing %r" % orig) |
|---|
| 135 | n/a | expect_without_blanks = [v for v in expect if len(v[1])] |
|---|
| 136 | n/a | result = urllib.parse.parse_qsl(orig, keep_blank_values=False) |
|---|
| 137 | n/a | self.assertEqual(result, expect_without_blanks, |
|---|
| 138 | n/a | "Error parsing %r" % orig) |
|---|
| 139 | n/a | |
|---|
| 140 | n/a | def test_qs(self): |
|---|
| 141 | n/a | for orig, expect in parse_qs_test_cases: |
|---|
| 142 | n/a | result = urllib.parse.parse_qs(orig, keep_blank_values=True) |
|---|
| 143 | n/a | self.assertEqual(result, expect, "Error parsing %r" % orig) |
|---|
| 144 | n/a | expect_without_blanks = {v: expect[v] |
|---|
| 145 | n/a | for v in expect if len(expect[v][0])} |
|---|
| 146 | n/a | result = urllib.parse.parse_qs(orig, keep_blank_values=False) |
|---|
| 147 | n/a | self.assertEqual(result, expect_without_blanks, |
|---|
| 148 | n/a | "Error parsing %r" % orig) |
|---|
| 149 | n/a | |
|---|
| 150 | n/a | def test_roundtrips(self): |
|---|
| 151 | n/a | str_cases = [ |
|---|
| 152 | n/a | ('file:///tmp/junk.txt', |
|---|
| 153 | n/a | ('file', '', '/tmp/junk.txt', '', '', ''), |
|---|
| 154 | n/a | ('file', '', '/tmp/junk.txt', '', '')), |
|---|
| 155 | n/a | ('imap://mail.python.org/mbox1', |
|---|
| 156 | n/a | ('imap', 'mail.python.org', '/mbox1', '', '', ''), |
|---|
| 157 | n/a | ('imap', 'mail.python.org', '/mbox1', '', '')), |
|---|
| 158 | n/a | ('mms://wms.sys.hinet.net/cts/Drama/09006251100.asf', |
|---|
| 159 | n/a | ('mms', 'wms.sys.hinet.net', '/cts/Drama/09006251100.asf', |
|---|
| 160 | n/a | '', '', ''), |
|---|
| 161 | n/a | ('mms', 'wms.sys.hinet.net', '/cts/Drama/09006251100.asf', |
|---|
| 162 | n/a | '', '')), |
|---|
| 163 | n/a | ('nfs://server/path/to/file.txt', |
|---|
| 164 | n/a | ('nfs', 'server', '/path/to/file.txt', '', '', ''), |
|---|
| 165 | n/a | ('nfs', 'server', '/path/to/file.txt', '', '')), |
|---|
| 166 | n/a | ('svn+ssh://svn.zope.org/repos/main/ZConfig/trunk/', |
|---|
| 167 | n/a | ('svn+ssh', 'svn.zope.org', '/repos/main/ZConfig/trunk/', |
|---|
| 168 | n/a | '', '', ''), |
|---|
| 169 | n/a | ('svn+ssh', 'svn.zope.org', '/repos/main/ZConfig/trunk/', |
|---|
| 170 | n/a | '', '')), |
|---|
| 171 | n/a | ('git+ssh://git@github.com/user/project.git', |
|---|
| 172 | n/a | ('git+ssh', 'git@github.com','/user/project.git', |
|---|
| 173 | n/a | '','',''), |
|---|
| 174 | n/a | ('git+ssh', 'git@github.com','/user/project.git', |
|---|
| 175 | n/a | '', '')), |
|---|
| 176 | n/a | ] |
|---|
| 177 | n/a | def _encode(t): |
|---|
| 178 | n/a | return (t[0].encode('ascii'), |
|---|
| 179 | n/a | tuple(x.encode('ascii') for x in t[1]), |
|---|
| 180 | n/a | tuple(x.encode('ascii') for x in t[2])) |
|---|
| 181 | n/a | bytes_cases = [_encode(x) for x in str_cases] |
|---|
| 182 | n/a | for url, parsed, split in str_cases + bytes_cases: |
|---|
| 183 | n/a | self.checkRoundtrips(url, parsed, split) |
|---|
| 184 | n/a | |
|---|
| 185 | n/a | def test_http_roundtrips(self): |
|---|
| 186 | n/a | # urllib.parse.urlsplit treats 'http:' as an optimized special case, |
|---|
| 187 | n/a | # so we test both 'http:' and 'https:' in all the following. |
|---|
| 188 | n/a | # Three cheers for white box knowledge! |
|---|
| 189 | n/a | str_cases = [ |
|---|
| 190 | n/a | ('://www.python.org', |
|---|
| 191 | n/a | ('www.python.org', '', '', '', ''), |
|---|
| 192 | n/a | ('www.python.org', '', '', '')), |
|---|
| 193 | n/a | ('://www.python.org#abc', |
|---|
| 194 | n/a | ('www.python.org', '', '', '', 'abc'), |
|---|
| 195 | n/a | ('www.python.org', '', '', 'abc')), |
|---|
| 196 | n/a | ('://www.python.org?q=abc', |
|---|
| 197 | n/a | ('www.python.org', '', '', 'q=abc', ''), |
|---|
| 198 | n/a | ('www.python.org', '', 'q=abc', '')), |
|---|
| 199 | n/a | ('://www.python.org/#abc', |
|---|
| 200 | n/a | ('www.python.org', '/', '', '', 'abc'), |
|---|
| 201 | n/a | ('www.python.org', '/', '', 'abc')), |
|---|
| 202 | n/a | ('://a/b/c/d;p?q#f', |
|---|
| 203 | n/a | ('a', '/b/c/d', 'p', 'q', 'f'), |
|---|
| 204 | n/a | ('a', '/b/c/d;p', 'q', 'f')), |
|---|
| 205 | n/a | ] |
|---|
| 206 | n/a | def _encode(t): |
|---|
| 207 | n/a | return (t[0].encode('ascii'), |
|---|
| 208 | n/a | tuple(x.encode('ascii') for x in t[1]), |
|---|
| 209 | n/a | tuple(x.encode('ascii') for x in t[2])) |
|---|
| 210 | n/a | bytes_cases = [_encode(x) for x in str_cases] |
|---|
| 211 | n/a | str_schemes = ('http', 'https') |
|---|
| 212 | n/a | bytes_schemes = (b'http', b'https') |
|---|
| 213 | n/a | str_tests = str_schemes, str_cases |
|---|
| 214 | n/a | bytes_tests = bytes_schemes, bytes_cases |
|---|
| 215 | n/a | for schemes, test_cases in (str_tests, bytes_tests): |
|---|
| 216 | n/a | for scheme in schemes: |
|---|
| 217 | n/a | for url, parsed, split in test_cases: |
|---|
| 218 | n/a | url = scheme + url |
|---|
| 219 | n/a | parsed = (scheme,) + parsed |
|---|
| 220 | n/a | split = (scheme,) + split |
|---|
| 221 | n/a | self.checkRoundtrips(url, parsed, split) |
|---|
| 222 | n/a | |
|---|
| 223 | n/a | def checkJoin(self, base, relurl, expected): |
|---|
| 224 | n/a | str_components = (base, relurl, expected) |
|---|
| 225 | n/a | self.assertEqual(urllib.parse.urljoin(base, relurl), expected) |
|---|
| 226 | n/a | bytes_components = baseb, relurlb, expectedb = [ |
|---|
| 227 | n/a | x.encode('ascii') for x in str_components] |
|---|
| 228 | n/a | self.assertEqual(urllib.parse.urljoin(baseb, relurlb), expectedb) |
|---|
| 229 | n/a | |
|---|
| 230 | n/a | def test_unparse_parse(self): |
|---|
| 231 | n/a | str_cases = ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',] |
|---|
| 232 | n/a | bytes_cases = [x.encode('ascii') for x in str_cases] |
|---|
| 233 | n/a | for u in str_cases + bytes_cases: |
|---|
| 234 | n/a | self.assertEqual(urllib.parse.urlunsplit(urllib.parse.urlsplit(u)), u) |
|---|
| 235 | n/a | self.assertEqual(urllib.parse.urlunparse(urllib.parse.urlparse(u)), u) |
|---|
| 236 | n/a | |
|---|
| 237 | n/a | def test_RFC1808(self): |
|---|
| 238 | n/a | # "normal" cases from RFC 1808: |
|---|
| 239 | n/a | self.checkJoin(RFC1808_BASE, 'g:h', 'g:h') |
|---|
| 240 | n/a | self.checkJoin(RFC1808_BASE, 'g', 'http://a/b/c/g') |
|---|
| 241 | n/a | self.checkJoin(RFC1808_BASE, './g', 'http://a/b/c/g') |
|---|
| 242 | n/a | self.checkJoin(RFC1808_BASE, 'g/', 'http://a/b/c/g/') |
|---|
| 243 | n/a | self.checkJoin(RFC1808_BASE, '/g', 'http://a/g') |
|---|
| 244 | n/a | self.checkJoin(RFC1808_BASE, '//g', 'http://g') |
|---|
| 245 | n/a | self.checkJoin(RFC1808_BASE, 'g?y', 'http://a/b/c/g?y') |
|---|
| 246 | n/a | self.checkJoin(RFC1808_BASE, 'g?y/./x', 'http://a/b/c/g?y/./x') |
|---|
| 247 | n/a | self.checkJoin(RFC1808_BASE, '#s', 'http://a/b/c/d;p?q#s') |
|---|
| 248 | n/a | self.checkJoin(RFC1808_BASE, 'g#s', 'http://a/b/c/g#s') |
|---|
| 249 | n/a | self.checkJoin(RFC1808_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x') |
|---|
| 250 | n/a | self.checkJoin(RFC1808_BASE, 'g?y#s', 'http://a/b/c/g?y#s') |
|---|
| 251 | n/a | self.checkJoin(RFC1808_BASE, 'g;x', 'http://a/b/c/g;x') |
|---|
| 252 | n/a | self.checkJoin(RFC1808_BASE, 'g;x?y#s', 'http://a/b/c/g;x?y#s') |
|---|
| 253 | n/a | self.checkJoin(RFC1808_BASE, '.', 'http://a/b/c/') |
|---|
| 254 | n/a | self.checkJoin(RFC1808_BASE, './', 'http://a/b/c/') |
|---|
| 255 | n/a | self.checkJoin(RFC1808_BASE, '..', 'http://a/b/') |
|---|
| 256 | n/a | self.checkJoin(RFC1808_BASE, '../', 'http://a/b/') |
|---|
| 257 | n/a | self.checkJoin(RFC1808_BASE, '../g', 'http://a/b/g') |
|---|
| 258 | n/a | self.checkJoin(RFC1808_BASE, '../..', 'http://a/') |
|---|
| 259 | n/a | self.checkJoin(RFC1808_BASE, '../../', 'http://a/') |
|---|
| 260 | n/a | self.checkJoin(RFC1808_BASE, '../../g', 'http://a/g') |
|---|
| 261 | n/a | |
|---|
| 262 | n/a | # "abnormal" cases from RFC 1808: |
|---|
| 263 | n/a | self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f') |
|---|
| 264 | n/a | self.checkJoin(RFC1808_BASE, 'g.', 'http://a/b/c/g.') |
|---|
| 265 | n/a | self.checkJoin(RFC1808_BASE, '.g', 'http://a/b/c/.g') |
|---|
| 266 | n/a | self.checkJoin(RFC1808_BASE, 'g..', 'http://a/b/c/g..') |
|---|
| 267 | n/a | self.checkJoin(RFC1808_BASE, '..g', 'http://a/b/c/..g') |
|---|
| 268 | n/a | self.checkJoin(RFC1808_BASE, './../g', 'http://a/b/g') |
|---|
| 269 | n/a | self.checkJoin(RFC1808_BASE, './g/.', 'http://a/b/c/g/') |
|---|
| 270 | n/a | self.checkJoin(RFC1808_BASE, 'g/./h', 'http://a/b/c/g/h') |
|---|
| 271 | n/a | self.checkJoin(RFC1808_BASE, 'g/../h', 'http://a/b/c/h') |
|---|
| 272 | n/a | |
|---|
| 273 | n/a | # RFC 1808 and RFC 1630 disagree on these (according to RFC 1808), |
|---|
| 274 | n/a | # so we'll not actually run these tests (which expect 1808 behavior). |
|---|
| 275 | n/a | #self.checkJoin(RFC1808_BASE, 'http:g', 'http:g') |
|---|
| 276 | n/a | #self.checkJoin(RFC1808_BASE, 'http:', 'http:') |
|---|
| 277 | n/a | |
|---|
| 278 | n/a | # XXX: The following tests are no longer compatible with RFC3986 |
|---|
| 279 | n/a | # self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g') |
|---|
| 280 | n/a | # self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g') |
|---|
| 281 | n/a | # self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g') |
|---|
| 282 | n/a | # self.checkJoin(RFC1808_BASE, '/../g', 'http://a/../g') |
|---|
| 283 | n/a | |
|---|
| 284 | n/a | |
|---|
| 285 | n/a | def test_RFC2368(self): |
|---|
| 286 | n/a | # Issue 11467: path that starts with a number is not parsed correctly |
|---|
| 287 | n/a | self.assertEqual(urllib.parse.urlparse('mailto:1337@example.org'), |
|---|
| 288 | n/a | ('mailto', '', '1337@example.org', '', '', '')) |
|---|
| 289 | n/a | |
|---|
| 290 | n/a | def test_RFC2396(self): |
|---|
| 291 | n/a | # cases from RFC 2396 |
|---|
| 292 | n/a | |
|---|
| 293 | n/a | |
|---|
| 294 | n/a | self.checkJoin(RFC2396_BASE, 'g:h', 'g:h') |
|---|
| 295 | n/a | self.checkJoin(RFC2396_BASE, 'g', 'http://a/b/c/g') |
|---|
| 296 | n/a | self.checkJoin(RFC2396_BASE, './g', 'http://a/b/c/g') |
|---|
| 297 | n/a | self.checkJoin(RFC2396_BASE, 'g/', 'http://a/b/c/g/') |
|---|
| 298 | n/a | self.checkJoin(RFC2396_BASE, '/g', 'http://a/g') |
|---|
| 299 | n/a | self.checkJoin(RFC2396_BASE, '//g', 'http://g') |
|---|
| 300 | n/a | self.checkJoin(RFC2396_BASE, 'g?y', 'http://a/b/c/g?y') |
|---|
| 301 | n/a | self.checkJoin(RFC2396_BASE, '#s', 'http://a/b/c/d;p?q#s') |
|---|
| 302 | n/a | self.checkJoin(RFC2396_BASE, 'g#s', 'http://a/b/c/g#s') |
|---|
| 303 | n/a | self.checkJoin(RFC2396_BASE, 'g?y#s', 'http://a/b/c/g?y#s') |
|---|
| 304 | n/a | self.checkJoin(RFC2396_BASE, 'g;x', 'http://a/b/c/g;x') |
|---|
| 305 | n/a | self.checkJoin(RFC2396_BASE, 'g;x?y#s', 'http://a/b/c/g;x?y#s') |
|---|
| 306 | n/a | self.checkJoin(RFC2396_BASE, '.', 'http://a/b/c/') |
|---|
| 307 | n/a | self.checkJoin(RFC2396_BASE, './', 'http://a/b/c/') |
|---|
| 308 | n/a | self.checkJoin(RFC2396_BASE, '..', 'http://a/b/') |
|---|
| 309 | n/a | self.checkJoin(RFC2396_BASE, '../', 'http://a/b/') |
|---|
| 310 | n/a | self.checkJoin(RFC2396_BASE, '../g', 'http://a/b/g') |
|---|
| 311 | n/a | self.checkJoin(RFC2396_BASE, '../..', 'http://a/') |
|---|
| 312 | n/a | self.checkJoin(RFC2396_BASE, '../../', 'http://a/') |
|---|
| 313 | n/a | self.checkJoin(RFC2396_BASE, '../../g', 'http://a/g') |
|---|
| 314 | n/a | self.checkJoin(RFC2396_BASE, '', RFC2396_BASE) |
|---|
| 315 | n/a | self.checkJoin(RFC2396_BASE, 'g.', 'http://a/b/c/g.') |
|---|
| 316 | n/a | self.checkJoin(RFC2396_BASE, '.g', 'http://a/b/c/.g') |
|---|
| 317 | n/a | self.checkJoin(RFC2396_BASE, 'g..', 'http://a/b/c/g..') |
|---|
| 318 | n/a | self.checkJoin(RFC2396_BASE, '..g', 'http://a/b/c/..g') |
|---|
| 319 | n/a | self.checkJoin(RFC2396_BASE, './../g', 'http://a/b/g') |
|---|
| 320 | n/a | self.checkJoin(RFC2396_BASE, './g/.', 'http://a/b/c/g/') |
|---|
| 321 | n/a | self.checkJoin(RFC2396_BASE, 'g/./h', 'http://a/b/c/g/h') |
|---|
| 322 | n/a | self.checkJoin(RFC2396_BASE, 'g/../h', 'http://a/b/c/h') |
|---|
| 323 | n/a | self.checkJoin(RFC2396_BASE, 'g;x=1/./y', 'http://a/b/c/g;x=1/y') |
|---|
| 324 | n/a | self.checkJoin(RFC2396_BASE, 'g;x=1/../y', 'http://a/b/c/y') |
|---|
| 325 | n/a | self.checkJoin(RFC2396_BASE, 'g?y/./x', 'http://a/b/c/g?y/./x') |
|---|
| 326 | n/a | self.checkJoin(RFC2396_BASE, 'g?y/../x', 'http://a/b/c/g?y/../x') |
|---|
| 327 | n/a | self.checkJoin(RFC2396_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x') |
|---|
| 328 | n/a | self.checkJoin(RFC2396_BASE, 'g#s/../x', 'http://a/b/c/g#s/../x') |
|---|
| 329 | n/a | |
|---|
| 330 | n/a | # XXX: The following tests are no longer compatible with RFC3986 |
|---|
| 331 | n/a | # self.checkJoin(RFC2396_BASE, '../../../g', 'http://a/../g') |
|---|
| 332 | n/a | # self.checkJoin(RFC2396_BASE, '../../../../g', 'http://a/../../g') |
|---|
| 333 | n/a | # self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g') |
|---|
| 334 | n/a | # self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g') |
|---|
| 335 | n/a | |
|---|
| 336 | n/a | |
|---|
| 337 | n/a | def test_RFC3986(self): |
|---|
| 338 | n/a | # Test cases from RFC3986 |
|---|
| 339 | n/a | self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y') |
|---|
| 340 | n/a | self.checkJoin(RFC3986_BASE, ';x', 'http://a/b/c/;x') |
|---|
| 341 | n/a | self.checkJoin(RFC3986_BASE, 'g:h','g:h') |
|---|
| 342 | n/a | self.checkJoin(RFC3986_BASE, 'g','http://a/b/c/g') |
|---|
| 343 | n/a | self.checkJoin(RFC3986_BASE, './g','http://a/b/c/g') |
|---|
| 344 | n/a | self.checkJoin(RFC3986_BASE, 'g/','http://a/b/c/g/') |
|---|
| 345 | n/a | self.checkJoin(RFC3986_BASE, '/g','http://a/g') |
|---|
| 346 | n/a | self.checkJoin(RFC3986_BASE, '//g','http://g') |
|---|
| 347 | n/a | self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y') |
|---|
| 348 | n/a | self.checkJoin(RFC3986_BASE, 'g?y','http://a/b/c/g?y') |
|---|
| 349 | n/a | self.checkJoin(RFC3986_BASE, '#s','http://a/b/c/d;p?q#s') |
|---|
| 350 | n/a | self.checkJoin(RFC3986_BASE, 'g#s','http://a/b/c/g#s') |
|---|
| 351 | n/a | self.checkJoin(RFC3986_BASE, 'g?y#s','http://a/b/c/g?y#s') |
|---|
| 352 | n/a | self.checkJoin(RFC3986_BASE, ';x','http://a/b/c/;x') |
|---|
| 353 | n/a | self.checkJoin(RFC3986_BASE, 'g;x','http://a/b/c/g;x') |
|---|
| 354 | n/a | self.checkJoin(RFC3986_BASE, 'g;x?y#s','http://a/b/c/g;x?y#s') |
|---|
| 355 | n/a | self.checkJoin(RFC3986_BASE, '','http://a/b/c/d;p?q') |
|---|
| 356 | n/a | self.checkJoin(RFC3986_BASE, '.','http://a/b/c/') |
|---|
| 357 | n/a | self.checkJoin(RFC3986_BASE, './','http://a/b/c/') |
|---|
| 358 | n/a | self.checkJoin(RFC3986_BASE, '..','http://a/b/') |
|---|
| 359 | n/a | self.checkJoin(RFC3986_BASE, '../','http://a/b/') |
|---|
| 360 | n/a | self.checkJoin(RFC3986_BASE, '../g','http://a/b/g') |
|---|
| 361 | n/a | self.checkJoin(RFC3986_BASE, '../..','http://a/') |
|---|
| 362 | n/a | self.checkJoin(RFC3986_BASE, '../../','http://a/') |
|---|
| 363 | n/a | self.checkJoin(RFC3986_BASE, '../../g','http://a/g') |
|---|
| 364 | n/a | self.checkJoin(RFC3986_BASE, '../../../g', 'http://a/g') |
|---|
| 365 | n/a | |
|---|
| 366 | n/a | #Abnormal Examples |
|---|
| 367 | n/a | |
|---|
| 368 | n/a | # The 'abnormal scenarios' are incompatible with RFC2986 parsing |
|---|
| 369 | n/a | # Tests are here for reference. |
|---|
| 370 | n/a | |
|---|
| 371 | n/a | self.checkJoin(RFC3986_BASE, '../../../g','http://a/g') |
|---|
| 372 | n/a | self.checkJoin(RFC3986_BASE, '../../../../g','http://a/g') |
|---|
| 373 | n/a | self.checkJoin(RFC3986_BASE, '/./g','http://a/g') |
|---|
| 374 | n/a | self.checkJoin(RFC3986_BASE, '/../g','http://a/g') |
|---|
| 375 | n/a | self.checkJoin(RFC3986_BASE, 'g.','http://a/b/c/g.') |
|---|
| 376 | n/a | self.checkJoin(RFC3986_BASE, '.g','http://a/b/c/.g') |
|---|
| 377 | n/a | self.checkJoin(RFC3986_BASE, 'g..','http://a/b/c/g..') |
|---|
| 378 | n/a | self.checkJoin(RFC3986_BASE, '..g','http://a/b/c/..g') |
|---|
| 379 | n/a | self.checkJoin(RFC3986_BASE, './../g','http://a/b/g') |
|---|
| 380 | n/a | self.checkJoin(RFC3986_BASE, './g/.','http://a/b/c/g/') |
|---|
| 381 | n/a | self.checkJoin(RFC3986_BASE, 'g/./h','http://a/b/c/g/h') |
|---|
| 382 | n/a | self.checkJoin(RFC3986_BASE, 'g/../h','http://a/b/c/h') |
|---|
| 383 | n/a | self.checkJoin(RFC3986_BASE, 'g;x=1/./y','http://a/b/c/g;x=1/y') |
|---|
| 384 | n/a | self.checkJoin(RFC3986_BASE, 'g;x=1/../y','http://a/b/c/y') |
|---|
| 385 | n/a | self.checkJoin(RFC3986_BASE, 'g?y/./x','http://a/b/c/g?y/./x') |
|---|
| 386 | n/a | self.checkJoin(RFC3986_BASE, 'g?y/../x','http://a/b/c/g?y/../x') |
|---|
| 387 | n/a | self.checkJoin(RFC3986_BASE, 'g#s/./x','http://a/b/c/g#s/./x') |
|---|
| 388 | n/a | self.checkJoin(RFC3986_BASE, 'g#s/../x','http://a/b/c/g#s/../x') |
|---|
| 389 | n/a | #self.checkJoin(RFC3986_BASE, 'http:g','http:g') # strict parser |
|---|
| 390 | n/a | self.checkJoin(RFC3986_BASE, 'http:g','http://a/b/c/g') #relaxed parser |
|---|
| 391 | n/a | |
|---|
| 392 | n/a | # Test for issue9721 |
|---|
| 393 | n/a | self.checkJoin('http://a/b/c/de', ';x','http://a/b/c/;x') |
|---|
| 394 | n/a | |
|---|
| 395 | n/a | def test_urljoins(self): |
|---|
| 396 | n/a | self.checkJoin(SIMPLE_BASE, 'g:h','g:h') |
|---|
| 397 | n/a | self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g') |
|---|
| 398 | n/a | self.checkJoin(SIMPLE_BASE, 'http:','http://a/b/c/d') |
|---|
| 399 | n/a | self.checkJoin(SIMPLE_BASE, 'g','http://a/b/c/g') |
|---|
| 400 | n/a | self.checkJoin(SIMPLE_BASE, './g','http://a/b/c/g') |
|---|
| 401 | n/a | self.checkJoin(SIMPLE_BASE, 'g/','http://a/b/c/g/') |
|---|
| 402 | n/a | self.checkJoin(SIMPLE_BASE, '/g','http://a/g') |
|---|
| 403 | n/a | self.checkJoin(SIMPLE_BASE, '//g','http://g') |
|---|
| 404 | n/a | self.checkJoin(SIMPLE_BASE, '?y','http://a/b/c/d?y') |
|---|
| 405 | n/a | self.checkJoin(SIMPLE_BASE, 'g?y','http://a/b/c/g?y') |
|---|
| 406 | n/a | self.checkJoin(SIMPLE_BASE, 'g?y/./x','http://a/b/c/g?y/./x') |
|---|
| 407 | n/a | self.checkJoin(SIMPLE_BASE, '.','http://a/b/c/') |
|---|
| 408 | n/a | self.checkJoin(SIMPLE_BASE, './','http://a/b/c/') |
|---|
| 409 | n/a | self.checkJoin(SIMPLE_BASE, '..','http://a/b/') |
|---|
| 410 | n/a | self.checkJoin(SIMPLE_BASE, '../','http://a/b/') |
|---|
| 411 | n/a | self.checkJoin(SIMPLE_BASE, '../g','http://a/b/g') |
|---|
| 412 | n/a | self.checkJoin(SIMPLE_BASE, '../..','http://a/') |
|---|
| 413 | n/a | self.checkJoin(SIMPLE_BASE, '../../g','http://a/g') |
|---|
| 414 | n/a | self.checkJoin(SIMPLE_BASE, './../g','http://a/b/g') |
|---|
| 415 | n/a | self.checkJoin(SIMPLE_BASE, './g/.','http://a/b/c/g/') |
|---|
| 416 | n/a | self.checkJoin(SIMPLE_BASE, 'g/./h','http://a/b/c/g/h') |
|---|
| 417 | n/a | self.checkJoin(SIMPLE_BASE, 'g/../h','http://a/b/c/h') |
|---|
| 418 | n/a | self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g') |
|---|
| 419 | n/a | self.checkJoin(SIMPLE_BASE, 'http:','http://a/b/c/d') |
|---|
| 420 | n/a | self.checkJoin(SIMPLE_BASE, 'http:?y','http://a/b/c/d?y') |
|---|
| 421 | n/a | self.checkJoin(SIMPLE_BASE, 'http:g?y','http://a/b/c/g?y') |
|---|
| 422 | n/a | self.checkJoin(SIMPLE_BASE, 'http:g?y/./x','http://a/b/c/g?y/./x') |
|---|
| 423 | n/a | self.checkJoin('http:///', '..','http:///') |
|---|
| 424 | n/a | self.checkJoin('', 'http://a/b/c/g?y/./x','http://a/b/c/g?y/./x') |
|---|
| 425 | n/a | self.checkJoin('', 'http://a/./g', 'http://a/./g') |
|---|
| 426 | n/a | self.checkJoin('svn://pathtorepo/dir1', 'dir2', 'svn://pathtorepo/dir2') |
|---|
| 427 | n/a | self.checkJoin('svn+ssh://pathtorepo/dir1', 'dir2', 'svn+ssh://pathtorepo/dir2') |
|---|
| 428 | n/a | self.checkJoin('ws://a/b','g','ws://a/g') |
|---|
| 429 | n/a | self.checkJoin('wss://a/b','g','wss://a/g') |
|---|
| 430 | n/a | |
|---|
| 431 | n/a | # XXX: The following tests are no longer compatible with RFC3986 |
|---|
| 432 | n/a | # self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g') |
|---|
| 433 | n/a | # self.checkJoin(SIMPLE_BASE, '/./g','http://a/./g') |
|---|
| 434 | n/a | |
|---|
| 435 | n/a | # test for issue22118 duplicate slashes |
|---|
| 436 | n/a | self.checkJoin(SIMPLE_BASE + '/', 'foo', SIMPLE_BASE + '/foo') |
|---|
| 437 | n/a | |
|---|
| 438 | n/a | # Non-RFC-defined tests, covering variations of base and trailing |
|---|
| 439 | n/a | # slashes |
|---|
| 440 | n/a | self.checkJoin('http://a/b/c/d/e/', '../../f/g/', 'http://a/b/c/f/g/') |
|---|
| 441 | n/a | self.checkJoin('http://a/b/c/d/e', '../../f/g/', 'http://a/b/f/g/') |
|---|
| 442 | n/a | self.checkJoin('http://a/b/c/d/e/', '/../../f/g/', 'http://a/f/g/') |
|---|
| 443 | n/a | self.checkJoin('http://a/b/c/d/e', '/../../f/g/', 'http://a/f/g/') |
|---|
| 444 | n/a | self.checkJoin('http://a/b/c/d/e/', '../../f/g', 'http://a/b/c/f/g') |
|---|
| 445 | n/a | self.checkJoin('http://a/b/', '../../f/g/', 'http://a/f/g/') |
|---|
| 446 | n/a | |
|---|
| 447 | n/a | # issue 23703: don't duplicate filename |
|---|
| 448 | n/a | self.checkJoin('a', 'b', 'b') |
|---|
| 449 | n/a | |
|---|
| 450 | n/a | def test_RFC2732(self): |
|---|
| 451 | n/a | str_cases = [ |
|---|
| 452 | n/a | ('http://Test.python.org:5432/foo/', 'test.python.org', 5432), |
|---|
| 453 | n/a | ('http://12.34.56.78:5432/foo/', '12.34.56.78', 5432), |
|---|
| 454 | n/a | ('http://[::1]:5432/foo/', '::1', 5432), |
|---|
| 455 | n/a | ('http://[dead:beef::1]:5432/foo/', 'dead:beef::1', 5432), |
|---|
| 456 | n/a | ('http://[dead:beef::]:5432/foo/', 'dead:beef::', 5432), |
|---|
| 457 | n/a | ('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]:5432/foo/', |
|---|
| 458 | n/a | 'dead:beef:cafe:5417:affe:8fa3:deaf:feed', 5432), |
|---|
| 459 | n/a | ('http://[::12.34.56.78]:5432/foo/', '::12.34.56.78', 5432), |
|---|
| 460 | n/a | ('http://[::ffff:12.34.56.78]:5432/foo/', |
|---|
| 461 | n/a | '::ffff:12.34.56.78', 5432), |
|---|
| 462 | n/a | ('http://Test.python.org/foo/', 'test.python.org', None), |
|---|
| 463 | n/a | ('http://12.34.56.78/foo/', '12.34.56.78', None), |
|---|
| 464 | n/a | ('http://[::1]/foo/', '::1', None), |
|---|
| 465 | n/a | ('http://[dead:beef::1]/foo/', 'dead:beef::1', None), |
|---|
| 466 | n/a | ('http://[dead:beef::]/foo/', 'dead:beef::', None), |
|---|
| 467 | n/a | ('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]/foo/', |
|---|
| 468 | n/a | 'dead:beef:cafe:5417:affe:8fa3:deaf:feed', None), |
|---|
| 469 | n/a | ('http://[::12.34.56.78]/foo/', '::12.34.56.78', None), |
|---|
| 470 | n/a | ('http://[::ffff:12.34.56.78]/foo/', |
|---|
| 471 | n/a | '::ffff:12.34.56.78', None), |
|---|
| 472 | n/a | ('http://Test.python.org:/foo/', 'test.python.org', None), |
|---|
| 473 | n/a | ('http://12.34.56.78:/foo/', '12.34.56.78', None), |
|---|
| 474 | n/a | ('http://[::1]:/foo/', '::1', None), |
|---|
| 475 | n/a | ('http://[dead:beef::1]:/foo/', 'dead:beef::1', None), |
|---|
| 476 | n/a | ('http://[dead:beef::]:/foo/', 'dead:beef::', None), |
|---|
| 477 | n/a | ('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]:/foo/', |
|---|
| 478 | n/a | 'dead:beef:cafe:5417:affe:8fa3:deaf:feed', None), |
|---|
| 479 | n/a | ('http://[::12.34.56.78]:/foo/', '::12.34.56.78', None), |
|---|
| 480 | n/a | ('http://[::ffff:12.34.56.78]:/foo/', |
|---|
| 481 | n/a | '::ffff:12.34.56.78', None), |
|---|
| 482 | n/a | ] |
|---|
| 483 | n/a | def _encode(t): |
|---|
| 484 | n/a | return t[0].encode('ascii'), t[1].encode('ascii'), t[2] |
|---|
| 485 | n/a | bytes_cases = [_encode(x) for x in str_cases] |
|---|
| 486 | n/a | for url, hostname, port in str_cases + bytes_cases: |
|---|
| 487 | n/a | urlparsed = urllib.parse.urlparse(url) |
|---|
| 488 | n/a | self.assertEqual((urlparsed.hostname, urlparsed.port) , (hostname, port)) |
|---|
| 489 | n/a | |
|---|
| 490 | n/a | str_cases = [ |
|---|
| 491 | n/a | 'http://::12.34.56.78]/', |
|---|
| 492 | n/a | 'http://[::1/foo/', |
|---|
| 493 | n/a | 'ftp://[::1/foo/bad]/bad', |
|---|
| 494 | n/a | 'http://[::1/foo/bad]/bad', |
|---|
| 495 | n/a | 'http://[::ffff:12.34.56.78'] |
|---|
| 496 | n/a | bytes_cases = [x.encode('ascii') for x in str_cases] |
|---|
| 497 | n/a | for invalid_url in str_cases + bytes_cases: |
|---|
| 498 | n/a | self.assertRaises(ValueError, urllib.parse.urlparse, invalid_url) |
|---|
| 499 | n/a | |
|---|
| 500 | n/a | def test_urldefrag(self): |
|---|
| 501 | n/a | str_cases = [ |
|---|
| 502 | n/a | ('http://python.org#frag', 'http://python.org', 'frag'), |
|---|
| 503 | n/a | ('http://python.org', 'http://python.org', ''), |
|---|
| 504 | n/a | ('http://python.org/#frag', 'http://python.org/', 'frag'), |
|---|
| 505 | n/a | ('http://python.org/', 'http://python.org/', ''), |
|---|
| 506 | n/a | ('http://python.org/?q#frag', 'http://python.org/?q', 'frag'), |
|---|
| 507 | n/a | ('http://python.org/?q', 'http://python.org/?q', ''), |
|---|
| 508 | n/a | ('http://python.org/p#frag', 'http://python.org/p', 'frag'), |
|---|
| 509 | n/a | ('http://python.org/p?q', 'http://python.org/p?q', ''), |
|---|
| 510 | n/a | (RFC1808_BASE, 'http://a/b/c/d;p?q', 'f'), |
|---|
| 511 | n/a | (RFC2396_BASE, 'http://a/b/c/d;p?q', ''), |
|---|
| 512 | n/a | ] |
|---|
| 513 | n/a | def _encode(t): |
|---|
| 514 | n/a | return type(t)(x.encode('ascii') for x in t) |
|---|
| 515 | n/a | bytes_cases = [_encode(x) for x in str_cases] |
|---|
| 516 | n/a | for url, defrag, frag in str_cases + bytes_cases: |
|---|
| 517 | n/a | result = urllib.parse.urldefrag(url) |
|---|
| 518 | n/a | self.assertEqual(result.geturl(), url) |
|---|
| 519 | n/a | self.assertEqual(result, (defrag, frag)) |
|---|
| 520 | n/a | self.assertEqual(result.url, defrag) |
|---|
| 521 | n/a | self.assertEqual(result.fragment, frag) |
|---|
| 522 | n/a | |
|---|
| 523 | n/a | def test_urlsplit_attributes(self): |
|---|
| 524 | n/a | url = "HTTP://WWW.PYTHON.ORG/doc/#frag" |
|---|
| 525 | n/a | p = urllib.parse.urlsplit(url) |
|---|
| 526 | n/a | self.assertEqual(p.scheme, "http") |
|---|
| 527 | n/a | self.assertEqual(p.netloc, "WWW.PYTHON.ORG") |
|---|
| 528 | n/a | self.assertEqual(p.path, "/doc/") |
|---|
| 529 | n/a | self.assertEqual(p.query, "") |
|---|
| 530 | n/a | self.assertEqual(p.fragment, "frag") |
|---|
| 531 | n/a | self.assertEqual(p.username, None) |
|---|
| 532 | n/a | self.assertEqual(p.password, None) |
|---|
| 533 | n/a | self.assertEqual(p.hostname, "www.python.org") |
|---|
| 534 | n/a | self.assertEqual(p.port, None) |
|---|
| 535 | n/a | # geturl() won't return exactly the original URL in this case |
|---|
| 536 | n/a | # since the scheme is always case-normalized |
|---|
| 537 | n/a | # We handle this by ignoring the first 4 characters of the URL |
|---|
| 538 | n/a | self.assertEqual(p.geturl()[4:], url[4:]) |
|---|
| 539 | n/a | |
|---|
| 540 | n/a | url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag" |
|---|
| 541 | n/a | p = urllib.parse.urlsplit(url) |
|---|
| 542 | n/a | self.assertEqual(p.scheme, "http") |
|---|
| 543 | n/a | self.assertEqual(p.netloc, "User:Pass@www.python.org:080") |
|---|
| 544 | n/a | self.assertEqual(p.path, "/doc/") |
|---|
| 545 | n/a | self.assertEqual(p.query, "query=yes") |
|---|
| 546 | n/a | self.assertEqual(p.fragment, "frag") |
|---|
| 547 | n/a | self.assertEqual(p.username, "User") |
|---|
| 548 | n/a | self.assertEqual(p.password, "Pass") |
|---|
| 549 | n/a | self.assertEqual(p.hostname, "www.python.org") |
|---|
| 550 | n/a | self.assertEqual(p.port, 80) |
|---|
| 551 | n/a | self.assertEqual(p.geturl(), url) |
|---|
| 552 | n/a | |
|---|
| 553 | n/a | # Addressing issue1698, which suggests Username can contain |
|---|
| 554 | n/a | # "@" characters. Though not RFC compliant, many ftp sites allow |
|---|
| 555 | n/a | # and request email addresses as usernames. |
|---|
| 556 | n/a | |
|---|
| 557 | n/a | url = "http://User@example.com:Pass@www.python.org:080/doc/?query=yes#frag" |
|---|
| 558 | n/a | p = urllib.parse.urlsplit(url) |
|---|
| 559 | n/a | self.assertEqual(p.scheme, "http") |
|---|
| 560 | n/a | self.assertEqual(p.netloc, "User@example.com:Pass@www.python.org:080") |
|---|
| 561 | n/a | self.assertEqual(p.path, "/doc/") |
|---|
| 562 | n/a | self.assertEqual(p.query, "query=yes") |
|---|
| 563 | n/a | self.assertEqual(p.fragment, "frag") |
|---|
| 564 | n/a | self.assertEqual(p.username, "User@example.com") |
|---|
| 565 | n/a | self.assertEqual(p.password, "Pass") |
|---|
| 566 | n/a | self.assertEqual(p.hostname, "www.python.org") |
|---|
| 567 | n/a | self.assertEqual(p.port, 80) |
|---|
| 568 | n/a | self.assertEqual(p.geturl(), url) |
|---|
| 569 | n/a | |
|---|
| 570 | n/a | # And check them all again, only with bytes this time |
|---|
| 571 | n/a | url = b"HTTP://WWW.PYTHON.ORG/doc/#frag" |
|---|
| 572 | n/a | p = urllib.parse.urlsplit(url) |
|---|
| 573 | n/a | self.assertEqual(p.scheme, b"http") |
|---|
| 574 | n/a | self.assertEqual(p.netloc, b"WWW.PYTHON.ORG") |
|---|
| 575 | n/a | self.assertEqual(p.path, b"/doc/") |
|---|
| 576 | n/a | self.assertEqual(p.query, b"") |
|---|
| 577 | n/a | self.assertEqual(p.fragment, b"frag") |
|---|
| 578 | n/a | self.assertEqual(p.username, None) |
|---|
| 579 | n/a | self.assertEqual(p.password, None) |
|---|
| 580 | n/a | self.assertEqual(p.hostname, b"www.python.org") |
|---|
| 581 | n/a | self.assertEqual(p.port, None) |
|---|
| 582 | n/a | self.assertEqual(p.geturl()[4:], url[4:]) |
|---|
| 583 | n/a | |
|---|
| 584 | n/a | url = b"http://User:Pass@www.python.org:080/doc/?query=yes#frag" |
|---|
| 585 | n/a | p = urllib.parse.urlsplit(url) |
|---|
| 586 | n/a | self.assertEqual(p.scheme, b"http") |
|---|
| 587 | n/a | self.assertEqual(p.netloc, b"User:Pass@www.python.org:080") |
|---|
| 588 | n/a | self.assertEqual(p.path, b"/doc/") |
|---|
| 589 | n/a | self.assertEqual(p.query, b"query=yes") |
|---|
| 590 | n/a | self.assertEqual(p.fragment, b"frag") |
|---|
| 591 | n/a | self.assertEqual(p.username, b"User") |
|---|
| 592 | n/a | self.assertEqual(p.password, b"Pass") |
|---|
| 593 | n/a | self.assertEqual(p.hostname, b"www.python.org") |
|---|
| 594 | n/a | self.assertEqual(p.port, 80) |
|---|
| 595 | n/a | self.assertEqual(p.geturl(), url) |
|---|
| 596 | n/a | |
|---|
| 597 | n/a | url = b"http://User@example.com:Pass@www.python.org:080/doc/?query=yes#frag" |
|---|
| 598 | n/a | p = urllib.parse.urlsplit(url) |
|---|
| 599 | n/a | self.assertEqual(p.scheme, b"http") |
|---|
| 600 | n/a | self.assertEqual(p.netloc, b"User@example.com:Pass@www.python.org:080") |
|---|
| 601 | n/a | self.assertEqual(p.path, b"/doc/") |
|---|
| 602 | n/a | self.assertEqual(p.query, b"query=yes") |
|---|
| 603 | n/a | self.assertEqual(p.fragment, b"frag") |
|---|
| 604 | n/a | self.assertEqual(p.username, b"User@example.com") |
|---|
| 605 | n/a | self.assertEqual(p.password, b"Pass") |
|---|
| 606 | n/a | self.assertEqual(p.hostname, b"www.python.org") |
|---|
| 607 | n/a | self.assertEqual(p.port, 80) |
|---|
| 608 | n/a | self.assertEqual(p.geturl(), url) |
|---|
| 609 | n/a | |
|---|
| 610 | n/a | # Verify an illegal port raises ValueError |
|---|
| 611 | n/a | url = b"HTTP://WWW.PYTHON.ORG:65536/doc/#frag" |
|---|
| 612 | n/a | p = urllib.parse.urlsplit(url) |
|---|
| 613 | n/a | with self.assertRaisesRegex(ValueError, "out of range"): |
|---|
| 614 | n/a | p.port |
|---|
| 615 | n/a | |
|---|
| 616 | n/a | def test_attributes_bad_port(self): |
|---|
| 617 | n/a | """Check handling of invalid ports.""" |
|---|
| 618 | n/a | for bytes in (False, True): |
|---|
| 619 | n/a | for parse in (urllib.parse.urlsplit, urllib.parse.urlparse): |
|---|
| 620 | n/a | for port in ("foo", "1.5", "-1", "0x10"): |
|---|
| 621 | n/a | with self.subTest(bytes=bytes, parse=parse, port=port): |
|---|
| 622 | n/a | netloc = "www.example.net:" + port |
|---|
| 623 | n/a | url = "http://" + netloc |
|---|
| 624 | n/a | if bytes: |
|---|
| 625 | n/a | netloc = netloc.encode("ascii") |
|---|
| 626 | n/a | url = url.encode("ascii") |
|---|
| 627 | n/a | p = parse(url) |
|---|
| 628 | n/a | self.assertEqual(p.netloc, netloc) |
|---|
| 629 | n/a | with self.assertRaises(ValueError): |
|---|
| 630 | n/a | p.port |
|---|
| 631 | n/a | |
|---|
| 632 | n/a | def test_attributes_without_netloc(self): |
|---|
| 633 | n/a | # This example is straight from RFC 3261. It looks like it |
|---|
| 634 | n/a | # should allow the username, hostname, and port to be filled |
|---|
| 635 | n/a | # in, but doesn't. Since it's a URI and doesn't use the |
|---|
| 636 | n/a | # scheme://netloc syntax, the netloc and related attributes |
|---|
| 637 | n/a | # should be left empty. |
|---|
| 638 | n/a | uri = "sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15" |
|---|
| 639 | n/a | p = urllib.parse.urlsplit(uri) |
|---|
| 640 | n/a | self.assertEqual(p.netloc, "") |
|---|
| 641 | n/a | self.assertEqual(p.username, None) |
|---|
| 642 | n/a | self.assertEqual(p.password, None) |
|---|
| 643 | n/a | self.assertEqual(p.hostname, None) |
|---|
| 644 | n/a | self.assertEqual(p.port, None) |
|---|
| 645 | n/a | self.assertEqual(p.geturl(), uri) |
|---|
| 646 | n/a | |
|---|
| 647 | n/a | p = urllib.parse.urlparse(uri) |
|---|
| 648 | n/a | self.assertEqual(p.netloc, "") |
|---|
| 649 | n/a | self.assertEqual(p.username, None) |
|---|
| 650 | n/a | self.assertEqual(p.password, None) |
|---|
| 651 | n/a | self.assertEqual(p.hostname, None) |
|---|
| 652 | n/a | self.assertEqual(p.port, None) |
|---|
| 653 | n/a | self.assertEqual(p.geturl(), uri) |
|---|
| 654 | n/a | |
|---|
| 655 | n/a | # You guessed it, repeating the test with bytes input |
|---|
| 656 | n/a | uri = b"sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15" |
|---|
| 657 | n/a | p = urllib.parse.urlsplit(uri) |
|---|
| 658 | n/a | self.assertEqual(p.netloc, b"") |
|---|
| 659 | n/a | self.assertEqual(p.username, None) |
|---|
| 660 | n/a | self.assertEqual(p.password, None) |
|---|
| 661 | n/a | self.assertEqual(p.hostname, None) |
|---|
| 662 | n/a | self.assertEqual(p.port, None) |
|---|
| 663 | n/a | self.assertEqual(p.geturl(), uri) |
|---|
| 664 | n/a | |
|---|
| 665 | n/a | p = urllib.parse.urlparse(uri) |
|---|
| 666 | n/a | self.assertEqual(p.netloc, b"") |
|---|
| 667 | n/a | self.assertEqual(p.username, None) |
|---|
| 668 | n/a | self.assertEqual(p.password, None) |
|---|
| 669 | n/a | self.assertEqual(p.hostname, None) |
|---|
| 670 | n/a | self.assertEqual(p.port, None) |
|---|
| 671 | n/a | self.assertEqual(p.geturl(), uri) |
|---|
| 672 | n/a | |
|---|
| 673 | n/a | def test_noslash(self): |
|---|
| 674 | n/a | # Issue 1637: http://foo.com?query is legal |
|---|
| 675 | n/a | self.assertEqual(urllib.parse.urlparse("http://example.com?blahblah=/foo"), |
|---|
| 676 | n/a | ('http', 'example.com', '', '', 'blahblah=/foo', '')) |
|---|
| 677 | n/a | self.assertEqual(urllib.parse.urlparse(b"http://example.com?blahblah=/foo"), |
|---|
| 678 | n/a | (b'http', b'example.com', b'', b'', b'blahblah=/foo', b'')) |
|---|
| 679 | n/a | |
|---|
| 680 | n/a | def test_withoutscheme(self): |
|---|
| 681 | n/a | # Test urlparse without scheme |
|---|
| 682 | n/a | # Issue 754016: urlparse goes wrong with IP:port without scheme |
|---|
| 683 | n/a | # RFC 1808 specifies that netloc should start with //, urlparse expects |
|---|
| 684 | n/a | # the same, otherwise it classifies the portion of url as path. |
|---|
| 685 | n/a | self.assertEqual(urllib.parse.urlparse("path"), |
|---|
| 686 | n/a | ('','','path','','','')) |
|---|
| 687 | n/a | self.assertEqual(urllib.parse.urlparse("//www.python.org:80"), |
|---|
| 688 | n/a | ('','www.python.org:80','','','','')) |
|---|
| 689 | n/a | self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"), |
|---|
| 690 | n/a | ('http','www.python.org:80','','','','')) |
|---|
| 691 | n/a | # Repeat for bytes input |
|---|
| 692 | n/a | self.assertEqual(urllib.parse.urlparse(b"path"), |
|---|
| 693 | n/a | (b'',b'',b'path',b'',b'',b'')) |
|---|
| 694 | n/a | self.assertEqual(urllib.parse.urlparse(b"//www.python.org:80"), |
|---|
| 695 | n/a | (b'',b'www.python.org:80',b'',b'',b'',b'')) |
|---|
| 696 | n/a | self.assertEqual(urllib.parse.urlparse(b"http://www.python.org:80"), |
|---|
| 697 | n/a | (b'http',b'www.python.org:80',b'',b'',b'',b'')) |
|---|
| 698 | n/a | |
|---|
| 699 | n/a | def test_portseparator(self): |
|---|
| 700 | n/a | # Issue 754016 makes changes for port separator ':' from scheme separator |
|---|
| 701 | n/a | self.assertEqual(urllib.parse.urlparse("path:80"), |
|---|
| 702 | n/a | ('','','path:80','','','')) |
|---|
| 703 | n/a | self.assertEqual(urllib.parse.urlparse("http:"),('http','','','','','')) |
|---|
| 704 | n/a | self.assertEqual(urllib.parse.urlparse("https:"),('https','','','','','')) |
|---|
| 705 | n/a | self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"), |
|---|
| 706 | n/a | ('http','www.python.org:80','','','','')) |
|---|
| 707 | n/a | # As usual, need to check bytes input as well |
|---|
| 708 | n/a | self.assertEqual(urllib.parse.urlparse(b"path:80"), |
|---|
| 709 | n/a | (b'',b'',b'path:80',b'',b'',b'')) |
|---|
| 710 | n/a | self.assertEqual(urllib.parse.urlparse(b"http:"),(b'http',b'',b'',b'',b'',b'')) |
|---|
| 711 | n/a | self.assertEqual(urllib.parse.urlparse(b"https:"),(b'https',b'',b'',b'',b'',b'')) |
|---|
| 712 | n/a | self.assertEqual(urllib.parse.urlparse(b"http://www.python.org:80"), |
|---|
| 713 | n/a | (b'http',b'www.python.org:80',b'',b'',b'',b'')) |
|---|
| 714 | n/a | |
|---|
| 715 | n/a | def test_usingsys(self): |
|---|
| 716 | n/a | # Issue 3314: sys module is used in the error |
|---|
| 717 | n/a | self.assertRaises(TypeError, urllib.parse.urlencode, "foo") |
|---|
| 718 | n/a | |
|---|
| 719 | n/a | def test_anyscheme(self): |
|---|
| 720 | n/a | # Issue 7904: s3://foo.com/stuff has netloc "foo.com". |
|---|
| 721 | n/a | self.assertEqual(urllib.parse.urlparse("s3://foo.com/stuff"), |
|---|
| 722 | n/a | ('s3', 'foo.com', '/stuff', '', '', '')) |
|---|
| 723 | n/a | self.assertEqual(urllib.parse.urlparse("x-newscheme://foo.com/stuff"), |
|---|
| 724 | n/a | ('x-newscheme', 'foo.com', '/stuff', '', '', '')) |
|---|
| 725 | n/a | self.assertEqual(urllib.parse.urlparse("x-newscheme://foo.com/stuff?query#fragment"), |
|---|
| 726 | n/a | ('x-newscheme', 'foo.com', '/stuff', '', 'query', 'fragment')) |
|---|
| 727 | n/a | self.assertEqual(urllib.parse.urlparse("x-newscheme://foo.com/stuff?query"), |
|---|
| 728 | n/a | ('x-newscheme', 'foo.com', '/stuff', '', 'query', '')) |
|---|
| 729 | n/a | |
|---|
| 730 | n/a | # And for bytes... |
|---|
| 731 | n/a | self.assertEqual(urllib.parse.urlparse(b"s3://foo.com/stuff"), |
|---|
| 732 | n/a | (b's3', b'foo.com', b'/stuff', b'', b'', b'')) |
|---|
| 733 | n/a | self.assertEqual(urllib.parse.urlparse(b"x-newscheme://foo.com/stuff"), |
|---|
| 734 | n/a | (b'x-newscheme', b'foo.com', b'/stuff', b'', b'', b'')) |
|---|
| 735 | n/a | self.assertEqual(urllib.parse.urlparse(b"x-newscheme://foo.com/stuff?query#fragment"), |
|---|
| 736 | n/a | (b'x-newscheme', b'foo.com', b'/stuff', b'', b'query', b'fragment')) |
|---|
| 737 | n/a | self.assertEqual(urllib.parse.urlparse(b"x-newscheme://foo.com/stuff?query"), |
|---|
| 738 | n/a | (b'x-newscheme', b'foo.com', b'/stuff', b'', b'query', b'')) |
|---|
| 739 | n/a | |
|---|
| 740 | n/a | def test_default_scheme(self): |
|---|
| 741 | n/a | # Exercise the scheme parameter of urlparse() and urlsplit() |
|---|
| 742 | n/a | for func in (urllib.parse.urlparse, urllib.parse.urlsplit): |
|---|
| 743 | n/a | with self.subTest(function=func): |
|---|
| 744 | n/a | result = func("http://example.net/", "ftp") |
|---|
| 745 | n/a | self.assertEqual(result.scheme, "http") |
|---|
| 746 | n/a | result = func(b"http://example.net/", b"ftp") |
|---|
| 747 | n/a | self.assertEqual(result.scheme, b"http") |
|---|
| 748 | n/a | self.assertEqual(func("path", "ftp").scheme, "ftp") |
|---|
| 749 | n/a | self.assertEqual(func("path", scheme="ftp").scheme, "ftp") |
|---|
| 750 | n/a | self.assertEqual(func(b"path", scheme=b"ftp").scheme, b"ftp") |
|---|
| 751 | n/a | self.assertEqual(func("path").scheme, "") |
|---|
| 752 | n/a | self.assertEqual(func(b"path").scheme, b"") |
|---|
| 753 | n/a | self.assertEqual(func(b"path", "").scheme, b"") |
|---|
| 754 | n/a | |
|---|
| 755 | n/a | def test_parse_fragments(self): |
|---|
| 756 | n/a | # Exercise the allow_fragments parameter of urlparse() and urlsplit() |
|---|
| 757 | n/a | tests = ( |
|---|
| 758 | n/a | ("http:#frag", "path"), |
|---|
| 759 | n/a | ("//example.net#frag", "path"), |
|---|
| 760 | n/a | ("index.html#frag", "path"), |
|---|
| 761 | n/a | (";a=b#frag", "params"), |
|---|
| 762 | n/a | ("?a=b#frag", "query"), |
|---|
| 763 | n/a | ("#frag", "path"), |
|---|
| 764 | n/a | ) |
|---|
| 765 | n/a | for url, attr in tests: |
|---|
| 766 | n/a | for func in (urllib.parse.urlparse, urllib.parse.urlsplit): |
|---|
| 767 | n/a | if attr == "params" and func is urllib.parse.urlsplit: |
|---|
| 768 | n/a | attr = "path" |
|---|
| 769 | n/a | with self.subTest(url=url, function=func): |
|---|
| 770 | n/a | result = func(url, allow_fragments=False) |
|---|
| 771 | n/a | self.assertEqual(result.fragment, "") |
|---|
| 772 | n/a | self.assertTrue(getattr(result, attr).endswith("#frag")) |
|---|
| 773 | n/a | self.assertEqual(func(url, "", False).fragment, "") |
|---|
| 774 | n/a | |
|---|
| 775 | n/a | result = func(url, allow_fragments=True) |
|---|
| 776 | n/a | self.assertEqual(result.fragment, "frag") |
|---|
| 777 | n/a | self.assertFalse(getattr(result, attr).endswith("frag")) |
|---|
| 778 | n/a | self.assertEqual(func(url, "", True).fragment, "frag") |
|---|
| 779 | n/a | self.assertEqual(func(url).fragment, "frag") |
|---|
| 780 | n/a | |
|---|
| 781 | n/a | def test_mixed_types_rejected(self): |
|---|
| 782 | n/a | # Several functions that process either strings or ASCII encoded bytes |
|---|
| 783 | n/a | # accept multiple arguments. Check they reject mixed type input |
|---|
| 784 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 785 | n/a | urllib.parse.urlparse("www.python.org", b"http") |
|---|
| 786 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 787 | n/a | urllib.parse.urlparse(b"www.python.org", "http") |
|---|
| 788 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 789 | n/a | urllib.parse.urlsplit("www.python.org", b"http") |
|---|
| 790 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 791 | n/a | urllib.parse.urlsplit(b"www.python.org", "http") |
|---|
| 792 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 793 | n/a | urllib.parse.urlunparse(( b"http", "www.python.org","","","","")) |
|---|
| 794 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 795 | n/a | urllib.parse.urlunparse(("http", b"www.python.org","","","","")) |
|---|
| 796 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 797 | n/a | urllib.parse.urlunsplit((b"http", "www.python.org","","","")) |
|---|
| 798 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 799 | n/a | urllib.parse.urlunsplit(("http", b"www.python.org","","","")) |
|---|
| 800 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 801 | n/a | urllib.parse.urljoin("http://python.org", b"http://python.org") |
|---|
| 802 | n/a | with self.assertRaisesRegex(TypeError, "Cannot mix str"): |
|---|
| 803 | n/a | urllib.parse.urljoin(b"http://python.org", "http://python.org") |
|---|
| 804 | n/a | |
|---|
| 805 | n/a | def _check_result_type(self, str_type): |
|---|
| 806 | n/a | num_args = len(str_type._fields) |
|---|
| 807 | n/a | bytes_type = str_type._encoded_counterpart |
|---|
| 808 | n/a | self.assertIs(bytes_type._decoded_counterpart, str_type) |
|---|
| 809 | n/a | str_args = ('',) * num_args |
|---|
| 810 | n/a | bytes_args = (b'',) * num_args |
|---|
| 811 | n/a | str_result = str_type(*str_args) |
|---|
| 812 | n/a | bytes_result = bytes_type(*bytes_args) |
|---|
| 813 | n/a | encoding = 'ascii' |
|---|
| 814 | n/a | errors = 'strict' |
|---|
| 815 | n/a | self.assertEqual(str_result, str_args) |
|---|
| 816 | n/a | self.assertEqual(bytes_result.decode(), str_args) |
|---|
| 817 | n/a | self.assertEqual(bytes_result.decode(), str_result) |
|---|
| 818 | n/a | self.assertEqual(bytes_result.decode(encoding), str_args) |
|---|
| 819 | n/a | self.assertEqual(bytes_result.decode(encoding), str_result) |
|---|
| 820 | n/a | self.assertEqual(bytes_result.decode(encoding, errors), str_args) |
|---|
| 821 | n/a | self.assertEqual(bytes_result.decode(encoding, errors), str_result) |
|---|
| 822 | n/a | self.assertEqual(bytes_result, bytes_args) |
|---|
| 823 | n/a | self.assertEqual(str_result.encode(), bytes_args) |
|---|
| 824 | n/a | self.assertEqual(str_result.encode(), bytes_result) |
|---|
| 825 | n/a | self.assertEqual(str_result.encode(encoding), bytes_args) |
|---|
| 826 | n/a | self.assertEqual(str_result.encode(encoding), bytes_result) |
|---|
| 827 | n/a | self.assertEqual(str_result.encode(encoding, errors), bytes_args) |
|---|
| 828 | n/a | self.assertEqual(str_result.encode(encoding, errors), bytes_result) |
|---|
| 829 | n/a | |
|---|
| 830 | n/a | def test_result_pairs(self): |
|---|
| 831 | n/a | # Check encoding and decoding between result pairs |
|---|
| 832 | n/a | result_types = [ |
|---|
| 833 | n/a | urllib.parse.DefragResult, |
|---|
| 834 | n/a | urllib.parse.SplitResult, |
|---|
| 835 | n/a | urllib.parse.ParseResult, |
|---|
| 836 | n/a | ] |
|---|
| 837 | n/a | for result_type in result_types: |
|---|
| 838 | n/a | self._check_result_type(result_type) |
|---|
| 839 | n/a | |
|---|
| 840 | n/a | def test_parse_qs_encoding(self): |
|---|
| 841 | n/a | result = urllib.parse.parse_qs("key=\u0141%E9", encoding="latin-1") |
|---|
| 842 | n/a | self.assertEqual(result, {'key': ['\u0141\xE9']}) |
|---|
| 843 | n/a | result = urllib.parse.parse_qs("key=\u0141%C3%A9", encoding="utf-8") |
|---|
| 844 | n/a | self.assertEqual(result, {'key': ['\u0141\xE9']}) |
|---|
| 845 | n/a | result = urllib.parse.parse_qs("key=\u0141%C3%A9", encoding="ascii") |
|---|
| 846 | n/a | self.assertEqual(result, {'key': ['\u0141\ufffd\ufffd']}) |
|---|
| 847 | n/a | result = urllib.parse.parse_qs("key=\u0141%E9-", encoding="ascii") |
|---|
| 848 | n/a | self.assertEqual(result, {'key': ['\u0141\ufffd-']}) |
|---|
| 849 | n/a | result = urllib.parse.parse_qs("key=\u0141%E9-", encoding="ascii", |
|---|
| 850 | n/a | errors="ignore") |
|---|
| 851 | n/a | self.assertEqual(result, {'key': ['\u0141-']}) |
|---|
| 852 | n/a | |
|---|
| 853 | n/a | def test_parse_qsl_encoding(self): |
|---|
| 854 | n/a | result = urllib.parse.parse_qsl("key=\u0141%E9", encoding="latin-1") |
|---|
| 855 | n/a | self.assertEqual(result, [('key', '\u0141\xE9')]) |
|---|
| 856 | n/a | result = urllib.parse.parse_qsl("key=\u0141%C3%A9", encoding="utf-8") |
|---|
| 857 | n/a | self.assertEqual(result, [('key', '\u0141\xE9')]) |
|---|
| 858 | n/a | result = urllib.parse.parse_qsl("key=\u0141%C3%A9", encoding="ascii") |
|---|
| 859 | n/a | self.assertEqual(result, [('key', '\u0141\ufffd\ufffd')]) |
|---|
| 860 | n/a | result = urllib.parse.parse_qsl("key=\u0141%E9-", encoding="ascii") |
|---|
| 861 | n/a | self.assertEqual(result, [('key', '\u0141\ufffd-')]) |
|---|
| 862 | n/a | result = urllib.parse.parse_qsl("key=\u0141%E9-", encoding="ascii", |
|---|
| 863 | n/a | errors="ignore") |
|---|
| 864 | n/a | self.assertEqual(result, [('key', '\u0141-')]) |
|---|
| 865 | n/a | |
|---|
| 866 | n/a | def test_urlencode_sequences(self): |
|---|
| 867 | n/a | # Other tests incidentally urlencode things; test non-covered cases: |
|---|
| 868 | n/a | # Sequence and object values. |
|---|
| 869 | n/a | result = urllib.parse.urlencode({'a': [1, 2], 'b': (3, 4, 5)}, True) |
|---|
| 870 | n/a | # we cannot rely on ordering here |
|---|
| 871 | n/a | assert set(result.split('&')) == {'a=1', 'a=2', 'b=3', 'b=4', 'b=5'} |
|---|
| 872 | n/a | |
|---|
| 873 | n/a | class Trivial: |
|---|
| 874 | n/a | def __str__(self): |
|---|
| 875 | n/a | return 'trivial' |
|---|
| 876 | n/a | |
|---|
| 877 | n/a | result = urllib.parse.urlencode({'a': Trivial()}, True) |
|---|
| 878 | n/a | self.assertEqual(result, 'a=trivial') |
|---|
| 879 | n/a | |
|---|
| 880 | n/a | def test_urlencode_quote_via(self): |
|---|
| 881 | n/a | result = urllib.parse.urlencode({'a': 'some value'}) |
|---|
| 882 | n/a | self.assertEqual(result, "a=some+value") |
|---|
| 883 | n/a | result = urllib.parse.urlencode({'a': 'some value/another'}, |
|---|
| 884 | n/a | quote_via=urllib.parse.quote) |
|---|
| 885 | n/a | self.assertEqual(result, "a=some%20value%2Fanother") |
|---|
| 886 | n/a | result = urllib.parse.urlencode({'a': 'some value/another'}, |
|---|
| 887 | n/a | safe='/', quote_via=urllib.parse.quote) |
|---|
| 888 | n/a | self.assertEqual(result, "a=some%20value/another") |
|---|
| 889 | n/a | |
|---|
| 890 | n/a | def test_quote_from_bytes(self): |
|---|
| 891 | n/a | self.assertRaises(TypeError, urllib.parse.quote_from_bytes, 'foo') |
|---|
| 892 | n/a | result = urllib.parse.quote_from_bytes(b'archaeological arcana') |
|---|
| 893 | n/a | self.assertEqual(result, 'archaeological%20arcana') |
|---|
| 894 | n/a | result = urllib.parse.quote_from_bytes(b'') |
|---|
| 895 | n/a | self.assertEqual(result, '') |
|---|
| 896 | n/a | |
|---|
| 897 | n/a | def test_unquote_to_bytes(self): |
|---|
| 898 | n/a | result = urllib.parse.unquote_to_bytes('abc%20def') |
|---|
| 899 | n/a | self.assertEqual(result, b'abc def') |
|---|
| 900 | n/a | result = urllib.parse.unquote_to_bytes('') |
|---|
| 901 | n/a | self.assertEqual(result, b'') |
|---|
| 902 | n/a | |
|---|
| 903 | n/a | def test_quote_errors(self): |
|---|
| 904 | n/a | self.assertRaises(TypeError, urllib.parse.quote, b'foo', |
|---|
| 905 | n/a | encoding='utf-8') |
|---|
| 906 | n/a | self.assertRaises(TypeError, urllib.parse.quote, b'foo', errors='strict') |
|---|
| 907 | n/a | |
|---|
| 908 | n/a | def test_issue14072(self): |
|---|
| 909 | n/a | p1 = urllib.parse.urlsplit('tel:+31-641044153') |
|---|
| 910 | n/a | self.assertEqual(p1.scheme, 'tel') |
|---|
| 911 | n/a | self.assertEqual(p1.path, '+31-641044153') |
|---|
| 912 | n/a | p2 = urllib.parse.urlsplit('tel:+31641044153') |
|---|
| 913 | n/a | self.assertEqual(p2.scheme, 'tel') |
|---|
| 914 | n/a | self.assertEqual(p2.path, '+31641044153') |
|---|
| 915 | n/a | # assert the behavior for urlparse |
|---|
| 916 | n/a | p1 = urllib.parse.urlparse('tel:+31-641044153') |
|---|
| 917 | n/a | self.assertEqual(p1.scheme, 'tel') |
|---|
| 918 | n/a | self.assertEqual(p1.path, '+31-641044153') |
|---|
| 919 | n/a | p2 = urllib.parse.urlparse('tel:+31641044153') |
|---|
| 920 | n/a | self.assertEqual(p2.scheme, 'tel') |
|---|
| 921 | n/a | self.assertEqual(p2.path, '+31641044153') |
|---|
| 922 | n/a | |
|---|
| 923 | n/a | def test_telurl_params(self): |
|---|
| 924 | n/a | p1 = urllib.parse.urlparse('tel:123-4;phone-context=+1-650-516') |
|---|
| 925 | n/a | self.assertEqual(p1.scheme, 'tel') |
|---|
| 926 | n/a | self.assertEqual(p1.path, '123-4') |
|---|
| 927 | n/a | self.assertEqual(p1.params, 'phone-context=+1-650-516') |
|---|
| 928 | n/a | |
|---|
| 929 | n/a | p1 = urllib.parse.urlparse('tel:+1-201-555-0123') |
|---|
| 930 | n/a | self.assertEqual(p1.scheme, 'tel') |
|---|
| 931 | n/a | self.assertEqual(p1.path, '+1-201-555-0123') |
|---|
| 932 | n/a | self.assertEqual(p1.params, '') |
|---|
| 933 | n/a | |
|---|
| 934 | n/a | p1 = urllib.parse.urlparse('tel:7042;phone-context=example.com') |
|---|
| 935 | n/a | self.assertEqual(p1.scheme, 'tel') |
|---|
| 936 | n/a | self.assertEqual(p1.path, '7042') |
|---|
| 937 | n/a | self.assertEqual(p1.params, 'phone-context=example.com') |
|---|
| 938 | n/a | |
|---|
| 939 | n/a | p1 = urllib.parse.urlparse('tel:863-1234;phone-context=+1-914-555') |
|---|
| 940 | n/a | self.assertEqual(p1.scheme, 'tel') |
|---|
| 941 | n/a | self.assertEqual(p1.path, '863-1234') |
|---|
| 942 | n/a | self.assertEqual(p1.params, 'phone-context=+1-914-555') |
|---|
| 943 | n/a | |
|---|
| 944 | n/a | def test_Quoter_repr(self): |
|---|
| 945 | n/a | quoter = urllib.parse.Quoter(urllib.parse._ALWAYS_SAFE) |
|---|
| 946 | n/a | self.assertIn('Quoter', repr(quoter)) |
|---|
| 947 | n/a | |
|---|
| 948 | n/a | def test_all(self): |
|---|
| 949 | n/a | expected = [] |
|---|
| 950 | n/a | undocumented = { |
|---|
| 951 | n/a | 'splitattr', 'splithost', 'splitnport', 'splitpasswd', |
|---|
| 952 | n/a | 'splitport', 'splitquery', 'splittag', 'splittype', 'splituser', |
|---|
| 953 | n/a | 'splitvalue', |
|---|
| 954 | n/a | 'Quoter', 'ResultBase', 'clear_cache', 'to_bytes', 'unwrap', |
|---|
| 955 | n/a | } |
|---|
| 956 | n/a | for name in dir(urllib.parse): |
|---|
| 957 | n/a | if name.startswith('_') or name in undocumented: |
|---|
| 958 | n/a | continue |
|---|
| 959 | n/a | object = getattr(urllib.parse, name) |
|---|
| 960 | n/a | if getattr(object, '__module__', None) == 'urllib.parse': |
|---|
| 961 | n/a | expected.append(name) |
|---|
| 962 | n/a | self.assertCountEqual(urllib.parse.__all__, expected) |
|---|
| 963 | n/a | |
|---|
| 964 | n/a | |
|---|
| 965 | n/a | class Utility_Tests(unittest.TestCase): |
|---|
| 966 | n/a | """Testcase to test the various utility functions in the urllib.""" |
|---|
| 967 | n/a | # In Python 2 this test class was in test_urllib. |
|---|
| 968 | n/a | |
|---|
| 969 | n/a | def test_splittype(self): |
|---|
| 970 | n/a | splittype = urllib.parse.splittype |
|---|
| 971 | n/a | self.assertEqual(splittype('type:opaquestring'), ('type', 'opaquestring')) |
|---|
| 972 | n/a | self.assertEqual(splittype('opaquestring'), (None, 'opaquestring')) |
|---|
| 973 | n/a | self.assertEqual(splittype(':opaquestring'), (None, ':opaquestring')) |
|---|
| 974 | n/a | self.assertEqual(splittype('type:'), ('type', '')) |
|---|
| 975 | n/a | self.assertEqual(splittype('type:opaque:string'), ('type', 'opaque:string')) |
|---|
| 976 | n/a | |
|---|
| 977 | n/a | def test_splithost(self): |
|---|
| 978 | n/a | splithost = urllib.parse.splithost |
|---|
| 979 | n/a | self.assertEqual(splithost('//www.example.org:80/foo/bar/baz.html'), |
|---|
| 980 | n/a | ('www.example.org:80', '/foo/bar/baz.html')) |
|---|
| 981 | n/a | self.assertEqual(splithost('//www.example.org:80'), |
|---|
| 982 | n/a | ('www.example.org:80', '')) |
|---|
| 983 | n/a | self.assertEqual(splithost('/foo/bar/baz.html'), |
|---|
| 984 | n/a | (None, '/foo/bar/baz.html')) |
|---|
| 985 | n/a | |
|---|
| 986 | n/a | def test_splituser(self): |
|---|
| 987 | n/a | splituser = urllib.parse.splituser |
|---|
| 988 | n/a | self.assertEqual(splituser('User:Pass@www.python.org:080'), |
|---|
| 989 | n/a | ('User:Pass', 'www.python.org:080')) |
|---|
| 990 | n/a | self.assertEqual(splituser('@www.python.org:080'), |
|---|
| 991 | n/a | ('', 'www.python.org:080')) |
|---|
| 992 | n/a | self.assertEqual(splituser('www.python.org:080'), |
|---|
| 993 | n/a | (None, 'www.python.org:080')) |
|---|
| 994 | n/a | self.assertEqual(splituser('User:Pass@'), |
|---|
| 995 | n/a | ('User:Pass', '')) |
|---|
| 996 | n/a | self.assertEqual(splituser('User@example.com:Pass@www.python.org:080'), |
|---|
| 997 | n/a | ('User@example.com:Pass', 'www.python.org:080')) |
|---|
| 998 | n/a | |
|---|
| 999 | n/a | def test_splitpasswd(self): |
|---|
| 1000 | n/a | # Some of the password examples are not sensible, but it is added to |
|---|
| 1001 | n/a | # confirming to RFC2617 and addressing issue4675. |
|---|
| 1002 | n/a | splitpasswd = urllib.parse.splitpasswd |
|---|
| 1003 | n/a | self.assertEqual(splitpasswd('user:ab'), ('user', 'ab')) |
|---|
| 1004 | n/a | self.assertEqual(splitpasswd('user:a\nb'), ('user', 'a\nb')) |
|---|
| 1005 | n/a | self.assertEqual(splitpasswd('user:a\tb'), ('user', 'a\tb')) |
|---|
| 1006 | n/a | self.assertEqual(splitpasswd('user:a\rb'), ('user', 'a\rb')) |
|---|
| 1007 | n/a | self.assertEqual(splitpasswd('user:a\fb'), ('user', 'a\fb')) |
|---|
| 1008 | n/a | self.assertEqual(splitpasswd('user:a\vb'), ('user', 'a\vb')) |
|---|
| 1009 | n/a | self.assertEqual(splitpasswd('user:a:b'), ('user', 'a:b')) |
|---|
| 1010 | n/a | self.assertEqual(splitpasswd('user:a b'), ('user', 'a b')) |
|---|
| 1011 | n/a | self.assertEqual(splitpasswd('user 2:ab'), ('user 2', 'ab')) |
|---|
| 1012 | n/a | self.assertEqual(splitpasswd('user+1:a+b'), ('user+1', 'a+b')) |
|---|
| 1013 | n/a | self.assertEqual(splitpasswd('user:'), ('user', '')) |
|---|
| 1014 | n/a | self.assertEqual(splitpasswd('user'), ('user', None)) |
|---|
| 1015 | n/a | self.assertEqual(splitpasswd(':ab'), ('', 'ab')) |
|---|
| 1016 | n/a | |
|---|
| 1017 | n/a | def test_splitport(self): |
|---|
| 1018 | n/a | splitport = urllib.parse.splitport |
|---|
| 1019 | n/a | self.assertEqual(splitport('parrot:88'), ('parrot', '88')) |
|---|
| 1020 | n/a | self.assertEqual(splitport('parrot'), ('parrot', None)) |
|---|
| 1021 | n/a | self.assertEqual(splitport('parrot:'), ('parrot', None)) |
|---|
| 1022 | n/a | self.assertEqual(splitport('127.0.0.1'), ('127.0.0.1', None)) |
|---|
| 1023 | n/a | self.assertEqual(splitport('parrot:cheese'), ('parrot:cheese', None)) |
|---|
| 1024 | n/a | self.assertEqual(splitport('[::1]:88'), ('[::1]', '88')) |
|---|
| 1025 | n/a | self.assertEqual(splitport('[::1]'), ('[::1]', None)) |
|---|
| 1026 | n/a | self.assertEqual(splitport(':88'), ('', '88')) |
|---|
| 1027 | n/a | |
|---|
| 1028 | n/a | def test_splitnport(self): |
|---|
| 1029 | n/a | splitnport = urllib.parse.splitnport |
|---|
| 1030 | n/a | self.assertEqual(splitnport('parrot:88'), ('parrot', 88)) |
|---|
| 1031 | n/a | self.assertEqual(splitnport('parrot'), ('parrot', -1)) |
|---|
| 1032 | n/a | self.assertEqual(splitnport('parrot', 55), ('parrot', 55)) |
|---|
| 1033 | n/a | self.assertEqual(splitnport('parrot:'), ('parrot', -1)) |
|---|
| 1034 | n/a | self.assertEqual(splitnport('parrot:', 55), ('parrot', 55)) |
|---|
| 1035 | n/a | self.assertEqual(splitnport('127.0.0.1'), ('127.0.0.1', -1)) |
|---|
| 1036 | n/a | self.assertEqual(splitnport('127.0.0.1', 55), ('127.0.0.1', 55)) |
|---|
| 1037 | n/a | self.assertEqual(splitnport('parrot:cheese'), ('parrot', None)) |
|---|
| 1038 | n/a | self.assertEqual(splitnport('parrot:cheese', 55), ('parrot', None)) |
|---|
| 1039 | n/a | |
|---|
| 1040 | n/a | def test_splitquery(self): |
|---|
| 1041 | n/a | # Normal cases are exercised by other tests; ensure that we also |
|---|
| 1042 | n/a | # catch cases with no port specified (testcase ensuring coverage) |
|---|
| 1043 | n/a | splitquery = urllib.parse.splitquery |
|---|
| 1044 | n/a | self.assertEqual(splitquery('http://python.org/fake?foo=bar'), |
|---|
| 1045 | n/a | ('http://python.org/fake', 'foo=bar')) |
|---|
| 1046 | n/a | self.assertEqual(splitquery('http://python.org/fake?foo=bar?'), |
|---|
| 1047 | n/a | ('http://python.org/fake?foo=bar', '')) |
|---|
| 1048 | n/a | self.assertEqual(splitquery('http://python.org/fake'), |
|---|
| 1049 | n/a | ('http://python.org/fake', None)) |
|---|
| 1050 | n/a | self.assertEqual(splitquery('?foo=bar'), ('', 'foo=bar')) |
|---|
| 1051 | n/a | |
|---|
| 1052 | n/a | def test_splittag(self): |
|---|
| 1053 | n/a | splittag = urllib.parse.splittag |
|---|
| 1054 | n/a | self.assertEqual(splittag('http://example.com?foo=bar#baz'), |
|---|
| 1055 | n/a | ('http://example.com?foo=bar', 'baz')) |
|---|
| 1056 | n/a | self.assertEqual(splittag('http://example.com?foo=bar#'), |
|---|
| 1057 | n/a | ('http://example.com?foo=bar', '')) |
|---|
| 1058 | n/a | self.assertEqual(splittag('#baz'), ('', 'baz')) |
|---|
| 1059 | n/a | self.assertEqual(splittag('http://example.com?foo=bar'), |
|---|
| 1060 | n/a | ('http://example.com?foo=bar', None)) |
|---|
| 1061 | n/a | self.assertEqual(splittag('http://example.com?foo=bar#baz#boo'), |
|---|
| 1062 | n/a | ('http://example.com?foo=bar#baz', 'boo')) |
|---|
| 1063 | n/a | |
|---|
| 1064 | n/a | def test_splitattr(self): |
|---|
| 1065 | n/a | splitattr = urllib.parse.splitattr |
|---|
| 1066 | n/a | self.assertEqual(splitattr('/path;attr1=value1;attr2=value2'), |
|---|
| 1067 | n/a | ('/path', ['attr1=value1', 'attr2=value2'])) |
|---|
| 1068 | n/a | self.assertEqual(splitattr('/path;'), ('/path', [''])) |
|---|
| 1069 | n/a | self.assertEqual(splitattr(';attr1=value1;attr2=value2'), |
|---|
| 1070 | n/a | ('', ['attr1=value1', 'attr2=value2'])) |
|---|
| 1071 | n/a | self.assertEqual(splitattr('/path'), ('/path', [])) |
|---|
| 1072 | n/a | |
|---|
| 1073 | n/a | def test_splitvalue(self): |
|---|
| 1074 | n/a | # Normal cases are exercised by other tests; test pathological cases |
|---|
| 1075 | n/a | # with no key/value pairs. (testcase ensuring coverage) |
|---|
| 1076 | n/a | splitvalue = urllib.parse.splitvalue |
|---|
| 1077 | n/a | self.assertEqual(splitvalue('foo=bar'), ('foo', 'bar')) |
|---|
| 1078 | n/a | self.assertEqual(splitvalue('foo='), ('foo', '')) |
|---|
| 1079 | n/a | self.assertEqual(splitvalue('=bar'), ('', 'bar')) |
|---|
| 1080 | n/a | self.assertEqual(splitvalue('foobar'), ('foobar', None)) |
|---|
| 1081 | n/a | self.assertEqual(splitvalue('foo=bar=baz'), ('foo', 'bar=baz')) |
|---|
| 1082 | n/a | |
|---|
| 1083 | n/a | def test_to_bytes(self): |
|---|
| 1084 | n/a | result = urllib.parse.to_bytes('http://www.python.org') |
|---|
| 1085 | n/a | self.assertEqual(result, 'http://www.python.org') |
|---|
| 1086 | n/a | self.assertRaises(UnicodeError, urllib.parse.to_bytes, |
|---|
| 1087 | n/a | 'http://www.python.org/medi\u00e6val') |
|---|
| 1088 | n/a | |
|---|
| 1089 | n/a | def test_unwrap(self): |
|---|
| 1090 | n/a | url = urllib.parse.unwrap('<URL:type://host/path>') |
|---|
| 1091 | n/a | self.assertEqual(url, 'type://host/path') |
|---|
| 1092 | n/a | |
|---|
| 1093 | n/a | |
|---|
| 1094 | n/a | if __name__ == "__main__": |
|---|
| 1095 | n/a | unittest.main() |
|---|
