summaryrefslogtreecommitdiffstats
path: root/Lib/test/test_urllib.py
blob: 4579c479d1478bbf06425104ee2f74531499514b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
"""Regresssion tests for urllib"""

import urllib
import httplib
import unittest
from test import test_support
import os
import mimetools
import tempfile
import StringIO

def hexescape(char):
    """Escape char as RFC 2396 specifies"""
    hex_repr = hex(ord(char))[2:].upper()
    if len(hex_repr) == 1:
        hex_repr = "0%s" % hex_repr
    return "%" + hex_repr

class urlopen_FileTests(unittest.TestCase):
    """Test urlopen() opening a temporary file.

    Try to test as much functionality as possible so as to cut down on reliance
    on connecting to the Net for testing.

    """

    def setUp(self):
        """Setup of a temp file to use for testing"""
        self.text = "test_urllib: %s\n" % self.__class__.__name__
        FILE = file(test_support.TESTFN, 'wb')
        try:
            FILE.write(self.text)
        finally:
            FILE.close()
        self.pathname = test_support.TESTFN
        self.returned_obj = urllib.urlopen("file:%s" % self.pathname)

    def tearDown(self):
        """Shut down the open object"""
        self.returned_obj.close()
        os.remove(test_support.TESTFN)

    def test_interface(self):
        # Make sure object returned by urlopen() has the specified methods
        for attr in ("read", "readline", "readlines", "fileno",
                     "close", "info", "geturl", "__iter__"):
            self.assert_(hasattr(self.returned_obj, attr),
                         "object returned by urlopen() lacks %s attribute" %
                         attr)

    def test_read(self):
        self.assertEqual(self.text, self.returned_obj.read())

    def test_readline(self):
        self.assertEqual(self.text, self.returned_obj.readline())
        self.assertEqual('', self.returned_obj.readline(),
                         "calling readline() after exhausting the file did not"
                         " return an empty string")

    def test_readlines(self):
        lines_list = self.returned_obj.readlines()
        self.assertEqual(len(lines_list), 1,
                         "readlines() returned the wrong number of lines")
        self.assertEqual(lines_list[0], self.text,
                         "readlines() returned improper text")

    def test_fileno(self):
        file_num = self.returned_obj.fileno()
        self.assert_(isinstance(file_num, int),
                     "fileno() did not return an int")
        self.assertEqual(os.read(file_num, len(self.text)), self.text,
                         "Reading on the file descriptor returned by fileno() "
                         "did not return the expected text")

    def test_close(self):
        # Test close() by calling it hear and then having it be called again
        # by the tearDown() method for the test
        self.returned_obj.close()

    def test_info(self):
        self.assert_(isinstance(self.returned_obj.info(), mimetools.Message))

    def test_geturl(self):
        self.assertEqual(self.returned_obj.geturl(), self.pathname)

    def test_iter(self):
        # Test iterator
        # Don't need to count number of iterations since test would fail the
        # instant it returned anything beyond the first line from the
        # comparison
        for line in self.returned_obj.__iter__():
            self.assertEqual(line, self.text)

class urlopen_HttpTests(unittest.TestCase):
    """Test urlopen() opening a fake http connection."""

    def fakehttp(self, fakedata):
        class FakeSocket(StringIO.StringIO):
            def sendall(self, str): pass
            def makefile(self, mode, name): return self
            def read(self, amt=None):
                if self.closed: return ''
                return StringIO.StringIO.read(self, amt)
            def readline(self, length=None):
                if self.closed: return ''
                return StringIO.StringIO.readline(self, length)
        class FakeHTTPConnection(httplib.HTTPConnection):
            def connect(self):
                self.sock = FakeSocket(fakedata)
        assert httplib.HTTP._connection_class == httplib.HTTPConnection
        httplib.HTTP._connection_class = FakeHTTPConnection

    def unfakehttp(self):
        httplib.HTTP._connection_class = httplib.HTTPConnection

    def test_read(self):
        self.fakehttp('Hello!')
        try:
            fp = urllib.urlopen("http://python.org/")
            self.assertEqual(fp.readline(), 'Hello!')
            self.assertEqual(fp.readline(), '')
        finally:
            self.unfakehttp()

class urlretrieve_FileTests(unittest.TestCase):
    """Test urllib.urlretrieve() on local files"""

    def setUp(self):
        # Create a list of temporary files. Each item in the list is a file
        # name (absolute path or relative to the current working directory).
        # All files in this list will be deleted in the tearDown method. Note,
        # this only helps to makes sure temporary files get deleted, but it
        # does nothing about trying to close files that may still be open. It
        # is the responsibility of the developer to properly close files even
        # when exceptional conditions occur.
        self.tempFiles = []

        # Create a temporary file.
        self.registerFileForCleanUp(test_support.TESTFN)
        self.text = 'testing urllib.urlretrieve'
        try:
            FILE = file(test_support.TESTFN, 'wb')
            FILE.write(self.text)
            FILE.close()
        finally:
            try: FILE.close()
            except: pass

    def tearDown(self):
        # Delete the temporary files.
        for each in self.tempFiles:
            try: os.remove(each)
            except: pass

    def constructLocalFileUrl(self, filePath):
        return "file://%s" % urllib.pathname2url(os.path.abspath(filePath))

    def createNewTempFile(self, data=""):
        """Creates a new temporary file containing the specified data,
        registers the file for deletion during the test fixture tear down, and
        returns the absolute path of the file."""

        newFd, newFilePath = tempfile.mkstemp()
        try:
            self.registerFileForCleanUp(newFilePath)
            newFile = os.fdopen(newFd, "wb")
            newFile.write(data)
            newFile.close()
        finally:
            try: newFile.close()
            except: pass
        return newFilePath

    def registerFileForCleanUp(self, fileName):
        self.tempFiles.append(fileName)

    def test_basic(self):
        # Make sure that a local file just gets its own location returned and
        # a headers value is returned.
        result = urllib.urlretrieve("file:%s" % test_support.TESTFN)
        self.assertEqual(result[0], test_support.TESTFN)
        self.assert_(isinstance(result[1], mimetools.Message),
                     "did not get a mimetools.Message instance as second "
                     "returned value")

    def test_copy(self):
        # Test that setting the filename argument works.
        second_temp = "%s.2" % test_support.TESTFN
        self.registerFileForCleanUp(second_temp)
        result = urllib.urlretrieve(self.constructLocalFileUrl(
            test_support.TESTFN), second_temp)
        self.assertEqual(second_temp, result[0])
        self.assert_(os.path.exists(second_temp), "copy of the file was not "
                                                  "made")
        FILE = file(second_temp, 'rb')
        try:
            text = FILE.read()
            FILE.close()
        finally:
            try: FILE.close()
            except: pass
        self.assertEqual(self.text, text)

    def test_reporthook(self):
        # Make sure that the reporthook works.
        def hooktester(count, block_size, total_size, count_holder=[0]):
            self.assert_(isinstance(count, int))
            self.assert_(isinstance(block_size, int))
            self.assert_(isinstance(total_size, int))
            self.assertEqual(count, count_holder[0])
            count_holder[0] = count_holder[0] + 1
        second_temp = "%s.2" % test_support.TESTFN
        self.registerFileForCleanUp(second_temp)
        urllib.urlretrieve(self.constructLocalFileUrl(test_support.TESTFN),
            second_temp, hooktester)

    def test_reporthook_0_bytes(self):
        # Test on zero length file. Should call reporthook only 1 time.
        report = []
        def hooktester(count, block_size, total_size, _report=report):
            _report.append((count, block_size, total_size))
        srcFileName = self.createNewTempFile()
        urllib.urlretrieve(self.constructLocalFileUrl(srcFileName),
            test_support.TESTFN, hooktester)
        self.assertEqual(len(report), 1)
        self.assertEqual(report[0][2], 0)

    def test_reporthook_5_bytes(self):
        # Test on 5 byte file. Should call reporthook only 2 times (once when
        # the "network connection" is established and once when the block is
        # read). Since the block size is 8192 bytes, only one block read is
        # required to read the entire file.
        report = []
        def hooktester(count, block_size, total_size, _report=report):
            _report.append((count, block_size, total_size))
        srcFileName = self.createNewTempFile("x" * 5)
        urllib.urlretrieve(self.constructLocalFileUrl(srcFileName),
            test_support.TESTFN, hooktester)
        self.assertEqual(len(report), 2)
        self.assertEqual(report[0][1], 8192)
        self.assertEqual(report[0][2], 5)

    def test_reporthook_8193_bytes(self):
        # Test on 8193 byte file. Should call reporthook only 3 times (once
        # when the "network connection" is established, once for the next 8192
        # bytes, and once for the last byte).
        report = []
        def hooktester(count, block_size, total_size, _report=report):
            _report.append((count, block_size, total_size))
        srcFileName = self.createNewTempFile("x" * 8193)
        urllib.urlretrieve(self.constructLocalFileUrl(srcFileName),
            test_support.TESTFN, hooktester)
        self.assertEqual(len(report), 3)
        self.assertEqual(report[0][1], 8192)
        self.assertEqual(report[0][2], 8193)

class QuotingTests(unittest.TestCase):
    """Tests for urllib.quote() and urllib.quote_plus()

    According to RFC 2396 ("Uniform Resource Identifiers), to escape a
    character you write it as '%' + <2 character US-ASCII hex value>.  The Python
    code of ``'%' + hex(ord(<character>))[2:]`` escapes a character properly.
    Case does not matter on the hex letters.

    The various character sets specified are:

    Reserved characters : ";/?:@&=+$,"
        Have special meaning in URIs and must be escaped if not being used for
        their special meaning
    Data characters : letters, digits, and "-_.!~*'()"
        Unreserved and do not need to be escaped; can be, though, if desired
    Control characters : 0x00 - 0x1F, 0x7F
        Have no use in URIs so must be escaped
    space : 0x20
        Must be escaped
    Delimiters : '<>#%"'
        Must be escaped
    Unwise : "{}|\^[]`"
        Must be escaped

    """

    def test_never_quote(self):
        # Make sure quote() does not quote letters, digits, and "_,.-"
        do_not_quote = '' .join(["ABCDEFGHIJKLMNOPQRSTUVWXYZ",
                                 "abcdefghijklmnopqrstuvwxyz",
                                 "0123456789",
                                 "_.-"])
        result = urllib.quote(do_not_quote)
        self.assertEqual(do_not_quote, result,
                         "using quote(): %s != %s" % (do_not_quote, result))
        result = urllib.quote_plus(do_not_quote)
        self.assertEqual(do_not_quote, result,
                        "using quote_plus(): %s != %s" % (do_not_quote, result))

    def test_default_safe(self):
        # Test '/' is default value for 'safe' parameter
        self.assertEqual(urllib.quote.func_defaults[0], '/')

    def test_safe(self):
        # Test setting 'safe' parameter does what it should do
        quote_by_default = "<>"
        result = urllib.quote(quote_by_default, safe=quote_by_default)
        self.assertEqual(quote_by_default, result,
                         "using quote(): %s != %s" % (quote_by_default, result))
        result = urllib.quote_plus(quote_by_default, safe=quote_by_default)
        self.assertEqual(quote_by_default, result,
                         "using quote_plus(): %s != %s" %
                         (quote_by_default, result))

    def test_default_quoting(self):
        # Make sure all characters that should be quoted are by default sans
        # space (separate test for that).
        should_quote = [chr(num) for num in range(32)] # For 0x00 - 0x1F
        should_quote.append('<>#%"{}|\^[]`')
        should_quote.append(chr(127)) # For 0x7F
        should_quote = ''.join(should_quote)
        for char in should_quote:
            result = urllib.quote(char)
            self.assertEqual(hexescape(char), result,
                             "using quote(): %s should be escaped to %s, not %s" %
                             (char, hexescape(char), result))
            result = urllib.quote_plus(char)
            self.assertEqual(hexescape(char), result,
                             "using quote_plus(): "
                             "%s should be escapes to %s, not %s" %
                             (char, hexescape(char), result))
        del should_quote
        partial_quote = "ab[]cd"
        expected = "ab%5B%5Dcd"
        result = urllib.quote(partial_quote)
        self.assertEqual(expected, result,
                         "using quote(): %s != %s" % (expected, result))
        self.assertEqual(expected, result,
                         "using quote_plus(): %s != %s" % (expected, result))

    def test_quoting_space(self):
        # Make sure quote() and quote_plus() handle spaces as specified in
        # their unique way
        result = urllib.quote(' ')
        self.assertEqual(result, hexescape(' '),
                         "using quote(): %s != %s" % (result, hexescape(' ')))
        result = urllib.quote_plus(' ')
        self.assertEqual(result, '+',
                         "using quote_plus(): %s != +" % result)
        given = "a b cd e f"
        expect = given.replace(' ', hexescape(' '))
        result = urllib.quote(given)
        self.assertEqual(expect, result,
                         "using quote(): %s != %s" % (expect, result))
        expect = given.replace(' ', '+')
        result = urllib.quote_plus(given)
        self.assertEqual(expect, result,
                         "using quote_plus(): %s != %s" % (expect, result))

    def test_quoting_plus(self):
        self.assertEqual(urllib.quote_plus('alpha+beta gamma'),
                         'alpha%2Bbeta+gamma')
        self.assertEqual(urllib.quote_plus('alpha+beta gamma', '+'),
                         'alpha+beta+gamma')

class UnquotingTests(unittest.TestCase):
    """Tests for unquote() and unquote_plus()

    See the doc string for quoting_Tests for details on quoting and such.

    """

    def test_unquoting(self):
        # Make sure unquoting of all ASCII values works
        escape_list = []
        for num in range(128):
            given = hexescape(chr(num))
            expect = chr(num)
            result = urllib.unquote(given)
            self.assertEqual(expect, result,
                             "using unquote(): %s != %s" % (expect, result))
            result = urllib.unquote_plus(given)
            self.assertEqual(expect, result,
                             "using unquote_plus(): %s != %s" %
                             (expect, result))
            escape_list.append(given)
        escape_string = ''.join(escape_list)
        del escape_list
        result = urllib.unquote(escape_string)
        self.assertEqual(result.count('%'), 1,
                         "using quote(): not all characters escaped; %s" %
                         result)
        result = urllib.unquote(escape_string)
        self.assertEqual(result.count('%'), 1,
                         "using unquote(): not all characters escaped: "
                         "%s" % result)

    def test_unquoting_parts(self):
        # Make sure unquoting works when have non-quoted characters
        # interspersed
        given = 'ab%sd' % hexescape('c')
        expect = "abcd"
        result = urllib.unquote(given)
        self.assertEqual(expect, result,
                         "using quote(): %s != %s" % (expect, result))
        result = urllib.unquote_plus(given)
        self.assertEqual(expect, result,
                         "using unquote_plus(): %s != %s" % (expect, result))

    def test_unquoting_plus(self):
        # Test difference between unquote() and unquote_plus()
        given = "are+there+spaces..."
        expect = given
        result = urllib.unquote(given)
        self.assertEqual(expect, result,
                         "using unquote(): %s != %s" % (expect, result))
        expect = given.replace('+', ' ')
        result = urllib.unquote_plus(given)
        self.assertEqual(expect, result,
                         "using unquote_plus(): %s != %s" % (expect, result))

    def test_unquote_with_unicode(self):
        r = urllib.unquote(u'br%C3%BCckner_sapporo_20050930.doc')
        self.assertEqual(r, u'br\xc3\xbcckner_sapporo_20050930.doc')

class urlencode_Tests(unittest.TestCase):
    """Tests for urlencode()"""

    def help_inputtype(self, given, test_type):
        """Helper method for testing different input types.

        'given' must lead to only the pairs:
            * 1st, 1
            * 2nd, 2
            * 3rd, 3

        Test cannot assume anything about order.  Docs make no guarantee and
        have possible dictionary input.

        """
        expect_somewhere = ["1st=1", "2nd=2", "3rd=3"]
        result = urllib.urlencode(given)
        for expected in expect_somewhere:
            self.assert_(expected in result,
                         "testing %s: %s not found in %s" %
                         (test_type, expected, result))
        self.assertEqual(result.count('&'), 2,
                         "testing %s: expected 2 '&'s; got %s" %
                         (test_type, result.count('&')))
        amp_location = result.index('&')
        on_amp_left = result[amp_location - 1]
        on_amp_right = result[amp_location + 1]
        self.assert_(on_amp_left.isdigit() and on_amp_right.isdigit(),
                     "testing %s: '&' not located in proper place in %s" %
                     (test_type, result))
        self.assertEqual(len(result), (5 * 3) + 2, #5 chars per thing and amps
                         "testing %s: "
                         "unexpected number of characters: %s != %s" %
                         (test_type, len(result), (5 * 3) + 2))

    def test_using_mapping(self):
        # Test passing in a mapping object as an argument.
        self.help_inputtype({"1st":'1', "2nd":'2', "3rd":'3'},
                            "using dict as input type")

    def test_using_sequence(self):
        # Test passing in a sequence of two-item sequences as an argument.
        self.help_inputtype([('1st', '1'), ('2nd', '2'), ('3rd', '3')],
                            "using sequence of two-item tuples as input")

    def test_quoting(self):
        # Make sure keys and values are quoted using quote_plus()
        given = {"&":"="}
        expect = "%s=%s" % (hexescape('&'), hexescape('='))
        result = urllib.urlencode(given)
        self.assertEqual(expect, result)
        given = {"key name":"A bunch of pluses"}
        expect = "key+name=A+bunch+of+pluses"
        result = urllib.urlencode(given)
        self.assertEqual(expect, result)

    def test_doseq(self):
        # Test that passing True for 'doseq' parameter works correctly
        given = {'sequence':['1', '2', '3']}
        expect = "sequence=%s" % urllib.quote_plus(str(['1', '2', '3']))
        result = urllib.urlencode(given)
        self.assertEqual(expect, result)
        result = urllib.urlencode(given, True)
        for value in given["sequence"]:
            expect = "sequence=%s" % value
            self.assert_(expect in result,
                         "%s not found in %s" % (expect, result))
        self.assertEqual(result.count('&'), 2,
                         "Expected 2 '&'s, got %s" % result.count('&'))

class Pathname_Tests(unittest.TestCase):
    """Test pathname2url() and url2pathname()"""

    def test_basic(self):
        # Make sure simple tests pass
        expected_path = os.path.join("parts", "of", "a", "path")
        expected_url = "parts/of/a/path"
        result = urllib.pathname2url(expected_path)
        self.assertEqual(expected_url, result,
                         "pathname2url() failed; %s != %s" %
                         (result, expected_url))
        result = urllib.url2pathname(expected_url)
        self.assertEqual(expected_path, result,
                         "url2pathame() failed; %s != %s" %
                         (result, expected_path))

    def test_quoting(self):
        # Test automatic quoting and unquoting works for pathnam2url() and
        # url2pathname() respectively
        given = os.path.join("needs", "quot=ing", "here")
        expect = "needs/%s/here" % urllib.quote("quot=ing")
        result = urllib.pathname2url(given)
        self.assertEqual(expect, result,
                         "pathname2url() failed; %s != %s" %
                         (expect, result))
        expect = given
        result = urllib.url2pathname(result)
        self.assertEqual(expect, result,
                         "url2pathname() failed; %s != %s" %
                         (expect, result))
        given = os.path.join("make sure", "using_quote")
        expect = "%s/using_quote" % urllib.quote("make sure")
        result = urllib.pathname2url(given)
        self.assertEqual(expect, result,
                         "pathname2url() failed; %s != %s" %
                         (expect, result))
        given = "make+sure/using_unquote"
        expect = os.path.join("make+sure", "using_unquote")
        result = urllib.url2pathname(given)
        self.assertEqual(expect, result,
                         "url2pathname() failed; %s != %s" %
                         (expect, result))



def test_main():
    test_support.run_unittest(
        urlopen_FileTests,
        urlopen_HttpTests,
        urlretrieve_FileTests,
        QuotingTests,
        UnquotingTests,
        urlencode_Tests,
        Pathname_Tests
    )



if __name__ == '__main__':
    test_main()