google-cloud-bigquery 1.12.0 → 1.38.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/AUTHENTICATION.md +9 -28
- data/CHANGELOG.md +372 -1
- data/CONTRIBUTING.md +328 -116
- data/LOGGING.md +2 -2
- 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 +154 -170
- data/lib/google/cloud/bigquery/copy_job.rb +40 -23
- 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 +322 -51
- data/lib/google/cloud/bigquery/dataset/list.rb +7 -13
- data/lib/google/cloud/bigquery/dataset.rb +960 -279
- 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 +217 -58
- data/lib/google/cloud/bigquery/insert_response.rb +1 -3
- data/lib/google/cloud/bigquery/job/list.rb +13 -20
- data/lib/google/cloud/bigquery/job.rb +286 -11
- data/lib/google/cloud/bigquery/load_job.rb +801 -133
- 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 +526 -243
- data/lib/google/cloud/bigquery/query_job.rb +584 -125
- 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 +186 -109
- data/lib/google/cloud/bigquery/standard_sql.rb +269 -53
- data/lib/google/cloud/bigquery/table/async_inserter.rb +86 -42
- data/lib/google/cloud/bigquery/table/list.rb +6 -11
- data/lib/google/cloud/bigquery/table.rb +1188 -326
- data/lib/google/cloud/bigquery/time.rb +6 -0
- data/lib/google/cloud/bigquery/version.rb +1 -1
- data/lib/google/cloud/bigquery.rb +18 -8
- data/lib/google-cloud-bigquery.rb +15 -13
- metadata +67 -40
@@ -19,7 +19,7 @@ require "google/cloud/errors"
|
|
19
19
|
require "google/apis/bigquery_v2"
|
20
20
|
require "pathname"
|
21
21
|
require "securerandom"
|
22
|
-
require "
|
22
|
+
require "mini_mime"
|
23
23
|
require "date"
|
24
24
|
|
25
25
|
module Google
|
@@ -39,15 +39,17 @@ module Google
|
|
39
39
|
attr_accessor :credentials
|
40
40
|
|
41
41
|
# @private
|
42
|
-
attr_reader :retries, :timeout
|
42
|
+
attr_reader :retries, :timeout, :host
|
43
43
|
|
44
44
|
##
|
45
45
|
# Creates a new Service instance.
|
46
|
-
def initialize project, credentials, retries: nil, timeout: nil
|
46
|
+
def initialize project, credentials, retries: nil, timeout: nil, host: nil, quota_project: nil
|
47
47
|
@project = project
|
48
48
|
@credentials = credentials
|
49
49
|
@retries = retries
|
50
50
|
@timeout = timeout
|
51
|
+
@host = host
|
52
|
+
@quota_project = quota_project
|
51
53
|
end
|
52
54
|
|
53
55
|
def service
|
@@ -55,8 +57,7 @@ module Google
|
|
55
57
|
@service ||= begin
|
56
58
|
service = API::BigqueryService.new
|
57
59
|
service.client_options.application_name = "gcloud-ruby"
|
58
|
-
service.client_options.application_version =
|
59
|
-
Google::Cloud::Bigquery::VERSION
|
60
|
+
service.client_options.application_version = Google::Cloud::Bigquery::VERSION
|
60
61
|
service.client_options.open_timeout_sec = timeout
|
61
62
|
service.client_options.read_timeout_sec = timeout
|
62
63
|
service.client_options.send_timeout_sec = timeout
|
@@ -64,7 +65,11 @@ module Google
|
|
64
65
|
service.request_options.header ||= {}
|
65
66
|
service.request_options.header["x-goog-api-client"] = \
|
66
67
|
"gl-ruby/#{RUBY_VERSION} gccl/#{Google::Cloud::Bigquery::VERSION}"
|
68
|
+
service.request_options.query ||= {}
|
69
|
+
service.request_options.query["prettyPrint"] = false
|
70
|
+
service.request_options.quota_project = @quota_project if @quota_project
|
67
71
|
service.authorization = @credentials.client
|
72
|
+
service.root_url = host if host
|
68
73
|
service
|
69
74
|
end
|
70
75
|
end
|
@@ -77,12 +82,10 @@ module Google
|
|
77
82
|
##
|
78
83
|
# Lists all datasets in the specified project to which you have
|
79
84
|
# been granted the READER dataset role.
|
80
|
-
def list_datasets
|
85
|
+
def list_datasets all: nil, filter: nil, max: nil, token: nil
|
81
86
|
# The list operation is considered idempotent
|
82
87
|
execute backoff: true do
|
83
|
-
service.list_datasets
|
84
|
-
@project, all: options[:all], filter: options[:filter],
|
85
|
-
max_results: options[:max], page_token: options[:token]
|
88
|
+
service.list_datasets @project, all: all, filter: filter, max_results: max, page_token: token
|
86
89
|
end
|
87
90
|
end
|
88
91
|
|
@@ -113,8 +116,7 @@ module Google
|
|
113
116
|
patch_with_backoff = true
|
114
117
|
end
|
115
118
|
execute backoff: patch_with_backoff do
|
116
|
-
service.patch_dataset @project, dataset_id, patched_dataset_gapi,
|
117
|
-
options: options
|
119
|
+
service.patch_dataset @project, dataset_id, patched_dataset_gapi, options: options
|
118
120
|
end
|
119
121
|
end
|
120
122
|
|
@@ -133,15 +135,15 @@ module Google
|
|
133
135
|
##
|
134
136
|
# Lists all tables in the specified dataset.
|
135
137
|
# Requires the READER dataset role.
|
136
|
-
def list_tables dataset_id,
|
138
|
+
def list_tables dataset_id, max: nil, token: nil
|
137
139
|
# The list operation is considered idempotent
|
138
140
|
execute backoff: true do
|
139
|
-
service.list_tables @project, dataset_id,
|
140
|
-
max_results: options[:max],
|
141
|
-
page_token: options[:token]
|
141
|
+
service.list_tables @project, dataset_id, max_results: max, page_token: token
|
142
142
|
end
|
143
143
|
end
|
144
144
|
|
145
|
+
##
|
146
|
+
# Gets the specified table resource by full table reference.
|
145
147
|
def get_project_table project_id, dataset_id, table_id
|
146
148
|
# The get operation is considered idempotent
|
147
149
|
execute backoff: true do
|
@@ -155,10 +157,7 @@ module Google
|
|
155
157
|
# it only returns the table resource,
|
156
158
|
# which describes the structure of this table.
|
157
159
|
def get_table dataset_id, table_id
|
158
|
-
|
159
|
-
execute backoff: true do
|
160
|
-
get_project_table @project, dataset_id, table_id
|
161
|
-
end
|
160
|
+
get_project_table @project, dataset_id, table_id
|
162
161
|
end
|
163
162
|
|
164
163
|
##
|
@@ -179,8 +178,35 @@ module Google
|
|
179
178
|
patch_with_backoff = true
|
180
179
|
end
|
181
180
|
execute backoff: patch_with_backoff do
|
182
|
-
service.patch_table @project, dataset_id, table_id,
|
183
|
-
|
181
|
+
service.patch_table @project, dataset_id, table_id, patched_table_gapi, options: options
|
182
|
+
end
|
183
|
+
end
|
184
|
+
|
185
|
+
##
|
186
|
+
# Returns Google::Apis::BigqueryV2::Policy
|
187
|
+
def get_table_policy dataset_id, table_id
|
188
|
+
policy_options = API::GetPolicyOptions.new requested_policy_version: 1
|
189
|
+
execute do
|
190
|
+
service.get_table_iam_policy table_path(dataset_id, table_id),
|
191
|
+
API::GetIamPolicyRequest.new(options: policy_options)
|
192
|
+
end
|
193
|
+
end
|
194
|
+
|
195
|
+
##
|
196
|
+
# @param [Google::Apis::BigqueryV2::Policy] new_policy
|
197
|
+
def set_table_policy dataset_id, table_id, new_policy
|
198
|
+
execute do
|
199
|
+
service.set_table_iam_policy table_path(dataset_id, table_id),
|
200
|
+
API::SetIamPolicyRequest.new(policy: new_policy)
|
201
|
+
end
|
202
|
+
end
|
203
|
+
|
204
|
+
##
|
205
|
+
# Returns Google::Apis::BigqueryV2::TestIamPermissionsResponse
|
206
|
+
def test_table_permissions dataset_id, table_id, permissions
|
207
|
+
execute do
|
208
|
+
service.test_table_iam_permissions table_path(dataset_id, table_id),
|
209
|
+
API::TestIamPermissionsRequest.new(permissions: permissions)
|
184
210
|
end
|
185
211
|
end
|
186
212
|
|
@@ -193,40 +219,45 @@ module Google
|
|
193
219
|
|
194
220
|
##
|
195
221
|
# Retrieves data from the table.
|
196
|
-
def list_tabledata dataset_id, table_id,
|
222
|
+
def list_tabledata dataset_id, table_id, max: nil, token: nil, start: nil
|
197
223
|
# The list operation is considered idempotent
|
198
224
|
execute backoff: true do
|
199
225
|
json_txt = service.list_table_data \
|
200
226
|
@project, dataset_id, table_id,
|
201
|
-
max_results:
|
202
|
-
page_token:
|
203
|
-
start_index:
|
227
|
+
max_results: max,
|
228
|
+
page_token: token,
|
229
|
+
start_index: start,
|
204
230
|
options: { skip_deserialization: true }
|
205
231
|
JSON.parse json_txt, symbolize_names: true
|
206
232
|
end
|
207
233
|
end
|
208
234
|
|
209
|
-
def insert_tabledata dataset_id, table_id, rows,
|
235
|
+
def insert_tabledata dataset_id, table_id, rows, insert_ids: nil, ignore_unknown: nil, skip_invalid: nil
|
210
236
|
json_rows = Array(rows).map { |row| Convert.to_json_row row }
|
211
|
-
insert_tabledata_json_rows dataset_id, table_id, json_rows,
|
237
|
+
insert_tabledata_json_rows dataset_id, table_id, json_rows, insert_ids: insert_ids,
|
238
|
+
ignore_unknown: ignore_unknown,
|
239
|
+
skip_invalid: skip_invalid
|
212
240
|
end
|
213
241
|
|
214
|
-
def insert_tabledata_json_rows dataset_id, table_id, json_rows,
|
215
|
-
|
216
|
-
|
217
|
-
rows_and_ids = Array(json_rows).zip Array(options[:insert_ids])
|
242
|
+
def insert_tabledata_json_rows dataset_id, table_id, json_rows, insert_ids: nil, ignore_unknown: nil,
|
243
|
+
skip_invalid: nil
|
244
|
+
rows_and_ids = Array(json_rows).zip Array(insert_ids)
|
218
245
|
insert_rows = rows_and_ids.map do |json_row, insert_id|
|
219
|
-
insert_id
|
220
|
-
|
221
|
-
|
222
|
-
|
223
|
-
|
246
|
+
if insert_id == :skip
|
247
|
+
{ json: json_row }
|
248
|
+
else
|
249
|
+
insert_id ||= SecureRandom.uuid
|
250
|
+
{
|
251
|
+
insertId: insert_id,
|
252
|
+
json: json_row
|
253
|
+
}
|
254
|
+
end
|
224
255
|
end
|
225
256
|
|
226
257
|
insert_req = {
|
227
258
|
rows: insert_rows,
|
228
|
-
ignoreUnknownValues:
|
229
|
-
skipInvalidRows:
|
259
|
+
ignoreUnknownValues: ignore_unknown,
|
260
|
+
skipInvalidRows: skip_invalid
|
230
261
|
}.to_json
|
231
262
|
|
232
263
|
# The insertAll with insertId operation is considered idempotent
|
@@ -245,27 +276,26 @@ module Google
|
|
245
276
|
options = { skip_deserialization: true }
|
246
277
|
# The list operation is considered idempotent
|
247
278
|
execute backoff: true do
|
248
|
-
json_txt = service.list_models @project, dataset_id,
|
249
|
-
max_results: max,
|
250
|
-
page_token: token,
|
251
|
-
options: options
|
279
|
+
json_txt = service.list_models @project, dataset_id, max_results: max, page_token: token, options: options
|
252
280
|
JSON.parse json_txt, symbolize_names: true
|
253
281
|
end
|
254
282
|
end
|
255
283
|
|
256
|
-
# Gets the specified model resource by model
|
257
|
-
|
258
|
-
# it only returns the model resource,
|
259
|
-
# which describes the structure of this model.
|
260
|
-
def get_model dataset_id, model_id
|
284
|
+
# Gets the specified model resource by full model reference.
|
285
|
+
def get_project_model project_id, dataset_id, model_id
|
261
286
|
# The get operation is considered idempotent
|
262
287
|
execute backoff: true do
|
263
|
-
json_txt = service.get_model
|
264
|
-
options: { skip_deserialization: true }
|
288
|
+
json_txt = service.get_model project_id, dataset_id, model_id, options: { skip_deserialization: true }
|
265
289
|
JSON.parse json_txt, symbolize_names: true
|
266
290
|
end
|
267
291
|
end
|
268
292
|
|
293
|
+
# Gets the specified model resource by model ID. This method does not return the data in the model, it only
|
294
|
+
# returns the model resource, which describes the structure of this model.
|
295
|
+
def get_model dataset_id, model_id
|
296
|
+
get_project_model @project, dataset_id, model_id
|
297
|
+
end
|
298
|
+
|
269
299
|
##
|
270
300
|
# Updates information in an existing model, replacing fields that
|
271
301
|
# are provided in the submitted model resource.
|
@@ -278,9 +308,7 @@ module Google
|
|
278
308
|
patch_with_backoff = true
|
279
309
|
end
|
280
310
|
execute backoff: patch_with_backoff do
|
281
|
-
json_txt = service.patch_model @project, dataset_id, model_id,
|
282
|
-
patched_model_gapi,
|
283
|
-
options: options
|
311
|
+
json_txt = service.patch_model @project, dataset_id, model_id, patched_model_gapi, options: options
|
284
312
|
JSON.parse json_txt, symbolize_names: true
|
285
313
|
end
|
286
314
|
end
|
@@ -292,16 +320,69 @@ module Google
|
|
292
320
|
execute { service.delete_model @project, dataset_id, model_id }
|
293
321
|
end
|
294
322
|
|
323
|
+
##
|
324
|
+
# Creates a new routine in the dataset.
|
325
|
+
def insert_routine dataset_id, new_routine_gapi
|
326
|
+
execute { service.insert_routine @project, dataset_id, new_routine_gapi }
|
327
|
+
end
|
328
|
+
|
329
|
+
##
|
330
|
+
# Lists all routines in the specified dataset.
|
331
|
+
# Requires the READER dataset role.
|
332
|
+
# Unless readMask is set in the request, only the following fields are populated:
|
333
|
+
# etag, projectId, datasetId, routineId, routineType, creationTime, lastModifiedTime, and language.
|
334
|
+
def list_routines dataset_id, max: nil, token: nil, filter: nil
|
335
|
+
# The list operation is considered idempotent
|
336
|
+
execute backoff: true do
|
337
|
+
service.list_routines @project, dataset_id, max_results: max,
|
338
|
+
page_token: token,
|
339
|
+
filter: filter
|
340
|
+
end
|
341
|
+
end
|
342
|
+
|
343
|
+
##
|
344
|
+
# Gets the specified routine resource by routine ID.
|
345
|
+
def get_routine dataset_id, routine_id
|
346
|
+
# The get operation is considered idempotent
|
347
|
+
execute backoff: true do
|
348
|
+
service.get_routine @project, dataset_id, routine_id
|
349
|
+
end
|
350
|
+
end
|
351
|
+
|
352
|
+
##
|
353
|
+
# Updates information in an existing routine, replacing the entire routine resource.
|
354
|
+
def update_routine dataset_id, routine_id, new_routine_gapi
|
355
|
+
update_with_backoff = false
|
356
|
+
options = {}
|
357
|
+
if new_routine_gapi.etag
|
358
|
+
options[:header] = { "If-Match" => new_routine_gapi.etag }
|
359
|
+
# The update with etag operation is considered idempotent
|
360
|
+
update_with_backoff = true
|
361
|
+
end
|
362
|
+
execute backoff: update_with_backoff do
|
363
|
+
service.update_routine @project, dataset_id, routine_id, new_routine_gapi, options: options
|
364
|
+
end
|
365
|
+
end
|
366
|
+
|
367
|
+
##
|
368
|
+
# Deletes the routine specified by routine_id from the dataset.
|
369
|
+
def delete_routine dataset_id, routine_id
|
370
|
+
execute { service.delete_routine @project, dataset_id, routine_id }
|
371
|
+
end
|
372
|
+
|
295
373
|
##
|
296
374
|
# Lists all jobs in the specified project to which you have
|
297
375
|
# been granted the READER job role.
|
298
|
-
def list_jobs
|
376
|
+
def list_jobs all: nil, token: nil, max: nil, filter: nil, min_created_at: nil, max_created_at: nil,
|
377
|
+
parent_job_id: nil
|
299
378
|
# The list operation is considered idempotent
|
379
|
+
min_creation_time = Convert.time_to_millis min_created_at
|
380
|
+
max_creation_time = Convert.time_to_millis max_created_at
|
300
381
|
execute backoff: true do
|
301
|
-
service.list_jobs
|
302
|
-
|
303
|
-
|
304
|
-
|
382
|
+
service.list_jobs @project, all_users: all, max_results: max,
|
383
|
+
page_token: token, projection: "full", state_filter: filter,
|
384
|
+
min_creation_time: min_creation_time, max_creation_time: max_creation_time,
|
385
|
+
parent_job_id: parent_job_id
|
305
386
|
end
|
306
387
|
end
|
307
388
|
|
@@ -324,10 +405,7 @@ module Google
|
|
324
405
|
end
|
325
406
|
|
326
407
|
def insert_job config, location: nil
|
327
|
-
job_object = API::Job.new(
|
328
|
-
job_reference: job_ref_from(nil, nil, location: location),
|
329
|
-
configuration: config
|
330
|
-
)
|
408
|
+
job_object = API::Job.new job_reference: job_ref_from(nil, nil, location: location), configuration: config
|
331
409
|
# Jobs have generated id, so this operation is considered idempotent
|
332
410
|
execute backoff: true do
|
333
411
|
service.insert_job @project, job_object
|
@@ -340,18 +418,25 @@ module Google
|
|
340
418
|
end
|
341
419
|
end
|
342
420
|
|
421
|
+
##
|
422
|
+
# Deletes the job specified by jobId and location (required).
|
423
|
+
def delete_job job_id, location: nil
|
424
|
+
execute do
|
425
|
+
service.delete_job @project, job_id, location: location
|
426
|
+
end
|
427
|
+
end
|
428
|
+
|
343
429
|
##
|
344
430
|
# Returns the query data for the job
|
345
|
-
def job_query_results job_id,
|
431
|
+
def job_query_results job_id, location: nil, max: nil, token: nil, start: nil, timeout: nil
|
346
432
|
# The get operation is considered idempotent
|
347
433
|
execute backoff: true do
|
348
|
-
service.get_job_query_results
|
349
|
-
|
350
|
-
|
351
|
-
|
352
|
-
|
353
|
-
|
354
|
-
timeout_ms: options.delete(:timeout)
|
434
|
+
service.get_job_query_results @project, job_id,
|
435
|
+
location: location,
|
436
|
+
max_results: max,
|
437
|
+
page_token: token,
|
438
|
+
start_index: start,
|
439
|
+
timeout_ms: timeout
|
355
440
|
end
|
356
441
|
end
|
357
442
|
|
@@ -375,10 +460,7 @@ module Google
|
|
375
460
|
|
376
461
|
def load_table_file file, load_job_gapi
|
377
462
|
execute backoff: true do
|
378
|
-
service.insert_job
|
379
|
-
@project,
|
380
|
-
load_job_gapi,
|
381
|
-
upload_source: file, content_type: mime_type_for(file)
|
463
|
+
service.insert_job @project, load_job_gapi, upload_source: file, content_type: mime_type_for(file)
|
382
464
|
end
|
383
465
|
end
|
384
466
|
|
@@ -402,34 +484,29 @@ module Google
|
|
402
484
|
def self.table_ref_from_s str, default_ref: {}
|
403
485
|
str = str.to_s
|
404
486
|
m = /\A(((?<prj>\S*)(:|\.))?(?<dts>\S*)\.)?(?<tbl>\S*)\z/.match str
|
405
|
-
unless m
|
406
|
-
raise ArgumentError, "unable to identify table from #{str.inspect}"
|
407
|
-
end
|
487
|
+
raise ArgumentError, "unable to identify table from #{str.inspect}" unless m
|
408
488
|
str_table_ref_hash = {
|
409
489
|
project_id: m["prj"],
|
410
490
|
dataset_id: m["dts"],
|
411
491
|
table_id: m["tbl"]
|
412
492
|
}.delete_if { |_, v| v.nil? }
|
413
493
|
str_table_ref_hash = default_ref.to_h.merge str_table_ref_hash
|
414
|
-
ref = Google::Apis::BigqueryV2::TableReference.new
|
494
|
+
ref = Google::Apis::BigqueryV2::TableReference.new(**str_table_ref_hash)
|
415
495
|
validate_table_ref ref
|
416
496
|
ref
|
417
497
|
end
|
418
498
|
|
419
499
|
def self.validate_table_ref table_ref
|
420
|
-
|
421
|
-
if table_ref.send(f).nil?
|
422
|
-
raise ArgumentError, "TableReference is missing #{f}"
|
423
|
-
end
|
500
|
+
[:project_id, :dataset_id, :table_id].each do |f|
|
501
|
+
raise ArgumentError, "TableReference is missing #{f}" if table_ref.send(f).nil?
|
424
502
|
end
|
425
503
|
end
|
426
504
|
|
427
505
|
##
|
428
506
|
# Lists all projects to which you have been granted any project role.
|
429
|
-
def list_projects
|
507
|
+
def list_projects max: nil, token: nil
|
430
508
|
execute backoff: true do
|
431
|
-
service.list_projects max_results:
|
432
|
-
page_token: options[:token]
|
509
|
+
service.list_projects max_results: max, page_token: token
|
433
510
|
end
|
434
511
|
end
|
435
512
|
|
@@ -439,10 +516,7 @@ module Google
|
|
439
516
|
def job_ref_from job_id, prefix, location: nil
|
440
517
|
prefix ||= "job_"
|
441
518
|
job_id ||= "#{prefix}#{generate_id}"
|
442
|
-
job_ref = API::JobReference.new
|
443
|
-
project_id: @project,
|
444
|
-
job_id: job_id
|
445
|
-
)
|
519
|
+
job_ref = API::JobReference.new project_id: @project, job_id: job_id
|
446
520
|
# BigQuery does not allow nil location, but missing is ok.
|
447
521
|
job_ref.location = location if location
|
448
522
|
job_ref
|
@@ -470,22 +544,27 @@ module Google
|
|
470
544
|
|
471
545
|
protected
|
472
546
|
|
547
|
+
# Creates a formatted table path.
|
548
|
+
def table_path dataset_id, table_id
|
549
|
+
"projects/#{@project}/datasets/#{dataset_id}/tables/#{table_id}"
|
550
|
+
end
|
551
|
+
|
473
552
|
# Generate a random string similar to the BigQuery service job IDs.
|
474
553
|
def generate_id
|
475
554
|
SecureRandom.urlsafe_base64 21
|
476
555
|
end
|
477
556
|
|
478
557
|
def mime_type_for file
|
479
|
-
mime_type =
|
480
|
-
return nil if mime_type.
|
481
|
-
mime_type
|
558
|
+
mime_type = MiniMime.lookup_by_filename Pathname(file).to_path
|
559
|
+
return nil if mime_type.nil?
|
560
|
+
mime_type.content_type
|
482
561
|
rescue StandardError
|
483
562
|
nil
|
484
563
|
end
|
485
564
|
|
486
|
-
def execute backoff: nil
|
565
|
+
def execute backoff: nil, &block
|
487
566
|
if backoff
|
488
|
-
Backoff.new(retries: retries).execute
|
567
|
+
Backoff.new(retries: retries).execute(&block)
|
489
568
|
else
|
490
569
|
yield
|
491
570
|
end
|
@@ -500,7 +579,7 @@ module Google
|
|
500
579
|
attr_accessor :backoff
|
501
580
|
end
|
502
581
|
self.retries = 5
|
503
|
-
self.reasons =
|
582
|
+
self.reasons = ["rateLimitExceeded", "backendError"]
|
504
583
|
self.backoff = lambda do |retries|
|
505
584
|
# Max delay is 32 seconds
|
506
585
|
# See "Back-off Requirements" here:
|
@@ -510,31 +589,29 @@ module Google
|
|
510
589
|
sleep delay
|
511
590
|
end
|
512
591
|
|
513
|
-
def initialize
|
514
|
-
@retries = (
|
515
|
-
@reasons = (
|
516
|
-
@backoff =
|
592
|
+
def initialize retries: nil, reasons: nil, backoff: nil
|
593
|
+
@retries = (retries || Backoff.retries).to_i
|
594
|
+
@reasons = (reasons || Backoff.reasons).to_a
|
595
|
+
@backoff = backoff || Backoff.backoff
|
517
596
|
end
|
518
597
|
|
519
598
|
def execute
|
520
599
|
current_retries = 0
|
521
600
|
loop do
|
522
|
-
|
523
|
-
|
524
|
-
|
525
|
-
|
526
|
-
|
527
|
-
|
528
|
-
current_retries += 1
|
529
|
-
end
|
601
|
+
return yield
|
602
|
+
rescue Google::Apis::Error => e
|
603
|
+
raise e unless retry? e.body, current_retries
|
604
|
+
|
605
|
+
@backoff.call current_retries
|
606
|
+
current_retries += 1
|
530
607
|
end
|
531
608
|
end
|
532
609
|
|
533
610
|
protected
|
534
611
|
|
535
|
-
def retry? result, current_retries
|
536
|
-
if current_retries < @retries
|
537
|
-
return true
|
612
|
+
def retry? result, current_retries
|
613
|
+
if current_retries < @retries && retry_error_reason?(result)
|
614
|
+
return true
|
538
615
|
end
|
539
616
|
false
|
540
617
|
end
|