google-cloud-bigquery 1.21.2 → 1.22.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +11 -0
- data/lib/google/cloud/bigquery/convert.rb +3 -1
- data/lib/google/cloud/bigquery/copy_job.rb +15 -6
- data/lib/google/cloud/bigquery/dataset.rb +43 -20
- data/lib/google/cloud/bigquery/extract_job.rb +153 -45
- data/lib/google/cloud/bigquery/load_job.rb +15 -6
- data/lib/google/cloud/bigquery/model.rb +164 -8
- data/lib/google/cloud/bigquery/project.rb +137 -68
- data/lib/google/cloud/bigquery/query_job.rb +15 -6
- data/lib/google/cloud/bigquery/service.rb +12 -10
- data/lib/google/cloud/bigquery/table.rb +63 -32
- data/lib/google/cloud/bigquery/version.rb +1 -1
- metadata +2 -2
@@ -1303,12 +1303,21 @@ module Google
|
|
1303
1303
|
# Sets the labels to use for the load job.
|
1304
1304
|
#
|
1305
1305
|
# @param [Hash] val A hash of user-provided labels associated with
|
1306
|
-
# the job. You can use these to organize and group your jobs.
|
1307
|
-
#
|
1308
|
-
#
|
1309
|
-
#
|
1310
|
-
#
|
1311
|
-
#
|
1306
|
+
# the job. You can use these to organize and group your jobs.
|
1307
|
+
#
|
1308
|
+
# The labels applied to a resource must meet the following requirements:
|
1309
|
+
#
|
1310
|
+
# * Each resource can have multiple labels, up to a maximum of 64.
|
1311
|
+
# * Each label must be a key-value pair.
|
1312
|
+
# * Keys have a minimum length of 1 character and a maximum length of
|
1313
|
+
# 63 characters, and cannot be empty. Values can be empty, and have
|
1314
|
+
# a maximum length of 63 characters.
|
1315
|
+
# * Keys and values can contain only lowercase letters, numeric characters,
|
1316
|
+
# underscores, and dashes. All characters must use UTF-8 encoding, and
|
1317
|
+
# international characters are allowed.
|
1318
|
+
# * The key portion of a label must be unique. However, you can use the
|
1319
|
+
# same key with multiple resources.
|
1320
|
+
# * Keys must start with a lowercase letter or international character.
|
1312
1321
|
#
|
1313
1322
|
# @!group Attributes
|
1314
1323
|
#
|
@@ -341,14 +341,19 @@ module Google
|
|
341
341
|
# the update to comply with ETag-based optimistic concurrency control.
|
342
342
|
#
|
343
343
|
# @param [Hash<String, String>] new_labels A hash containing key/value
|
344
|
-
# pairs.
|
345
|
-
#
|
346
|
-
# *
|
347
|
-
# *
|
348
|
-
#
|
349
|
-
#
|
350
|
-
#
|
351
|
-
# *
|
344
|
+
# pairs. The labels applied to a resource must meet the following requirements:
|
345
|
+
#
|
346
|
+
# * Each resource can have multiple labels, up to a maximum of 64.
|
347
|
+
# * Each label must be a key-value pair.
|
348
|
+
# * Keys have a minimum length of 1 character and a maximum length of
|
349
|
+
# 63 characters, and cannot be empty. Values can be empty, and have
|
350
|
+
# a maximum length of 63 characters.
|
351
|
+
# * Keys and values can contain only lowercase letters, numeric characters,
|
352
|
+
# underscores, and dashes. All characters must use UTF-8 encoding, and
|
353
|
+
# international characters are allowed.
|
354
|
+
# * The key portion of a label must be unique. However, you can use the
|
355
|
+
# same key with multiple resources.
|
356
|
+
# * Keys must start with a lowercase letter or international character.
|
352
357
|
#
|
353
358
|
# @example
|
354
359
|
# require "google/cloud/bigquery"
|
@@ -482,6 +487,146 @@ module Google
|
|
482
487
|
Array @gapi_json[:trainingRuns]
|
483
488
|
end
|
484
489
|
|
490
|
+
##
|
491
|
+
# Exports the model to Google Cloud Storage asynchronously, immediately
|
492
|
+
# returning an {ExtractJob} that can be used to track the progress of the
|
493
|
+
# export job. The caller may poll the service by repeatedly calling
|
494
|
+
# {Job#reload!} and {Job#done?} to detect when the job is done, or
|
495
|
+
# simply block until the job is done by calling #{Job#wait_until_done!}.
|
496
|
+
# See also {#extract}.
|
497
|
+
#
|
498
|
+
# The geographic location for the job ("US", "EU", etc.) can be set via
|
499
|
+
# {ExtractJob::Updater#location=} in a block passed to this method. If
|
500
|
+
# the model is a full resource representation (see {#resource_full?}),
|
501
|
+
# the location of the job will automatically be set to the location of
|
502
|
+
# the model.
|
503
|
+
#
|
504
|
+
# @see https://cloud.google.com/bigquery-ml/docs/exporting-models
|
505
|
+
# Exporting models
|
506
|
+
#
|
507
|
+
# @param [String] extract_url The Google Storage URI to which BigQuery
|
508
|
+
# should extract the model. This value should be end in an object name
|
509
|
+
# prefix, since multiple objects will be exported.
|
510
|
+
# @param [String] format The exported file format. The default value is
|
511
|
+
# `ml_tf_saved_model`.
|
512
|
+
#
|
513
|
+
# The following values are supported:
|
514
|
+
#
|
515
|
+
# * `ml_tf_saved_model` - TensorFlow SavedModel
|
516
|
+
# * `ml_xgboost_booster` - XGBoost Booster
|
517
|
+
# @param [String] job_id A user-defined ID for the extract job. The ID
|
518
|
+
# must contain only letters (a-z, A-Z), numbers (0-9), underscores
|
519
|
+
# (_), or dashes (-). The maximum length is 1,024 characters. If
|
520
|
+
# `job_id` is provided, then `prefix` will not be used.
|
521
|
+
#
|
522
|
+
# See [Generating a job
|
523
|
+
# ID](https://cloud.google.com/bigquery/docs/managing-jobs#generate-jobid).
|
524
|
+
# @param [String] prefix A string, usually human-readable, that will be
|
525
|
+
# prepended to a generated value to produce a unique job ID. For
|
526
|
+
# example, the prefix `daily_import_job_` can be given to generate a
|
527
|
+
# job ID such as `daily_import_job_12vEDtMQ0mbp1Mo5Z7mzAFQJZazh`. The
|
528
|
+
# prefix must contain only letters (a-z, A-Z), numbers (0-9),
|
529
|
+
# underscores (_), or dashes (-). The maximum length of the entire ID
|
530
|
+
# is 1,024 characters. If `job_id` is provided, then `prefix` will not
|
531
|
+
# be used.
|
532
|
+
# @param [Hash] labels A hash of user-provided labels associated with
|
533
|
+
# the job. You can use these to organize and group your jobs.
|
534
|
+
#
|
535
|
+
# The labels applied to a resource must meet the following requirements:
|
536
|
+
#
|
537
|
+
# * Each resource can have multiple labels, up to a maximum of 64.
|
538
|
+
# * Each label must be a key-value pair.
|
539
|
+
# * Keys have a minimum length of 1 character and a maximum length of
|
540
|
+
# 63 characters, and cannot be empty. Values can be empty, and have
|
541
|
+
# a maximum length of 63 characters.
|
542
|
+
# * Keys and values can contain only lowercase letters, numeric characters,
|
543
|
+
# underscores, and dashes. All characters must use UTF-8 encoding, and
|
544
|
+
# international characters are allowed.
|
545
|
+
# * The key portion of a label must be unique. However, you can use the
|
546
|
+
# same key with multiple resources.
|
547
|
+
# * Keys must start with a lowercase letter or international character.
|
548
|
+
#
|
549
|
+
# @yield [job] a job configuration object
|
550
|
+
# @yieldparam [Google::Cloud::Bigquery::ExtractJob::Updater] job a job
|
551
|
+
# configuration object for setting additional options.
|
552
|
+
#
|
553
|
+
# @return [Google::Cloud::Bigquery::ExtractJob]
|
554
|
+
#
|
555
|
+
# @example
|
556
|
+
# require "google/cloud/bigquery"
|
557
|
+
#
|
558
|
+
# bigquery = Google::Cloud::Bigquery.new
|
559
|
+
# dataset = bigquery.dataset "my_dataset"
|
560
|
+
# model = dataset.model "my_model"
|
561
|
+
#
|
562
|
+
# extract_job = model.extract_job "gs://my-bucket/#{model.model_id}"
|
563
|
+
#
|
564
|
+
# extract_job.wait_until_done!
|
565
|
+
# extract_job.done? #=> true
|
566
|
+
#
|
567
|
+
# @!group Data
|
568
|
+
#
|
569
|
+
def extract_job extract_url, format: nil, job_id: nil, prefix: nil, labels: nil
|
570
|
+
ensure_service!
|
571
|
+
options = { format: format, job_id: job_id, prefix: prefix, labels: labels }
|
572
|
+
updater = ExtractJob::Updater.from_options service, model_ref, extract_url, options
|
573
|
+
updater.location = location if location # may be model reference
|
574
|
+
|
575
|
+
yield updater if block_given?
|
576
|
+
|
577
|
+
job_gapi = updater.to_gapi
|
578
|
+
gapi = service.extract_table job_gapi
|
579
|
+
Job.from_gapi gapi, service
|
580
|
+
end
|
581
|
+
|
582
|
+
##
|
583
|
+
# Exports the model to Google Cloud Storage using a synchronous method
|
584
|
+
# that blocks for a response. Timeouts and transient errors are generally
|
585
|
+
# handled as needed to complete the job. See also {#extract_job}.
|
586
|
+
#
|
587
|
+
# The geographic location for the job ("US", "EU", etc.) can be set via
|
588
|
+
# {ExtractJob::Updater#location=} in a block passed to this method. If
|
589
|
+
# the model is a full resource representation (see {#resource_full?}),
|
590
|
+
# the location of the job will automatically be set to the location of
|
591
|
+
# the model.
|
592
|
+
#
|
593
|
+
# @see https://cloud.google.com/bigquery-ml/docs/exporting-models
|
594
|
+
# Exporting models
|
595
|
+
#
|
596
|
+
# @param [String] extract_url The Google Storage URI to which BigQuery
|
597
|
+
# should extract the model. This value should be end in an object name
|
598
|
+
# prefix, since multiple objects will be exported.
|
599
|
+
# @param [String] format The exported file format. The default value is
|
600
|
+
# `ml_tf_saved_model`.
|
601
|
+
#
|
602
|
+
# The following values are supported:
|
603
|
+
#
|
604
|
+
# * `ml_tf_saved_model` - TensorFlow SavedModel
|
605
|
+
# * `ml_xgboost_booster` - XGBoost Booster
|
606
|
+
# @yield [job] a job configuration object
|
607
|
+
# @yieldparam [Google::Cloud::Bigquery::ExtractJob::Updater] job a job
|
608
|
+
# configuration object for setting additional options.
|
609
|
+
#
|
610
|
+
# @return [Boolean] Returns `true` if the extract operation succeeded.
|
611
|
+
#
|
612
|
+
# @example
|
613
|
+
# require "google/cloud/bigquery"
|
614
|
+
#
|
615
|
+
# bigquery = Google::Cloud::Bigquery.new
|
616
|
+
# dataset = bigquery.dataset "my_dataset"
|
617
|
+
# model = dataset.model "my_model"
|
618
|
+
#
|
619
|
+
# model.extract "gs://my-bucket/#{model.model_id}"
|
620
|
+
#
|
621
|
+
# @!group Data
|
622
|
+
#
|
623
|
+
def extract extract_url, format: nil, &block
|
624
|
+
job = extract_job extract_url, format: format, &block
|
625
|
+
job.wait_until_done!
|
626
|
+
ensure_job_succeeded! job
|
627
|
+
true
|
628
|
+
end
|
629
|
+
|
485
630
|
##
|
486
631
|
# Permanently deletes the model.
|
487
632
|
#
|
@@ -734,6 +879,17 @@ module Google
|
|
734
879
|
def ensure_full_data!
|
735
880
|
reload! unless resource_full?
|
736
881
|
end
|
882
|
+
|
883
|
+
def ensure_job_succeeded! job
|
884
|
+
return unless job.failed?
|
885
|
+
begin
|
886
|
+
# raise to activate ruby exception cause handling
|
887
|
+
raise job.gapi_error
|
888
|
+
rescue StandardError => e
|
889
|
+
# wrap Google::Apis::Error with Google::Cloud::Error
|
890
|
+
raise Google::Cloud::Error.from_error(e)
|
891
|
+
end
|
892
|
+
end
|
737
893
|
end
|
738
894
|
end
|
739
895
|
end
|
@@ -153,13 +153,21 @@ module Google
|
|
153
153
|
# is 1,024 characters. If `job_id` is provided, then `prefix` will not
|
154
154
|
# be used.
|
155
155
|
# @param [Hash] labels A hash of user-provided labels associated with
|
156
|
-
# the job. You can use these to organize and group your jobs.
|
157
|
-
#
|
158
|
-
#
|
159
|
-
#
|
160
|
-
#
|
161
|
-
#
|
162
|
-
#
|
156
|
+
# the job. You can use these to organize and group your jobs.
|
157
|
+
#
|
158
|
+
# The labels applied to a resource must meet the following requirements:
|
159
|
+
#
|
160
|
+
# * Each resource can have multiple labels, up to a maximum of 64.
|
161
|
+
# * Each label must be a key-value pair.
|
162
|
+
# * Keys have a minimum length of 1 character and a maximum length of
|
163
|
+
# 63 characters, and cannot be empty. Values can be empty, and have
|
164
|
+
# a maximum length of 63 characters.
|
165
|
+
# * Keys and values can contain only lowercase letters, numeric characters,
|
166
|
+
# underscores, and dashes. All characters must use UTF-8 encoding, and
|
167
|
+
# international characters are allowed.
|
168
|
+
# * The key portion of a label must be unique. However, you can use the
|
169
|
+
# same key with multiple resources.
|
170
|
+
# * Keys must start with a lowercase letter or international character.
|
163
171
|
# @yield [job] a job configuration object
|
164
172
|
# @yieldparam [Google::Cloud::Bigquery::CopyJob::Updater] job a job
|
165
173
|
# configuration object for setting additional options.
|
@@ -411,13 +419,21 @@ module Google
|
|
411
419
|
# See [Generating a job
|
412
420
|
# ID](https://cloud.google.com/bigquery/docs/managing-jobs#generate-jobid).
|
413
421
|
# @param [Hash] labels A hash of user-provided labels associated with
|
414
|
-
# the job. You can use these to organize and group your jobs.
|
415
|
-
#
|
416
|
-
#
|
417
|
-
#
|
418
|
-
#
|
419
|
-
#
|
420
|
-
#
|
422
|
+
# the job. You can use these to organize and group your jobs.
|
423
|
+
#
|
424
|
+
# The labels applied to a resource must meet the following requirements:
|
425
|
+
#
|
426
|
+
# * Each resource can have multiple labels, up to a maximum of 64.
|
427
|
+
# * Each label must be a key-value pair.
|
428
|
+
# * Keys have a minimum length of 1 character and a maximum length of
|
429
|
+
# 63 characters, and cannot be empty. Values can be empty, and have
|
430
|
+
# a maximum length of 63 characters.
|
431
|
+
# * Keys and values can contain only lowercase letters, numeric characters,
|
432
|
+
# underscores, and dashes. All characters must use UTF-8 encoding, and
|
433
|
+
# international characters are allowed.
|
434
|
+
# * The key portion of a label must be unique. However, you can use the
|
435
|
+
# same key with multiple resources.
|
436
|
+
# * Keys must start with a lowercase letter or international character.
|
421
437
|
# @param [Array<String>, String] udfs User-defined function resources
|
422
438
|
# used in a legacy SQL query. May be either a code resource to load from
|
423
439
|
# a Google Cloud Storage URI (`gs://bucket/path`), or an inline resource
|
@@ -1445,46 +1461,58 @@ module Google
|
|
1445
1461
|
end
|
1446
1462
|
|
1447
1463
|
##
|
1448
|
-
# Extracts the data from
|
1449
|
-
#
|
1450
|
-
#
|
1451
|
-
# calling {Job#reload!} and {Job#done?} to detect when the job
|
1452
|
-
# or simply block until the job is done by calling
|
1464
|
+
# Extracts the data from a table or exports a model to Google Cloud Storage
|
1465
|
+
# asynchronously, immediately returning an {ExtractJob} that can be used to
|
1466
|
+
# track the progress of the export job. The caller may poll the service by
|
1467
|
+
# repeatedly calling {Job#reload!} and {Job#done?} to detect when the job
|
1468
|
+
# is done, or simply block until the job is done by calling
|
1453
1469
|
# #{Job#wait_until_done!}. See {#extract} for the synchronous version.
|
1454
|
-
#
|
1455
|
-
#
|
1470
|
+
#
|
1471
|
+
# Use this method instead of {Table#extract_job} or {Model#extract_job} to
|
1472
|
+
# extract data from source tables or models in other projects.
|
1456
1473
|
#
|
1457
1474
|
# The geographic location for the job ("US", "EU", etc.) can be set via
|
1458
1475
|
# {ExtractJob::Updater#location=} in a block passed to this method.
|
1459
1476
|
#
|
1460
|
-
# @see https://cloud.google.com/bigquery/exporting-data
|
1461
|
-
# Exporting
|
1477
|
+
# @see https://cloud.google.com/bigquery/docs/exporting-data
|
1478
|
+
# Exporting table data
|
1479
|
+
# @see https://cloud.google.com/bigquery-ml/docs/exporting-models
|
1480
|
+
# Exporting models
|
1462
1481
|
#
|
1463
|
-
# @param [
|
1464
|
-
#
|
1465
|
-
# [Standard SQL Query
|
1482
|
+
# @param [Table, Model, String] source The source table or model for
|
1483
|
+
# the extract operation. This can be a table or model object; or a
|
1484
|
+
# table ID string as specified by the [Standard SQL Query
|
1466
1485
|
# Reference](https://cloud.google.com/bigquery/docs/reference/standard-sql/query-syntax#from-clause)
|
1467
1486
|
# (`project-name.dataset_id.table_id`) or the [Legacy SQL Query
|
1468
1487
|
# Reference](https://cloud.google.com/bigquery/query-reference#from)
|
1469
1488
|
# (`project-name:dataset_id.table_id`).
|
1470
1489
|
# @param [Google::Cloud::Storage::File, String, Array<String>]
|
1471
1490
|
# extract_url The Google Storage file or file URI pattern(s) to which
|
1472
|
-
# BigQuery should extract
|
1473
|
-
#
|
1474
|
-
#
|
1491
|
+
# BigQuery should extract. For a model export this value should be a
|
1492
|
+
# string ending in an object name prefix, since multiple objects will
|
1493
|
+
# be exported.
|
1494
|
+
# @param [String] format The exported file format. The default value for
|
1495
|
+
# tables is `csv`. Tables with nested or repeated fields cannot be
|
1496
|
+
# exported as CSV. The default value for models is `ml_tf_saved_model`.
|
1475
1497
|
#
|
1476
|
-
#
|
1498
|
+
# Supported values for tables:
|
1477
1499
|
#
|
1478
1500
|
# * `csv` - CSV
|
1479
1501
|
# * `json` - [Newline-delimited JSON](http://jsonlines.org/)
|
1480
1502
|
# * `avro` - [Avro](http://avro.apache.org/)
|
1503
|
+
#
|
1504
|
+
# Supported values for models:
|
1505
|
+
#
|
1506
|
+
# * `ml_tf_saved_model` - TensorFlow SavedModel
|
1507
|
+
# * `ml_xgboost_booster` - XGBoost Booster
|
1481
1508
|
# @param [String] compression The compression type to use for exported
|
1482
1509
|
# files. Possible values include `GZIP` and `NONE`. The default value
|
1483
|
-
# is `NONE`.
|
1510
|
+
# is `NONE`. Not applicable when extracting models.
|
1484
1511
|
# @param [String] delimiter Delimiter to use between fields in the
|
1485
|
-
# exported data. Default is
|
1486
|
-
#
|
1487
|
-
#
|
1512
|
+
# exported table data. Default is `,`. Not applicable when extracting
|
1513
|
+
# models.
|
1514
|
+
# @param [Boolean] header Whether to print out a header row in table
|
1515
|
+
# exports. Default is `true`. Not applicable when extracting models.
|
1488
1516
|
# @param [String] job_id A user-defined ID for the extract job. The ID
|
1489
1517
|
# must contain only letters (a-z, A-Z), numbers (0-9), underscores
|
1490
1518
|
# (_), or dashes (-). The maximum length is 1,024 characters. If
|
@@ -1501,40 +1529,60 @@ module Google
|
|
1501
1529
|
# is 1,024 characters. If `job_id` is provided, then `prefix` will not
|
1502
1530
|
# be used.
|
1503
1531
|
# @param [Hash] labels A hash of user-provided labels associated with
|
1504
|
-
# the job. You can use these to organize and group your jobs.
|
1505
|
-
#
|
1506
|
-
#
|
1507
|
-
#
|
1508
|
-
#
|
1509
|
-
#
|
1510
|
-
#
|
1532
|
+
# the job. You can use these to organize and group your jobs.
|
1533
|
+
#
|
1534
|
+
# The labels applied to a resource must meet the following requirements:
|
1535
|
+
#
|
1536
|
+
# * Each resource can have multiple labels, up to a maximum of 64.
|
1537
|
+
# * Each label must be a key-value pair.
|
1538
|
+
# * Keys have a minimum length of 1 character and a maximum length of
|
1539
|
+
# 63 characters, and cannot be empty. Values can be empty, and have
|
1540
|
+
# a maximum length of 63 characters.
|
1541
|
+
# * Keys and values can contain only lowercase letters, numeric characters,
|
1542
|
+
# underscores, and dashes. All characters must use UTF-8 encoding, and
|
1543
|
+
# international characters are allowed.
|
1544
|
+
# * The key portion of a label must be unique. However, you can use the
|
1545
|
+
# same key with multiple resources.
|
1546
|
+
# * Keys must start with a lowercase letter or international character.
|
1511
1547
|
# @yield [job] a job configuration object
|
1512
1548
|
# @yieldparam [Google::Cloud::Bigquery::ExtractJob::Updater] job a job
|
1513
1549
|
# configuration object for setting additional options.
|
1514
1550
|
#
|
1515
1551
|
# @return [Google::Cloud::Bigquery::ExtractJob]
|
1516
1552
|
#
|
1517
|
-
# @example
|
1553
|
+
# @example Export table data
|
1518
1554
|
# require "google/cloud/bigquery"
|
1519
1555
|
#
|
1520
1556
|
# bigquery = Google::Cloud::Bigquery.new
|
1521
1557
|
#
|
1522
1558
|
# table_id = "bigquery-public-data.samples.shakespeare"
|
1523
|
-
# extract_job = bigquery.extract_job table_id,
|
1524
|
-
# "gs://my-bucket/shakespeare.csv"
|
1559
|
+
# extract_job = bigquery.extract_job table_id, "gs://my-bucket/shakespeare.csv"
|
1525
1560
|
# extract_job.wait_until_done!
|
1526
1561
|
# extract_job.done? #=> true
|
1527
1562
|
#
|
1563
|
+
# @example Export a model
|
1564
|
+
# require "google/cloud/bigquery"
|
1565
|
+
#
|
1566
|
+
# bigquery = Google::Cloud::Bigquery.new
|
1567
|
+
# dataset = bigquery.dataset "my_dataset"
|
1568
|
+
# model = dataset.model "my_model"
|
1569
|
+
#
|
1570
|
+
# extract_job = bigquery.extract model, "gs://my-bucket/#{model.model_id}"
|
1571
|
+
#
|
1528
1572
|
# @!group Data
|
1529
1573
|
#
|
1530
|
-
def extract_job
|
1574
|
+
def extract_job source, extract_url, format: nil, compression: nil, delimiter: nil, header: nil, job_id: nil,
|
1531
1575
|
prefix: nil, labels: nil
|
1532
1576
|
ensure_service!
|
1533
1577
|
options = { format: format, compression: compression, delimiter: delimiter, header: header, job_id: job_id,
|
1534
1578
|
prefix: prefix, labels: labels }
|
1579
|
+
source_ref = if source.respond_to? :model_ref
|
1580
|
+
source.model_ref
|
1581
|
+
else
|
1582
|
+
Service.get_table_ref source, default_ref: project_ref
|
1583
|
+
end
|
1535
1584
|
|
1536
|
-
|
1537
|
-
updater = ExtractJob::Updater.from_options service, table_ref, extract_url, options
|
1585
|
+
updater = ExtractJob::Updater.from_options service, source_ref, extract_url, options
|
1538
1586
|
|
1539
1587
|
yield updater if block_given?
|
1540
1588
|
|
@@ -1544,51 +1592,63 @@ module Google
|
|
1544
1592
|
end
|
1545
1593
|
|
1546
1594
|
##
|
1547
|
-
# Extracts the data from
|
1548
|
-
#
|
1595
|
+
# Extracts the data from a table or exports a model to Google Cloud Storage
|
1596
|
+
# using a synchronous method that blocks for a response. Timeouts
|
1549
1597
|
# and transient errors are generally handled as needed to complete the
|
1550
|
-
# job. See {#extract_job} for the asynchronous version.
|
1551
|
-
#
|
1552
|
-
#
|
1598
|
+
# job. See {#extract_job} for the asynchronous version.
|
1599
|
+
#
|
1600
|
+
# Use this method instead of {Table#extract} or {Model#extract} to
|
1601
|
+
# extract data from source tables or models in other projects.
|
1553
1602
|
#
|
1554
1603
|
# The geographic location for the job ("US", "EU", etc.) can be set via
|
1555
1604
|
# {ExtractJob::Updater#location=} in a block passed to this method.
|
1556
1605
|
#
|
1557
|
-
# @see https://cloud.google.com/bigquery/exporting-data
|
1558
|
-
# Exporting
|
1606
|
+
# @see https://cloud.google.com/bigquery/docs/exporting-data
|
1607
|
+
# Exporting table data
|
1608
|
+
# @see https://cloud.google.com/bigquery-ml/docs/exporting-models
|
1609
|
+
# Exporting models
|
1559
1610
|
#
|
1560
|
-
# @param [
|
1561
|
-
#
|
1562
|
-
# [Standard SQL Query
|
1611
|
+
# @param [Table, Model, String] source The source table or model for
|
1612
|
+
# the extract operation. This can be a table or model object; or a
|
1613
|
+
# table ID string as specified by the [Standard SQL Query
|
1563
1614
|
# Reference](https://cloud.google.com/bigquery/docs/reference/standard-sql/query-syntax#from-clause)
|
1564
1615
|
# (`project-name.dataset_id.table_id`) or the [Legacy SQL Query
|
1565
1616
|
# Reference](https://cloud.google.com/bigquery/query-reference#from)
|
1566
1617
|
# (`project-name:dataset_id.table_id`).
|
1567
1618
|
# @param [Google::Cloud::Storage::File, String, Array<String>]
|
1568
1619
|
# extract_url The Google Storage file or file URI pattern(s) to which
|
1569
|
-
# BigQuery should extract
|
1570
|
-
#
|
1571
|
-
#
|
1620
|
+
# BigQuery should extract. For a model export this value should be a
|
1621
|
+
# string ending in an object name prefix, since multiple objects will
|
1622
|
+
# be exported.
|
1623
|
+
# @param [String] format The exported file format. The default value for
|
1624
|
+
# tables is `csv`. Tables with nested or repeated fields cannot be
|
1625
|
+
# exported as CSV. The default value for models is `ml_tf_saved_model`.
|
1572
1626
|
#
|
1573
|
-
#
|
1627
|
+
# Supported values for tables:
|
1574
1628
|
#
|
1575
1629
|
# * `csv` - CSV
|
1576
1630
|
# * `json` - [Newline-delimited JSON](http://jsonlines.org/)
|
1577
1631
|
# * `avro` - [Avro](http://avro.apache.org/)
|
1632
|
+
#
|
1633
|
+
# Supported values for models:
|
1634
|
+
#
|
1635
|
+
# * `ml_tf_saved_model` - TensorFlow SavedModel
|
1636
|
+
# * `ml_xgboost_booster` - XGBoost Booster
|
1578
1637
|
# @param [String] compression The compression type to use for exported
|
1579
1638
|
# files. Possible values include `GZIP` and `NONE`. The default value
|
1580
|
-
# is `NONE`.
|
1639
|
+
# is `NONE`. Not applicable when extracting models.
|
1581
1640
|
# @param [String] delimiter Delimiter to use between fields in the
|
1582
|
-
# exported data. Default is
|
1583
|
-
#
|
1584
|
-
#
|
1641
|
+
# exported table data. Default is `,`. Not applicable when extracting
|
1642
|
+
# models.
|
1643
|
+
# @param [Boolean] header Whether to print out a header row in table
|
1644
|
+
# exports. Default is `true`. Not applicable when extracting models.
|
1585
1645
|
# @yield [job] a job configuration object
|
1586
1646
|
# @yieldparam [Google::Cloud::Bigquery::ExtractJob::Updater] job a job
|
1587
1647
|
# configuration object for setting additional options.
|
1588
1648
|
#
|
1589
1649
|
# @return [Boolean] Returns `true` if the extract operation succeeded.
|
1590
1650
|
#
|
1591
|
-
# @example
|
1651
|
+
# @example Export table data
|
1592
1652
|
# require "google/cloud/bigquery"
|
1593
1653
|
#
|
1594
1654
|
# bigquery = Google::Cloud::Bigquery.new
|
@@ -1596,10 +1656,19 @@ module Google
|
|
1596
1656
|
# bigquery.extract "bigquery-public-data.samples.shakespeare",
|
1597
1657
|
# "gs://my-bucket/shakespeare.csv"
|
1598
1658
|
#
|
1659
|
+
# @example Export a model
|
1660
|
+
# require "google/cloud/bigquery"
|
1661
|
+
#
|
1662
|
+
# bigquery = Google::Cloud::Bigquery.new
|
1663
|
+
# dataset = bigquery.dataset "my_dataset"
|
1664
|
+
# model = dataset.model "my_model"
|
1665
|
+
#
|
1666
|
+
# bigquery.extract model, "gs://my-bucket/#{model.model_id}"
|
1667
|
+
#
|
1599
1668
|
# @!group Data
|
1600
1669
|
#
|
1601
|
-
def extract
|
1602
|
-
job = extract_job
|
1670
|
+
def extract source, extract_url, format: nil, compression: nil, delimiter: nil, header: nil, &block
|
1671
|
+
job = extract_job source, extract_url,
|
1603
1672
|
format: format,
|
1604
1673
|
compression: compression,
|
1605
1674
|
delimiter: delimiter,
|