Repository navigation
Expand file tree
/
Copy pathtest_csv.py
More file actions
1245 lines (1073 loc) · 49.3 KB
/
Copy pathtest_csv.py
File metadata and controls
1245 lines (1073 loc) · 49.3 KB
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
# Copyright (C) 2001,2002 Python Software Foundation
# csv package unit tests
import copy
import sys
import unittest
from io import StringIO
from tempfile import TemporaryFile
import csv
import gc
import pickle
from test import support
from test.support import warnings_helper
from itertools import permutations
from textwrap import dedent
from collections import OrderedDict
class BadIterable:
def __iter__(self):
raise OSError
class Test_Csv(unittest.TestCase):
"""
Test the underlying C csv parser in ways that are not appropriate
from the high level interface. Further tests of this nature are done
in TestDialectRegistry.
"""
def _test_arg_valid(self, ctor, arg):
self.assertRaises(TypeError, ctor)
self.assertRaises(TypeError, ctor, None)
self.assertRaises(TypeError, ctor, arg, bad_attr = 0)
self.assertRaises(TypeError, ctor, arg, delimiter = 0)
self.assertRaises(TypeError, ctor, arg, delimiter = 'XX')
self.assertRaises(csv.Error, ctor, arg, 'foo')
self.assertRaises(TypeError, ctor, arg, delimiter=None)
self.assertRaises(TypeError, ctor, arg, delimiter=1)
self.assertRaises(TypeError, ctor, arg, quotechar=1)
self.assertRaises(TypeError, ctor, arg, lineterminator=None)
self.assertRaises(TypeError, ctor, arg, lineterminator=1)
self.assertRaises(TypeError, ctor, arg, quoting=None)
self.assertRaises(TypeError, ctor, arg,
quoting=csv.QUOTE_ALL, quotechar='')
self.assertRaises(TypeError, ctor, arg,
quoting=csv.QUOTE_ALL, quotechar=None)
def test_reader_arg_valid(self):
self._test_arg_valid(csv.reader, [])
self.assertRaises(OSError, csv.reader, BadIterable())
def test_writer_arg_valid(self):
self._test_arg_valid(csv.writer, StringIO())
class BadWriter:
@property
def write(self):
raise OSError
self.assertRaises(OSError, csv.writer, BadWriter())
def _test_default_attrs(self, ctor, *args):
obj = ctor(*args)
# Check defaults
self.assertEqual(obj.dialect.delimiter, ',')
self.assertIs(obj.dialect.doublequote, True)
self.assertEqual(obj.dialect.escapechar, None)
self.assertEqual(obj.dialect.lineterminator, "\r\n")
self.assertEqual(obj.dialect.quotechar, '"')
self.assertEqual(obj.dialect.quoting, csv.QUOTE_MINIMAL)
self.assertIs(obj.dialect.skipinitialspace, False)
self.assertIs(obj.dialect.strict, False)
# Try deleting or changing attributes (they are read-only)
self.assertRaises(AttributeError, delattr, obj.dialect, 'delimiter')
self.assertRaises(AttributeError, setattr, obj.dialect, 'delimiter', ':')
self.assertRaises(AttributeError, delattr, obj.dialect, 'quoting')
self.assertRaises(AttributeError, setattr, obj.dialect,
'quoting', None)
def test_reader_attrs(self):
self._test_default_attrs(csv.reader, [])
def test_writer_attrs(self):
self._test_default_attrs(csv.writer, StringIO())
def _test_kw_attrs(self, ctor, *args):
# Now try with alternate options
kwargs = dict(delimiter=':', doublequote=False, escapechar='\\',
lineterminator='\r', quotechar='*',
quoting=csv.QUOTE_NONE, skipinitialspace=True,
strict=True)
obj = ctor(*args, **kwargs)
self.assertEqual(obj.dialect.delimiter, ':')
self.assertIs(obj.dialect.doublequote, False)
self.assertEqual(obj.dialect.escapechar, '\\')
self.assertEqual(obj.dialect.lineterminator, "\r")
self.assertEqual(obj.dialect.quotechar, '*')
self.assertEqual(obj.dialect.quoting, csv.QUOTE_NONE)
self.assertIs(obj.dialect.skipinitialspace, True)
self.assertIs(obj.dialect.strict, True)
def test_reader_kw_attrs(self):
self._test_kw_attrs(csv.reader, [])
def test_writer_kw_attrs(self):
self._test_kw_attrs(csv.writer, StringIO())
def _test_dialect_attrs(self, ctor, *args):
# Now try with dialect-derived options
class dialect:
delimiter='-'
doublequote=False
escapechar='^'
lineterminator='$'
quotechar='#'
quoting=csv.QUOTE_ALL
skipinitialspace=True
strict=False
args = args + (dialect,)
obj = ctor(*args)
self.assertEqual(obj.dialect.delimiter, '-')
self.assertIs(obj.dialect.doublequote, False)
self.assertEqual(obj.dialect.escapechar, '^')
self.assertEqual(obj.dialect.lineterminator, "$")
self.assertEqual(obj.dialect.quotechar, '#')
self.assertEqual(obj.dialect.quoting, csv.QUOTE_ALL)
self.assertIs(obj.dialect.skipinitialspace, True)
self.assertIs(obj.dialect.strict, False)
def test_reader_dialect_attrs(self):
self._test_dialect_attrs(csv.reader, [])
def test_writer_dialect_attrs(self):
self._test_dialect_attrs(csv.writer, StringIO())
def _write_test(self, fields, expect, **kwargs):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, **kwargs)
writer.writerow(fields)
fileobj.seek(0)
self.assertEqual(fileobj.read(),
expect + writer.dialect.lineterminator)
def _write_error_test(self, exc, fields, **kwargs):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, **kwargs)
with self.assertRaises(exc):
writer.writerow(fields)
fileobj.seek(0)
self.assertEqual(fileobj.read(), '')
def test_write_arg_valid(self):
self._write_error_test(csv.Error, None)
self._write_test((), '')
self._write_test([None], '""')
self._write_error_test(csv.Error, [None], quoting = csv.QUOTE_NONE)
# Check that exceptions are passed up the chain
self._write_error_test(OSError, BadIterable())
class BadList:
def __len__(self):
return 10;
def __getitem__(self, i):
if i > 2:
raise OSError
self._write_error_test(OSError, BadList())
class BadItem:
def __str__(self):
raise OSError
self._write_error_test(OSError, [BadItem()])
def test_write_bigfield(self):
# This exercises the buffer realloc functionality
bigstring = 'X' * 50000
self._write_test([bigstring,bigstring], '%s,%s' % \
(bigstring, bigstring))
def test_write_quoting(self):
self._write_test(['a',1,'p,q'], 'a,1,"p,q"')
self._write_error_test(csv.Error, ['a',1,'p,q'],
quoting = csv.QUOTE_NONE)
self._write_test(['a',1,'p,q'], 'a,1,"p,q"',
quoting = csv.QUOTE_MINIMAL)
self._write_test(['a',1,'p,q'], '"a",1,"p,q"',
quoting = csv.QUOTE_NONNUMERIC)
self._write_test(['a',1,'p,q'], '"a","1","p,q"',
quoting = csv.QUOTE_ALL)
self._write_test(['a\nb',1], '"a\nb","1"',
quoting = csv.QUOTE_ALL)
def test_write_escape(self):
self._write_test(['a',1,'p,q'], 'a,1,"p,q"',
escapechar='\\')
self._write_error_test(csv.Error, ['a',1,'p,"q"'],
escapechar=None, doublequote=False)
self._write_test(['a',1,'p,"q"'], 'a,1,"p,\\"q\\""',
escapechar='\\', doublequote = False)
self._write_test(['"'], '""""',
escapechar='\\', quoting = csv.QUOTE_MINIMAL)
self._write_test(['"'], '\\"',
escapechar='\\', quoting = csv.QUOTE_MINIMAL,
doublequote = False)
self._write_test(['"'], '\\"',
escapechar='\\', quoting = csv.QUOTE_NONE)
self._write_test(['a',1,'p,q'], 'a,1,p\\,q',
escapechar='\\', quoting = csv.QUOTE_NONE)
self._write_test(['\\', 'a'], '\\\\,a',
escapechar='\\', quoting=csv.QUOTE_NONE)
self._write_test(['\\', 'a'], '\\\\,a',
escapechar='\\', quoting=csv.QUOTE_MINIMAL)
self._write_test(['\\', 'a'], '"\\\\","a"',
escapechar='\\', quoting=csv.QUOTE_ALL)
self._write_test(['\\ ', 'a'], '\\\\ ,a',
escapechar='\\', quoting=csv.QUOTE_MINIMAL)
self._write_test(['\\,', 'a'], '\\\\\\,,a',
escapechar='\\', quoting=csv.QUOTE_NONE)
self._write_test([',\\', 'a'], '",\\\\",a',
escapechar='\\', quoting=csv.QUOTE_MINIMAL)
self._write_test(['C\\', '6', '7', 'X"'], 'C\\\\,6,7,"X"""',
escapechar='\\', quoting=csv.QUOTE_MINIMAL)
def test_write_iterable(self):
self._write_test(iter(['a', 1, 'p,q']), 'a,1,"p,q"')
self._write_test(iter(['a', 1, None]), 'a,1,')
self._write_test(iter([]), '')
self._write_test(iter([None]), '""')
self._write_error_test(csv.Error, iter([None]), quoting=csv.QUOTE_NONE)
self._write_test(iter([None, None]), ',')
def test_writerows(self):
class BrokenFile:
def write(self, buf):
raise OSError
writer = csv.writer(BrokenFile())
self.assertRaises(OSError, writer.writerows, [['a']])
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj)
self.assertRaises(TypeError, writer.writerows, None)
writer.writerows([['a', 'b'], ['c', 'd']])
fileobj.seek(0)
self.assertEqual(fileobj.read(), "a,b\r\nc,d\r\n")
def test_writerows_with_none(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj)
writer.writerows([['a', None], [None, 'd']])
fileobj.seek(0)
self.assertEqual(fileobj.read(), "a,\r\n,d\r\n")
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj)
writer.writerows([[None], ['a']])
fileobj.seek(0)
self.assertEqual(fileobj.read(), '""\r\na\r\n')
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj)
writer.writerows([['a'], [None]])
fileobj.seek(0)
self.assertEqual(fileobj.read(), 'a\r\n""\r\n')
def test_writerows_errors(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj)
self.assertRaises(TypeError, writer.writerows, None)
self.assertRaises(OSError, writer.writerows, BadIterable())
@support.cpython_only
@support.requires_legacy_unicode_capi
@warnings_helper.ignore_warnings(category=DeprecationWarning)
def test_writerows_legacy_strings(self):
import _testcapi
c = _testcapi.unicode_legacy_string('a')
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj)
writer.writerows([[c]])
fileobj.seek(0)
self.assertEqual(fileobj.read(), "a\r\n")
def _read_test(self, input, expect, **kwargs):
reader = csv.reader(input, **kwargs)
result = list(reader)
self.assertEqual(result, expect)
def test_read_oddinputs(self):
self._read_test([], [])
self._read_test([''], [[]])
self.assertRaises(csv.Error, self._read_test,
['"ab"c'], None, strict = 1)
# cannot handle null bytes for the moment
self.assertRaises(csv.Error, self._read_test,
['ab\0c'], None, strict = 1)
self._read_test(['"ab"c'], [['abc']], doublequote = 0)
self.assertRaises(csv.Error, self._read_test,
[b'ab\0c'], None)
def test_read_eol(self):
self._read_test(['a,b'], [['a','b']])
self._read_test(['a,b\n'], [['a','b']])
self._read_test(['a,b\r\n'], [['a','b']])
self._read_test(['a,b\r'], [['a','b']])
self.assertRaises(csv.Error, self._read_test, ['a,b\rc,d'], [])
self.assertRaises(csv.Error, self._read_test, ['a,b\nc,d'], [])
self.assertRaises(csv.Error, self._read_test, ['a,b\r\nc,d'], [])
def test_read_eof(self):
self._read_test(['a,"'], [['a', '']])
self._read_test(['"a'], [['a']])
self._read_test(['^'], [['\n']], escapechar='^')
self.assertRaises(csv.Error, self._read_test, ['a,"'], [], strict=True)
self.assertRaises(csv.Error, self._read_test, ['"a'], [], strict=True)
self.assertRaises(csv.Error, self._read_test,
['^'], [], escapechar='^', strict=True)
def test_read_escape(self):
self._read_test(['a,\\b,c'], [['a', 'b', 'c']], escapechar='\\')
self._read_test(['a,b\\,c'], [['a', 'b,c']], escapechar='\\')
self._read_test(['a,"b\\,c"'], [['a', 'b,c']], escapechar='\\')
self._read_test(['a,"b,\\c"'], [['a', 'b,c']], escapechar='\\')
self._read_test(['a,"b,c\\""'], [['a', 'b,c"']], escapechar='\\')
self._read_test(['a,"b,c"\\'], [['a', 'b,c\\']], escapechar='\\')
def test_read_quoting(self):
self._read_test(['1,",3,",5'], [['1', ',3,', '5']])
self._read_test(['1,",3,",5'], [['1', '"', '3', '"', '5']],
quotechar=None, escapechar='\\')
self._read_test(['1,",3,",5'], [['1', '"', '3', '"', '5']],
quoting=csv.QUOTE_NONE, escapechar='\\')
# will this fail where locale uses comma for decimals?
self._read_test([',3,"5",7.3, 9'], [['', 3, '5', 7.3, 9]],
quoting=csv.QUOTE_NONNUMERIC)
self._read_test(['"a\nb", 7'], [['a\nb', ' 7']])
self.assertRaises(ValueError, self._read_test,
['abc,3'], [[]],
quoting=csv.QUOTE_NONNUMERIC)
def test_read_bigfield(self):
# This exercises the buffer realloc functionality and field size
# limits.
limit = csv.field_size_limit()
try:
size = 50000
bigstring = 'X' * size
bigline = '%s,%s' % (bigstring, bigstring)
self._read_test([bigline], [[bigstring, bigstring]])
csv.field_size_limit(size)
self._read_test([bigline], [[bigstring, bigstring]])
self.assertEqual(csv.field_size_limit(), size)
csv.field_size_limit(size-1)
self.assertRaises(csv.Error, self._read_test, [bigline], [])
self.assertRaises(TypeError, csv.field_size_limit, None)
self.assertRaises(TypeError, csv.field_size_limit, 1, None)
finally:
csv.field_size_limit(limit)
def test_read_linenum(self):
r = csv.reader(['line,1', 'line,2', 'line,3'])
self.assertEqual(r.line_num, 0)
next(r)
self.assertEqual(r.line_num, 1)
next(r)
self.assertEqual(r.line_num, 2)
next(r)
self.assertEqual(r.line_num, 3)
self.assertRaises(StopIteration, next, r)
self.assertEqual(r.line_num, 3)
def test_roundtrip_quoteed_newlines(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj)
rows = [['a\nb','b'],['c','x\r\nd']]
writer.writerows(rows)
fileobj.seek(0)
for i, row in enumerate(csv.reader(fileobj)):
self.assertEqual(row, rows[i])
def test_roundtrip_escaped_unquoted_newlines(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj,quoting=csv.QUOTE_NONE,escapechar="\\")
rows = [['a\nb','b'],['c','x\r\nd']]
writer.writerows(rows)
fileobj.seek(0)
for i, row in enumerate(csv.reader(fileobj,quoting=csv.QUOTE_NONE,escapechar="\\")):
self.assertEqual(row,rows[i])
class TestDialectRegistry(unittest.TestCase):
def test_registry_badargs(self):
self.assertRaises(TypeError, csv.list_dialects, None)
self.assertRaises(TypeError, csv.get_dialect)
self.assertRaises(csv.Error, csv.get_dialect, None)
self.assertRaises(csv.Error, csv.get_dialect, "nonesuch")
self.assertRaises(TypeError, csv.unregister_dialect)
self.assertRaises(csv.Error, csv.unregister_dialect, None)
self.assertRaises(csv.Error, csv.unregister_dialect, "nonesuch")
self.assertRaises(TypeError, csv.register_dialect, None)
self.assertRaises(TypeError, csv.register_dialect, None, None)
self.assertRaises(TypeError, csv.register_dialect, "nonesuch", 0, 0)
self.assertRaises(TypeError, csv.register_dialect, "nonesuch",
badargument=None)
self.assertRaises(TypeError, csv.register_dialect, "nonesuch",
quoting=None)
self.assertRaises(TypeError, csv.register_dialect, [])
def test_registry(self):
class myexceltsv(csv.excel):
delimiter = "\t"
name = "myexceltsv"
expected_dialects = csv.list_dialects() + [name]
expected_dialects.sort()
csv.register_dialect(name, myexceltsv)
self.addCleanup(csv.unregister_dialect, name)
self.assertEqual(csv.get_dialect(name).delimiter, '\t')
got_dialects = sorted(csv.list_dialects())
self.assertEqual(expected_dialects, got_dialects)
def test_register_kwargs(self):
name = 'fedcba'
csv.register_dialect(name, delimiter=';')
self.addCleanup(csv.unregister_dialect, name)
self.assertEqual(csv.get_dialect(name).delimiter, ';')
self.assertEqual([['X', 'Y', 'Z']], list(csv.reader(['X;Y;Z'], name)))
def test_incomplete_dialect(self):
class myexceltsv(csv.Dialect):
delimiter = "\t"
self.assertRaises(csv.Error, myexceltsv)
def test_space_dialect(self):
class space(csv.excel):
delimiter = " "
quoting = csv.QUOTE_NONE
escapechar = "\\"
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("abc def\nc1ccccc1 benzene\n")
fileobj.seek(0)
reader = csv.reader(fileobj, dialect=space())
self.assertEqual(next(reader), ["abc", "def"])
self.assertEqual(next(reader), ["c1ccccc1", "benzene"])
def compare_dialect_123(self, expected, *writeargs, **kwwriteargs):
with TemporaryFile("w+", newline='', encoding="utf-8") as fileobj:
writer = csv.writer(fileobj, *writeargs, **kwwriteargs)
writer.writerow([1,2,3])
fileobj.seek(0)
self.assertEqual(fileobj.read(), expected)
def test_dialect_apply(self):
class testA(csv.excel):
delimiter = "\t"
class testB(csv.excel):
delimiter = ":"
class testC(csv.excel):
delimiter = "|"
class testUni(csv.excel):
delimiter = "\u039B"
csv.register_dialect('testC', testC)
try:
self.compare_dialect_123("1,2,3\r\n")
self.compare_dialect_123("1\t2\t3\r\n", testA)
self.compare_dialect_123("1:2:3\r\n", dialect=testB())
self.compare_dialect_123("1|2|3\r\n", dialect='testC')
self.compare_dialect_123("1;2;3\r\n", dialect=testA,
delimiter=';')
self.compare_dialect_123("1\u039B2\u039B3\r\n",
dialect=testUni)
finally:
csv.unregister_dialect('testC')
def test_bad_dialect(self):
# Unknown parameter
self.assertRaises(TypeError, csv.reader, [], bad_attr = 0)
# Bad values
self.assertRaises(TypeError, csv.reader, [], delimiter = None)
self.assertRaises(TypeError, csv.reader, [], quoting = -1)
self.assertRaises(TypeError, csv.reader, [], quoting = 100)
def test_copy(self):
for name in csv.list_dialects():
dialect = csv.get_dialect(name)
self.assertRaises(TypeError, copy.copy, dialect)
def test_pickle(self):
for name in csv.list_dialects():
dialect = csv.get_dialect(name)
for proto in range(pickle.HIGHEST_PROTOCOL + 1):
self.assertRaises(TypeError, pickle.dumps, dialect, proto)
class TestCsvBase(unittest.TestCase):
def readerAssertEqual(self, input, expected_result):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
fileobj.write(input)
fileobj.seek(0)
reader = csv.reader(fileobj, dialect = self.dialect)
fields = list(reader)
self.assertEqual(fields, expected_result)
def writerAssertEqual(self, input, expected_result):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, dialect = self.dialect)
writer.writerows(input)
fileobj.seek(0)
self.assertEqual(fileobj.read(), expected_result)
class TestDialectExcel(TestCsvBase):
dialect = 'excel'
def test_single(self):
self.readerAssertEqual('abc', [['abc']])
def test_simple(self):
self.readerAssertEqual('1,2,3,4,5', [['1','2','3','4','5']])
def test_blankline(self):
self.readerAssertEqual('', [])
def test_empty_fields(self):
self.readerAssertEqual(',', [['', '']])
def test_singlequoted(self):
self.readerAssertEqual('""', [['']])
def test_singlequoted_left_empty(self):
self.readerAssertEqual('"",', [['','']])
def test_singlequoted_right_empty(self):
self.readerAssertEqual(',""', [['','']])
def test_single_quoted_quote(self):
self.readerAssertEqual('""""', [['"']])
def test_quoted_quotes(self):
self.readerAssertEqual('""""""', [['""']])
def test_inline_quote(self):
self.readerAssertEqual('a""b', [['a""b']])
def test_inline_quotes(self):
self.readerAssertEqual('a"b"c', [['a"b"c']])
def test_quotes_and_more(self):
# Excel would never write a field containing '"a"b', but when
# reading one, it will return 'ab'.
self.readerAssertEqual('"a"b', [['ab']])
def test_lone_quote(self):
self.readerAssertEqual('a"b', [['a"b']])
def test_quote_and_quote(self):
# Excel would never write a field containing '"a" "b"', but when
# reading one, it will return 'a "b"'.
self.readerAssertEqual('"a" "b"', [['a "b"']])
def test_space_and_quote(self):
self.readerAssertEqual(' "a"', [[' "a"']])
def test_quoted(self):
self.readerAssertEqual('1,2,3,"I think, therefore I am",5,6',
[['1', '2', '3',
'I think, therefore I am',
'5', '6']])
def test_quoted_quote(self):
self.readerAssertEqual('1,2,3,"""I see,"" said the blind man","as he picked up his hammer and saw"',
[['1', '2', '3',
'"I see," said the blind man',
'as he picked up his hammer and saw']])
def test_quoted_nl(self):
input = '''\
1,2,3,"""I see,""
said the blind man","as he picked up his
hammer and saw"
9,8,7,6'''
self.readerAssertEqual(input,
[['1', '2', '3',
'"I see,"\nsaid the blind man',
'as he picked up his\nhammer and saw'],
['9','8','7','6']])
def test_dubious_quote(self):
self.readerAssertEqual('12,12,1",', [['12', '12', '1"', '']])
def test_null(self):
self.writerAssertEqual([], '')
def test_single_writer(self):
self.writerAssertEqual([['abc']], 'abc\r\n')
def test_simple_writer(self):
self.writerAssertEqual([[1, 2, 'abc', 3, 4]], '1,2,abc,3,4\r\n')
def test_quotes(self):
self.writerAssertEqual([[1, 2, 'a"bc"', 3, 4]], '1,2,"a""bc""",3,4\r\n')
def test_quote_fieldsep(self):
self.writerAssertEqual([['abc,def']], '"abc,def"\r\n')
def test_newlines(self):
self.writerAssertEqual([[1, 2, 'a\nbc', 3, 4]], '1,2,"a\nbc",3,4\r\n')
class EscapedExcel(csv.excel):
quoting = csv.QUOTE_NONE
escapechar = '\\'
class TestEscapedExcel(TestCsvBase):
dialect = EscapedExcel()
def test_escape_fieldsep(self):
self.writerAssertEqual([['abc,def']], 'abc\\,def\r\n')
def test_read_escape_fieldsep(self):
self.readerAssertEqual('abc\\,def\r\n', [['abc,def']])
class TestDialectUnix(TestCsvBase):
dialect = 'unix'
def test_simple_writer(self):
self.writerAssertEqual([[1, 'abc def', 'abc']], '"1","abc def","abc"\n')
def test_simple_reader(self):
self.readerAssertEqual('"1","abc def","abc"\n', [['1', 'abc def', 'abc']])
class QuotedEscapedExcel(csv.excel):
quoting = csv.QUOTE_NONNUMERIC
escapechar = '\\'
class TestQuotedEscapedExcel(TestCsvBase):
dialect = QuotedEscapedExcel()
def test_write_escape_fieldsep(self):
self.writerAssertEqual([['abc,def']], '"abc,def"\r\n')
def test_read_escape_fieldsep(self):
self.readerAssertEqual('"abc\\,def"\r\n', [['abc,def']])
class TestDictFields(unittest.TestCase):
### "long" means the row is longer than the number of fieldnames
### "short" means there are fewer elements in the row than fieldnames
def test_writeheader_return_value(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.DictWriter(fileobj, fieldnames = ["f1", "f2", "f3"])
writeheader_return_value = writer.writeheader()
self.assertEqual(writeheader_return_value, 10)
def test_write_simple_dict(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.DictWriter(fileobj, fieldnames = ["f1", "f2", "f3"])
writer.writeheader()
fileobj.seek(0)
self.assertEqual(fileobj.readline(), "f1,f2,f3\r\n")
writer.writerow({"f1": 10, "f3": "abc"})
fileobj.seek(0)
fileobj.readline() # header
self.assertEqual(fileobj.read(), "10,,abc\r\n")
def test_write_multiple_dict_rows(self):
fileobj = StringIO()
writer = csv.DictWriter(fileobj, fieldnames=["f1", "f2", "f3"])
writer.writeheader()
self.assertEqual(fileobj.getvalue(), "f1,f2,f3\r\n")
writer.writerows([{"f1": 1, "f2": "abc", "f3": "f"},
{"f1": 2, "f2": 5, "f3": "xyz"}])
self.assertEqual(fileobj.getvalue(),
"f1,f2,f3\r\n1,abc,f\r\n2,5,xyz\r\n")
def test_write_no_fields(self):
fileobj = StringIO()
self.assertRaises(TypeError, csv.DictWriter, fileobj)
def test_write_fields_not_in_fieldnames(self):
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.DictWriter(fileobj, fieldnames = ["f1", "f2", "f3"])
# Of special note is the non-string key (issue 19449)
with self.assertRaises(ValueError) as cx:
writer.writerow({"f4": 10, "f2": "spam", 1: "abc"})
exception = str(cx.exception)
self.assertIn("fieldnames", exception)
self.assertIn("'f4'", exception)
self.assertNotIn("'f2'", exception)
self.assertIn("1", exception)
def test_typo_in_extrasaction_raises_error(self):
fileobj = StringIO()
self.assertRaises(ValueError, csv.DictWriter, fileobj, ['f1', 'f2'],
extrasaction="raised")
def test_write_field_not_in_field_names_raise(self):
fileobj = StringIO()
writer = csv.DictWriter(fileobj, ['f1', 'f2'], extrasaction="raise")
dictrow = {'f0': 0, 'f1': 1, 'f2': 2, 'f3': 3}
self.assertRaises(ValueError, csv.DictWriter.writerow, writer, dictrow)
def test_write_field_not_in_field_names_ignore(self):
fileobj = StringIO()
writer = csv.DictWriter(fileobj, ['f1', 'f2'], extrasaction="ignore")
dictrow = {'f0': 0, 'f1': 1, 'f2': 2, 'f3': 3}
csv.DictWriter.writerow(writer, dictrow)
self.assertEqual(fileobj.getvalue(), "1,2\r\n")
def test_read_dict_fields(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("1,2,abc\r\n")
fileobj.seek(0)
reader = csv.DictReader(fileobj,
fieldnames=["f1", "f2", "f3"])
self.assertEqual(next(reader), {"f1": '1', "f2": '2', "f3": 'abc'})
def test_read_dict_no_fieldnames(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("f1,f2,f3\r\n1,2,abc\r\n")
fileobj.seek(0)
reader = csv.DictReader(fileobj)
self.assertEqual(next(reader), {"f1": '1', "f2": '2', "f3": 'abc'})
self.assertEqual(reader.fieldnames, ["f1", "f2", "f3"])
# Two test cases to make sure existing ways of implicitly setting
# fieldnames continue to work. Both arise from discussion in issue3436.
def test_read_dict_fieldnames_from_file(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("f1,f2,f3\r\n1,2,abc\r\n")
fileobj.seek(0)
reader = csv.DictReader(fileobj,
fieldnames=next(csv.reader(fileobj)))
self.assertEqual(reader.fieldnames, ["f1", "f2", "f3"])
self.assertEqual(next(reader), {"f1": '1', "f2": '2', "f3": 'abc'})
def test_read_dict_fieldnames_chain(self):
import itertools
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("f1,f2,f3\r\n1,2,abc\r\n")
fileobj.seek(0)
reader = csv.DictReader(fileobj)
first = next(reader)
for row in itertools.chain([first], reader):
self.assertEqual(reader.fieldnames, ["f1", "f2", "f3"])
self.assertEqual(row, {"f1": '1', "f2": '2', "f3": 'abc'})
def test_read_long(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("1,2,abc,4,5,6\r\n")
fileobj.seek(0)
reader = csv.DictReader(fileobj,
fieldnames=["f1", "f2"])
self.assertEqual(next(reader), {"f1": '1', "f2": '2',
None: ["abc", "4", "5", "6"]})
def test_read_long_with_rest(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("1,2,abc,4,5,6\r\n")
fileobj.seek(0)
reader = csv.DictReader(fileobj,
fieldnames=["f1", "f2"], restkey="_rest")
self.assertEqual(next(reader), {"f1": '1', "f2": '2',
"_rest": ["abc", "4", "5", "6"]})
def test_read_long_with_rest_no_fieldnames(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("f1,f2\r\n1,2,abc,4,5,6\r\n")
fileobj.seek(0)
reader = csv.DictReader(fileobj, restkey="_rest")
self.assertEqual(reader.fieldnames, ["f1", "f2"])
self.assertEqual(next(reader), {"f1": '1', "f2": '2',
"_rest": ["abc", "4", "5", "6"]})
def test_read_short(self):
with TemporaryFile("w+", encoding="utf-8") as fileobj:
fileobj.write("1,2,abc,4,5,6\r\n1,2,abc\r\n")
fileobj.seek(0)
reader = csv.DictReader(fileobj,
fieldnames="1 2 3 4 5 6".split(),
restval="DEFAULT")
self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
"4": '4', "5": '5', "6": '6'})
self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
"4": 'DEFAULT', "5": 'DEFAULT',
"6": 'DEFAULT'})
def test_read_multi(self):
sample = [
'2147483648,43.0e12,17,abc,def\r\n',
'147483648,43.0e2,17,abc,def\r\n',
'47483648,43.0,170,abc,def\r\n'
]
reader = csv.DictReader(sample,
fieldnames="i1 float i2 s1 s2".split())
self.assertEqual(next(reader), {"i1": '2147483648',
"float": '43.0e12',
"i2": '17',
"s1": 'abc',
"s2": 'def'})
def test_read_with_blanks(self):
reader = csv.DictReader(["1,2,abc,4,5,6\r\n","\r\n",
"1,2,abc,4,5,6\r\n"],
fieldnames="1 2 3 4 5 6".split())
self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
"4": '4', "5": '5', "6": '6'})
self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
"4": '4', "5": '5', "6": '6'})
def test_read_semi_sep(self):
reader = csv.DictReader(["1;2;abc;4;5;6\r\n"],
fieldnames="1 2 3 4 5 6".split(),
delimiter=';')
self.assertEqual(next(reader), {"1": '1', "2": '2', "3": 'abc',
"4": '4', "5": '5', "6": '6'})
class TestArrayWrites(unittest.TestCase):
def test_int_write(self):
import array
contents = [(20-i) for i in range(20)]
a = array.array('i', contents)
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, dialect="excel")
writer.writerow(a)
expected = ",".join([str(i) for i in a])+"\r\n"
fileobj.seek(0)
self.assertEqual(fileobj.read(), expected)
def test_double_write(self):
import array
contents = [(20-i)*0.1 for i in range(20)]
a = array.array('d', contents)
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, dialect="excel")
writer.writerow(a)
expected = ",".join([str(i) for i in a])+"\r\n"
fileobj.seek(0)
self.assertEqual(fileobj.read(), expected)
def test_float_write(self):
import array
contents = [(20-i)*0.1 for i in range(20)]
a = array.array('f', contents)
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, dialect="excel")
writer.writerow(a)
expected = ",".join([str(i) for i in a])+"\r\n"
fileobj.seek(0)
self.assertEqual(fileobj.read(), expected)
def test_char_write(self):
import array, string
a = array.array('u', string.ascii_letters)
with TemporaryFile("w+", encoding="utf-8", newline='') as fileobj:
writer = csv.writer(fileobj, dialect="excel")
writer.writerow(a)
expected = ",".join(a)+"\r\n"
fileobj.seek(0)
self.assertEqual(fileobj.read(), expected)
class TestDialectValidity(unittest.TestCase):
def test_quoting(self):
class mydialect(csv.Dialect):
delimiter = ";"
escapechar = '\\'
doublequote = False
skipinitialspace = True
lineterminator = '\r\n'
quoting = csv.QUOTE_NONE
d = mydialect()
self.assertEqual(d.quoting, csv.QUOTE_NONE)
mydialect.quoting = None
self.assertRaises(csv.Error, mydialect)
mydialect.doublequote = True
mydialect.quoting = csv.QUOTE_ALL
mydialect.quotechar = '"'
d = mydialect()
self.assertEqual(d.quoting, csv.QUOTE_ALL)
self.assertEqual(d.quotechar, '"')
self.assertTrue(d.doublequote)
mydialect.quotechar = "''"
with self.assertRaises(csv.Error) as cm:
mydialect()
self.assertEqual(str(cm.exception),
'"quotechar" must be a 1-character string')
mydialect.quotechar = 4
with self.assertRaises(csv.Error) as cm:
mydialect()
self.assertEqual(str(cm.exception),
'"quotechar" must be string, not int')
def test_delimiter(self):
class mydialect(csv.Dialect):
delimiter = ";"
escapechar = '\\'
doublequote = False
skipinitialspace = True
lineterminator = '\r\n'
quoting = csv.QUOTE_NONE
d = mydialect()
self.assertEqual(d.delimiter, ";")
mydialect.delimiter = ":::"
with self.assertRaises(csv.Error) as cm:
mydialect()
self.assertEqual(str(cm.exception),
'"delimiter" must be a 1-character string')
mydialect.delimiter = ""
with self.assertRaises(csv.Error) as cm:
mydialect()
self.assertEqual(str(cm.exception),
'"delimiter" must be a 1-character string')
mydialect.delimiter = b","
with self.assertRaises(csv.Error) as cm:
mydialect()
self.assertEqual(str(cm.exception),
'"delimiter" must be string, not bytes')
mydialect.delimiter = 4
with self.assertRaises(csv.Error) as cm:
mydialect()
self.assertEqual(str(cm.exception),
'"delimiter" must be string, not int')
def test_lineterminator(self):
class mydialect(csv.Dialect):
delimiter = ";"
escapechar = '\\'
doublequote = False
skipinitialspace = True
lineterminator = '\r\n'
quoting = csv.QUOTE_NONE
d = mydialect()
self.assertEqual(d.lineterminator, '\r\n')
mydialect.lineterminator = ":::"
d = mydialect()
self.assertEqual(d.lineterminator, ":::")
mydialect.lineterminator = 4
with self.assertRaises(csv.Error) as cm:
mydialect()
self.assertEqual(str(cm.exception),
'"lineterminator" must be a string')
def test_invalid_chars(self):
def create_invalid(field_name, value):
class mydialect(csv.Dialect):
pass
setattr(mydialect, field_name, value)
d = mydialect()
for field_name in ("delimiter", "escapechar", "quotechar"):
with self.subTest(field_name=field_name):
self.assertRaises(csv.Error, create_invalid, field_name, "")
self.assertRaises(csv.Error, create_invalid, field_name, "abc")
self.assertRaises(csv.Error, create_invalid, field_name, b'x')
self.assertRaises(csv.Error, create_invalid, field_name, 5)
class TestSniffer(unittest.TestCase):
sample1 = """\
Harry's, Arlington Heights, IL, 2/1/03, Kimi Hayes
Shark City, Glendale Heights, IL, 12/28/02, Prezence
Tommy's Place, Blue Island, IL, 12/28/02, Blue Sunday/White Crow
Stonecutters Seafood and Chop House, Lemont, IL, 12/19/02, Week Back
"""
sample2 = """\
'Harry''s':'Arlington Heights':'IL':'2/1/03':'Kimi Hayes'
'Shark City':'Glendale Heights':'IL':'12/28/02':'Prezence'
'Tommy''s Place':'Blue Island':'IL':'12/28/02':'Blue Sunday/White Crow'
'Stonecutters ''Seafood'' and Chop House':'Lemont':'IL':'12/19/02':'Week Back'
"""
header1 = '''\
"venue","city","state","date","performers"
'''
sample3 = '''\
05/05/03?05/05/03?05/05/03?05/05/03?05/05/03?05/05/03
05/05/03?05/05/03?05/05/03?05/05/03?05/05/03?05/05/03
05/05/03?05/05/03?05/05/03?05/05/03?05/05/03?05/05/03
'''
sample4 = '''\
2147483648;43.0e12;17;abc;def
147483648;43.0e2;17;abc;def
47483648;43.0;170;abc;def
'''
sample5 = "aaa\tbbb\r\nAAA\t\r\nBBB\t\r\n"
sample6 = "a|b|c\r\nd|e|f\r\n"
sample7 = "'a'|'b'|'c'\r\n'd'|e|f\r\n"
# Issue 18155: Use a delimiter that is a special char to regex: