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
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
|
"""Regresssion tests for urllib"""
import urllib.parse
import urllib.request
import urllib.error
import http.client
import email.message
import io
import unittest
from unittest.mock import patch
from test import support
import os
import ssl
import sys
import tempfile
from nturl2path import url2pathname, pathname2url
from base64 import b64encode
import collections
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
# Shortcut for testing FancyURLopener
_urlopener = None
def urlopen(url, data=None, proxies=None):
"""urlopen(url [, data]) -> open file-like object"""
global _urlopener
if proxies is not None:
opener = urllib.request.FancyURLopener(proxies=proxies)
elif not _urlopener:
with support.check_warnings(
('FancyURLopener style of invoking requests is deprecated.',
DeprecationWarning)):
opener = urllib.request.FancyURLopener()
_urlopener = opener
else:
opener = _urlopener
if data is None:
return opener.open(url)
else:
return opener.open(url, data)
def fakehttp(fakedata):
class FakeSocket(io.BytesIO):
io_refs = 1
def sendall(self, data):
FakeHTTPConnection.buf = data
def makefile(self, *args, **kwds):
self.io_refs += 1
return self
def read(self, amt=None):
if self.closed:
return b""
return io.BytesIO.read(self, amt)
def readline(self, length=None):
if self.closed:
return b""
return io.BytesIO.readline(self, length)
def close(self):
self.io_refs -= 1
if self.io_refs == 0:
io.BytesIO.close(self)
class FakeHTTPConnection(http.client.HTTPConnection):
# buffer to store data for verification in urlopen tests.
buf = None
fakesock = FakeSocket(fakedata)
def connect(self):
self.sock = self.fakesock
return FakeHTTPConnection
class FakeHTTPMixin(object):
def fakehttp(self, fakedata):
self._connection_class = http.client.HTTPConnection
http.client.HTTPConnection = fakehttp(fakedata)
def unfakehttp(self):
http.client.HTTPConnection = self._connection_class
class FakeFTPMixin(object):
def fakeftp(self):
class FakeFtpWrapper(object):
def __init__(self, user, passwd, host, port, dirs, timeout=None,
persistent=True):
pass
def retrfile(self, file, type):
return io.BytesIO(), 0
def close(self):
pass
self._ftpwrapper_class = urllib.request.ftpwrapper
urllib.request.ftpwrapper = FakeFtpWrapper
def unfakeftp(self):
urllib.request.ftpwrapper = self._ftpwrapper_class
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):
# Create a temp file to use for testing
self.text = bytes("test_urllib: %s\n" % self.__class__.__name__,
"ascii")
f = open(support.TESTFN, 'wb')
try:
f.write(self.text)
finally:
f.close()
self.pathname = support.TESTFN
self.returned_obj = urlopen("file:%s" % self.pathname)
def tearDown(self):
"""Shut down the open object"""
self.returned_obj.close()
os.remove(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", "getcode", "__iter__"):
self.assertTrue(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(b'', 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.assertIsInstance(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 here and then having it be called again
# by the tearDown() method for the test
self.returned_obj.close()
def test_info(self):
self.assertIsInstance(self.returned_obj.info(), email.message.Message)
def test_geturl(self):
self.assertEqual(self.returned_obj.geturl(), self.pathname)
def test_getcode(self):
self.assertIsNone(self.returned_obj.getcode())
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.
# Use the iterator in the usual implicit way to test for ticket #4608.
for line in self.returned_obj:
self.assertEqual(line, self.text)
def test_relativelocalfile(self):
self.assertRaises(ValueError,urllib.request.urlopen,'./' + self.pathname)
class ProxyTests(unittest.TestCase):
def setUp(self):
# Records changes to env vars
self.env = support.EnvironmentVarGuard()
# Delete all proxy related env vars
for k in list(os.environ):
if 'proxy' in k.lower():
self.env.unset(k)
def tearDown(self):
# Restore all proxy related env vars
self.env.__exit__()
del self.env
def test_getproxies_environment_keep_no_proxies(self):
self.env.set('NO_PROXY', 'localhost')
proxies = urllib.request.getproxies_environment()
# getproxies_environment use lowered case truncated (no '_proxy') keys
self.assertEqual('localhost', proxies['no'])
# List of no_proxies with space.
self.env.set('NO_PROXY', 'localhost, anotherdomain.com, newdomain.com')
self.assertTrue(urllib.request.proxy_bypass_environment('anotherdomain.com'))
class urlopen_HttpTests(unittest.TestCase, FakeHTTPMixin, FakeFTPMixin):
"""Test urlopen() opening a fake http connection."""
def check_read(self, ver):
self.fakehttp(b"HTTP/" + ver + b" 200 OK\r\n\r\nHello!")
try:
fp = urlopen("http://python.org/")
self.assertEqual(fp.readline(), b"Hello!")
self.assertEqual(fp.readline(), b"")
self.assertEqual(fp.geturl(), 'http://python.org/')
self.assertEqual(fp.getcode(), 200)
finally:
self.unfakehttp()
def test_url_fragment(self):
# Issue #11703: geturl() omits fragments in the original URL.
url = 'http://docs.python.org/library/urllib.html#OK'
self.fakehttp(b"HTTP/1.1 200 OK\r\n\r\nHello!")
try:
fp = urllib.request.urlopen(url)
self.assertEqual(fp.geturl(), url)
finally:
self.unfakehttp()
def test_willclose(self):
self.fakehttp(b"HTTP/1.1 200 OK\r\n\r\nHello!")
try:
resp = urlopen("http://www.python.org")
self.assertTrue(resp.fp.will_close)
finally:
self.unfakehttp()
def test_read_0_9(self):
# "0.9" response accepted (but not "simple responses" without
# a status line)
self.check_read(b"0.9")
def test_read_1_0(self):
self.check_read(b"1.0")
def test_read_1_1(self):
self.check_read(b"1.1")
def test_read_bogus(self):
# urlopen() should raise OSError for many error codes.
self.fakehttp(b'''HTTP/1.1 401 Authentication Required
Date: Wed, 02 Jan 2008 03:03:54 GMT
Server: Apache/1.3.33 (Debian GNU/Linux) mod_ssl/2.8.22 OpenSSL/0.9.7e
Connection: close
Content-Type: text/html; charset=iso-8859-1
''')
try:
self.assertRaises(OSError, urlopen, "http://python.org/")
finally:
self.unfakehttp()
def test_invalid_redirect(self):
# urlopen() should raise OSError for many error codes.
self.fakehttp(b'''HTTP/1.1 302 Found
Date: Wed, 02 Jan 2008 03:03:54 GMT
Server: Apache/1.3.33 (Debian GNU/Linux) mod_ssl/2.8.22 OpenSSL/0.9.7e
Location: file://guidocomputer.athome.com:/python/license
Connection: close
Content-Type: text/html; charset=iso-8859-1
''')
try:
self.assertRaises(urllib.error.HTTPError, urlopen,
"http://python.org/")
finally:
self.unfakehttp()
def test_empty_socket(self):
# urlopen() raises OSError if the underlying socket does not send any
# data. (#1680230)
self.fakehttp(b'')
try:
self.assertRaises(OSError, urlopen, "http://something")
finally:
self.unfakehttp()
def test_missing_localfile(self):
# Test for #10836
with self.assertRaises(urllib.error.URLError) as e:
urlopen('file://localhost/a/file/which/doesnot/exists.py')
self.assertTrue(e.exception.filename)
self.assertTrue(e.exception.reason)
def test_file_notexists(self):
fd, tmp_file = tempfile.mkstemp()
tmp_fileurl = 'file://localhost/' + tmp_file.replace(os.path.sep, '/')
try:
self.assertTrue(os.path.exists(tmp_file))
with urlopen(tmp_fileurl) as fobj:
self.assertTrue(fobj)
finally:
os.close(fd)
os.unlink(tmp_file)
self.assertFalse(os.path.exists(tmp_file))
with self.assertRaises(urllib.error.URLError):
urlopen(tmp_fileurl)
def test_ftp_nohost(self):
test_ftp_url = 'ftp:///path'
with self.assertRaises(urllib.error.URLError) as e:
urlopen(test_ftp_url)
self.assertFalse(e.exception.filename)
self.assertTrue(e.exception.reason)
def test_ftp_nonexisting(self):
with self.assertRaises(urllib.error.URLError) as e:
urlopen('ftp://localhost/a/file/which/doesnot/exists.py')
self.assertFalse(e.exception.filename)
self.assertTrue(e.exception.reason)
@patch.object(urllib.request, 'MAXFTPCACHE', 0)
def test_ftp_cache_pruning(self):
self.fakeftp()
try:
urllib.request.ftpcache['test'] = urllib.request.ftpwrapper('user', 'pass', 'localhost', 21, [])
urlopen('ftp://localhost')
finally:
self.unfakeftp()
def test_userpass_inurl(self):
self.fakehttp(b"HTTP/1.0 200 OK\r\n\r\nHello!")
try:
fp = urlopen("http://user:pass@python.org/")
self.assertEqual(fp.readline(), b"Hello!")
self.assertEqual(fp.readline(), b"")
self.assertEqual(fp.geturl(), 'http://user:pass@python.org/')
self.assertEqual(fp.getcode(), 200)
finally:
self.unfakehttp()
def test_userpass_inurl_w_spaces(self):
self.fakehttp(b"HTTP/1.0 200 OK\r\n\r\nHello!")
try:
userpass = "a b:c d"
url = "http://{}@python.org/".format(userpass)
fakehttp_wrapper = http.client.HTTPConnection
authorization = ("Authorization: Basic %s\r\n" %
b64encode(userpass.encode("ASCII")).decode("ASCII"))
fp = urlopen(url)
# The authorization header must be in place
self.assertIn(authorization, fakehttp_wrapper.buf.decode("UTF-8"))
self.assertEqual(fp.readline(), b"Hello!")
self.assertEqual(fp.readline(), b"")
# the spaces are quoted in URL so no match
self.assertNotEqual(fp.geturl(), url)
self.assertEqual(fp.getcode(), 200)
finally:
self.unfakehttp()
def test_URLopener_deprecation(self):
with support.check_warnings(('',DeprecationWarning)):
urllib.request.URLopener()
def test_cafile_and_context(self):
context = ssl.create_default_context()
with self.assertRaises(ValueError):
urllib.request.urlopen(
"https://localhost", cafile="/nonexistent/path", context=context
)
class urlopen_DataTests(unittest.TestCase):
"""Test urlopen() opening a data URL."""
def setUp(self):
# text containing URL special- and unicode-characters
self.text = "test data URLs :;,%=& \u00f6 \u00c4 "
# 2x1 pixel RGB PNG image with one black and one white pixel
self.image = (
b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x02\x00\x00\x00'
b'\x01\x08\x02\x00\x00\x00{@\xe8\xdd\x00\x00\x00\x01sRGB\x00\xae'
b'\xce\x1c\xe9\x00\x00\x00\x0fIDAT\x08\xd7c```\xf8\xff\xff?\x00'
b'\x06\x01\x02\xfe\no/\x1e\x00\x00\x00\x00IEND\xaeB`\x82')
self.text_url = (
"data:text/plain;charset=UTF-8,test%20data%20URLs%20%3A%3B%2C%25%3"
"D%26%20%C3%B6%20%C3%84%20")
self.text_url_base64 = (
"data:text/plain;charset=ISO-8859-1;base64,dGVzdCBkYXRhIFVSTHMgOjs"
"sJT0mIPYgxCA%3D")
# base64 encoded data URL that contains ignorable spaces,
# such as "\n", " ", "%0A", and "%20".
self.image_url = (
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAIAAAABCAIAAAB7\n"
"QOjdAAAAAXNSR0IArs4c6QAAAA9JREFUCNdj%0AYGBg%2BP//PwAGAQL%2BCm8 "
"vHgAAAABJRU5ErkJggg%3D%3D%0A%20")
self.text_url_resp = urllib.request.urlopen(self.text_url)
self.text_url_base64_resp = urllib.request.urlopen(
self.text_url_base64)
self.image_url_resp = urllib.request.urlopen(self.image_url)
def test_interface(self):
# Make sure object returned by urlopen() has the specified methods
for attr in ("read", "readline", "readlines",
"close", "info", "geturl", "getcode", "__iter__"):
self.assertTrue(hasattr(self.text_url_resp, attr),
"object returned by urlopen() lacks %s attribute" %
attr)
def test_info(self):
self.assertIsInstance(self.text_url_resp.info(), email.message.Message)
self.assertEqual(self.text_url_base64_resp.info().get_params(),
[('text/plain', ''), ('charset', 'ISO-8859-1')])
self.assertEqual(self.image_url_resp.info()['content-length'],
str(len(self.image)))
self.assertEqual(urllib.request.urlopen("data:,").info().get_params(),
[('text/plain', ''), ('charset', 'US-ASCII')])
def test_geturl(self):
self.assertEqual(self.text_url_resp.geturl(), self.text_url)
self.assertEqual(self.text_url_base64_resp.geturl(),
self.text_url_base64)
self.assertEqual(self.image_url_resp.geturl(), self.image_url)
def test_read_text(self):
self.assertEqual(self.text_url_resp.read().decode(
dict(self.text_url_resp.info().get_params())['charset']), self.text)
def test_read_text_base64(self):
self.assertEqual(self.text_url_base64_resp.read().decode(
dict(self.text_url_base64_resp.info().get_params())['charset']),
self.text)
def test_read_image(self):
self.assertEqual(self.image_url_resp.read(), self.image)
def test_missing_comma(self):
self.assertRaises(ValueError,urllib.request.urlopen,'data:text/plain')
def test_invalid_base64_data(self):
# missing padding character
self.assertRaises(ValueError,urllib.request.urlopen,'data:;base64,Cg=')
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(support.TESTFN)
self.text = b'testing urllib.urlretrieve'
try:
FILE = open(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):
filePath = os.path.abspath(filePath)
try:
filePath.encode("utf-8")
except UnicodeEncodeError:
raise unittest.SkipTest("filePath is not encodable to utf8")
return "file://%s" % urllib.request.pathname2url(filePath)
def createNewTempFile(self, data=b""):
"""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.request.urlretrieve("file:%s" % support.TESTFN)
self.assertEqual(result[0], support.TESTFN)
self.assertIsInstance(result[1], email.message.Message,
"did not get a email.message.Message instance "
"as second returned value")
def test_copy(self):
# Test that setting the filename argument works.
second_temp = "%s.2" % support.TESTFN
self.registerFileForCleanUp(second_temp)
result = urllib.request.urlretrieve(self.constructLocalFileUrl(
support.TESTFN), second_temp)
self.assertEqual(second_temp, result[0])
self.assertTrue(os.path.exists(second_temp), "copy of the file was not "
"made")
FILE = open(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(block_count, block_read_size, file_size, count_holder=[0]):
self.assertIsInstance(block_count, int)
self.assertIsInstance(block_read_size, int)
self.assertIsInstance(file_size, int)
self.assertEqual(block_count, count_holder[0])
count_holder[0] = count_holder[0] + 1
second_temp = "%s.2" % support.TESTFN
self.registerFileForCleanUp(second_temp)
urllib.request.urlretrieve(
self.constructLocalFileUrl(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(block_count, block_read_size, file_size, _report=report):
_report.append((block_count, block_read_size, file_size))
srcFileName = self.createNewTempFile()
urllib.request.urlretrieve(self.constructLocalFileUrl(srcFileName),
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).
report = []
def hooktester(block_count, block_read_size, file_size, _report=report):
_report.append((block_count, block_read_size, file_size))
srcFileName = self.createNewTempFile(b"x" * 5)
urllib.request.urlretrieve(self.constructLocalFileUrl(srcFileName),
support.TESTFN, hooktester)
self.assertEqual(len(report), 2)
self.assertEqual(report[0][2], 5)
self.assertEqual(report[1][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(block_count, block_read_size, file_size, _report=report):
_report.append((block_count, block_read_size, file_size))
srcFileName = self.createNewTempFile(b"x" * 8193)
urllib.request.urlretrieve(self.constructLocalFileUrl(srcFileName),
support.TESTFN, hooktester)
self.assertEqual(len(report), 3)
self.assertEqual(report[0][2], 8193)
self.assertEqual(report[0][1], 8192)
self.assertEqual(report[1][1], 8192)
self.assertEqual(report[2][1], 8192)
class urlretrieve_HttpTests(unittest.TestCase, FakeHTTPMixin):
"""Test urllib.urlretrieve() using fake http connections"""
def test_short_content_raises_ContentTooShortError(self):
self.fakehttp(b'''HTTP/1.1 200 OK
Date: Wed, 02 Jan 2008 03:03:54 GMT
Server: Apache/1.3.33 (Debian GNU/Linux) mod_ssl/2.8.22 OpenSSL/0.9.7e
Connection: close
Content-Length: 100
Content-Type: text/html; charset=iso-8859-1
FF
''')
def _reporthook(par1, par2, par3):
pass
with self.assertRaises(urllib.error.ContentTooShortError):
try:
urllib.request.urlretrieve('http://example.com/',
reporthook=_reporthook)
finally:
self.unfakehttp()
def test_short_content_raises_ContentTooShortError_without_reporthook(self):
self.fakehttp(b'''HTTP/1.1 200 OK
Date: Wed, 02 Jan 2008 03:03:54 GMT
Server: Apache/1.3.33 (Debian GNU/Linux) mod_ssl/2.8.22 OpenSSL/0.9.7e
Connection: close
Content-Length: 100
Content-Type: text/html; charset=iso-8859-1
FF
''')
with self.assertRaises(urllib.error.ContentTooShortError):
try:
urllib.request.urlretrieve('http://example.com/')
finally:
self.unfakehttp()
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.parse.quote(do_not_quote)
self.assertEqual(do_not_quote, result,
"using quote(): %r != %r" % (do_not_quote, result))
result = urllib.parse.quote_plus(do_not_quote)
self.assertEqual(do_not_quote, result,
"using quote_plus(): %r != %r" % (do_not_quote, result))
def test_default_safe(self):
# Test '/' is default value for 'safe' parameter
self.assertEqual(urllib.parse.quote.__defaults__[0], '/')
def test_safe(self):
# Test setting 'safe' parameter does what it should do
quote_by_default = "<>"
result = urllib.parse.quote(quote_by_default, safe=quote_by_default)
self.assertEqual(quote_by_default, result,
"using quote(): %r != %r" % (quote_by_default, result))
result = urllib.parse.quote_plus(quote_by_default,
safe=quote_by_default)
self.assertEqual(quote_by_default, result,
"using quote_plus(): %r != %r" %
(quote_by_default, result))
# Safe expressed as bytes rather than str
result = urllib.parse.quote(quote_by_default, safe=b"<>")
self.assertEqual(quote_by_default, result,
"using quote(): %r != %r" % (quote_by_default, result))
# "Safe" non-ASCII characters should have no effect
# (Since URIs are not allowed to have non-ASCII characters)
result = urllib.parse.quote("a\xfcb", encoding="latin-1", safe="\xfc")
expect = urllib.parse.quote("a\xfcb", encoding="latin-1", safe="")
self.assertEqual(expect, result,
"using quote(): %r != %r" %
(expect, result))
# Same as above, but using a bytes rather than str
result = urllib.parse.quote("a\xfcb", encoding="latin-1", safe=b"\xfc")
expect = urllib.parse.quote("a\xfcb", encoding="latin-1", safe="")
self.assertEqual(expect, result,
"using quote(): %r != %r" %
(expect, 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.parse.quote(char)
self.assertEqual(hexescape(char), result,
"using quote(): "
"%s should be escaped to %s, not %s" %
(char, hexescape(char), result))
result = urllib.parse.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.parse.quote(partial_quote)
self.assertEqual(expected, result,
"using quote(): %r != %r" % (expected, result))
result = urllib.parse.quote_plus(partial_quote)
self.assertEqual(expected, result,
"using quote_plus(): %r != %r" % (expected, result))
def test_quoting_space(self):
# Make sure quote() and quote_plus() handle spaces as specified in
# their unique way
result = urllib.parse.quote(' ')
self.assertEqual(result, hexescape(' '),
"using quote(): %r != %r" % (result, hexescape(' ')))
result = urllib.parse.quote_plus(' ')
self.assertEqual(result, '+',
"using quote_plus(): %r != +" % result)
given = "a b cd e f"
expect = given.replace(' ', hexescape(' '))
result = urllib.parse.quote(given)
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
expect = given.replace(' ', '+')
result = urllib.parse.quote_plus(given)
self.assertEqual(expect, result,
"using quote_plus(): %r != %r" % (expect, result))
def test_quoting_plus(self):
self.assertEqual(urllib.parse.quote_plus('alpha+beta gamma'),
'alpha%2Bbeta+gamma')
self.assertEqual(urllib.parse.quote_plus('alpha+beta gamma', '+'),
'alpha+beta+gamma')
# Test with bytes
self.assertEqual(urllib.parse.quote_plus(b'alpha+beta gamma'),
'alpha%2Bbeta+gamma')
# Test with safe bytes
self.assertEqual(urllib.parse.quote_plus('alpha+beta gamma', b'+'),
'alpha+beta+gamma')
def test_quote_bytes(self):
# Bytes should quote directly to percent-encoded values
given = b"\xa2\xd8ab\xff"
expect = "%A2%D8ab%FF"
result = urllib.parse.quote(given)
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
# Encoding argument should raise type error on bytes input
self.assertRaises(TypeError, urllib.parse.quote, given,
encoding="latin-1")
# quote_from_bytes should work the same
result = urllib.parse.quote_from_bytes(given)
self.assertEqual(expect, result,
"using quote_from_bytes(): %r != %r"
% (expect, result))
def test_quote_with_unicode(self):
# Characters in Latin-1 range, encoded by default in UTF-8
given = "\xa2\xd8ab\xff"
expect = "%C2%A2%C3%98ab%C3%BF"
result = urllib.parse.quote(given)
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
# Characters in Latin-1 range, encoded by with None (default)
result = urllib.parse.quote(given, encoding=None, errors=None)
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
# Characters in Latin-1 range, encoded with Latin-1
given = "\xa2\xd8ab\xff"
expect = "%A2%D8ab%FF"
result = urllib.parse.quote(given, encoding="latin-1")
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
# Characters in BMP, encoded by default in UTF-8
given = "\u6f22\u5b57" # "Kanji"
expect = "%E6%BC%A2%E5%AD%97"
result = urllib.parse.quote(given)
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
# Characters in BMP, encoded with Latin-1
given = "\u6f22\u5b57"
self.assertRaises(UnicodeEncodeError, urllib.parse.quote, given,
encoding="latin-1")
# Characters in BMP, encoded with Latin-1, with replace error handling
given = "\u6f22\u5b57"
expect = "%3F%3F" # "??"
result = urllib.parse.quote(given, encoding="latin-1",
errors="replace")
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
# Characters in BMP, Latin-1, with xmlcharref error handling
given = "\u6f22\u5b57"
expect = "%26%2328450%3B%26%2323383%3B" # "漢字"
result = urllib.parse.quote(given, encoding="latin-1",
errors="xmlcharrefreplace")
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
def test_quote_plus_with_unicode(self):
# Encoding (latin-1) test for quote_plus
given = "\xa2\xd8 \xff"
expect = "%A2%D8+%FF"
result = urllib.parse.quote_plus(given, encoding="latin-1")
self.assertEqual(expect, result,
"using quote_plus(): %r != %r" % (expect, result))
# Errors test for quote_plus
given = "ab\u6f22\u5b57 cd"
expect = "ab%3F%3F+cd"
result = urllib.parse.quote_plus(given, encoding="latin-1",
errors="replace")
self.assertEqual(expect, result,
"using quote_plus(): %r != %r" % (expect, result))
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.parse.unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
result = urllib.parse.unquote_plus(given)
self.assertEqual(expect, result,
"using unquote_plus(): %r != %r" %
(expect, result))
escape_list.append(given)
escape_string = ''.join(escape_list)
del escape_list
result = urllib.parse.unquote(escape_string)
self.assertEqual(result.count('%'), 1,
"using unquote(): not all characters escaped: "
"%s" % result)
self.assertRaises((TypeError, AttributeError), urllib.parse.unquote, None)
self.assertRaises((TypeError, AttributeError), urllib.parse.unquote, ())
with support.check_warnings(('', BytesWarning), quiet=True):
self.assertRaises((TypeError, AttributeError), urllib.parse.unquote, b'')
def test_unquoting_badpercent(self):
# Test unquoting on bad percent-escapes
given = '%xab'
expect = given
result = urllib.parse.unquote(given)
self.assertEqual(expect, result, "using unquote(): %r != %r"
% (expect, result))
given = '%x'
expect = given
result = urllib.parse.unquote(given)
self.assertEqual(expect, result, "using unquote(): %r != %r"
% (expect, result))
given = '%'
expect = given
result = urllib.parse.unquote(given)
self.assertEqual(expect, result, "using unquote(): %r != %r"
% (expect, result))
# unquote_to_bytes
given = '%xab'
expect = bytes(given, 'ascii')
result = urllib.parse.unquote_to_bytes(given)
self.assertEqual(expect, result, "using unquote_to_bytes(): %r != %r"
% (expect, result))
given = '%x'
expect = bytes(given, 'ascii')
result = urllib.parse.unquote_to_bytes(given)
self.assertEqual(expect, result, "using unquote_to_bytes(): %r != %r"
% (expect, result))
given = '%'
expect = bytes(given, 'ascii')
result = urllib.parse.unquote_to_bytes(given)
self.assertEqual(expect, result, "using unquote_to_bytes(): %r != %r"
% (expect, result))
self.assertRaises((TypeError, AttributeError), urllib.parse.unquote_to_bytes, None)
self.assertRaises((TypeError, AttributeError), urllib.parse.unquote_to_bytes, ())
def test_unquoting_mixed_case(self):
# Test unquoting on mixed-case hex digits in the percent-escapes
given = '%Ab%eA'
expect = b'\xab\xea'
result = urllib.parse.unquote_to_bytes(given)
self.assertEqual(expect, result,
"using unquote_to_bytes(): %r != %r"
% (expect, 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.parse.unquote(given)
self.assertEqual(expect, result,
"using quote(): %r != %r" % (expect, result))
result = urllib.parse.unquote_plus(given)
self.assertEqual(expect, result,
"using unquote_plus(): %r != %r" % (expect, result))
def test_unquoting_plus(self):
# Test difference between unquote() and unquote_plus()
given = "are+there+spaces..."
expect = given
result = urllib.parse.unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
expect = given.replace('+', ' ')
result = urllib.parse.unquote_plus(given)
self.assertEqual(expect, result,
"using unquote_plus(): %r != %r" % (expect, result))
def test_unquote_to_bytes(self):
given = 'br%C3%BCckner_sapporo_20050930.doc'
expect = b'br\xc3\xbcckner_sapporo_20050930.doc'
result = urllib.parse.unquote_to_bytes(given)
self.assertEqual(expect, result,
"using unquote_to_bytes(): %r != %r"
% (expect, result))
# Test on a string with unescaped non-ASCII characters
# (Technically an invalid URI; expect those characters to be UTF-8
# encoded).
result = urllib.parse.unquote_to_bytes("\u6f22%C3%BC")
expect = b'\xe6\xbc\xa2\xc3\xbc' # UTF-8 for "\u6f22\u00fc"
self.assertEqual(expect, result,
"using unquote_to_bytes(): %r != %r"
% (expect, result))
# Test with a bytes as input
given = b'%A2%D8ab%FF'
expect = b'\xa2\xd8ab\xff'
result = urllib.parse.unquote_to_bytes(given)
self.assertEqual(expect, result,
"using unquote_to_bytes(): %r != %r"
% (expect, result))
# Test with a bytes as input, with unescaped non-ASCII bytes
# (Technically an invalid URI; expect those bytes to be preserved)
given = b'%A2\xd8ab%FF'
expect = b'\xa2\xd8ab\xff'
result = urllib.parse.unquote_to_bytes(given)
self.assertEqual(expect, result,
"using unquote_to_bytes(): %r != %r"
% (expect, result))
def test_unquote_with_unicode(self):
# Characters in the Latin-1 range, encoded with UTF-8
given = 'br%C3%BCckner_sapporo_20050930.doc'
expect = 'br\u00fcckner_sapporo_20050930.doc'
result = urllib.parse.unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Characters in the Latin-1 range, encoded with None (default)
result = urllib.parse.unquote(given, encoding=None, errors=None)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Characters in the Latin-1 range, encoded with Latin-1
result = urllib.parse.unquote('br%FCckner_sapporo_20050930.doc',
encoding="latin-1")
expect = 'br\u00fcckner_sapporo_20050930.doc'
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Characters in BMP, encoded with UTF-8
given = "%E6%BC%A2%E5%AD%97"
expect = "\u6f22\u5b57" # "Kanji"
result = urllib.parse.unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Decode with UTF-8, invalid sequence
given = "%F3%B1"
expect = "\ufffd" # Replacement character
result = urllib.parse.unquote(given)
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Decode with UTF-8, invalid sequence, replace errors
result = urllib.parse.unquote(given, errors="replace")
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# Decode with UTF-8, invalid sequence, ignoring errors
given = "%F3%B1"
expect = ""
result = urllib.parse.unquote(given, errors="ignore")
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# A mix of non-ASCII and percent-encoded characters, UTF-8
result = urllib.parse.unquote("\u6f22%C3%BC")
expect = '\u6f22\u00fc'
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
# A mix of non-ASCII and percent-encoded characters, Latin-1
# (Note, the string contains non-Latin-1-representable characters)
result = urllib.parse.unquote("\u6f22%FC", encoding="latin-1")
expect = '\u6f22\u00fc'
self.assertEqual(expect, result,
"using unquote(): %r != %r" % (expect, result))
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.parse.urlencode(given)
for expected in expect_somewhere:
self.assertIn(expected, 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.assertTrue(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.parse.urlencode(given)
self.assertEqual(expect, result)
given = {"key name":"A bunch of pluses"}
expect = "key+name=A+bunch+of+pluses"
result = urllib.parse.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.parse.quote_plus(str(['1', '2', '3']))
result = urllib.parse.urlencode(given)
self.assertEqual(expect, result)
result = urllib.parse.urlencode(given, True)
for value in given["sequence"]:
expect = "sequence=%s" % value
self.assertIn(expect, result)
self.assertEqual(result.count('&'), 2,
"Expected 2 '&'s, got %s" % result.count('&'))
def test_empty_sequence(self):
self.assertEqual("", urllib.parse.urlencode({}))
self.assertEqual("", urllib.parse.urlencode([]))
def test_nonstring_values(self):
self.assertEqual("a=1", urllib.parse.urlencode({"a": 1}))
self.assertEqual("a=None", urllib.parse.urlencode({"a": None}))
def test_nonstring_seq_values(self):
self.assertEqual("a=1&a=2", urllib.parse.urlencode({"a": [1, 2]}, True))
self.assertEqual("a=None&a=a",
urllib.parse.urlencode({"a": [None, "a"]}, True))
data = collections.OrderedDict([("a", 1), ("b", 1)])
self.assertEqual("a=a&a=b",
urllib.parse.urlencode({"a": data}, True))
def test_urlencode_encoding(self):
# ASCII encoding. Expect %3F with errors="replace'
given = (('\u00a0', '\u00c1'),)
expect = '%3F=%3F'
result = urllib.parse.urlencode(given, encoding="ASCII", errors="replace")
self.assertEqual(expect, result)
# Default is UTF-8 encoding.
given = (('\u00a0', '\u00c1'),)
expect = '%C2%A0=%C3%81'
result = urllib.parse.urlencode(given)
self.assertEqual(expect, result)
# Latin-1 encoding.
given = (('\u00a0', '\u00c1'),)
expect = '%A0=%C1'
result = urllib.parse.urlencode(given, encoding="latin-1")
self.assertEqual(expect, result)
def test_urlencode_encoding_doseq(self):
# ASCII Encoding. Expect %3F with errors="replace'
given = (('\u00a0', '\u00c1'),)
expect = '%3F=%3F'
result = urllib.parse.urlencode(given, doseq=True,
encoding="ASCII", errors="replace")
self.assertEqual(expect, result)
# ASCII Encoding. On a sequence of values.
given = (("\u00a0", (1, "\u00c1")),)
expect = '%3F=1&%3F=%3F'
result = urllib.parse.urlencode(given, True,
encoding="ASCII", errors="replace")
self.assertEqual(expect, result)
# Utf-8
given = (("\u00a0", "\u00c1"),)
expect = '%C2%A0=%C3%81'
result = urllib.parse.urlencode(given, True)
self.assertEqual(expect, result)
given = (("\u00a0", (42, "\u00c1")),)
expect = '%C2%A0=42&%C2%A0=%C3%81'
result = urllib.parse.urlencode(given, True)
self.assertEqual(expect, result)
# latin-1
given = (("\u00a0", "\u00c1"),)
expect = '%A0=%C1'
result = urllib.parse.urlencode(given, True, encoding="latin-1")
self.assertEqual(expect, result)
given = (("\u00a0", (42, "\u00c1")),)
expect = '%A0=42&%A0=%C1'
result = urllib.parse.urlencode(given, True, encoding="latin-1")
self.assertEqual(expect, result)
def test_urlencode_bytes(self):
given = ((b'\xa0\x24', b'\xc1\x24'),)
expect = '%A0%24=%C1%24'
result = urllib.parse.urlencode(given)
self.assertEqual(expect, result)
result = urllib.parse.urlencode(given, True)
self.assertEqual(expect, result)
# Sequence of values
given = ((b'\xa0\x24', (42, b'\xc1\x24')),)
expect = '%A0%24=42&%A0%24=%C1%24'
result = urllib.parse.urlencode(given, True)
self.assertEqual(expect, result)
def test_urlencode_encoding_safe_parameter(self):
# Send '$' (\x24) as safe character
# Default utf-8 encoding
given = ((b'\xa0\x24', b'\xc1\x24'),)
result = urllib.parse.urlencode(given, safe=":$")
expect = '%A0$=%C1$'
self.assertEqual(expect, result)
given = ((b'\xa0\x24', b'\xc1\x24'),)
result = urllib.parse.urlencode(given, doseq=True, safe=":$")
expect = '%A0$=%C1$'
self.assertEqual(expect, result)
# Safe parameter in sequence
given = ((b'\xa0\x24', (b'\xc1\x24', 0xd, 42)),)
expect = '%A0$=%C1$&%A0$=13&%A0$=42'
result = urllib.parse.urlencode(given, True, safe=":$")
self.assertEqual(expect, result)
# Test all above in latin-1 encoding
given = ((b'\xa0\x24', b'\xc1\x24'),)
result = urllib.parse.urlencode(given, safe=":$",
encoding="latin-1")
expect = '%A0$=%C1$'
self.assertEqual(expect, result)
given = ((b'\xa0\x24', b'\xc1\x24'),)
expect = '%A0$=%C1$'
result = urllib.parse.urlencode(given, doseq=True, safe=":$",
encoding="latin-1")
given = ((b'\xa0\x24', (b'\xc1\x24', 0xd, 42)),)
expect = '%A0$=%C1$&%A0$=13&%A0$=42'
result = urllib.parse.urlencode(given, True, safe=":$",
encoding="latin-1")
self.assertEqual(expect, result)
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.request.pathname2url(expected_path)
self.assertEqual(expected_url, result,
"pathname2url() failed; %s != %s" %
(result, expected_url))
result = urllib.request.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.parse.quote("quot=ing")
result = urllib.request.pathname2url(given)
self.assertEqual(expect, result,
"pathname2url() failed; %s != %s" %
(expect, result))
expect = given
result = urllib.request.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.parse.quote("make sure")
result = urllib.request.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.request.url2pathname(given)
self.assertEqual(expect, result,
"url2pathname() failed; %s != %s" %
(expect, result))
@unittest.skipUnless(sys.platform == 'win32',
'test specific to the urllib.url2path function.')
def test_ntpath(self):
given = ('/C:/', '///C:/', '/C|//')
expect = 'C:\\'
for url in given:
result = urllib.request.url2pathname(url)
self.assertEqual(expect, result,
'urllib.request..url2pathname() failed; %s != %s' %
(expect, result))
given = '///C|/path'
expect = 'C:\\path'
result = urllib.request.url2pathname(given)
self.assertEqual(expect, result,
'urllib.request.url2pathname() failed; %s != %s' %
(expect, result))
class Utility_Tests(unittest.TestCase):
"""Testcase to test the various utility functions in the urllib."""
def test_splitpasswd(self):
"""Some of password examples are not sensible, but it is added to
confirming to RFC2617 and addressing issue4675.
"""
self.assertEqual(('user', 'ab'),urllib.parse.splitpasswd('user:ab'))
self.assertEqual(('user', 'a\nb'),urllib.parse.splitpasswd('user:a\nb'))
self.assertEqual(('user', 'a\tb'),urllib.parse.splitpasswd('user:a\tb'))
self.assertEqual(('user', 'a\rb'),urllib.parse.splitpasswd('user:a\rb'))
self.assertEqual(('user', 'a\fb'),urllib.parse.splitpasswd('user:a\fb'))
self.assertEqual(('user', 'a\vb'),urllib.parse.splitpasswd('user:a\vb'))
self.assertEqual(('user', 'a:b'),urllib.parse.splitpasswd('user:a:b'))
self.assertEqual(('user', 'a b'),urllib.parse.splitpasswd('user:a b'))
self.assertEqual(('user 2', 'ab'),urllib.parse.splitpasswd('user 2:ab'))
self.assertEqual(('user+1', 'a+b'),urllib.parse.splitpasswd('user+1:a+b'))
def test_thishost(self):
"""Test the urllib.request.thishost utility function returns a tuple"""
self.assertIsInstance(urllib.request.thishost(), tuple)
class URLopener_Tests(unittest.TestCase):
"""Testcase to test the open method of URLopener class."""
def test_quoted_open(self):
class DummyURLopener(urllib.request.URLopener):
def open_spam(self, url):
return url
with support.check_warnings(
('DummyURLopener style of invoking requests is deprecated.',
DeprecationWarning)):
self.assertEqual(DummyURLopener().open(
'spam://example/ /'),'//example/%20/')
# test the safe characters are not quoted by urlopen
self.assertEqual(DummyURLopener().open(
"spam://c:|windows%/:=&?~#+!$,;'@()*[]|/path/"),
"//c:|windows%/:=&?~#+!$,;'@()*[]|/path/")
# Just commented them out.
# Can't really tell why keep failing in windows and sparc.
# Everywhere else they work ok, but on those machines, sometimes
# fail in one of the tests, sometimes in other. I have a linux, and
# the tests go ok.
# If anybody has one of the problematic environments, please help!
# . Facundo
#
# def server(evt):
# import socket, time
# serv = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
# serv.settimeout(3)
# serv.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
# serv.bind(("", 9093))
# serv.listen(5)
# try:
# conn, addr = serv.accept()
# conn.send("1 Hola mundo\n")
# cantdata = 0
# while cantdata < 13:
# data = conn.recv(13-cantdata)
# cantdata += len(data)
# time.sleep(.3)
# conn.send("2 No more lines\n")
# conn.close()
# except socket.timeout:
# pass
# finally:
# serv.close()
# evt.set()
#
# class FTPWrapperTests(unittest.TestCase):
#
# def setUp(self):
# import ftplib, time, threading
# ftplib.FTP.port = 9093
# self.evt = threading.Event()
# threading.Thread(target=server, args=(self.evt,)).start()
# time.sleep(.1)
#
# def tearDown(self):
# self.evt.wait()
#
# def testBasic(self):
# # connects
# ftp = urllib.ftpwrapper("myuser", "mypass", "localhost", 9093, [])
# ftp.close()
#
# def testTimeoutNone(self):
# # global default timeout is ignored
# import socket
# self.assertIsNone(socket.getdefaulttimeout())
# socket.setdefaulttimeout(30)
# try:
# ftp = urllib.ftpwrapper("myuser", "mypass", "localhost", 9093, [])
# finally:
# socket.setdefaulttimeout(None)
# self.assertEqual(ftp.ftp.sock.gettimeout(), 30)
# ftp.close()
#
# def testTimeoutDefault(self):
# # global default timeout is used
# import socket
# self.assertIsNone(socket.getdefaulttimeout())
# socket.setdefaulttimeout(30)
# try:
# ftp = urllib.ftpwrapper("myuser", "mypass", "localhost", 9093, [])
# finally:
# socket.setdefaulttimeout(None)
# self.assertEqual(ftp.ftp.sock.gettimeout(), 30)
# ftp.close()
#
# def testTimeoutValue(self):
# ftp = urllib.ftpwrapper("myuser", "mypass", "localhost", 9093, [],
# timeout=30)
# self.assertEqual(ftp.ftp.sock.gettimeout(), 30)
# ftp.close()
class RequestTests(unittest.TestCase):
"""Unit tests for urllib.request.Request."""
def test_default_values(self):
Request = urllib.request.Request
request = Request("http://www.python.org")
self.assertEqual(request.get_method(), 'GET')
request = Request("http://www.python.org", {})
self.assertEqual(request.get_method(), 'POST')
def test_with_method_arg(self):
Request = urllib.request.Request
request = Request("http://www.python.org", method='HEAD')
self.assertEqual(request.method, 'HEAD')
self.assertEqual(request.get_method(), 'HEAD')
request = Request("http://www.python.org", {}, method='HEAD')
self.assertEqual(request.method, 'HEAD')
self.assertEqual(request.get_method(), 'HEAD')
request = Request("http://www.python.org", method='GET')
self.assertEqual(request.get_method(), 'GET')
request.method = 'HEAD'
self.assertEqual(request.get_method(), 'HEAD')
class URL2PathNameTests(unittest.TestCase):
def test_converting_drive_letter(self):
self.assertEqual(url2pathname("///C|"), 'C:')
self.assertEqual(url2pathname("///C:"), 'C:')
self.assertEqual(url2pathname("///C|/"), 'C:\\')
def test_converting_when_no_drive_letter(self):
# cannot end a raw string in \
self.assertEqual(url2pathname("///C/test/"), r'\\\C\test' '\\')
self.assertEqual(url2pathname("////C/test/"), r'\\C\test' '\\')
def test_simple_compare(self):
self.assertEqual(url2pathname("///C|/foo/bar/spam.foo"),
r'C:\foo\bar\spam.foo')
def test_non_ascii_drive_letter(self):
self.assertRaises(IOError, url2pathname, "///\u00e8|/")
def test_roundtrip_url2pathname(self):
list_of_paths = ['C:',
r'\\\C\test\\',
r'C:\foo\bar\spam.foo'
]
for path in list_of_paths:
self.assertEqual(url2pathname(pathname2url(path)), path)
class PathName2URLTests(unittest.TestCase):
def test_converting_drive_letter(self):
self.assertEqual(pathname2url("C:"), '///C:')
self.assertEqual(pathname2url("C:\\"), '///C:')
def test_converting_when_no_drive_letter(self):
self.assertEqual(pathname2url(r"\\\folder\test" "\\"),
'/////folder/test/')
self.assertEqual(pathname2url(r"\\folder\test" "\\"),
'////folder/test/')
self.assertEqual(pathname2url(r"\folder\test" "\\"),
'/folder/test/')
def test_simple_compare(self):
self.assertEqual(pathname2url(r'C:\foo\bar\spam.foo'),
"///C:/foo/bar/spam.foo" )
def test_long_drive_letter(self):
self.assertRaises(IOError, pathname2url, "XX:\\")
def test_roundtrip_pathname2url(self):
list_of_paths = ['///C:',
'/////folder/test/',
'///C:/foo/bar/spam.foo']
for path in list_of_paths:
self.assertEqual(pathname2url(url2pathname(path)), path)
if __name__ == '__main__':
unittest.main()
|