forked from thepaul/cassandra-dtest
-
Notifications
You must be signed in to change notification settings - Fork 0
/
paging_test.py
971 lines (779 loc) · 38.1 KB
/
paging_test.py
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
import time
import uuid
from cassandra import ConsistencyLevel as CL
from cassandra import InvalidRequest
from cassandra.query import SimpleStatement, dict_factory
from dtest import Tester, run_scenarios
from tools import since
from datahelp import create_rows, parse_data_into_dicts, flatten_into_set
class Page(object):
data = None
def __init__(self):
self.data = []
def add_row(self, row):
self.data.append(row)
class PageFetcher(object):
"""
Requests pages, handles their receipt,
and provides paged data for testing.
The first page is automatically retrieved, so an initial
call to request_one is actually getting the *second* page!
"""
pages = None
error = None
future = None
requested_pages = None
retrieved_pages = None
retrieved_empty_pages = None
def __init__(self, future):
self.pages = []
# the first page is automagically returned (eventually)
# so we'll count this as a request, but the retrieved count
# won't be incremented until it actually arrives
self.requested_pages = 1
self.retrieved_pages = 0
self.retrieved_empty_pages = 0
self.future = future
self.future.add_callbacks(
callback=self.handle_page,
errback=self.handle_error
)
# wait for the first page to arrive, otherwise we may call
# future.has_more_pages too early, since it should only be
# called after the first page is returned
self.wait(seconds=30)
def handle_page(self, rows):
# occasionally get a final blank page that is useless
if rows == []:
self.retrieved_empty_pages += 1
return
page = Page()
self.pages.append(page)
for row in rows:
page.add_row(row)
self.retrieved_pages += 1
def handle_error(self, exc):
self.error = exc
raise exc
def request_one(self):
"""
Requests the next page if there is one.
If the future is exhausted, this is a no-op.
"""
if self.future.has_more_pages:
self.future.start_fetching_next_page()
self.requested_pages += 1
self.wait()
return self
def request_all(self):
"""
Requests any remaining pages.
If the future is exhausted, this is a no-op.
"""
while self.future.has_more_pages:
self.future.start_fetching_next_page()
self.requested_pages += 1
self.wait()
return self
def wait(self, seconds=5):
"""
Blocks until all *requested* pages have been returned.
Requests are made by calling request_one and/or request_all.
Raises RuntimeError if seconds is exceeded.
"""
expiry = time.time() + seconds
while time.time() < expiry:
if self.requested_pages == (self.retrieved_pages + self.retrieved_empty_pages):
return self
raise RuntimeError("Requested pages were not delivered before timeout.")
def pagecount(self):
"""
Returns count of *retrieved* pages which were not empty.
Pages are retrieved by requesting them with request_one and/or request_all.
"""
return len(self.pages)
def num_results(self, page_num):
"""
Returns the number of results found at page_num
"""
return len(self.pages[page_num - 1].data)
def num_results_all(self):
return [len(page.data) for page in self.pages]
def page_data(self, page_num):
"""
Returns retreived data found at pagenum.
The page should have already been requested with request_one and/or request_all.
"""
return self.pages[page_num - 1].data
def all_data(self):
"""
Returns all retrieved data flattened into a single list (instead of separated into Page objects).
The page(s) should have already been requested with request_one and/or request_all.
"""
all_pages_combined = []
for page in self.pages:
all_pages_combined.extend(page.data[:])
return all_pages_combined
@property # make property to match python driver api
def has_more_pages(self):
"""
Returns bool indicating if there are any pages not retrieved.
"""
return self.future.has_more_pages
class PageAssertionMixin(object):
"""Can be added to subclasses of unittest.Tester"""
def assertEqualIgnoreOrder(self, actual, expected):
return self.assertItemsEqual(actual, expected)
def assertIsSubsetOf(self, subset, superset):
assert flatten_into_set(subset).issubset(flatten_into_set(superset))
class BasePagingTester(Tester):
def prepare(self):
cluster = self.cluster
cluster.populate(3).start()
node1, node2, node3 = cluster.nodelist()
cursor = self.cql_connection(node1)
cursor.row_factory = dict_factory
return cursor
@since('2.0')
class TestPagingSize(BasePagingTester, PageAssertionMixin):
"""
Basic tests relating to page size (relative to results set)
and validation of page size setting.
"""
def test_with_no_results(self):
"""
No errors when a page is requested and query has no results.
"""
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int PRIMARY KEY, value text )")
# run a query that has no results and make sure it's exhausted
future = cursor.execute_async(
SimpleStatement("select * from paging_test", fetch_size=100, consistency_level=CL.ALL)
)
pf = PageFetcher(future)
pf.request_all()
self.assertEqual([], pf.all_data())
self.assertFalse(pf.has_more_pages)
def test_with_less_results_than_page_size(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int PRIMARY KEY, value text )")
data = """
|id| value |
|1 |testing |
|2 |and more testing|
|3 |and more testing|
|4 |and more testing|
|5 |and more testing|
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': unicode})
future = cursor.execute_async(
SimpleStatement("select * from paging_test", fetch_size=100, consistency_level=CL.ALL)
)
pf = PageFetcher(future)
pf.request_all()
self.assertFalse(pf.has_more_pages)
self.assertEqual(len(expected_data), len(pf.all_data()))
def test_with_more_results_than_page_size(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int PRIMARY KEY, value text )")
data = """
|id| value |
|1 |testing |
|2 |and more testing|
|3 |and more testing|
|4 |and more testing|
|5 |and more testing|
|6 |testing |
|7 |and more testing|
|8 |and more testing|
|9 |and more testing|
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': unicode})
future = cursor.execute_async(
SimpleStatement("select * from paging_test", fetch_size=5, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.pagecount(), 2)
self.assertEqual(pf.num_results_all(), [5, 4])
# make sure expected and actual have same data elements (ignoring order)
self.assertEqualIgnoreOrder(pf.all_data(), expected_data)
def test_with_equal_results_to_page_size(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int PRIMARY KEY, value text )")
data = """
|id| value |
|1 |testing |
|2 |and more testing|
|3 |and more testing|
|4 |and more testing|
|5 |and more testing|
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': unicode})
future = cursor.execute_async(
SimpleStatement("select * from paging_test", fetch_size=5, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.num_results_all(), [5])
self.assertEqual(pf.pagecount(), 1)
# make sure expected and actual have same data elements (ignoring order)
self.assertEqualIgnoreOrder(pf.all_data(), expected_data)
def test_undefined_page_size_default(self):
"""
If the page size isn't sent then the default fetch size is used.
"""
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id uuid PRIMARY KEY, value text )")
def random_txt(text):
return uuid.uuid4()
data = """
| id |value |
*5001| [uuid] |testing |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': random_txt, 'value': unicode})
future = cursor.execute_async(
SimpleStatement("select * from paging_test", consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.num_results_all(), [5000, 1])
# make sure expected and actual have same data elements (ignoring order)
self.assertEqualIgnoreOrder(pf.all_data(), expected_data)
@since('2.0')
class TestPagingWithModifiers(BasePagingTester, PageAssertionMixin):
"""
Tests concerned with paging when CQL modifiers (such as order, limit, allow filtering) are used.
"""
def test_with_order_by(self):
""""
Paging over a single partition with ordering should work.
(Spanning multiple partitions won't though, by design. See CASSANDRA-6722).
"""
cursor = self.prepare()
self.create_ks(cursor, 'test_paging', 2)
cursor.execute(
"""
CREATE TABLE paging_test (
id int,
value text,
PRIMARY KEY (id, value)
) WITH CLUSTERING ORDER BY (value ASC)
""")
data = """
|id|value|
|1 |a |
|1 |b |
|1 |c |
|1 |d |
|1 |e |
|1 |f |
|1 |g |
|1 |h |
|1 |i |
|1 |j |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': unicode})
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id = 1 order by value asc", fetch_size=5, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.pagecount(), 2)
self.assertEqual(pf.num_results_all(), [5, 5])
# these should be equal (in the same order)
self.assertEqual(pf.all_data(), expected_data)
# make sure we don't allow paging over multiple partitions with order because that's weird
with self.assertRaisesRegexp(InvalidRequest, 'Cannot page queries with both ORDER BY and a IN restriction on the partition key'):
stmt = SimpleStatement("select * from paging_test where id in (1,2) order by value asc", consistency_level=CL.ALL)
cursor.execute(stmt)
def test_with_order_by_reversed(self):
""""
Paging over a single partition with ordering and a reversed clustering order.
"""
cursor = self.prepare()
self.create_ks(cursor, 'test_paging', 2)
cursor.execute(
"""
CREATE TABLE paging_test (
id int,
value text,
value2 text,
PRIMARY KEY (id, value)
) WITH CLUSTERING ORDER BY (value DESC)
""")
data = """
|id|value|value2|
|1 |a |a |
|1 |b |b |
|1 |c |c |
|1 |d |d |
|1 |e |e |
|1 |f |f |
|1 |g |g |
|1 |h |h |
|1 |i |i |
|1 |j |j |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': unicode, 'value2': unicode})
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id = 1 order by value asc", fetch_size=3, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.pagecount(), 4)
self.assertEqual(pf.num_results_all(), [3, 3, 3, 1])
# these should be equal (in the same order)
self.assertEqual(pf.all_data(), expected_data)
# drop the ORDER BY
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id = 1", fetch_size=3, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.pagecount(), 4)
self.assertEqual(pf.num_results_all(), [3, 3, 3, 1])
# these should be equal (in the same order)
self.assertEqual(pf.all_data(), list(reversed(expected_data)))
def test_with_limit(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, value text, PRIMARY KEY (id, value) )")
def random_txt(text):
return unicode(uuid.uuid4())
data = """
| id | value |
*5| 1 | [random text] |
*5| 2 | [random text] |
*10| 3 | [random text] |
*10| 4 | [random text] |
*20| 5 | [random text] |
*30| 6 | [random text] |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': random_txt})
scenarios = [
# using equals clause w/single partition
{'limit': 10, 'fetch': 20, 'data_size': 30, 'whereclause': 'WHERE id = 6', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # limit < fetch < data
{'limit': 10, 'fetch': 30, 'data_size': 20, 'whereclause': 'WHERE id = 5', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # limit < data < fetch
{'limit': 20, 'fetch': 10, 'data_size': 30, 'whereclause': 'WHERE id = 6', 'expect_pgcount': 2, 'expect_pgsizes': [10, 10]}, # fetch < limit < data
{'limit': 30, 'fetch': 10, 'data_size': 20, 'whereclause': 'WHERE id = 5', 'expect_pgcount': 2, 'expect_pgsizes': [10, 10]}, # fetch < data < limit
{'limit': 20, 'fetch': 30, 'data_size': 10, 'whereclause': 'WHERE id = 3', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # data < limit < fetch
{'limit': 30, 'fetch': 20, 'data_size': 10, 'whereclause': 'WHERE id = 3', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # data < fetch < limit
# using 'in' clause w/multi partitions
{'limit': 9, 'fetch': 20, 'data_size': 80, 'whereclause': 'WHERE id in (1,2,3,4,5,6)', 'expect_pgcount': 1, 'expect_pgsizes': [9]}, # limit < fetch < data
{'limit': 10, 'fetch': 30, 'data_size': 20, 'whereclause': 'WHERE id in (3,4)', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # limit < data < fetch
{'limit': 20, 'fetch': 10, 'data_size': 30, 'whereclause': 'WHERE id in (4,5)', 'expect_pgcount': 2, 'expect_pgsizes': [10, 10]}, # fetch < limit < data
{'limit': 30, 'fetch': 10, 'data_size': 20, 'whereclause': 'WHERE id in (3,4)', 'expect_pgcount': 2, 'expect_pgsizes': [10, 10]}, # fetch < data < limit
{'limit': 20, 'fetch': 30, 'data_size': 10, 'whereclause': 'WHERE id in (1,2)', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # data < limit < fetch
{'limit': 30, 'fetch': 20, 'data_size': 10, 'whereclause': 'WHERE id in (1,2)', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # data < fetch < limit
# no limit but with a defined pagesize. Scenarios added for CASSANDRA-8408.
{'limit': None, 'fetch': 20, 'data_size': 80, 'whereclause': 'WHERE id in (1,2,3,4,5,6)', 'expect_pgcount': 4, 'expect_pgsizes': [20, 20, 20, 20]}, # fetch < data
{'limit': None, 'fetch': 30, 'data_size': 20, 'whereclause': 'WHERE id in (3,4)', 'expect_pgcount': 1, 'expect_pgsizes': [20]}, # data < fetch
{'limit': None, 'fetch': 10, 'data_size': 30, 'whereclause': 'WHERE id in (4,5)', 'expect_pgcount': 3, 'expect_pgsizes': [10, 10, 10]}, # fetch < data
{'limit': None, 'fetch': 30, 'data_size': 10, 'whereclause': 'WHERE id in (1,2)', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # data < fetch
# not setting fetch_size (unpaged) but using limit. Scenarios added for CASSANDRA-8408.
{'limit': 9, 'fetch': None, 'data_size': 80, 'whereclause': 'WHERE id in (1,2,3,4,5,6)', 'expect_pgcount': 1, 'expect_pgsizes': [9]}, # limit < data
{'limit': 30, 'fetch': None, 'data_size': 10, 'whereclause': 'WHERE id in (1,2)', 'expect_pgcount': 1, 'expect_pgsizes': [10]}, # data < limit
]
def handle_scenario(scenario):
# using a limit and a fetch
if scenario['limit'] and scenario['fetch']:
future = cursor.execute_async(
SimpleStatement(
"select * from paging_test {} limit {}".format(scenario['whereclause'], scenario['limit']),
fetch_size=scenario['fetch'], consistency_level=CL.ALL)
)
# using a limit but not specifying a fetch_size
elif scenario['limit'] and scenario['fetch'] is None:
future = cursor.execute_async(
SimpleStatement(
"select * from paging_test {} limit {}".format(scenario['whereclause'], scenario['limit']),
consistency_level=CL.ALL)
)
# no limit but a fetch_size specified
elif scenario['limit'] is None and scenario['fetch']:
future = cursor.execute_async(
SimpleStatement(
"select * from paging_test {}".format(scenario['whereclause']),
fetch_size=scenario['fetch'], consistency_level=CL.ALL)
)
else:
# this should not happen
assert False
pf = PageFetcher(future).request_all()
self.assertEqual(pf.num_results_all(), scenario['expect_pgsizes'])
self.assertEqual(pf.pagecount(), scenario['expect_pgcount'])
# make sure all the data retrieved is a subset of input data
self.assertIsSubsetOf(pf.all_data(), expected_data)
run_scenarios(scenarios, handle_scenario, deferred_exceptions=(AssertionError,))
def test_with_allow_filtering(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, value text, PRIMARY KEY (id, value) )")
data = """
|id|value |
|1 |testing |
|2 |and more testing|
|3 |and more testing|
|4 |and more testing|
|5 |and more testing|
|6 |testing |
|7 |and more testing|
|8 |and more testing|
|9 |and more testing|
"""
create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': unicode})
future = cursor.execute_async(
SimpleStatement("select * from paging_test where value = 'and more testing' ALLOW FILTERING", fetch_size=4, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.pagecount(), 2)
self.assertEqual(pf.num_results_all(), [4, 3])
# make sure the allow filtering query matches the expected results (ignoring order)
self.assertEqualIgnoreOrder(
pf.all_data(),
parse_data_into_dicts(
"""
|id|value |
|2 |and more testing|
|3 |and more testing|
|4 |and more testing|
|5 |and more testing|
|7 |and more testing|
|8 |and more testing|
|9 |and more testing|
""", format_funcs={'id': int, 'value': unicode}
)
)
@since('2.0')
class TestPagingData(BasePagingTester, PageAssertionMixin):
def test_paging_a_single_wide_row(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, value text, PRIMARY KEY (id, value) )")
def random_txt(text):
return unicode(uuid.uuid4())
data = """
| id | value |
*10000| 1 | [replaced with random] |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': random_txt})
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id = 1", fetch_size=3000, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.pagecount(), 4)
self.assertEqual(pf.num_results_all(), [3000, 3000, 3000, 1000])
self.assertEqualIgnoreOrder(pf.all_data(), expected_data)
def test_paging_across_multi_wide_rows(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, value text, PRIMARY KEY (id, value) )")
def random_txt(text):
return unicode(uuid.uuid4())
data = """
| id | value |
*5000| 1 | [replaced with random] |
*5000| 2 | [replaced with random] |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'value': random_txt})
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id in (1,2)", fetch_size=3000, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
self.assertEqual(pf.pagecount(), 4)
self.assertEqual(pf.num_results_all(), [3000, 3000, 3000, 1000])
self.assertEqualIgnoreOrder(pf.all_data(), expected_data)
def test_paging_using_secondary_indexes(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, mybool boolean, sometext text, PRIMARY KEY (id, sometext) )")
cursor.execute("CREATE INDEX ON paging_test(mybool)")
def random_txt(text):
return unicode(uuid.uuid4())
def bool_from_str_int(text):
return bool(int(text))
data = """
| id | mybool| sometext |
*100| 1 | 1 | [random] |
*300| 2 | 0 | [random] |
*500| 3 | 1 | [random] |
*400| 4 | 0 | [random] |
"""
all_data = create_rows(
data, cursor, 'paging_test', cl=CL.ALL,
format_funcs={'id': int, 'mybool': bool_from_str_int, 'sometext': random_txt}
)
future = cursor.execute_async(
SimpleStatement("select * from paging_test where mybool = true", fetch_size=400, consistency_level=CL.ALL)
)
pf = PageFetcher(future).request_all()
# the query only searched for True rows, so let's pare down the expectations for comparison
expected_data = filter(lambda x: x.get('mybool') is True, all_data)
self.assertEqual(pf.pagecount(), 2)
self.assertEqual(pf.num_results_all(), [400, 200])
self.assertEqualIgnoreOrder(expected_data, pf.all_data())
@since('2.0')
class TestPagingDatasetChanges(BasePagingTester, PageAssertionMixin):
"""
Tests concerned with paging when the queried dataset changes while pages are being retrieved.
"""
def test_data_change_impacting_earlier_page(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, mytext text, PRIMARY KEY (id, mytext) )")
def random_txt(text):
return unicode(uuid.uuid4())
data = """
| id | mytext |
*500| 1 | [random] |
*500| 2 | [random] |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'mytext': random_txt})
# get 501 rows so we have definitely got the 1st row of the second partition
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id in (1,2)", fetch_size=501, consistency_level=CL.ALL)
)
pf = PageFetcher(future)
# no need to request page here, because the first page is automatically retrieved
# we got one page and should be done with the first partition (for id=1)
# let's add another row for that first partition (id=1) and make sure it won't sneak into results
cursor.execute(SimpleStatement("insert into paging_test (id, mytext) values (1, 'foo')", consistency_level=CL.ALL))
pf.request_all()
self.assertEqual(pf.pagecount(), 2)
self.assertEqual(pf.num_results_all(), [501, 499])
self.assertEqualIgnoreOrder(pf.all_data(), expected_data)
def test_data_change_impacting_later_page(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, mytext text, PRIMARY KEY (id, mytext) )")
def random_txt(text):
return unicode(uuid.uuid4())
data = """
| id | mytext |
*500| 1 | [random] |
*499| 2 | [random] |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'mytext': random_txt})
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id in (1,2)", fetch_size=500, consistency_level=CL.ALL)
)
pf = PageFetcher(future)
# no need to request page here, because the first page is automatically retrieved
# we've already paged the first partition, but adding a row for the second (id=2)
# should still result in the row being seen on the subsequent pages
cursor.execute(SimpleStatement("insert into paging_test (id, mytext) values (2, 'foo')", consistency_level=CL.ALL))
pf.request_all()
self.assertEqual(pf.pagecount(), 2)
self.assertEqual(pf.num_results_all(), [500, 500])
# add the new row to the expected data and then do a compare
expected_data.append({u'id': 2, u'mytext': u'foo'})
self.assertEqualIgnoreOrder(pf.all_data(), expected_data)
def test_data_delete_removing_remainder(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, mytext text, PRIMARY KEY (id, mytext) )")
def random_txt(text):
return unicode(uuid.uuid4())
data = """
| id | mytext |
*500| 1 | [random] |
*500| 2 | [random] |
"""
create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'mytext': random_txt})
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id in (1,2)", fetch_size=500, consistency_level=CL.ALL)
)
pf = PageFetcher(future)
# no need to request page here, because the first page is automatically retrieved
# delete the results that would have shown up on page 2
cursor.execute(SimpleStatement("delete from paging_test where id = 2", consistency_level=CL.ALL))
pf.request_all()
self.assertEqual(pf.pagecount(), 1)
self.assertEqual(pf.num_results_all(), [500])
def test_row_TTL_expiry_during_paging(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, mytext text, PRIMARY KEY (id, mytext) )")
def random_txt(text):
return unicode(uuid.uuid4())
# create rows with TTL (some of which we'll try to get after expiry)
create_rows(
"""
| id | mytext |
*300| 1 | [random] |
*400| 2 | [random] |
""",
cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'mytext': random_txt}, postfix='USING TTL 10'
)
# create rows without TTL
create_rows(
"""
| id | mytext |
*500| 3 | [random] |
""",
cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'mytext': random_txt}
)
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id in (1,2,3)", fetch_size=300, consistency_level=CL.ALL)
)
pf = PageFetcher(future)
# no need to request page here, because the first page is automatically retrieved
# this page will be partition id=1, it has TTL rows but they are not expired yet
# sleep so that the remaining TTL rows from partition id=2 expire
time.sleep(15)
pf.request_all()
self.assertEqual(pf.pagecount(), 3)
self.assertEqual(pf.num_results_all(), [300, 300, 200])
def test_cell_TTL_expiry_during_paging(self):
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("""
CREATE TABLE paging_test (
id int,
mytext text,
somevalue text,
anothervalue text,
PRIMARY KEY (id, mytext) )
""")
def random_txt(text):
return unicode(uuid.uuid4())
data = create_rows(
"""
| id | mytext | somevalue | anothervalue |
*500| 1 | [random] | foo | bar |
*500| 2 | [random] | foo | bar |
*500| 3 | [random] | foo | bar |
""",
cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'mytext': random_txt}
)
future = cursor.execute_async(
SimpleStatement("select * from paging_test where id in (1,2,3)", fetch_size=500, consistency_level=CL.ALL)
)
pf = PageFetcher(future)
# no need to request page here, because the first page is automatically retrieved
page1 = pf.page_data(1)
self.assertEqualIgnoreOrder(page1, data[:500])
# set some TTLs for data on page 3
for row in data[1000:1500]:
_id, mytext = row['id'], row['mytext']
stmt = SimpleStatement("""
update paging_test using TTL 10
set somevalue='one', anothervalue='two' where id = {id} and mytext = '{mytext}'
""".format(id=_id, mytext=mytext),
consistency_level=CL.ALL
)
cursor.execute(stmt)
# check page two
pf.request_one()
page2 = pf.page_data(2)
self.assertEqualIgnoreOrder(page2, data[500:1000])
page3expected = []
for row in data[1000:1500]:
_id, mytext = row['id'], row['mytext']
page3expected.append(
{u'id': _id, u'mytext': mytext, u'somevalue': None, u'anothervalue': None}
)
time.sleep(15)
pf.request_one()
page3 = pf.page_data(3)
self.assertEqualIgnoreOrder(page3, page3expected)
def test_node_unavailabe_during_paging(self):
cluster = self.cluster
cluster.populate(3).start()
node1, node2, node3 = cluster.nodelist()
cursor = self.cql_connection(node1)
self.create_ks(cursor, 'test_paging_size', 1)
cursor.execute("CREATE TABLE paging_test ( id uuid, mytext text, PRIMARY KEY (id, mytext) )")
def make_uuid(text):
return uuid.uuid4()
create_rows(
"""
| id | mytext |
*10000| [uuid] | foo |
""",
cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': make_uuid}
)
future = cursor.execute_async(
SimpleStatement("select * from paging_test where mytext = 'foo' allow filtering", fetch_size=2000, consistency_level=CL.ALL)
)
pf = PageFetcher(future)
# no need to request page here, because the first page is automatically retrieved
# stop a node and make sure we get an error trying to page the rest
node1.stop()
with self.assertRaisesRegexp(RuntimeError, 'Requested pages were not delivered before timeout'):
pf.request_all()
# TODO: can we resume the node and expect to get more results from the result set or is it done?
@since('2.0')
class TestPagingQueryIsolation(BasePagingTester, PageAssertionMixin):
"""
Tests concerned with isolation of paged queries (queries can't affect each other).
"""
def test_query_isolation(self):
"""
Interleave some paged queries and make sure nothing bad happens.
"""
cursor = self.prepare()
self.create_ks(cursor, 'test_paging_size', 2)
cursor.execute("CREATE TABLE paging_test ( id int, mytext text, PRIMARY KEY (id, mytext) )")
def random_txt(text):
return unicode(uuid.uuid4())
data = """
| id | mytext |
*5000| 1 | [random] |
*5000| 2 | [random] |
*5000| 3 | [random] |
*5000| 4 | [random] |
*5000| 5 | [random] |
*5000| 6 | [random] |
*5000| 7 | [random] |
*5000| 8 | [random] |
*5000| 9 | [random] |
*5000| 10 | [random] |
"""
expected_data = create_rows(data, cursor, 'paging_test', cl=CL.ALL, format_funcs={'id': int, 'mytext': random_txt})
stmts = [
SimpleStatement("select * from paging_test where id in (1)", fetch_size=500, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (2)", fetch_size=600, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (3)", fetch_size=700, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (4)", fetch_size=800, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (5)", fetch_size=900, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (1)", fetch_size=1000, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (2)", fetch_size=1100, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (3)", fetch_size=1200, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (4)", fetch_size=1300, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (5)", fetch_size=1400, consistency_level=CL.ALL),
SimpleStatement("select * from paging_test where id in (1,2,3,4,5,6,7,8,9,10)", fetch_size=1500, consistency_level=CL.ALL)
]
page_fetchers = []
for stmt in stmts:
future = cursor.execute_async(stmt)
page_fetchers.append(PageFetcher(future))
# first page is auto-retrieved, so no need to request it
for pf in page_fetchers:
pf.request_one()
for pf in page_fetchers:
pf.request_one()
for pf in page_fetchers:
pf.request_all()
self.assertEqual(page_fetchers[0].pagecount(), 10)
self.assertEqual(page_fetchers[1].pagecount(), 9)
self.assertEqual(page_fetchers[2].pagecount(), 8)
self.assertEqual(page_fetchers[3].pagecount(), 7)
self.assertEqual(page_fetchers[4].pagecount(), 6)
self.assertEqual(page_fetchers[5].pagecount(), 5)
self.assertEqual(page_fetchers[6].pagecount(), 5)
self.assertEqual(page_fetchers[7].pagecount(), 5)
self.assertEqual(page_fetchers[8].pagecount(), 4)
self.assertEqual(page_fetchers[9].pagecount(), 4)
self.assertEqual(page_fetchers[10].pagecount(), 34)
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[0].all_data()), flatten_into_set(expected_data[:5000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[1].all_data()), flatten_into_set(expected_data[5000:10000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[2].all_data()), flatten_into_set(expected_data[10000:15000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[3].all_data()), flatten_into_set(expected_data[15000:20000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[4].all_data()), flatten_into_set(expected_data[20000:25000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[5].all_data()), flatten_into_set(expected_data[:5000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[6].all_data()), flatten_into_set(expected_data[5000:10000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[7].all_data()), flatten_into_set(expected_data[10000:15000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[8].all_data()), flatten_into_set(expected_data[15000:20000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[9].all_data()), flatten_into_set(expected_data[20000:25000]))
self.assertEqualIgnoreOrder(flatten_into_set(page_fetchers[10].all_data()), flatten_into_set(expected_data[:50000]))