Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / python / google-api-python-client / 2f245374da9c895dbd8bb0423e98707d51b53414 / . / docs / dyn / dataflow_v1b3.projects.templates.html
blob: c5f399829819e1b0805cc0f2208d7c012a90a761 [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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]98 "maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
99 # available to your pipeline during execution, from 1 to 1000.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]105 "bypassTempDirValidation": True or False, # Whether to bypass the safety checks for the job's temporary directory.
106 # Use with caution.
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 },
Thomas Coffee2f245372017-03-27 10:39:26 -0700[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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]224 "ipConfiguration": "A String", # Configuration for VM IPs.
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.
235 "metadata": { # Metadata to set on the Google Compute Engine VMs.
236 "a_key": "A String",
237 },
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".
261 "poolArgs": { # Extra arguments for this worker pool.
262 "a_key": "", # Properties of the object. Contains field @type with type URL.
263 },
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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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}
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]279 "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
280 # taskrunner; e.g. "root".
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700[diff] [blame]281 "commandlinesFileName": "A String", # The file to store preprocessing commands in.
282 "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
283 "vmId": "A String", # The ID string of the VM.
284 "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
285 "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]286 "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
287 # access the Cloud Dataflow API.
288 "A String",
289 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]290 "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
291 "reportingEnabled": True or False, # Whether to send work progress updates to the service.
292 "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
293 # "shuffle/v1beta1".
294 "workerId": "A String", # The ID of the worker running this pipeline.
295 "baseUrl": "A String", # The base URL for accessing Google Cloud APIs.
296 #
297 # When workers access Google Cloud APIs, they logically do so via
298 # relative URLs. If this field is specified, it supplies the base
299 # URL to use for resolving these relative URLs. The normative
300 # algorithm used is defined by RFC 1808, "Relative Uniform Resource
301 # Locators".
302 #
303 # If not specified, the default value is "http://www.googleapis.com/"
304 "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example,
305 # "dataflow/v1b3/projects".
306 "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
307 # storage.
308 #
309 # The supported resource type is:
310 #
311 # Google Cloud Storage:
312 #
313 # storage.googleapis.com/{bucket}/{object}
314 # bucket.storage.googleapis.com/{object}
315 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700[diff] [blame]316 "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
317 # taskrunner; e.g. "wheel".
318 "languageHint": "A String", # The suggested backend language.
319 "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
320 # console.
321 "streamingWorkerMainClass": "A String", # The streaming worker main class name.
322 "logDir": "A String", # The directory on the VM to store logs.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]323 "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]324 "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
325 #
326 # When workers access Google Cloud APIs, they logically do so via
327 # relative URLs. If this field is specified, it supplies the base
328 # URL to use for resolving these relative URLs. The normative
329 # algorithm used is defined by RFC 1808, "Relative Uniform Resource
330 # Locators".
331 #
332 # If not specified, the default value is "http://www.googleapis.com/"
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700[diff] [blame]333 "harnessCommand": "A String", # The command to launch the worker harness.
334 "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
335 # temporary storage.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]336 #
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700[diff] [blame]337 # The supported resource type is:
338 #
339 # Google Cloud Storage:
340 # storage.googleapis.com/{bucket}/{object}
341 # bucket.storage.googleapis.com/{object}
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]342 },
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]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.
346 "packages": [ # Packages to be installed on workers.
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 "name": "A String", # The name of the package.
357 "location": "A String", # The resource to read the package from. The supported resource type is:
358 #
359 # Google Cloud Storage:
360 #
361 # storage.googleapis.com/{bucket}
362 # bucket.storage.googleapis.com/
363 },
364 ],
365 "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
366 "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
367 "algorithm": "A String", # The algorithm to use for autoscaling.
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 ],
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]394 "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]436 "durationValue": "A String", # Contains value if the data is of duration type.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]468 "durationValue": "A String", # Contains value if the data is of duration type.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]492 "name": "A String", # Dataflow service generated name for this source.
493 "sizeBytes": "A String", # Size of the source, if measurable.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]501 "name": "A String", # Dataflow service generated name for this source.
502 "sizeBytes": "A String", # Size of the source, if measurable.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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 },
Thomas Coffee2f245372017-03-27 10:39:26 -0700[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 ],
Thomas Coffee2f245372017-03-27 10:39:26 -0700[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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]585 #
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]722 "maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
723 # available to your pipeline during execution, from 1 to 1000.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]729 "bypassTempDirValidation": True or False, # Whether to bypass the safety checks for the job's temporary directory.
730 # Use with caution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]753 "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
754 # the job was successfully launched.
755 "clientRequestId": "A String", # The client's unique identifier of the job, re-used across retried attempts.
756 # If this field is set, the service will ensure its uniqueness.
757 # The request to create a job will fail if the service has knowledge of a
758 # previously submitted job with the same client's ID and job name.
759 # The caller may use this field to ensure idempotence of job
760 # creation across retried attempts to create a job.
761 # By default, the field is empty and, in that case, the service ignores it.
762 "requestedState": "A String", # The job's requested state.
763 #
764 # `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and
765 # `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may
766 # also be used to directly set a job's requested state to
767 # `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
768 # job if it has not already reached a terminal state.
769 "name": "A String", # The user-specified Cloud Dataflow job name.
770 #
771 # Only one Job with a given name may exist in a project at any
772 # given time. If a caller attempts to create a Job with the same
773 # name as an already-existing Job, the attempt returns the
774 # existing Job.
775 #
776 # The name must match the regular expression
777 # `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
778 "currentStateTime": "A String", # The timestamp associated with the current state.
779 "replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
780 # `JOB_STATE_UPDATED`), this field contains the ID of that job.
781 "projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
782 "labels": { # User-defined labels for this job.
783 #
784 # The labels map can contain no more than 64 entries. Entries of the labels
785 # map are UTF8 strings that comply with the following restrictions:
786 #
787 # * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62}
788 # * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63}
789 # * Both keys and values are additionally constrained to be <= 128 bytes in
790 # size.
791 "a_key": "A String",
792 },
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]793 "location": "A String", # The location that contains this job.
794 "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
795 # Cloud Dataflow service.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]796 "transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
797 # corresponding name prefixes of the new job.
798 "a_key": "A String",
799 },
800 "environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
801 "version": { # A structure describing which components and their versions of the service
802 # are required in order to run the job.
803 "a_key": "", # Properties of the object.
804 },
805 "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
806 # storage. The system will append the suffix "/temp-{JOBNAME} to
807 # this resource prefix, where {JOBNAME} is the value of the
808 # job_name field. The resulting bucket and object prefix is used
809 # as the prefix of the resources used to store temporary data
810 # needed during the job execution. NOTE: This will override the
811 # value in taskrunner_settings.
812 # The supported resource type is:
813 #
814 # Google Cloud Storage:
815 #
816 # storage.googleapis.com/{bucket}/{object}
817 # bucket.storage.googleapis.com/{object}
818 "internalExperiments": { # Experimental settings.
819 "a_key": "", # Properties of the object. Contains field @type with type URL.
820 },
821 "dataset": "A String", # The dataset for the current project where various workflow
822 # related tables are stored.
823 #
824 # The supported resource type is:
825 #
826 # Google BigQuery:
827 # bigquery.googleapis.com/{dataset}
828 "experiments": [ # The list of experiments to enable.
829 "A String",
830 ],
831 "serviceAccountEmail": "A String", # Identity to run virtual machines as. Defaults to the default account.
832 "sdkPipelineOptions": { # The Cloud Dataflow SDK pipeline options specified by the user. These
833 # options are passed through the service and are used to recreate the
834 # SDK pipeline options on the worker in a language agnostic and platform
835 # independent way.
836 "a_key": "", # Properties of the object.
837 },
838 "userAgent": { # A description of the process that generated the request.
839 "a_key": "", # Properties of the object.
840 },
841 "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or
842 # unspecified, the service will attempt to choose a reasonable
843 # default. This should be in the form of the API service name,
844 # e.g. "compute.googleapis.com".
845 "workerPools": [ # The worker pools. At least one "harness" worker pool must be
846 # specified in order for the job to have workers.
847 { # Describes one particular pool of Cloud Dataflow workers to be
848 # instantiated by the Cloud Dataflow service in order to perform the
849 # computations required by a job. Note that a workflow job may use
850 # multiple pools, in order to match the various computational
851 # requirements of the various stages of the job.
852 "diskSourceImage": "A String", # Fully qualified source image for disks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]853 "ipConfiguration": "A String", # Configuration for VM IPs.
854 "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
855 # are supported.
856 "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
857 # service will attempt to choose a reasonable default.
858 "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
859 # the service will use the network "default".
860 "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
861 # will attempt to choose a reasonable default.
862 "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
863 # attempt to choose a reasonable default.
864 "metadata": { # Metadata to set on the Google Compute Engine VMs.
865 "a_key": "A String",
866 },
867 "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
868 # Compute Engine API.
869 "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
870 # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
871 # `TEARDOWN_NEVER`.
872 # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
873 # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
874 # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
875 # down.
876 #
877 # If the workers are not torn down by the service, they will
878 # continue to run and use Google Compute Engine VM resources in the
879 # user's project until they are explicitly terminated by the user.
880 # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
881 # policy except for small, manually supervised test jobs.
882 #
883 # If unknown or unspecified, the service will attempt to choose a reasonable
884 # default.
885 "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
886 # service will choose a number of threads (according to the number of cores
887 # on the selected machine type for batch, or 1 by convention for streaming).
888 "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
889 # the form "regions/REGION/subnetworks/SUBNETWORK".
890 "poolArgs": { # Extra arguments for this worker pool.
891 "a_key": "", # Properties of the object. Contains field @type with type URL.
892 },
893 "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
894 # execute the job. If zero or unspecified, the service will
895 # attempt to choose a reasonable default.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]896 "taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
897 # using the standard Dataflow task runner. Users should ignore
898 # this field.
899 "workflowFileName": "A String", # The file to store the workflow in.
900 "logUploadLocation": "A String", # Indicates where to put logs. If this is not specified, the logs
901 # will not be uploaded.
902 #
903 # The supported resource type is:
904 #
905 # Google Cloud Storage:
906 # storage.googleapis.com/{bucket}/{object}
907 # bucket.storage.googleapis.com/{object}
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]908 "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
909 # taskrunner; e.g. "root".
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700[diff] [blame]910 "commandlinesFileName": "A String", # The file to store preprocessing commands in.
911 "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
912 "vmId": "A String", # The ID string of the VM.
913 "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
914 "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]915 "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
916 # access the Cloud Dataflow API.
917 "A String",
918 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]919 "parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
920 "reportingEnabled": True or False, # Whether to send work progress updates to the service.
921 "shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
922 # "shuffle/v1beta1".
923 "workerId": "A String", # The ID of the worker running this pipeline.
924 "baseUrl": "A String", # The base URL for accessing Google Cloud APIs.
925 #
926 # When workers access Google Cloud APIs, they logically do so via
927 # relative URLs. If this field is specified, it supplies the base
928 # URL to use for resolving these relative URLs. The normative
929 # algorithm used is defined by RFC 1808, "Relative Uniform Resource
930 # Locators".
931 #
932 # If not specified, the default value is "http://www.googleapis.com/"
933 "servicePath": "A String", # The Cloud Dataflow service path relative to the root URL, for example,
934 # "dataflow/v1b3/projects".
935 "tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
936 # storage.
937 #
938 # The supported resource type is:
939 #
940 # Google Cloud Storage:
941 #
942 # storage.googleapis.com/{bucket}/{object}
943 # bucket.storage.googleapis.com/{object}
944 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700[diff] [blame]945 "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
946 # taskrunner; e.g. "wheel".
947 "languageHint": "A String", # The suggested backend language.
948 "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
949 # console.
950 "streamingWorkerMainClass": "A String", # The streaming worker main class name.
951 "logDir": "A String", # The directory on the VM to store logs.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]952 "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]953 "baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
954 #
955 # When workers access Google Cloud APIs, they logically do so via
956 # relative URLs. If this field is specified, it supplies the base
957 # URL to use for resolving these relative URLs. The normative
958 # algorithm used is defined by RFC 1808, "Relative Uniform Resource
959 # Locators".
960 #
961 # If not specified, the default value is "http://www.googleapis.com/"
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700[diff] [blame]962 "harnessCommand": "A String", # The command to launch the worker harness.
963 "tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
964 # temporary storage.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]965 #
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700[diff] [blame]966 # The supported resource type is:
967 #
968 # Google Cloud Storage:
969 # storage.googleapis.com/{bucket}/{object}
970 # bucket.storage.googleapis.com/{object}
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]971 },
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]972 "defaultPackageSet": "A String", # The default package set to install. This allows the service to
973 # select a default set of packages which are useful to worker
974 # harnesses written in a particular language.
975 "packages": [ # Packages to be installed on workers.
976 { # The packages that must be installed in order for a worker to run the
977 # steps of the Cloud Dataflow job that will be assigned to its worker
978 # pool.
979 #
980 # This is the mechanism by which the Cloud Dataflow SDK causes code to
981 # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
982 # might use this to install jars containing the user's code and all of the
983 # various dependencies (libraries, data files, etc.) required in order
984 # for that code to run.
985 "name": "A String", # The name of the package.
986 "location": "A String", # The resource to read the package from. The supported resource type is:
987 #
988 # Google Cloud Storage:
989 #
990 # storage.googleapis.com/{bucket}
991 # bucket.storage.googleapis.com/
992 },
993 ],
994 "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
995 "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
996 "algorithm": "A String", # The algorithm to use for autoscaling.
997 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]998 "dataDisks": [ # Data disks that are used by a VM in this workflow.
999 { # Describes the data disk used by a workflow job.
1000 "mountPoint": "A String", # Directory in a VM where disk is mounted.
1001 "sizeGb": 42, # Size of disk in GB. If zero or unspecified, the service will
1002 # attempt to choose a reasonable default.
1003 "diskType": "A String", # Disk storage type, as defined by Google Compute Engine. This
1004 # must be a disk type appropriate to the project and zone in which
1005 # the workers will run. If unknown or unspecified, the service
1006 # will attempt to choose a reasonable default.
1007 #
1008 # For example, the standard persistent disk type is a resource name
1009 # typically ending in "pd-standard". If SSD persistent disks are
1010 # available, the resource name typically ends with "pd-ssd". The
1011 # actual valid values are defined the Google Compute Engine API,
1012 # not by the Cloud Dataflow API; consult the Google Compute Engine
1013 # documentation for more information about determining the set of
1014 # available disk types for a particular project and zone.
1015 #
1016 # Google Compute Engine Disk types are local to a particular
1017 # project in a particular zone, and so the resource name will
1018 # typically look something like this:
1019 #
1020 # compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
1021 },
1022 ],
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1023 "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1024 # attempt to choose a reasonable default.
1025 "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
1026 # harness, residing in Google Container Registry.
1027 },
1028 ],
1029 },
1030 "pipelineDescription": { # A descriptive representation of submitted pipeline as well as the executed # Preliminary field: The format of this data may change at any time.
1031 # A description of the user pipeline and stages through which it is executed.
1032 # Created by Cloud Dataflow service. Only retrieved with
1033 # JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
1034 # form. This data is provided by the Dataflow service for ease of visualizing
1035 # the pipeline and interpretting Dataflow provided metrics.
1036 "originalPipelineTransform": [ # Description of each transform in the pipeline and collections between them.
1037 { # Description of the type, names/ids, and input/outputs for a transform.
1038 "kind": "A String", # Type of transform.
1039 "name": "A String", # User provided name for this transform instance.
1040 "inputCollectionName": [ # User names for all collection inputs to this transform.
1041 "A String",
1042 ],
1043 "displayData": [ # Transform-specific display data.
1044 { # Data provided with a pipeline or transform to provide descriptive info.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1045 "key": "A String", # The key identifying the display data.
1046 # This is intended to be used as a label for the display data
1047 # when viewed in a dax monitoring system.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1048 "shortStrValue": "A String", # A possible additional shorter value to display.
1049 # For example a java_class_name_value of com.mypackage.MyDoFn
1050 # will be stored with MyDoFn as the short_str_value and
1051 # com.mypackage.MyDoFn as the java_class_name value.
1052 # short_str_value can be displayed and java_class_name_value
1053 # will be displayed as a tooltip.
1054 "timestampValue": "A String", # Contains value if the data is of timestamp type.
1055 "url": "A String", # An optional full URL.
1056 "floatValue": 3.14, # Contains value if the data is of float type.
1057 "namespace": "A String", # The namespace for the key. This is usually a class name or programming
1058 # language namespace (i.e. python module) which defines the display data.
1059 # This allows a dax monitoring system to specially handle the data
1060 # and perform custom rendering.
1061 "javaClassValue": "A String", # Contains value if the data is of java class type.
1062 "label": "A String", # An optional label to display in a dax UI for the element.
1063 "boolValue": True or False, # Contains value if the data is of a boolean type.
1064 "strValue": "A String", # Contains value if the data is of string type.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1065 "durationValue": "A String", # Contains value if the data is of duration type.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1066 "int64Value": "A String", # Contains value if the data is of int64 type.
1067 },
1068 ],
1069 "outputCollectionName": [ # User names for all collection outputs to this transform.
1070 "A String",
1071 ],
1072 "id": "A String", # SDK generated id of this transform instance.
1073 },
1074 ],
1075 "displayData": [ # Pipeline level display data.
1076 { # Data provided with a pipeline or transform to provide descriptive info.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1077 "key": "A String", # The key identifying the display data.
1078 # This is intended to be used as a label for the display data
1079 # when viewed in a dax monitoring system.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1080 "shortStrValue": "A String", # A possible additional shorter value to display.
1081 # For example a java_class_name_value of com.mypackage.MyDoFn
1082 # will be stored with MyDoFn as the short_str_value and
1083 # com.mypackage.MyDoFn as the java_class_name value.
1084 # short_str_value can be displayed and java_class_name_value
1085 # will be displayed as a tooltip.
1086 "timestampValue": "A String", # Contains value if the data is of timestamp type.
1087 "url": "A String", # An optional full URL.
1088 "floatValue": 3.14, # Contains value if the data is of float type.
1089 "namespace": "A String", # The namespace for the key. This is usually a class name or programming
1090 # language namespace (i.e. python module) which defines the display data.
1091 # This allows a dax monitoring system to specially handle the data
1092 # and perform custom rendering.
1093 "javaClassValue": "A String", # Contains value if the data is of java class type.
1094 "label": "A String", # An optional label to display in a dax UI for the element.
1095 "boolValue": True or False, # Contains value if the data is of a boolean type.
1096 "strValue": "A String", # Contains value if the data is of string type.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1097 "durationValue": "A String", # Contains value if the data is of duration type.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1098 "int64Value": "A String", # Contains value if the data is of int64 type.
1099 },
1100 ],
1101 "executionPipelineStage": [ # Description of each stage of execution of the pipeline.
1102 { # Description of the composing transforms, names/ids, and input/outputs of a
1103 # stage of execution. Some composing transforms and sources may have been
1104 # generated by the Dataflow service during execution planning.
1105 "componentSource": [ # Collections produced and consumed by component transforms of this stage.
1106 { # Description of an interstitial value between transforms in an execution
1107 # stage.
1108 "userName": "A String", # Human-readable name for this transform; may be user or system generated.
1109 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
1110 # source is most closely associated.
1111 "name": "A String", # Dataflow service generated name for this source.
1112 },
1113 ],
1114 "kind": "A String", # Type of tranform this stage is executing.
1115 "name": "A String", # Dataflow service generated name for this stage.
1116 "outputSource": [ # Output sources for this stage.
1117 { # Description of an input or output of an execution stage.
1118 "userName": "A String", # Human-readable name for this source; may be user or system generated.
1119 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
1120 # source is most closely associated.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1121 "name": "A String", # Dataflow service generated name for this source.
1122 "sizeBytes": "A String", # Size of the source, if measurable.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1123 },
1124 ],
1125 "inputSource": [ # Input sources for this stage.
1126 { # Description of an input or output of an execution stage.
1127 "userName": "A String", # Human-readable name for this source; may be user or system generated.
1128 "originalTransformOrCollection": "A String", # User name for the original user transform or collection with which this
1129 # source is most closely associated.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1130 "name": "A String", # Dataflow service generated name for this source.
1131 "sizeBytes": "A String", # Size of the source, if measurable.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1132 },
1133 ],
1134 "componentTransform": [ # Transforms that comprise this execution stage.
1135 { # Description of a transform executed as part of an execution stage.
1136 "userName": "A String", # Human-readable name for this transform; may be user or system generated.
1137 "originalTransform": "A String", # User name for the original user transform with which this transform is
1138 # most closely associated.
1139 "name": "A String", # Dataflow service generated name for this source.
1140 },
1141 ],
1142 "id": "A String", # Dataflow service generated id for this stage.
1143 },
1144 ],
1145 },
1146 "steps": [ # The top-level steps that constitute the entire job.
1147 { # Defines a particular step within a Cloud Dataflow job.
1148 #
1149 # A job consists of multiple steps, each of which performs some
1150 # specific operation as part of the overall job. Data is typically
1151 # passed from one step to another as part of the job.
1152 #
1153 # Here's an example of a sequence of steps which together implement a
1154 # Map-Reduce job:
1155 #
1156 # * Read a collection of data from some source, parsing the
1157 # collection's elements.
1158 #
1159 # * Validate the elements.
1160 #
1161 # * Apply a user-defined function to map each element to some value
1162 # and extract an element-specific key value.
1163 #
1164 # * Group elements with the same key into a single element with
1165 # that key, transforming a multiply-keyed collection into a
1166 # uniquely-keyed collection.
1167 #
1168 # * Write the elements out to some data sink.
1169 #
1170 # Note that the Cloud Dataflow service may be used to run many different
1171 # types of jobs, not just Map-Reduce.
1172 "kind": "A String", # The kind of step in the Cloud Dataflow job.
1173 "properties": { # Named properties associated with the step. Each kind of
1174 # predefined step has its own required set of properties.
1175 # Must be provided on Create. Only retrieved with JOB_VIEW_ALL.
1176 "a_key": "", # Properties of the object.
1177 },
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1178 "name": "A String", # The name that identifies the step. This must be unique for each
1179 # step with respect to all other steps in the Cloud Dataflow job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1180 },
1181 ],
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1182 "currentState": "A String", # The current state of the job.
1183 #
1184 # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
1185 # specified.
1186 #
1187 # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
1188 # terminal state. After a job has reached a terminal state, no
1189 # further state updates may be made.
1190 #
1191 # This field may be mutated by the Cloud Dataflow service;
1192 # callers cannot mutate it.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1193 "tempFiles": [ # A set of files the system should be aware of that are used
1194 # for temporary storage. These temporary files will be
1195 # removed on job completion.
1196 # No duplicates are allowed.
1197 # No file patterns are supported.
1198 #
1199 # The supported files are:
1200 #
1201 # Google Cloud Storage:
1202 #
1203 # storage.googleapis.com/{bucket}/{object}
1204 # bucket.storage.googleapis.com/{object}
1205 "A String",
1206 ],
1207 "type": "A String", # The type of Cloud Dataflow job.
1208 "id": "A String", # The unique ID of this job.
1209 #
1210 # This field is set by the Cloud Dataflow service when the Job is
1211 # created, and is immutable for the life of the job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1212 "replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
1213 # of the job it replaced.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1214 #
Thomas Coffee2f245372017-03-27 10:39:26 -0700[diff] [blame^]1215 # When sending a `CreateJobRequest`, you can update a job by specifying it
1216 # here. The job named here is stopped, and its intermediate state is
1217 # transferred to this job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400[diff] [blame]1218 "executionInfo": { # Additional information about how a Cloud Dataflow job will be executed that # Deprecated.
1219 # isn't contained in the submitted job.
1220 "stages": { # A mapping from each stage to the information about that stage.
1221 "a_key": { # Contains information about how a particular
1222 # google.dataflow.v1beta3.Step will be executed.
1223 "stepName": [ # The steps associated with the execution stage.
1224 # Note that stages may have several steps, and that a given step
1225 # might be run by more than one stage.
1226 "A String",
1227 ],
1228 },
1229 },
1230 },
1231 },
1232 }</pre>
1233</div>
1234
Jon Wayne Parrott7d5badb2016-08-16 12:44:29 -0700[diff] [blame]1235</body></html>