google-cloud-bigquery 1.14.0 → 1.42.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/AUTHENTICATION.md +17 -54
- data/CHANGELOG.md +377 -0
- data/CONTRIBUTING.md +328 -116
- data/LOGGING.md +1 -1
- data/OVERVIEW.md +21 -20
- data/TROUBLESHOOTING.md +2 -8
- data/lib/google/cloud/bigquery/argument.rb +197 -0
- data/lib/google/cloud/bigquery/convert.rb +155 -173
- data/lib/google/cloud/bigquery/copy_job.rb +74 -26
- data/lib/google/cloud/bigquery/credentials.rb +5 -12
- data/lib/google/cloud/bigquery/data.rb +109 -18
- data/lib/google/cloud/bigquery/dataset/access.rb +474 -52
- data/lib/google/cloud/bigquery/dataset/list.rb +7 -13
- data/lib/google/cloud/bigquery/dataset/tag.rb +67 -0
- data/lib/google/cloud/bigquery/dataset.rb +1044 -287
- data/lib/google/cloud/bigquery/external/avro_source.rb +107 -0
- data/lib/google/cloud/bigquery/external/bigtable_source/column.rb +404 -0
- data/lib/google/cloud/bigquery/external/bigtable_source/column_family.rb +945 -0
- data/lib/google/cloud/bigquery/external/bigtable_source.rb +230 -0
- data/lib/google/cloud/bigquery/external/csv_source.rb +481 -0
- data/lib/google/cloud/bigquery/external/data_source.rb +771 -0
- data/lib/google/cloud/bigquery/external/json_source.rb +170 -0
- data/lib/google/cloud/bigquery/external/parquet_source.rb +148 -0
- data/lib/google/cloud/bigquery/external/sheets_source.rb +166 -0
- data/lib/google/cloud/bigquery/external.rb +50 -2256
- data/lib/google/cloud/bigquery/extract_job.rb +226 -61
- data/lib/google/cloud/bigquery/insert_response.rb +1 -3
- data/lib/google/cloud/bigquery/job/list.rb +10 -14
- data/lib/google/cloud/bigquery/job.rb +289 -14
- data/lib/google/cloud/bigquery/load_job.rb +810 -136
- data/lib/google/cloud/bigquery/model/list.rb +5 -9
- data/lib/google/cloud/bigquery/model.rb +247 -16
- data/lib/google/cloud/bigquery/policy.rb +432 -0
- data/lib/google/cloud/bigquery/project/list.rb +6 -11
- data/lib/google/cloud/bigquery/project.rb +509 -250
- data/lib/google/cloud/bigquery/query_job.rb +594 -128
- data/lib/google/cloud/bigquery/routine/list.rb +165 -0
- data/lib/google/cloud/bigquery/routine.rb +1227 -0
- data/lib/google/cloud/bigquery/schema/field.rb +413 -63
- data/lib/google/cloud/bigquery/schema.rb +221 -48
- data/lib/google/cloud/bigquery/service.rb +204 -112
- data/lib/google/cloud/bigquery/standard_sql.rb +269 -53
- data/lib/google/cloud/bigquery/table/async_inserter.rb +86 -43
- data/lib/google/cloud/bigquery/table/list.rb +6 -11
- data/lib/google/cloud/bigquery/table.rb +1470 -377
- data/lib/google/cloud/bigquery/time.rb +6 -0
- data/lib/google/cloud/bigquery/version.rb +1 -1
- data/lib/google/cloud/bigquery.rb +4 -6
- data/lib/google-cloud-bigquery.rb +14 -13
- metadata +66 -38
@@ -0,0 +1,771 @@
|
|
1
|
+
# Copyright 2021 Google LLC
|
2
|
+
#
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
# you may not use this file except in compliance with the License.
|
5
|
+
# You may obtain a copy of the License at
|
6
|
+
#
|
7
|
+
# https://www.apache.org/licenses/LICENSE-2.0
|
8
|
+
#
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
+
# See the License for the specific language governing permissions and
|
13
|
+
# limitations under the License.
|
14
|
+
|
15
|
+
|
16
|
+
require "google/apis/bigquery_v2"
|
17
|
+
|
18
|
+
module Google
|
19
|
+
module Cloud
|
20
|
+
module Bigquery
|
21
|
+
module External
|
22
|
+
##
|
23
|
+
# # DataSource
|
24
|
+
#
|
25
|
+
# External::DataSource and its subclasses represents an external data
|
26
|
+
# source that can be queried from directly, even though the data is not
|
27
|
+
# stored in BigQuery. Instead of loading or streaming the data, this
|
28
|
+
# object references the external data source.
|
29
|
+
#
|
30
|
+
# The AVRO and Datastore Backup formats use {External::DataSource}. See
|
31
|
+
# {External::CsvSource}, {External::JsonSource},
|
32
|
+
# {External::SheetsSource}, {External::BigtableSource} for the other
|
33
|
+
# formats.
|
34
|
+
#
|
35
|
+
# @example
|
36
|
+
# require "google/cloud/bigquery"
|
37
|
+
#
|
38
|
+
# bigquery = Google::Cloud::Bigquery.new
|
39
|
+
#
|
40
|
+
# avro_url = "gs://bucket/path/to/*.avro"
|
41
|
+
# avro_table = bigquery.external avro_url do |avro|
|
42
|
+
# avro.autodetect = true
|
43
|
+
# end
|
44
|
+
#
|
45
|
+
# data = bigquery.query "SELECT * FROM my_ext_table",
|
46
|
+
# external: { my_ext_table: avro_table }
|
47
|
+
#
|
48
|
+
# # Iterate over the first page of results
|
49
|
+
# data.each do |row|
|
50
|
+
# puts row[:name]
|
51
|
+
# end
|
52
|
+
# # Retrieve the next page of results
|
53
|
+
# data = data.next if data.next?
|
54
|
+
#
|
55
|
+
# @example Hive partitioning options:
|
56
|
+
# require "google/cloud/bigquery"
|
57
|
+
#
|
58
|
+
# bigquery = Google::Cloud::Bigquery.new
|
59
|
+
#
|
60
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
61
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
62
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
63
|
+
# ext.hive_partitioning_mode = :auto
|
64
|
+
# ext.hive_partitioning_require_partition_filter = true
|
65
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
66
|
+
# end
|
67
|
+
#
|
68
|
+
# external_data.hive_partitioning? #=> true
|
69
|
+
# external_data.hive_partitioning_mode #=> "AUTO"
|
70
|
+
# external_data.hive_partitioning_require_partition_filter? #=> true
|
71
|
+
# external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
|
72
|
+
#
|
73
|
+
class DataSource
|
74
|
+
##
|
75
|
+
# @private The Google API Client object.
|
76
|
+
attr_accessor :gapi
|
77
|
+
|
78
|
+
##
|
79
|
+
# @private Create an empty Table object.
|
80
|
+
def initialize
|
81
|
+
@gapi = Google::Apis::BigqueryV2::ExternalDataConfiguration.new
|
82
|
+
end
|
83
|
+
|
84
|
+
##
|
85
|
+
# The data format. For CSV files, specify "CSV". For Google sheets,
|
86
|
+
# specify "GOOGLE_SHEETS". For newline-delimited JSON, specify
|
87
|
+
# "NEWLINE_DELIMITED_JSON". For Avro files, specify "AVRO". For Google
|
88
|
+
# Cloud Datastore backups, specify "DATASTORE_BACKUP". [Beta] For
|
89
|
+
# Google Cloud Bigtable, specify "BIGTABLE".
|
90
|
+
#
|
91
|
+
# @return [String]
|
92
|
+
#
|
93
|
+
# @example
|
94
|
+
# require "google/cloud/bigquery"
|
95
|
+
#
|
96
|
+
# bigquery = Google::Cloud::Bigquery.new
|
97
|
+
#
|
98
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
99
|
+
# csv_table = bigquery.external csv_url
|
100
|
+
#
|
101
|
+
# csv_table.format #=> "CSV"
|
102
|
+
#
|
103
|
+
def format
|
104
|
+
@gapi.source_format
|
105
|
+
end
|
106
|
+
|
107
|
+
##
|
108
|
+
# Whether the data format is "CSV".
|
109
|
+
#
|
110
|
+
# @return [Boolean]
|
111
|
+
#
|
112
|
+
# @example
|
113
|
+
# require "google/cloud/bigquery"
|
114
|
+
#
|
115
|
+
# bigquery = Google::Cloud::Bigquery.new
|
116
|
+
#
|
117
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
118
|
+
# csv_table = bigquery.external csv_url
|
119
|
+
#
|
120
|
+
# csv_table.format #=> "CSV"
|
121
|
+
# csv_table.csv? #=> true
|
122
|
+
#
|
123
|
+
def csv?
|
124
|
+
@gapi.source_format == "CSV"
|
125
|
+
end
|
126
|
+
|
127
|
+
##
|
128
|
+
# Whether the data format is "NEWLINE_DELIMITED_JSON".
|
129
|
+
#
|
130
|
+
# @return [Boolean]
|
131
|
+
#
|
132
|
+
# @example
|
133
|
+
# require "google/cloud/bigquery"
|
134
|
+
#
|
135
|
+
# bigquery = Google::Cloud::Bigquery.new
|
136
|
+
#
|
137
|
+
# json_url = "gs://bucket/path/to/data.json"
|
138
|
+
# json_table = bigquery.external json_url
|
139
|
+
#
|
140
|
+
# json_table.format #=> "NEWLINE_DELIMITED_JSON"
|
141
|
+
# json_table.json? #=> true
|
142
|
+
#
|
143
|
+
def json?
|
144
|
+
@gapi.source_format == "NEWLINE_DELIMITED_JSON"
|
145
|
+
end
|
146
|
+
|
147
|
+
##
|
148
|
+
# Whether the data format is "GOOGLE_SHEETS".
|
149
|
+
#
|
150
|
+
# @return [Boolean]
|
151
|
+
#
|
152
|
+
# @example
|
153
|
+
# require "google/cloud/bigquery"
|
154
|
+
#
|
155
|
+
# bigquery = Google::Cloud::Bigquery.new
|
156
|
+
#
|
157
|
+
# sheets_url = "https://docs.google.com/spreadsheets/d/1234567980"
|
158
|
+
# sheets_table = bigquery.external sheets_url
|
159
|
+
#
|
160
|
+
# sheets_table.format #=> "GOOGLE_SHEETS"
|
161
|
+
# sheets_table.sheets? #=> true
|
162
|
+
#
|
163
|
+
def sheets?
|
164
|
+
@gapi.source_format == "GOOGLE_SHEETS"
|
165
|
+
end
|
166
|
+
|
167
|
+
##
|
168
|
+
# Whether the data format is "AVRO".
|
169
|
+
#
|
170
|
+
# @return [Boolean]
|
171
|
+
#
|
172
|
+
# @example
|
173
|
+
# require "google/cloud/bigquery"
|
174
|
+
#
|
175
|
+
# bigquery = Google::Cloud::Bigquery.new
|
176
|
+
#
|
177
|
+
# avro_url = "gs://bucket/path/to/*.avro"
|
178
|
+
# avro_table = bigquery.external avro_url
|
179
|
+
#
|
180
|
+
# avro_table.format #=> "AVRO"
|
181
|
+
# avro_table.avro? #=> true
|
182
|
+
#
|
183
|
+
def avro?
|
184
|
+
@gapi.source_format == "AVRO"
|
185
|
+
end
|
186
|
+
|
187
|
+
##
|
188
|
+
# Whether the data format is "DATASTORE_BACKUP".
|
189
|
+
#
|
190
|
+
# @return [Boolean]
|
191
|
+
#
|
192
|
+
# @example
|
193
|
+
# require "google/cloud/bigquery"
|
194
|
+
#
|
195
|
+
# bigquery = Google::Cloud::Bigquery.new
|
196
|
+
#
|
197
|
+
# backup_url = "gs://bucket/path/to/data.backup_info"
|
198
|
+
# backup_table = bigquery.external backup_url
|
199
|
+
#
|
200
|
+
# backup_table.format #=> "DATASTORE_BACKUP"
|
201
|
+
# backup_table.backup? #=> true
|
202
|
+
#
|
203
|
+
def backup?
|
204
|
+
@gapi.source_format == "DATASTORE_BACKUP"
|
205
|
+
end
|
206
|
+
|
207
|
+
##
|
208
|
+
# Whether the data format is "BIGTABLE".
|
209
|
+
#
|
210
|
+
# @return [Boolean]
|
211
|
+
#
|
212
|
+
# @example
|
213
|
+
# require "google/cloud/bigquery"
|
214
|
+
#
|
215
|
+
# bigquery = Google::Cloud::Bigquery.new
|
216
|
+
#
|
217
|
+
# bigtable_url = "https://googleapis.com/bigtable/projects/..."
|
218
|
+
# bigtable_table = bigquery.external bigtable_url
|
219
|
+
#
|
220
|
+
# bigtable_table.format #=> "BIGTABLE"
|
221
|
+
# bigtable_table.bigtable? #=> true
|
222
|
+
#
|
223
|
+
def bigtable?
|
224
|
+
@gapi.source_format == "BIGTABLE"
|
225
|
+
end
|
226
|
+
|
227
|
+
##
|
228
|
+
# Whether the data format is "ORC".
|
229
|
+
#
|
230
|
+
# @return [Boolean]
|
231
|
+
#
|
232
|
+
# @example
|
233
|
+
# require "google/cloud/bigquery"
|
234
|
+
#
|
235
|
+
# bigquery = Google::Cloud::Bigquery.new
|
236
|
+
#
|
237
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
238
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
239
|
+
# external_data = bigquery.external gcs_uri, format: :orc do |ext|
|
240
|
+
# ext.hive_partitioning_mode = :auto
|
241
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
242
|
+
# end
|
243
|
+
# external_data.format #=> "ORC"
|
244
|
+
# external_data.orc? #=> true
|
245
|
+
#
|
246
|
+
def orc?
|
247
|
+
@gapi.source_format == "ORC"
|
248
|
+
end
|
249
|
+
|
250
|
+
##
|
251
|
+
# Whether the data format is "PARQUET".
|
252
|
+
#
|
253
|
+
# @return [Boolean]
|
254
|
+
#
|
255
|
+
# @example
|
256
|
+
# require "google/cloud/bigquery"
|
257
|
+
#
|
258
|
+
# bigquery = Google::Cloud::Bigquery.new
|
259
|
+
#
|
260
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
261
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
262
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
263
|
+
# ext.hive_partitioning_mode = :auto
|
264
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
265
|
+
# end
|
266
|
+
# external_data.format #=> "PARQUET"
|
267
|
+
# external_data.parquet? #=> true
|
268
|
+
#
|
269
|
+
def parquet?
|
270
|
+
@gapi.source_format == "PARQUET"
|
271
|
+
end
|
272
|
+
|
273
|
+
##
|
274
|
+
# The fully-qualified URIs that point to your data in Google Cloud.
|
275
|
+
# For Google Cloud Storage URIs: Each URI can contain one '*' wildcard
|
276
|
+
# character and it must come after the 'bucket' name. Size limits
|
277
|
+
# related to load jobs apply to external data sources. For Google
|
278
|
+
# Cloud Bigtable URIs: Exactly one URI can be specified and it has be
|
279
|
+
# a fully specified and valid HTTPS URL for a Google Cloud Bigtable
|
280
|
+
# table. For Google Cloud Datastore backups, exactly one URI can be
|
281
|
+
# specified, and it must end with '.backup_info'. Also, the '*'
|
282
|
+
# wildcard character is not allowed.
|
283
|
+
#
|
284
|
+
# @return [Array<String>]
|
285
|
+
#
|
286
|
+
# @example
|
287
|
+
# require "google/cloud/bigquery"
|
288
|
+
#
|
289
|
+
# bigquery = Google::Cloud::Bigquery.new
|
290
|
+
#
|
291
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
292
|
+
# csv_table = bigquery.external csv_url
|
293
|
+
#
|
294
|
+
# csv_table.urls #=> ["gs://bucket/path/to/data.csv"]
|
295
|
+
#
|
296
|
+
def urls
|
297
|
+
@gapi.source_uris
|
298
|
+
end
|
299
|
+
|
300
|
+
##
|
301
|
+
# Indicates if the schema and format options are detected
|
302
|
+
# automatically.
|
303
|
+
#
|
304
|
+
# @return [Boolean]
|
305
|
+
#
|
306
|
+
# @example
|
307
|
+
# require "google/cloud/bigquery"
|
308
|
+
#
|
309
|
+
# bigquery = Google::Cloud::Bigquery.new
|
310
|
+
#
|
311
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
312
|
+
# csv_table = bigquery.external csv_url do |csv|
|
313
|
+
# csv.autodetect = true
|
314
|
+
# end
|
315
|
+
#
|
316
|
+
# csv_table.autodetect #=> true
|
317
|
+
#
|
318
|
+
def autodetect
|
319
|
+
@gapi.autodetect
|
320
|
+
end
|
321
|
+
|
322
|
+
##
|
323
|
+
# Set whether to detect schema and format options automatically. Any
|
324
|
+
# option specified explicitly will be honored.
|
325
|
+
#
|
326
|
+
# @param [Boolean] new_autodetect New autodetect value
|
327
|
+
#
|
328
|
+
# @example
|
329
|
+
# require "google/cloud/bigquery"
|
330
|
+
#
|
331
|
+
# bigquery = Google::Cloud::Bigquery.new
|
332
|
+
#
|
333
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
334
|
+
# csv_table = bigquery.external csv_url do |csv|
|
335
|
+
# csv.autodetect = true
|
336
|
+
# end
|
337
|
+
#
|
338
|
+
# csv_table.autodetect #=> true
|
339
|
+
#
|
340
|
+
def autodetect= new_autodetect
|
341
|
+
frozen_check!
|
342
|
+
@gapi.autodetect = new_autodetect
|
343
|
+
end
|
344
|
+
|
345
|
+
##
|
346
|
+
# The compression type of the data source. Possible values include
|
347
|
+
# `"GZIP"` and `nil`. The default value is `nil`. This setting is
|
348
|
+
# ignored for Google Cloud Bigtable, Google Cloud Datastore backups
|
349
|
+
# and Avro formats. Optional.
|
350
|
+
#
|
351
|
+
# @return [String]
|
352
|
+
#
|
353
|
+
# @example
|
354
|
+
# require "google/cloud/bigquery"
|
355
|
+
#
|
356
|
+
# bigquery = Google::Cloud::Bigquery.new
|
357
|
+
#
|
358
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
359
|
+
# csv_table = bigquery.external csv_url do |csv|
|
360
|
+
# csv.compression = "GZIP"
|
361
|
+
# end
|
362
|
+
#
|
363
|
+
# csv_table.compression #=> "GZIP"
|
364
|
+
def compression
|
365
|
+
@gapi.compression
|
366
|
+
end
|
367
|
+
|
368
|
+
##
|
369
|
+
# Set the compression type of the data source. Possible values include
|
370
|
+
# `"GZIP"` and `nil`. The default value is `nil`. This setting is
|
371
|
+
# ignored for Google Cloud Bigtable, Google Cloud Datastore backups
|
372
|
+
# and Avro formats. Optional.
|
373
|
+
#
|
374
|
+
# @param [String] new_compression New compression value
|
375
|
+
#
|
376
|
+
# @example
|
377
|
+
# require "google/cloud/bigquery"
|
378
|
+
#
|
379
|
+
# bigquery = Google::Cloud::Bigquery.new
|
380
|
+
#
|
381
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
382
|
+
# csv_table = bigquery.external csv_url do |csv|
|
383
|
+
# csv.compression = "GZIP"
|
384
|
+
# end
|
385
|
+
#
|
386
|
+
# csv_table.compression #=> "GZIP"
|
387
|
+
#
|
388
|
+
def compression= new_compression
|
389
|
+
frozen_check!
|
390
|
+
@gapi.compression = new_compression
|
391
|
+
end
|
392
|
+
|
393
|
+
##
|
394
|
+
# Indicates if BigQuery should allow extra values that are not
|
395
|
+
# represented in the table schema. If `true`, the extra values are
|
396
|
+
# ignored. If `false`, records with extra columns are treated as bad
|
397
|
+
# records, and if there are too many bad records, an invalid error is
|
398
|
+
# returned in the job result. The default value is `false`.
|
399
|
+
#
|
400
|
+
# BigQuery treats trailing columns as an extra in `CSV`, named values
|
401
|
+
# that don't match any column names in `JSON`. This setting is ignored
|
402
|
+
# for Google Cloud Bigtable, Google Cloud Datastore backups and Avro
|
403
|
+
# formats. Optional.
|
404
|
+
#
|
405
|
+
# @return [Boolean]
|
406
|
+
#
|
407
|
+
# @example
|
408
|
+
# require "google/cloud/bigquery"
|
409
|
+
#
|
410
|
+
# bigquery = Google::Cloud::Bigquery.new
|
411
|
+
#
|
412
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
413
|
+
# csv_table = bigquery.external csv_url do |csv|
|
414
|
+
# csv.ignore_unknown = true
|
415
|
+
# end
|
416
|
+
#
|
417
|
+
# csv_table.ignore_unknown #=> true
|
418
|
+
#
|
419
|
+
def ignore_unknown
|
420
|
+
@gapi.ignore_unknown_values
|
421
|
+
end
|
422
|
+
|
423
|
+
##
|
424
|
+
# Set whether BigQuery should allow extra values that are not
|
425
|
+
# represented in the table schema. If `true`, the extra values are
|
426
|
+
# ignored. If `false`, records with extra columns are treated as bad
|
427
|
+
# records, and if there are too many bad records, an invalid error is
|
428
|
+
# returned in the job result. The default value is `false`.
|
429
|
+
#
|
430
|
+
# BigQuery treats trailing columns as an extra in `CSV`, named values
|
431
|
+
# that don't match any column names in `JSON`. This setting is ignored
|
432
|
+
# for Google Cloud Bigtable, Google Cloud Datastore backups and Avro
|
433
|
+
# formats. Optional.
|
434
|
+
#
|
435
|
+
# @param [Boolean] new_ignore_unknown New ignore_unknown value
|
436
|
+
#
|
437
|
+
# @example
|
438
|
+
# require "google/cloud/bigquery"
|
439
|
+
#
|
440
|
+
# bigquery = Google::Cloud::Bigquery.new
|
441
|
+
#
|
442
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
443
|
+
# csv_table = bigquery.external csv_url do |csv|
|
444
|
+
# csv.ignore_unknown = true
|
445
|
+
# end
|
446
|
+
#
|
447
|
+
# csv_table.ignore_unknown #=> true
|
448
|
+
#
|
449
|
+
def ignore_unknown= new_ignore_unknown
|
450
|
+
frozen_check!
|
451
|
+
@gapi.ignore_unknown_values = new_ignore_unknown
|
452
|
+
end
|
453
|
+
|
454
|
+
##
|
455
|
+
# The maximum number of bad records that BigQuery can ignore when
|
456
|
+
# reading data. If the number of bad records exceeds this value, an
|
457
|
+
# invalid error is returned in the job result. The default value is 0,
|
458
|
+
# which requires that all records are valid. This setting is ignored
|
459
|
+
# for Google Cloud Bigtable, Google Cloud Datastore backups and Avro
|
460
|
+
# formats.
|
461
|
+
#
|
462
|
+
# @return [Integer]
|
463
|
+
#
|
464
|
+
# @example
|
465
|
+
# require "google/cloud/bigquery"
|
466
|
+
#
|
467
|
+
# bigquery = Google::Cloud::Bigquery.new
|
468
|
+
#
|
469
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
470
|
+
# csv_table = bigquery.external csv_url do |csv|
|
471
|
+
# csv.max_bad_records = 10
|
472
|
+
# end
|
473
|
+
#
|
474
|
+
# csv_table.max_bad_records #=> 10
|
475
|
+
#
|
476
|
+
def max_bad_records
|
477
|
+
@gapi.max_bad_records
|
478
|
+
end
|
479
|
+
|
480
|
+
##
|
481
|
+
# Set the maximum number of bad records that BigQuery can ignore when
|
482
|
+
# reading data. If the number of bad records exceeds this value, an
|
483
|
+
# invalid error is returned in the job result. The default value is 0,
|
484
|
+
# which requires that all records are valid. This setting is ignored
|
485
|
+
# for Google Cloud Bigtable, Google Cloud Datastore backups and Avro
|
486
|
+
# formats.
|
487
|
+
#
|
488
|
+
# @param [Integer] new_max_bad_records New max_bad_records value
|
489
|
+
#
|
490
|
+
# @example
|
491
|
+
# require "google/cloud/bigquery"
|
492
|
+
#
|
493
|
+
# bigquery = Google::Cloud::Bigquery.new
|
494
|
+
#
|
495
|
+
# csv_url = "gs://bucket/path/to/data.csv"
|
496
|
+
# csv_table = bigquery.external csv_url do |csv|
|
497
|
+
# csv.max_bad_records = 10
|
498
|
+
# end
|
499
|
+
#
|
500
|
+
# csv_table.max_bad_records #=> 10
|
501
|
+
#
|
502
|
+
def max_bad_records= new_max_bad_records
|
503
|
+
frozen_check!
|
504
|
+
@gapi.max_bad_records = new_max_bad_records
|
505
|
+
end
|
506
|
+
|
507
|
+
###
|
508
|
+
# Checks if hive partitioning options are set.
|
509
|
+
#
|
510
|
+
# Not all storage formats support hive partitioning. Requesting hive partitioning on an unsupported format
|
511
|
+
# will lead to an error. Currently supported types include: `avro`, `csv`, `json`, `orc` and `parquet`.
|
512
|
+
# If your data is stored in ORC or Parquet on Cloud Storage, see [Querying columnar formats on Cloud
|
513
|
+
# Storage](https://cloud.google.com/bigquery/pricing#columnar_formats_pricing).
|
514
|
+
#
|
515
|
+
# @return [Boolean] `true` when hive partitioning options are set, or `false` otherwise.
|
516
|
+
#
|
517
|
+
# @example
|
518
|
+
# require "google/cloud/bigquery"
|
519
|
+
#
|
520
|
+
# bigquery = Google::Cloud::Bigquery.new
|
521
|
+
#
|
522
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
523
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
524
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
525
|
+
# ext.hive_partitioning_mode = :auto
|
526
|
+
# ext.hive_partitioning_require_partition_filter = true
|
527
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
528
|
+
# end
|
529
|
+
#
|
530
|
+
# external_data.hive_partitioning? #=> true
|
531
|
+
# external_data.hive_partitioning_mode #=> "AUTO"
|
532
|
+
# external_data.hive_partitioning_require_partition_filter? #=> true
|
533
|
+
# external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
|
534
|
+
#
|
535
|
+
def hive_partitioning?
|
536
|
+
!@gapi.hive_partitioning_options.nil?
|
537
|
+
end
|
538
|
+
|
539
|
+
###
|
540
|
+
# The mode of hive partitioning to use when reading data. The following modes are supported:
|
541
|
+
#
|
542
|
+
# 1. `AUTO`: automatically infer partition key name(s) and type(s).
|
543
|
+
# 2. `STRINGS`: automatically infer partition key name(s). All types are interpreted as strings.
|
544
|
+
# 3. `CUSTOM`: partition key schema is encoded in the source URI prefix.
|
545
|
+
#
|
546
|
+
# @return [String, nil] The mode of hive partitioning, or `nil` if not set.
|
547
|
+
#
|
548
|
+
# @example
|
549
|
+
# require "google/cloud/bigquery"
|
550
|
+
#
|
551
|
+
# bigquery = Google::Cloud::Bigquery.new
|
552
|
+
#
|
553
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
554
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
555
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
556
|
+
# ext.hive_partitioning_mode = :auto
|
557
|
+
# ext.hive_partitioning_require_partition_filter = true
|
558
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
559
|
+
# end
|
560
|
+
#
|
561
|
+
# external_data.hive_partitioning? #=> true
|
562
|
+
# external_data.hive_partitioning_mode #=> "AUTO"
|
563
|
+
# external_data.hive_partitioning_require_partition_filter? #=> true
|
564
|
+
# external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
|
565
|
+
#
|
566
|
+
def hive_partitioning_mode
|
567
|
+
@gapi.hive_partitioning_options.mode if hive_partitioning?
|
568
|
+
end
|
569
|
+
|
570
|
+
##
|
571
|
+
# Sets the mode of hive partitioning to use when reading data. The following modes are supported:
|
572
|
+
#
|
573
|
+
# 1. `auto`: automatically infer partition key name(s) and type(s).
|
574
|
+
# 2. `strings`: automatically infer partition key name(s). All types are interpreted as strings.
|
575
|
+
# 3. `custom`: partition key schema is encoded in the source URI prefix.
|
576
|
+
#
|
577
|
+
# Not all storage formats support hive partitioning. Requesting hive partitioning on an unsupported format
|
578
|
+
# will lead to an error. Currently supported types include: `avro`, `csv`, `json`, `orc` and `parquet`.
|
579
|
+
# If your data is stored in ORC or Parquet on Cloud Storage, see [Querying columnar formats on Cloud
|
580
|
+
# Storage](https://cloud.google.com/bigquery/pricing#columnar_formats_pricing).
|
581
|
+
#
|
582
|
+
# See {#format}, {#hive_partitioning_require_partition_filter=} and {#hive_partitioning_source_uri_prefix=}.
|
583
|
+
#
|
584
|
+
# @param [String, Symbol] mode The mode of hive partitioning to use when reading data.
|
585
|
+
#
|
586
|
+
# @example
|
587
|
+
# require "google/cloud/bigquery"
|
588
|
+
#
|
589
|
+
# bigquery = Google::Cloud::Bigquery.new
|
590
|
+
#
|
591
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
592
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
593
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
594
|
+
# ext.hive_partitioning_mode = :auto
|
595
|
+
# ext.hive_partitioning_require_partition_filter = true
|
596
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
597
|
+
# end
|
598
|
+
#
|
599
|
+
# external_data.hive_partitioning? #=> true
|
600
|
+
# external_data.hive_partitioning_mode #=> "AUTO"
|
601
|
+
# external_data.hive_partitioning_require_partition_filter? #=> true
|
602
|
+
# external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
|
603
|
+
#
|
604
|
+
def hive_partitioning_mode= mode
|
605
|
+
@gapi.hive_partitioning_options ||= Google::Apis::BigqueryV2::HivePartitioningOptions.new
|
606
|
+
@gapi.hive_partitioning_options.mode = mode.to_s.upcase
|
607
|
+
end
|
608
|
+
|
609
|
+
###
|
610
|
+
# Whether queries over the table using this external data source require a partition filter that can be used
|
611
|
+
# for partition elimination to be specified. Note that this field should only be true when creating a
|
612
|
+
# permanent external table or querying a temporary external table.
|
613
|
+
#
|
614
|
+
# @return [Boolean] `true` when queries over this table require a partition filter, or `false` otherwise.
|
615
|
+
#
|
616
|
+
# @example
|
617
|
+
# require "google/cloud/bigquery"
|
618
|
+
#
|
619
|
+
# bigquery = Google::Cloud::Bigquery.new
|
620
|
+
#
|
621
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
622
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
623
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
624
|
+
# ext.hive_partitioning_mode = :auto
|
625
|
+
# ext.hive_partitioning_require_partition_filter = true
|
626
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
627
|
+
# end
|
628
|
+
#
|
629
|
+
# external_data.hive_partitioning? #=> true
|
630
|
+
# external_data.hive_partitioning_mode #=> "AUTO"
|
631
|
+
# external_data.hive_partitioning_require_partition_filter? #=> true
|
632
|
+
# external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
|
633
|
+
#
|
634
|
+
def hive_partitioning_require_partition_filter?
|
635
|
+
return false unless hive_partitioning?
|
636
|
+
!@gapi.hive_partitioning_options.require_partition_filter.nil?
|
637
|
+
end
|
638
|
+
|
639
|
+
##
|
640
|
+
# Sets whether queries over the table using this external data source require a partition filter
|
641
|
+
# that can be used for partition elimination to be specified.
|
642
|
+
#
|
643
|
+
# See {#format}, {#hive_partitioning_mode=} and {#hive_partitioning_source_uri_prefix=}.
|
644
|
+
#
|
645
|
+
# @param [Boolean] require_partition_filter `true` if a partition filter must be specified, `false` otherwise.
|
646
|
+
#
|
647
|
+
# @example
|
648
|
+
# require "google/cloud/bigquery"
|
649
|
+
#
|
650
|
+
# bigquery = Google::Cloud::Bigquery.new
|
651
|
+
#
|
652
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
653
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
654
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
655
|
+
# ext.hive_partitioning_mode = :auto
|
656
|
+
# ext.hive_partitioning_require_partition_filter = true
|
657
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
658
|
+
# end
|
659
|
+
#
|
660
|
+
# external_data.hive_partitioning? #=> true
|
661
|
+
# external_data.hive_partitioning_mode #=> "AUTO"
|
662
|
+
# external_data.hive_partitioning_require_partition_filter? #=> true
|
663
|
+
# external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
|
664
|
+
#
|
665
|
+
def hive_partitioning_require_partition_filter= require_partition_filter
|
666
|
+
@gapi.hive_partitioning_options ||= Google::Apis::BigqueryV2::HivePartitioningOptions.new
|
667
|
+
@gapi.hive_partitioning_options.require_partition_filter = require_partition_filter
|
668
|
+
end
|
669
|
+
|
670
|
+
###
|
671
|
+
# The common prefix for all source uris when hive partition detection is requested. The prefix must end
|
672
|
+
# immediately before the partition key encoding begins. For example, consider files following this data
|
673
|
+
# layout:
|
674
|
+
#
|
675
|
+
# ```
|
676
|
+
# gs://bucket/path_to_table/dt=2019-01-01/country=BR/id=7/file.avro
|
677
|
+
# gs://bucket/path_to_table/dt=2018-12-31/country=CA/id=3/file.avro
|
678
|
+
# ```
|
679
|
+
#
|
680
|
+
# When hive partitioning is requested with either `AUTO` or `STRINGS` mode, the common prefix can be either of
|
681
|
+
# `gs://bucket/path_to_table` or `gs://bucket/path_to_table/` (trailing slash does not matter).
|
682
|
+
#
|
683
|
+
# @return [String, nil] The common prefix for all source uris, or `nil` if not set.
|
684
|
+
#
|
685
|
+
# @example
|
686
|
+
# require "google/cloud/bigquery"
|
687
|
+
#
|
688
|
+
# bigquery = Google::Cloud::Bigquery.new
|
689
|
+
#
|
690
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
691
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
692
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
693
|
+
# ext.hive_partitioning_mode = :auto
|
694
|
+
# ext.hive_partitioning_require_partition_filter = true
|
695
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
696
|
+
# end
|
697
|
+
#
|
698
|
+
# external_data.hive_partitioning? #=> true
|
699
|
+
# external_data.hive_partitioning_mode #=> "AUTO"
|
700
|
+
# external_data.hive_partitioning_require_partition_filter? #=> true
|
701
|
+
# external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
|
702
|
+
#
|
703
|
+
def hive_partitioning_source_uri_prefix
|
704
|
+
@gapi.hive_partitioning_options.source_uri_prefix if hive_partitioning?
|
705
|
+
end
|
706
|
+
|
707
|
+
##
|
708
|
+
# Sets the common prefix for all source uris when hive partition detection is requested. The prefix must end
|
709
|
+
# immediately before the partition key encoding begins. For example, consider files following this data
|
710
|
+
# layout:
|
711
|
+
#
|
712
|
+
# ```
|
713
|
+
# gs://bucket/path_to_table/dt=2019-01-01/country=BR/id=7/file.avro
|
714
|
+
# gs://bucket/path_to_table/dt=2018-12-31/country=CA/id=3/file.avro
|
715
|
+
# ```
|
716
|
+
#
|
717
|
+
# When hive partitioning is requested with either `AUTO` or `STRINGS` mode, the common prefix can be either of
|
718
|
+
# `gs://bucket/path_to_table` or `gs://bucket/path_to_table/` (trailing slash does not matter).
|
719
|
+
#
|
720
|
+
# See {#format}, {#hive_partitioning_mode=} and {#hive_partitioning_require_partition_filter=}.
|
721
|
+
#
|
722
|
+
# @param [String] source_uri_prefix The common prefix for all source uris.
|
723
|
+
#
|
724
|
+
# @example
|
725
|
+
# require "google/cloud/bigquery"
|
726
|
+
#
|
727
|
+
# bigquery = Google::Cloud::Bigquery.new
|
728
|
+
#
|
729
|
+
# gcs_uri = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/*"
|
730
|
+
# source_uri_prefix = "gs://cloud-samples-data/bigquery/hive-partitioning-samples/autolayout/"
|
731
|
+
# external_data = bigquery.external gcs_uri, format: :parquet do |ext|
|
732
|
+
# ext.hive_partitioning_mode = :auto
|
733
|
+
# ext.hive_partitioning_require_partition_filter = true
|
734
|
+
# ext.hive_partitioning_source_uri_prefix = source_uri_prefix
|
735
|
+
# end
|
736
|
+
#
|
737
|
+
# external_data.hive_partitioning? #=> true
|
738
|
+
# external_data.hive_partitioning_mode #=> "AUTO"
|
739
|
+
# external_data.hive_partitioning_require_partition_filter? #=> true
|
740
|
+
# external_data.hive_partitioning_source_uri_prefix #=> source_uri_prefix
|
741
|
+
#
|
742
|
+
def hive_partitioning_source_uri_prefix= source_uri_prefix
|
743
|
+
@gapi.hive_partitioning_options ||= Google::Apis::BigqueryV2::HivePartitioningOptions.new
|
744
|
+
@gapi.hive_partitioning_options.source_uri_prefix = source_uri_prefix
|
745
|
+
end
|
746
|
+
|
747
|
+
##
|
748
|
+
# @private Google API Client object.
|
749
|
+
def to_gapi
|
750
|
+
@gapi
|
751
|
+
end
|
752
|
+
|
753
|
+
##
|
754
|
+
# @private Google API Client object.
|
755
|
+
def self.from_gapi gapi
|
756
|
+
new_table = new
|
757
|
+
new_table.instance_variable_set :@gapi, gapi
|
758
|
+
new_table
|
759
|
+
end
|
760
|
+
|
761
|
+
protected
|
762
|
+
|
763
|
+
def frozen_check!
|
764
|
+
return unless frozen?
|
765
|
+
raise ArgumentError, "Cannot modify external data source when frozen"
|
766
|
+
end
|
767
|
+
end
|
768
|
+
end
|
769
|
+
end
|
770
|
+
end
|
771
|
+
end
|