1 | #! /usr/bin/env python
|
---|
2 |
|
---|
3 | from test import test_support
|
---|
4 | import unittest
|
---|
5 | import urlparse
|
---|
6 |
|
---|
7 | RFC1808_BASE = "http://a/b/c/d;p?q#f"
|
---|
8 | RFC2396_BASE = "http://a/b/c/d;p?q"
|
---|
9 | RFC3986_BASE = 'http://a/b/c/d;p?q'
|
---|
10 | SIMPLE_BASE = 'http://a/b/c/d'
|
---|
11 |
|
---|
12 | # A list of test cases. Each test case is a two-tuple that contains
|
---|
13 | # a string with the query and a dictionary with the expected result.
|
---|
14 |
|
---|
15 | parse_qsl_test_cases = [
|
---|
16 | ("", []),
|
---|
17 | ("&", []),
|
---|
18 | ("&&", []),
|
---|
19 | ("=", [('', '')]),
|
---|
20 | ("=a", [('', 'a')]),
|
---|
21 | ("a", [('a', '')]),
|
---|
22 | ("a=", [('a', '')]),
|
---|
23 | ("a=", [('a', '')]),
|
---|
24 | ("&a=b", [('a', 'b')]),
|
---|
25 | ("a=a+b&b=b+c", [('a', 'a b'), ('b', 'b c')]),
|
---|
26 | ("a=1&a=2", [('a', '1'), ('a', '2')]),
|
---|
27 | ]
|
---|
28 |
|
---|
29 | class UrlParseTestCase(unittest.TestCase):
|
---|
30 |
|
---|
31 | def checkRoundtrips(self, url, parsed, split):
|
---|
32 | result = urlparse.urlparse(url)
|
---|
33 | self.assertEqual(result, parsed)
|
---|
34 | t = (result.scheme, result.netloc, result.path,
|
---|
35 | result.params, result.query, result.fragment)
|
---|
36 | self.assertEqual(t, parsed)
|
---|
37 | # put it back together and it should be the same
|
---|
38 | result2 = urlparse.urlunparse(result)
|
---|
39 | self.assertEqual(result2, url)
|
---|
40 | self.assertEqual(result2, result.geturl())
|
---|
41 |
|
---|
42 | # the result of geturl() is a fixpoint; we can always parse it
|
---|
43 | # again to get the same result:
|
---|
44 | result3 = urlparse.urlparse(result.geturl())
|
---|
45 | self.assertEqual(result3.geturl(), result.geturl())
|
---|
46 | self.assertEqual(result3, result)
|
---|
47 | self.assertEqual(result3.scheme, result.scheme)
|
---|
48 | self.assertEqual(result3.netloc, result.netloc)
|
---|
49 | self.assertEqual(result3.path, result.path)
|
---|
50 | self.assertEqual(result3.params, result.params)
|
---|
51 | self.assertEqual(result3.query, result.query)
|
---|
52 | self.assertEqual(result3.fragment, result.fragment)
|
---|
53 | self.assertEqual(result3.username, result.username)
|
---|
54 | self.assertEqual(result3.password, result.password)
|
---|
55 | self.assertEqual(result3.hostname, result.hostname)
|
---|
56 | self.assertEqual(result3.port, result.port)
|
---|
57 |
|
---|
58 | # check the roundtrip using urlsplit() as well
|
---|
59 | result = urlparse.urlsplit(url)
|
---|
60 | self.assertEqual(result, split)
|
---|
61 | t = (result.scheme, result.netloc, result.path,
|
---|
62 | result.query, result.fragment)
|
---|
63 | self.assertEqual(t, split)
|
---|
64 | result2 = urlparse.urlunsplit(result)
|
---|
65 | self.assertEqual(result2, url)
|
---|
66 | self.assertEqual(result2, result.geturl())
|
---|
67 |
|
---|
68 | # check the fixpoint property of re-parsing the result of geturl()
|
---|
69 | result3 = urlparse.urlsplit(result.geturl())
|
---|
70 | self.assertEqual(result3.geturl(), result.geturl())
|
---|
71 | self.assertEqual(result3, result)
|
---|
72 | self.assertEqual(result3.scheme, result.scheme)
|
---|
73 | self.assertEqual(result3.netloc, result.netloc)
|
---|
74 | self.assertEqual(result3.path, result.path)
|
---|
75 | self.assertEqual(result3.query, result.query)
|
---|
76 | self.assertEqual(result3.fragment, result.fragment)
|
---|
77 | self.assertEqual(result3.username, result.username)
|
---|
78 | self.assertEqual(result3.password, result.password)
|
---|
79 | self.assertEqual(result3.hostname, result.hostname)
|
---|
80 | self.assertEqual(result3.port, result.port)
|
---|
81 |
|
---|
82 | def test_qsl(self):
|
---|
83 | for orig, expect in parse_qsl_test_cases:
|
---|
84 | result = urlparse.parse_qsl(orig, keep_blank_values=True)
|
---|
85 | self.assertEqual(result, expect, "Error parsing %r" % orig)
|
---|
86 | expect_without_blanks = [v for v in expect if len(v[1])]
|
---|
87 | result = urlparse.parse_qsl(orig, keep_blank_values=False)
|
---|
88 | self.assertEqual(result, expect_without_blanks,
|
---|
89 | "Error parsing %r" % orig)
|
---|
90 |
|
---|
91 |
|
---|
92 | def test_roundtrips(self):
|
---|
93 | testcases = [
|
---|
94 | ('file:///tmp/junk.txt',
|
---|
95 | ('file', '', '/tmp/junk.txt', '', '', ''),
|
---|
96 | ('file', '', '/tmp/junk.txt', '', '')),
|
---|
97 | ('imap://mail.python.org/mbox1',
|
---|
98 | ('imap', 'mail.python.org', '/mbox1', '', '', ''),
|
---|
99 | ('imap', 'mail.python.org', '/mbox1', '', '')),
|
---|
100 | ('mms://wms.sys.hinet.net/cts/Drama/09006251100.asf',
|
---|
101 | ('mms', 'wms.sys.hinet.net', '/cts/Drama/09006251100.asf',
|
---|
102 | '', '', ''),
|
---|
103 | ('mms', 'wms.sys.hinet.net', '/cts/Drama/09006251100.asf',
|
---|
104 | '', '')),
|
---|
105 | ('nfs://server/path/to/file.txt',
|
---|
106 | ('nfs', 'server', '/path/to/file.txt', '', '', ''),
|
---|
107 | ('nfs', 'server', '/path/to/file.txt', '', '')),
|
---|
108 | ('svn+ssh://svn.zope.org/repos/main/ZConfig/trunk/',
|
---|
109 | ('svn+ssh', 'svn.zope.org', '/repos/main/ZConfig/trunk/',
|
---|
110 | '', '', ''),
|
---|
111 | ('svn+ssh', 'svn.zope.org', '/repos/main/ZConfig/trunk/',
|
---|
112 | '', '')),
|
---|
113 | ('git+ssh://git@github.com/user/project.git',
|
---|
114 | ('git+ssh', 'git@github.com','/user/project.git',
|
---|
115 | '','',''),
|
---|
116 | ('git+ssh', 'git@github.com','/user/project.git',
|
---|
117 | '', ''))
|
---|
118 | ]
|
---|
119 | for url, parsed, split in testcases:
|
---|
120 | self.checkRoundtrips(url, parsed, split)
|
---|
121 |
|
---|
122 | def test_http_roundtrips(self):
|
---|
123 | # urlparse.urlsplit treats 'http:' as an optimized special case,
|
---|
124 | # so we test both 'http:' and 'https:' in all the following.
|
---|
125 | # Three cheers for white box knowledge!
|
---|
126 | testcases = [
|
---|
127 | ('://www.python.org',
|
---|
128 | ('www.python.org', '', '', '', ''),
|
---|
129 | ('www.python.org', '', '', '')),
|
---|
130 | ('://www.python.org#abc',
|
---|
131 | ('www.python.org', '', '', '', 'abc'),
|
---|
132 | ('www.python.org', '', '', 'abc')),
|
---|
133 | ('://www.python.org?q=abc',
|
---|
134 | ('www.python.org', '', '', 'q=abc', ''),
|
---|
135 | ('www.python.org', '', 'q=abc', '')),
|
---|
136 | ('://www.python.org/#abc',
|
---|
137 | ('www.python.org', '/', '', '', 'abc'),
|
---|
138 | ('www.python.org', '/', '', 'abc')),
|
---|
139 | ('://a/b/c/d;p?q#f',
|
---|
140 | ('a', '/b/c/d', 'p', 'q', 'f'),
|
---|
141 | ('a', '/b/c/d;p', 'q', 'f')),
|
---|
142 | ]
|
---|
143 | for scheme in ('http', 'https'):
|
---|
144 | for url, parsed, split in testcases:
|
---|
145 | url = scheme + url
|
---|
146 | parsed = (scheme,) + parsed
|
---|
147 | split = (scheme,) + split
|
---|
148 | self.checkRoundtrips(url, parsed, split)
|
---|
149 |
|
---|
150 | def checkJoin(self, base, relurl, expected):
|
---|
151 | self.assertEqual(urlparse.urljoin(base, relurl), expected,
|
---|
152 | (base, relurl, expected))
|
---|
153 |
|
---|
154 | def test_unparse_parse(self):
|
---|
155 | for u in ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]:
|
---|
156 | self.assertEqual(urlparse.urlunsplit(urlparse.urlsplit(u)), u)
|
---|
157 | self.assertEqual(urlparse.urlunparse(urlparse.urlparse(u)), u)
|
---|
158 |
|
---|
159 | def test_RFC1808(self):
|
---|
160 | # "normal" cases from RFC 1808:
|
---|
161 | self.checkJoin(RFC1808_BASE, 'g:h', 'g:h')
|
---|
162 | self.checkJoin(RFC1808_BASE, 'g', 'http://a/b/c/g')
|
---|
163 | self.checkJoin(RFC1808_BASE, './g', 'http://a/b/c/g')
|
---|
164 | self.checkJoin(RFC1808_BASE, 'g/', 'http://a/b/c/g/')
|
---|
165 | self.checkJoin(RFC1808_BASE, '/g', 'http://a/g')
|
---|
166 | self.checkJoin(RFC1808_BASE, '//g', 'http://g')
|
---|
167 | self.checkJoin(RFC1808_BASE, 'g?y', 'http://a/b/c/g?y')
|
---|
168 | self.checkJoin(RFC1808_BASE, 'g?y/./x', 'http://a/b/c/g?y/./x')
|
---|
169 | self.checkJoin(RFC1808_BASE, '#s', 'http://a/b/c/d;p?q#s')
|
---|
170 | self.checkJoin(RFC1808_BASE, 'g#s', 'http://a/b/c/g#s')
|
---|
171 | self.checkJoin(RFC1808_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x')
|
---|
172 | self.checkJoin(RFC1808_BASE, 'g?y#s', 'http://a/b/c/g?y#s')
|
---|
173 | self.checkJoin(RFC1808_BASE, 'g;x', 'http://a/b/c/g;x')
|
---|
174 | self.checkJoin(RFC1808_BASE, 'g;x?y#s', 'http://a/b/c/g;x?y#s')
|
---|
175 | self.checkJoin(RFC1808_BASE, '.', 'http://a/b/c/')
|
---|
176 | self.checkJoin(RFC1808_BASE, './', 'http://a/b/c/')
|
---|
177 | self.checkJoin(RFC1808_BASE, '..', 'http://a/b/')
|
---|
178 | self.checkJoin(RFC1808_BASE, '../', 'http://a/b/')
|
---|
179 | self.checkJoin(RFC1808_BASE, '../g', 'http://a/b/g')
|
---|
180 | self.checkJoin(RFC1808_BASE, '../..', 'http://a/')
|
---|
181 | self.checkJoin(RFC1808_BASE, '../../', 'http://a/')
|
---|
182 | self.checkJoin(RFC1808_BASE, '../../g', 'http://a/g')
|
---|
183 |
|
---|
184 | # "abnormal" cases from RFC 1808:
|
---|
185 | self.checkJoin(RFC1808_BASE, '', 'http://a/b/c/d;p?q#f')
|
---|
186 | self.checkJoin(RFC1808_BASE, '../../../g', 'http://a/../g')
|
---|
187 | self.checkJoin(RFC1808_BASE, '../../../../g', 'http://a/../../g')
|
---|
188 | self.checkJoin(RFC1808_BASE, '/./g', 'http://a/./g')
|
---|
189 | self.checkJoin(RFC1808_BASE, '/../g', 'http://a/../g')
|
---|
190 | self.checkJoin(RFC1808_BASE, 'g.', 'http://a/b/c/g.')
|
---|
191 | self.checkJoin(RFC1808_BASE, '.g', 'http://a/b/c/.g')
|
---|
192 | self.checkJoin(RFC1808_BASE, 'g..', 'http://a/b/c/g..')
|
---|
193 | self.checkJoin(RFC1808_BASE, '..g', 'http://a/b/c/..g')
|
---|
194 | self.checkJoin(RFC1808_BASE, './../g', 'http://a/b/g')
|
---|
195 | self.checkJoin(RFC1808_BASE, './g/.', 'http://a/b/c/g/')
|
---|
196 | self.checkJoin(RFC1808_BASE, 'g/./h', 'http://a/b/c/g/h')
|
---|
197 | self.checkJoin(RFC1808_BASE, 'g/../h', 'http://a/b/c/h')
|
---|
198 |
|
---|
199 | # RFC 1808 and RFC 1630 disagree on these (according to RFC 1808),
|
---|
200 | # so we'll not actually run these tests (which expect 1808 behavior).
|
---|
201 | #self.checkJoin(RFC1808_BASE, 'http:g', 'http:g')
|
---|
202 | #self.checkJoin(RFC1808_BASE, 'http:', 'http:')
|
---|
203 |
|
---|
204 | def test_RFC2368(self):
|
---|
205 | # Issue 11467: path that starts with a number is not parsed correctly
|
---|
206 | self.assertEqual(urlparse.urlparse('mailto:1337@example.org'),
|
---|
207 | ('mailto', '', '1337@example.org', '', '', ''))
|
---|
208 |
|
---|
209 | def test_RFC2396(self):
|
---|
210 | # cases from RFC 2396
|
---|
211 | self.checkJoin(RFC2396_BASE, 'g:h', 'g:h')
|
---|
212 | self.checkJoin(RFC2396_BASE, 'g', 'http://a/b/c/g')
|
---|
213 | self.checkJoin(RFC2396_BASE, './g', 'http://a/b/c/g')
|
---|
214 | self.checkJoin(RFC2396_BASE, 'g/', 'http://a/b/c/g/')
|
---|
215 | self.checkJoin(RFC2396_BASE, '/g', 'http://a/g')
|
---|
216 | self.checkJoin(RFC2396_BASE, '//g', 'http://g')
|
---|
217 | self.checkJoin(RFC2396_BASE, 'g?y', 'http://a/b/c/g?y')
|
---|
218 | self.checkJoin(RFC2396_BASE, '#s', 'http://a/b/c/d;p?q#s')
|
---|
219 | self.checkJoin(RFC2396_BASE, 'g#s', 'http://a/b/c/g#s')
|
---|
220 | self.checkJoin(RFC2396_BASE, 'g?y#s', 'http://a/b/c/g?y#s')
|
---|
221 | self.checkJoin(RFC2396_BASE, 'g;x', 'http://a/b/c/g;x')
|
---|
222 | self.checkJoin(RFC2396_BASE, 'g;x?y#s', 'http://a/b/c/g;x?y#s')
|
---|
223 | self.checkJoin(RFC2396_BASE, '.', 'http://a/b/c/')
|
---|
224 | self.checkJoin(RFC2396_BASE, './', 'http://a/b/c/')
|
---|
225 | self.checkJoin(RFC2396_BASE, '..', 'http://a/b/')
|
---|
226 | self.checkJoin(RFC2396_BASE, '../', 'http://a/b/')
|
---|
227 | self.checkJoin(RFC2396_BASE, '../g', 'http://a/b/g')
|
---|
228 | self.checkJoin(RFC2396_BASE, '../..', 'http://a/')
|
---|
229 | self.checkJoin(RFC2396_BASE, '../../', 'http://a/')
|
---|
230 | self.checkJoin(RFC2396_BASE, '../../g', 'http://a/g')
|
---|
231 | self.checkJoin(RFC2396_BASE, '', RFC2396_BASE)
|
---|
232 | self.checkJoin(RFC2396_BASE, '../../../g', 'http://a/../g')
|
---|
233 | self.checkJoin(RFC2396_BASE, '../../../../g', 'http://a/../../g')
|
---|
234 | self.checkJoin(RFC2396_BASE, '/./g', 'http://a/./g')
|
---|
235 | self.checkJoin(RFC2396_BASE, '/../g', 'http://a/../g')
|
---|
236 | self.checkJoin(RFC2396_BASE, 'g.', 'http://a/b/c/g.')
|
---|
237 | self.checkJoin(RFC2396_BASE, '.g', 'http://a/b/c/.g')
|
---|
238 | self.checkJoin(RFC2396_BASE, 'g..', 'http://a/b/c/g..')
|
---|
239 | self.checkJoin(RFC2396_BASE, '..g', 'http://a/b/c/..g')
|
---|
240 | self.checkJoin(RFC2396_BASE, './../g', 'http://a/b/g')
|
---|
241 | self.checkJoin(RFC2396_BASE, './g/.', 'http://a/b/c/g/')
|
---|
242 | self.checkJoin(RFC2396_BASE, 'g/./h', 'http://a/b/c/g/h')
|
---|
243 | self.checkJoin(RFC2396_BASE, 'g/../h', 'http://a/b/c/h')
|
---|
244 | self.checkJoin(RFC2396_BASE, 'g;x=1/./y', 'http://a/b/c/g;x=1/y')
|
---|
245 | self.checkJoin(RFC2396_BASE, 'g;x=1/../y', 'http://a/b/c/y')
|
---|
246 | self.checkJoin(RFC2396_BASE, 'g?y/./x', 'http://a/b/c/g?y/./x')
|
---|
247 | self.checkJoin(RFC2396_BASE, 'g?y/../x', 'http://a/b/c/g?y/../x')
|
---|
248 | self.checkJoin(RFC2396_BASE, 'g#s/./x', 'http://a/b/c/g#s/./x')
|
---|
249 | self.checkJoin(RFC2396_BASE, 'g#s/../x', 'http://a/b/c/g#s/../x')
|
---|
250 |
|
---|
251 | def test_RFC3986(self):
|
---|
252 | # Test cases from RFC3986
|
---|
253 | self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y')
|
---|
254 | self.checkJoin(RFC2396_BASE, ';x', 'http://a/b/c/;x')
|
---|
255 | self.checkJoin(RFC3986_BASE, 'g:h','g:h')
|
---|
256 | self.checkJoin(RFC3986_BASE, 'g','http://a/b/c/g')
|
---|
257 | self.checkJoin(RFC3986_BASE, './g','http://a/b/c/g')
|
---|
258 | self.checkJoin(RFC3986_BASE, 'g/','http://a/b/c/g/')
|
---|
259 | self.checkJoin(RFC3986_BASE, '/g','http://a/g')
|
---|
260 | self.checkJoin(RFC3986_BASE, '//g','http://g')
|
---|
261 | self.checkJoin(RFC3986_BASE, '?y','http://a/b/c/d;p?y')
|
---|
262 | self.checkJoin(RFC3986_BASE, 'g?y','http://a/b/c/g?y')
|
---|
263 | self.checkJoin(RFC3986_BASE, '#s','http://a/b/c/d;p?q#s')
|
---|
264 | self.checkJoin(RFC3986_BASE, 'g#s','http://a/b/c/g#s')
|
---|
265 | self.checkJoin(RFC3986_BASE, 'g?y#s','http://a/b/c/g?y#s')
|
---|
266 | self.checkJoin(RFC3986_BASE, ';x','http://a/b/c/;x')
|
---|
267 | self.checkJoin(RFC3986_BASE, 'g;x','http://a/b/c/g;x')
|
---|
268 | self.checkJoin(RFC3986_BASE, 'g;x?y#s','http://a/b/c/g;x?y#s')
|
---|
269 | self.checkJoin(RFC3986_BASE, '','http://a/b/c/d;p?q')
|
---|
270 | self.checkJoin(RFC3986_BASE, '.','http://a/b/c/')
|
---|
271 | self.checkJoin(RFC3986_BASE, './','http://a/b/c/')
|
---|
272 | self.checkJoin(RFC3986_BASE, '..','http://a/b/')
|
---|
273 | self.checkJoin(RFC3986_BASE, '../','http://a/b/')
|
---|
274 | self.checkJoin(RFC3986_BASE, '../g','http://a/b/g')
|
---|
275 | self.checkJoin(RFC3986_BASE, '../..','http://a/')
|
---|
276 | self.checkJoin(RFC3986_BASE, '../../','http://a/')
|
---|
277 | self.checkJoin(RFC3986_BASE, '../../g','http://a/g')
|
---|
278 |
|
---|
279 | #Abnormal Examples
|
---|
280 |
|
---|
281 | # The 'abnormal scenarios' are incompatible with RFC2986 parsing
|
---|
282 | # Tests are here for reference.
|
---|
283 |
|
---|
284 | #self.checkJoin(RFC3986_BASE, '../../../g','http://a/g')
|
---|
285 | #self.checkJoin(RFC3986_BASE, '../../../../g','http://a/g')
|
---|
286 | #self.checkJoin(RFC3986_BASE, '/./g','http://a/g')
|
---|
287 | #self.checkJoin(RFC3986_BASE, '/../g','http://a/g')
|
---|
288 |
|
---|
289 | self.checkJoin(RFC3986_BASE, 'g.','http://a/b/c/g.')
|
---|
290 | self.checkJoin(RFC3986_BASE, '.g','http://a/b/c/.g')
|
---|
291 | self.checkJoin(RFC3986_BASE, 'g..','http://a/b/c/g..')
|
---|
292 | self.checkJoin(RFC3986_BASE, '..g','http://a/b/c/..g')
|
---|
293 | self.checkJoin(RFC3986_BASE, './../g','http://a/b/g')
|
---|
294 | self.checkJoin(RFC3986_BASE, './g/.','http://a/b/c/g/')
|
---|
295 | self.checkJoin(RFC3986_BASE, 'g/./h','http://a/b/c/g/h')
|
---|
296 | self.checkJoin(RFC3986_BASE, 'g/../h','http://a/b/c/h')
|
---|
297 | self.checkJoin(RFC3986_BASE, 'g;x=1/./y','http://a/b/c/g;x=1/y')
|
---|
298 | self.checkJoin(RFC3986_BASE, 'g;x=1/../y','http://a/b/c/y')
|
---|
299 | self.checkJoin(RFC3986_BASE, 'g?y/./x','http://a/b/c/g?y/./x')
|
---|
300 | self.checkJoin(RFC3986_BASE, 'g?y/../x','http://a/b/c/g?y/../x')
|
---|
301 | self.checkJoin(RFC3986_BASE, 'g#s/./x','http://a/b/c/g#s/./x')
|
---|
302 | self.checkJoin(RFC3986_BASE, 'g#s/../x','http://a/b/c/g#s/../x')
|
---|
303 | #self.checkJoin(RFC3986_BASE, 'http:g','http:g') # strict parser
|
---|
304 | self.checkJoin(RFC3986_BASE, 'http:g','http://a/b/c/g') # relaxed parser
|
---|
305 |
|
---|
306 | # Test for issue9721
|
---|
307 | self.checkJoin('http://a/b/c/de', ';x','http://a/b/c/;x')
|
---|
308 |
|
---|
309 | def test_urljoins(self):
|
---|
310 | self.checkJoin(SIMPLE_BASE, 'g:h','g:h')
|
---|
311 | self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g')
|
---|
312 | self.checkJoin(SIMPLE_BASE, 'http:','http://a/b/c/d')
|
---|
313 | self.checkJoin(SIMPLE_BASE, 'g','http://a/b/c/g')
|
---|
314 | self.checkJoin(SIMPLE_BASE, './g','http://a/b/c/g')
|
---|
315 | self.checkJoin(SIMPLE_BASE, 'g/','http://a/b/c/g/')
|
---|
316 | self.checkJoin(SIMPLE_BASE, '/g','http://a/g')
|
---|
317 | self.checkJoin(SIMPLE_BASE, '//g','http://g')
|
---|
318 | self.checkJoin(SIMPLE_BASE, '?y','http://a/b/c/d?y')
|
---|
319 | self.checkJoin(SIMPLE_BASE, 'g?y','http://a/b/c/g?y')
|
---|
320 | self.checkJoin(SIMPLE_BASE, 'g?y/./x','http://a/b/c/g?y/./x')
|
---|
321 | self.checkJoin(SIMPLE_BASE, '.','http://a/b/c/')
|
---|
322 | self.checkJoin(SIMPLE_BASE, './','http://a/b/c/')
|
---|
323 | self.checkJoin(SIMPLE_BASE, '..','http://a/b/')
|
---|
324 | self.checkJoin(SIMPLE_BASE, '../','http://a/b/')
|
---|
325 | self.checkJoin(SIMPLE_BASE, '../g','http://a/b/g')
|
---|
326 | self.checkJoin(SIMPLE_BASE, '../..','http://a/')
|
---|
327 | self.checkJoin(SIMPLE_BASE, '../../g','http://a/g')
|
---|
328 | self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g')
|
---|
329 | self.checkJoin(SIMPLE_BASE, './../g','http://a/b/g')
|
---|
330 | self.checkJoin(SIMPLE_BASE, './g/.','http://a/b/c/g/')
|
---|
331 | self.checkJoin(SIMPLE_BASE, '/./g','http://a/./g')
|
---|
332 | self.checkJoin(SIMPLE_BASE, 'g/./h','http://a/b/c/g/h')
|
---|
333 | self.checkJoin(SIMPLE_BASE, 'g/../h','http://a/b/c/h')
|
---|
334 | self.checkJoin(SIMPLE_BASE, 'http:g','http://a/b/c/g')
|
---|
335 | self.checkJoin(SIMPLE_BASE, 'http:','http://a/b/c/d')
|
---|
336 | self.checkJoin(SIMPLE_BASE, 'http:?y','http://a/b/c/d?y')
|
---|
337 | self.checkJoin(SIMPLE_BASE, 'http:g?y','http://a/b/c/g?y')
|
---|
338 | self.checkJoin(SIMPLE_BASE, 'http:g?y/./x','http://a/b/c/g?y/./x')
|
---|
339 | self.checkJoin('http:///', '..','http:///')
|
---|
340 | self.checkJoin('', 'http://a/b/c/g?y/./x','http://a/b/c/g?y/./x')
|
---|
341 | self.checkJoin('', 'http://a/./g', 'http://a/./g')
|
---|
342 | self.checkJoin('svn://pathtorepo/dir1','dir2','svn://pathtorepo/dir2')
|
---|
343 | self.checkJoin('svn+ssh://pathtorepo/dir1','dir2','svn+ssh://pathtorepo/dir2')
|
---|
344 |
|
---|
345 | def test_RFC2732(self):
|
---|
346 | for url, hostname, port in [
|
---|
347 | ('http://Test.python.org:5432/foo/', 'test.python.org', 5432),
|
---|
348 | ('http://12.34.56.78:5432/foo/', '12.34.56.78', 5432),
|
---|
349 | ('http://[::1]:5432/foo/', '::1', 5432),
|
---|
350 | ('http://[dead:beef::1]:5432/foo/', 'dead:beef::1', 5432),
|
---|
351 | ('http://[dead:beef::]:5432/foo/', 'dead:beef::', 5432),
|
---|
352 | ('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]:5432/foo/',
|
---|
353 | 'dead:beef:cafe:5417:affe:8fa3:deaf:feed', 5432),
|
---|
354 | ('http://[::12.34.56.78]:5432/foo/', '::12.34.56.78', 5432),
|
---|
355 | ('http://[::ffff:12.34.56.78]:5432/foo/',
|
---|
356 | '::ffff:12.34.56.78', 5432),
|
---|
357 | ('http://Test.python.org/foo/', 'test.python.org', None),
|
---|
358 | ('http://12.34.56.78/foo/', '12.34.56.78', None),
|
---|
359 | ('http://[::1]/foo/', '::1', None),
|
---|
360 | ('http://[dead:beef::1]/foo/', 'dead:beef::1', None),
|
---|
361 | ('http://[dead:beef::]/foo/', 'dead:beef::', None),
|
---|
362 | ('http://[dead:beef:cafe:5417:affe:8FA3:deaf:feed]/foo/',
|
---|
363 | 'dead:beef:cafe:5417:affe:8fa3:deaf:feed', None),
|
---|
364 | ('http://[::12.34.56.78]/foo/', '::12.34.56.78', None),
|
---|
365 | ('http://[::ffff:12.34.56.78]/foo/',
|
---|
366 | '::ffff:12.34.56.78', None),
|
---|
367 | ]:
|
---|
368 | urlparsed = urlparse.urlparse(url)
|
---|
369 | self.assertEqual((urlparsed.hostname, urlparsed.port) , (hostname, port))
|
---|
370 |
|
---|
371 | for invalid_url in [
|
---|
372 | 'http://::12.34.56.78]/',
|
---|
373 | 'http://[::1/foo/',
|
---|
374 | 'ftp://[::1/foo/bad]/bad',
|
---|
375 | 'http://[::1/foo/bad]/bad',
|
---|
376 | 'http://[::ffff:12.34.56.78']:
|
---|
377 | self.assertRaises(ValueError, urlparse.urlparse, invalid_url)
|
---|
378 |
|
---|
379 | def test_urldefrag(self):
|
---|
380 | for url, defrag, frag in [
|
---|
381 | ('http://python.org#frag', 'http://python.org', 'frag'),
|
---|
382 | ('http://python.org', 'http://python.org', ''),
|
---|
383 | ('http://python.org/#frag', 'http://python.org/', 'frag'),
|
---|
384 | ('http://python.org/', 'http://python.org/', ''),
|
---|
385 | ('http://python.org/?q#frag', 'http://python.org/?q', 'frag'),
|
---|
386 | ('http://python.org/?q', 'http://python.org/?q', ''),
|
---|
387 | ('http://python.org/p#frag', 'http://python.org/p', 'frag'),
|
---|
388 | ('http://python.org/p?q', 'http://python.org/p?q', ''),
|
---|
389 | (RFC1808_BASE, 'http://a/b/c/d;p?q', 'f'),
|
---|
390 | (RFC2396_BASE, 'http://a/b/c/d;p?q', ''),
|
---|
391 | ]:
|
---|
392 | self.assertEqual(urlparse.urldefrag(url), (defrag, frag))
|
---|
393 |
|
---|
394 | def test_urlsplit_attributes(self):
|
---|
395 | url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
|
---|
396 | p = urlparse.urlsplit(url)
|
---|
397 | self.assertEqual(p.scheme, "http")
|
---|
398 | self.assertEqual(p.netloc, "WWW.PYTHON.ORG")
|
---|
399 | self.assertEqual(p.path, "/doc/")
|
---|
400 | self.assertEqual(p.query, "")
|
---|
401 | self.assertEqual(p.fragment, "frag")
|
---|
402 | self.assertEqual(p.username, None)
|
---|
403 | self.assertEqual(p.password, None)
|
---|
404 | self.assertEqual(p.hostname, "www.python.org")
|
---|
405 | self.assertEqual(p.port, None)
|
---|
406 | # geturl() won't return exactly the original URL in this case
|
---|
407 | # since the scheme is always case-normalized
|
---|
408 | #self.assertEqual(p.geturl(), url)
|
---|
409 |
|
---|
410 | url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag"
|
---|
411 | p = urlparse.urlsplit(url)
|
---|
412 | self.assertEqual(p.scheme, "http")
|
---|
413 | self.assertEqual(p.netloc, "User:Pass@www.python.org:080")
|
---|
414 | self.assertEqual(p.path, "/doc/")
|
---|
415 | self.assertEqual(p.query, "query=yes")
|
---|
416 | self.assertEqual(p.fragment, "frag")
|
---|
417 | self.assertEqual(p.username, "User")
|
---|
418 | self.assertEqual(p.password, "Pass")
|
---|
419 | self.assertEqual(p.hostname, "www.python.org")
|
---|
420 | self.assertEqual(p.port, 80)
|
---|
421 | self.assertEqual(p.geturl(), url)
|
---|
422 |
|
---|
423 | # Addressing issue1698, which suggests Username can contain
|
---|
424 | # "@" characters. Though not RFC compliant, many ftp sites allow
|
---|
425 | # and request email addresses as usernames.
|
---|
426 |
|
---|
427 | url = "http://User@example.com:Pass@www.python.org:080/doc/?query=yes#frag"
|
---|
428 | p = urlparse.urlsplit(url)
|
---|
429 | self.assertEqual(p.scheme, "http")
|
---|
430 | self.assertEqual(p.netloc, "User@example.com:Pass@www.python.org:080")
|
---|
431 | self.assertEqual(p.path, "/doc/")
|
---|
432 | self.assertEqual(p.query, "query=yes")
|
---|
433 | self.assertEqual(p.fragment, "frag")
|
---|
434 | self.assertEqual(p.username, "User@example.com")
|
---|
435 | self.assertEqual(p.password, "Pass")
|
---|
436 | self.assertEqual(p.hostname, "www.python.org")
|
---|
437 | self.assertEqual(p.port, 80)
|
---|
438 | self.assertEqual(p.geturl(), url)
|
---|
439 |
|
---|
440 | # Verify an illegal port of value greater than 65535 is set as None
|
---|
441 | url = "http://www.python.org:65536"
|
---|
442 | p = urlparse.urlsplit(url)
|
---|
443 | self.assertEqual(p.port, None)
|
---|
444 |
|
---|
445 | def test_issue14072(self):
|
---|
446 | p1 = urlparse.urlsplit('tel:+31-641044153')
|
---|
447 | self.assertEqual(p1.scheme, 'tel')
|
---|
448 | self.assertEqual(p1.path, '+31-641044153')
|
---|
449 |
|
---|
450 | p2 = urlparse.urlsplit('tel:+31641044153')
|
---|
451 | self.assertEqual(p2.scheme, 'tel')
|
---|
452 | self.assertEqual(p2.path, '+31641044153')
|
---|
453 |
|
---|
454 | # Assert for urlparse
|
---|
455 | p1 = urlparse.urlparse('tel:+31-641044153')
|
---|
456 | self.assertEqual(p1.scheme, 'tel')
|
---|
457 | self.assertEqual(p1.path, '+31-641044153')
|
---|
458 |
|
---|
459 | p2 = urlparse.urlparse('tel:+31641044153')
|
---|
460 | self.assertEqual(p2.scheme, 'tel')
|
---|
461 | self.assertEqual(p2.path, '+31641044153')
|
---|
462 |
|
---|
463 |
|
---|
464 | def test_telurl_params(self):
|
---|
465 | p1 = urlparse.urlparse('tel:123-4;phone-context=+1-650-516')
|
---|
466 | self.assertEqual(p1.scheme, 'tel')
|
---|
467 | self.assertEqual(p1.path, '123-4')
|
---|
468 | self.assertEqual(p1.params, 'phone-context=+1-650-516')
|
---|
469 |
|
---|
470 | p1 = urlparse.urlparse('tel:+1-201-555-0123')
|
---|
471 | self.assertEqual(p1.scheme, 'tel')
|
---|
472 | self.assertEqual(p1.path, '+1-201-555-0123')
|
---|
473 | self.assertEqual(p1.params, '')
|
---|
474 |
|
---|
475 | p1 = urlparse.urlparse('tel:7042;phone-context=example.com')
|
---|
476 | self.assertEqual(p1.scheme, 'tel')
|
---|
477 | self.assertEqual(p1.path, '7042')
|
---|
478 | self.assertEqual(p1.params, 'phone-context=example.com')
|
---|
479 |
|
---|
480 | p1 = urlparse.urlparse('tel:863-1234;phone-context=+1-914-555')
|
---|
481 | self.assertEqual(p1.scheme, 'tel')
|
---|
482 | self.assertEqual(p1.path, '863-1234')
|
---|
483 | self.assertEqual(p1.params, 'phone-context=+1-914-555')
|
---|
484 |
|
---|
485 |
|
---|
486 | def test_attributes_bad_port(self):
|
---|
487 | """Check handling of non-integer ports."""
|
---|
488 | p = urlparse.urlsplit("http://www.example.net:foo")
|
---|
489 | self.assertEqual(p.netloc, "www.example.net:foo")
|
---|
490 | self.assertRaises(ValueError, lambda: p.port)
|
---|
491 |
|
---|
492 | p = urlparse.urlparse("http://www.example.net:foo")
|
---|
493 | self.assertEqual(p.netloc, "www.example.net:foo")
|
---|
494 | self.assertRaises(ValueError, lambda: p.port)
|
---|
495 |
|
---|
496 | def test_attributes_without_netloc(self):
|
---|
497 | # This example is straight from RFC 3261. It looks like it
|
---|
498 | # should allow the username, hostname, and port to be filled
|
---|
499 | # in, but doesn't. Since it's a URI and doesn't use the
|
---|
500 | # scheme://netloc syntax, the netloc and related attributes
|
---|
501 | # should be left empty.
|
---|
502 | uri = "sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15"
|
---|
503 | p = urlparse.urlsplit(uri)
|
---|
504 | self.assertEqual(p.netloc, "")
|
---|
505 | self.assertEqual(p.username, None)
|
---|
506 | self.assertEqual(p.password, None)
|
---|
507 | self.assertEqual(p.hostname, None)
|
---|
508 | self.assertEqual(p.port, None)
|
---|
509 | self.assertEqual(p.geturl(), uri)
|
---|
510 |
|
---|
511 | p = urlparse.urlparse(uri)
|
---|
512 | self.assertEqual(p.netloc, "")
|
---|
513 | self.assertEqual(p.username, None)
|
---|
514 | self.assertEqual(p.password, None)
|
---|
515 | self.assertEqual(p.hostname, None)
|
---|
516 | self.assertEqual(p.port, None)
|
---|
517 | self.assertEqual(p.geturl(), uri)
|
---|
518 |
|
---|
519 | def test_caching(self):
|
---|
520 | # Test case for bug #1313119
|
---|
521 | uri = "http://example.com/doc/"
|
---|
522 | unicode_uri = unicode(uri)
|
---|
523 |
|
---|
524 | urlparse.urlparse(unicode_uri)
|
---|
525 | p = urlparse.urlparse(uri)
|
---|
526 | self.assertEqual(type(p.scheme), type(uri))
|
---|
527 | self.assertEqual(type(p.hostname), type(uri))
|
---|
528 | self.assertEqual(type(p.path), type(uri))
|
---|
529 |
|
---|
530 | def test_noslash(self):
|
---|
531 | # Issue 1637: http://foo.com?query is legal
|
---|
532 | self.assertEqual(urlparse.urlparse("http://example.com?blahblah=/foo"),
|
---|
533 | ('http', 'example.com', '', '', 'blahblah=/foo', ''))
|
---|
534 |
|
---|
535 | def test_anyscheme(self):
|
---|
536 | # Issue 7904: s3://foo.com/stuff has netloc "foo.com".
|
---|
537 | self.assertEqual(urlparse.urlparse("s3://foo.com/stuff"),
|
---|
538 | ('s3','foo.com','/stuff','','',''))
|
---|
539 | self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff"),
|
---|
540 | ('x-newscheme','foo.com','/stuff','','',''))
|
---|
541 | self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff?query#fragment"),
|
---|
542 | ('x-newscheme','foo.com','/stuff','','query','fragment'))
|
---|
543 | self.assertEqual(urlparse.urlparse("x-newscheme://foo.com/stuff?query"),
|
---|
544 | ('x-newscheme','foo.com','/stuff','','query',''))
|
---|
545 |
|
---|
546 | def test_withoutscheme(self):
|
---|
547 | # Test urlparse without scheme
|
---|
548 | # Issue 754016: urlparse goes wrong with IP:port without scheme
|
---|
549 | # RFC 1808 specifies that netloc should start with //, urlparse expects
|
---|
550 | # the same, otherwise it classifies the portion of url as path.
|
---|
551 | self.assertEqual(urlparse.urlparse("path"),
|
---|
552 | ('','','path','','',''))
|
---|
553 | self.assertEqual(urlparse.urlparse("//www.python.org:80"),
|
---|
554 | ('','www.python.org:80','','','',''))
|
---|
555 | self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
|
---|
556 | ('http','www.python.org:80','','','',''))
|
---|
557 |
|
---|
558 | def test_portseparator(self):
|
---|
559 | # Issue 754016 makes changes for port separator ':' from scheme separator
|
---|
560 | self.assertEqual(urlparse.urlparse("path:80"),
|
---|
561 | ('','','path:80','','',''))
|
---|
562 | self.assertEqual(urlparse.urlparse("http:"),('http','','','','',''))
|
---|
563 | self.assertEqual(urlparse.urlparse("https:"),('https','','','','',''))
|
---|
564 | self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
|
---|
565 | ('http','www.python.org:80','','','',''))
|
---|
566 |
|
---|
567 | def test_main():
|
---|
568 | test_support.run_unittest(UrlParseTestCase)
|
---|
569 |
|
---|
570 | if __name__ == "__main__":
|
---|
571 | test_main()
|
---|