Clean and regen docs (#401)
diff --git a/docs/dyn/dataflow_v1b3.projects.templates.html b/docs/dyn/dataflow_v1b3.projects.templates.html
index c5f3998..73bacf7 100644
--- a/docs/dyn/dataflow_v1b3.projects.templates.html
+++ b/docs/dyn/dataflow_v1b3.projects.templates.html
@@ -78,10 +78,10 @@
<code><a href="#create">create(projectId, body, x__xgafv=None)</a></code></p>
<p class="firstline">Creates a Cloud Dataflow job from a template.</p>
<p class="toc_element">
- <code><a href="#get">get(projectId, gcsPath=None, x__xgafv=None, view=None)</a></code></p>
+ <code><a href="#get">get(projectId, gcsPath=None, location=None, x__xgafv=None, view=None)</a></code></p>
<p class="firstline">Get the template associated with a template.</p>
<p class="toc_element">
- <code><a href="#launch">launch(projectId, body, dryRun=None, gcsPath=None, x__xgafv=None)</a></code></p>
+ <code><a href="#launch">launch(projectId, body, gcsPath=None, location=None, validateOnly=None, x__xgafv=None)</a></code></p>
<p class="firstline">Launch a template.</p>
<h3>Method Details</h3>
<div class="method">
@@ -95,19 +95,23 @@
{ # A request to create a Cloud Dataflow job from a template.
"environment": { # The environment values to set at runtime. # The runtime environment for the job.
- "maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
- # available to your pipeline during execution, from 1 to 1000.
- "tempLocation": "A String", # The Cloud Storage path to use for temporary files.
- # Must be a valid Cloud Storage URL, beginning with `gs://`.
- "serviceAccountEmail": "A String", # The email address of the service account to run the job as.
- "zone": "A String", # The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)
+ "machineType": "A String", # The machine type to use for the job. Defaults to the value from the
+ # template if not specified.
+ "zone": "A String", # The Compute Engine [availability
+ # zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)
# for launching worker instances to run your pipeline.
"bypassTempDirValidation": True or False, # Whether to bypass the safety checks for the job's temporary directory.
# Use with caution.
+ "tempLocation": "A String", # The Cloud Storage path to use for temporary files.
+ # Must be a valid Cloud Storage URL, beginning with `gs://`.
+ "serviceAccountEmail": "A String", # The email address of the service account to run the job as.
+ "maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
+ # available to your pipeline during execution, from 1 to 1000.
},
"gcsPath": "A String", # Required. A Cloud Storage path to the template from which to
# create the job.
# Must be a valid Cloud Storage URL, beginning with `gs://`.
+ "location": "A String", # The location to which to direct the request.
"parameters": { # The runtime parameters to pass to the job.
"a_key": "A String",
},
@@ -146,10 +150,21 @@
#
# The name must match the regular expression
# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
- "currentStateTime": "A String", # The timestamp associated with the current state.
+ "location": "A String", # The location that contains this job.
"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
# `JOB_STATE_UPDATED`), this field contains the ID of that job.
"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
+ "currentState": "A String", # The current state of the job.
+ #
+ # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+ # specified.
+ #
+ # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+ # terminal state. After a job has reached a terminal state, no
+ # further state updates may be made.
+ #
+ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
"labels": { # User-defined labels for this job.
#
# The labels map can contain no more than 64 entries. Entries of the labels
@@ -161,13 +176,14 @@
# size.
"a_key": "A String",
},
- "location": "A String", # The location that contains this job.
- "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
- # Cloud Dataflow service.
"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
# corresponding name prefixes of the new job.
"a_key": "A String",
},
+ "id": "A String", # The unique ID of this job.
+ #
+ # This field is set by the Cloud Dataflow service when the Job is
+ # created, and is immutable for the life of the job.
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
@@ -221,49 +237,6 @@
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
"diskSourceImage": "A String", # Fully qualified source image for disks.
- "ipConfiguration": "A String", # Configuration for VM IPs.
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
- "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
- # service will attempt to choose a reasonable default.
- "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
- # the service will use the network "default".
- "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
- # will attempt to choose a reasonable default.
- "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
- "metadata": { # Metadata to set on the Google Compute Engine VMs.
- "a_key": "A String",
- },
- "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
- # Compute Engine API.
- "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
- # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
- # `TEARDOWN_NEVER`.
- # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
- # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
- # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
- # down.
- #
- # If the workers are not torn down by the service, they will
- # continue to run and use Google Compute Engine VM resources in the
- # user's project until they are explicitly terminated by the user.
- # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
- # policy except for small, manually supervised test jobs.
- #
- # If unknown or unspecified, the service will attempt to choose a reasonable
- # default.
- "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
- # service will choose a number of threads (according to the number of cores
- # on the selected machine type for batch, or 1 by convention for streaming).
- "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
- # the form "regions/REGION/subnetworks/SUBNETWORK".
- "poolArgs": { # Extra arguments for this worker pool.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
- # execute the job. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -276,17 +249,7 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
- "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "root".
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
- "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
- "vmId": "A String", # The ID string of the VM.
- "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
- "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
- "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
- # access the Cloud Dataflow API.
- "A String",
- ],
"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
"reportingEnabled": True or False, # Whether to send work progress updates to the service.
"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
@@ -313,14 +276,15 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "wheel".
- "languageHint": "A String", # The suggested backend language.
- "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
- # console.
- "streamingWorkerMainClass": "A String", # The streaming worker main class name.
- "logDir": "A String", # The directory on the VM to store logs.
- "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
+ "vmId": "A String", # The ID string of the VM.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
#
# When workers access Google Cloud APIs, they logically do so via
@@ -330,6 +294,14 @@
# Locators".
#
# If not specified, the default value is "http://www.googleapis.com/"
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "languageHint": "A String", # The suggested backend language.
+ "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+ # console.
+ "streamingWorkerMainClass": "A String", # The streaming worker main class name.
+ "logDir": "A String", # The directory on the VM to store logs.
+ "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
"harnessCommand": "A String", # The command to launch the worker harness.
"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
# temporary storage.
@@ -339,33 +311,18 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
},
- "defaultPackageSet": "A String", # The default package set to install. This allows the service to
- # select a default set of packages which are useful to worker
- # harnesses written in a particular language.
- "packages": [ # Packages to be installed on workers.
- { # The packages that must be installed in order for a worker to run the
- # steps of the Cloud Dataflow job that will be assigned to its worker
- # pool.
- #
- # This is the mechanism by which the Cloud Dataflow SDK causes code to
- # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
- # might use this to install jars containing the user's code and all of the
- # various dependencies (libraries, data files, etc.) required in order
- # for that code to run.
- "name": "A String", # The name of the package.
- "location": "A String", # The resource to read the package from. The supported resource type is:
- #
- # Google Cloud Storage:
- #
- # storage.googleapis.com/{bucket}
- # bucket.storage.googleapis.com/
- },
- ],
- "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
- "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
- "algorithm": "A String", # The algorithm to use for autoscaling.
- },
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
+ # service will attempt to choose a reasonable default.
+ "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
+ # the service will use the network "default".
+ "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
+ # will attempt to choose a reasonable default.
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"dataDisks": [ # Data disks that are used by a VM in this workflow.
{ # Describes the data disk used by a workflow job.
"mountPoint": "A String", # Directory in a VM where disk is mounted.
@@ -391,10 +348,69 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
+ # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+ # `TEARDOWN_NEVER`.
+ # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+ # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+ # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+ # down.
+ #
+ # If the workers are not torn down by the service, they will
+ # continue to run and use Google Compute Engine VM resources in the
+ # user's project until they are explicitly terminated by the user.
+ # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+ # policy except for small, manually supervised test jobs.
+ #
+ # If unknown or unspecified, the service will attempt to choose a reasonable
+ # default.
+ "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
+ # Compute Engine API.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
+ # service will choose a number of threads (according to the number of cores
+ # on the selected machine type for batch, or 1 by convention for streaming).
+ "poolArgs": { # Extra arguments for this worker pool.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
+ # execute the job. If zero or unspecified, the service will
# attempt to choose a reasonable default.
"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
# harness, residing in Google Container Registry.
+ "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
+ # the form "regions/REGION/subnetworks/SUBNETWORK".
+ "packages": [ # Packages to be installed on workers.
+ { # The packages that must be installed in order for a worker to run the
+ # steps of the Cloud Dataflow job that will be assigned to its worker
+ # pool.
+ #
+ # This is the mechanism by which the Cloud Dataflow SDK causes code to
+ # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+ # might use this to install jars containing the user's code and all of the
+ # various dependencies (libraries, data files, etc.) required in order
+ # for that code to run.
+ "location": "A String", # The resource to read the package from. The supported resource type is:
+ #
+ # Google Cloud Storage:
+ #
+ # storage.googleapis.com/{bucket}
+ # bucket.storage.googleapis.com/
+ "name": "A String", # The name of the package.
+ },
+ ],
+ "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+ "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
+ "algorithm": "A String", # The algorithm to use for autoscaling.
+ },
+ "defaultPackageSet": "A String", # The default package set to install. This allows the service to
+ # select a default set of packages which are useful to worker
+ # harnesses written in a particular language.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ # attempt to choose a reasonable default.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
},
],
},
@@ -413,16 +429,13 @@
],
"displayData": [ # Transform-specific display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -433,8 +446,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"outputCollectionName": [ # User names for all collection outputs to this transform.
@@ -445,16 +461,13 @@
],
"displayData": [ # Pipeline level display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -465,8 +478,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"executionPipelineStage": [ # Description of each stage of execution of the pipeline.
@@ -550,17 +566,7 @@
# step with respect to all other steps in the Cloud Dataflow job.
},
],
- "currentState": "A String", # The current state of the job.
- #
- # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
- # specified.
- #
- # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
- # terminal state. After a job has reached a terminal state, no
- # further state updates may be made.
- #
- # This field may be mutated by the Cloud Dataflow service;
- # callers cannot mutate it.
+ "currentStateTime": "A String", # The timestamp associated with the current state.
"tempFiles": [ # A set of files the system should be aware of that are used
# for temporary storage. These temporary files will be
# removed on job completion.
@@ -575,11 +581,17 @@
# bucket.storage.googleapis.com/{object}
"A String",
],
+ "stageStates": [ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
+ { # A message describing the state of a particular execution stage.
+ "executionStageName": "A String", # The name of the execution stage.
+ "executionStageState": "A String", # Executions stage states allow the same set of values as JobState.
+ "currentStateTime": "A String", # The time at which the stage transitioned to this state.
+ },
+ ],
"type": "A String", # The type of Cloud Dataflow job.
- "id": "A String", # The unique ID of this job.
- #
- # This field is set by the Cloud Dataflow service when the Job is
- # created, and is immutable for the life of the job.
+ "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
+ # Cloud Dataflow service.
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
# of the job it replaced.
#
@@ -603,7 +615,7 @@
</div>
<div class="method">
- <code class="details" id="get">get(projectId, gcsPath=None, x__xgafv=None, view=None)</code>
+ <code class="details" id="get">get(projectId, gcsPath=None, location=None, x__xgafv=None, view=None)</code>
<pre>Get the template associated with a template.
Args:
@@ -611,6 +623,7 @@
gcsPath: string, Required. A Cloud Storage path to the template from which to
create the job.
Must be a valid Cloud Storage URL, beginning with `gs://`.
+ location: string, The location to which to direct the request.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
@@ -639,7 +652,7 @@
# error message is needed, put the localized message in the error details or
# localize it in the client. The optional error details may contain arbitrary
# information about the error. There is a predefined set of error detail types
- # in the package `google.rpc` which can be used for common error conditions.
+ # in the package `google.rpc` that can be used for common error conditions.
#
# # Language mapping
#
@@ -662,7 +675,7 @@
# errors.
#
# - Workflow errors. A typical workflow has multiple steps. Each step may
- # have a `Status` message for error reporting purpose.
+ # have a `Status` message for error reporting.
#
# - Batch operations. If a client uses batch request and batch response, the
# `Status` message should be used directly inside batch response, one for
@@ -687,10 +700,6 @@
},
"metadata": { # Metadata describing a template. # The template metadata describing the template name, available
# parameters, etc.
- "bypassTempDirValidation": True or False, # If true, will bypass the validation that the temp directory is
- # writable. This should only be used with templates for pipelines
- # that are guaranteed not to need to write to the temp directory,
- # which is subject to change based on the optimizer.
"name": "A String", # Required. The name of the template.
"parameters": [ # The parameters for the template.
{ # Metadata for a specific parameter.
@@ -709,7 +718,7 @@
</div>
<div class="method">
- <code class="details" id="launch">launch(projectId, body, dryRun=None, gcsPath=None, x__xgafv=None)</code>
+ <code class="details" id="launch">launch(projectId, body, gcsPath=None, location=None, validateOnly=None, x__xgafv=None)</code>
<pre>Launch a template.
Args:
@@ -719,15 +728,18 @@
{ # Parameters to provide to the template being launched.
"environment": { # The environment values to set at runtime. # The runtime environment for the job.
- "maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
- # available to your pipeline during execution, from 1 to 1000.
- "tempLocation": "A String", # The Cloud Storage path to use for temporary files.
- # Must be a valid Cloud Storage URL, beginning with `gs://`.
- "serviceAccountEmail": "A String", # The email address of the service account to run the job as.
- "zone": "A String", # The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)
+ "machineType": "A String", # The machine type to use for the job. Defaults to the value from the
+ # template if not specified.
+ "zone": "A String", # The Compute Engine [availability
+ # zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)
# for launching worker instances to run your pipeline.
"bypassTempDirValidation": True or False, # Whether to bypass the safety checks for the job's temporary directory.
# Use with caution.
+ "tempLocation": "A String", # The Cloud Storage path to use for temporary files.
+ # Must be a valid Cloud Storage URL, beginning with `gs://`.
+ "serviceAccountEmail": "A String", # The email address of the service account to run the job as.
+ "maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
+ # available to your pipeline during execution, from 1 to 1000.
},
"parameters": { # The runtime parameters to pass to the job.
"a_key": "A String",
@@ -735,12 +747,12 @@
"jobName": "A String", # Required. The job name to use for the created job.
}
- dryRun: boolean, Whether or not the job should actually be executed after
-validating parameters. Defaults to false. Validation errors do
-not cause the HTTP request to fail if true.
gcsPath: string, Required. A Cloud Storage path to the template from which to create
the job.
Must be valid Cloud Storage URL, beginning with 'gs://'.
+ location: string, The location to which to direct the request.
+ validateOnly: boolean, If true, the request is validated but not actually executed.
+Defaults to false.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
@@ -775,10 +787,21 @@
#
# The name must match the regular expression
# `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
- "currentStateTime": "A String", # The timestamp associated with the current state.
+ "location": "A String", # The location that contains this job.
"replacedByJobId": "A String", # If another job is an update of this job (and thus, this job is in
# `JOB_STATE_UPDATED`), this field contains the ID of that job.
"projectId": "A String", # The ID of the Cloud Platform project that the job belongs to.
+ "currentState": "A String", # The current state of the job.
+ #
+ # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
+ # specified.
+ #
+ # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
+ # terminal state. After a job has reached a terminal state, no
+ # further state updates may be made.
+ #
+ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
"labels": { # User-defined labels for this job.
#
# The labels map can contain no more than 64 entries. Entries of the labels
@@ -790,13 +813,14 @@
# size.
"a_key": "A String",
},
- "location": "A String", # The location that contains this job.
- "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
- # Cloud Dataflow service.
"transformNameMapping": { # The map of transform name prefixes of the job to be replaced to the
# corresponding name prefixes of the new job.
"a_key": "A String",
},
+ "id": "A String", # The unique ID of this job.
+ #
+ # This field is set by the Cloud Dataflow service when the Job is
+ # created, and is immutable for the life of the job.
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
@@ -850,49 +874,6 @@
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
"diskSourceImage": "A String", # Fully qualified source image for disks.
- "ipConfiguration": "A String", # Configuration for VM IPs.
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
- "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
- # service will attempt to choose a reasonable default.
- "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
- # the service will use the network "default".
- "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
- # will attempt to choose a reasonable default.
- "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
- "metadata": { # Metadata to set on the Google Compute Engine VMs.
- "a_key": "A String",
- },
- "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
- # Compute Engine API.
- "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
- # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
- # `TEARDOWN_NEVER`.
- # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
- # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
- # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
- # down.
- #
- # If the workers are not torn down by the service, they will
- # continue to run and use Google Compute Engine VM resources in the
- # user's project until they are explicitly terminated by the user.
- # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
- # policy except for small, manually supervised test jobs.
- #
- # If unknown or unspecified, the service will attempt to choose a reasonable
- # default.
- "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
- # service will choose a number of threads (according to the number of cores
- # on the selected machine type for batch, or 1 by convention for streaming).
- "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
- # the form "regions/REGION/subnetworks/SUBNETWORK".
- "poolArgs": { # Extra arguments for this worker pool.
- "a_key": "", # Properties of the object. Contains field @type with type URL.
- },
- "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
- # execute the job. If zero or unspecified, the service will
- # attempt to choose a reasonable default.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -905,17 +886,7 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
- "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "root".
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
- "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
- "vmId": "A String", # The ID string of the VM.
- "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
- "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
- "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
- # access the Cloud Dataflow API.
- "A String",
- ],
"parallelWorkerSettings": { # Provides data to pass through to the worker harness. # The settings to pass to the parallel worker harness.
"reportingEnabled": True or False, # Whether to send work progress updates to the service.
"shuffleServicePath": "A String", # The Shuffle service path relative to the root URL, for example,
@@ -942,14 +913,15 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
- # taskrunner; e.g. "wheel".
- "languageHint": "A String", # The suggested backend language.
- "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
- # console.
- "streamingWorkerMainClass": "A String", # The streaming worker main class name.
- "logDir": "A String", # The directory on the VM to store logs.
- "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
+ "vmId": "A String", # The ID string of the VM.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
"baseUrl": "A String", # The base URL for the taskrunner to use when accessing Google Cloud APIs.
#
# When workers access Google Cloud APIs, they logically do so via
@@ -959,6 +931,14 @@
# Locators".
#
# If not specified, the default value is "http://www.googleapis.com/"
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "languageHint": "A String", # The suggested backend language.
+ "logToSerialconsole": True or False, # Whether to send taskrunner log info to Google Compute Engine VM serial
+ # console.
+ "streamingWorkerMainClass": "A String", # The streaming worker main class name.
+ "logDir": "A String", # The directory on the VM to store logs.
+ "dataflowApiVersion": "A String", # The API version of endpoint, e.g. "v1b3"
"harnessCommand": "A String", # The command to launch the worker harness.
"tempStoragePrefix": "A String", # The prefix of the resources the taskrunner should use for
# temporary storage.
@@ -968,33 +948,18 @@
# Google Cloud Storage:
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
},
- "defaultPackageSet": "A String", # The default package set to install. This allows the service to
- # select a default set of packages which are useful to worker
- # harnesses written in a particular language.
- "packages": [ # Packages to be installed on workers.
- { # The packages that must be installed in order for a worker to run the
- # steps of the Cloud Dataflow job that will be assigned to its worker
- # pool.
- #
- # This is the mechanism by which the Cloud Dataflow SDK causes code to
- # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
- # might use this to install jars containing the user's code and all of the
- # various dependencies (libraries, data files, etc.) required in order
- # for that code to run.
- "name": "A String", # The name of the package.
- "location": "A String", # The resource to read the package from. The supported resource type is:
- #
- # Google Cloud Storage:
- #
- # storage.googleapis.com/{bucket}
- # bucket.storage.googleapis.com/
- },
- ],
- "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
- "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
- "algorithm": "A String", # The algorithm to use for autoscaling.
- },
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty or unspecified, the
+ # service will attempt to choose a reasonable default.
+ "network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
+ # the service will use the network "default".
+ "zone": "A String", # Zone to run the worker pools in. If empty or unspecified, the service
+ # will attempt to choose a reasonable default.
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"dataDisks": [ # Data disks that are used by a VM in this workflow.
{ # Describes the data disk used by a workflow job.
"mountPoint": "A String", # Directory in a VM where disk is mounted.
@@ -1020,10 +985,69 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ "teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
+ # Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
+ # `TEARDOWN_NEVER`.
+ # `TEARDOWN_ALWAYS` means workers are always torn down regardless of whether
+ # the job succeeds. `TEARDOWN_ON_SUCCESS` means workers are torn down
+ # if the job succeeds. `TEARDOWN_NEVER` means the workers are never torn
+ # down.
+ #
+ # If the workers are not torn down by the service, they will
+ # continue to run and use Google Compute Engine VM resources in the
+ # user's project until they are explicitly terminated by the user.
+ # Because of this, Google recommends using the `TEARDOWN_ALWAYS`
+ # policy except for small, manually supervised test jobs.
+ #
+ # If unknown or unspecified, the service will attempt to choose a reasonable
+ # default.
+ "onHostMaintenance": "A String", # The action to take on host maintenance, as defined by the Google
+ # Compute Engine API.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "numThreadsPerWorker": 42, # The number of threads per worker harness. If empty or unspecified, the
+ # service will choose a number of threads (according to the number of cores
+ # on the selected machine type for batch, or 1 by convention for streaming).
+ "poolArgs": { # Extra arguments for this worker pool.
+ "a_key": "", # Properties of the object. Contains field @type with type URL.
+ },
+ "numWorkers": 42, # Number of Google Compute Engine workers in this pool needed to
+ # execute the job. If zero or unspecified, the service will
# attempt to choose a reasonable default.
"workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
# harness, residing in Google Container Registry.
+ "subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
+ # the form "regions/REGION/subnetworks/SUBNETWORK".
+ "packages": [ # Packages to be installed on workers.
+ { # The packages that must be installed in order for a worker to run the
+ # steps of the Cloud Dataflow job that will be assigned to its worker
+ # pool.
+ #
+ # This is the mechanism by which the Cloud Dataflow SDK causes code to
+ # be loaded onto the workers. For example, the Cloud Dataflow Java SDK
+ # might use this to install jars containing the user's code and all of the
+ # various dependencies (libraries, data files, etc.) required in order
+ # for that code to run.
+ "location": "A String", # The resource to read the package from. The supported resource type is:
+ #
+ # Google Cloud Storage:
+ #
+ # storage.googleapis.com/{bucket}
+ # bucket.storage.googleapis.com/
+ "name": "A String", # The name of the package.
+ },
+ ],
+ "autoscalingSettings": { # Settings for WorkerPool autoscaling. # Settings for autoscaling of this WorkerPool.
+ "maxNumWorkers": 42, # The maximum number of workers to cap scaling at.
+ "algorithm": "A String", # The algorithm to use for autoscaling.
+ },
+ "defaultPackageSet": "A String", # The default package set to install. This allows the service to
+ # select a default set of packages which are useful to worker
+ # harnesses written in a particular language.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
+ # attempt to choose a reasonable default.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
},
],
},
@@ -1042,16 +1066,13 @@
],
"displayData": [ # Transform-specific display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -1062,8 +1083,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"outputCollectionName": [ # User names for all collection outputs to this transform.
@@ -1074,16 +1098,13 @@
],
"displayData": [ # Pipeline level display data.
{ # Data provided with a pipeline or transform to provide descriptive info.
- "key": "A String", # The key identifying the display data.
- # This is intended to be used as a label for the display data
- # when viewed in a dax monitoring system.
"shortStrValue": "A String", # A possible additional shorter value to display.
# For example a java_class_name_value of com.mypackage.MyDoFn
# will be stored with MyDoFn as the short_str_value and
# com.mypackage.MyDoFn as the java_class_name value.
# short_str_value can be displayed and java_class_name_value
# will be displayed as a tooltip.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"url": "A String", # An optional full URL.
"floatValue": 3.14, # Contains value if the data is of float type.
"namespace": "A String", # The namespace for the key. This is usually a class name or programming
@@ -1094,8 +1115,11 @@
"label": "A String", # An optional label to display in a dax UI for the element.
"boolValue": True or False, # Contains value if the data is of a boolean type.
"strValue": "A String", # Contains value if the data is of string type.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "key": "A String", # The key identifying the display data.
+ # This is intended to be used as a label for the display data
+ # when viewed in a dax monitoring system.
"int64Value": "A String", # Contains value if the data is of int64 type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
"executionPipelineStage": [ # Description of each stage of execution of the pipeline.
@@ -1179,17 +1203,7 @@
# step with respect to all other steps in the Cloud Dataflow job.
},
],
- "currentState": "A String", # The current state of the job.
- #
- # Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise
- # specified.
- #
- # A job in the `JOB_STATE_RUNNING` state may asynchronously enter a
- # terminal state. After a job has reached a terminal state, no
- # further state updates may be made.
- #
- # This field may be mutated by the Cloud Dataflow service;
- # callers cannot mutate it.
+ "currentStateTime": "A String", # The timestamp associated with the current state.
"tempFiles": [ # A set of files the system should be aware of that are used
# for temporary storage. These temporary files will be
# removed on job completion.
@@ -1204,11 +1218,17 @@
# bucket.storage.googleapis.com/{object}
"A String",
],
+ "stageStates": [ # This field may be mutated by the Cloud Dataflow service;
+ # callers cannot mutate it.
+ { # A message describing the state of a particular execution stage.
+ "executionStageName": "A String", # The name of the execution stage.
+ "executionStageState": "A String", # Executions stage states allow the same set of values as JobState.
+ "currentStateTime": "A String", # The time at which the stage transitioned to this state.
+ },
+ ],
"type": "A String", # The type of Cloud Dataflow job.
- "id": "A String", # The unique ID of this job.
- #
- # This field is set by the Cloud Dataflow service when the Job is
- # created, and is immutable for the life of the job.
+ "createTime": "A String", # The timestamp when the job was initially created. Immutable and set by the
+ # Cloud Dataflow service.
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
# of the job it replaced.
#