Blame - docs/dyn/dataflow_v1b3.projects.locations.flexTemplates.html - platform/external/python/google-api-python-client

2020-05-20 12:08:20 -0700

[diff] [blame]

94

"launchParameter": { # Launch FlexTemplate Parameter. # Required. Parameter to launch a job form Flex Template.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

95

"launchOptions": { # Launch options for this flex template job. This is a common set of options

96

# across languages and templates. This should not be used to pass job

97

# parameters.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

98

"a_key": "A String",

99

},

100

"jobName": "A String", # Required. The job name to use for the created job.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

101

"containerSpecGcsPath": "A String", # Gcs path to a file with json serialized ContainerSpec as content.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

102

"containerSpec": { # Container Spec. # Spec about the container image to launch.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

103

"image": "A String", # Name of the docker container image. E.g., gcr.io/project/some-image

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

104

"sdkInfo": { # SDK Information. # Required. SDK info of the Flex Template.

105

"language": "A String", # Required. The SDK Language.

106

"version": "A String", # Optional. The SDK version.

107

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

108

"metadata": { # Metadata describing a template. # Metadata describing a template including description and validation rules.

109

"description": "A String", # Optional. A description of the template.

110

"parameters": [ # The parameters for the template.

111

{ # Metadata for a specific parameter.

112

"label": "A String", # Required. The label to display for the parameter.

113

"helpText": "A String", # Required. The help text to display for the parameter.

114

"regexes": [ # Optional. Regexes that the parameter must match.

115

"A String",

116

],

117

"paramType": "A String", # Optional. The type of the parameter.

118

# Used for selecting input picker.

119

"isOptional": True or False, # Optional. Whether the parameter is optional. Defaults to false.

120

"name": "A String", # Required. The name of the parameter.

121

},

122

],

123

"name": "A String", # Required. The name of the template.

124

},

125

},

126

"parameters": { # The parameters for FlexTemplate.

127

# Ex. {"num_workers":"5"}

128

"a_key": "A String",

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

129

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

130

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

131

"validateOnly": True or False, # If true, the request is validated but not actually executed.

132

# Defaults to false.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

133

}

134

135

x__xgafv: string, V1 error format.

Allowed values

1 - v1 error format

2 - v2 error format

Returns:

An object of the form:

142

143

{ # Response to the request to launch a job from Flex Template.

144

"job": { # Defines a job to be run by the Cloud Dataflow service. # The job that was launched, if the request was not a dry run and

145

# the job was successfully launched.

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

146

"pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.

147

# A description of the user pipeline and stages through which it is executed.

148

# Created by Cloud Dataflow service. Only retrieved with

149

# JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.

150

# form. This data is provided by the Dataflow service for ease of visualizing

151

# the pipeline and interpreting Dataflow provided metrics.

152

"displayData": [ # Pipeline level display data.

153

{ # Data provided with a pipeline or transform to provide descriptive info.

154

"url": "A String", # An optional full URL.

155

"javaClassValue": "A String", # Contains value if the data is of java class type.

156

"timestampValue": "A String", # Contains value if the data is of timestamp type.

157

"durationValue": "A String", # Contains value if the data is of duration type.

158

"label": "A String", # An optional label to display in a dax UI for the element.

159

"key": "A String", # The key identifying the display data.

160

# This is intended to be used as a label for the display data

161

# when viewed in a dax monitoring system.

162

"namespace": "A String", # The namespace for the key. This is usually a class name or programming

163

# language namespace (i.e. python module) which defines the display data.

164

# This allows a dax monitoring system to specially handle the data

165

# and perform custom rendering.

166

"floatValue": 3.14, # Contains value if the data is of float type.

167

"strValue": "A String", # Contains value if the data is of string type.

168

"int64Value": "A String", # Contains value if the data is of int64 type.

169

"boolValue": True or False, # Contains value if the data is of a boolean type.

170

"shortStrValue": "A String", # A possible additional shorter value to display.

171

# For example a java_class_name_value of com.mypackage.MyDoFn

172

# will be stored with MyDoFn as the short_str_value and

173

# com.mypackage.MyDoFn as the java_class_name value.

174

# short_str_value can be displayed and java_class_name_value

175

# will be displayed as a tooltip.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

176

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

177

],

178

"originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them.

179

{ # Description of the type, names/ids, and input/outputs for a transform.

180

"outputCollectionName": [ # User names for all collection outputs to this transform.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

181

"A String",

182

],

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

183

"displayData": [ # Transform-specific display data.

184

{ # Data provided with a pipeline or transform to provide descriptive info.

185

"url": "A String", # An optional full URL.

186

"javaClassValue": "A String", # Contains value if the data is of java class type.

187

"timestampValue": "A String", # Contains value if the data is of timestamp type.

188

"durationValue": "A String", # Contains value if the data is of duration type.

189

"label": "A String", # An optional label to display in a dax UI for the element.

190

"key": "A String", # The key identifying the display data.

191

# This is intended to be used as a label for the display data

192

# when viewed in a dax monitoring system.

193

"namespace": "A String", # The namespace for the key. This is usually a class name or programming

194

# language namespace (i.e. python module) which defines the display data.

195

# This allows a dax monitoring system to specially handle the data

196

# and perform custom rendering.

197

"floatValue": 3.14, # Contains value if the data is of float type.

198

"strValue": "A String", # Contains value if the data is of string type.

199

"int64Value": "A String", # Contains value if the data is of int64 type.

200

"boolValue": True or False, # Contains value if the data is of a boolean type.

201

"shortStrValue": "A String", # A possible additional shorter value to display.

202

# For example a java_class_name_value of com.mypackage.MyDoFn

203

# will be stored with MyDoFn as the short_str_value and

204

# com.mypackage.MyDoFn as the java_class_name value.

205

# short_str_value can be displayed and java_class_name_value

206

# will be displayed as a tooltip.

207

},

208

],

209

"id": "A String", # SDK generated id of this transform instance.

210

"inputCollectionName": [ # User names for all collection inputs to this transform.

211

"A String",

212

],

213

"name": "A String", # User provided name for this transform instance.

214

"kind": "A String", # Type of transform.

215

},

216

],

217

"executionPipelineStage": [ # Description of each stage of execution of the pipeline.

218

{ # Description of the composing transforms, names/ids, and input/outputs of a

219

# stage of execution. Some composing transforms and sources may have been

220

# generated by the Dataflow service during execution planning.

221

"componentSource": [ # Collections produced and consumed by component transforms of this stage.

222

{ # Description of an interstitial value between transforms in an execution

223

# stage.

224

"userName": "A String", # Human-readable name for this transform; may be user or system generated.

225

"name": "A String", # Dataflow service generated name for this source.

226

"originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this

227

# source is most closely associated.

228

},

229

],

230

"inputSource": [ # Input sources for this stage.

231

{ # Description of an input or output of an execution stage.

232

"userName": "A String", # Human-readable name for this source; may be user or system generated.

233

"originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this

234

# source is most closely associated.

235

"sizeBytes": "A String", # Size of the source, if measurable.

236

"name": "A String", # Dataflow service generated name for this source.

237

},

238

],

239

"name": "A String", # Dataflow service generated name for this stage.

240

"componentTransform": [ # Transforms that comprise this execution stage.

241

{ # Description of a transform executed as part of an execution stage.

242

"name": "A String", # Dataflow service generated name for this source.

243

"userName": "A String", # Human-readable name for this transform; may be user or system generated.

244

"originalTransform": "A String", # User name for the original user transform with which this transform is

245

# most closely associated.

246

},

247

],

248

"id": "A String", # Dataflow service generated id for this stage.

249

"outputSource": [ # Output sources for this stage.

250

{ # Description of an input or output of an execution stage.

251

"userName": "A String", # Human-readable name for this source; may be user or system generated.

252

"originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this

253

# source is most closely associated.

254

"sizeBytes": "A String", # Size of the source, if measurable.

255

"name": "A String", # Dataflow service generated name for this source.

256

},

257

],

258

"kind": "A String", # Type of tranform this stage is executing.

},

],

},

"labels": { # User-defined labels for this job.

263

#

264

# The labels map can contain no more than 64 entries. Entries of the labels

265

# map are UTF8 strings that comply with the following restrictions:

266

#

267

# * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62}

268

# * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63}

269

# * Both keys and values are additionally constrained to be <= 128 bytes in

# size.

"a_key": "A String",

},

"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.

274

"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.

275

"flexResourceSchedulingGoal": "A String", # Which Flexible Resource Scheduling mode to run in.

276

"workerRegion": "A String", # The Compute Engine region

277

# (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in

278

# which worker processing should occur, e.g. "us-west1". Mutually exclusive

279

# with worker_zone. If neither worker_region nor worker_zone is specified,

280

# default to the control plane's region.

281

"userAgent": { # A description of the process that generated the request.

282

"a_key": "", # Properties of the object.

283

},

284

"serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account.

285

"version": { # A structure describing which components and their versions of the service

286

# are required in order to run the job.

287

"a_key": "", # Properties of the object.

288

},

289

"serviceKmsKeyName": "A String", # If set, contains the Cloud KMS key identifier used to encrypt data

290

# at rest, AKA a Customer Managed Encryption Key (CMEK).

291

#

292

# Format:

293

# projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY

294

"experiments": [ # The list of experiments to enable.

295

"A String",

296

],

297

"workerZone": "A String", # The Compute Engine zone

298

# (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in

299

# which worker processing should occur, e.g. "us-west1-a". Mutually exclusive

300

# with worker_region. If neither worker_region nor worker_zone is specified,

301

# a zone in the control plane's region is chosen based on available capacity.

302

"workerPools": [ # The worker pools. At least one "harness" worker pool must be

303

# specified in order for the job to have workers.

304

{ # Describes one particular pool of Cloud Dataflow workers to be

305

# instantiated by the Cloud Dataflow service in order to perform the

306

# computations required by a job. Note that a workflow job may use

307

# multiple pools, in order to match the various computational

308

# requirements of the various stages of the job.

309

"onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google

310

# Compute Engine API.

311

"sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will

312

# only be set in the Fn API path. For non-cross-language pipelines this

313

# should have only one entry. Cross-language pipelines will have two or more

314

# entries.

315

{ # Defines a SDK harness container for executing Dataflow pipelines.

316

"containerImage": "A String", # A docker container image that resides in Google Container Registry.

317

"useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK

318

# container instance with this image. If false (or unset) recommends using

319

# more than one core per SDK container instance with this image for

320

# efficiency. Note that Dataflow service may choose to override this property

# if needed.

},

],

"zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service

325

# will attempt to choose a reasonable default.

326

"kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`

327

# are supported.

328

"metadata": { # Metadata to set on the Google Compute Engine VMs.

329

"a_key": "A String",

330

},

331

"diskSourceImage": "A String", # Fully qualified source image for disks.

332

"dataDisks": [ # Data disks that are used by a VM in this workflow.

333

{ # Describes the data disk used by a workflow job.

334

"sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will

335

# attempt to choose a reasonable default.

336

"diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This

337

# must be a disk type appropriate to the project and zone in which

338

# the workers will run. If unknown or unspecified, the service

339

# will attempt to choose a reasonable default.

340

#

341

# For example, the standard persistent disk type is a resource name

342

# typically ending in "pd-standard". If SSD persistent disks are

343

# available, the resource name typically ends with "pd-ssd". The

344

# actual valid values are defined the Google Compute Engine API,

345

# not by the Cloud Dataflow API; consult the Google Compute Engine

346

# documentation for more information about determining the set of

347

# available disk types for a particular project and zone.

348

#

349

# Google Compute Engine Disk types are local to a particular

350

# project in a particular zone, and so the resource name will

351

# typically look something like this:

352

#

353

# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard

354

"mountPoint": "A String", # Directory in a VM where disk is mounted.

355

},

356

],

357

"packages": [ # Packages to be installed on workers.

358

{ # The packages that must be installed in order for a worker to run the

359

# steps of the Cloud Dataflow job that will be assigned to its worker

360

# pool.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

361

#

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

362

# This is the mechanism by which the Cloud Dataflow SDK causes code to

363

# be loaded onto the workers. For example, the Cloud Dataflow Java SDK

364

# might use this to install jars containing the user's code and all of the

365

# various dependencies (libraries, data files, etc.) required in order

366

# for that code to run.

367

"name": "A String", # The name of the package.

368

"location": "A String", # The resource to read the package from. The supported resource type is:

369

#

370

# Google Cloud Storage:

371

#

372

# storage.googleapis.com/{bucket}

373

# bucket.storage.googleapis.com/

374

},

375

],

376

"teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.

377

# Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and

378

# `TEARDOWN_NEVER`.

379

# `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether

380

# the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down

381

# if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn

382

# down.

383

#

384

# If the workers are not torn down by the service, they will

385

# continue to run and use Google Compute Engine VM resources in the

386

# user's project until they are explicitly terminated by the user.

387

# Because of this, Google recommends using the `TEARDOWN_ALWAYS`

388

# policy except for small, manually supervised test jobs.

389

#

390

# If unknown or unspecified, the service will attempt to choose a reasonable

391

# default.

392

"network": "A String", # Network to which VMs will be assigned. If empty or unspecified,

393

# the service will use the network "default".

394

"ipConfiguration": "A String", # Configuration for VM IPs.

395

"diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will

396

# attempt to choose a reasonable default.

397

"autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.

398

"maxNumWorkers": 42, # The maximum number of workers to cap scaling at.

399

"algorithm": "A String", # The algorithm to use for autoscaling.

400

},

401

"poolArgs": { # Extra arguments for this worker pool.

402

"a_key": "", # Properties of the object. Contains field @type with type URL.

403

},

404

"subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of

405

# the form "regions/REGION/subnetworks/SUBNETWORK".

406

"numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to

407

# execute the job. If zero or unspecified, the service will

408

# attempt to choose a reasonable default.

409

"numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the

410

# service will choose a number of threads (according to the number of cores

411

# on the selected machine type for batch, or 1 by convention for streaming).

412

"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker

413

# harness, residing in Google Container Registry.

414

#

415

# Deprecated for the Fn API path. Use sdk_harness_container_images instead.

416

"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when

417

# using the standard Dataflow task runner. Users should ignore

418

# this field.

419

"dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"

420

"oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to

421

# access the Cloud Dataflow API.

422

"A String",

423

],

424

"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

425

#

426

# When workers access Google Cloud APIs, they logically do so via

427

# relative URLs. If this field is specified, it supplies the base

428

# URL to use for resolving these relative URLs. The normative

429

# algorithm used is defined by RFC 1808, "Relative Uniform Resource

430

# Locators".

431

#

432

# If not specified, the default value is "http://www.googleapis.com/"

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

433

"workflowFileName": "A String", # The file to store the workflow in.

434

"logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial

435

# console.

436

"baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.

437

"taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by

438

# taskrunner; e.g. "root".

439

"vmId": "A String", # The ID string of the VM.

440

"alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.

441

"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.

442

"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,

443

# "shuffle/v1beta1".

444

"tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary

445

# storage.

446

#

447

# The supported resource type is:

448

#

449

# Google Cloud Storage:

450

#

451

# storage.googleapis.com/{bucket}/{object}

452

# bucket.storage.googleapis.com/{object}

453

"reportingEnabled": True or False, # Whether to send work progress updates to the service.

454

"servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example,

455

# "dataflow/v1b3/projects".

456

"baseUrl": "A String", # The base URL for accessing Google Cloud APIs.

457

#

458

# When workers access Google Cloud APIs, they logically do so via

459

# relative URLs. If this field is specified, it supplies the base

460

# URL to use for resolving these relative URLs. The normative

461

# algorithm used is defined by RFC 1808, "Relative Uniform Resource

462

# Locators".

463

#

464

# If not specified, the default value is "http://www.googleapis.com/"

465

"workerId": "A String", # The ID of the worker running this pipeline.

466

},

467

"harnessCommand": "A String", # The command to launch the worker harness.

468

"logDir": "A String", # The directory on the VM to store logs.

469

"streamingWorkerMainClass": "A String", # The streaming worker main class name.

470

"languageHint": "A String", # The suggested backend language.

471

"taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by

472

# taskrunner; e.g. "wheel".

473

"logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs

474

# will not be uploaded.

475

#

476

# The supported resource type is:

477

#

478

# Google Cloud Storage:

479

# storage.googleapis.com/{bucket}/{object}

480

# bucket.storage.googleapis.com/{object}

481

"commandlinesFileName": "A String", # The file to store preprocessing commands in.

482

"continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.

483

"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for

484

# temporary storage.

485

#

486

# The supported resource type is:

487

#

488

# Google Cloud Storage:

489

# storage.googleapis.com/{bucket}/{object}

490

# bucket.storage.googleapis.com/{object}

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

491

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

492

"diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will

493

# attempt to choose a reasonable default.

494

"defaultPackageSet": "A String", # The default package set to install. This allows the service to

495

# select a default set of packages which are useful to worker

496

# harnesses written in a particular language.

497

"machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the

498

# service will attempt to choose a reasonable default.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

499

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

500

],

501

"tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary

502

# storage. The system will append the suffix "/temp-{JOBNAME} to

503

# this resource prefix, where {JOBNAME} is the value of the

504

# job_name field. The resulting bucket and object prefix is used

505

# as the prefix of the resources used to store temporary data

506

# needed during the job execution. NOTE: This will override the

507

# value in taskrunner_settings.

508

# The supported resource type is:

509

#

510

# Google Cloud Storage:

511

#

512

# storage.googleapis.com/{bucket}/{object}

513

# bucket.storage.googleapis.com/{object}

514

"internalExperiments": { # Experimental settings.

515

"a_key": "", # Properties of the object. Contains field @type with type URL.

Bu Sun Kim

2020-05-27 12:20:54 -0700

[diff] [blame]

516

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

517

"sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These

518

# options are passed through the service and are used to recreate the

519

# SDK pipeline options on the worker in a language agnostic and platform

520

# independent way.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

521

"a_key": "", # Properties of the object.

522

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

523

"dataset": "A String", # The dataset for the current project where various workflow

524

# related tables are stored.

525

#

526

# The supported resource type is:

527

#

528

# Google BigQuery:

529

# bigquery.googleapis.com/{dataset}

530

"clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or

531

# unspecified, the service will attempt to choose a reasonable

532

# default. This should be in the form of the API service name,

533

# e.g. "compute.googleapis.com".

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

534

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

535

"stepsLocation": "A String", # The GCS location where the steps are stored.

536

"steps": [ # Exactly one of step or steps_location should be specified.

537

#

538

# The top-level steps that constitute the entire job.

539

{ # Defines a particular step within a Cloud Dataflow job.

540

#

541

# A job consists of multiple steps, each of which performs some

542

# specific operation as part of the overall job. Data is typically

543

# passed from one step to another as part of the job.

544

#

545

# Here's an example of a sequence of steps which together implement a

546

# Map-Reduce job:

547

#

548

# * Read a collection of data from some source, parsing the

549

# collection's elements.

550

#

551

# * Validate the elements.

552

#

553

# * Apply a user-defined function to map each element to some value

554

# and extract an element-specific key value.

555

#

556

# * Group elements with the same key into a single element with

557

# that key, transforming a multiply-keyed collection into a

558

# uniquely-keyed collection.

559

#

560

# * Write the elements out to some data sink.

561

#

562

# Note that the Cloud Dataflow service may be used to run many different

563

# types of jobs, not just Map-Reduce.

564

"kind": "A String", # The kind of step in the Cloud Dataflow job.

565

"properties": { # Named properties associated with the step. Each kind of

566

# predefined step has its own required set of properties.

567

# Must be provided on Create. Only retrieved with JOB_VIEW_ALL.

568

"a_key": "", # Properties of the object.

569

},

570

"name": "A String", # The name that identifies the step. This must be unique for each

571

# step with respect to all other steps in the Cloud Dataflow job.

572

},

573

],

574

"stageStates": [ # This field may be mutated by the Cloud Dataflow service;

575

# callers cannot mutate it.

576

{ # A message describing the state of a particular execution stage.

577

"executionStageState": "A String", # Executions stage states allow the same set of values as JobState.

578

"executionStageName": "A String", # The name of the execution stage.

579

"currentStateTime": "A String", # The time at which the stage transitioned to this state.

580

},

581

],

582

"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in

583

# `JOB_STATE_UPDATED`), this field contains the ID of that job.

584

"jobMetadata": { # Metadata available primarily for filtering jobs. Will be included in the # This field is populated by the Dataflow service to support filtering jobs

585

# by the metadata values provided here. Populated for ListJobs and all GetJob

586

# views SUMMARY and higher.

587

# ListJob response and Job SUMMARY view.

588

"sdkVersion": { # The version of the SDK used to run the job. # The SDK version used to run the job.

589

"sdkSupportStatus": "A String", # The support status for this SDK version.

590

"versionDisplayName": "A String", # A readable string describing the version of the SDK.

591

"version": "A String", # The version of the SDK used to run the job.

592

},

593

"bigTableDetails": [ # Identification of a BigTable source used in the Dataflow job.

594

{ # Metadata for a BigTable connector used by the job.

595

"instanceId": "A String", # InstanceId accessed in the connection.

596

"tableId": "A String", # TableId accessed in the connection.

597

"projectId": "A String", # ProjectId accessed in the connection.

598

},

599

],

600

"pubsubDetails": [ # Identification of a PubSub source used in the Dataflow job.

601

{ # Metadata for a PubSub connector used by the job.

602

"subscription": "A String", # Subscription used in the connection.

603

"topic": "A String", # Topic accessed in the connection.

604

},

605

],

606

"bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job.

607

{ # Metadata for a BigQuery connector used by the job.

608

"dataset": "A String", # Dataset accessed in the connection.

609

"projectId": "A String", # Project accessed in the connection.

610

"query": "A String", # Query used to access data in the connection.

611

"table": "A String", # Table accessed in the connection.

612

},

613

],

614

"fileDetails": [ # Identification of a File source used in the Dataflow job.

615

{ # Metadata for a File connector used by the job.

616

"filePattern": "A String", # File Pattern used to access files by the connector.

617

},

618

],

619

"datastoreDetails": [ # Identification of a Datastore source used in the Dataflow job.

620

{ # Metadata for a Datastore connector used by the job.

621

"namespace": "A String", # Namespace used in the connection.

622

"projectId": "A String", # ProjectId accessed in the connection.

623

},

624

],

625

"spannerDetails": [ # Identification of a Spanner source used in the Dataflow job.

626

{ # Metadata for a Spanner connector used by the job.

627

"instanceId": "A String", # InstanceId accessed in the connection.

628

"databaseId": "A String", # DatabaseId accessed in the connection.

629

"projectId": "A String", # ProjectId accessed in the connection.

},

],

},

"location": "A String", # The [regional endpoint]

634

# (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that

635

# contains this job.

636

"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the

637

# corresponding name prefixes of the new job.

638

"a_key": "A String",

639

},

640

"startTime": "A String", # The timestamp when the job was started (transitioned to JOB_STATE_PENDING).

641

# Flexible resource scheduling jobs are started with some delay after job

642

# creation, so start_time is unset before start and is updated when the

643

# job is started by the Cloud Dataflow service. For other jobs, start_time

644

# always equals to create_time and is immutable and set by the Cloud Dataflow

645

# service.

646

"clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts.

647

# If this field is set, the service will ensure its uniqueness.

648

# The request to create a job will fail if the service has knowledge of a

649

# previously submitted job with the same client's ID and job name.

650

# The caller may use this field to ensure idempotence of job

651

# creation across retried attempts to create a job.

652

# By default, the field is empty and, in that case, the service ignores it.

653

"executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.

654

# isn't contained in the submitted job.

655

"stages": { # A mapping from each stage to the information about that stage.

656

"a_key": { # Contains information about how a particular

657

# google.dataflow.v1beta3.Step will be executed.

658

"stepName": [ # The steps associated with the execution stage.

659

# Note that stages may have several steps, and that a given step

660

# might be run by more than one stage.

661

"A String",

662

],

663

},

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

664

},

665

},

Bu Sun Kim

2020-07-22 17:02:09 -0700

[diff] [blame]

666

"type": "A String", # The type of Cloud Dataflow job.

667

"createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the

668

# Cloud Dataflow service.

669

"tempFiles": [ # A set of files the system should be aware of that are used

670

# for temporary storage. These temporary files will be

671

# removed on job completion.

672

# No duplicates are allowed.

673

# No file patterns are supported.

674

#

675

# The supported files are:

676

#

677

# Google Cloud Storage:

678

#

679

# storage.googleapis.com/{bucket}/{object}

680

# bucket.storage.googleapis.com/{object}

681

"A String",

682

],

683

"id": "A String", # The unique ID of this job.

684

#

685

# This field is set by the Cloud Dataflow service when the Job is

686

# created, and is immutable for the life of the job.

687

"requestedState": "A String", # The job's requested state.

688

#

689

# `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and

690

# `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may

691

# also be used to directly set a job's requested state to

692

# `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the

693

# job if it has not already reached a terminal state.

694

"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID

695

# of the job it replaced.

696

#

697

# When sending a `CreateJobRequest`, you can update a job by specifying it

698

# here. The job named here is stopped, and its intermediate state is

699

# transferred to this job.

700

"createdFromSnapshotId": "A String", # If this is specified, the job's initial state is populated from the given

701

# snapshot.

702

"currentState": "A String", # The current state of the job.

703

#

704

# Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise

705

# specified.

706

#

707

# A job in the `JOB_STATE_RUNNING` state may asynchronously enter a

708

# terminal state. After a job has reached a terminal state, no

709

# further state updates may be made.

710

#

711

# This field may be mutated by the Cloud Dataflow service;

712

# callers cannot mutate it.

713

"name": "A String", # The user-specified Cloud Dataflow job name.

714

#

715

# Only one Job with a given name may exist in a project at any

716

# given time. If a caller attempts to create a Job with the same

717

# name as an already-existing Job, the attempt returns the

718

# existing Job.

719

#

720

# The name must match the regular expression

721

# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`

722

"currentStateTime": "A String", # The timestamp associated with the current state.

Bu Sun Kim

2020-05-20 12:08:20 -0700

[diff] [blame]

723

},

Bu Sun Kim