Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / python / google-api-python-client / c30d2b5d4478b230246dcaaa9f1c533ca3304387 / . / docs / dyn / dataflow_v1b3.projects.templates.html
blob: c325c0f88ea50c062dfbb668571a94006f77c0b5 [file] [log] [blame]
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]1<html><body>
2<style>
3
4body, h1, h2, h3, div, span, p, pre, a {
5 margin: 0;
6 padding: 0;
7 border: 0;
8 font-weight: inherit;
9 font-style: inherit;
10 font-size: 100%;
11 font-family: inherit;
12 vertical-align: baseline;
13}
14
15body {
16 font-size: 13px;
17 padding: 1em;
18}
19
20h1 {
21 font-size: 26px;
22 margin-bottom: 1em;
23}
24
25h2 {
26 font-size: 24px;
27 margin-bottom: 1em;
28}
29
30h3 {
31 font-size: 20px;
32 margin-bottom: 1em;
33 margin-top: 1em;
34}
35
36pre, code {
37 line-height: 1.5;
38 font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
39}
40
41pre {
42 margin-top: 0.5em;
43}
44
45h1, h2, h3, p {
46 font-family: Arial, sans serif;
47}
48
49h1, h2, h3 {
50 border-bottom: solid #CCC 1px;
51}
52
53.toc_element {
54 margin-top: 0.5em;
55}
56
57.firstline {
58 margin-left: 2 em;
59}
60
61.method {
62 margin-top: 1em;
63 border: solid 1px #CCC;
64 padding: 1em;
65 background: #EEE;
66}
67
68.details {
69 font-weight: bold;
70 font-size: 14px;
71}
72
73</style>
74
75<h1><a href="dataflow_v1b3.html">Google Dataflow API</a> . <a href="dataflow_v1b3.projects.html">projects</a> . <a href="dataflow_v1b3.projects.templates.html">templates</a></h1>
76<h2>Instance Methods</h2>
77<p class="toc_element">
78 <code><a href="#create">create(projectId, body, x__xgafv=None)</a></code></p>
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]79<p class="firstline">Creates a Cloud Dataflow job from a template.</p>
80<p class="toc_element">
81 <code><a href="#get">get(projectId, gcsPath=None, x__xgafv=None, view=None)</a></code></p>
82<p class="firstline">Get the template associated with a template.</p>
83<p class="toc_element">
84 <code><a href="#launch">launch(projectId, body, dryRun=None, gcsPath=None, x__xgafv=None)</a></code></p>
85<p class="firstline">Launch a template.</p>
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]86<h3>Method Details</h3>
87<div class="method">
88 <code class="details" id="create">create(projectId, body, x__xgafv=None)</code>
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]89 <pre>Creates a Cloud Dataflow job from a template.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]90
91Args:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]92 projectId: string, Required. The ID of the Cloud Platform project that the job belongs to. (required)
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]93 body: object, The request body. (required)
94 The object takes the form of:
95
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]96{ # A request to create a Cloud Dataflow job from a template.
97 "environment": { # The environment values to set at runtime. # The runtime environment for the job.
98 "bypassTempDirValidation": True or False, # Whether to bypass the safety checks for the job's temporary directory.
99 # Use with caution.
100 "tempLocation": "A String", # The Cloud Storage path to use for temporary files.
101 # Must be a valid Cloud Storage URL, beginning with `gs://`.
102 "serviceAccountEmail": "A String", # The email address of the service account to run the job as.
103 "zone": "A String", # The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)
104 # for launching worker instances to run your pipeline.
105 "maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
106 # available to your pipeline during execution, from 1 to 1000.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800[diff] [blame]107 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]108 "gcsPath": "A String", # Required. A Cloud Storage path to the template from which to
109 # create the job.
110 # Must be a valid Cloud Storage URL, beginning with `gs://`.
111 "parameters": { # The runtime parameters to pass to the job.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]112 "a_key": "A String",
113 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]114 "jobName": "A String", # Required. The job name to use for the created job.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]115 }
116
117 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]118 Allowed values
119 1 - v1 error format
120 2 - v2 error format
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]121
122Returns:
123 An object of the form:
124
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]125 { # Defines a job to be run by the Cloud Dataflow service.
126 "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts.
127 # If this field is set, the service will ensure its uniqueness.
128 # The request to create a job will fail if the service has knowledge of a
129 # previously submitted job with the same client's ID and job name.
130 # The caller may use this field to ensure idempotence of job
131 # creation across retried attempts to create a job.
132 # By default, the field is empty and, in that case, the service ignores it.
133 "requestedState": "A String", # The job's requested state.
134 #
135 # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
136 # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may
137 # also be used to directly set a job's requested state to
138 # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
139 # job if it has not already reached a terminal state.
140 "name": "A String", # The user-specified Cloud Dataflow job name.
141 #
142 # Only one Job with a given name may exist in a project at any
143 # given time. If a caller attempts to create a Job with the same
144 # name as an already-existing Job, the attempt returns the
145 # existing Job.
146 #
147 # The name must match the regular expression
148 # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
149 "currentStateTime": "A String", # The timestamp associated with the current state.
150 "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
151 # `JOB_STATE_UPDATED`), this field contains the ID of that job.
152 "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
153 "labels": { # User-defined labels for this job.
154 #
155 # The labels map can contain no more than 64 entries. Entries of the labels
156 # map are UTF8 strings that comply with the following restrictions:
157 #
158 # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62}
159 # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63}
160 # * Both keys and values are additionally constrained to be <= 128 bytes in
161 # size.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]162 "a_key": "A String",
163 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]164 "location": "A String", # The location that contains this job.
165 "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
166 # Cloud Dataflow service.
167 "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
168 # corresponding name prefixes of the new job.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]169 "a_key": "A String",
170 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]171 "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
172 "version": { # A structure describing which components and their versions of the service
173 # are required in order to run the job.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]174 "a_key": "", # Properties of the object.
175 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]176 "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
177 # storage. The system will append the suffix "/temp-{JOBNAME} to
178 # this resource prefix, where {JOBNAME} is the value of the
179 # job_name field. The resulting bucket and object prefix is used
180 # as the prefix of the resources used to store temporary data
181 # needed during the job execution. NOTE: This will override the
182 # value in taskrunner_settings.
183 # The supported resource type is:
184 #
185 # Google Cloud Storage:
186 #
187 # storage.googleapis.com/{bucket}/{object}
188 # bucket.storage.googleapis.com/{object}
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]189 "internalExperiments": { # Experimental settings.
190 "a_key": "", # Properties of the object. Contains field @type with type URL.
191 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]192 "dataset": "A String", # The dataset for the current project where various workflow
193 # related tables are stored.
194 #
195 # The supported resource type is:
196 #
197 # Google BigQuery:
198 # bigquery.googleapis.com/{dataset}
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]199 "experiments": [ # The list of experiments to enable.
200 "A String",
201 ],
Sai Cheemalapatiea3a5e12016-10-12 14:05:53 -0700[diff] [blame]202 "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]203 "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These
204 # options are passed through the service and are used to recreate the
205 # SDK pipeline options on the worker in a language agnostic and platform
206 # independent way.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]207 "a_key": "", # Properties of the object.
208 },
209 "userAgent": { # A description of the process that generated the request.
210 "a_key": "", # Properties of the object.
211 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]212 "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or
213 # unspecified, the service will attempt to choose a reasonable
214 # default. This should be in the form of the API service name,
215 # e.g. "compute.googleapis.com".
216 "workerPools": [ # The worker pools. At least one "harness" worker pool must be
217 # specified in order for the job to have workers.
218 { # Describes one particular pool of Cloud Dataflow workers to be
219 # instantiated by the Cloud Dataflow service in order to perform the
220 # computations required by a job. Note that a workflow job may use
221 # multiple pools, in order to match the various computational
222 # requirements of the various stages of the job.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]223 "diskSourceImage": "A String", # Fully qualified source image for disks.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]224 "ipConfiguration": "A String", # Configuration for VM IPs.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]225 "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
226 # are supported.
227 "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
228 # service will attempt to choose a reasonable default.
229 "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
230 # the service will use the network "default".
231 "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
232 # will attempt to choose a reasonable default.
233 "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
234 # attempt to choose a reasonable default.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]235 "metadata": { # Metadata to set on the Google Compute Engine VMs.
236 "a_key": "A String",
237 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]238 "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
239 # Compute Engine API.
240 "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
241 # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
242 # `TEARDOWN_NEVER`.
243 # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
244 # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
245 # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
246 # down.
247 #
248 # If the workers are not torn down by the service, they will
249 # continue to run and use Google Compute Engine VM resources in the
250 # user's project until they are explicitly terminated by the user.
251 # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
252 # policy except for small, manually supervised test jobs.
253 #
254 # If unknown or unspecified, the service will attempt to choose a reasonable
255 # default.
256 "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
257 # service will choose a number of threads (according to the number of cores
258 # on the selected machine type for batch, or 1 by convention for streaming).
259 "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
260 # the form "regions/REGION/subnetworks/SUBNETWORK".
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]261 "poolArgs": { # Extra arguments for this worker pool.
262 "a_key": "", # Properties of the object. Contains field @type with type URL.
263 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]264 "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
265 # execute the job. If zero or unspecified, the service will
266 # attempt to choose a reasonable default.
267 "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
268 # using the standard Dataflow task runner. Users should ignore
269 # this field.
270 "workflowFileName": "A String", # The file to store the workflow in.
271 "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs
272 # will not be uploaded.
273 #
274 # The supported resource type is:
275 #
276 # Google Cloud Storage:
277 # storage.googleapis.com/{bucket}/{object}
278 # bucket.storage.googleapis.com/{object}
279 "commandlinesFileName": "A String", # The file to store preprocessing commands in.
280 "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
281 "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
282 "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
283 "vmId": "A String", # The ID string of the VM.
284 "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
285 # taskrunner; e.g. "wheel".
286 "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
287 # taskrunner; e.g. "root".
288 "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
289 # access the Cloud Dataflow API.
290 "A String",
291 ],
292 "languageHint": "A String", # The suggested backend language.
293 "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
294 # console.
295 "streamingWorkerMainClass": "A String", # The streaming worker main class name.
296 "logDir": "A String", # The directory on the VM to store logs.
297 "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
298 "reportingEnabled": True or False, # Whether to send work progress updates to the service.
299 "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
300 # "shuffle/v1beta1".
301 "workerId": "A String", # The ID of the worker running this pipeline.
302 "baseUrl": "A String", # The base URL for accessing Google Cloud APIs.
303 #
304 # When workers access Google Cloud APIs, they logically do so via
305 # relative URLs. If this field is specified, it supplies the base
306 # URL to use for resolving these relative URLs. The normative
307 # algorithm used is defined by RFC 1808, "Relative Uniform Resource
308 # Locators".
309 #
310 # If not specified, the default value is "http://www.googleapis.com/"
311 "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example,
312 # "dataflow/v1b3/projects".
313 "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
314 # storage.
315 #
316 # The supported resource type is:
317 #
318 # Google Cloud Storage:
319 #
320 # storage.googleapis.com/{bucket}/{object}
321 # bucket.storage.googleapis.com/{object}
322 },
323 "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
324 "harnessCommand": "A String", # The command to launch the worker harness.
325 "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
326 # temporary storage.
327 #
328 # The supported resource type is:
329 #
330 # Google Cloud Storage:
331 # storage.googleapis.com/{bucket}/{object}
332 # bucket.storage.googleapis.com/{object}
333 "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
334 #
335 # When workers access Google Cloud APIs, they logically do so via
336 # relative URLs. If this field is specified, it supplies the base
337 # URL to use for resolving these relative URLs. The normative
338 # algorithm used is defined by RFC 1808, "Relative Uniform Resource
339 # Locators".
340 #
341 # If not specified, the default value is "http://www.googleapis.com/"
342 },
343 "defaultPackageSet": "A String", # The default package set to install. This allows the service to
344 # select a default set of packages which are useful to worker
345 # harnesses written in a particular language.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]346 "packages": [ # Packages to be installed on workers.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]347 { # The packages that must be installed in order for a worker to run the
348 # steps of the Cloud Dataflow job that will be assigned to its worker
349 # pool.
350 #
351 # This is the mechanism by which the Cloud Dataflow SDK causes code to
352 # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
353 # might use this to install jars containing the user's code and all of the
354 # various dependencies (libraries, data files, etc.) required in order
355 # for that code to run.
356 "location": "A String", # The resource to read the package from. The supported resource type is:
357 #
358 # Google Cloud Storage:
359 #
360 # storage.googleapis.com/{bucket}
361 # bucket.storage.googleapis.com/
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]362 "name": "A String", # The name of the package.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]363 },
364 ],
365 "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]366 "algorithm": "A String", # The algorithm to use for autoscaling.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]367 "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]368 },
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]369 "dataDisks": [ # Data disks that are used by a VM in this workflow.
370 { # Describes the data disk used by a workflow job.
371 "mountPoint": "A String", # Directory in a VM where disk is mounted.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]372 "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will
373 # attempt to choose a reasonable default.
374 "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This
375 # must be a disk type appropriate to the project and zone in which
376 # the workers will run. If unknown or unspecified, the service
377 # will attempt to choose a reasonable default.
378 #
379 # For example, the standard persistent disk type is a resource name
380 # typically ending in "pd-standard". If SSD persistent disks are
381 # available, the resource name typically ends with "pd-ssd". The
382 # actual valid values are defined the Google Compute Engine API,
383 # not by the Cloud Dataflow API; consult the Google Compute Engine
384 # documentation for more information about determining the set of
385 # available disk types for a particular project and zone.
386 #
387 # Google Compute Engine Disk types are local to a particular
388 # project in a particular zone, and so the resource name will
389 # typically look something like this:
390 #
391 # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]392 },
393 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]394 "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
395 # attempt to choose a reasonable default.
396 "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
397 # harness, residing in Google Container Registry.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]398 },
399 ],
400 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]401 "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
402 # A description of the user pipeline and stages through which it is executed.
403 # Created by Cloud Dataflow service. Only retrieved with
404 # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
405 # form. This data is provided by the Dataflow service for ease of visualizing
406 # the pipeline and interpretting Dataflow provided metrics.
407 "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them.
408 { # Description of the type, names/ids, and input/outputs for a transform.
409 "kind": "A String", # Type of transform.
410 "name": "A String", # User provided name for this transform instance.
411 "inputCollectionName": [ # User names for all collection inputs to this transform.
412 "A String",
413 ],
414 "displayData": [ # Transform-specific display data.
415 { # Data provided with a pipeline or transform to provide descriptive info.
416 "key": "A String", # The key identifying the display data.
417 # This is intended to be used as a label for the display data
418 # when viewed in a dax monitoring system.
419 "shortStrValue": "A String", # A possible additional shorter value to display.
420 # For example a java_class_name_value of com.mypackage.MyDoFn
421 # will be stored with MyDoFn as the short_str_value and
422 # com.mypackage.MyDoFn as the java_class_name value.
423 # short_str_value can be displayed and java_class_name_value
424 # will be displayed as a tooltip.
425 "timestampValue": "A String", # Contains value if the data is of timestamp type.
426 "url": "A String", # An optional full URL.
427 "floatValue": 3.14, # Contains value if the data is of float type.
428 "namespace": "A String", # The namespace for the key. This is usually a class name or programming
429 # language namespace (i.e. python module) which defines the display data.
430 # This allows a dax monitoring system to specially handle the data
431 # and perform custom rendering.
432 "javaClassValue": "A String", # Contains value if the data is of java class type.
433 "label": "A String", # An optional label to display in a dax UI for the element.
434 "boolValue": True or False, # Contains value if the data is of a boolean type.
435 "strValue": "A String", # Contains value if the data is of string type.
436 "durationValue": "A String", # Contains value if the data is of duration type.
437 "int64Value": "A String", # Contains value if the data is of int64 type.
438 },
439 ],
440 "outputCollectionName": [ # User names for all collection outputs to this transform.
441 "A String",
442 ],
443 "id": "A String", # SDK generated id of this transform instance.
444 },
445 ],
446 "displayData": [ # Pipeline level display data.
447 { # Data provided with a pipeline or transform to provide descriptive info.
448 "key": "A String", # The key identifying the display data.
449 # This is intended to be used as a label for the display data
450 # when viewed in a dax monitoring system.
451 "shortStrValue": "A String", # A possible additional shorter value to display.
452 # For example a java_class_name_value of com.mypackage.MyDoFn
453 # will be stored with MyDoFn as the short_str_value and
454 # com.mypackage.MyDoFn as the java_class_name value.
455 # short_str_value can be displayed and java_class_name_value
456 # will be displayed as a tooltip.
457 "timestampValue": "A String", # Contains value if the data is of timestamp type.
458 "url": "A String", # An optional full URL.
459 "floatValue": 3.14, # Contains value if the data is of float type.
460 "namespace": "A String", # The namespace for the key. This is usually a class name or programming
461 # language namespace (i.e. python module) which defines the display data.
462 # This allows a dax monitoring system to specially handle the data
463 # and perform custom rendering.
464 "javaClassValue": "A String", # Contains value if the data is of java class type.
465 "label": "A String", # An optional label to display in a dax UI for the element.
466 "boolValue": True or False, # Contains value if the data is of a boolean type.
467 "strValue": "A String", # Contains value if the data is of string type.
468 "durationValue": "A String", # Contains value if the data is of duration type.
469 "int64Value": "A String", # Contains value if the data is of int64 type.
470 },
471 ],
472 "executionPipelineStage": [ # Description of each stage of execution of the pipeline.
473 { # Description of the composing transforms, names/ids, and input/outputs of a
474 # stage of execution. Some composing transforms and sources may have been
475 # generated by the Dataflow service during execution planning.
476 "componentSource": [ # Collections produced and consumed by component transforms of this stage.
477 { # Description of an interstitial value between transforms in an execution
478 # stage.
479 "userName": "A String", # Human-readable name for this transform; may be user or system generated.
480 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
481 # source is most closely associated.
482 "name": "A String", # Dataflow service generated name for this source.
483 },
484 ],
485 "kind": "A String", # Type of tranform this stage is executing.
486 "name": "A String", # Dataflow service generated name for this stage.
487 "outputSource": [ # Output sources for this stage.
488 { # Description of an input or output of an execution stage.
489 "userName": "A String", # Human-readable name for this source; may be user or system generated.
490 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
491 # source is most closely associated.
492 "name": "A String", # Dataflow service generated name for this source.
493 "sizeBytes": "A String", # Size of the source, if measurable.
494 },
495 ],
496 "inputSource": [ # Input sources for this stage.
497 { # Description of an input or output of an execution stage.
498 "userName": "A String", # Human-readable name for this source; may be user or system generated.
499 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
500 # source is most closely associated.
501 "name": "A String", # Dataflow service generated name for this source.
502 "sizeBytes": "A String", # Size of the source, if measurable.
503 },
504 ],
505 "componentTransform": [ # Transforms that comprise this execution stage.
506 { # Description of a transform executed as part of an execution stage.
507 "userName": "A String", # Human-readable name for this transform; may be user or system generated.
508 "originalTransform": "A String", # User name for the original user transform with which this transform is
509 # most closely associated.
510 "name": "A String", # Dataflow service generated name for this source.
511 },
512 ],
513 "id": "A String", # Dataflow service generated id for this stage.
514 },
515 ],
516 },
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]517 "steps": [ # The top-level steps that constitute the entire job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]518 { # Defines a particular step within a Cloud Dataflow job.
519 #
520 # A job consists of multiple steps, each of which performs some
521 # specific operation as part of the overall job. Data is typically
522 # passed from one step to another as part of the job.
523 #
524 # Here's an example of a sequence of steps which together implement a
525 # Map-Reduce job:
526 #
527 # * Read a collection of data from some source, parsing the
528 # collection's elements.
529 #
530 # * Validate the elements.
531 #
532 # * Apply a user-defined function to map each element to some value
533 # and extract an element-specific key value.
534 #
535 # * Group elements with the same key into a single element with
536 # that key, transforming a multiply-keyed collection into a
537 # uniquely-keyed collection.
538 #
539 # * Write the elements out to some data sink.
540 #
541 # Note that the Cloud Dataflow service may be used to run many different
542 # types of jobs, not just Map-Reduce.
543 "kind": "A String", # The kind of step in the Cloud Dataflow job.
544 "properties": { # Named properties associated with the step. Each kind of
545 # predefined step has its own required set of properties.
546 # Must be provided on Create. Only retrieved with JOB_VIEW_ALL.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]547 "a_key": "", # Properties of the object.
548 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]549 "name": "A String", # The name that identifies the step. This must be unique for each
550 # step with respect to all other steps in the Cloud Dataflow job.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]551 },
552 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]553 "currentState": "A String", # The current state of the job.
554 #
555 # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
556 # specified.
557 #
558 # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
559 # terminal state. After a job has reached a terminal state, no
560 # further state updates may be made.
561 #
562 # This field may be mutated by the Cloud Dataflow service;
563 # callers cannot mutate it.
564 "tempFiles": [ # A set of files the system should be aware of that are used
565 # for temporary storage. These temporary files will be
566 # removed on job completion.
567 # No duplicates are allowed.
568 # No file patterns are supported.
569 #
570 # The supported files are:
571 #
572 # Google Cloud Storage:
573 #
574 # storage.googleapis.com/{bucket}/{object}
575 # bucket.storage.googleapis.com/{object}
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]576 "A String",
577 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]578 "type": "A String", # The type of Cloud Dataflow job.
579 "id": "A String", # The unique ID of this job.
580 #
581 # This field is set by the Cloud Dataflow service when the Job is
582 # created, and is immutable for the life of the job.
583 "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
584 # of the job it replaced.
585 #
586 # When sending a `CreateJobRequest`, you can update a job by specifying it
587 # here. The job named here is stopped, and its intermediate state is
588 # transferred to this job.
589 "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
590 # isn't contained in the submitted job.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]591 "stages": { # A mapping from each stage to the information about that stage.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]592 "a_key": { # Contains information about how a particular
593 # google.dataflow.v1beta3.Step will be executed.
594 "stepName": [ # The steps associated with the execution stage.
595 # Note that stages may have several steps, and that a given step
596 # might be run by more than one stage.
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]597 "A String",
598 ],
599 },
600 },
601 },
602 }</pre>
603</div>
604
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame^]605<div class="method">
606 <code class="details" id="get">get(projectId, gcsPath=None, x__xgafv=None, view=None)</code>
607 <pre>Get the template associated with a template.
608
609Args:
610 projectId: string, Required. The ID of the Cloud Platform project that the job belongs to. (required)
611 gcsPath: string, Required. A Cloud Storage path to the template from which to
612create the job.
613Must be a valid Cloud Storage URL, beginning with `gs://`.
614 x__xgafv: string, V1 error format.
615 Allowed values
616 1 - v1 error format
617 2 - v2 error format
618 view: string, The view to retrieve. Defaults to METADATA_ONLY.
619
620Returns:
621 An object of the form:
622
623 { # The response to a GetTemplate request.
624 "status": { # The `Status` type defines a logical error model that is suitable for different # The status of the get template request. Any problems with the
625 # request will be indicated in the error_details.
626 # programming environments, including REST APIs and RPC APIs. It is used by
627 # [gRPC](https://github.com/grpc). The error model is designed to be:
628 #
629 # - Simple to use and understand for most users
630 # - Flexible enough to meet unexpected needs
631 #
632 # # Overview
633 #
634 # The `Status` message contains three pieces of data: error code, error message,
635 # and error details. The error code should be an enum value of
636 # google.rpc.Code, but it may accept additional error codes if needed. The
637 # error message should be a developer-facing English message that helps
638 # developers *understand* and *resolve* the error. If a localized user-facing
639 # error message is needed, put the localized message in the error details or
640 # localize it in the client. The optional error details may contain arbitrary
641 # information about the error. There is a predefined set of error detail types
642 # in the package `google.rpc` which can be used for common error conditions.
643 #
644 # # Language mapping
645 #
646 # The `Status` message is the logical representation of the error model, but it
647 # is not necessarily the actual wire format. When the `Status` message is
648 # exposed in different client libraries and different wire protocols, it can be
649 # mapped differently. For example, it will likely be mapped to some exceptions
650 # in Java, but more likely mapped to some error codes in C.
651 #
652 # # Other uses
653 #
654 # The error model and the `Status` message can be used in a variety of
655 # environments, either with or without APIs, to provide a
656 # consistent developer experience across different environments.
657 #
658 # Example uses of this error model include:
659 #
660 # - Partial errors. If a service needs to return partial errors to the client,
661 # it may embed the `Status` in the normal response to indicate the partial
662 # errors.
663 #
664 # - Workflow errors. A typical workflow has multiple steps. Each step may
665 # have a `Status` message for error reporting purpose.
666 #
667 # - Batch operations. If a client uses batch request and batch response, the
668 # `Status` message should be used directly inside batch response, one for
669 # each error sub-response.
670 #
671 # - Asynchronous operations. If an API call embeds asynchronous operation
672 # results in its response, the status of those operations should be
673 # represented directly using the `Status` message.
674 #
675 # - Logging. If some API errors are stored in logs, the message `Status` could
676 # be used directly after any stripping needed for security/privacy reasons.
677 "message": "A String", # A developer-facing error message, which should be in English. Any
678 # user-facing error message should be localized and sent in the
679 # google.rpc.Status.details field, or localized by the client.
680 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
681 "details": [ # A list of messages that carry the error details. There will be a
682 # common set of message types for APIs to use.
683 {
684 "a_key": "", # Properties of the object. Contains field @type with type URL.
685 },
686 ],
687 },
688 "metadata": { # Metadata describing a template. # The template metadata describing the template name, available
689 # parameters, etc.
690 "bypassTempDirValidation": True or False, # If true, will bypass the validation that the temp directory is
691 # writable. This should only be used with templates for pipelines
692 # that are guaranteed not to need to write to the temp directory,
693 # which is subject to change based on the optimizer.
694 "name": "A String", # Required. The name of the template.
695 "parameters": [ # The parameters for the template.
696 { # Metadata for a specific parameter.
697 "regexes": [ # Optional. Regexes that the parameter must match.
698 "A String",
699 ],
700 "helpText": "A String", # Required. The help text to display for the parameter.
701 "name": "A String", # Required. The name of the parameter.
702 "isOptional": True or False, # Optional. Whether the parameter is optional. Defaults to false.
703 "label": "A String", # Required. The label to display for the parameter.
704 },
705 ],
706 "description": "A String", # Optional. A description of the template.
707 },
708 }</pre>
709</div>
710
711<div class="method">
712 <code class="details" id="launch">launch(projectId, body, dryRun=None, gcsPath=None, x__xgafv=None)</code>
713 <pre>Launch a template.
714
715Args:
716 projectId: string, Required. The ID of the Cloud Platform project that the job belongs to. (required)
717 body: object, The request body. (required)
718 The object takes the form of:
719
720{ # Parameters to provide to the template being launched.
721 "environment": { # The environment values to set at runtime. # The runtime environment for the job.
722 "bypassTempDirValidation": True or False, # Whether to bypass the safety checks for the job's temporary directory.
723 # Use with caution.
724 "tempLocation": "A String", # The Cloud Storage path to use for temporary files.
725 # Must be a valid Cloud Storage URL, beginning with `gs://`.
726 "serviceAccountEmail": "A String", # The email address of the service account to run the job as.
727 "zone": "A String", # The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)
728 # for launching worker instances to run your pipeline.
729 "maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
730 # available to your pipeline during execution, from 1 to 1000.
731 },
732 "parameters": { # The runtime parameters to pass to the job.
733 "a_key": "A String",
734 },
735 "jobName": "A String", # Required. The job name to use for the created job.
736 }
737
738 dryRun: boolean, Whether or not the job should actually be executed after
739validating parameters. Defaults to false. Validation errors do
740not cause the HTTP request to fail if true.
741 gcsPath: string, Required. A Cloud Storage path to the template from which to create
742the job.
743Must be valid Cloud Storage URL, beginning with 'gs://'.
744 x__xgafv: string, V1 error format.
745 Allowed values
746 1 - v1 error format
747 2 - v2 error format
748
749Returns:
750 An object of the form:
751
752 { # Response to the request to launch a template.
753 "status": { # The `Status` type defines a logical error model that is suitable for different # The status of the launch template request. Any problems with the request
754 # will be indicated in the error_details.
755 # programming environments, including REST APIs and RPC APIs. It is used by
756 # [gRPC](https://github.com/grpc). The error model is designed to be:
757 #
758 # - Simple to use and understand for most users
759 # - Flexible enough to meet unexpected needs
760 #
761 # # Overview
762 #
763 # The `Status` message contains three pieces of data: error code, error message,
764 # and error details. The error code should be an enum value of
765 # google.rpc.Code, but it may accept additional error codes if needed. The
766 # error message should be a developer-facing English message that helps
767 # developers *understand* and *resolve* the error. If a localized user-facing
768 # error message is needed, put the localized message in the error details or
769 # localize it in the client. The optional error details may contain arbitrary
770 # information about the error. There is a predefined set of error detail types
771 # in the package `google.rpc` which can be used for common error conditions.
772 #
773 # # Language mapping
774 #
775 # The `Status` message is the logical representation of the error model, but it
776 # is not necessarily the actual wire format. When the `Status` message is
777 # exposed in different client libraries and different wire protocols, it can be
778 # mapped differently. For example, it will likely be mapped to some exceptions
779 # in Java, but more likely mapped to some error codes in C.
780 #
781 # # Other uses
782 #
783 # The error model and the `Status` message can be used in a variety of
784 # environments, either with or without APIs, to provide a
785 # consistent developer experience across different environments.
786 #
787 # Example uses of this error model include:
788 #
789 # - Partial errors. If a service needs to return partial errors to the client,
790 # it may embed the `Status` in the normal response to indicate the partial
791 # errors.
792 #
793 # - Workflow errors. A typical workflow has multiple steps. Each step may
794 # have a `Status` message for error reporting purpose.
795 #
796 # - Batch operations. If a client uses batch request and batch response, the
797 # `Status` message should be used directly inside batch response, one for
798 # each error sub-response.
799 #
800 # - Asynchronous operations. If an API call embeds asynchronous operation
801 # results in its response, the status of those operations should be
802 # represented directly using the `Status` message.
803 #
804 # - Logging. If some API errors are stored in logs, the message `Status` could
805 # be used directly after any stripping needed for security/privacy reasons.
806 "message": "A String", # A developer-facing error message, which should be in English. Any
807 # user-facing error message should be localized and sent in the
808 # google.rpc.Status.details field, or localized by the client.
809 "code": 42, # The status code, which should be an enum value of google.rpc.Code.
810 "details": [ # A list of messages that carry the error details. There will be a
811 # common set of message types for APIs to use.
812 {
813 "a_key": "", # Properties of the object. Contains field @type with type URL.
814 },
815 ],
816 },
817 "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
818 # the job was successfully launched.
819 "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts.
820 # If this field is set, the service will ensure its uniqueness.
821 # The request to create a job will fail if the service has knowledge of a
822 # previously submitted job with the same client's ID and job name.
823 # The caller may use this field to ensure idempotence of job
824 # creation across retried attempts to create a job.
825 # By default, the field is empty and, in that case, the service ignores it.
826 "requestedState": "A String", # The job's requested state.
827 #
828 # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
829 # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may
830 # also be used to directly set a job's requested state to
831 # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
832 # job if it has not already reached a terminal state.
833 "name": "A String", # The user-specified Cloud Dataflow job name.
834 #
835 # Only one Job with a given name may exist in a project at any
836 # given time. If a caller attempts to create a Job with the same
837 # name as an already-existing Job, the attempt returns the
838 # existing Job.
839 #
840 # The name must match the regular expression
841 # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
842 "currentStateTime": "A String", # The timestamp associated with the current state.
843 "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
844 # `JOB_STATE_UPDATED`), this field contains the ID of that job.
845 "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
846 "labels": { # User-defined labels for this job.
847 #
848 # The labels map can contain no more than 64 entries. Entries of the labels
849 # map are UTF8 strings that comply with the following restrictions:
850 #
851 # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62}
852 # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63}
853 # * Both keys and values are additionally constrained to be <= 128 bytes in
854 # size.
855 "a_key": "A String",
856 },
857 "location": "A String", # The location that contains this job.
858 "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
859 # Cloud Dataflow service.
860 "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
861 # corresponding name prefixes of the new job.
862 "a_key": "A String",
863 },
864 "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
865 "version": { # A structure describing which components and their versions of the service
866 # are required in order to run the job.
867 "a_key": "", # Properties of the object.
868 },
869 "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
870 # storage. The system will append the suffix "/temp-{JOBNAME} to
871 # this resource prefix, where {JOBNAME} is the value of the
872 # job_name field. The resulting bucket and object prefix is used
873 # as the prefix of the resources used to store temporary data
874 # needed during the job execution. NOTE: This will override the
875 # value in taskrunner_settings.
876 # The supported resource type is:
877 #
878 # Google Cloud Storage:
879 #
880 # storage.googleapis.com/{bucket}/{object}
881 # bucket.storage.googleapis.com/{object}
882 "internalExperiments": { # Experimental settings.
883 "a_key": "", # Properties of the object. Contains field @type with type URL.
884 },
885 "dataset": "A String", # The dataset for the current project where various workflow
886 # related tables are stored.
887 #
888 # The supported resource type is:
889 #
890 # Google BigQuery:
891 # bigquery.googleapis.com/{dataset}
892 "experiments": [ # The list of experiments to enable.
893 "A String",
894 ],
895 "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account.
896 "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These
897 # options are passed through the service and are used to recreate the
898 # SDK pipeline options on the worker in a language agnostic and platform
899 # independent way.
900 "a_key": "", # Properties of the object.
901 },
902 "userAgent": { # A description of the process that generated the request.
903 "a_key": "", # Properties of the object.
904 },
905 "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or
906 # unspecified, the service will attempt to choose a reasonable
907 # default. This should be in the form of the API service name,
908 # e.g. "compute.googleapis.com".
909 "workerPools": [ # The worker pools. At least one "harness" worker pool must be
910 # specified in order for the job to have workers.
911 { # Describes one particular pool of Cloud Dataflow workers to be
912 # instantiated by the Cloud Dataflow service in order to perform the
913 # computations required by a job. Note that a workflow job may use
914 # multiple pools, in order to match the various computational
915 # requirements of the various stages of the job.
916 "diskSourceImage": "A String", # Fully qualified source image for disks.
917 "ipConfiguration": "A String", # Configuration for VM IPs.
918 "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
919 # are supported.
920 "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
921 # service will attempt to choose a reasonable default.
922 "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
923 # the service will use the network "default".
924 "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
925 # will attempt to choose a reasonable default.
926 "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
927 # attempt to choose a reasonable default.
928 "metadata": { # Metadata to set on the Google Compute Engine VMs.
929 "a_key": "A String",
930 },
931 "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
932 # Compute Engine API.
933 "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
934 # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
935 # `TEARDOWN_NEVER`.
936 # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
937 # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
938 # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
939 # down.
940 #
941 # If the workers are not torn down by the service, they will
942 # continue to run and use Google Compute Engine VM resources in the
943 # user's project until they are explicitly terminated by the user.
944 # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
945 # policy except for small, manually supervised test jobs.
946 #
947 # If unknown or unspecified, the service will attempt to choose a reasonable
948 # default.
949 "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
950 # service will choose a number of threads (according to the number of cores
951 # on the selected machine type for batch, or 1 by convention for streaming).
952 "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
953 # the form "regions/REGION/subnetworks/SUBNETWORK".
954 "poolArgs": { # Extra arguments for this worker pool.
955 "a_key": "", # Properties of the object. Contains field @type with type URL.
956 },
957 "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
958 # execute the job. If zero or unspecified, the service will
959 # attempt to choose a reasonable default.
960 "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
961 # using the standard Dataflow task runner. Users should ignore
962 # this field.
963 "workflowFileName": "A String", # The file to store the workflow in.
964 "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs
965 # will not be uploaded.
966 #
967 # The supported resource type is:
968 #
969 # Google Cloud Storage:
970 # storage.googleapis.com/{bucket}/{object}
971 # bucket.storage.googleapis.com/{object}
972 "commandlinesFileName": "A String", # The file to store preprocessing commands in.
973 "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
974 "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
975 "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
976 "vmId": "A String", # The ID string of the VM.
977 "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
978 # taskrunner; e.g. "wheel".
979 "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
980 # taskrunner; e.g. "root".
981 "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
982 # access the Cloud Dataflow API.
983 "A String",
984 ],
985 "languageHint": "A String", # The suggested backend language.
986 "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
987 # console.
988 "streamingWorkerMainClass": "A String", # The streaming worker main class name.
989 "logDir": "A String", # The directory on the VM to store logs.
990 "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
991 "reportingEnabled": True or False, # Whether to send work progress updates to the service.
992 "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
993 # "shuffle/v1beta1".
994 "workerId": "A String", # The ID of the worker running this pipeline.
995 "baseUrl": "A String", # The base URL for accessing Google Cloud APIs.
996 #
997 # When workers access Google Cloud APIs, they logically do so via
998 # relative URLs. If this field is specified, it supplies the base
999 # URL to use for resolving these relative URLs. The normative
1000 # algorithm used is defined by RFC 1808, "Relative Uniform Resource
1001 # Locators".
1002 #
1003 # If not specified, the default value is "http://www.googleapis.com/"
1004 "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example,
1005 # "dataflow/v1b3/projects".
1006 "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
1007 # storage.
1008 #
1009 # The supported resource type is:
1010 #
1011 # Google Cloud Storage:
1012 #
1013 # storage.googleapis.com/{bucket}/{object}
1014 # bucket.storage.googleapis.com/{object}
1015 },
1016 "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
1017 "harnessCommand": "A String", # The command to launch the worker harness.
1018 "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
1019 # temporary storage.
1020 #
1021 # The supported resource type is:
1022 #
1023 # Google Cloud Storage:
1024 # storage.googleapis.com/{bucket}/{object}
1025 # bucket.storage.googleapis.com/{object}
1026 "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
1027 #
1028 # When workers access Google Cloud APIs, they logically do so via
1029 # relative URLs. If this field is specified, it supplies the base
1030 # URL to use for resolving these relative URLs. The normative
1031 # algorithm used is defined by RFC 1808, "Relative Uniform Resource
1032 # Locators".
1033 #
1034 # If not specified, the default value is "http://www.googleapis.com/"
1035 },
1036 "defaultPackageSet": "A String", # The default package set to install. This allows the service to
1037 # select a default set of packages which are useful to worker
1038 # harnesses written in a particular language.
1039 "packages": [ # Packages to be installed on workers.
1040 { # The packages that must be installed in order for a worker to run the
1041 # steps of the Cloud Dataflow job that will be assigned to its worker
1042 # pool.
1043 #
1044 # This is the mechanism by which the Cloud Dataflow SDK causes code to
1045 # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
1046 # might use this to install jars containing the user's code and all of the
1047 # various dependencies (libraries, data files, etc.) required in order
1048 # for that code to run.
1049 "location": "A String", # The resource to read the package from. The supported resource type is:
1050 #
1051 # Google Cloud Storage:
1052 #
1053 # storage.googleapis.com/{bucket}
1054 # bucket.storage.googleapis.com/
1055 "name": "A String", # The name of the package.
1056 },
1057 ],
1058 "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
1059 "algorithm": "A String", # The algorithm to use for autoscaling.
1060 "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
1061 },
1062 "dataDisks": [ # Data disks that are used by a VM in this workflow.
1063 { # Describes the data disk used by a workflow job.
1064 "mountPoint": "A String", # Directory in a VM where disk is mounted.
1065 "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will
1066 # attempt to choose a reasonable default.
1067 "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This
1068 # must be a disk type appropriate to the project and zone in which
1069 # the workers will run. If unknown or unspecified, the service
1070 # will attempt to choose a reasonable default.
1071 #
1072 # For example, the standard persistent disk type is a resource name
1073 # typically ending in "pd-standard". If SSD persistent disks are
1074 # available, the resource name typically ends with "pd-ssd". The
1075 # actual valid values are defined the Google Compute Engine API,
1076 # not by the Cloud Dataflow API; consult the Google Compute Engine
1077 # documentation for more information about determining the set of
1078 # available disk types for a particular project and zone.
1079 #
1080 # Google Compute Engine Disk types are local to a particular
1081 # project in a particular zone, and so the resource name will
1082 # typically look something like this:
1083 #
1084 # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
1085 },
1086 ],
1087 "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
1088 # attempt to choose a reasonable default.
1089 "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
1090 # harness, residing in Google Container Registry.
1091 },
1092 ],
1093 },
1094 "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
1095 # A description of the user pipeline and stages through which it is executed.
1096 # Created by Cloud Dataflow service. Only retrieved with
1097 # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
1098 # form. This data is provided by the Dataflow service for ease of visualizing
1099 # the pipeline and interpretting Dataflow provided metrics.
1100 "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them.
1101 { # Description of the type, names/ids, and input/outputs for a transform.
1102 "kind": "A String", # Type of transform.
1103 "name": "A String", # User provided name for this transform instance.
1104 "inputCollectionName": [ # User names for all collection inputs to this transform.
1105 "A String",
1106 ],
1107 "displayData": [ # Transform-specific display data.
1108 { # Data provided with a pipeline or transform to provide descriptive info.
1109 "key": "A String", # The key identifying the display data.
1110 # This is intended to be used as a label for the display data
1111 # when viewed in a dax monitoring system.
1112 "shortStrValue": "A String", # A possible additional shorter value to display.
1113 # For example a java_class_name_value of com.mypackage.MyDoFn
1114 # will be stored with MyDoFn as the short_str_value and
1115 # com.mypackage.MyDoFn as the java_class_name value.
1116 # short_str_value can be displayed and java_class_name_value
1117 # will be displayed as a tooltip.
1118 "timestampValue": "A String", # Contains value if the data is of timestamp type.
1119 "url": "A String", # An optional full URL.
1120 "floatValue": 3.14, # Contains value if the data is of float type.
1121 "namespace": "A String", # The namespace for the key. This is usually a class name or programming
1122 # language namespace (i.e. python module) which defines the display data.
1123 # This allows a dax monitoring system to specially handle the data
1124 # and perform custom rendering.
1125 "javaClassValue": "A String", # Contains value if the data is of java class type.
1126 "label": "A String", # An optional label to display in a dax UI for the element.
1127 "boolValue": True or False, # Contains value if the data is of a boolean type.
1128 "strValue": "A String", # Contains value if the data is of string type.
1129 "durationValue": "A String", # Contains value if the data is of duration type.
1130 "int64Value": "A String", # Contains value if the data is of int64 type.
1131 },
1132 ],
1133 "outputCollectionName": [ # User names for all collection outputs to this transform.
1134 "A String",
1135 ],
1136 "id": "A String", # SDK generated id of this transform instance.
1137 },
1138 ],
1139 "displayData": [ # Pipeline level display data.
1140 { # Data provided with a pipeline or transform to provide descriptive info.
1141 "key": "A String", # The key identifying the display data.
1142 # This is intended to be used as a label for the display data
1143 # when viewed in a dax monitoring system.
1144 "shortStrValue": "A String", # A possible additional shorter value to display.
1145 # For example a java_class_name_value of com.mypackage.MyDoFn
1146 # will be stored with MyDoFn as the short_str_value and
1147 # com.mypackage.MyDoFn as the java_class_name value.
1148 # short_str_value can be displayed and java_class_name_value
1149 # will be displayed as a tooltip.
1150 "timestampValue": "A String", # Contains value if the data is of timestamp type.
1151 "url": "A String", # An optional full URL.
1152 "floatValue": 3.14, # Contains value if the data is of float type.
1153 "namespace": "A String", # The namespace for the key. This is usually a class name or programming
1154 # language namespace (i.e. python module) which defines the display data.
1155 # This allows a dax monitoring system to specially handle the data
1156 # and perform custom rendering.
1157 "javaClassValue": "A String", # Contains value if the data is of java class type.
1158 "label": "A String", # An optional label to display in a dax UI for the element.
1159 "boolValue": True or False, # Contains value if the data is of a boolean type.
1160 "strValue": "A String", # Contains value if the data is of string type.
1161 "durationValue": "A String", # Contains value if the data is of duration type.
1162 "int64Value": "A String", # Contains value if the data is of int64 type.
1163 },
1164 ],
1165 "executionPipelineStage": [ # Description of each stage of execution of the pipeline.
1166 { # Description of the composing transforms, names/ids, and input/outputs of a
1167 # stage of execution. Some composing transforms and sources may have been
1168 # generated by the Dataflow service during execution planning.
1169 "componentSource": [ # Collections produced and consumed by component transforms of this stage.
1170 { # Description of an interstitial value between transforms in an execution
1171 # stage.
1172 "userName": "A String", # Human-readable name for this transform; may be user or system generated.
1173 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
1174 # source is most closely associated.
1175 "name": "A String", # Dataflow service generated name for this source.
1176 },
1177 ],
1178 "kind": "A String", # Type of tranform this stage is executing.
1179 "name": "A String", # Dataflow service generated name for this stage.
1180 "outputSource": [ # Output sources for this stage.
1181 { # Description of an input or output of an execution stage.
1182 "userName": "A String", # Human-readable name for this source; may be user or system generated.
1183 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
1184 # source is most closely associated.
1185 "name": "A String", # Dataflow service generated name for this source.
1186 "sizeBytes": "A String", # Size of the source, if measurable.
1187 },
1188 ],
1189 "inputSource": [ # Input sources for this stage.
1190 { # Description of an input or output of an execution stage.
1191 "userName": "A String", # Human-readable name for this source; may be user or system generated.
1192 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
1193 # source is most closely associated.
1194 "name": "A String", # Dataflow service generated name for this source.
1195 "sizeBytes": "A String", # Size of the source, if measurable.
1196 },
1197 ],
1198 "componentTransform": [ # Transforms that comprise this execution stage.
1199 { # Description of a transform executed as part of an execution stage.
1200 "userName": "A String", # Human-readable name for this transform; may be user or system generated.
1201 "originalTransform": "A String", # User name for the original user transform with which this transform is
1202 # most closely associated.
1203 "name": "A String", # Dataflow service generated name for this source.
1204 },
1205 ],
1206 "id": "A String", # Dataflow service generated id for this stage.
1207 },
1208 ],
1209 },
1210 "steps": [ # The top-level steps that constitute the entire job.
1211 { # Defines a particular step within a Cloud Dataflow job.
1212 #
1213 # A job consists of multiple steps, each of which performs some
1214 # specific operation as part of the overall job. Data is typically
1215 # passed from one step to another as part of the job.
1216 #
1217 # Here's an example of a sequence of steps which together implement a
1218 # Map-Reduce job:
1219 #
1220 # * Read a collection of data from some source, parsing the
1221 # collection's elements.
1222 #
1223 # * Validate the elements.
1224 #
1225 # * Apply a user-defined function to map each element to some value
1226 # and extract an element-specific key value.
1227 #
1228 # * Group elements with the same key into a single element with
1229 # that key, transforming a multiply-keyed collection into a
1230 # uniquely-keyed collection.
1231 #
1232 # * Write the elements out to some data sink.
1233 #
1234 # Note that the Cloud Dataflow service may be used to run many different
1235 # types of jobs, not just Map-Reduce.
1236 "kind": "A String", # The kind of step in the Cloud Dataflow job.
1237 "properties": { # Named properties associated with the step. Each kind of
1238 # predefined step has its own required set of properties.
1239 # Must be provided on Create. Only retrieved with JOB_VIEW_ALL.
1240 "a_key": "", # Properties of the object.
1241 },
1242 "name": "A String", # The name that identifies the step. This must be unique for each
1243 # step with respect to all other steps in the Cloud Dataflow job.
1244 },
1245 ],
1246 "currentState": "A String", # The current state of the job.
1247 #
1248 # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
1249 # specified.
1250 #
1251 # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
1252 # terminal state. After a job has reached a terminal state, no
1253 # further state updates may be made.
1254 #
1255 # This field may be mutated by the Cloud Dataflow service;
1256 # callers cannot mutate it.
1257 "tempFiles": [ # A set of files the system should be aware of that are used
1258 # for temporary storage. These temporary files will be
1259 # removed on job completion.
1260 # No duplicates are allowed.
1261 # No file patterns are supported.
1262 #
1263 # The supported files are:
1264 #
1265 # Google Cloud Storage:
1266 #
1267 # storage.googleapis.com/{bucket}/{object}
1268 # bucket.storage.googleapis.com/{object}
1269 "A String",
1270 ],
1271 "type": "A String", # The type of Cloud Dataflow job.
1272 "id": "A String", # The unique ID of this job.
1273 #
1274 # This field is set by the Cloud Dataflow service when the Job is
1275 # created, and is immutable for the life of the job.
1276 "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
1277 # of the job it replaced.
1278 #
1279 # When sending a `CreateJobRequest`, you can update a job by specifying it
1280 # here. The job named here is stopped, and its intermediate state is
1281 # transferred to this job.
1282 "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
1283 # isn't contained in the submitted job.
1284 "stages": { # A mapping from each stage to the information about that stage.
1285 "a_key": { # Contains information about how a particular
1286 # google.dataflow.v1beta3.Step will be executed.
1287 "stepName": [ # The steps associated with the execution stage.
1288 # Note that stages may have several steps, and that a given step
1289 # might be run by more than one stage.
1290 "A String",
1291 ],
1292 },
1293 },
1294 },
1295 },
1296 }</pre>
1297</div>
1298
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]1299</body></html>