Repository navigation
Expand file tree
/
Copy pathsnippets.py
More file actions
1191 lines (989 loc) · 42.6 KB
/
Copy pathsnippets.py
File metadata and controls
1191 lines (989 loc) · 42.6 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 2016 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Testable usage examples for Google BigQuery API wrapper
Each example function takes a ``client`` argument (which must be an instance
of :class:`google.cloud.bigquery.client.Client`) and uses it to perform a task
with the API.
To facilitate running the examples as system tests, each example is also passed
a ``to_delete`` list; the function adds to the list any objects created which
need to be deleted during teardown.
"""
import os
import time
import pytest
import six
try:
import fastparquet
except (ImportError, AttributeError):
fastparquet = None
try:
import pandas
except (ImportError, AttributeError):
pandas = None
try:
import pyarrow
except (ImportError, AttributeError):
pyarrow = None
from google.api_core.exceptions import InternalServerError
from google.api_core.exceptions import ServiceUnavailable
from google.api_core.exceptions import TooManyRequests
from google.cloud import bigquery
from google.cloud import storage
from test_utils.retry import RetryErrors
ORIGINAL_FRIENDLY_NAME = "Original friendly name"
ORIGINAL_DESCRIPTION = "Original description"
LOCALLY_CHANGED_FRIENDLY_NAME = "Locally-changed friendly name"
LOCALLY_CHANGED_DESCRIPTION = "Locally-changed description"
UPDATED_FRIENDLY_NAME = "Updated friendly name"
UPDATED_DESCRIPTION = "Updated description"
SCHEMA = [
bigquery.SchemaField("full_name", "STRING", mode="REQUIRED"),
bigquery.SchemaField("age", "INTEGER", mode="REQUIRED"),
]
ROWS = [
("Phred Phlyntstone", 32),
("Bharney Rhubble", 33),
("Wylma Phlyntstone", 29),
("Bhettye Rhubble", 27),
]
QUERY = (
"SELECT name FROM `bigquery-public-data.usa_names.usa_1910_2013` "
'WHERE state = "TX"'
)
retry_429 = RetryErrors(TooManyRequests)
retry_storage_errors = RetryErrors(
(TooManyRequests, InternalServerError, ServiceUnavailable)
)
@pytest.fixture(scope="module")
def client():
return bigquery.Client()
@pytest.fixture
def to_delete(client):
doomed = []
yield doomed
for item in doomed:
if isinstance(item, (bigquery.Dataset, bigquery.DatasetReference)):
retry_429(client.delete_dataset)(item, delete_contents=True)
elif isinstance(item, storage.Bucket):
retry_storage_errors(item.delete)()
else:
retry_429(item.delete)()
def _millis():
return int(time.time() * 1000)
class _CloseOnDelete(object):
def __init__(self, wrapped):
self._wrapped = wrapped
def delete(self):
self._wrapped.close()
def test_create_client_default_credentials():
"""Create a BigQuery client with Application Default Credentials"""
# [START bigquery_client_default_credentials]
from google.cloud import bigquery
# If you don't specify credentials when constructing the client, the
# client library will look for credentials in the environment.
client = bigquery.Client()
# [END bigquery_client_default_credentials]
assert client is not None
def test_create_table_nested_repeated_schema(client, to_delete):
dataset_id = "create_table_nested_repeated_{}".format(_millis())
dataset_ref = client.dataset(dataset_id)
dataset = bigquery.Dataset(dataset_ref)
client.create_dataset(dataset)
to_delete.append(dataset)
# [START bigquery_nested_repeated_schema]
# from google.cloud import bigquery
# client = bigquery.Client()
# dataset_ref = client.dataset('my_dataset')
schema = [
bigquery.SchemaField("id", "STRING", mode="NULLABLE"),
bigquery.SchemaField("first_name", "STRING", mode="NULLABLE"),
bigquery.SchemaField("last_name", "STRING", mode="NULLABLE"),
bigquery.SchemaField("dob", "DATE", mode="NULLABLE"),
bigquery.SchemaField(
"addresses",
"RECORD",
mode="REPEATED",
fields=[
bigquery.SchemaField("status", "STRING", mode="NULLABLE"),
bigquery.SchemaField("address", "STRING", mode="NULLABLE"),
bigquery.SchemaField("city", "STRING", mode="NULLABLE"),
bigquery.SchemaField("state", "STRING", mode="NULLABLE"),
bigquery.SchemaField("zip", "STRING", mode="NULLABLE"),
bigquery.SchemaField("numberOfYears", "STRING", mode="NULLABLE"),
],
),
]
table_ref = dataset_ref.table("my_table")
table = bigquery.Table(table_ref, schema=schema)
table = client.create_table(table) # API request
print("Created table {}".format(table.full_table_id))
# [END bigquery_nested_repeated_schema]
def test_create_table_cmek(client, to_delete):
dataset_id = "create_table_cmek_{}".format(_millis())
dataset = bigquery.Dataset(client.dataset(dataset_id))
client.create_dataset(dataset)
to_delete.append(dataset)
# [START bigquery_create_table_cmek]
# from google.cloud import bigquery
# client = bigquery.Client()
# dataset_id = 'my_dataset'
table_ref = client.dataset(dataset_id).table("my_table")
table = bigquery.Table(table_ref)
# Set the encryption key to use for the table.
# TODO: Replace this key with a key you have created in Cloud KMS.
kms_key_name = "projects/{}/locations/{}/keyRings/{}/cryptoKeys/{}".format(
"cloud-samples-tests", "us", "test", "test"
)
table.encryption_configuration = bigquery.EncryptionConfiguration(
kms_key_name=kms_key_name
)
table = client.create_table(table) # API request
assert table.encryption_configuration.kms_key_name == kms_key_name
# [END bigquery_create_table_cmek]
def test_create_partitioned_table(client, to_delete):
dataset_id = "create_table_partitioned_{}".format(_millis())
dataset_ref = bigquery.Dataset(client.dataset(dataset_id))
dataset = client.create_dataset(dataset_ref)
to_delete.append(dataset)
# [START bigquery_create_table_partitioned]
# from google.cloud import bigquery
# client = bigquery.Client()
# dataset_ref = client.dataset('my_dataset')
table_ref = dataset_ref.table("my_partitioned_table")
schema = [
bigquery.SchemaField("name", "STRING"),
bigquery.SchemaField("post_abbr", "STRING"),
bigquery.SchemaField("date", "DATE"),
]
table = bigquery.Table(table_ref, schema=schema)
table.time_partitioning = bigquery.TimePartitioning(
type_=bigquery.TimePartitioningType.DAY,
field="date", # name of column to use for partitioning
expiration_ms=7776000000,
) # 90 days
table = client.create_table(table)
print(
"Created table {}, partitioned on column {}".format(
table.table_id, table.time_partitioning.field
)
)
# [END bigquery_create_table_partitioned]
assert table.time_partitioning.type_ == "DAY"
assert table.time_partitioning.field == "date"
assert table.time_partitioning.expiration_ms == 7776000000
@pytest.mark.skip(
reason=(
"update_table() is flaky "
"https://github.com/GoogleCloudPlatform/google-cloud-python/issues/5589"
)
)
def test_manage_table_labels(client, to_delete):
dataset_id = "label_table_dataset_{}".format(_millis())
table_id = "label_table_{}".format(_millis())
dataset = bigquery.Dataset(client.dataset(dataset_id))
client.create_dataset(dataset)
to_delete.append(dataset)
table = bigquery.Table(dataset.table(table_id), schema=SCHEMA)
table = client.create_table(table)
# [START bigquery_label_table]
# from google.cloud import bigquery
# client = bigquery.Client()
# table_ref = client.dataset('my_dataset').table('my_table')
# table = client.get_table(table_ref) # API request
assert table.labels == {}
labels = {"color": "green"}
table.labels = labels
table = client.update_table(table, ["labels"]) # API request
assert table.labels == labels
# [END bigquery_label_table]
# [START bigquery_get_table_labels]
# from google.cloud import bigquery
# client = bigquery.Client()
# dataset_id = 'my_dataset'
# table_id = 'my_table'
dataset_ref = client.dataset(dataset_id)
table_ref = dataset_ref.table(table_id)
table = client.get_table(table_ref) # API Request
# View table labels
print("Table ID: {}".format(table_id))
print("Labels:")
if table.labels:
for label, value in table.labels.items():
print("\t{}: {}".format(label, value))
else:
print("\tTable has no labels defined.")
# [END bigquery_get_table_labels]
assert table.labels == labels
# [START bigquery_delete_label_table]
# from google.cloud import bigquery
# client = bigquery.Client()
# table_ref = client.dataset('my_dataset').table('my_table')
# table = client.get_table(table_ref) # API request
# This example table starts with one label
assert table.labels == {"color": "green"}
# To delete a label from a table, set its value to None
table.labels["color"] = None
table = client.update_table(table, ["labels"]) # API request
assert table.labels == {}
# [END bigquery_delete_label_table]
@pytest.mark.skip(
reason=(
"update_table() is flaky "
"https://github.com/GoogleCloudPlatform/google-cloud-python/issues/5589"
)
)
def test_update_table_description(client, to_delete):
"""Update a table's description."""
dataset_id = "update_table_description_dataset_{}".format(_millis())
table_id = "update_table_description_table_{}".format(_millis())
dataset = bigquery.Dataset(client.dataset(dataset_id))
client.create_dataset(dataset)
to_delete.append(dataset)
table = bigquery.Table(dataset.table(table_id), schema=SCHEMA)
table.description = "Original description."
table = client.create_table(table)
# [START bigquery_update_table_description]
# from google.cloud import bigquery
# client = bigquery.Client()
# table_ref = client.dataset('my_dataset').table('my_table')
# table = client.get_table(table_ref) # API request
assert table.description == "Original description."
table.description = "Updated description."
table = client.update_table(table, ["description"]) # API request
assert table.description == "Updated description."
# [END bigquery_update_table_description]
@pytest.mark.skip(
reason=(
"update_table() is flaky "
"https://github.com/GoogleCloudPlatform/google-cloud-python/issues/5589"
)
)
def test_update_table_expiration(client, to_delete):
"""Update a table's expiration time."""
dataset_id = "update_table_expiration_dataset_{}".format(_millis())
table_id = "update_table_expiration_table_{}".format(_millis())
dataset = bigquery.Dataset(client.dataset(dataset_id))
client.create_dataset(dataset)
to_delete.append(dataset)
table = bigquery.Table(dataset.table(table_id), schema=SCHEMA)
table = client.create_table(table)
# [START bigquery_update_table_expiration]
import datetime
import pytz
# from google.cloud import bigquery
# client = bigquery.Client()
# table_ref = client.dataset('my_dataset').table('my_table')
# table = client.get_table(table_ref) # API request
assert table.expires is None
# set table to expire 5 days from now
expiration = datetime.datetime.now(pytz.utc) + datetime.timedelta(days=5)
table.expires = expiration
table = client.update_table(table, ["expires"]) # API request
# expiration is stored in milliseconds
margin = datetime.timedelta(microseconds=1000)
assert expiration - margin <= table.expires <= expiration + margin
# [END bigquery_update_table_expiration]
@pytest.mark.skip(
reason=(
"update_table() is flaky "
"https://github.com/GoogleCloudPlatform/google-cloud-python/issues/5589"
)
)
def test_relax_column(client, to_delete):
"""Updates a schema field from required to nullable."""
dataset_id = "relax_column_dataset_{}".format(_millis())
table_id = "relax_column_table_{}".format(_millis())
dataset = bigquery.Dataset(client.dataset(dataset_id))
dataset = client.create_dataset(dataset)
to_delete.append(dataset)
# [START bigquery_relax_column]
# from google.cloud import bigquery
# client = bigquery.Client()
# dataset_id = 'my_dataset'
# table_id = 'my_table'
original_schema = [
bigquery.SchemaField("full_name", "STRING", mode="REQUIRED"),
bigquery.SchemaField("age", "INTEGER", mode="REQUIRED"),
]
table_ref = client.dataset(dataset_id).table(table_id)
table = bigquery.Table(table_ref, schema=original_schema)
table = client.create_table(table)
assert all(field.mode == "REQUIRED" for field in table.schema)
# SchemaField properties cannot be edited after initialization.
# To make changes, construct new SchemaField objects.
relaxed_schema = [
bigquery.SchemaField("full_name", "STRING", mode="NULLABLE"),
bigquery.SchemaField("age", "INTEGER", mode="NULLABLE"),
]
table.schema = relaxed_schema
table = client.update_table(table, ["schema"])
assert all(field.mode == "NULLABLE" for field in table.schema)
# [END bigquery_relax_column]
@pytest.mark.skip(
reason=(
"update_table() is flaky "
"https://github.com/GoogleCloudPlatform/google-cloud-python/issues/5589"
)
)
def test_update_table_cmek(client, to_delete):
"""Patch a table's metadata."""
dataset_id = "update_table_cmek_{}".format(_millis())
table_id = "update_table_cmek_{}".format(_millis())
dataset = bigquery.Dataset(client.dataset(dataset_id))
client.create_dataset(dataset)
to_delete.append(dataset)
table = bigquery.Table(dataset.table(table_id))
original_kms_key_name = "projects/{}/locations/{}/keyRings/{}/cryptoKeys/{}".format(
"cloud-samples-tests", "us", "test", "test"
)
table.encryption_configuration = bigquery.EncryptionConfiguration(
kms_key_name=original_kms_key_name
)
table = client.create_table(table)
# [START bigquery_update_table_cmek]
# from google.cloud import bigquery
# client = bigquery.Client()
assert table.encryption_configuration.kms_key_name == original_kms_key_name
# Set a new encryption key to use for the destination.
# TODO: Replace this key with a key you have created in KMS.
updated_kms_key_name = (
"projects/cloud-samples-tests/locations/us/keyRings/test/cryptoKeys/otherkey"
)
table.encryption_configuration = bigquery.EncryptionConfiguration(
kms_key_name=updated_kms_key_name
)
table = client.update_table(table, ["encryption_configuration"]) # API request
assert table.encryption_configuration.kms_key_name == updated_kms_key_name
assert original_kms_key_name != updated_kms_key_name
# [END bigquery_update_table_cmek]
@pytest.mark.skip(
reason=(
"update_table() is flaky "
"https://github.com/GoogleCloudPlatform/google-cloud-python/issues/5589"
)
)
def test_manage_views(client, to_delete):
project = client.project
source_dataset_id = "source_dataset_{}".format(_millis())
source_dataset_ref = client.dataset(source_dataset_id)
source_dataset = bigquery.Dataset(source_dataset_ref)
source_dataset = client.create_dataset(source_dataset)
to_delete.append(source_dataset)
job_config = bigquery.LoadJobConfig()
job_config.schema = [
bigquery.SchemaField("name", "STRING"),
bigquery.SchemaField("post_abbr", "STRING"),
]
job_config.skip_leading_rows = 1
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.csv"
source_table_id = "us_states"
load_job = client.load_table_from_uri(
uri, source_dataset.table(source_table_id), job_config=job_config
)
load_job.result()
shared_dataset_id = "shared_dataset_{}".format(_millis())
shared_dataset_ref = client.dataset(shared_dataset_id)
shared_dataset = bigquery.Dataset(shared_dataset_ref)
shared_dataset = client.create_dataset(shared_dataset)
to_delete.append(shared_dataset)
# [START bigquery_create_view]
# from google.cloud import bigquery
# client = bigquery.Client()
# project = 'my-project'
# source_dataset_id = 'my_source_dataset'
# source_table_id = 'us_states'
# shared_dataset_ref = client.dataset('my_shared_dataset')
# This example shows how to create a shared view of a source table of
# US States. The source table contains all 50 states, while the view will
# contain only states with names starting with 'W'.
view_ref = shared_dataset_ref.table("my_shared_view")
view = bigquery.Table(view_ref)
sql_template = 'SELECT name, post_abbr FROM `{}.{}.{}` WHERE name LIKE "W%"'
view.view_query = sql_template.format(project, source_dataset_id, source_table_id)
view = client.create_table(view) # API request
print("Successfully created view at {}".format(view.full_table_id))
# [END bigquery_create_view]
# [START bigquery_update_view_query]
# from google.cloud import bigquery
# client = bigquery.Client()
# project = 'my-project'
# source_dataset_id = 'my_source_dataset'
# source_table_id = 'us_states'
# shared_dataset_ref = client.dataset('my_shared_dataset')
# This example shows how to update a shared view of a source table of
# US States. The view's query will be updated to contain only states with
# names starting with 'M'.
view_ref = shared_dataset_ref.table("my_shared_view")
view = bigquery.Table(view_ref)
sql_template = 'SELECT name, post_abbr FROM `{}.{}.{}` WHERE name LIKE "M%"'
view.view_query = sql_template.format(project, source_dataset_id, source_table_id)
view = client.update_table(view, ["view_query"]) # API request
# [END bigquery_update_view_query]
# [START bigquery_get_view]
# from google.cloud import bigquery
# client = bigquery.Client()
# shared_dataset_id = 'my_shared_dataset'
view_ref = client.dataset(shared_dataset_id).table("my_shared_view")
view = client.get_table(view_ref) # API Request
# Display view properties
print("View at {}".format(view.full_table_id))
print("View Query:\n{}".format(view.view_query))
# [END bigquery_get_view]
assert view.view_query is not None
analyst_group_email = "example-analyst-group@google.com"
# [START bigquery_grant_view_access]
# from google.cloud import bigquery
# client = bigquery.Client()
# Assign access controls to the dataset containing the view
# shared_dataset_id = 'my_shared_dataset'
# analyst_group_email = 'data_analysts@example.com'
shared_dataset = client.get_dataset(
client.dataset(shared_dataset_id)
) # API request
access_entries = shared_dataset.access_entries
access_entries.append(
bigquery.AccessEntry("READER", "groupByEmail", analyst_group_email)
)
shared_dataset.access_entries = access_entries
shared_dataset = client.update_dataset(
shared_dataset, ["access_entries"]
) # API request
# Authorize the view to access the source dataset
# project = 'my-project'
# source_dataset_id = 'my_source_dataset'
source_dataset = client.get_dataset(
client.dataset(source_dataset_id)
) # API request
view_reference = {
"projectId": project,
"datasetId": shared_dataset_id,
"tableId": "my_shared_view",
}
access_entries = source_dataset.access_entries
access_entries.append(bigquery.AccessEntry(None, "view", view_reference))
source_dataset.access_entries = access_entries
source_dataset = client.update_dataset(
source_dataset, ["access_entries"]
) # API request
# [END bigquery_grant_view_access]
def test_load_table_from_uri_autodetect(client, to_delete, capsys):
"""Load table from a GCS URI using various formats and auto-detected schema
Each file format has its own tested load from URI sample. Because most of
the code is common for autodetect, append, and truncate, this sample
includes snippets for all supported formats but only calls a single load
job.
This code snippet is made up of shared code, then format-specific code,
followed by more shared code. Note that only the last format in the
format-specific code section will be tested in this test.
"""
dataset_id = "load_table_from_uri_auto_{}".format(_millis())
dataset = bigquery.Dataset(client.dataset(dataset_id))
client.create_dataset(dataset)
to_delete.append(dataset)
# Shared code
# [START bigquery_load_table_gcs_csv_autodetect]
# [START bigquery_load_table_gcs_json_autodetect]
# from google.cloud import bigquery
# client = bigquery.Client()
# dataset_id = 'my_dataset'
dataset_ref = client.dataset(dataset_id)
job_config = bigquery.LoadJobConfig()
job_config.autodetect = True
# [END bigquery_load_table_gcs_csv_autodetect]
# [END bigquery_load_table_gcs_json_autodetect]
# Format-specific code
# [START bigquery_load_table_gcs_csv_autodetect]
job_config.skip_leading_rows = 1
# The source format defaults to CSV, so the line below is optional.
job_config.source_format = bigquery.SourceFormat.CSV
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.csv"
# [END bigquery_load_table_gcs_csv_autodetect]
# unset csv-specific attribute
del job_config._properties["load"]["skipLeadingRows"]
# [START bigquery_load_table_gcs_json_autodetect]
job_config.source_format = bigquery.SourceFormat.NEWLINE_DELIMITED_JSON
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.json"
# [END bigquery_load_table_gcs_json_autodetect]
# Shared code
# [START bigquery_load_table_gcs_csv_autodetect]
# [START bigquery_load_table_gcs_json_autodetect]
load_job = client.load_table_from_uri(
uri, dataset_ref.table("us_states"), job_config=job_config
) # API request
print("Starting job {}".format(load_job.job_id))
load_job.result() # Waits for table load to complete.
print("Job finished.")
destination_table = client.get_table(dataset_ref.table("us_states"))
print("Loaded {} rows.".format(destination_table.num_rows))
# [END bigquery_load_table_gcs_csv_autodetect]
# [END bigquery_load_table_gcs_json_autodetect]
out, _ = capsys.readouterr()
assert "Loaded 50 rows." in out
def test_load_table_from_uri_truncate(client, to_delete, capsys):
"""Replaces table data with data from a GCS URI using various formats
Each file format has its own tested load from URI sample. Because most of
the code is common for autodetect, append, and truncate, this sample
includes snippets for all supported formats but only calls a single load
job.
This code snippet is made up of shared code, then format-specific code,
followed by more shared code. Note that only the last format in the
format-specific code section will be tested in this test.
"""
dataset_id = "load_table_from_uri_trunc_{}".format(_millis())
dataset = bigquery.Dataset(client.dataset(dataset_id))
client.create_dataset(dataset)
to_delete.append(dataset)
job_config = bigquery.LoadJobConfig()
job_config.schema = [
bigquery.SchemaField("name", "STRING"),
bigquery.SchemaField("post_abbr", "STRING"),
]
table_ref = dataset.table("us_states")
body = six.BytesIO(b"Washington,WA")
client.load_table_from_file(body, table_ref, job_config=job_config).result()
previous_rows = client.get_table(table_ref).num_rows
assert previous_rows > 0
# Shared code
# [START bigquery_load_table_gcs_avro_truncate]
# [START bigquery_load_table_gcs_csv_truncate]
# [START bigquery_load_table_gcs_json_truncate]
# [START bigquery_load_table_gcs_parquet_truncate]
# [START bigquery_load_table_gcs_orc_truncate]
# from google.cloud import bigquery
# client = bigquery.Client()
# table_ref = client.dataset('my_dataset').table('existing_table')
job_config = bigquery.LoadJobConfig()
job_config.write_disposition = bigquery.WriteDisposition.WRITE_TRUNCATE
# [END bigquery_load_table_gcs_avro_truncate]
# [END bigquery_load_table_gcs_csv_truncate]
# [END bigquery_load_table_gcs_json_truncate]
# [END bigquery_load_table_gcs_parquet_truncate]
# [END bigquery_load_table_gcs_orc_truncate]
# Format-specific code
# [START bigquery_load_table_gcs_avro_truncate]
job_config.source_format = bigquery.SourceFormat.AVRO
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.avro"
# [END bigquery_load_table_gcs_avro_truncate]
# [START bigquery_load_table_gcs_csv_truncate]
job_config.skip_leading_rows = 1
# The source format defaults to CSV, so the line below is optional.
job_config.source_format = bigquery.SourceFormat.CSV
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.csv"
# [END bigquery_load_table_gcs_csv_truncate]
# unset csv-specific attribute
del job_config._properties["load"]["skipLeadingRows"]
# [START bigquery_load_table_gcs_json_truncate]
job_config.source_format = bigquery.SourceFormat.NEWLINE_DELIMITED_JSON
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.json"
# [END bigquery_load_table_gcs_json_truncate]
# [START bigquery_load_table_gcs_parquet_truncate]
job_config.source_format = bigquery.SourceFormat.PARQUET
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.parquet"
# [END bigquery_load_table_gcs_parquet_truncate]
# [START bigquery_load_table_gcs_orc_truncate]
job_config.source_format = bigquery.SourceFormat.ORC
uri = "gs://cloud-samples-data/bigquery/us-states/us-states.orc"
# [END bigquery_load_table_gcs_orc_truncate]
# Shared code
# [START bigquery_load_table_gcs_avro_truncate]
# [START bigquery_load_table_gcs_csv_truncate]
# [START bigquery_load_table_gcs_json_truncate]
# [START bigquery_load_table_gcs_parquet_truncate]
# [START bigquery_load_table_gcs_orc_truncate]
load_job = client.load_table_from_uri(
uri, table_ref, job_config=job_config
) # API request
print("Starting job {}".format(load_job.job_id))
load_job.result() # Waits for table load to complete.
print("Job finished.")
destination_table = client.get_table(table_ref)
print("Loaded {} rows.".format(destination_table.num_rows))
# [END bigquery_load_table_gcs_avro_truncate]
# [END bigquery_load_table_gcs_csv_truncate]
# [END bigquery_load_table_gcs_json_truncate]
# [END bigquery_load_table_gcs_parquet_truncate]
# [END bigquery_load_table_gcs_orc_truncate]
out, _ = capsys.readouterr()
assert "Loaded 50 rows." in out
def test_load_table_add_column(client, to_delete):
dataset_id = "load_table_add_column_{}".format(_millis())
dataset_ref = client.dataset(dataset_id)
dataset = bigquery.Dataset(dataset_ref)
dataset.location = "US"
dataset = client.create_dataset(dataset)
to_delete.append(dataset)
snippets_dir = os.path.abspath(os.path.dirname(__file__))
filepath = os.path.join(snippets_dir, "..", "tests", "data", "people.csv")
table_ref = dataset_ref.table("my_table")
old_schema = [bigquery.SchemaField("full_name", "STRING", mode="REQUIRED")]
table = client.create_table(bigquery.Table(table_ref, schema=old_schema))
# [START bigquery_add_column_load_append]
# from google.cloud import bigquery
# client = bigquery.Client()
# dataset_ref = client.dataset('my_dataset')
# filepath = 'path/to/your_file.csv'
# Retrieves the destination table and checks the length of the schema
table_id = "my_table"
table_ref = dataset_ref.table(table_id)
table = client.get_table(table_ref)
print("Table {} contains {} columns.".format(table_id, len(table.schema)))
# Configures the load job to append the data to the destination table,
# allowing field addition
job_config = bigquery.LoadJobConfig()
job_config.write_disposition = bigquery.WriteDisposition.WRITE_APPEND
job_config.schema_update_options = [
bigquery.SchemaUpdateOption.ALLOW_FIELD_ADDITION
]
# In this example, the existing table contains only the 'full_name' column.
# 'REQUIRED' fields cannot be added to an existing schema, so the
# additional column must be 'NULLABLE'.
job_config.schema = [
bigquery.SchemaField("full_name", "STRING", mode="REQUIRED"),
bigquery.SchemaField("age", "INTEGER", mode="NULLABLE"),
]
job_config.source_format = bigquery.SourceFormat.CSV
job_config.skip_leading_rows = 1
with open(filepath, "rb") as source_file:
job = client.load_table_from_file(
source_file,
table_ref,
location="US", # Must match the destination dataset location.
job_config=job_config,
) # API request
job.result() # Waits for table load to complete.
print(
"Loaded {} rows into {}:{}.".format(
job.output_rows, dataset_id, table_ref.table_id
)
)
# Checks the updated length of the schema
table = client.get_table(table)
print("Table {} now contains {} columns.".format(table_id, len(table.schema)))
# [END bigquery_add_column_load_append]
assert len(table.schema) == 2
assert table.num_rows > 0
def test_load_table_relax_column(client, to_delete):
dataset_id = "load_table_relax_column_{}".format(_millis())
dataset_ref = client.dataset(dataset_id)
dataset = bigquery.Dataset(dataset_ref)
dataset.location = "US"
dataset = client.create_dataset(dataset)
to_delete.append(dataset)
snippets_dir = os.path.abspath(os.path.dirname(__file__))
filepath = os.path.join(snippets_dir, "..", "tests", "data", "people.csv")
table_ref = dataset_ref.table("my_table")
old_schema = [
bigquery.SchemaField("full_name", "STRING", mode="REQUIRED"),
bigquery.SchemaField("age", "INTEGER", mode="REQUIRED"),
bigquery.SchemaField("favorite_color", "STRING", mode="REQUIRED"),
]
table = client.create_table(bigquery.Table(table_ref, schema=old_schema))
# [START bigquery_relax_column_load_append]
# from google.cloud import bigquery
# client = bigquery.Client()
# dataset_ref = client.dataset('my_dataset')
# filepath = 'path/to/your_file.csv'
# Retrieves the destination table and checks the number of required fields
table_id = "my_table"
table_ref = dataset_ref.table(table_id)
table = client.get_table(table_ref)
original_required_fields = sum(field.mode == "REQUIRED" for field in table.schema)
# In this example, the existing table has 3 required fields.
print("{} fields in the schema are required.".format(original_required_fields))
# Configures the load job to append the data to a destination table,
# allowing field relaxation
job_config = bigquery.LoadJobConfig()
job_config.write_disposition = bigquery.WriteDisposition.WRITE_APPEND
job_config.schema_update_options = [
bigquery.SchemaUpdateOption.ALLOW_FIELD_RELAXATION
]
# In this example, the existing table contains three required fields
# ('full_name', 'age', and 'favorite_color'), while the data to load
# contains only the first two fields.
job_config.schema = [
bigquery.SchemaField("full_name", "STRING", mode="REQUIRED"),
bigquery.SchemaField("age", "INTEGER", mode="REQUIRED"),
]
job_config.source_format = bigquery.SourceFormat.CSV
job_config.skip_leading_rows = 1
with open(filepath, "rb") as source_file:
job = client.load_table_from_file(
source_file,
table_ref,
location="US", # Must match the destination dataset location.
job_config=job_config,
) # API request
job.result() # Waits for table load to complete.
print(
"Loaded {} rows into {}:{}.".format(
job.output_rows, dataset_id, table_ref.table_id
)
)
# Checks the updated number of required fields
table = client.get_table(table)
current_required_fields = sum(field.mode == "REQUIRED" for field in table.schema)
print("{} fields in the schema are now required.".format(current_required_fields))
# [END bigquery_relax_column_load_append]
assert original_required_fields - current_required_fields == 1
assert len(table.schema) == 3
assert table.schema[2].mode == "NULLABLE"
assert table.num_rows > 0
def test_extract_table(client, to_delete):
bucket_name = "extract_shakespeare_{}".format(_millis())
storage_client = storage.Client()
bucket = retry_storage_errors(storage_client.create_bucket)(bucket_name)
to_delete.append(bucket)
# [START bigquery_extract_table]
# from google.cloud import bigquery
# client = bigquery.Client()
# bucket_name = 'my-bucket'
project = "bigquery-public-data"
dataset_id = "samples"
table_id = "shakespeare"
destination_uri = "gs://{}/{}".format(bucket_name, "shakespeare.csv")
dataset_ref = client.dataset(dataset_id, project=project)
table_ref = dataset_ref.table(table_id)
extract_job = client.extract_table(
table_ref,
destination_uri,
# Location must match that of the source table.
location="US",
) # API request
extract_job.result() # Waits for job to complete.
print(
"Exported {}:{}.{} to {}".format(project, dataset_id, table_id, destination_uri)
)
# [END bigquery_extract_table]
blob = retry_storage_errors(bucket.get_blob)("shakespeare.csv")
assert blob.exists
assert blob.size > 0
to_delete.insert(0, blob)
def test_extract_table_json(client, to_delete):
bucket_name = "extract_shakespeare_json_{}".format(_millis())
storage_client = storage.Client()
bucket = retry_storage_errors(storage_client.create_bucket)(bucket_name)
to_delete.append(bucket)
# [START bigquery_extract_table_json]
# from google.cloud import bigquery
# client = bigquery.Client()
# bucket_name = 'my-bucket'
destination_uri = "gs://{}/{}".format(bucket_name, "shakespeare.json")
dataset_ref = client.dataset("samples", project="bigquery-public-data")
table_ref = dataset_ref.table("shakespeare")
job_config = bigquery.job.ExtractJobConfig()
job_config.destination_format = bigquery.DestinationFormat.NEWLINE_DELIMITED_JSON
extract_job = client.extract_table(
table_ref,
destination_uri,
job_config=job_config,
# Location must match that of the source table.
location="US",
) # API request
extract_job.result() # Waits for job to complete.
# [END bigquery_extract_table_json]
blob = retry_storage_errors(bucket.get_blob)("shakespeare.json")
assert blob.exists
assert blob.size > 0
to_delete.insert(0, blob)
def test_extract_table_compressed(client, to_delete):
bucket_name = "extract_shakespeare_compress_{}".format(_millis())
storage_client = storage.Client()
bucket = retry_storage_errors(storage_client.create_bucket)(bucket_name)
to_delete.append(bucket)
# [START bigquery_extract_table_compressed]
# from google.cloud import bigquery
# client = bigquery.Client()
# bucket_name = 'my-bucket'
destination_uri = "gs://{}/{}".format(bucket_name, "shakespeare.csv.gz")
dataset_ref = client.dataset("samples", project="bigquery-public-data")
table_ref = dataset_ref.table("shakespeare")
job_config = bigquery.job.ExtractJobConfig()
job_config.compression = bigquery.Compression.GZIP
extract_job = client.extract_table(
table_ref,
destination_uri,
# Location must match that of the source table.
location="US",
job_config=job_config,
) # API request
extract_job.result() # Waits for job to complete.
# [END bigquery_extract_table_compressed]
blob = retry_storage_errors(bucket.get_blob)("shakespeare.csv.gz")
assert blob.exists
assert blob.size > 0
to_delete.insert(0, blob)
def test_client_query_total_rows(client, capsys):
"""Run a query and just check for how many rows."""
# [START bigquery_query_total_rows]
# from google.cloud import bigquery
# client = bigquery.Client()
query = (
"SELECT name FROM `bigquery-public-data.usa_names.usa_1910_2013` "
'WHERE state = "TX" '
"LIMIT 100"