chore: regens API reference docs (#889)
diff --git a/docs/dyn/dataflow_v1b3.projects.templates.html b/docs/dyn/dataflow_v1b3.projects.templates.html
index a08f01e..b26398f 100644
--- a/docs/dyn/dataflow_v1b3.projects.templates.html
+++ b/docs/dyn/dataflow_v1b3.projects.templates.html
@@ -75,26 +75,31 @@
<h1><a href="dataflow_v1b3.html">Dataflow API</a> . <a href="dataflow_v1b3.projects.html">projects</a> . <a href="dataflow_v1b3.projects.templates.html">templates</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
- <code><a href="#create">create(projectId, body, x__xgafv=None)</a></code></p>
+ <code><a href="#create">create(projectId, body=None, 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, 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, dynamicTemplate_gcsPath=None, x__xgafv=None, dynamicTemplate_stagingLocation=None, location=None, gcsPath=None, validateOnly=None)</a></code></p>
+ <code><a href="#launch">launch(projectId, body=None, dynamicTemplate_gcsPath=None, x__xgafv=None, dynamicTemplate_stagingLocation=None, location=None, gcsPath=None, validateOnly=None)</a></code></p>
<p class="firstline">Launch a template.</p>
<h3>Method Details</h3>
<div class="method">
- <code class="details" id="create">create(projectId, body, x__xgafv=None)</code>
+ <code class="details" id="create">create(projectId, body=None, x__xgafv=None)</code>
<pre>Creates a Cloud Dataflow job from a template.
Args:
projectId: string, Required. The ID of the Cloud Platform project that the job belongs to. (required)
- body: object, The request body. (required)
+ body: object, The request body.
The object takes the form of:
{ # 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.
+ "workerRegion": "A String", # The Compute Engine region
+ # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+ # which worker processing should occur, e.g. "us-west1". Mutually exclusive
+ # with worker_zone. If neither worker_region nor worker_zone is specified,
+ # default to the control plane's region.
"machineType": "A String", # The machine type to use for the job. Defaults to the value from the
# template if not specified.
"network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
@@ -102,25 +107,36 @@
"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.
+ # In the future, worker_zone will take precedence.
"additionalUserLabels": { # Additional user labels to be specified for the job.
# Keys and values should follow the restrictions specified in the [labeling
# restrictions](https://cloud.google.com/compute/docs/labeling-resources#restrictions)
# page.
"a_key": "A String",
},
+ "numWorkers": 42, # The initial number of Google Compute Engine instnaces for the job.
"additionalExperiments": [ # Additional experiment flags for the job.
"A String",
],
+ "ipConfiguration": "A String", # Configuration for VM IPs.
"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.
- "numWorkers": 42, # The initial number of Google Compute Engine instnaces for the job.
+ "kmsKeyName": "A String", # Optional. Name for the Cloud KMS key for the job.
+ # Key format is:
+ # projects/<project>/locations/<location>/keyRings/<keyring>/cryptoKeys/<key>
"maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
# available to your pipeline during execution, from 1 to 1000.
"subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
# the form "regions/REGION/subnetworks/SUBNETWORK".
+ "workerZone": "A String", # The Compute Engine zone
+ # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+ # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive
+ # with worker_region. If neither worker_region nor worker_zone is specified,
+ # a zone in the control plane's region is chosen based on available capacity.
+ # If both `worker_zone` and `zone` are set, `worker_zone` takes precedence.
},
"gcsPath": "A String", # Required. A Cloud Storage path to the template from which to
# create the job.
@@ -150,7 +166,7 @@
#
# * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62}
# * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63}
- # * Both keys and values are additionally constrained to be <= 128 bytes in
+ # * Both keys and values are additionally constrained to be <= 128 bytes in
# size.
"a_key": "A String",
},
@@ -197,9 +213,9 @@
"bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job.
{ # Metadata for a BigQuery connector used by the job.
"projectId": "A String", # Project accessed in the connection.
- "dataset": "A String", # Dataset accessed in the connection.
- "table": "A String", # Table accessed in the connection.
"query": "A String", # Query used to access data in the connection.
+ "table": "A String", # Table accessed in the connection.
+ "dataset": "A String", # Dataset accessed in the connection.
},
],
},
@@ -218,13 +234,16 @@
],
"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.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp 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
@@ -235,11 +254,8 @@
"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.
- "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.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"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.
@@ -294,13 +310,16 @@
],
"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.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp 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
@@ -311,11 +330,8 @@
"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.
- "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.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"int64Value": "A String", # Contains value if the data is of int64 type.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
},
@@ -339,6 +355,11 @@
"a_key": "A String",
},
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
+ "workerRegion": "A String", # The Compute Engine region
+ # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+ # which worker processing should occur, e.g. "us-west1". Mutually exclusive
+ # with worker_zone. If neither worker_region nor worker_zone is specified,
+ # default to the control plane's region.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
"a_key": "", # Properties of the object.
@@ -372,10 +393,11 @@
"userAgent": { # A description of the process that generated the request.
"a_key": "", # Properties of the object.
},
- "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or
- # unspecified, the service will attempt to choose a reasonable
- # default. This should be in the form of the API service name,
- # e.g. "compute.googleapis.com".
+ "workerZone": "A String", # The Compute Engine zone
+ # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+ # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive
+ # with worker_region. If neither worker_region nor worker_zone is specified,
+ # a zone in the control plane's region is chosen based on available capacity.
"workerPools": [ # The worker pools. At least one "harness" worker pool must be
# specified in order for the job to have workers.
{ # Describes one particular pool of Cloud Dataflow workers to be
@@ -383,7 +405,27 @@
# computations required by a job. Note that a workflow job may use
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
+ "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
+ # harness, residing in Google Container Registry.
+ #
+ # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "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.
+ },
"diskSourceImage": "A String", # Fully qualified source image for disks.
+ "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.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty 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.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -397,6 +439,23 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "vmId": "A String", # The ID string of the VM.
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "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.
"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,
@@ -423,31 +482,6 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "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
- # relative URLs. If this field is specified, it supplies the base
- # URL to use for resolving these relative URLs. The normative
- # algorithm used is defined by RFC 1808, "Relative Uniform Resource
- # 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
@@ -458,10 +492,22 @@
# 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.
+ "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
+ # relative URLs. If this field is specified, it supplies the base
+ # URL to use for resolving these relative URLs. The normative
+ # algorithm used is defined by RFC 1808, "Relative Uniform Resource
+ # Locators".
+ #
+ # If not specified, the default value is "http://www.googleapis.com/"
},
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
+ "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.
+ },
"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
@@ -481,13 +527,12 @@
"name": "A String", # The name of the package.
},
],
- "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
+ "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.
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
# attempt to choose a reasonable default.
"teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
# Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
@@ -505,20 +550,11 @@
#
# 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.
- },
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"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".
"dataDisks": [ # Data disks that are used by a VM in this workflow.
@@ -546,20 +582,25 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "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",
- },
+ "sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will
+ # only be set in the Fn API path. For non-cross-language pipelines this
+ # should have only one entry. Cross-language pipelines will have two or more
+ # entries.
+ { # Defines a SDK harness container for executing Dataflow pipelines.
+ "containerImage": "A String", # A docker container image that resides in Google Container Registry.
+ "useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK
+ # container instance with this image. If false (or unset) recommends using
+ # more than one core per SDK container instance with this image for
+ # efficiency. Note that Dataflow service may choose to override this property
+ # if needed.
+ },
+ ],
},
],
+ "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or
+ # unspecified, the service will attempt to choose a reasonable
+ # default. This should be in the form of the API service name,
+ # e.g. "compute.googleapis.com".
"tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
# storage. The system will append the suffix "/temp-{JOBNAME} to
# this resource prefix, where {JOBNAME} is the value of the
@@ -656,13 +697,13 @@
# Note that the Cloud Dataflow service may be used to run many different
# types of jobs, not just Map-Reduce.
"kind": "A String", # The kind of step in the Cloud Dataflow job.
+ "name": "A String", # The name that identifies the step. This must be unique for each
+ # step with respect to all other steps in the Cloud Dataflow job.
"properties": { # Named properties associated with the step. Each kind of
# predefined step has its own required set of properties.
# Must be provided on Create. Only retrieved with JOB_VIEW_ALL.
"a_key": "", # Properties of the object.
},
- "name": "A String", # The name that identifies the step. This must be unique for each
- # step with respect to all other steps in the Cloud Dataflow job.
},
],
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID
@@ -723,56 +764,11 @@
"status": { # The `Status` type defines a logical error model that is suitable for # The status of the get template request. Any problems with the
# request will be indicated in the error_details.
# different programming environments, including REST APIs and RPC APIs. It is
- # used by [gRPC](https://github.com/grpc). The error model is designed to be:
+ # used by [gRPC](https://github.com/grpc). Each `Status` message contains
+ # three pieces of data: error code, error message, and error details.
#
- # - Simple to use and understand for most users
- # - Flexible enough to meet unexpected needs
- #
- # # Overview
- #
- # The `Status` message contains three pieces of data: error code, error
- # message, and error details. The error code should be an enum value of
- # google.rpc.Code, but it may accept additional error codes if needed. The
- # error message should be a developer-facing English message that helps
- # developers *understand* and *resolve* the error. If a localized user-facing
- # 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` that can be used for common error conditions.
- #
- # # Language mapping
- #
- # The `Status` message is the logical representation of the error model, but it
- # is not necessarily the actual wire format. When the `Status` message is
- # exposed in different client libraries and different wire protocols, it can be
- # mapped differently. For example, it will likely be mapped to some exceptions
- # in Java, but more likely mapped to some error codes in C.
- #
- # # Other uses
- #
- # The error model and the `Status` message can be used in a variety of
- # environments, either with or without APIs, to provide a
- # consistent developer experience across different environments.
- #
- # Example uses of this error model include:
- #
- # - Partial errors. If a service needs to return partial errors to the client,
- # it may embed the `Status` in the normal response to indicate the partial
- # errors.
- #
- # - Workflow errors. A typical workflow has multiple steps. Each step may
- # 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
- # each error sub-response.
- #
- # - Asynchronous operations. If an API call embeds asynchronous operation
- # results in its response, the status of those operations should be
- # represented directly using the `Status` message.
- #
- # - Logging. If some API errors are stored in logs, the message `Status` could
- # be used directly after any stripping needed for security/privacy reasons.
+ # You can find out more about this error model and how to work with it in the
+ # [API Design Guide](https://cloud.google.com/apis/design/errors).
"message": "A String", # A developer-facing error message, which should be in English. Any
# user-facing error message should be localized and sent in the
# google.rpc.Status.details field, or localized by the client.
@@ -784,18 +780,40 @@
},
],
},
+ "templateType": "A String", # Template Type.
+ "runtimeMetadata": { # RuntimeMetadata describing a runtime environment. # Describes the runtime metadata with SDKInfo and available parameters.
+ "parameters": [ # The parameters for the template.
+ { # Metadata for a specific parameter.
+ "name": "A String", # Required. The name of the parameter.
+ "isOptional": True or False, # Optional. Whether the parameter is optional. Defaults to false.
+ "regexes": [ # Optional. Regexes that the parameter must match.
+ "A String",
+ ],
+ "label": "A String", # Required. The label to display for the parameter.
+ "helpText": "A String", # Required. The help text to display for the parameter.
+ "paramType": "A String", # Optional. The type of the parameter.
+ # Used for selecting input picker.
+ },
+ ],
+ "sdkInfo": { # SDK Information. # SDK Info for the template.
+ "version": "A String", # Optional. The SDK version.
+ "language": "A String", # Required. The SDK Language.
+ },
+ },
"metadata": { # Metadata describing a template. # The template metadata describing the template name, available
# parameters, etc.
"name": "A String", # Required. The name of the template.
"parameters": [ # The parameters for the template.
{ # Metadata for a specific parameter.
+ "name": "A String", # Required. The name of the parameter.
+ "isOptional": True or False, # Optional. Whether the parameter is optional. Defaults to false.
"regexes": [ # Optional. Regexes that the parameter must match.
"A String",
],
- "helpText": "A String", # Required. The help text to display for the parameter.
- "name": "A String", # Required. The name of the parameter.
- "isOptional": True or False, # Optional. Whether the parameter is optional. Defaults to false.
"label": "A String", # Required. The label to display for the parameter.
+ "helpText": "A String", # Required. The help text to display for the parameter.
+ "paramType": "A String", # Optional. The type of the parameter.
+ # Used for selecting input picker.
},
],
"description": "A String", # Optional. A description of the template.
@@ -804,16 +822,21 @@
</div>
<div class="method">
- <code class="details" id="launch">launch(projectId, body, dynamicTemplate_gcsPath=None, x__xgafv=None, dynamicTemplate_stagingLocation=None, location=None, gcsPath=None, validateOnly=None)</code>
+ <code class="details" id="launch">launch(projectId, body=None, dynamicTemplate_gcsPath=None, x__xgafv=None, dynamicTemplate_stagingLocation=None, location=None, gcsPath=None, validateOnly=None)</code>
<pre>Launch a template.
Args:
projectId: string, Required. The ID of the Cloud Platform project that the job belongs to. (required)
- body: object, The request body. (required)
+ body: object, The request body.
The object takes the form of:
{ # Parameters to provide to the template being launched.
"environment": { # The environment values to set at runtime. # The runtime environment for the job.
+ "workerRegion": "A String", # The Compute Engine region
+ # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+ # which worker processing should occur, e.g. "us-west1". Mutually exclusive
+ # with worker_zone. If neither worker_region nor worker_zone is specified,
+ # default to the control plane's region.
"machineType": "A String", # The machine type to use for the job. Defaults to the value from the
# template if not specified.
"network": "A String", # Network to which VMs will be assigned. If empty or unspecified,
@@ -821,26 +844,43 @@
"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.
+ # In the future, worker_zone will take precedence.
"additionalUserLabels": { # Additional user labels to be specified for the job.
# Keys and values should follow the restrictions specified in the [labeling
# restrictions](https://cloud.google.com/compute/docs/labeling-resources#restrictions)
# page.
"a_key": "A String",
},
+ "numWorkers": 42, # The initial number of Google Compute Engine instnaces for the job.
"additionalExperiments": [ # Additional experiment flags for the job.
"A String",
],
+ "ipConfiguration": "A String", # Configuration for VM IPs.
"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.
- "numWorkers": 42, # The initial number of Google Compute Engine instnaces for the job.
+ "kmsKeyName": "A String", # Optional. Name for the Cloud KMS key for the job.
+ # Key format is:
+ # projects/<project>/locations/<location>/keyRings/<keyring>/cryptoKeys/<key>
"maxWorkers": 42, # The maximum number of Google Compute Engine instances to be made
# available to your pipeline during execution, from 1 to 1000.
"subnetwork": "A String", # Subnetwork to which VMs will be assigned, if desired. Expected to be of
# the form "regions/REGION/subnetworks/SUBNETWORK".
+ "workerZone": "A String", # The Compute Engine zone
+ # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+ # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive
+ # with worker_region. If neither worker_region nor worker_zone is specified,
+ # a zone in the control plane's region is chosen based on available capacity.
+ # If both `worker_zone` and `zone` are set, `worker_zone` takes precedence.
},
+ "transformNameMapping": { # Only applicable when updating a pipeline. Map of transform name prefixes of
+ # the job to be replaced to the corresponding name prefixes of the new job.
+ "a_key": "A String",
+ },
+ "update": True or False, # If set, replace the existing pipeline with the name specified by jobName
+ # with this pipeline, preserving state.
"parameters": { # The runtime parameters to pass to the job.
"a_key": "A String",
},
@@ -877,7 +917,7 @@
#
# * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62}
# * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63}
- # * Both keys and values are additionally constrained to be <= 128 bytes in
+ # * Both keys and values are additionally constrained to be <= 128 bytes in
# size.
"a_key": "A String",
},
@@ -924,9 +964,9 @@
"bigqueryDetails": [ # Identification of a BigQuery source used in the Dataflow job.
{ # Metadata for a BigQuery connector used by the job.
"projectId": "A String", # Project accessed in the connection.
- "dataset": "A String", # Dataset accessed in the connection.
- "table": "A String", # Table accessed in the connection.
"query": "A String", # Query used to access data in the connection.
+ "table": "A String", # Table accessed in the connection.
+ "dataset": "A String", # Dataset accessed in the connection.
},
],
},
@@ -945,13 +985,16 @@
],
"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.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp 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
@@ -962,11 +1005,8 @@
"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.
- "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.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"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.
@@ -1021,13 +1061,16 @@
],
"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.
- "durationValue": "A String", # Contains value if the data is of duration type.
+ "timestampValue": "A String", # Contains value if the data is of timestamp 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
@@ -1038,11 +1081,8 @@
"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.
- "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.
+ "durationValue": "A String", # Contains value if the data is of duration type.
"int64Value": "A String", # Contains value if the data is of int64 type.
- "timestampValue": "A String", # Contains value if the data is of timestamp type.
},
],
},
@@ -1066,6 +1106,11 @@
"a_key": "A String",
},
"environment": { # Describes the environment in which a Dataflow Job runs. # The environment for the job.
+ "workerRegion": "A String", # The Compute Engine region
+ # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+ # which worker processing should occur, e.g. "us-west1". Mutually exclusive
+ # with worker_zone. If neither worker_region nor worker_zone is specified,
+ # default to the control plane's region.
"version": { # A structure describing which components and their versions of the service
# are required in order to run the job.
"a_key": "", # Properties of the object.
@@ -1099,10 +1144,11 @@
"userAgent": { # A description of the process that generated the request.
"a_key": "", # Properties of the object.
},
- "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or
- # unspecified, the service will attempt to choose a reasonable
- # default. This should be in the form of the API service name,
- # e.g. "compute.googleapis.com".
+ "workerZone": "A String", # The Compute Engine zone
+ # (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in
+ # which worker processing should occur, e.g. "us-west1-a". Mutually exclusive
+ # with worker_region. If neither worker_region nor worker_zone is specified,
+ # a zone in the control plane's region is chosen based on available capacity.
"workerPools": [ # The worker pools. At least one "harness" worker pool must be
# specified in order for the job to have workers.
{ # Describes one particular pool of Cloud Dataflow workers to be
@@ -1110,7 +1156,27 @@
# computations required by a job. Note that a workflow job may use
# multiple pools, in order to match the various computational
# requirements of the various stages of the job.
+ "workerHarnessContainerImage": "A String", # Required. Docker container image that executes the Cloud Dataflow worker
+ # harness, residing in Google Container Registry.
+ #
+ # Deprecated for the Fn API path. Use sdk_harness_container_images instead.
+ "ipConfiguration": "A String", # Configuration for VM IPs.
+ "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.
+ },
"diskSourceImage": "A String", # Fully qualified source image for disks.
+ "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.
+ "metadata": { # Metadata to set on the Google Compute Engine VMs.
+ "a_key": "A String",
+ },
+ "machineType": "A String", # Machine type (e.g. "n1-standard-1"). If empty 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.
"taskrunnerSettings": { # Taskrunner configuration settings. # Settings passed through to Google Compute Engine workers when
# using the standard Dataflow task runner. Users should ignore
# this field.
@@ -1124,6 +1190,23 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
"commandlinesFileName": "A String", # The file to store preprocessing commands in.
+ "alsologtostderr": True or False, # Whether to also send taskrunner log info to stderr.
+ "continueOnException": True or False, # Whether to continue taskrunner if an exception is hit.
+ "baseTaskDir": "A String", # The location on the worker for task-specific subdirectories.
+ "vmId": "A String", # The ID string of the VM.
+ "taskGroup": "A String", # The UNIX group ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "wheel".
+ "taskUser": "A String", # The UNIX user ID on the worker VM to use for tasks launched by
+ # taskrunner; e.g. "root".
+ "oauthScopes": [ # The OAuth2 scopes to be requested by the taskrunner in order to
+ # access the Cloud Dataflow API.
+ "A String",
+ ],
+ "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.
"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,
@@ -1150,31 +1233,6 @@
# storage.googleapis.com/{bucket}/{object}
# bucket.storage.googleapis.com/{object}
},
- "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
- # relative URLs. If this field is specified, it supplies the base
- # URL to use for resolving these relative URLs. The normative
- # algorithm used is defined by RFC 1808, "Relative Uniform Resource
- # 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
@@ -1185,10 +1243,22 @@
# 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.
+ "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
+ # relative URLs. If this field is specified, it supplies the base
+ # URL to use for resolving these relative URLs. The normative
+ # algorithm used is defined by RFC 1808, "Relative Uniform Resource
+ # Locators".
+ #
+ # If not specified, the default value is "http://www.googleapis.com/"
},
- "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
- # are supported.
+ "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.
+ },
"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
@@ -1208,13 +1278,12 @@
"name": "A String", # The name of the package.
},
],
- "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
+ "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.
+ "kind": "A String", # The kind of the worker pool; currently only `harness` and `shuffle`
+ # are supported.
+ "diskType": "A String", # Type of root disk for VMs. If empty or unspecified, the service will
# attempt to choose a reasonable default.
"teardownPolicy": "A String", # Sets the policy for determining when to turndown worker pool.
# Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
@@ -1232,20 +1301,11 @@
#
# 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.
- },
+ "diskSizeGb": 42, # Size of root disk for VMs, in GB. If zero or unspecified, the service will
+ # attempt to choose a reasonable default.
"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".
"dataDisks": [ # Data disks that are used by a VM in this workflow.
@@ -1273,20 +1333,25 @@
# compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard
},
],
- "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",
- },
+ "sdkHarnessContainerImages": [ # Set of SDK harness containers needed to execute this pipeline. This will
+ # only be set in the Fn API path. For non-cross-language pipelines this
+ # should have only one entry. Cross-language pipelines will have two or more
+ # entries.
+ { # Defines a SDK harness container for executing Dataflow pipelines.
+ "containerImage": "A String", # A docker container image that resides in Google Container Registry.
+ "useSingleCorePerContainer": True or False, # If true, recommends the Dataflow service to use only one core per SDK
+ # container instance with this image. If false (or unset) recommends using
+ # more than one core per SDK container instance with this image for
+ # efficiency. Note that Dataflow service may choose to override this property
+ # if needed.
+ },
+ ],
},
],
+ "clusterManagerApiService": "A String", # The type of cluster manager API to use. If unknown or
+ # unspecified, the service will attempt to choose a reasonable
+ # default. This should be in the form of the API service name,
+ # e.g. "compute.googleapis.com".
"tempStoragePrefix": "A String", # The prefix of the resources the system should use for temporary
# storage. The system will append the suffix "/temp-{JOBNAME} to
# this resource prefix, where {JOBNAME} is the value of the
@@ -1383,13 +1448,13 @@
# Note that the Cloud Dataflow service may be used to run many different
# types of jobs, not just Map-Reduce.
"kind": "A String", # The kind of step in the Cloud Dataflow job.
+ "name": "A String", # The name that identifies the step. This must be unique for each
+ # step with respect to all other steps in the Cloud Dataflow job.
"properties": { # Named properties associated with the step. Each kind of
# predefined step has its own required set of properties.
# Must be provided on Create. Only retrieved with JOB_VIEW_ALL.
"a_key": "", # Properties of the object.
},
- "name": "A String", # The name that identifies the step. This must be unique for each
- # step with respect to all other steps in the Cloud Dataflow job.
},
],
"replaceJobId": "A String", # If this job is an update of an existing job, this field is the job ID