forked from googleapis/python-bigquery
/
load.py
779 lines (633 loc) · 26 KB
/
load.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
# Copyright 2015 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.
"""Classes for load jobs."""
from google.cloud.bigquery.encryption_configuration import EncryptionConfiguration
from google.cloud.bigquery.external_config import HivePartitioningOptions
from google.cloud.bigquery.format_options import ParquetOptions
from google.cloud.bigquery import _helpers
from google.cloud.bigquery.schema import SchemaField
from google.cloud.bigquery.schema import _to_schema_fields
from google.cloud.bigquery.table import RangePartitioning
from google.cloud.bigquery.table import TableReference
from google.cloud.bigquery.table import TimePartitioning
from google.cloud.bigquery.job.base import _AsyncJob
from google.cloud.bigquery.job.base import _JobConfig
from google.cloud.bigquery.job.base import _JobReference
class LoadJobConfig(_JobConfig):
"""Configuration options for load jobs.
All properties in this class are optional. Values which are :data:`None` ->
server defaults. Set properties on the constructed configuration by using
the property name as the name of a keyword argument.
"""
def __init__(self, **kwargs):
super(LoadJobConfig, self).__init__("load", **kwargs)
@property
def allow_jagged_rows(self):
"""Optional[bool]: Allow missing trailing optional columns (CSV only).
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.allow_jagged_rows
"""
return self._get_sub_prop("allowJaggedRows")
@allow_jagged_rows.setter
def allow_jagged_rows(self, value):
self._set_sub_prop("allowJaggedRows", value)
@property
def allow_quoted_newlines(self):
"""Optional[bool]: Allow quoted data containing newline characters (CSV only).
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.allow_quoted_newlines
"""
return self._get_sub_prop("allowQuotedNewlines")
@allow_quoted_newlines.setter
def allow_quoted_newlines(self, value):
self._set_sub_prop("allowQuotedNewlines", value)
@property
def autodetect(self):
"""Optional[bool]: Automatically infer the schema from a sample of the data.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.autodetect
"""
return self._get_sub_prop("autodetect")
@autodetect.setter
def autodetect(self, value):
self._set_sub_prop("autodetect", value)
@property
def clustering_fields(self):
"""Optional[List[str]]: Fields defining clustering for the table
(Defaults to :data:`None`).
Clustering fields are immutable after table creation.
.. note::
BigQuery supports clustering for both partitioned and
non-partitioned tables.
"""
prop = self._get_sub_prop("clustering")
if prop is not None:
return list(prop.get("fields", ()))
@clustering_fields.setter
def clustering_fields(self, value):
"""Optional[List[str]]: Fields defining clustering for the table
(Defaults to :data:`None`).
"""
if value is not None:
self._set_sub_prop("clustering", {"fields": value})
else:
self._del_sub_prop("clustering")
@property
def create_disposition(self):
"""Optional[google.cloud.bigquery.job.CreateDisposition]: Specifies behavior
for creating tables.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.create_disposition
"""
return self._get_sub_prop("createDisposition")
@create_disposition.setter
def create_disposition(self, value):
self._set_sub_prop("createDisposition", value)
@property
def destination_encryption_configuration(self):
"""Optional[google.cloud.bigquery.encryption_configuration.EncryptionConfiguration]: Custom
encryption configuration for the destination table.
Custom encryption configuration (e.g., Cloud KMS keys) or :data:`None`
if using default encryption.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.destination_encryption_configuration
"""
prop = self._get_sub_prop("destinationEncryptionConfiguration")
if prop is not None:
prop = EncryptionConfiguration.from_api_repr(prop)
return prop
@destination_encryption_configuration.setter
def destination_encryption_configuration(self, value):
api_repr = value
if value is not None:
api_repr = value.to_api_repr()
self._set_sub_prop("destinationEncryptionConfiguration", api_repr)
else:
self._del_sub_prop("destinationEncryptionConfiguration")
@property
def destination_table_description(self):
"""Optional[str]: Name given to destination table.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#DestinationTableProperties.FIELDS.description
"""
prop = self._get_sub_prop("destinationTableProperties")
if prop is not None:
return prop["description"]
@destination_table_description.setter
def destination_table_description(self, value):
keys = [self._job_type, "destinationTableProperties", "description"]
if value is not None:
_helpers._set_sub_prop(self._properties, keys, value)
else:
_helpers._del_sub_prop(self._properties, keys)
@property
def destination_table_friendly_name(self):
"""Optional[str]: Name given to destination table.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#DestinationTableProperties.FIELDS.friendly_name
"""
prop = self._get_sub_prop("destinationTableProperties")
if prop is not None:
return prop["friendlyName"]
@destination_table_friendly_name.setter
def destination_table_friendly_name(self, value):
keys = [self._job_type, "destinationTableProperties", "friendlyName"]
if value is not None:
_helpers._set_sub_prop(self._properties, keys, value)
else:
_helpers._del_sub_prop(self._properties, keys)
@property
def encoding(self):
"""Optional[google.cloud.bigquery.job.Encoding]: The character encoding of the
data.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.encoding
"""
return self._get_sub_prop("encoding")
@encoding.setter
def encoding(self, value):
self._set_sub_prop("encoding", value)
@property
def field_delimiter(self):
"""Optional[str]: The separator for fields in a CSV file.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.field_delimiter
"""
return self._get_sub_prop("fieldDelimiter")
@field_delimiter.setter
def field_delimiter(self, value):
self._set_sub_prop("fieldDelimiter", value)
@property
def hive_partitioning(self):
"""Optional[:class:`~.external_config.HivePartitioningOptions`]: [Beta] When set, \
it configures hive partitioning support.
.. note::
**Experimental**. This feature is experimental and might change or
have limited support.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.hive_partitioning_options
"""
prop = self._get_sub_prop("hivePartitioningOptions")
if prop is None:
return None
return HivePartitioningOptions.from_api_repr(prop)
@hive_partitioning.setter
def hive_partitioning(self, value):
if value is not None:
if isinstance(value, HivePartitioningOptions):
value = value.to_api_repr()
else:
raise TypeError("Expected a HivePartitioningOptions instance or None.")
self._set_sub_prop("hivePartitioningOptions", value)
@property
def ignore_unknown_values(self):
"""Optional[bool]: Ignore extra values not represented in the table schema.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.ignore_unknown_values
"""
return self._get_sub_prop("ignoreUnknownValues")
@ignore_unknown_values.setter
def ignore_unknown_values(self, value):
self._set_sub_prop("ignoreUnknownValues", value)
@property
def max_bad_records(self):
"""Optional[int]: Number of invalid rows to ignore.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.max_bad_records
"""
return _helpers._int_or_none(self._get_sub_prop("maxBadRecords"))
@max_bad_records.setter
def max_bad_records(self, value):
self._set_sub_prop("maxBadRecords", value)
@property
def null_marker(self):
"""Optional[str]: Represents a null value (CSV only).
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.null_marker
"""
return self._get_sub_prop("nullMarker")
@null_marker.setter
def null_marker(self, value):
self._set_sub_prop("nullMarker", value)
@property
def quote_character(self):
"""Optional[str]: Character used to quote data sections (CSV only).
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.quote
"""
return self._get_sub_prop("quote")
@quote_character.setter
def quote_character(self, value):
self._set_sub_prop("quote", value)
@property
def range_partitioning(self):
"""Optional[google.cloud.bigquery.table.RangePartitioning]:
Configures range-based partitioning for destination table.
.. note::
**Beta**. The integer range partitioning feature is in a
pre-release state and might change or have limited support.
Only specify at most one of
:attr:`~google.cloud.bigquery.job.LoadJobConfig.time_partitioning` or
:attr:`~google.cloud.bigquery.job.LoadJobConfig.range_partitioning`.
Raises:
ValueError:
If the value is not
:class:`~google.cloud.bigquery.table.RangePartitioning` or
:data:`None`.
"""
resource = self._get_sub_prop("rangePartitioning")
if resource is not None:
return RangePartitioning(_properties=resource)
@range_partitioning.setter
def range_partitioning(self, value):
resource = value
if isinstance(value, RangePartitioning):
resource = value._properties
elif value is not None:
raise ValueError(
"Expected value to be RangePartitioning or None, got {}.".format(value)
)
self._set_sub_prop("rangePartitioning", resource)
@property
def schema(self):
"""Optional[Sequence[Union[ \
:class:`~google.cloud.bigquery.schema.SchemaField`, \
Mapping[str, Any] \
]]]: Schema of the destination table.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.schema
"""
schema = _helpers._get_sub_prop(self._properties, ["load", "schema", "fields"])
if schema is None:
return
return [SchemaField.from_api_repr(field) for field in schema]
@schema.setter
def schema(self, value):
if value is None:
self._del_sub_prop("schema")
return
value = _to_schema_fields(value)
_helpers._set_sub_prop(
self._properties,
["load", "schema", "fields"],
[field.to_api_repr() for field in value],
)
@property
def schema_update_options(self):
"""Optional[List[google.cloud.bigquery.job.SchemaUpdateOption]]: Specifies
updates to the destination table schema to allow as a side effect of
the load job.
"""
return self._get_sub_prop("schemaUpdateOptions")
@schema_update_options.setter
def schema_update_options(self, values):
self._set_sub_prop("schemaUpdateOptions", values)
@property
def skip_leading_rows(self):
"""Optional[int]: Number of rows to skip when reading data (CSV only).
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.skip_leading_rows
"""
return _helpers._int_or_none(self._get_sub_prop("skipLeadingRows"))
@skip_leading_rows.setter
def skip_leading_rows(self, value):
self._set_sub_prop("skipLeadingRows", str(value))
@property
def source_format(self):
"""Optional[google.cloud.bigquery.job.SourceFormat]: File format of the data.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.source_format
"""
return self._get_sub_prop("sourceFormat")
@source_format.setter
def source_format(self, value):
self._set_sub_prop("sourceFormat", value)
@property
def time_partitioning(self):
"""Optional[google.cloud.bigquery.table.TimePartitioning]: Specifies time-based
partitioning for the destination table.
Only specify at most one of
:attr:`~google.cloud.bigquery.job.LoadJobConfig.time_partitioning` or
:attr:`~google.cloud.bigquery.job.LoadJobConfig.range_partitioning`.
"""
prop = self._get_sub_prop("timePartitioning")
if prop is not None:
prop = TimePartitioning.from_api_repr(prop)
return prop
@time_partitioning.setter
def time_partitioning(self, value):
api_repr = value
if value is not None:
api_repr = value.to_api_repr()
self._set_sub_prop("timePartitioning", api_repr)
else:
self._del_sub_prop("timePartitioning")
@property
def use_avro_logical_types(self):
"""Optional[bool]: For loads of Avro data, governs whether Avro logical types are
converted to their corresponding BigQuery types (e.g. TIMESTAMP) rather than
raw types (e.g. INTEGER).
"""
return self._get_sub_prop("useAvroLogicalTypes")
@use_avro_logical_types.setter
def use_avro_logical_types(self, value):
self._set_sub_prop("useAvroLogicalTypes", bool(value))
@property
def write_disposition(self):
"""Optional[google.cloud.bigquery.job.WriteDisposition]: Action that occurs if
the destination table already exists.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.write_disposition
"""
return self._get_sub_prop("writeDisposition")
@write_disposition.setter
def write_disposition(self, value):
self._set_sub_prop("writeDisposition", value)
@property
def parquet_options(self):
"""Optional[google.cloud.bigquery.format_options.ParquetOptions]: Additional
properties to set if ``sourceFormat`` is set to PARQUET.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.parquet_options
"""
prop = self._get_sub_prop("parquetOptions")
if prop is not None:
prop = ParquetOptions.from_api_repr(prop)
return prop
@parquet_options.setter
def parquet_options(self, value):
if value is not None:
self._set_sub_prop("parquetOptions", value.to_api_repr())
else:
self._del_sub_prop("parquetOptions")
class LoadJob(_AsyncJob):
"""Asynchronous job for loading data into a table.
Can load from Google Cloud Storage URIs or from a file.
Args:
job_id (str): the job's ID
source_uris (Optional[Sequence[str]]):
URIs of one or more data files to be loaded. See
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.source_uris
for supported URI formats. Pass None for jobs that load from a file.
destination (google.cloud.bigquery.table.TableReference): reference to table into which data is to be loaded.
client (google.cloud.bigquery.client.Client):
A client which holds credentials and project configuration
for the dataset (which requires a project).
"""
_JOB_TYPE = "load"
def __init__(self, job_id, source_uris, destination, client, job_config=None):
super(LoadJob, self).__init__(job_id, client)
if not job_config:
job_config = LoadJobConfig()
self._configuration = job_config
self._properties["configuration"] = job_config._properties
if source_uris is not None:
_helpers._set_sub_prop(
self._properties, ["configuration", "load", "sourceUris"], source_uris
)
if destination is not None:
_helpers._set_sub_prop(
self._properties,
["configuration", "load", "destinationTable"],
destination.to_api_repr(),
)
@property
def destination(self):
"""google.cloud.bigquery.table.TableReference: table where loaded rows are written
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.destination_table
"""
dest_config = _helpers._get_sub_prop(
self._properties, ["configuration", "load", "destinationTable"]
)
return TableReference.from_api_repr(dest_config)
@property
def source_uris(self):
"""Optional[Sequence[str]]: URIs of data files to be loaded. See
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#JobConfigurationLoad.FIELDS.source_uris
for supported URI formats. None for jobs that load from a file.
"""
return _helpers._get_sub_prop(
self._properties, ["configuration", "load", "sourceUris"]
)
@property
def allow_jagged_rows(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.allow_jagged_rows`.
"""
return self._configuration.allow_jagged_rows
@property
def allow_quoted_newlines(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.allow_quoted_newlines`.
"""
return self._configuration.allow_quoted_newlines
@property
def autodetect(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.autodetect`.
"""
return self._configuration.autodetect
@property
def create_disposition(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.create_disposition`.
"""
return self._configuration.create_disposition
@property
def encoding(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.encoding`.
"""
return self._configuration.encoding
@property
def field_delimiter(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.field_delimiter`.
"""
return self._configuration.field_delimiter
@property
def ignore_unknown_values(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.ignore_unknown_values`.
"""
return self._configuration.ignore_unknown_values
@property
def max_bad_records(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.max_bad_records`.
"""
return self._configuration.max_bad_records
@property
def null_marker(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.null_marker`.
"""
return self._configuration.null_marker
@property
def quote_character(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.quote_character`.
"""
return self._configuration.quote_character
@property
def skip_leading_rows(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.skip_leading_rows`.
"""
return self._configuration.skip_leading_rows
@property
def source_format(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.source_format`.
"""
return self._configuration.source_format
@property
def write_disposition(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.write_disposition`.
"""
return self._configuration.write_disposition
@property
def schema(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.schema`.
"""
return self._configuration.schema
@property
def destination_encryption_configuration(self):
"""google.cloud.bigquery.encryption_configuration.EncryptionConfiguration: Custom
encryption configuration for the destination table.
Custom encryption configuration (e.g., Cloud KMS keys)
or :data:`None` if using default encryption.
See
:attr:`google.cloud.bigquery.job.LoadJobConfig.destination_encryption_configuration`.
"""
return self._configuration.destination_encryption_configuration
@property
def destination_table_description(self):
"""Optional[str] name given to destination table.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#DestinationTableProperties.FIELDS.description
"""
return self._configuration.destination_table_description
@property
def destination_table_friendly_name(self):
"""Optional[str] name given to destination table.
See:
https://cloud.google.com/bigquery/docs/reference/rest/v2/Job#DestinationTableProperties.FIELDS.friendly_name
"""
return self._configuration.destination_table_friendly_name
@property
def range_partitioning(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.range_partitioning`.
"""
return self._configuration.range_partitioning
@property
def time_partitioning(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.time_partitioning`.
"""
return self._configuration.time_partitioning
@property
def use_avro_logical_types(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.use_avro_logical_types`.
"""
return self._configuration.use_avro_logical_types
@property
def clustering_fields(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.clustering_fields`.
"""
return self._configuration.clustering_fields
@property
def schema_update_options(self):
"""See
:attr:`google.cloud.bigquery.job.LoadJobConfig.schema_update_options`.
"""
return self._configuration.schema_update_options
@property
def input_file_bytes(self):
"""Count of bytes loaded from source files.
Returns:
Optional[int]: the count (None until set from the server).
Raises:
ValueError: for invalid value types.
"""
return _helpers._int_or_none(
_helpers._get_sub_prop(
self._properties, ["statistics", "load", "inputFileBytes"]
)
)
@property
def input_files(self):
"""Count of source files.
Returns:
Optional[int]: the count (None until set from the server).
"""
return _helpers._int_or_none(
_helpers._get_sub_prop(
self._properties, ["statistics", "load", "inputFiles"]
)
)
@property
def output_bytes(self):
"""Count of bytes saved to destination table.
Returns:
Optional[int]: the count (None until set from the server).
"""
return _helpers._int_or_none(
_helpers._get_sub_prop(
self._properties, ["statistics", "load", "outputBytes"]
)
)
@property
def output_rows(self):
"""Count of rows saved to destination table.
Returns:
Optional[int]: the count (None until set from the server).
"""
return _helpers._int_or_none(
_helpers._get_sub_prop(
self._properties, ["statistics", "load", "outputRows"]
)
)
def to_api_repr(self):
"""Generate a resource for :meth:`_begin`."""
# Exclude statistics, if set.
return {
"jobReference": self._properties["jobReference"],
"configuration": self._properties["configuration"],
}
@classmethod
def from_api_repr(cls, resource: dict, client) -> "LoadJob":
"""Factory: construct a job given its API representation
.. note:
This method assumes that the project found in the resource matches
the client's project.
Args:
resource (Dict): dataset job representation returned from the API
client (google.cloud.bigquery.client.Client):
Client which holds credentials and project
configuration for the dataset.
Returns:
google.cloud.bigquery.job.LoadJob: Job parsed from ``resource``.
"""
cls._check_resource_config(resource)
job_ref = _JobReference._from_api_repr(resource["jobReference"])
job = cls(job_ref, None, None, client)
job._set_properties(resource)
return job