{ "baseUrl": "https://dataflow.googleapis.com/", "mtlsRootUrl": "https://dataflow.mtls.googleapis.com/", "basePath": "", "name": "dataflow", "servicePath": "", "documentationLink": "https://cloud.google.com/dataflow", "canonicalName": "Dataflow", "endpoints": [ { "location": "africa-south1", "endpointUrl": "https://dataflow.africa-south1.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.asia-east1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "asia-east1" }, { "endpointUrl": "https://dataflow.asia-east2.rep.googleapis.com/", "description": "Regional Endpoint", "location": "asia-east2" }, { "endpointUrl": "https://dataflow.asia-northeast1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "asia-northeast1" }, { "location": "asia-northeast2", "endpointUrl": "https://dataflow.asia-northeast2.rep.googleapis.com/", "description": "Regional Endpoint" }, { "location": "asia-northeast3", "endpointUrl": "https://dataflow.asia-northeast3.rep.googleapis.com/", "description": "Regional Endpoint" }, { "location": "asia-south1", "endpointUrl": "https://dataflow.asia-south1.rep.googleapis.com/", "description": "Regional Endpoint" }, { "location": "asia-south2", "endpointUrl": "https://dataflow.asia-south2.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.asia-southeast1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "asia-southeast1" }, { "location": "asia-southeast2", "endpointUrl": "https://dataflow.asia-southeast2.rep.googleapis.com/", "description": "Regional Endpoint" }, { "location": "asia-southeast3", "endpointUrl": "https://dataflow.asia-southeast3.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.australia-southeast1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "australia-southeast1" }, { "location": "australia-southeast2", "endpointUrl": "https://dataflow.australia-southeast2.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.europe-central2.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-central2" }, { "endpointUrl": "https://dataflow.europe-north1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-north1" }, { "location": "europe-north2", "endpointUrl": "https://dataflow.europe-north2.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.europe-southwest1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-southwest1" }, { "endpointUrl": "https://dataflow.europe-west1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-west1" }, { "endpointUrl": "https://dataflow.europe-west10.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-west10" }, { "location": "europe-west12", "endpointUrl": "https://dataflow.europe-west12.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.europe-west2.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-west2" }, { "endpointUrl": "https://dataflow.europe-west3.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-west3" }, { "location": "europe-west4", "endpointUrl": "https://dataflow.europe-west4.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.europe-west6.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-west6" }, { "endpointUrl": "https://dataflow.europe-west8.rep.googleapis.com/", "description": "Regional Endpoint", "location": "europe-west8" }, { "location": "europe-west9", "endpointUrl": "https://dataflow.europe-west9.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.me-central1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "me-central1" }, { "location": "me-central2", "endpointUrl": "https://dataflow.me-central2.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.me-west1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "me-west1" }, { "location": "northamerica-northeast1", "endpointUrl": "https://dataflow.northamerica-northeast1.rep.googleapis.com/", "description": "Regional Endpoint" }, { "location": "northamerica-northeast2", "endpointUrl": "https://dataflow.northamerica-northeast2.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.northamerica-south1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "northamerica-south1" }, { "endpointUrl": "https://dataflow.southamerica-east1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "southamerica-east1" }, { "location": "southamerica-west1", "endpointUrl": "https://dataflow.southamerica-west1.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.us-central1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "us-central1" }, { "location": "us-central2", "endpointUrl": "https://dataflow.us-central2.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.us-east1.rep.googleapis.com/", "description": "Regional Endpoint", "location": "us-east1" }, { "endpointUrl": "https://dataflow.us-east4.rep.googleapis.com/", "description": "Regional Endpoint", "location": "us-east4" }, { "location": "us-east5", "endpointUrl": "https://dataflow.us-east5.rep.googleapis.com/", "description": "Regional Endpoint" }, { "location": "us-east7", "endpointUrl": "https://dataflow.us-east7.rep.googleapis.com/", "description": "Regional Endpoint" }, { "location": "us-south1", "endpointUrl": "https://dataflow.us-south1.rep.googleapis.com/", "description": "Regional Endpoint" }, { "location": "us-west1", "endpointUrl": "https://dataflow.us-west1.rep.googleapis.com/", "description": "Regional Endpoint" }, { "endpointUrl": "https://dataflow.us-west2.rep.googleapis.com/", "description": "Regional Endpoint", "location": "us-west2" }, { "endpointUrl": "https://dataflow.us-west3.rep.googleapis.com/", "description": "Regional Endpoint", "location": "us-west3" }, { "endpointUrl": "https://dataflow.us-west4.rep.googleapis.com/", "description": "Regional Endpoint", "location": "us-west4" }, { "endpointUrl": "https://dataflow.us-west8.rep.googleapis.com/", "description": "Regional Endpoint", "location": "us-west8" } ], "protocol": "rest", "kind": "discovery#restDescription", "rootUrl": "https://dataflow.googleapis.com/", "auth": { "oauth2": { "scopes": { "https://www.googleapis.com/auth/cloud-platform": { "description": "See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account." }, "https://www.googleapis.com/auth/compute": { "description": "View and manage your Google Compute Engine resources" } } } }, "schemas": { "WriteInstruction": { "type": "object", "id": "WriteInstruction", "properties": { "input": { "description": "The input.", "$ref": "InstructionInput" }, "sink": { "description": "The sink to write to.", "$ref": "Sink" } }, "description": "An instruction that writes records. Takes one input, produces no outputs." }, "FlattenInstruction": { "description": "An instruction that copies its inputs (zero or more) to its (single) output.", "type": "object", "id": "FlattenInstruction", "properties": { "inputs": { "description": "Describes the inputs to the flatten instruction.", "type": "array", "items": { "$ref": "InstructionInput" } } } }, "CounterUpdate": { "type": "object", "id": "CounterUpdate", "properties": { "nameAndKind": { "description": "Counter name and aggregation type.", "$ref": "NameAndKind" }, "internal": { "description": "Value for internally-defined counters used by the Dataflow service.", "type": "any" }, "stringList": { "$ref": "StringList", "description": "List of strings, for Set." }, "boundedTrie": { "description": "Bounded trie data", "$ref": "BoundedTrie" }, "structuredNameAndMetadata": { "description": "Counter structured name and metadata.", "$ref": "CounterStructuredNameAndMetadata" }, "integerList": { "description": "List of integers, for Set.", "$ref": "IntegerList" }, "integerGauge": { "$ref": "IntegerGauge", "description": "Gauge data" }, "floatingPointMean": { "$ref": "FloatingPointMean", "description": "Floating point mean aggregation value for Mean." }, "boolean": { "description": "Boolean value for And, Or.", "type": "boolean" }, "floatingPointList": { "description": "List of floating point numbers, for Set.", "$ref": "FloatingPointList" }, "integer": { "description": "Integer value for Sum, Max, Min.", "$ref": "SplitInt64" }, "cumulative": { "description": "True if this counter is reported as the total cumulative aggregate value accumulated since the worker started working on this WorkItem. By default this is false, indicating that this counter is reported as a delta.", "type": "boolean" }, "floatingPoint": { "description": "Floating point value for Sum, Max, Min.", "type": "number", "format": "double" }, "shortId": { "format": "int64", "description": "The service-generated short identifier for this counter. The short_id -\u003e (name, metadata) mapping is constant for the lifetime of a job.", "type": "string" }, "distribution": { "description": "Distribution data", "$ref": "DistributionUpdate" }, "integerMean": { "description": "Integer mean aggregation value for Mean.", "$ref": "IntegerMean" } }, "description": "An update to a Counter sent from a worker. Next ID: 17" }, "TemplateMetadata": { "type": "object", "description": "Metadata describing a template.", "id": "TemplateMetadata", "properties": { "defaultStreamingMode": { "description": "Optional. Indicates the default streaming mode for a streaming template. Only valid if both supports_at_least_once and supports_exactly_once are true. Possible values: UNSPECIFIED, EXACTLY_ONCE and AT_LEAST_ONCE", "type": "string" }, "supportsAtLeastOnce": { "description": "Optional. Indicates if the streaming template supports at least once mode.", "type": "boolean" }, "supportsExactlyOnce": { "type": "boolean", "description": "Optional. Indicates if the streaming template supports exactly once mode." }, "parameters": { "description": "The parameters for the template.", "type": "array", "items": { "$ref": "ParameterMetadata" } }, "yamlDefinition": { "description": "Optional. For future use.", "type": "string" }, "description": { "type": "string", "description": "Optional. A description of the template." }, "name": { "description": "Required. The name of the template.", "type": "string" }, "streaming": { "type": "boolean", "description": "Optional. Indicates if the template is streaming or not." } } }, "Sink": { "properties": { "spec": { "additionalProperties": { "type": "any", "description": "Properties of the object." }, "type": "object", "description": "The sink to write to, plus its parameters." }, "codec": { "description": "The codec to use to encode data written to the sink.", "additionalProperties": { "type": "any", "description": "Properties of the object." }, "type": "object" } }, "type": "object", "description": "A sink that records can be encoded and written to.", "id": "Sink" }, "FileIODetails": { "type": "object", "id": "FileIODetails", "description": "Metadata for a File connector used by the job.", "properties": { "filePattern": { "description": "File Pattern used to access files by the connector.", "type": "string" } } }, "ContainerSpec": { "properties": { "imageRepositoryUsernameSecretId": { "type": "string", "description": "Secret Manager secret id for username to authenticate to private registry." }, "metadata": { "description": "Metadata describing a template including description and validation rules.", "$ref": "TemplateMetadata" }, "image": { "type": "string", "description": "Name of the docker container image. E.g., gcr.io/project/some-image" }, "defaultEnvironment": { "$ref": "FlexTemplateRuntimeEnvironment", "description": "Default runtime environment for the job." }, "imageRepositoryCertPath": { "type": "string", "description": "Cloud Storage path to self-signed certificate of private registry." }, "imageRepositoryPasswordSecretId": { "description": "Secret Manager secret id for password to authenticate to private registry.", "type": "string" }, "sdkInfo": { "description": "Required. SDK info of the Flex Template.", "$ref": "SDKInfo" } }, "type": "object", "id": "ContainerSpec", "description": "Container Spec." }, "ServiceResources": { "description": "Resources used by the Dataflow Service to run the job.", "properties": { "zones": { "type": "array", "readOnly": true, "items": { "type": "string" }, "description": "Output only. List of Cloud Zones being used by the Dataflow Service for this job. Example: us-central1-c" } }, "id": "ServiceResources", "type": "object" }, "SourceMetadata": { "properties": { "infinite": { "type": "boolean", "description": "Specifies that the size of this source is known to be infinite (this is a streaming source)." }, "producesSortedKeys": { "description": "Whether this source is known to produce key/value pairs with the (encoded) keys in lexicographically sorted order.", "type": "boolean" }, "estimatedSizeBytes": { "description": "An estimate of the total size (in bytes) of the data that would be read from this source. This estimate is in terms of external storage size, before any decompression or other processing done by the reader.", "format": "int64", "type": "string" } }, "id": "SourceMetadata", "type": "object", "description": "Metadata about a Source useful for automatically optimizing and tuning the pipeline, etc." }, "WorkerPool": { "properties": { "defaultPackageSet": { "enum": [ "DEFAULT_PACKAGE_SET_UNKNOWN", "DEFAULT_PACKAGE_SET_NONE", "DEFAULT_PACKAGE_SET_JAVA", "DEFAULT_PACKAGE_SET_PYTHON" ], "description": "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.", "enumDescriptions": [ "The default set of packages to stage is unknown, or unspecified.", "Indicates that no packages should be staged at the worker unless explicitly specified by the job.", "Stage packages typically useful to workers written in Java.", "Stage packages typically useful to workers written in Python." ], "type": "string" }, "ipConfiguration": { "enum": [ "WORKER_IP_UNSPECIFIED", "WORKER_IP_PUBLIC", "WORKER_IP_PRIVATE" ], "enumDescriptions": [ "The configuration is unknown, or unspecified.", "Workers should have public IP addresses.", "Workers should have private IP addresses." ], "description": "Configuration for VM IPs.", "type": "string" }, "zone": { "description": "Zone to run the worker pools in. If empty or unspecified, the service will attempt to choose a reasonable default.", "type": "string" }, "numThreadsPerWorker": { "description": "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).", "type": "integer", "format": "int32" }, "poolArgs": { "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." }, "description": "Extra arguments for this worker pool.", "type": "object" }, "network": { "description": "Network to which VMs will be assigned. If empty or unspecified, the service will use the network \"default\".", "type": "string" }, "diskSizeGb": { "description": "Size of root disk for VMs, in GB. If zero or unspecified, the service will attempt to choose a reasonable default.", "type": "integer", "format": "int32" }, "onHostMaintenance": { "type": "string", "description": "The action to take on host maintenance, as defined by the Google Compute Engine API." }, "diskProvisionedIops": { "format": "int64", "description": "Optional. IOPS provisioned for the root disk for VMs.", "type": "string" }, "metadata": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Metadata to set on the Google Compute Engine VMs." }, "taskrunnerSettings": { "description": "Settings passed through to Google Compute Engine workers when using the standard Dataflow task runner. Users should ignore this field.", "$ref": "TaskRunnerSettings" }, "diskType": { "type": "string", "description": "Type of root disk for VMs. If empty or unspecified, the service will attempt to choose a reasonable default." }, "numWorkers": { "format": "int32", "description": "Number of Google Compute Engine workers in this pool needed to execute the job. If zero or unspecified, the service will attempt to choose a reasonable default.", "type": "integer" }, "diskProvisionedThroughputMibps": { "description": "Optional. Throughput provisioned for the root disk for VMs.", "format": "int64", "type": "string" }, "dataDisks": { "type": "array", "description": "Data disks that are used by a VM in this workflow.", "items": { "$ref": "Disk" } }, "packages": { "description": "Packages to be installed on workers.", "type": "array", "items": { "$ref": "Package" } }, "autoscalingSettings": { "$ref": "AutoscalingSettings", "description": "Settings for autoscaling of this WorkerPool." }, "teardownPolicy": { "description": "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.", "type": "string", "enumDescriptions": [ "The teardown policy isn't specified, or is unknown.", "Always teardown the resource.", "Teardown the resource on success. This is useful for debugging failures.", "Never teardown the resource. This is useful for debugging and development." ], "enum": [ "TEARDOWN_POLICY_UNKNOWN", "TEARDOWN_ALWAYS", "TEARDOWN_ON_SUCCESS", "TEARDOWN_NEVER" ] }, "diskSourceImage": { "description": "Fully qualified source image for disks.", "type": "string" }, "workerHarnessContainerImage": { "type": "string", "description": "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." }, "machineType": { "description": "Machine type (e.g. \"n1-standard-1\"). If empty or unspecified, the service will attempt to choose a reasonable default.", "type": "string" }, "kind": { "description": "The kind of the worker pool; currently only `harness` and `shuffle` are supported.", "type": "string" }, "subnetwork": { "description": "Subnetwork to which VMs will be assigned, if desired. Expected to be of the form \"regions/REGION/subnetworks/SUBNETWORK\".", "type": "string" }, "sdkHarnessContainerImages": { "type": "array", "items": { "$ref": "SdkHarnessContainerImage" }, "description": "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." } }, "type": "object", "description": "Describes one particular pool of Cloud Dataflow workers to be instantiated by the Cloud Dataflow service in order to perform the 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.", "id": "WorkerPool" }, "InstructionInput": { "type": "object", "description": "An input of an instruction, as a reference to an output of a producer instruction.", "id": "InstructionInput", "properties": { "producerInstructionIndex": { "format": "int32", "description": "The index (origin zero) of the parallel instruction that produces the output to be consumed by this input. This index is relative to the list of instructions in this input's instruction's containing MapTask.", "type": "integer" }, "outputNum": { "format": "int32", "description": "The output index (origin zero) within the producer.", "type": "integer" } } }, "DataDiskAssignment": { "properties": { "dataDisks": { "description": "Mounted data disks. The order is important a data disk's 0-based index in this list defines which persistent directory the disk is mounted to, for example the list of { \"myproject-1014-104817-4c2-harness-0-disk-0\" }, { \"myproject-1014-104817-4c2-harness-0-disk-1\" }.", "items": { "type": "string" }, "type": "array" }, "vmInstance": { "type": "string", "description": "VM instance name the data disks mounted to, for example \"myproject-1014-104817-4c2-harness-0\"." } }, "description": "Data disk assignment for a given VM instance.", "type": "object", "id": "DataDiskAssignment" }, "SourceSplitShard": { "type": "object", "id": "SourceSplitShard", "properties": { "source": { "$ref": "Source", "description": "DEPRECATED" }, "derivationMode": { "description": "DEPRECATED", "enum": [ "SOURCE_DERIVATION_MODE_UNKNOWN", "SOURCE_DERIVATION_MODE_INDEPENDENT", "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT", "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT" ], "enumDescriptions": [ "The source derivation is unknown, or unspecified.", "Produce a completely independent Source with no base.", "Produce a Source based on the Source being split.", "Produce a Source based on the base of the Source being split." ], "type": "string" } }, "description": "DEPRECATED in favor of DerivedSource." }, "RuntimeUpdatableParams": { "description": "Additional job parameters that can only be updated during runtime using the projects.jobs.update method. These fields have no effect when specified during job creation.", "type": "object", "properties": { "autoscalingTier": { "description": "Optional. Deprecated: Use `latency_tier` instead. The backlog threshold tier for autoscaling. Value must be one of \"low-latency\", \"medium-latency\", or \"high-latency\".", "deprecated": true, "type": "string" }, "minNumWorkers": { "description": "The minimum number of workers to scale down to. This field is currently only supported for Streaming Engine jobs.", "type": "integer", "format": "int32" }, "workerUtilizationHint": { "description": "Target worker utilization, compared against the aggregate utilization of the worker pool by autoscaler, to determine upscaling and downscaling when absent other constraints such as backlog. For more information, see [Update an existing pipeline](https://cloud.google.com/dataflow/docs/guides/updating-a-pipeline).", "type": "number", "format": "double" }, "latencyTier": { "type": "string", "description": "Optional. The backlog threshold tier for autoscaling. Value must be one of \"low-latency\", \"medium-latency\", or \"high-latency\"." }, "schedules": { "description": "Optional. The schedule for autoscaling.", "type": "array", "items": { "$ref": "AutoscalingSchedule" } }, "acceptableBacklogDuration": { "format": "google-duration", "type": "string", "deprecated": true, "description": "Optional. Deprecated: Use `latency_tier` instead. The backlog threshold duration in seconds for autoscaling. Value must be non-negative." }, "maxNumWorkers": { "type": "integer", "description": "The maximum number of workers to cap autoscaling at. This field is currently only supported for Streaming Engine jobs.", "format": "int32" } }, "id": "RuntimeUpdatableParams" }, "PerStepNamespaceMetrics": { "properties": { "originalStep": { "type": "string", "description": "The original system name of the unfused step that these metrics are reported from." }, "metricsNamespace": { "type": "string", "description": "The namespace of these metrics on the worker." }, "metricValues": { "items": { "$ref": "MetricValue" }, "description": "Optional. Metrics that are recorded for this namespace and unfused step.", "type": "array" } }, "description": "Metrics for a particular unfused step and namespace. A metric is uniquely identified by the `metrics_namespace`, `original_step`, `metric name` and `metric_labels`.", "type": "object", "id": "PerStepNamespaceMetrics" }, "HotKeyDetection": { "id": "HotKeyDetection", "description": "Proto describing a hot key detected on a given WorkItem.", "properties": { "systemName": { "type": "string", "description": "System-defined name of the step containing this hot key. Unique across the workflow." }, "userStepName": { "description": "User-provided name of the step that contains this hot key.", "type": "string" }, "hotKeyAge": { "type": "string", "format": "google-duration", "description": "The age of the hot key measured from when it was first detected." } }, "type": "object" }, "TransformSummary": { "properties": { "displayData": { "items": { "$ref": "DisplayData" }, "type": "array", "description": "Transform-specific display data." }, "kind": { "description": "Type of transform.", "enumDescriptions": [ "Unrecognized transform type.", "ParDo transform.", "Group By Key transform.", "Flatten transform.", "Read transform.", "Write transform.", "Constructs from a constant value, such as with Create.of.", "Creates a Singleton view of a collection.", "Opening or closing a shuffle session, often as part of a GroupByKey." ], "type": "string", "enum": [ "UNKNOWN_KIND", "PAR_DO_KIND", "GROUP_BY_KEY_KIND", "FLATTEN_KIND", "READ_KIND", "WRITE_KIND", "CONSTANT_KIND", "SINGLETON_KIND", "SHUFFLE_KIND" ] }, "inputCollectionName": { "items": { "type": "string" }, "description": "User names for all collection inputs to this transform.", "type": "array" }, "id": { "type": "string", "description": "SDK generated id of this transform instance." }, "outputCollectionName": { "type": "array", "description": "User names for all collection outputs to this transform.", "items": { "type": "string" } }, "name": { "type": "string", "description": "User provided name for this transform instance." } }, "description": "Description of the type, names/ids, and input/outputs for a transform.", "type": "object", "id": "TransformSummary" }, "GetWorkerStacktracesRequest": { "type": "object", "id": "GetWorkerStacktracesRequest", "properties": { "endTime": { "format": "google-datetime", "type": "string", "description": "The end time for the stacktrace query. The returned stacktraces will be a recent stack trace at or shortly before this time." }, "workerId": { "type": "string", "description": "The worker for which to get stacktraces. The returned stacktraces will be for the SDK harness running on this worker." } }, "description": "Request to get worker stacktraces from debug capture." }, "WorkItemDetails": { "properties": { "taskId": { "type": "string", "description": "Name of this work item." }, "attemptId": { "description": "Attempt ID of this work item", "type": "string" }, "stragglerInfo": { "$ref": "StragglerInfo", "description": "Information about straggler detections for this work item." }, "state": { "enumDescriptions": [ "The component state is unknown or unspecified.", "The component is not yet running.", "The component is currently running.", "The component succeeded.", "The component failed.", "Execution of the component was cancelled." ], "type": "string", "description": "State of this work item.", "enum": [ "EXECUTION_STATE_UNKNOWN", "EXECUTION_STATE_NOT_STARTED", "EXECUTION_STATE_RUNNING", "EXECUTION_STATE_SUCCEEDED", "EXECUTION_STATE_FAILED", "EXECUTION_STATE_CANCELLED" ] }, "metrics": { "type": "array", "description": "Metrics for this work item.", "items": { "$ref": "MetricUpdate" } }, "progress": { "$ref": "ProgressTimeseries", "description": "Progress of this work item." }, "endTime": { "format": "google-datetime", "type": "string", "description": "End time of this work item attempt. If the work item is completed, this is the actual end time of the work item. Otherwise, it is the predicted end time." }, "startTime": { "type": "string", "format": "google-datetime", "description": "Start time of this work item attempt." } }, "type": "object", "description": "Information about an individual work item execution.", "id": "WorkItemDetails" }, "StreamingSideInputLocation": { "description": "Identifies the location of a streaming side input.", "id": "StreamingSideInputLocation", "type": "object", "properties": { "stateFamily": { "type": "string", "description": "Identifies the state family where this side input is stored." }, "tag": { "type": "string", "description": "Identifies the particular side input within the streaming Dataflow job." } } }, "StageSummary": { "properties": { "startTime": { "type": "string", "description": "Start time of this stage.", "format": "google-datetime" }, "progress": { "description": "Progress for this stage. Only applicable to Batch jobs.", "$ref": "ProgressTimeseries" }, "stageId": { "description": "ID of this stage", "type": "string" }, "endTime": { "description": "End time of this stage. If the work item is completed, this is the actual end time of the stage. Otherwise, it is the predicted end time.", "type": "string", "format": "google-datetime" }, "metrics": { "type": "array", "description": "Metrics for this stage.", "items": { "$ref": "MetricUpdate" } }, "state": { "type": "string", "enumDescriptions": [ "The component state is unknown or unspecified.", "The component is not yet running.", "The component is currently running.", "The component succeeded.", "The component failed.", "Execution of the component was cancelled." ], "description": "State of this stage.", "enum": [ "EXECUTION_STATE_UNKNOWN", "EXECUTION_STATE_NOT_STARTED", "EXECUTION_STATE_RUNNING", "EXECUTION_STATE_SUCCEEDED", "EXECUTION_STATE_FAILED", "EXECUTION_STATE_CANCELLED" ] }, "stragglerSummary": { "$ref": "StragglerSummary", "description": "Straggler summary for this stage." } }, "id": "StageSummary", "description": "Information about a particular execution stage of a job.", "type": "object" }, "WorkItem": { "type": "object", "id": "WorkItem", "properties": { "sourceOperationTask": { "description": "Additional information for source operation WorkItems.", "$ref": "SourceOperationRequest" }, "id": { "format": "int64", "description": "Identifies this WorkItem.", "type": "string" }, "jobId": { "type": "string", "description": "Identifies the workflow job this WorkItem belongs to." }, "leaseExpireTime": { "description": "Time when the lease on this Work will expire.", "type": "string", "format": "google-datetime" }, "shellTask": { "description": "Additional information for ShellTask WorkItems.", "$ref": "ShellTask" }, "seqMapTask": { "description": "Additional information for SeqMapTask WorkItems.", "$ref": "SeqMapTask" }, "streamingSetupTask": { "$ref": "StreamingSetupTask", "description": "Additional information for StreamingSetupTask WorkItems." }, "streamingConfigTask": { "description": "Additional information for StreamingConfigTask WorkItems.", "$ref": "StreamingConfigTask" }, "initialReportIndex": { "description": "The initial index to use when reporting the status of the WorkItem.", "type": "string", "format": "int64" }, "packages": { "type": "array", "items": { "$ref": "Package" }, "description": "Any required packages that need to be fetched in order to execute this WorkItem." }, "projectId": { "description": "Identifies the cloud project this WorkItem belongs to.", "type": "string" }, "mapTask": { "$ref": "MapTask", "description": "Additional information for MapTask WorkItems." }, "reportStatusInterval": { "format": "google-duration", "description": "Recommended reporting interval.", "type": "string" }, "configuration": { "description": "Work item-specific configuration as an opaque blob.", "type": "string" }, "streamingComputationTask": { "$ref": "StreamingComputationTask", "description": "Additional information for StreamingComputationTask WorkItems." } }, "description": "WorkItem represents basic information about a WorkItem to be executed in the cloud." }, "StreamingOperationalLimits": { "id": "StreamingOperationalLimits", "type": "object", "properties": { "maxKeyBytes": { "description": "The maximum size allowed for a key.", "type": "string", "format": "int64" }, "maxProductionOutputBytes": { "type": "string", "format": "int64", "description": "The maximum size for a single output element." }, "maxValueBytes": { "description": "The maximum size for a value state field.", "type": "string", "format": "int64" }, "maxBagElementBytes": { "format": "int64", "type": "string", "description": "The maximum size for an element in bag state." }, "maxGlobalDataBytes": { "description": "The maximum size for an element in global data.", "type": "string", "format": "int64" }, "maxSortedListElementBytes": { "format": "int64", "description": "The maximum size for an element in sorted list state.", "type": "string" }, "maxSourceStateBytes": { "type": "string", "format": "int64", "description": "The maximum size for a source state update." }, "maxTagBytes": { "description": "The maximum size for a state tag.", "format": "int64", "type": "string" } }, "description": "Operational limits imposed on streaming jobs by the backend." }, "Straggler": { "id": "Straggler", "description": "Information for a straggler.", "type": "object", "properties": { "batchStraggler": { "$ref": "StragglerInfo", "description": "Batch straggler identification and debugging information." }, "streamingStraggler": { "$ref": "StreamingStragglerInfo", "description": "Streaming straggler identification and debugging information." } } }, "ExecutionStageState": { "description": "A message describing the state of a particular execution stage.", "properties": { "executionStageName": { "description": "The name of the execution stage.", "type": "string" }, "executionStageState": { "enum": [ "JOB_STATE_UNKNOWN", "JOB_STATE_STOPPED", "JOB_STATE_RUNNING", "JOB_STATE_DONE", "JOB_STATE_FAILED", "JOB_STATE_CANCELLED", "JOB_STATE_UPDATED", "JOB_STATE_DRAINING", "JOB_STATE_DRAINED", "JOB_STATE_PENDING", "JOB_STATE_CANCELLING", "JOB_STATE_QUEUED", "JOB_STATE_RESOURCE_CLEANING_UP", "JOB_STATE_PAUSING", "JOB_STATE_PAUSED" ], "type": "string", "enumDescriptions": [ "The job's run state isn't specified.", "`JOB_STATE_STOPPED` indicates that the job has not yet started to run.", "`JOB_STATE_RUNNING` indicates that the job is currently running.", "`JOB_STATE_DONE` indicates that the job has successfully completed. This is a terminal job state. This state may be set by the Cloud Dataflow service, as a transition from `JOB_STATE_RUNNING`. It may also be set via a Cloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal state.", "`JOB_STATE_FAILED` indicates that the job has failed. This is a terminal job state. This state may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.", "`JOB_STATE_CANCELLED` indicates that the job has been explicitly cancelled. This is a terminal job state. This state may only be set via a Cloud Dataflow `UpdateJob` call, and only if the job has not yet reached another terminal state.", "`JOB_STATE_UPDATED` indicates that the job was successfully updated, meaning that this job was stopped and another job was started, inheriting state from this one. This is a terminal job state. This state may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.", "`JOB_STATE_DRAINING` indicates that the job is in the process of draining. A draining job has stopped pulling from its input sources and is processing any data that remains in-flight. This state may be set via a Cloud Dataflow `UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs that are draining may only transition to `JOB_STATE_DRAINED`, `JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.", "`JOB_STATE_DRAINED` indicates that the job has been drained. A drained job terminated by stopping pulling from its input sources and processing any data that remained in-flight when draining was requested. This state is a terminal state, may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_DRAINING`.", "`JOB_STATE_PENDING` indicates that the job has been created but is not yet running. Jobs that are pending may only transition to `JOB_STATE_RUNNING`, or `JOB_STATE_FAILED`.", "`JOB_STATE_CANCELLING` indicates that the job has been explicitly cancelled and is in the process of stopping. Jobs that are cancelling may only transition to `JOB_STATE_CANCELLED` or `JOB_STATE_FAILED`.", "`JOB_STATE_QUEUED` indicates that the job has been created but is being delayed until launch. Jobs that are queued may only transition to `JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`.", "`JOB_STATE_RESOURCE_CLEANING_UP` indicates that the batch job's associated resources are currently being cleaned up after a successful run. Currently, this is an opt-in feature, please reach out to Cloud support team if you are interested.", "`JOB_STATE_PAUSING` indicates that the job is in the process of pausing. A pausing job will stop processing, archive in-flight Shuffle data, and transition to `JOB_STATE_PAUSED`. Jobs in this state can transition to `JOB_STATE_CANCELLING` if cancellation is requested, or can transition back to `JOB_STATE_RUNNING` if the pause fails to complete.", "`JOB_STATE_PAUSED` indicates that the job is not currently processing. Jobs in this state can transition back to `JOB_STATE_RUNNING` to continue processing where they left off, or can transition to `JOB_STATE_CANCELLING` if cancellation is requested." ], "description": "Executions stage states allow the same set of values as JobState." }, "currentStateTime": { "type": "string", "description": "The time at which the stage transitioned to this state.", "format": "google-datetime" } }, "type": "object", "id": "ExecutionStageState" }, "GetWorkerStacktracesResponse": { "properties": { "sdks": { "type": "array", "items": { "$ref": "Sdk" }, "description": "Repeated as unified worker may have multiple SDK processes." } }, "description": "Response to get worker stacktraces from debug capture.", "type": "object", "id": "GetWorkerStacktracesResponse" }, "WorkerLifecycleEvent": { "description": "A report of an event in a worker's lifecycle. The proto contains one event, because the worker is expected to asynchronously send each message immediately after the event. Due to this asynchrony, messages may arrive out of order (or missing), and it is up to the consumer to interpret. The timestamp of the event is in the enclosing WorkerMessage proto.", "properties": { "containerStartTime": { "format": "google-datetime", "type": "string", "description": "The start time of this container. All events will report this so that events can be grouped together across container/VM restarts." }, "metadata": { "description": "Other stats that can accompany an event. E.g. { \"downloaded_bytes\" : \"123456\" }", "type": "object", "additionalProperties": { "type": "string" } }, "event": { "enumDescriptions": [ "Invalid event.", "The time the VM started.", "Our container code starts running. Multiple containers could be distinguished with WorkerMessage.labels if desired.", "The worker has a functional external network connection.", "Started downloading staging files.", "Finished downloading all staging files.", "For applicable SDKs, started installation of SDK and worker packages.", "Finished installing SDK." ], "enum": [ "UNKNOWN_EVENT", "OS_START", "CONTAINER_START", "NETWORK_UP", "STAGING_FILES_DOWNLOAD_START", "STAGING_FILES_DOWNLOAD_FINISH", "SDK_INSTALL_START", "SDK_INSTALL_FINISH" ], "description": "The event being reported.", "type": "string" } }, "type": "object", "id": "WorkerLifecycleEvent" }, "ResourceUtilizationReport": { "properties": { "containers": { "type": "object", "additionalProperties": { "$ref": "ResourceUtilizationReport" }, "description": "Per container information. Key: container name." }, "cpuTime": { "description": "CPU utilization samples.", "items": { "$ref": "CPUTime" }, "type": "array" }, "gpuUsage": { "type": "array", "items": { "$ref": "GPUUsage" }, "description": "Optional. GPU usage samples." }, "memoryInfo": { "type": "array", "items": { "$ref": "MemInfo" }, "description": "Memory utilization samples." } }, "type": "object", "description": "Worker metrics exported from workers. This contains resource utilization metrics accumulated from a variety of sources. For more information, see go/df-resource-signals.", "id": "ResourceUtilizationReport" }, "MemInfo": { "type": "object", "properties": { "currentLimitBytes": { "description": "Instantenous memory limit in bytes.", "format": "uint64", "type": "string" }, "totalGbMs": { "type": "string", "description": "Total memory (RSS) usage since start up in GB * ms.", "format": "uint64" }, "currentRssBytes": { "description": "Instantenous memory (RSS) size in bytes.", "type": "string", "format": "uint64" }, "currentOoms": { "type": "string", "description": "Number of Out of Memory (OOM) events recorded since the previous measurement.", "format": "int64" }, "timestamp": { "description": "Timestamp of the measurement.", "format": "google-datetime", "type": "string" } }, "description": "Information about the memory usage of a worker or a container within a worker.", "id": "MemInfo" }, "AutoscalingSchedule": { "properties": { "crontab": { "description": "Optional. A crontab specification of when this schedule should trigger applying overrides. The overrides will be applied from the trigger time until the specified duration elapses.", "type": "string" }, "updateTime": { "description": "Output only. When the customer last updated the schedule.", "readOnly": true, "type": "string", "format": "google-datetime" }, "parameters": { "description": "Optional. The parameters to use for autoscaling when this schedule is active.", "$ref": "Parameters" }, "name": { "description": "Optional. The name of the schedule.", "type": "string" }, "duration": { "type": "string", "format": "google-duration", "description": "Optional. The duration for which the parameter overrides for this schedule will be applied when triggered by the crontab." }, "timeZone": { "description": "Optional. The time zone for the schedule. The value of this field must be a time zone name from the [tz database](http://en.wikipedia.org/wiki/Tz_database). The default value is UTC.", "type": "string" }, "priority": { "type": "string", "description": "Optional. Specifies the priority of the schedule. If two schedules overlap, the one with the higher priority will be used. The higher the value, the higher the priority of the schedule.", "format": "int64" } }, "type": "object", "description": "A schedule for autoscaling.", "id": "AutoscalingSchedule" }, "ReportWorkItemStatusRequest": { "type": "object", "properties": { "workerId": { "type": "string", "description": "The ID of the worker reporting the WorkItem status. If this does not match the ID of the worker which the Dataflow service believes currently has the lease on the WorkItem, the report will be dropped (with an error response)." }, "projectNumber": { "format": "int64", "description": "Optional. The project number of the project which owns the WorkItem's job.", "type": "string" }, "unifiedWorkerRequest": { "type": "object", "description": "Untranslated bag-of-bytes WorkProgressUpdateRequest from UnifiedWorker.", "additionalProperties": { "description": "Properties of the object. Contains field @type with type URL.", "type": "any" } }, "currentWorkerTime": { "description": "The current timestamp at the worker.", "type": "string", "format": "google-datetime" }, "workItemStatuses": { "description": "The order is unimportant, except that the order of the WorkItemServiceState messages in the ReportWorkItemStatusResponse corresponds to the order of WorkItemStatus messages here.", "items": { "$ref": "WorkItemStatus" }, "type": "array" }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the WorkItem's job.", "type": "string" } }, "id": "ReportWorkItemStatusRequest", "description": "Request to report the status of WorkItems." }, "GPUUtilization": { "description": "Utilization details about the GPU.", "properties": { "rate": { "description": "Required. GPU utilization rate of any kernel over the last sample period in the range of [0, 1].", "format": "double", "type": "number" } }, "id": "GPUUtilization", "type": "object" }, "TaskRunnerSettings": { "type": "object", "id": "TaskRunnerSettings", "properties": { "logUploadLocation": { "description": "Indicates where to put logs. If this is not specified, the logs will not be uploaded. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}", "type": "string" }, "commandlinesFileName": { "type": "string", "description": "The file to store preprocessing commands in." }, "logDir": { "description": "The directory on the VM to store logs.", "type": "string" }, "parallelWorkerSettings": { "description": "The settings to pass to the parallel worker harness.", "$ref": "WorkerSettings" }, "dataflowApiVersion": { "description": "The API version of endpoint, e.g. \"v1b3\"", "type": "string" }, "harnessCommand": { "description": "The command to launch the worker harness.", "type": "string" }, "streamingWorkerMainClass": { "type": "string", "description": "The streaming worker main class name." }, "taskGroup": { "type": "string", "description": "The UNIX group ID on the worker VM to use for tasks launched by taskrunner; e.g. \"wheel\"." }, "tempStoragePrefix": { "description": "The prefix of the resources the taskrunner should use for temporary storage. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}", "type": "string" }, "continueOnException": { "description": "Whether to continue taskrunner if an exception is hit.", "type": "boolean" }, "baseUrl": { "type": "string", "description": "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/\"" }, "taskUser": { "description": "The UNIX user ID on the worker VM to use for tasks launched by taskrunner; e.g. \"root\".", "type": "string" }, "logToSerialconsole": { "type": "boolean", "description": "Whether to send taskrunner log info to Google Compute Engine VM serial console." }, "languageHint": { "type": "string", "description": "The suggested backend language." }, "alsologtostderr": { "type": "boolean", "description": "Whether to also send taskrunner log info to stderr." }, "workflowFileName": { "description": "The file to store the workflow in.", "type": "string" }, "vmId": { "description": "The ID string of the VM.", "type": "string" }, "oauthScopes": { "items": { "type": "string" }, "type": "array", "description": "The OAuth2 scopes to be requested by the taskrunner in order to access the Cloud Dataflow API." }, "baseTaskDir": { "description": "The location on the worker for task-specific subdirectories.", "type": "string" } }, "description": "Taskrunner configuration settings." }, "StragglerInfo": { "properties": { "causes": { "description": "The straggler causes, keyed by the string representation of the StragglerCause enum and contains specialized debugging information for each straggler cause.", "type": "object", "additionalProperties": { "$ref": "StragglerDebuggingInfo" } }, "startTime": { "format": "google-datetime", "description": "The time when the work item attempt became a straggler.", "type": "string" } }, "id": "StragglerInfo", "type": "object", "description": "Information useful for straggler identification and debugging." }, "HotKeyDebuggingInfo": { "type": "object", "id": "HotKeyDebuggingInfo", "properties": { "detectedHotKeys": { "additionalProperties": { "$ref": "HotKeyInfo" }, "type": "object", "description": "Debugging information for each detected hot key. Keyed by a hash of the key." } }, "description": "Information useful for debugging a hot key detection." }, "ExecutionStageSummary": { "description": "Description of the composing transforms, names/ids, and input/outputs of a stage of execution. Some composing transforms and sources may have been generated by the Dataflow service during execution planning.", "type": "object", "id": "ExecutionStageSummary", "properties": { "name": { "description": "Dataflow service generated name for this stage.", "type": "string" }, "inputSource": { "description": "Input sources for this stage.", "type": "array", "items": { "$ref": "StageSource" } }, "outputSource": { "items": { "$ref": "StageSource" }, "description": "Output sources for this stage.", "type": "array" }, "id": { "description": "Dataflow service generated id for this stage.", "type": "string" }, "componentTransform": { "items": { "$ref": "ComponentTransform" }, "type": "array", "description": "Transforms that comprise this execution stage." }, "prerequisiteStage": { "type": "array", "description": "Other stages that must complete before this stage can run.", "items": { "type": "string" } }, "componentSource": { "type": "array", "items": { "$ref": "ComponentSource" }, "description": "Collections produced and consumed by component transforms of this stage." }, "kind": { "type": "string", "description": "Type of transform this stage is executing.", "enumDescriptions": [ "Unrecognized transform type.", "ParDo transform.", "Group By Key transform.", "Flatten transform.", "Read transform.", "Write transform.", "Constructs from a constant value, such as with Create.of.", "Creates a Singleton view of a collection.", "Opening or closing a shuffle session, often as part of a GroupByKey." ], "enum": [ "UNKNOWN_KIND", "PAR_DO_KIND", "GROUP_BY_KEY_KIND", "FLATTEN_KIND", "READ_KIND", "WRITE_KIND", "CONSTANT_KIND", "SINGLETON_KIND", "SHUFFLE_KIND" ] } } }, "StreamingScalingReport": { "description": "Contains per-user worker telemetry used in streaming autoscaling.", "id": "StreamingScalingReport", "properties": { "activeBundleCount": { "deprecated": true, "type": "integer", "format": "int32" }, "maximumBytes": { "type": "string", "description": "Maximum bytes.", "format": "int64" }, "maximumThreadCount": { "format": "int32", "description": "Maximum thread count limit.", "type": "integer" }, "maximumBytesCount": { "type": "integer", "deprecated": true, "format": "int32" }, "outstandingBytes": { "description": "Current outstanding bytes.", "format": "int64", "type": "string" }, "activeThreadCount": { "description": "Current acive thread count.", "type": "integer", "format": "int32" }, "outstandingBundleCount": { "type": "integer", "description": "Current outstanding bundle count.", "format": "int32" }, "outstandingBytesCount": { "type": "integer", "deprecated": true, "format": "int32" }, "maximumBundleCount": { "type": "integer", "format": "int32", "description": "Maximum bundle count." } }, "type": "object" }, "SideInputInfo": { "properties": { "tag": { "description": "The id of the tag the user code will access this side input by; this should correspond to the tag of some MultiOutputInfo.", "type": "string" }, "sources": { "description": "The source(s) to read element(s) from to get the value of this side input. If more than one source, then the elements are taken from the sources, in the specified order if order matters. At least one source is required.", "items": { "$ref": "Source" }, "type": "array" }, "kind": { "type": "object", "additionalProperties": { "description": "Properties of the object.", "type": "any" }, "description": "How to interpret the source element(s) as a side input value." } }, "id": "SideInputInfo", "type": "object", "description": "Information about a side input of a DoFn or an input of a SeqDoFn." }, "ReportedParallelism": { "type": "object", "description": "Represents the level of parallelism in a WorkItem's input, reported by the worker.", "id": "ReportedParallelism", "properties": { "value": { "type": "number", "format": "double", "description": "Specifies the level of parallelism in case it is finite." }, "isInfinite": { "type": "boolean", "description": "Specifies whether the parallelism is infinite. If true, \"value\" is ignored. Infinite parallelism means the service will assume that the work item can always be split into more non-empty work items by dynamic splitting. This is a work-around for lack of support for infinity by the current JSON-based Java RPC stack." } } }, "SendDebugCaptureResponse": { "id": "SendDebugCaptureResponse", "properties": {}, "description": "Response to a send capture request. nothing", "type": "object" }, "SplitInt64": { "type": "object", "id": "SplitInt64", "properties": { "lowBits": { "type": "integer", "format": "uint32", "description": "The low order bits: n & 0xffffffff." }, "highBits": { "type": "integer", "format": "int32", "description": "The high order bits, including the sign: n \u003e\u003e 32." } }, "description": "A representation of an int64, n, that is immune to precision loss when encoded in JSON." }, "SendDebugCaptureRequest": { "id": "SendDebugCaptureRequest", "properties": { "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id.", "type": "string" }, "componentId": { "description": "The internal component id for which debug information is sent.", "type": "string" }, "workerId": { "description": "The worker id, i.e., VM hostname.", "type": "string" }, "data": { "description": "The encoded debug information.", "type": "string" }, "dataFormat": { "description": "Format for the data field above (id=5).", "type": "string", "enumDescriptions": [ "Format unspecified, parsing is determined based upon page type and legacy encoding. (go/protodosdonts#do-include-an-unspecified-value-in-an-enum)", "Raw HTML string.", "JSON-encoded string.", "Websafe encoded zlib-compressed string.", "Websafe encoded brotli-compressed string." ], "enum": [ "DATA_FORMAT_UNSPECIFIED", "RAW", "JSON", "ZLIB", "BROTLI" ] } }, "description": "Request to send encoded debug information. Next ID: 8", "type": "object" }, "KeyRangeLocation": { "description": "Location information for a specific key-range of a sharded computation. Currently we only support UTF-8 character splits to simplify encoding into JSON.", "id": "KeyRangeLocation", "type": "object", "properties": { "deliveryEndpoint": { "type": "string", "description": "The physical location of this range assignment to be used for streaming computation cross-worker message delivery." }, "start": { "description": "The start (inclusive) of the key range.", "type": "string" }, "dataDisk": { "type": "string", "description": "The name of the data disk where data for this range is stored. This name is local to the Google Cloud Platform project and uniquely identifies the disk within that project, for example \"myproject-1014-104817-4c2-harness-0-disk-1\"." }, "deprecatedPersistentDirectory": { "type": "string", "description": "DEPRECATED. The location of the persistent state for this range, as a persistent directory in the worker local filesystem.", "deprecated": true }, "end": { "description": "The end (exclusive) of the key range.", "type": "string" } } }, "SpannerIODetails": { "description": "Metadata for a Spanner connector used by the job.", "id": "SpannerIODetails", "properties": { "instanceId": { "description": "InstanceId accessed in the connection.", "type": "string" }, "projectId": { "description": "ProjectId accessed in the connection.", "type": "string" }, "databaseId": { "description": "DatabaseId accessed in the connection.", "type": "string" } }, "type": "object" }, "JobMetrics": { "type": "object", "properties": { "metricTime": { "type": "string", "format": "google-datetime", "description": "Timestamp as of which metric values are current." }, "metrics": { "type": "array", "description": "All metrics for this job.", "items": { "$ref": "MetricUpdate" } } }, "description": "JobMetrics contains a collection of metrics describing the detailed progress of a Dataflow job. Metrics correspond to user-defined and system-defined metrics in the job. For more information, see [Dataflow job metrics] (https://cloud.google.com/dataflow/docs/guides/using-monitoring-intf). This resource captures only the most recent values of each metric; time-series data can be queried for them (under the same metric names) from Cloud Monitoring.", "id": "JobMetrics" }, "DerivedSource": { "type": "object", "properties": { "derivationMode": { "enum": [ "SOURCE_DERIVATION_MODE_UNKNOWN", "SOURCE_DERIVATION_MODE_INDEPENDENT", "SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT", "SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT" ], "type": "string", "description": "What source to base the produced source on (if any).", "enumDescriptions": [ "The source derivation is unknown, or unspecified.", "Produce a completely independent Source with no base.", "Produce a Source based on the Source being split.", "Produce a Source based on the base of the Source being split." ] }, "source": { "description": "Specification of the source.", "$ref": "Source" } }, "description": "Specification of one of the bundles produced as a result of splitting a Source (e.g. when executing a SourceSplitRequest, or when splitting an active task using WorkItemStatus.dynamic_source_split), relative to the source being split.", "id": "DerivedSource" }, "StragglerDebuggingInfo": { "id": "StragglerDebuggingInfo", "type": "object", "properties": { "hotKey": { "$ref": "HotKeyDebuggingInfo", "description": "Hot key debugging details." } }, "description": "Information useful for debugging a straggler. Each type will provide specialized debugging information relevant for a particular cause. The StragglerDebuggingInfo will be 1:1 mapping to the StragglerCause enum." }, "PubSubIODetails": { "type": "object", "description": "Metadata for a Pub/Sub connector used by the job.", "properties": { "topic": { "type": "string", "description": "Topic accessed in the connection." }, "subscription": { "description": "Subscription used in the connection.", "type": "string" } }, "id": "PubSubIODetails" }, "MultiOutputInfo": { "properties": { "tag": { "type": "string", "description": "The id of the tag the user code will emit to this output by; this should correspond to the tag of some SideInputInfo." } }, "id": "MultiOutputInfo", "type": "object", "description": "Information about an output of a multi-output DoFn." }, "ListJobsResponse": { "id": "ListJobsResponse", "type": "object", "properties": { "nextPageToken": { "type": "string", "description": "Set if there may be more results than fit in this response." }, "jobs": { "items": { "$ref": "Job" }, "type": "array", "description": "A subset of the requested job information." }, "failedLocation": { "type": "array", "items": { "$ref": "FailedLocation" }, "description": "Zero or more messages describing the [regional endpoints] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that failed to respond." } }, "description": "Response to a request to list Cloud Dataflow jobs in a project. This might be a partial response, depending on the page size in the ListJobsRequest. However, if the project does not have any jobs, an instance of ListJobsResponse is not returned and the requests's response body is empty {}." }, "WorkerHealthReport": { "id": "WorkerHealthReport", "properties": { "msg": { "description": "Message describing any unusual health reports.", "type": "string" }, "reportInterval": { "type": "string", "format": "google-duration", "description": "The interval at which the worker is sending health reports. The default value of 0 should be interpreted as the field is not being explicitly set by the worker." }, "vmBrokenCode": { "description": "Code to describe a specific reason, if known, that a VM has reported broken state.", "type": "string" }, "vmStartupTime": { "description": "The time the VM was booted.", "format": "google-datetime", "type": "string" }, "vmIsHealthy": { "description": "Whether the VM is currently healthy.", "type": "boolean" }, "pods": { "type": "array", "description": "The pods running on the worker. See: http://kubernetes.io/v1.1/docs/api-reference/v1/definitions.html#_v1_pod This field is used by the worker to send the status of the indvidual containers running on each worker.", "items": { "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object." } } }, "vmIsBroken": { "type": "boolean", "description": "Whether the VM is in a permanently broken state. Broken VMs should be abandoned or deleted ASAP to avoid assigning or completing any work." } }, "type": "object", "description": "WorkerHealthReport contains information about the health of a worker. The VM should be identified by the labels attached to the WorkerMessage that this health ping belongs to." }, "InstructionOutput": { "properties": { "originalName": { "description": "System-defined name for this output in the original workflow graph. Outputs that do not contribute to an original instruction do not set this.", "type": "string" }, "name": { "description": "The user-provided name of this output.", "type": "string" }, "systemName": { "description": "System-defined name of this output. Unique across the workflow.", "type": "string" }, "onlyCountKeyBytes": { "type": "boolean", "description": "For system-generated byte and mean byte metrics, certain instructions should only report the key size." }, "onlyCountValueBytes": { "type": "boolean", "description": "For system-generated byte and mean byte metrics, certain instructions should only report the value size." }, "codec": { "additionalProperties": { "type": "any", "description": "Properties of the object." }, "description": "The codec to use to encode data being written via this output.", "type": "object" } }, "description": "An output of an instruction.", "type": "object", "id": "InstructionOutput" }, "Package": { "id": "Package", "description": "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.", "type": "object", "properties": { "name": { "description": "The name of the package.", "type": "string" }, "location": { "type": "string", "description": "The resource to read the package from. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket} bucket.storage.googleapis.com/" }, "sha256": { "description": "Optional. The hex-encoded SHA256 checksum of the package. If the checksum is provided, the worker will verify the checksum of the package before using it. If the checksum does not match, the worker will fail to start.", "type": "string" } } }, "StreamingConfigTask": { "properties": { "userWorkerRunnerV1Settings": { "description": "Binary encoded proto to control runtime behavior of the java runner v1 user worker.", "type": "string", "format": "byte" }, "windmillServicePort": { "format": "int64", "type": "string", "description": "If present, the worker must use this port to communicate with Windmill Service dispatchers. Only applicable when windmill_service_endpoint is specified." }, "userStepToStateFamilyNameMap": { "description": "Map from user step names to state families.", "type": "object", "additionalProperties": { "type": "string" } }, "operationalLimits": { "$ref": "StreamingOperationalLimits", "description": "Operational limits for the streaming job. Can be used by the worker to validate outputs sent to the backend." }, "streamingEngineStateTagEncodingVersion": { "format": "int32", "description": "Optional. The state tag encoding format version for streaming engine jobs.", "type": "integer" }, "commitStreamChunkSizeBytes": { "description": "Chunk size for commit streams from the harness to windmill.", "format": "int64", "type": "string" }, "windmillServiceEndpoint": { "description": "If present, the worker must use this endpoint to communicate with Windmill Service dispatchers, otherwise the worker must continue to use whatever endpoint it had been using.", "type": "string" }, "userWorkerRunnerV2Settings": { "format": "byte", "description": "Binary encoded proto to control runtime behavior of the runner v2 user worker.", "type": "string" }, "getDataStreamChunkSizeBytes": { "format": "int64", "type": "string", "description": "Chunk size for get data streams from the harness to windmill." }, "streamingComputationConfigs": { "type": "array", "items": { "$ref": "StreamingComputationConfig" }, "description": "Set of computation configuration information." }, "maxWorkItemCommitBytes": { "description": "Maximum size for work item commit supported windmill storage layer.", "type": "string", "format": "int64" } }, "type": "object", "description": "A task that carries configuration information for streaming computations.", "id": "StreamingConfigTask" }, "GPUUsage": { "type": "object", "id": "GPUUsage", "description": "Information about the GPU usage on the worker.", "properties": { "timestamp": { "description": "Required. Timestamp of the measurement.", "format": "google-datetime", "type": "string" }, "utilization": { "$ref": "GPUUtilization", "description": "Required. Utilization info about the GPU." } } }, "Source": { "type": "object", "properties": { "doesNotNeedSplitting": { "description": "Setting this value to true hints to the framework that the source doesn't need splitting, and using SourceSplitRequest on it would yield SOURCE_SPLIT_OUTCOME_USE_CURRENT. E.g. a file splitter may set this to true when splitting a single file into a set of byte ranges of appropriate size, and set this to false when splitting a filepattern into individual files. However, for efficiency, a file splitter may decide to produce file subranges directly from the filepattern to avoid a splitting round-trip. See SourceSplitRequest for an overview of the splitting process. This field is meaningful only in the Source objects populated by the user (e.g. when filling in a DerivedSource). Source objects supplied by the framework to the user don't have this field populated.", "type": "boolean" }, "spec": { "description": "The source to read from, plus its parameters.", "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object." } }, "codec": { "additionalProperties": { "description": "Properties of the object.", "type": "any" }, "type": "object", "description": "The codec to use to decode data read from the source." }, "baseSpecs": { "description": "While splitting, sources may specify the produced bundles as differences against another source, in order to save backend-side memory and allow bigger jobs. For details, see SourceSplitRequest. To support this use case, the full set of parameters of the source is logically obtained by taking the latest explicitly specified value of each parameter in the order: base_specs (later items win), spec (overrides anything in base_specs).", "items": { "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object." } }, "type": "array" }, "metadata": { "$ref": "SourceMetadata", "description": "Optionally, metadata for this source can be supplied right away, avoiding a SourceGetMetadataOperation roundtrip (see SourceOperationRequest). This field is meaningful only in the Source objects populated by the user (e.g. when filling in a DerivedSource). Source objects supplied by the framework to the user don't have this field populated." } }, "description": "A source that records can be read and decoded from.", "id": "Source" }, "Histogram": { "id": "Histogram", "properties": { "bucketCounts": { "description": "Counts of values in each bucket. For efficiency, prefix and trailing buckets with count = 0 are elided. Buckets can store the full range of values of an unsigned long, with ULLONG_MAX falling into the 59th bucket with range [1e19, 2e19).", "type": "array", "items": { "format": "int64", "type": "string" } }, "firstBucketOffset": { "description": "Starting index of first stored bucket. The non-inclusive upper-bound of the ith bucket is given by: pow(10,(i-first_bucket_offset)/3) * (1,2,5)[(i-first_bucket_offset)%3]", "type": "integer", "format": "int32" } }, "description": "Histogram of value counts for a distribution. Buckets have an inclusive lower bound and exclusive upper bound and use \"1,2,5 bucketing\": The first bucket range is from [0,1) and all subsequent bucket boundaries are powers of ten multiplied by 1, 2, or 5. Thus, bucket boundaries are 0, 1, 2, 5, 10, 20, 50, 100, 200, 500, 1000, ... Negative values are not supported.", "type": "object" }, "MetricShortId": { "description": "The metric short id is returned to the user alongside an offset into ReportWorkItemStatusRequest", "properties": { "metricIndex": { "description": "The index of the corresponding metric in the ReportWorkItemStatusRequest. Required.", "type": "integer", "format": "int32" }, "shortId": { "type": "string", "description": "The service-generated short identifier for the metric.", "format": "int64" } }, "type": "object", "id": "MetricShortId" }, "MountedDataDisk": { "type": "object", "id": "MountedDataDisk", "description": "Describes mounted data disk.", "properties": { "dataDisk": { "description": "The name of the data disk. This name is local to the Google Cloud Platform project and uniquely identifies the disk within that project, for example \"myproject-1014-104817-4c2-harness-0-disk-1\".", "type": "string" } } }, "Linear": { "properties": { "start": { "description": "Lower bound of the first bucket.", "format": "double", "type": "number" }, "width": { "description": "Distance between bucket boundaries. Must be greater than 0.", "format": "double", "type": "number" }, "numberOfBuckets": { "description": "Must be greater than 0.", "type": "integer", "format": "int32" } }, "id": "Linear", "description": "Linear buckets with the following boundaries for indices in 0 to n-1. - i in [0, n-1]: [start + (i)*width, start + (i+1)*width)", "type": "object" }, "SourceGetMetadataRequest": { "description": "A request to compute the SourceMetadata of a Source.", "type": "object", "properties": { "source": { "$ref": "Source", "description": "Specification of the source whose metadata should be computed." } }, "id": "SourceGetMetadataRequest" }, "WorkItemServiceState": { "properties": { "completeWorkStatus": { "$ref": "Status", "description": "If set, a request to complete the work item with the given status. This will not be set to OK, unless supported by the specific kind of WorkItem. It can be used for the backend to indicate a WorkItem must terminate, e.g., for aborting work." }, "metricShortId": { "description": "The short ids that workers should use in subsequent metric updates. Workers should strive to use short ids whenever possible, but it is ok to request the short_id again if a worker lost track of it (e.g. if the worker is recovering from a crash). NOTE: it is possible that the response may have short ids for a subset of the metrics.", "type": "array", "items": { "$ref": "MetricShortId" } }, "nextReportIndex": { "description": "The index value to use for the next report sent by the worker. Note: If the report call fails for whatever reason, the worker should reuse this index for subsequent report attempts.", "format": "int64", "type": "string" }, "suggestedStopPosition": { "$ref": "Position", "description": "Obsolete, always empty.", "deprecated": true }, "splitRequest": { "$ref": "ApproximateSplitRequest", "description": "The progress point in the WorkItem where the Dataflow service suggests that the worker truncate the task." }, "hotKeyDetection": { "description": "A hot key is a symptom of poor data distribution in which there are enough elements mapped to a single key to impact pipeline performance. When present, this field includes metadata associated with any hot key.", "$ref": "HotKeyDetection" }, "leaseExpireTime": { "description": "Time at which the current lease will expire.", "type": "string", "format": "google-datetime" }, "harnessData": { "type": "object", "description": "Other data returned by the service, specific to the particular worker harness.", "additionalProperties": { "type": "any", "description": "Properties of the object." } }, "suggestedStopPoint": { "$ref": "ApproximateProgress", "description": "DEPRECATED in favor of split_request.", "deprecated": true }, "reportStatusInterval": { "format": "google-duration", "type": "string", "description": "New recommended reporting interval." } }, "description": "The Dataflow service's idea of the current state of a WorkItem being processed by a worker.", "type": "object", "id": "WorkItemServiceState" }, "ResolveConfigStoreSettingRequest": { "properties": {}, "id": "ResolveConfigStoreSettingRequest", "description": "Request message for ResolveConfigStoreSetting.", "type": "object" }, "AutoscalingEvent": { "properties": { "workerPool": { "description": "A short and friendly name for the worker pool this event refers to.", "type": "string" }, "eventType": { "enum": [ "TYPE_UNKNOWN", "TARGET_NUM_WORKERS_CHANGED", "CURRENT_NUM_WORKERS_CHANGED", "ACTUATION_FAILURE", "NO_CHANGE" ], "description": "The type of autoscaling event to report.", "enumDescriptions": [ "Default type for the enum. Value should never be returned.", "The TARGET_NUM_WORKERS_CHANGED type should be used when the target worker pool size has changed at the start of an actuation. An event should always be specified as TARGET_NUM_WORKERS_CHANGED if it reflects a change in the target_num_workers.", "The CURRENT_NUM_WORKERS_CHANGED type should be used when actual worker pool size has been changed, but the target_num_workers has not changed.", "The ACTUATION_FAILURE type should be used when we want to report an error to the user indicating why the current number of workers in the pool could not be changed. Displayed in the current status and history widgets.", "Used when we want to report to the user a reason why we are not currently adjusting the number of workers. Should specify both target_num_workers, current_num_workers and a decision_message." ], "type": "string" }, "description": { "description": "A message describing why the system decided to adjust the current number of workers, why it failed, or why the system decided to not make any changes to the number of workers.", "$ref": "StructuredMessage" }, "targetNumWorkers": { "description": "The target number of workers the worker pool wants to resize to use.", "type": "string", "format": "int64" }, "currentNumWorkers": { "format": "int64", "type": "string", "description": "The current number of workers the job has." }, "time": { "type": "string", "description": "The time this event was emitted to indicate a new target or current num_workers value.", "format": "google-datetime" } }, "id": "AutoscalingEvent", "type": "object", "description": "A structured message reporting an autoscaling decision made by the Dataflow service." }, "WorkerMessageCode": { "id": "WorkerMessageCode", "properties": { "code": { "type": "string", "description": "The code is a string intended for consumption by a machine that identifies the type of message being sent. Examples: 1. \"HARNESS_STARTED\" might be used to indicate the worker harness has started. 2. \"GCS_DOWNLOAD_ERROR\" might be used to indicate an error downloading a Cloud Storage file as part of the boot process of one of the worker containers. This is a string and not an enum to make it easy to add new codes without waiting for an API change." }, "parameters": { "type": "object", "additionalProperties": { "description": "Properties of the object.", "type": "any" }, "description": "Parameters contains specific information about the code. This is a struct to allow parameters of different types. Examples: 1. For a \"HARNESS_STARTED\" message parameters might provide the name of the worker and additional data like timing information. 2. For a \"GCS_DOWNLOAD_ERROR\" parameters might contain fields listing the Cloud Storage objects being downloaded and fields containing errors. In general complex data structures should be avoided. If a worker needs to send a specific and complicated data structure then please consider defining a new proto and adding it to the data oneof in WorkerMessageResponse. Conventions: Parameters should only be used for information that isn't typically passed as a label. hostname and other worker identifiers should almost always be passed as labels since they will be included on most messages." } }, "description": "A message code is used to report status and error messages to the service. The message codes are intended to be machine readable. The service will take care of translating these into user understandable messages if necessary. Example use cases: 1. Worker processes reporting successful startup. 2. Worker processes reporting specific errors (e.g. package staging failure).", "type": "object" }, "FlexTemplateRuntimeEnvironment": { "description": "The environment values to be set at runtime for flex template.", "properties": { "kmsKeyName": { "description": "Name for the Cloud KMS key for the job. Key format is: projects//locations//keyRings//cryptoKeys/", "type": "string" }, "additionalPipelineOptions": { "type": "array", "description": "Optional. Additional pipeline option flags for the job.", "items": { "type": "string" } }, "tempLocation": { "description": "The Cloud Storage path to use for temporary files. Must be a valid Cloud Storage URL, beginning with `gs://`.", "type": "string" }, "stagingLocation": { "type": "string", "description": "The Cloud Storage path for staging local files. Must be a valid Cloud Storage URL, beginning with `gs://`." }, "ipConfiguration": { "enumDescriptions": [ "The configuration is unknown, or unspecified.", "Workers should have public IP addresses.", "Workers should have private IP addresses." ], "type": "string", "description": "Configuration for VM IPs.", "enum": [ "WORKER_IP_UNSPECIFIED", "WORKER_IP_PUBLIC", "WORKER_IP_PRIVATE" ] }, "workerZone": { "type": "string", "description": "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." }, "dumpHeapOnOom": { "type": "boolean", "description": "If true, when processing time is spent almost entirely on garbage collection (GC), saves a heap dump before ending the thread or process. If false, ends the thread or process without saving a heap dump. Does not save a heap dump when the Java Virtual Machine (JVM) has an out of memory error during processing. The location of the heap file is either echoed back to the user, or the user is given the opportunity to download the heap file." }, "flexrsGoal": { "type": "string", "description": "Set FlexRS goal for the job. https://cloud.google.com/dataflow/docs/guides/flexrs", "enumDescriptions": [ "Run in the default mode.", "Optimize for lower execution time.", "Optimize for lower cost." ], "enum": [ "FLEXRS_UNSPECIFIED", "FLEXRS_SPEED_OPTIMIZED", "FLEXRS_COST_OPTIMIZED" ] }, "maxWorkers": { "type": "integer", "description": "The maximum number of Google Compute Engine instances to be made available to your pipeline during execution, from 1 to 1000.", "format": "int32" }, "additionalUserLabels": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Additional user labels to be specified for the job. Keys and values must follow the restrictions specified in the [labeling restrictions](https://cloud.google.com/compute/docs/labeling-resources#restrictions) page. An object containing a list of \"key\": value pairs. Example: { \"name\": \"wrench\", \"mass\": \"1kg\", \"count\": \"3\" }." }, "saveHeapDumpsToGcsPath": { "description": "Cloud Storage bucket (directory) to upload heap dumps to. Enabling this field implies that `dump_heap_on_oom` is set to true.", "type": "string" }, "autoscalingAlgorithm": { "type": "string", "description": "The algorithm to use for autoscaling", "enumDescriptions": [ "The algorithm is unknown, or unspecified.", "Disable autoscaling.", "Increase worker count over time to reduce job execution time." ], "enum": [ "AUTOSCALING_ALGORITHM_UNKNOWN", "AUTOSCALING_ALGORITHM_NONE", "AUTOSCALING_ALGORITHM_BASIC" ] }, "numWorkers": { "type": "integer", "format": "int32", "description": "The initial number of Google Compute Engine instances for the job." }, "enableLauncherVmSerialPortLogging": { "description": "If true serial port logging will be enabled for the launcher VM.", "type": "boolean" }, "launcherMachineType": { "description": "The machine type to use for launching the job. If not set, Dataflow will select a default machine type.", "type": "string" }, "zone": { "description": "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.", "type": "string" }, "machineType": { "type": "string", "description": "The machine type to use for the job. Defaults to the value from the template if not specified." }, "diskSizeGb": { "description": "Worker disk size, in gigabytes.", "format": "int32", "type": "integer" }, "serviceAccountEmail": { "type": "string", "description": "The email address of the service account to run the job as." }, "subnetwork": { "description": "Subnetwork to which VMs will be assigned, if desired. You can specify a subnetwork using either a complete URL or an abbreviated path. Expected to be of the form \"https://www.googleapis.com/compute/v1/projects/HOST_PROJECT_ID/regions/REGION/subnetworks/SUBNETWORK\" or \"regions/REGION/subnetworks/SUBNETWORK\". If the subnetwork is located in a Shared VPC network, you must use the complete URL.", "type": "string" }, "workerRegion": { "description": "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.", "type": "string" }, "enableStreamingEngine": { "type": "boolean", "description": "Whether to enable Streaming Engine for the job." }, "network": { "description": "Network to which VMs will be assigned. If empty or unspecified, the service will use the network \"default\".", "type": "string" }, "sdkContainerImage": { "description": "Docker registry location of container image to use for the 'worker harness. Default is the container for the version of the SDK. Note this field is only valid for portable pipelines.", "type": "string" }, "additionalExperiments": { "description": "Additional experiment flags for the job.", "type": "array", "items": { "type": "string" } }, "streamingMode": { "type": "string", "enumDescriptions": [ "Run in the default mode.", "In this mode, message deduplication is performed against persistent state to make sure each message is processed and committed to storage exactly once.", "Message deduplication is not performed. Messages might be processed multiple times, and the results are applied multiple times. Note: Setting this value also enables Streaming Engine and Streaming Engine resource-based billing." ], "enum": [ "STREAMING_MODE_UNSPECIFIED", "STREAMING_MODE_EXACTLY_ONCE", "STREAMING_MODE_AT_LEAST_ONCE" ], "description": "Optional. Specifies the Streaming Engine message processing guarantees. Reduces cost and latency but might result in duplicate messages committed to storage. Designed to run simple mapping streaming ETL jobs at the lowest cost. For example, Change Data Capture (CDC) to BigQuery is a canonical use case. For more information, see [Set the pipeline streaming mode](https://cloud.google.com/dataflow/docs/guides/streaming-modes)." } }, "id": "FlexTemplateRuntimeEnvironment", "type": "object" }, "SourceFork": { "id": "SourceFork", "description": "DEPRECATED in favor of DynamicSourceSplit.", "properties": { "primary": { "$ref": "SourceSplitShard", "description": "DEPRECATED" }, "primarySource": { "description": "DEPRECATED", "$ref": "DerivedSource" }, "residualSource": { "description": "DEPRECATED", "$ref": "DerivedSource" }, "residual": { "$ref": "SourceSplitShard", "description": "DEPRECATED" } }, "type": "object" }, "WorkItemStatus": { "description": "Conveys a worker's progress through the work described by a WorkItem.", "type": "object", "id": "WorkItemStatus", "properties": { "requestedLeaseDuration": { "type": "string", "format": "google-duration", "description": "Amount of time the worker requests for its lease." }, "progress": { "deprecated": true, "description": "DEPRECATED in favor of reported_progress.", "$ref": "ApproximateProgress" }, "stopPosition": { "description": "A worker may split an active map task in two parts, \"primary\" and \"residual\", continuing to process the primary part and returning the residual part into the pool of available work. This event is called a \"dynamic split\" and is critical to the dynamic work rebalancing feature. The two obtained sub-tasks are called \"parts\" of the split. The parts, if concatenated, must represent the same input as would be read by the current task if the split did not happen. The exact way in which the original task is decomposed into the two parts is specified either as a position demarcating them (stop_position), or explicitly as two DerivedSources, if this task consumes a user-defined source type (dynamic_source_split). The \"current\" task is adjusted as a result of the split: after a task with range [A, B) sends a stop_position update at C, its range is considered to be [A, C), e.g.: * Progress should be interpreted relative to the new range, e.g. \"75% completed\" means \"75% of [A, C) completed\" * The worker should interpret proposed_stop_position relative to the new range, e.g. \"split at 68%\" should be interpreted as \"split at 68% of [A, C)\". * If the worker chooses to split again using stop_position, only stop_positions in [A, C) will be accepted. * Etc. dynamic_source_split has similar semantics: e.g., if a task with source S splits using dynamic_source_split into {P, R} (where P and R must be together equivalent to S), then subsequent progress and proposed_stop_position should be interpreted relative to P, and in a potential subsequent dynamic_source_split into {P', R'}, P' and R' must be together equivalent to P, etc.", "$ref": "Position" }, "dynamicSourceSplit": { "$ref": "DynamicSourceSplit", "description": "See documentation of stop_position." }, "counterUpdates": { "items": { "$ref": "CounterUpdate" }, "type": "array", "description": "Worker output counters for this WorkItem." }, "errors": { "items": { "$ref": "Status" }, "type": "array", "description": "Specifies errors which occurred during processing. If errors are provided, and completed = true, then the WorkItem is considered to have failed." }, "sourceFork": { "deprecated": true, "description": "DEPRECATED in favor of dynamic_source_split.", "$ref": "SourceFork" }, "sourceOperationResponse": { "description": "If the work item represented a SourceOperationRequest, and the work is completed, contains the result of the operation.", "$ref": "SourceOperationResponse" }, "totalThrottlerWaitTimeSeconds": { "type": "number", "format": "double", "description": "Total time the worker spent being throttled by external systems." }, "workItemId": { "description": "Identifies the WorkItem.", "type": "string" }, "metricUpdates": { "deprecated": true, "items": { "$ref": "MetricUpdate" }, "description": "DEPRECATED in favor of counter_updates.", "type": "array" }, "reportIndex": { "type": "string", "format": "int64", "description": "The report index. When a WorkItem is leased, the lease will contain an initial report index. When a WorkItem's status is reported to the system, the report should be sent with that report index, and the response will contain the index the worker should use for the next report. Reports received with unexpected index values will be rejected by the service. In order to preserve idempotency, the worker should not alter the contents of a report, even if the worker must submit the same report multiple times before getting back a response. The worker should not submit a subsequent report until the response for the previous report had been received from the service." }, "completed": { "description": "True if the WorkItem was completed (successfully or unsuccessfully).", "type": "boolean" }, "reportedProgress": { "description": "The worker's progress through this WorkItem.", "$ref": "ApproximateReportedProgress" } } }, "Sdk": { "id": "Sdk", "type": "object", "properties": { "sdkId": { "description": "The SDK harness id.", "type": "string" }, "stacks": { "description": "The stacktraces for the processes running on the SDK harness.", "items": { "$ref": "Stack" }, "type": "array" } }, "description": "A structured representation of an SDK." }, "Point": { "id": "Point", "description": "A point in the timeseries.", "type": "object", "properties": { "time": { "type": "string", "format": "google-datetime", "description": "The timestamp of the point." }, "value": { "type": "number", "format": "double", "description": "The value of the point." } } }, "NameAndKind": { "properties": { "name": { "type": "string", "description": "Name of the counter." }, "kind": { "enumDescriptions": [ "Counter aggregation kind was not set.", "Aggregated value is the sum of all contributed values.", "Aggregated value is the max of all contributed values.", "Aggregated value is the min of all contributed values.", "Aggregated value is the mean of all contributed values.", "Aggregated value represents the logical 'or' of all contributed values.", "Aggregated value represents the logical 'and' of all contributed values.", "Aggregated value is a set of unique contributed values.", "Aggregated value captures statistics about a distribution.", "Aggregated value tracks the latest value of a variable." ], "description": "Counter aggregation kind.", "type": "string", "enum": [ "INVALID", "SUM", "MAX", "MIN", "MEAN", "OR", "AND", "SET", "DISTRIBUTION", "LATEST_VALUE" ] } }, "id": "NameAndKind", "type": "object", "description": "Basic metadata about a counter." }, "DataSamplingConfig": { "type": "object", "properties": { "behaviors": { "description": "List of given sampling behaviors to enable. For example, specifying behaviors = [ALWAYS_ON] samples in-flight elements but does not sample exceptions. Can be used to specify multiple behaviors like, behaviors = [ALWAYS_ON, EXCEPTIONS] for specifying periodic sampling and exception sampling. If DISABLED is in the list, then sampling will be disabled and ignore the other given behaviors. Ordering does not matter.", "type": "array", "items": { "enum": [ "DATA_SAMPLING_BEHAVIOR_UNSPECIFIED", "DISABLED", "ALWAYS_ON", "EXCEPTIONS" ], "enumDescriptions": [ "If given, has no effect on sampling behavior. Used as an unknown or unset sentinel value.", "When given, disables element sampling. Has same behavior as not setting the behavior.", "When given, enables sampling in-flight from all PCollections.", "When given, enables sampling input elements when a user-defined DoFn causes an exception." ], "type": "string" } } }, "id": "DataSamplingConfig", "description": "Configuration options for sampling elements." }, "Job": { "description": "Defines a job to be run by the Cloud Dataflow service. Do not enter confidential information when you supply string values using the API.", "type": "object", "properties": { "runtimeUpdatableParams": { "$ref": "RuntimeUpdatableParams", "description": "This field may ONLY be modified at runtime using the projects.jobs.update method to adjust job behavior. This field has no effect when specified at job creation." }, "projectId": { "description": "The ID of the Google Cloud project that the job belongs to.", "type": "string" }, "steps": { "description": "Exactly one of step or steps_location should be specified. The top-level steps that constitute the entire job. Only retrieved with JOB_VIEW_ALL.", "type": "array", "items": { "$ref": "Step" } }, "replaceJobId": { "description": "If this job is an update of an existing job, this field is the job ID of the job it replaced. When sending a `CreateJobRequest`, you can update a job by specifying it here. The job named here is stopped, and its intermediate state is transferred to this job.", "type": "string" }, "environment": { "description": "Optional. The environment for the job.", "$ref": "Environment" }, "transformNameMapping": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Optional. The map of transform name prefixes of the job to be replaced to the corresponding name prefixes of the new job." }, "type": { "type": "string", "description": "Optional. The type of Dataflow job.", "enum": [ "JOB_TYPE_UNKNOWN", "JOB_TYPE_BATCH", "JOB_TYPE_STREAMING" ], "enumDescriptions": [ "The type of the job is unspecified, or unknown.", "A batch job with a well-defined end point: data is read, data is processed, data is written, and the job is done.", "A continuously streaming job with no end: data is read, processed, and written continuously." ] }, "pipelineDescription": { "description": "Preliminary field: The format of this data may change at any time. A description of the user pipeline and stages through which it is executed. Created by Cloud Dataflow service. Only retrieved with JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.", "$ref": "PipelineDescription" }, "name": { "type": "string", "description": "Optional. The user-specified Dataflow job name. Only one active job with a given name can exist in a project within one region at any given time. Jobs in different regions can have the same name. If a caller attempts to create a job with the same name as an active job that already exists, the attempt returns the existing job. The name must match the regular expression `[a-z]([-a-z0-9]{0,1022}[a-z0-9])?`" }, "clientRequestId": { "description": "The client's unique identifier of the job, re-used across retried attempts. If this field is set, the service will ensure its uniqueness. The request to create a job will fail if the service has knowledge of a previously submitted job with the same client's ID and job name. The caller may use this field to ensure idempotence of job creation across retried attempts to create a job. By default, the field is empty and, in that case, the service ignores it.", "type": "string" }, "id": { "description": "The unique ID of this job. This field is set by the Dataflow service when the job is created, and is immutable for the life of the job.", "type": "string" }, "createTime": { "type": "string", "format": "google-datetime", "description": "The timestamp when the job was initially created. Immutable and set by the Cloud Dataflow service." }, "startTime": { "format": "google-datetime", "type": "string", "description": "The timestamp when the job was started (transitioned to JOB_STATE_PENDING). Flexible resource scheduling jobs are started with some delay after job creation, so start_time is unset before start and is updated when the job is started by the Cloud Dataflow service. For other jobs, start_time always equals to create_time and is immutable and set by the Cloud Dataflow service." }, "createdFromSnapshotId": { "description": "If this is specified, the job's initial state is populated from the given snapshot.", "type": "string" }, "location": { "description": "Optional. The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "type": "string" }, "labels": { "type": "object", "additionalProperties": { "type": "string" }, "description": "User-defined labels for this job. The labels map can contain no more than 64 entries. Entries of the labels map are UTF8 strings that comply with the following restrictions: * 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 \u003c= 128 bytes in size." }, "requestedState": { "type": "string", "enum": [ "JOB_STATE_UNKNOWN", "JOB_STATE_STOPPED", "JOB_STATE_RUNNING", "JOB_STATE_DONE", "JOB_STATE_FAILED", "JOB_STATE_CANCELLED", "JOB_STATE_UPDATED", "JOB_STATE_DRAINING", "JOB_STATE_DRAINED", "JOB_STATE_PENDING", "JOB_STATE_CANCELLING", "JOB_STATE_QUEUED", "JOB_STATE_RESOURCE_CLEANING_UP", "JOB_STATE_PAUSING", "JOB_STATE_PAUSED" ], "description": "The job's requested state. Applies to `UpdateJob` requests. Set `requested_state` with `UpdateJob` requests to switch between the states `JOB_STATE_STOPPED` and `JOB_STATE_RUNNING`. You can also use `UpdateJob` requests to change a job's state from `JOB_STATE_RUNNING` to `JOB_STATE_CANCELLED`, `JOB_STATE_DONE`, or `JOB_STATE_DRAINED`. These states irrevocably terminate the job if it hasn't already reached a terminal state. This field has no effect on `CreateJob` requests.", "enumDescriptions": [ "The job's run state isn't specified.", "`JOB_STATE_STOPPED` indicates that the job has not yet started to run.", "`JOB_STATE_RUNNING` indicates that the job is currently running.", "`JOB_STATE_DONE` indicates that the job has successfully completed. This is a terminal job state. This state may be set by the Cloud Dataflow service, as a transition from `JOB_STATE_RUNNING`. It may also be set via a Cloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal state.", "`JOB_STATE_FAILED` indicates that the job has failed. This is a terminal job state. This state may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.", "`JOB_STATE_CANCELLED` indicates that the job has been explicitly cancelled. This is a terminal job state. This state may only be set via a Cloud Dataflow `UpdateJob` call, and only if the job has not yet reached another terminal state.", "`JOB_STATE_UPDATED` indicates that the job was successfully updated, meaning that this job was stopped and another job was started, inheriting state from this one. This is a terminal job state. This state may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.", "`JOB_STATE_DRAINING` indicates that the job is in the process of draining. A draining job has stopped pulling from its input sources and is processing any data that remains in-flight. This state may be set via a Cloud Dataflow `UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs that are draining may only transition to `JOB_STATE_DRAINED`, `JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.", "`JOB_STATE_DRAINED` indicates that the job has been drained. A drained job terminated by stopping pulling from its input sources and processing any data that remained in-flight when draining was requested. This state is a terminal state, may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_DRAINING`.", "`JOB_STATE_PENDING` indicates that the job has been created but is not yet running. Jobs that are pending may only transition to `JOB_STATE_RUNNING`, or `JOB_STATE_FAILED`.", "`JOB_STATE_CANCELLING` indicates that the job has been explicitly cancelled and is in the process of stopping. Jobs that are cancelling may only transition to `JOB_STATE_CANCELLED` or `JOB_STATE_FAILED`.", "`JOB_STATE_QUEUED` indicates that the job has been created but is being delayed until launch. Jobs that are queued may only transition to `JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`.", "`JOB_STATE_RESOURCE_CLEANING_UP` indicates that the batch job's associated resources are currently being cleaned up after a successful run. Currently, this is an opt-in feature, please reach out to Cloud support team if you are interested.", "`JOB_STATE_PAUSING` indicates that the job is in the process of pausing. A pausing job will stop processing, archive in-flight Shuffle data, and transition to `JOB_STATE_PAUSED`. Jobs in this state can transition to `JOB_STATE_CANCELLING` if cancellation is requested, or can transition back to `JOB_STATE_RUNNING` if the pause fails to complete.", "`JOB_STATE_PAUSED` indicates that the job is not currently processing. Jobs in this state can transition back to `JOB_STATE_RUNNING` to continue processing where they left off, or can transition to `JOB_STATE_CANCELLING` if cancellation is requested." ] }, "stepsLocation": { "type": "string", "description": "The Cloud Storage location where the steps are stored." }, "executionInfo": { "description": "Deprecated.", "$ref": "JobExecutionInfo" }, "jobMetadata": { "description": "This field is populated by the Dataflow service to support filtering jobs by the metadata values provided here. Populated for ListJobs and all GetJob views SUMMARY and higher.", "$ref": "JobMetadata" }, "satisfiesPzs": { "description": "Reserved for future use. This field is set only in responses from the server; it is ignored if it is set in any requests.", "type": "boolean" }, "pausable": { "readOnly": true, "description": "Output only. Indicates whether the job can be paused.", "type": "boolean" }, "serviceResources": { "$ref": "ServiceResources", "description": "Output only. Resources used by the Dataflow Service to run the job.", "readOnly": true }, "stageStates": { "type": "array", "items": { "$ref": "ExecutionStageState" }, "description": "This field may be mutated by the Cloud Dataflow service; callers cannot mutate it." }, "satisfiesPzi": { "type": "boolean", "description": "Output only. Reserved for future use. This field is set only in responses from the server; it is ignored if it is set in any requests.", "readOnly": true }, "replacedByJobId": { "description": "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.", "type": "string" }, "currentState": { "enumDescriptions": [ "The job's run state isn't specified.", "`JOB_STATE_STOPPED` indicates that the job has not yet started to run.", "`JOB_STATE_RUNNING` indicates that the job is currently running.", "`JOB_STATE_DONE` indicates that the job has successfully completed. This is a terminal job state. This state may be set by the Cloud Dataflow service, as a transition from `JOB_STATE_RUNNING`. It may also be set via a Cloud Dataflow `UpdateJob` call, if the job has not yet reached a terminal state.", "`JOB_STATE_FAILED` indicates that the job has failed. This is a terminal job state. This state may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.", "`JOB_STATE_CANCELLED` indicates that the job has been explicitly cancelled. This is a terminal job state. This state may only be set via a Cloud Dataflow `UpdateJob` call, and only if the job has not yet reached another terminal state.", "`JOB_STATE_UPDATED` indicates that the job was successfully updated, meaning that this job was stopped and another job was started, inheriting state from this one. This is a terminal job state. This state may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.", "`JOB_STATE_DRAINING` indicates that the job is in the process of draining. A draining job has stopped pulling from its input sources and is processing any data that remains in-flight. This state may be set via a Cloud Dataflow `UpdateJob` call, but only as a transition from `JOB_STATE_RUNNING`. Jobs that are draining may only transition to `JOB_STATE_DRAINED`, `JOB_STATE_CANCELLED`, or `JOB_STATE_FAILED`.", "`JOB_STATE_DRAINED` indicates that the job has been drained. A drained job terminated by stopping pulling from its input sources and processing any data that remained in-flight when draining was requested. This state is a terminal state, may only be set by the Cloud Dataflow service, and only as a transition from `JOB_STATE_DRAINING`.", "`JOB_STATE_PENDING` indicates that the job has been created but is not yet running. Jobs that are pending may only transition to `JOB_STATE_RUNNING`, or `JOB_STATE_FAILED`.", "`JOB_STATE_CANCELLING` indicates that the job has been explicitly cancelled and is in the process of stopping. Jobs that are cancelling may only transition to `JOB_STATE_CANCELLED` or `JOB_STATE_FAILED`.", "`JOB_STATE_QUEUED` indicates that the job has been created but is being delayed until launch. Jobs that are queued may only transition to `JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`.", "`JOB_STATE_RESOURCE_CLEANING_UP` indicates that the batch job's associated resources are currently being cleaned up after a successful run. Currently, this is an opt-in feature, please reach out to Cloud support team if you are interested.", "`JOB_STATE_PAUSING` indicates that the job is in the process of pausing. A pausing job will stop processing, archive in-flight Shuffle data, and transition to `JOB_STATE_PAUSED`. Jobs in this state can transition to `JOB_STATE_CANCELLING` if cancellation is requested, or can transition back to `JOB_STATE_RUNNING` if the pause fails to complete.", "`JOB_STATE_PAUSED` indicates that the job is not currently processing. Jobs in this state can transition back to `JOB_STATE_RUNNING` to continue processing where they left off, or can transition to `JOB_STATE_CANCELLING` if cancellation is requested." ], "type": "string", "enum": [ "JOB_STATE_UNKNOWN", "JOB_STATE_STOPPED", "JOB_STATE_RUNNING", "JOB_STATE_DONE", "JOB_STATE_FAILED", "JOB_STATE_CANCELLED", "JOB_STATE_UPDATED", "JOB_STATE_DRAINING", "JOB_STATE_DRAINED", "JOB_STATE_PENDING", "JOB_STATE_CANCELLING", "JOB_STATE_QUEUED", "JOB_STATE_RESOURCE_CLEANING_UP", "JOB_STATE_PAUSING", "JOB_STATE_PAUSED" ], "description": "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 might be mutated by the Dataflow service; callers cannot mutate it." }, "tempFiles": { "description": "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. No duplicates are allowed. No file patterns are supported. The supported files are: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}", "items": { "type": "string" }, "type": "array" }, "currentStateTime": { "type": "string", "format": "google-datetime", "description": "The timestamp associated with the current state." } }, "id": "Job" }, "ParallelInstruction": { "description": "Describes a particular operation comprising a MapTask.", "id": "ParallelInstruction", "properties": { "systemName": { "type": "string", "description": "System-defined name of this operation. Unique across the workflow." }, "name": { "description": "User-provided name of this operation.", "type": "string" }, "parDo": { "description": "Additional information for ParDo instructions.", "$ref": "ParDoInstruction" }, "partialGroupByKey": { "$ref": "PartialGroupByKeyInstruction", "description": "Additional information for PartialGroupByKey instructions." }, "flatten": { "$ref": "FlattenInstruction", "description": "Additional information for Flatten instructions." }, "write": { "$ref": "WriteInstruction", "description": "Additional information for Write instructions." }, "originalName": { "description": "System-defined name for the operation in the original workflow graph.", "type": "string" }, "read": { "$ref": "ReadInstruction", "description": "Additional information for Read instructions." }, "outputs": { "description": "Describes the outputs of the instruction.", "items": { "$ref": "InstructionOutput" }, "type": "array" } }, "type": "object" }, "SnapshotJobRequest": { "id": "SnapshotJobRequest", "description": "Request to create a snapshot of a job.", "type": "object", "properties": { "ttl": { "format": "google-duration", "type": "string", "description": "TTL for the snapshot." }, "snapshotSources": { "type": "boolean", "description": "If true, perform snapshots for sources which support this." }, "location": { "description": "The location that contains this job.", "type": "string" }, "description": { "description": "User specified description of the snapshot. Maybe empty.", "type": "string" } } }, "DistributionUpdate": { "type": "object", "properties": { "sumOfSquares": { "type": "number", "description": "Use a double since the sum of squares is likely to overflow int64.", "format": "double" }, "sum": { "description": "Use an int64 since we'd prefer the added precision. If overflow is a common problem we can detect it and use an additional int64 or a double.", "$ref": "SplitInt64" }, "max": { "description": "The maximum value present in the distribution.", "$ref": "SplitInt64" }, "min": { "description": "The minimum value present in the distribution.", "$ref": "SplitInt64" }, "histogram": { "$ref": "Histogram", "description": "(Optional) Histogram of value counts for the distribution." }, "count": { "description": "The count of the number of elements present in the distribution.", "$ref": "SplitInt64" } }, "id": "DistributionUpdate", "description": "A metric value representing a distribution." }, "Environment": { "type": "object", "id": "Environment", "description": "Describes the environment in which a Dataflow Job runs.", "properties": { "internalExperiments": { "type": "object", "description": "Experimental settings.", "additionalProperties": { "description": "Properties of the object. Contains field @type with type URL.", "type": "any" } }, "streamingMode": { "enum": [ "STREAMING_MODE_UNSPECIFIED", "STREAMING_MODE_EXACTLY_ONCE", "STREAMING_MODE_AT_LEAST_ONCE" ], "enumDescriptions": [ "Run in the default mode.", "In this mode, message deduplication is performed against persistent state to make sure each message is processed and committed to storage exactly once.", "Message deduplication is not performed. Messages might be processed multiple times, and the results are applied multiple times. Note: Setting this value also enables Streaming Engine and Streaming Engine resource-based billing." ], "type": "string", "description": "Optional. Specifies the Streaming Engine message processing guarantees. Reduces cost and latency but might result in duplicate messages committed to storage. Designed to run simple mapping streaming ETL jobs at the lowest cost. For example, Change Data Capture (CDC) to BigQuery is a canonical use case. For more information, see [Set the pipeline streaming mode](https://cloud.google.com/dataflow/docs/guides/streaming-modes)." }, "userAgent": { "description": "Optional. A description of the process that generated the request.", "additionalProperties": { "type": "any", "description": "Properties of the object." }, "type": "object" }, "experiments": { "description": "The list of experiments to enable. This field should be used for SDK related experiments and not for service related experiments. The proper field for service related experiments is service_options.", "type": "array", "items": { "type": "string" } }, "dataset": { "description": "Optional. The dataset for the current project where various workflow related tables are stored. The supported resource type is: Google BigQuery: bigquery.googleapis.com/{dataset}", "type": "string" }, "useStreamingEngineResourceBasedBilling": { "type": "boolean", "description": "Output only. Whether the job uses the Streaming Engine resource-based billing model.", "readOnly": true }, "sdkPipelineOptions": { "type": "object", "description": "The Cloud Dataflow SDK pipeline options specified by the user. These options are passed through the service and are used to recreate the SDK pipeline options on the worker in a language agnostic and platform independent way.", "additionalProperties": { "description": "Properties of the object.", "type": "any" } }, "version": { "type": "object", "additionalProperties": { "description": "Properties of the object.", "type": "any" }, "description": "A structure describing which components and their versions of the service are required in order to run the job." }, "workerZone": { "type": "string", "description": "Optional. 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." }, "serviceKmsKeyName": { "description": "Optional. If set, contains the Cloud KMS key identifier used to encrypt data at rest, AKA a Customer Managed Encryption Key (CMEK). Format: projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY", "type": "string" }, "usePublicIps": { "type": "boolean", "description": "Optional. True when any worker pool that uses public IPs is present." }, "clusterManagerApiService": { "description": "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\".", "type": "string" }, "serviceAccountEmail": { "description": "Optional. Identity to run virtual machines as. Defaults to the default account.", "type": "string" }, "shuffleMode": { "description": "Output only. The shuffle mode used for the job.", "enum": [ "SHUFFLE_MODE_UNSPECIFIED", "VM_BASED", "SERVICE_BASED" ], "type": "string", "readOnly": true, "enumDescriptions": [ "Shuffle mode information is not available.", "Shuffle is done on the worker VMs.", "Shuffle is done on the service side." ] }, "debugOptions": { "description": "Optional. Any debugging options to be supplied to the job.", "$ref": "DebugOptions" }, "flexResourceSchedulingGoal": { "type": "string", "description": "Optional. Which Flexible Resource Scheduling mode to run in.", "enumDescriptions": [ "Run in the default mode.", "Optimize for lower execution time.", "Optimize for lower cost." ], "enum": [ "FLEXRS_UNSPECIFIED", "FLEXRS_SPEED_OPTIMIZED", "FLEXRS_COST_OPTIMIZED" ] }, "serviceOptions": { "description": "Optional. The list of service options to enable. This field should be used for service related experiments only. These experiments, when graduating to GA, should be replaced by dedicated fields or become default (i.e. always on).", "items": { "type": "string" }, "type": "array" }, "tempStoragePrefix": { "description": "The prefix of the resources the system should use for temporary storage. The system will append the suffix \"/temp-{JOBNAME} to this resource prefix, where {JOBNAME} is the value of the job_name field. The resulting bucket and object prefix is used as the prefix of the resources used to store temporary data needed during the job execution. NOTE: This will override the value in taskrunner_settings. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}", "type": "string" }, "workerRegion": { "type": "string", "description": "Optional. The Compute Engine region (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in which worker processing should occur, e.g. \"us-west1\". Mutually exclusive with worker_zone. If neither worker_region nor worker_zone is specified, default to the control plane's region." }, "workerPools": { "items": { "$ref": "WorkerPool" }, "description": "The worker pools. At least one \"harness\" worker pool must be specified in order for the job to have workers.", "type": "array" } } }, "MetricValue": { "id": "MetricValue", "description": "The value of a metric along with its name and labels.", "type": "object", "properties": { "metricLabels": { "type": "object", "description": "Optional. Set of metric labels for this metric.", "additionalProperties": { "type": "string" } }, "valueGauge64": { "description": "Non-cumulative int64 value of this metric.", "$ref": "DataflowGaugeValue" }, "valueInt64": { "description": "Integer value of this metric.", "type": "string", "format": "int64" }, "valueHistogram": { "description": "Histogram value of this metric.", "$ref": "DataflowHistogramValue" }, "metric": { "type": "string", "description": "Base name for this metric." } } }, "JobExecutionStageInfo": { "id": "JobExecutionStageInfo", "description": "Contains information about how a particular google.dataflow.v1beta3.Step will be executed.", "properties": { "stepName": { "items": { "type": "string" }, "type": "array", "description": "The steps associated with the execution stage. Note that stages may have several steps, and that a given step might be run by more than one stage." } }, "type": "object" }, "LaunchFlexTemplateParameter": { "description": "Launch FlexTemplate Parameter.", "properties": { "containerSpec": { "description": "Spec about the container image to launch.", "$ref": "ContainerSpec" }, "containerSpecGcsPath": { "description": "Cloud Storage path to a file with json serialized ContainerSpec as content.", "type": "string" }, "update": { "type": "boolean", "description": "Set this to true if you are sending a request to update a running streaming job. When set, the job name should be the same as the running job." }, "environment": { "$ref": "FlexTemplateRuntimeEnvironment", "description": "The runtime environment for the FlexTemplate job" }, "launchOptions": { "type": "object", "description": "Launch options for this flex template job. This is a common set of options across languages and templates. This should not be used to pass job parameters.", "additionalProperties": { "type": "string" } }, "transformNameMappings": { "additionalProperties": { "type": "string" }, "description": "Use this to pass transform_name_mappings for streaming update jobs. Ex:{\"oldTransformName\":\"newTransformName\",...}'", "type": "object" }, "parameters": { "additionalProperties": { "type": "string" }, "description": "The parameters for FlexTemplate. Ex. {\"num_workers\":\"5\"}", "type": "object" }, "jobName": { "type": "string", "description": "Required. The job name to use for the created job. For update job request, job name should be same as the existing running job." } }, "type": "object", "id": "LaunchFlexTemplateParameter" }, "FailedLocation": { "properties": { "name": { "type": "string", "description": "The name of the [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that failed to respond." } }, "description": "Indicates which [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) failed to respond to a request for data.", "id": "FailedLocation", "type": "object" }, "SendWorkerMessagesResponse": { "id": "SendWorkerMessagesResponse", "properties": { "workerMessageResponses": { "type": "array", "description": "The servers response to the worker messages.", "items": { "$ref": "WorkerMessageResponse" } } }, "description": "The response to the worker messages.", "type": "object" }, "SeqMapTaskOutputInfo": { "id": "SeqMapTaskOutputInfo", "description": "Information about an output of a SeqMapTask.", "type": "object", "properties": { "tag": { "type": "string", "description": "The id of the TupleTag the user code will tag the output value by." }, "sink": { "$ref": "Sink", "description": "The sink to write the output value to." } } }, "Stack": { "description": "A structuredstacktrace for a process running on the worker.", "id": "Stack", "type": "object", "properties": { "threadCount": { "type": "integer", "format": "int32", "description": "With java thread dumps we may get collapsed stacks e.g., N threads in stack \"\". Instead of having to copy over the same stack trace N times, this int field captures this." }, "stackContent": { "description": "The raw stack trace.", "type": "string" }, "threadState": { "type": "string", "description": "The state of the thread. For example, \"WAITING\"." }, "timestamp": { "format": "google-datetime", "type": "string", "description": "Timestamp at which the stack was captured." }, "threadName": { "description": "Thread name. For example, \"CommitThread-0,10,main\"", "type": "string" } } }, "SendWorkerMessagesRequest": { "description": "A request for sending worker messages to the service.", "type": "object", "properties": { "workerMessages": { "description": "The WorkerMessages to send.", "type": "array", "items": { "$ref": "WorkerMessage" } }, "location": { "type": "string", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job." } }, "id": "SendWorkerMessagesRequest" }, "HotKeyInfo": { "type": "object", "description": "Information about a hot key.", "id": "HotKeyInfo", "properties": { "hotKeyAge": { "type": "string", "description": "The age of the hot key measured from when it was first detected.", "format": "google-duration" }, "key": { "description": "A detected hot key that is causing limited parallelism. This field will be populated only if the following flag is set to true: \"--enable_hot_key_logging\".", "type": "string" }, "keyTruncated": { "type": "boolean", "description": "If true, then the above key is truncated and cannot be deserialized. This occurs if the key above is populated and the key size is \u003e5MB." } } }, "SourceSplitResponse": { "properties": { "outcome": { "description": "Indicates whether splitting happened and produced a list of bundles. If this is USE_CURRENT_SOURCE_AS_IS, the current source should be processed \"as is\" without splitting. \"bundles\" is ignored in this case. If this is SPLITTING_HAPPENED, then \"bundles\" contains a list of bundles into which the source was split.", "type": "string", "enum": [ "SOURCE_SPLIT_OUTCOME_UNKNOWN", "SOURCE_SPLIT_OUTCOME_USE_CURRENT", "SOURCE_SPLIT_OUTCOME_SPLITTING_HAPPENED" ], "enumDescriptions": [ "The source split outcome is unknown, or unspecified.", "The current source should be processed \"as is\" without splitting.", "Splitting produced a list of bundles." ] }, "bundles": { "type": "array", "description": "If outcome is SPLITTING_HAPPENED, then this is a list of bundles into which the source was split. Otherwise this field is ignored. This list can be empty, which means the source represents an empty input.", "items": { "$ref": "DerivedSource" } }, "shards": { "description": "DEPRECATED in favor of bundles.", "type": "array", "items": { "$ref": "SourceSplitShard" }, "deprecated": true } }, "type": "object", "description": "The response to a SourceSplitRequest.", "id": "SourceSplitResponse" }, "WorkerMessageResponse": { "id": "WorkerMessageResponse", "type": "object", "description": "A worker_message response allows the server to pass information to the sender.", "properties": { "workerMetricsResponse": { "$ref": "ResourceUtilizationReportResponse", "description": "Service's response to reporting worker metrics (currently empty)." }, "workerShutdownNoticeResponse": { "description": "Service's response to shutdown notice (currently empty).", "$ref": "WorkerShutdownNoticeResponse" }, "workerThreadScalingReportResponse": { "description": "Service's thread scaling recommendation for workers.", "$ref": "WorkerThreadScalingReportResponse" }, "streamingScalingReportResponse": { "description": "Service's streaming scaling response for workers.", "$ref": "StreamingScalingReportResponse" }, "workerHealthReportResponse": { "$ref": "WorkerHealthReportResponse", "description": "The service's response to a worker's health report." } } }, "BoundedTrieNode": { "description": "A single node in a BoundedTrie.", "properties": { "children": { "description": "Children of this node. Must be empty if truncated is true.", "type": "object", "additionalProperties": { "$ref": "BoundedTrieNode" } }, "truncated": { "type": "boolean", "description": "Whether this node has been truncated. A truncated leaf represents possibly many children with the same prefix." } }, "id": "BoundedTrieNode", "type": "object" }, "GetDebugConfigRequest": { "properties": { "componentId": { "description": "The internal component id for which debug configuration is requested.", "type": "string" }, "workerId": { "description": "The worker id, i.e., VM hostname.", "type": "string" }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id.", "type": "string" } }, "type": "object", "id": "GetDebugConfigRequest", "description": "Request to get updated debug configuration for component." }, "MetricUpdate": { "type": "object", "description": "Describes the state of a metric.", "properties": { "updateTime": { "format": "google-datetime", "description": "Timestamp associated with the metric value. Optional when workers are reporting work progress; it will be filled in responses from the metrics API.", "type": "string" }, "cumulative": { "description": "True if this metric is reported as the total cumulative aggregate value accumulated since the worker started working on this WorkItem. By default this is false, indicating that this metric is reported as a delta that is not associated with any WorkItem.", "type": "boolean" }, "boundedTrie": { "type": "any", "description": "Worker-computed aggregate value for the \"Trie\" aggregation kind. The only possible value type is a BoundedTrieNode. Introduced this field to avoid breaking older SDKs when Dataflow service starts to populate the `bounded_trie` field." }, "gauge": { "type": "any", "description": "A struct value describing properties of a Gauge. Metrics of gauge type show the value of a metric across time, and is aggregated based on the newest value." }, "meanSum": { "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind. This holds the sum of the aggregated values and is used in combination with mean_count below to obtain the actual mean aggregate value. The only possible value types are Long and Double.", "type": "any" }, "set": { "description": "Worker-computed aggregate value for the \"Set\" aggregation kind. The only possible value type is a list of Values whose type can be Long, Double, String, or BoundedTrie according to the metric's type. All Values in the list must be of the same type.", "type": "any" }, "distribution": { "description": "A struct value describing properties of a distribution of numeric values.", "type": "any" }, "kind": { "type": "string", "description": "Metric aggregation kind. The possible metric aggregation kinds are \"Sum\", \"Max\", \"Min\", \"Mean\", \"Set\", \"And\", \"Or\", and \"Distribution\". The specified aggregation kind is case-insensitive. If omitted, this is not an aggregated value but instead a single metric sample value." }, "scalar": { "description": "Worker-computed aggregate value for aggregation kinds \"Sum\", \"Max\", \"Min\", \"And\", and \"Or\". The possible value types are Long, Double, and Boolean.", "type": "any" }, "internal": { "type": "any", "description": "Worker-computed aggregate value for internal use by the Dataflow service." }, "name": { "$ref": "MetricStructuredName", "description": "Name of the metric." }, "trie": { "description": "Worker-computed aggregate value for the \"Trie\" aggregation kind. The only possible value type is a BoundedTrieNode.", "type": "any" }, "meanCount": { "description": "Worker-computed aggregate value for the \"Mean\" aggregation kind. This holds the count of the aggregated values and is used in combination with mean_sum above to obtain the actual mean aggregate value. The only possible value type is Long.", "type": "any" } }, "id": "MetricUpdate" }, "StageSource": { "id": "StageSource", "properties": { "userName": { "description": "Human-readable name for this source; may be user or system generated.", "type": "string" }, "sizeBytes": { "type": "string", "format": "int64", "description": "Size of the source, if measurable." }, "name": { "type": "string", "description": "Dataflow service generated name for this source." }, "originalTransformOrCollection": { "description": "User name for the original user transform or collection with which this source is most closely associated.", "type": "string" } }, "description": "Description of an input or output of an execution stage.", "type": "object" }, "StragglerSummary": { "id": "StragglerSummary", "type": "object", "properties": { "recentStragglers": { "type": "array", "items": { "$ref": "Straggler" }, "description": "The most recent stragglers." }, "totalStragglerCount": { "description": "The total count of stragglers.", "type": "string", "format": "int64" }, "stragglerCauseCount": { "additionalProperties": { "type": "string", "format": "int64" }, "type": "object", "description": "Aggregated counts of straggler causes, keyed by the string representation of the StragglerCause enum." } }, "description": "Summarized straggler identification details." }, "WorkerHealthReportResponse": { "type": "object", "id": "WorkerHealthReportResponse", "properties": { "reportInterval": { "description": "A positive value indicates the worker should change its reporting interval to the specified value. The default value of zero means no change in report rate is requested by the server.", "format": "google-duration", "type": "string" } }, "description": "WorkerHealthReportResponse contains information returned to the worker in response to a health ping." }, "DeleteSnapshotResponse": { "id": "DeleteSnapshotResponse", "properties": {}, "description": "Response from deleting a snapshot.", "type": "object" }, "BigQueryIODetails": { "type": "object", "description": "Metadata for a BigQuery connector used by the job.", "properties": { "dataset": { "description": "Dataset accessed in the connection.", "type": "string" }, "table": { "type": "string", "description": "Table accessed in the connection." }, "query": { "type": "string", "description": "Query used to access data in the connection." }, "projectId": { "type": "string", "description": "Project accessed in the connection." } }, "id": "BigQueryIODetails" }, "DynamicSourceSplit": { "type": "object", "description": "When a task splits using WorkItemStatus.dynamic_source_split, this message describes the two parts of the split relative to the description of the current task's input.", "properties": { "residual": { "$ref": "DerivedSource", "description": "Residual part (returned to the pool of work). Specified relative to the previously-current source." }, "primary": { "$ref": "DerivedSource", "description": "Primary part (continued to be processed by worker). Specified relative to the previously-current source. Becomes current." } }, "id": "DynamicSourceSplit" }, "CounterStructuredNameAndMetadata": { "properties": { "metadata": { "description": "Metadata associated with a counter", "$ref": "CounterMetadata" }, "name": { "description": "Structured name of the counter.", "$ref": "CounterStructuredName" } }, "description": "A single message which encapsulates structured name and metadata for a given counter.", "type": "object", "id": "CounterStructuredNameAndMetadata" }, "Empty": { "type": "object", "description": "A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); }", "id": "Empty", "properties": {} }, "FloatingPointList": { "properties": { "elements": { "type": "array", "description": "Elements of the list.", "items": { "type": "number", "format": "double" } } }, "type": "object", "id": "FloatingPointList", "description": "A metric value representing a list of floating point numbers." }, "StreamingComputationRanges": { "properties": { "rangeAssignments": { "description": "Data disk assignments for ranges from this computation.", "type": "array", "items": { "$ref": "KeyRangeDataDiskAssignment" } }, "computationId": { "type": "string", "description": "The ID of the computation." } }, "id": "StreamingComputationRanges", "description": "Describes full or partial data disk assignment information of the computation ranges.", "type": "object" }, "IntegerList": { "properties": { "elements": { "type": "array", "items": { "$ref": "SplitInt64" }, "description": "Elements of the list." } }, "id": "IntegerList", "type": "object", "description": "A metric value representing a list of integers." }, "DataSamplingReport": { "type": "object", "id": "DataSamplingReport", "properties": { "exceptionsSampledCount": { "format": "int64", "type": "string", "description": "Optional. Delta of number of samples taken from user code exceptions from previous report." }, "bytesWrittenDelta": { "format": "int64", "type": "string", "description": "Optional. Delta of bytes written to file from previous report." }, "translationErrorsCount": { "type": "string", "description": "Optional. Delta of errors counts from retrieving, or translating the samples from previous report.", "format": "int64" }, "elementsSampledCount": { "format": "int64", "type": "string", "description": "Optional. Delta of number of elements sampled from previous report." }, "pcollectionsSampledCount": { "format": "int64", "type": "string", "description": "Optional. Delta of number of PCollections sampled from previous report." }, "elementsSampledBytes": { "description": "Optional. Delta of bytes sampled from previous report.", "format": "int64", "type": "string" }, "persistenceErrorsCount": { "description": "Optional. Delta of errors counts from persisting the samples from previous report.", "format": "int64", "type": "string" } }, "description": "Contains per-worker telemetry about the data sampling feature." }, "ListSnapshotsResponse": { "type": "object", "id": "ListSnapshotsResponse", "description": "List of snapshots.", "properties": { "snapshots": { "type": "array", "items": { "$ref": "Snapshot" }, "description": "Returned snapshots." } } }, "ReportWorkItemStatusResponse": { "type": "object", "id": "ReportWorkItemStatusResponse", "properties": { "workItemServiceStates": { "type": "array", "items": { "$ref": "WorkItemServiceState" }, "description": "A set of messages indicating the service-side state for each WorkItem whose status was reported, in the same order as the WorkItemStatus messages in the ReportWorkItemStatusRequest which resulting in this response." }, "unifiedWorkerResponse": { "description": "Untranslated bag-of-bytes WorkProgressUpdateResponse for UnifiedWorker.", "type": "object", "additionalProperties": { "description": "Properties of the object. Contains field @type with type URL.", "type": "any" } } }, "description": "Response from a request to report the status of WorkItems." }, "BoundedTrie": { "properties": { "singleton": { "type": "array", "description": "A more efficient representation for metrics consisting of a single value.", "items": { "type": "string" } }, "root": { "$ref": "BoundedTrieNode", "description": "A compact representation of all the elements in this trie." }, "bound": { "type": "integer", "format": "int32", "description": "The maximum number of elements to store before truncation." } }, "type": "object", "description": "The message type used for encoding metrics of type bounded trie.", "id": "BoundedTrie" }, "ProgressTimeseries": { "id": "ProgressTimeseries", "description": "Information about the progress of some component of job execution.", "properties": { "currentProgress": { "format": "double", "type": "number", "description": "The current progress of the component, in the range [0,1]." }, "dataPoints": { "description": "History of progress for the component. Points are sorted by time.", "type": "array", "items": { "$ref": "Point" } } }, "type": "object" }, "ConfigStoreSettingValue": { "type": "object", "id": "ConfigStoreSettingValue", "properties": { "stringValue": { "description": "Represents a string value.", "type": "string" }, "boolValue": { "type": "boolean", "description": "Represents a boolean value." } }, "description": "Represents a dynamically typed value." }, "CounterMetadata": { "properties": { "kind": { "description": "Counter aggregation kind.", "enum": [ "INVALID", "SUM", "MAX", "MIN", "MEAN", "OR", "AND", "SET", "DISTRIBUTION", "LATEST_VALUE" ], "enumDescriptions": [ "Counter aggregation kind was not set.", "Aggregated value is the sum of all contributed values.", "Aggregated value is the max of all contributed values.", "Aggregated value is the min of all contributed values.", "Aggregated value is the mean of all contributed values.", "Aggregated value represents the logical 'or' of all contributed values.", "Aggregated value represents the logical 'and' of all contributed values.", "Aggregated value is a set of unique contributed values.", "Aggregated value captures statistics about a distribution.", "Aggregated value tracks the latest value of a variable." ], "type": "string" }, "otherUnits": { "description": "A string referring to the unit type.", "type": "string" }, "standardUnits": { "enumDescriptions": [ "Counter returns a value in bytes.", "Counter returns a value in bytes per second.", "Counter returns a value in milliseconds.", "Counter returns a value in microseconds.", "Counter returns a value in nanoseconds.", "Counter returns a timestamp in milliseconds.", "Counter returns a timestamp in microseconds.", "Counter returns a timestamp in nanoseconds." ], "description": "System defined Units, see above enum.", "enum": [ "BYTES", "BYTES_PER_SEC", "MILLISECONDS", "MICROSECONDS", "NANOSECONDS", "TIMESTAMP_MSEC", "TIMESTAMP_USEC", "TIMESTAMP_NSEC" ], "type": "string" }, "description": { "type": "string", "description": "Human-readable description of the counter semantics." } }, "description": "CounterMetadata includes all static non-name non-value counter attributes.", "type": "object", "id": "CounterMetadata" }, "CustomSourceLocation": { "description": "Identifies the location of a custom souce.", "id": "CustomSourceLocation", "properties": { "stateful": { "type": "boolean", "description": "Whether this source is stateful." } }, "type": "object" }, "StreamingScalingReportResponse": { "type": "object", "id": "StreamingScalingReportResponse", "description": "Contains per-user-worker streaming scaling recommendation from the backend.", "properties": { "maximumThreadCount": { "type": "integer", "format": "int32", "description": "Maximum thread count limit;" } } }, "DatastoreIODetails": { "properties": { "namespace": { "description": "Namespace used in the connection.", "type": "string" }, "projectId": { "type": "string", "description": "ProjectId accessed in the connection." } }, "type": "object", "id": "DatastoreIODetails", "description": "Metadata for a Datastore connector used by the job." }, "Base2Exponent": { "type": "object", "properties": { "numberOfBuckets": { "type": "integer", "description": "Must be greater than 0.", "format": "int32" }, "scale": { "type": "integer", "format": "int32", "description": "Must be between -3 and 3. This forces the growth factor of the bucket boundaries to be between `2^(1/8)` and `256`." } }, "id": "Base2Exponent", "description": "Exponential buckets where the growth factor between buckets is `2**(2**-scale)`. e.g. for `scale=1` growth factor is `2**(2**(-1))=sqrt(2)`. `n` buckets will have the following boundaries. - 0th: [0, gf) - i in [1, n-1]: [gf^(i), gf^(i+1))" }, "ConfigStoreSetting": { "description": "A ConfigStoreSetting resource.", "type": "object", "properties": { "name": { "type": "string", "description": "Identifier. The resource name of the setting." }, "value": { "description": "Required. The dynamic value of the setting.", "$ref": "ConfigStoreSettingValue" } }, "id": "ConfigStoreSetting" }, "StateFamilyConfig": { "properties": { "stateFamily": { "type": "string", "description": "The state family value." }, "isRead": { "description": "If true, this family corresponds to a read operation.", "type": "boolean" } }, "type": "object", "description": "State family configuration.", "id": "StateFamilyConfig" }, "GetTemplateResponse": { "description": "The response to a GetTemplate request.", "properties": { "runtimeMetadata": { "description": "Describes the runtime metadata with SDKInfo and available parameters.", "$ref": "RuntimeMetadata" }, "metadata": { "description": "The template metadata describing the template name, available parameters, etc.", "$ref": "TemplateMetadata" }, "templateType": { "type": "string", "description": "Template Type.", "enumDescriptions": [ "Unknown Template Type.", "Legacy Template.", "Flex Template." ], "enum": [ "UNKNOWN", "LEGACY", "FLEX" ] }, "status": { "description": "The status of the get template request. Any problems with the request will be indicated in the error_details.", "$ref": "Status" } }, "id": "GetTemplateResponse", "type": "object" }, "PartialGroupByKeyInstruction": { "properties": { "inputElementCodec": { "additionalProperties": { "description": "Properties of the object.", "type": "any" }, "type": "object", "description": "The codec to use for interpreting an element in the input PTable." }, "originalCombineValuesStepName": { "type": "string", "description": "If this instruction includes a combining function, this is the name of the CombineValues instruction lifted into this instruction." }, "originalCombineValuesInputStoreName": { "description": "If this instruction includes a combining function this is the name of the intermediate store between the GBK and the CombineValues.", "type": "string" }, "input": { "description": "Describes the input to the partial group-by-key instruction.", "$ref": "InstructionInput" }, "sideInputs": { "type": "array", "items": { "$ref": "SideInputInfo" }, "description": "Zero or more side inputs." }, "valueCombiningFn": { "additionalProperties": { "type": "any", "description": "Properties of the object." }, "description": "The value combining function to invoke.", "type": "object" } }, "type": "object", "description": "An instruction that does a partial group-by-key. One input and one output.", "id": "PartialGroupByKeyInstruction" }, "KeyRangeDataDiskAssignment": { "id": "KeyRangeDataDiskAssignment", "description": "Data disk assignment information for a specific key-range of a sharded computation. Currently we only support UTF-8 character splits to simplify encoding into JSON.", "type": "object", "properties": { "start": { "description": "The start (inclusive) of the key range.", "type": "string" }, "dataDisk": { "type": "string", "description": "The name of the data disk where data for this range is stored. This name is local to the Google Cloud Platform project and uniquely identifies the disk within that project, for example \"myproject-1014-104817-4c2-harness-0-disk-1\"." }, "end": { "description": "The end (exclusive) of the key range.", "type": "string" } } }, "ResourceUtilizationReportResponse": { "type": "object", "id": "ResourceUtilizationReportResponse", "properties": {}, "description": "Service-side response to WorkerMessage reporting resource utilization." }, "ResolveConfigStoreSettingResponse": { "id": "ResolveConfigStoreSettingResponse", "description": "Response message for ResolveConfigStoreSetting.", "type": "object", "properties": { "setting": { "$ref": "ConfigStoreSetting", "description": "The dry-run setting result." }, "choices": { "items": { "$ref": "ConfigStoreSetting" }, "description": "The list of settings that were considered during resolution.", "type": "array" } } }, "DataflowHistogramValue": { "id": "DataflowHistogramValue", "properties": { "bucketOptions": { "$ref": "BucketOptions", "description": "Describes the bucket boundaries used in the histogram." }, "count": { "description": "Number of values recorded in this histogram.", "type": "string", "format": "int64" }, "bucketCounts": { "description": "Optional. The number of values in each bucket of the histogram, as described in `bucket_options`. `bucket_counts` should contain N values, where N is the number of buckets specified in `bucket_options`. If `bucket_counts` has fewer than N values, the remaining values are assumed to be 0.", "type": "array", "items": { "type": "string", "format": "int64" } }, "outlierStats": { "description": "Statistics on the values recorded in the histogram that fall out of the bucket boundaries.", "$ref": "OutlierStats" } }, "description": "Summary statistics for a population of values. HistogramValue contains a sequence of buckets and gives a count of values that fall into each bucket. Bucket boundares are defined by a formula and bucket widths are either fixed or exponentially increasing.", "type": "object" }, "ComputationTopology": { "properties": { "outputs": { "items": { "$ref": "StreamLocation" }, "description": "The outputs from the computation.", "type": "array" }, "keyRanges": { "type": "array", "items": { "$ref": "KeyRangeLocation" }, "description": "The key ranges processed by the computation." }, "stateFamilies": { "items": { "$ref": "StateFamilyConfig" }, "type": "array", "description": "The state family values." }, "inputs": { "description": "The inputs to the computation.", "items": { "$ref": "StreamLocation" }, "type": "array" }, "computationId": { "description": "The ID of the computation.", "type": "string" }, "systemStageName": { "description": "The system stage name.", "type": "string" } }, "type": "object", "description": "All configuration data for a particular Computation.", "id": "ComputationTopology" }, "CPUTime": { "properties": { "rate": { "description": "Average CPU utilization rate (% non-idle cpu / second) since previous sample.", "type": "number", "format": "double" }, "timestamp": { "type": "string", "description": "Timestamp of the measurement.", "format": "google-datetime" }, "totalMs": { "format": "uint64", "description": "Total active CPU time across all cores (ie., non-idle) in milliseconds since start-up.", "type": "string" } }, "id": "CPUTime", "type": "object", "description": "Modeled after information exposed by /proc/stat." }, "Parameter": { "properties": { "key": { "description": "Key or name for this parameter.", "type": "string" }, "value": { "type": "any", "description": "Value for this parameter." } }, "id": "Parameter", "description": "Structured data associated with this message.", "type": "object" }, "WorkerDetails": { "properties": { "workItems": { "type": "array", "items": { "$ref": "WorkItemDetails" }, "description": "Work items processed by this worker, sorted by time." }, "workerName": { "type": "string", "description": "Name of this worker" } }, "type": "object", "id": "WorkerDetails", "description": "Information about a worker" }, "JobMessage": { "id": "JobMessage", "properties": { "messageText": { "type": "string", "description": "The text of the message." }, "id": { "description": "Deprecated.", "type": "string" }, "time": { "format": "google-datetime", "type": "string", "description": "The timestamp of the message." }, "messageImportance": { "type": "string", "enumDescriptions": [ "The message importance isn't specified, or is unknown.", "The message is at the 'debug' level: typically only useful for software engineers working on the code the job is running. Typically, Dataflow pipeline runners do not display log messages at this level by default.", "The message is at the 'detailed' level: somewhat verbose, but potentially useful to users. Typically, Dataflow pipeline runners do not display log messages at this level by default. These messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'basic' level: useful for keeping track of the execution of a Dataflow pipeline. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'warning' level: indicating a condition pertaining to a job which may require human intervention. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'error' level: indicating a condition preventing a job from succeeding. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI." ], "description": "Importance level of the message.", "enum": [ "JOB_MESSAGE_IMPORTANCE_UNKNOWN", "JOB_MESSAGE_DEBUG", "JOB_MESSAGE_DETAILED", "JOB_MESSAGE_BASIC", "JOB_MESSAGE_WARNING", "JOB_MESSAGE_ERROR" ] } }, "type": "object", "description": "A particular message pertaining to a Dataflow job." }, "TopologyConfig": { "id": "TopologyConfig", "type": "object", "description": "Global topology of the streaming Dataflow job, including all computations and their sharded locations.", "properties": { "userStageToComputationNameMap": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Maps user stage names to stable computation names." }, "computations": { "description": "The computations associated with a streaming Dataflow job.", "type": "array", "items": { "$ref": "ComputationTopology" } }, "forwardingKeyBits": { "format": "int32", "type": "integer", "description": "The size (in bits) of keys that will be assigned to source messages." }, "dataDiskAssignments": { "type": "array", "items": { "$ref": "DataDiskAssignment" }, "description": "The disks assigned to a streaming Dataflow job." }, "persistentStateVersion": { "format": "int32", "type": "integer", "description": "Version number for persistent state." } } }, "ParDoInstruction": { "description": "An instruction that does a ParDo operation. Takes one main input and zero or more side inputs, and produces zero or more outputs. Runs user code.", "id": "ParDoInstruction", "type": "object", "properties": { "numOutputs": { "description": "The number of outputs.", "type": "integer", "format": "int32" }, "userFn": { "type": "object", "description": "The user function to invoke.", "additionalProperties": { "type": "any", "description": "Properties of the object." } }, "input": { "description": "The input.", "$ref": "InstructionInput" }, "sideInputs": { "items": { "$ref": "SideInputInfo" }, "type": "array", "description": "Zero or more side inputs." }, "multiOutputInfos": { "description": "Information about each of the outputs, if user_fn is a MultiDoFn.", "type": "array", "items": { "$ref": "MultiOutputInfo" } } } }, "StreamingStageLocation": { "id": "StreamingStageLocation", "type": "object", "properties": { "streamId": { "type": "string", "description": "Identifies the particular stream within the streaming Dataflow job." } }, "description": "Identifies the location of a streaming computation stage, for stage-to-stage communication." }, "OutlierStats": { "id": "OutlierStats", "description": "Statistics for the underflow and overflow bucket.", "type": "object", "properties": { "overflowCount": { "format": "int64", "description": "Number of values that are larger than the upper bound of the largest bucket.", "type": "string" }, "overflowMean": { "type": "number", "description": "Mean of values in the overflow bucket.", "format": "double" }, "underflowCount": { "type": "string", "description": "Number of values that are smaller than the lower bound of the smallest bucket.", "format": "int64" }, "underflowMean": { "format": "double", "type": "number", "description": "Mean of values in the undeflow bucket." } } }, "WorkerShutdownNoticeResponse": { "properties": {}, "description": "Service-side response to WorkerMessage issuing shutdown notice.", "type": "object", "id": "WorkerShutdownNoticeResponse" }, "Status": { "description": "The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. 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).", "properties": { "details": { "items": { "type": "object", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } }, "type": "array", "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use." }, "code": { "description": "The status code, which should be an enum value of google.rpc.Code.", "format": "int32", "type": "integer" }, "message": { "type": "string", "description": "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." } }, "id": "Status", "type": "object" }, "PubsubSnapshotMetadata": { "properties": { "topicName": { "type": "string", "description": "The name of the Pubsub topic." }, "expireTime": { "format": "google-datetime", "type": "string", "description": "The expire time of the Pubsub snapshot." }, "snapshotName": { "description": "The name of the Pubsub snapshot.", "type": "string" } }, "description": "Represents a Pubsub snapshot.", "type": "object", "id": "PubsubSnapshotMetadata" }, "SourceGetMetadataResponse": { "description": "The result of a SourceGetMetadataOperation.", "type": "object", "properties": { "metadata": { "description": "The computed metadata.", "$ref": "SourceMetadata" } }, "id": "SourceGetMetadataResponse" }, "LeaseWorkItemRequest": { "id": "LeaseWorkItemRequest", "type": "object", "properties": { "unifiedWorkerRequest": { "type": "object", "description": "Untranslated bag-of-bytes WorkRequest from UnifiedWorker.", "additionalProperties": { "description": "Properties of the object. Contains field @type with type URL.", "type": "any" } }, "workerCapabilities": { "type": "array", "items": { "type": "string" }, "description": "Worker capabilities. WorkItems might be limited to workers with specific capabilities." }, "currentWorkerTime": { "description": "The current timestamp at the worker.", "type": "string", "format": "google-datetime" }, "projectNumber": { "type": "string", "format": "int64", "description": "Optional. The project number of the project this worker belongs to." }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the WorkItem's job.", "type": "string" }, "workItemTypes": { "type": "array", "items": { "type": "string" }, "description": "Filter for WorkItem type." }, "requestedLeaseDuration": { "format": "google-duration", "type": "string", "description": "The initial lease period." }, "workerId": { "type": "string", "description": "Identifies the worker leasing work -- typically the ID of the virtual machine running the worker." } }, "description": "Request to lease WorkItems." }, "Parameters": { "description": "The parameters to use for autoscaling when this schedule is active.", "properties": { "latencyTarget": { "type": "string", "description": "Optional. The target latency for this schedule." }, "maxWorkerCount": { "description": "Optional. The maximum number of workers for this schedule.", "type": "integer", "format": "int32" }, "cpuUtilizationTarget": { "format": "double", "type": "number", "description": "Optional. The target CPU utilization for this schedule." }, "minWorkerCount": { "description": "Optional. The minimum number of workers for this schedule.", "format": "int32", "type": "integer" } }, "id": "Parameters", "type": "object" }, "SourceOperationRequest": { "description": "A work item that represents the different operations that can be performed on a user-defined Source specification.", "type": "object", "id": "SourceOperationRequest", "properties": { "split": { "description": "Information about a request to split a source.", "$ref": "SourceSplitRequest" }, "systemName": { "type": "string", "description": "System-defined name of the Read instruction for this source. Unique across the workflow." }, "originalName": { "type": "string", "description": "System-defined name for the Read instruction for this source in the original workflow graph." }, "name": { "type": "string", "description": "User-provided name of the Read instruction for this source." }, "getMetadata": { "description": "Information about a request to get metadata about a source.", "$ref": "SourceGetMetadataRequest" }, "stageName": { "description": "System-defined name of the stage containing the source operation. Unique across the workflow.", "type": "string" } } }, "RuntimeEnvironment": { "description": "The environment values to set at runtime.", "id": "RuntimeEnvironment", "type": "object", "properties": { "network": { "description": "Optional. Network to which VMs will be assigned. If empty or unspecified, the service will use the network \"default\".", "type": "string" }, "diskSizeGb": { "description": "Optional. The disk size, in gigabytes, to use on each remote Compute Engine worker instance.", "type": "integer", "format": "int32" }, "kmsKeyName": { "description": "Optional. Name for the Cloud KMS key for the job. Key format is: projects//locations//keyRings//cryptoKeys/", "type": "string" }, "workerZone": { "type": "string", "description": "Optional. 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." }, "streamingMode": { "enumDescriptions": [ "Run in the default mode.", "In this mode, message deduplication is performed against persistent state to make sure each message is processed and committed to storage exactly once.", "Message deduplication is not performed. Messages might be processed multiple times, and the results are applied multiple times. Note: Setting this value also enables Streaming Engine and Streaming Engine resource-based billing." ], "type": "string", "enum": [ "STREAMING_MODE_UNSPECIFIED", "STREAMING_MODE_EXACTLY_ONCE", "STREAMING_MODE_AT_LEAST_ONCE" ], "description": "Optional. Specifies the Streaming Engine message processing guarantees. Reduces cost and latency but might result in duplicate messages committed to storage. Designed to run simple mapping streaming ETL jobs at the lowest cost. For example, Change Data Capture (CDC) to BigQuery is a canonical use case. For more information, see [Set the pipeline streaming mode](https://cloud.google.com/dataflow/docs/guides/streaming-modes)." }, "zone": { "description": "Optional. 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.", "type": "string" }, "workerRegion": { "type": "string", "description": "Required. 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." }, "bypassTempDirValidation": { "description": "Optional. Whether to bypass the safety checks for the job's temporary directory. Use with caution.", "type": "boolean" }, "ipConfiguration": { "type": "string", "description": "Optional. Configuration for VM IPs.", "enumDescriptions": [ "The configuration is unknown, or unspecified.", "Workers should have public IP addresses.", "Workers should have private IP addresses." ], "enum": [ "WORKER_IP_UNSPECIFIED", "WORKER_IP_PUBLIC", "WORKER_IP_PRIVATE" ] }, "additionalPipelineOptions": { "type": "array", "description": "Optional. Additional pipeline option flags for the job.", "items": { "type": "string" } }, "maxWorkers": { "format": "int32", "description": "Optional. The maximum number of Google Compute Engine instances to be made available to your pipeline during execution, from 1 to 1000. The default value is 1.", "type": "integer" }, "additionalUserLabels": { "additionalProperties": { "type": "string" }, "type": "object", "description": "Optional. 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. An object containing a list of \"key\": value pairs. Example: { \"name\": \"wrench\", \"mass\": \"1kg\", \"count\": \"3\" }." }, "additionalExperiments": { "type": "array", "items": { "type": "string" }, "description": "Optional. Additional experiment flags for the job, specified with the `--experiments` option." }, "subnetwork": { "description": "Optional. Subnetwork to which VMs will be assigned, if desired. You can specify a subnetwork using either a complete URL or an abbreviated path. Expected to be of the form \"https://www.googleapis.com/compute/v1/projects/HOST_PROJECT_ID/regions/REGION/subnetworks/SUBNETWORK\" or \"regions/REGION/subnetworks/SUBNETWORK\". If the subnetwork is located in a Shared VPC network, you must use the complete URL.", "type": "string" }, "machineType": { "description": "Optional. The machine type to use for the job. Defaults to the value from the template if not specified.", "type": "string" }, "numWorkers": { "type": "integer", "format": "int32", "description": "Optional. The initial number of Google Compute Engine instances for the job. The default value is 11." }, "enableStreamingEngine": { "description": "Optional. Whether to enable Streaming Engine for the job.", "type": "boolean" }, "serviceAccountEmail": { "type": "string", "description": "Optional. The email address of the service account to run the job as." }, "tempLocation": { "description": "Required. The Cloud Storage path to use for temporary files. Must be a valid Cloud Storage URL, beginning with `gs://`.", "type": "string" } } }, "ParameterMetadata": { "properties": { "parentTriggerValues": { "description": "Optional. The value(s) of the 'parent_name' parameter which will trigger this parameter to be shown. If left empty, ANY non-empty value in parent_name will trigger this parameter to be shown. Only considered when this parameter is conditional (when 'parent_name' has been provided).", "type": "array", "items": { "type": "string" } }, "paramType": { "enumDeprecated": [ false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, false, true, false, false ], "type": "string", "enum": [ "DEFAULT", "TEXT", "GCS_READ_BUCKET", "GCS_WRITE_BUCKET", "GCS_READ_FILE", "GCS_WRITE_FILE", "GCS_READ_FOLDER", "GCS_WRITE_FOLDER", "PUBSUB_TOPIC", "PUBSUB_SUBSCRIPTION", "BIGQUERY_TABLE", "JAVASCRIPT_UDF_FILE", "SERVICE_ACCOUNT", "MACHINE_TYPE", "KMS_KEY_NAME", "WORKER_REGION", "WORKER_ZONE", "BOOLEAN", "ENUM", "NUMBER", "KAFKA_TOPIC", "KAFKA_READ_TOPIC", "KAFKA_WRITE_TOPIC" ], "description": "Optional. The type of the parameter. Used for selecting input picker.", "enumDescriptions": [ "Default input type.", "The parameter specifies generic text input.", "The parameter specifies a Cloud Storage Bucket to read from.", "The parameter specifies a Cloud Storage Bucket to write to.", "The parameter specifies a Cloud Storage file path to read from.", "The parameter specifies a Cloud Storage file path to write to.", "The parameter specifies a Cloud Storage folder path to read from.", "The parameter specifies a Cloud Storage folder to write to.", "The parameter specifies a Pub/Sub Topic.", "The parameter specifies a Pub/Sub Subscription.", "The parameter specifies a BigQuery table.", "The parameter specifies a JavaScript UDF in Cloud Storage.", "The parameter specifies a Service Account email.", "The parameter specifies a Machine Type.", "The parameter specifies a KMS Key name.", "The parameter specifies a Worker Region.", "The parameter specifies a Worker Zone.", "The parameter specifies a boolean input.", "The parameter specifies an enum input.", "The parameter specifies a number input.", "Deprecated. Please use KAFKA_READ_TOPIC instead.", "The parameter specifies the fully-qualified name of an Apache Kafka topic. This can be either a Google Managed Kafka topic or a non-managed Kafka topic.", "The parameter specifies the fully-qualified name of an Apache Kafka topic. This can be an existing Google Managed Kafka topic, the name for a new Google Managed Kafka topic, or an existing non-managed Kafka topic." ] }, "groupName": { "description": "Optional. Specifies a group name for this parameter to be rendered under. Group header text will be rendered exactly as specified in this field. Only considered when parent_name is NOT provided.", "type": "string" }, "isOptional": { "description": "Optional. Whether the parameter is optional. Defaults to false.", "type": "boolean" }, "name": { "description": "Required. The name of the parameter.", "type": "string" }, "customMetadata": { "type": "object", "description": "Optional. Additional metadata for describing this parameter.", "additionalProperties": { "type": "string" } }, "hiddenUi": { "description": "Optional. Whether the parameter should be hidden in the UI.", "type": "boolean" }, "defaultValue": { "type": "string", "description": "Optional. The default values will pre-populate the parameter with the given value from the proto. If default_value is left empty, the parameter will be populated with a default of the relevant type, e.g. false for a boolean." }, "helpText": { "description": "Required. The help text to display for the parameter.", "type": "string" }, "parentName": { "description": "Optional. Specifies the name of the parent parameter. Used in conjunction with 'parent_trigger_values' to make this parameter conditional (will only be rendered conditionally). Should be mappable to a ParameterMetadata.name field.", "type": "string" }, "regexes": { "description": "Optional. Regexes that the parameter must match.", "type": "array", "items": { "type": "string" } }, "enumOptions": { "items": { "$ref": "ParameterMetadataEnumOption" }, "type": "array", "description": "Optional. The options shown when ENUM ParameterType is specified." }, "label": { "description": "Required. The label to display for the parameter.", "type": "string" } }, "description": "Metadata for a specific parameter.", "type": "object", "id": "ParameterMetadata" }, "JobMetadata": { "properties": { "datastoreDetails": { "description": "Identification of a Datastore source used in the Dataflow job.", "type": "array", "items": { "$ref": "DatastoreIODetails" } }, "fileDetails": { "items": { "$ref": "FileIODetails" }, "type": "array", "description": "Identification of a File source used in the Dataflow job." }, "sdkVersion": { "description": "The SDK version used to run the job.", "$ref": "SdkVersion" }, "pubsubDetails": { "items": { "$ref": "PubSubIODetails" }, "description": "Identification of a Pub/Sub source used in the Dataflow job.", "type": "array" }, "spannerDetails": { "items": { "$ref": "SpannerIODetails" }, "description": "Identification of a Spanner source used in the Dataflow job.", "type": "array" }, "bigqueryDetails": { "description": "Identification of a BigQuery source used in the Dataflow job.", "type": "array", "items": { "$ref": "BigQueryIODetails" } }, "userDisplayProperties": { "type": "object", "description": "List of display properties to help UI filter jobs.", "additionalProperties": { "type": "string" } }, "bigTableDetails": { "description": "Identification of a Cloud Bigtable source used in the Dataflow job.", "items": { "$ref": "BigTableIODetails" }, "type": "array" } }, "description": "Metadata available primarily for filtering jobs. Will be included in the ListJob response and Job SUMMARY view.", "id": "JobMetadata", "type": "object" }, "StageExecutionDetails": { "type": "object", "description": "Information about the workers and work items within a stage.", "id": "StageExecutionDetails", "properties": { "workers": { "description": "Workers that have done work on the stage.", "type": "array", "items": { "$ref": "WorkerDetails" } }, "nextPageToken": { "type": "string", "description": "If present, this response does not contain all requested tasks. To obtain the next page of results, repeat the request with page_token set to this value." } } }, "GetDebugConfigResponse": { "type": "object", "id": "GetDebugConfigResponse", "properties": { "config": { "description": "The encoded debug configuration for the requested component.", "type": "string" } }, "description": "Response to a get debug configuration request." }, "Step": { "description": "Defines a particular step within a Cloud Dataflow job. A job consists of multiple steps, each of which performs some specific operation as part of the overall job. Data is typically passed from one step to another as part of the job. **Note:** The properties of this object are not stable and might change. Here's an example of a sequence of steps which together implement a Map-Reduce job: * Read a collection of data from some source, parsing the collection's elements. * Validate the elements. * Apply a user-defined function to map each element to some value and extract an element-specific key value. * Group elements with the same key into a single element with that key, transforming a multiply-keyed collection into a uniquely-keyed collection. * Write the elements out to some data sink. Note that the Cloud Dataflow service may be used to run many different types of jobs, not just Map-Reduce.", "properties": { "properties": { "description": "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.", "additionalProperties": { "type": "any", "description": "Properties of the object." }, "type": "object" }, "kind": { "description": "The kind of step in the Cloud Dataflow job.", "type": "string" }, "name": { "description": "The name that identifies the step. This must be unique for each step with respect to all other steps in the Cloud Dataflow job.", "type": "string" } }, "id": "Step", "type": "object" }, "LaunchFlexTemplateRequest": { "properties": { "validateOnly": { "type": "boolean", "description": "If true, the request is validated but not actually executed. Defaults to false." }, "launchParameter": { "description": "Required. Parameter to launch a job form Flex Template.", "$ref": "LaunchFlexTemplateParameter" } }, "type": "object", "description": "A request to launch a Cloud Dataflow job from a FlexTemplate.", "id": "LaunchFlexTemplateRequest" }, "RuntimeMetadata": { "description": "RuntimeMetadata describing a runtime environment.", "type": "object", "properties": { "parameters": { "type": "array", "description": "The parameters for the template.", "items": { "$ref": "ParameterMetadata" } }, "sdkInfo": { "$ref": "SDKInfo", "description": "SDK Info for the template." } }, "id": "RuntimeMetadata" }, "WorkerThreadScalingReport": { "type": "object", "id": "WorkerThreadScalingReport", "properties": { "currentThreadCount": { "type": "integer", "format": "int32", "description": "Current number of active threads in a worker." } }, "description": "Contains information about the thread scaling information of a worker." }, "ApproximateProgress": { "type": "object", "id": "ApproximateProgress", "properties": { "remainingTime": { "deprecated": true, "format": "google-duration", "description": "Obsolete.", "type": "string" }, "position": { "$ref": "Position", "deprecated": true, "description": "Obsolete." }, "percentComplete": { "format": "float", "description": "Obsolete.", "deprecated": true, "type": "number" } }, "description": "Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest." }, "ComponentTransform": { "type": "object", "properties": { "originalTransform": { "description": "User name for the original user transform with which this transform is most closely associated.", "type": "string" }, "userName": { "description": "Human-readable name for this transform; may be user or system generated.", "type": "string" }, "name": { "description": "Dataflow service generated name for this source.", "type": "string" } }, "id": "ComponentTransform", "description": "Description of a transform executed as part of an execution stage." }, "StreamingApplianceSnapshotConfig": { "type": "object", "id": "StreamingApplianceSnapshotConfig", "description": "Streaming appliance snapshot configuration.", "properties": { "importStateEndpoint": { "description": "Indicates which endpoint is used to import appliance state.", "type": "string" }, "snapshotId": { "description": "If set, indicates the snapshot id for the snapshot being performed.", "type": "string" } } }, "DataflowGaugeValue": { "type": "object", "id": "DataflowGaugeValue", "description": "The gauge value of a metric.", "properties": { "value": { "format": "int64", "type": "string", "description": "The value of the gauge." }, "measuredTime": { "description": "The timestamp when the gauge was recorded.", "type": "string", "format": "google-datetime" } } }, "WorkerSettings": { "description": "Provides data to pass through to the worker harness.", "properties": { "shuffleServicePath": { "description": "The Shuffle service path relative to the root URL, for example, \"shuffle/v1beta1\".", "type": "string" }, "baseUrl": { "type": "string", "description": "The base URL for 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/\"" }, "tempStoragePrefix": { "description": "The prefix of the resources the system should use for temporary storage. The supported resource type is: Google Cloud Storage: storage.googleapis.com/{bucket}/{object} bucket.storage.googleapis.com/{object}", "type": "string" }, "servicePath": { "type": "string", "description": "The Cloud Dataflow service path relative to the root URL, for example, \"dataflow/v1b3/projects\"." }, "reportingEnabled": { "type": "boolean", "description": "Whether to send work progress updates to the service." }, "workerId": { "type": "string", "description": "The ID of the worker running this pipeline." } }, "type": "object", "id": "WorkerSettings" }, "ShellTask": { "type": "object", "description": "A task which consists of a shell command for the worker to execute.", "id": "ShellTask", "properties": { "command": { "type": "string", "description": "The shell command to run." }, "exitCode": { "type": "integer", "description": "Exit code for the task.", "format": "int32" } } }, "MetricStructuredName": { "description": "Identifies a metric, by describing the source which generated the metric.", "type": "object", "properties": { "name": { "description": "Worker-defined metric name.", "type": "string" }, "context": { "type": "object", "description": "Zero or more labeled fields which identify the part of the job this metric is associated with, such as the name of a step or collection. For example, built-in counters associated with steps will have context['step'] = . Counters associated with PCollections in the SDK will have context['pcollection'] = .", "additionalProperties": { "type": "string" } }, "origin": { "description": "Origin (namespace) of metric name. May be blank for user-define metrics; will be \"dataflow\" for metrics defined by the Dataflow service or SDK.", "type": "string" } }, "id": "MetricStructuredName" }, "SourceSplitRequest": { "id": "SourceSplitRequest", "description": "Represents the operation to split a high-level Source specification into bundles (parts for parallel processing). At a high level, splitting of a source into bundles happens as follows: SourceSplitRequest is applied to the source. If it returns SOURCE_SPLIT_OUTCOME_USE_CURRENT, no further splitting happens and the source is used \"as is\". Otherwise, splitting is applied recursively to each produced DerivedSource. As an optimization, for any Source, if its does_not_need_splitting is true, the framework assumes that splitting this source would return SOURCE_SPLIT_OUTCOME_USE_CURRENT, and doesn't initiate a SourceSplitRequest. This applies both to the initial source being split and to bundles produced from it.", "properties": { "options": { "description": "Hints for tuning the splitting process.", "$ref": "SourceSplitOptions" }, "source": { "description": "Specification of the source to be split.", "$ref": "Source" } }, "type": "object" }, "StreamingComputationTask": { "description": "A task which describes what action should be performed for the specified streaming computation ranges.", "type": "object", "id": "StreamingComputationTask", "properties": { "dataDisks": { "items": { "$ref": "MountedDataDisk" }, "description": "Describes the set of data disks this task should apply to.", "type": "array" }, "taskType": { "type": "string", "description": "A type of streaming computation task.", "enumDescriptions": [ "The streaming computation task is unknown, or unspecified.", "Stop processing specified streaming computation range(s).", "Start processing specified streaming computation range(s)." ], "enum": [ "STREAMING_COMPUTATION_TASK_UNKNOWN", "STREAMING_COMPUTATION_TASK_STOP", "STREAMING_COMPUTATION_TASK_START" ] }, "computationRanges": { "type": "array", "items": { "$ref": "StreamingComputationRanges" }, "description": "Contains ranges of a streaming computation this task should apply to." } } }, "LaunchTemplateResponse": { "id": "LaunchTemplateResponse", "type": "object", "properties": { "job": { "$ref": "Job", "description": "The job that was launched, if the request was not a dry run and the job was successfully launched." } }, "description": "Response to the request to launch a template." }, "DisplayData": { "type": "object", "id": "DisplayData", "description": "Data provided with a pipeline or transform to provide descriptive info.", "properties": { "javaClassValue": { "description": "Contains value if the data is of java class type.", "type": "string" }, "url": { "description": "An optional full URL.", "type": "string" }, "floatValue": { "type": "number", "format": "float", "description": "Contains value if the data is of float type." }, "boolValue": { "description": "Contains value if the data is of a boolean type.", "type": "boolean" }, "shortStrValue": { "description": "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.", "type": "string" }, "label": { "description": "An optional label to display in a dax UI for the element.", "type": "string" }, "strValue": { "description": "Contains value if the data is of string type.", "type": "string" }, "int64Value": { "format": "int64", "type": "string", "description": "Contains value if the data is of int64 type." }, "timestampValue": { "type": "string", "description": "Contains value if the data is of timestamp type.", "format": "google-datetime" }, "namespace": { "description": "The namespace for the key. This is usually a class name or programming language namespace (i.e. python module) which defines the display data. This allows a dax monitoring system to specially handle the data and perform custom rendering.", "type": "string" }, "durationValue": { "type": "string", "description": "Contains value if the data is of duration type.", "format": "google-duration" }, "key": { "type": "string", "description": "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." } } }, "ApproximateReportedProgress": { "properties": { "position": { "$ref": "Position", "description": "A Position within the work to represent a progress." }, "consumedParallelism": { "$ref": "ReportedParallelism", "description": "Total amount of parallelism in the portion of input of this task that has already been consumed and is no longer active. In the first two examples above (see remaining_parallelism), the value should be 29 or 2 respectively. The sum of remaining_parallelism and consumed_parallelism should equal the total amount of parallelism in this work item. If specified, must be finite." }, "remainingParallelism": { "description": "Total amount of parallelism in the input of this task that remains, (i.e. can be delegated to this task and any new tasks via dynamic splitting). Always at least 1 for non-finished work items and 0 for finished. \"Amount of parallelism\" refers to how many non-empty parts of the input can be read in parallel. This does not necessarily equal number of records. An input that can be read in parallel down to the individual records is called \"perfectly splittable\". An example of non-perfectly parallelizable input is a block-compressed file format where a block of records has to be read as a whole, but different blocks can be read in parallel. Examples: * If we are processing record #30 (starting at 1) out of 50 in a perfectly splittable 50-record input, this value should be 21 (20 remaining + 1 current). * If we are reading through block 3 in a block-compressed file consisting of 5 blocks, this value should be 3 (since blocks 4 and 5 can be processed in parallel by new tasks via dynamic splitting and the current task remains processing block 3). * If we are reading through the last block in a block-compressed file, or reading or processing the last record in a perfectly splittable input, this value should be 1, because apart from the current task, no additional remainder can be split off.", "$ref": "ReportedParallelism" }, "fractionConsumed": { "type": "number", "format": "double", "description": "Completion as fraction of the input consumed, from 0.0 (beginning, nothing consumed), to 1.0 (end of the input, entire input consumed)." } }, "type": "object", "description": "A progress measurement of a WorkItem by a worker.", "id": "ApproximateReportedProgress" }, "JobExecutionInfo": { "id": "JobExecutionInfo", "properties": { "stages": { "description": "A mapping from each stage to the information about that stage.", "type": "object", "additionalProperties": { "$ref": "JobExecutionStageInfo" } } }, "type": "object", "description": "Additional information about how a Cloud Dataflow job will be executed that isn't contained in the submitted job." }, "PubsubLocation": { "description": "Identifies a pubsub location to use for transferring data into or out of a streaming Dataflow job.", "type": "object", "properties": { "subscription": { "description": "A pubsub subscription, in the form of \"pubsub.googleapis.com/subscriptions//\"", "type": "string" }, "topic": { "type": "string", "description": "A pubsub topic, in the form of \"pubsub.googleapis.com/topics//\"" }, "trackingSubscription": { "type": "string", "description": "If set, specifies the pubsub subscription that will be used for tracking custom time timestamps for watermark estimation." }, "withAttributes": { "type": "boolean", "description": "If true, then the client has requested to get pubsub attributes." }, "dropLateData": { "type": "boolean", "description": "Indicates whether the pipeline allows late-arriving data." }, "dynamicDestinations": { "description": "If true, then this location represents dynamic topics.", "type": "boolean" }, "timestampLabel": { "type": "string", "description": "If set, contains a pubsub label from which to extract record timestamps. If left empty, record timestamps will be generated upon arrival." }, "idLabel": { "description": "If set, contains a pubsub label from which to extract record ids. If left empty, record deduplication will be strictly best effort.", "type": "string" } }, "id": "PubsubLocation" }, "Position": { "description": "Position defines a position within a collection of data. The value can be either the end position, a key (used with ordered collections), a byte offset, or a record index.", "type": "object", "id": "Position", "properties": { "end": { "type": "boolean", "description": "Position is past all other positions. Also useful for the end position of an unbounded range." }, "key": { "description": "Position is a string key, ordered lexicographically.", "type": "string" }, "byteOffset": { "type": "string", "description": "Position is a byte offset.", "format": "int64" }, "shufflePosition": { "description": "CloudPosition is a base64 encoded BatchShufflePosition (with FIXED sharding).", "type": "string" }, "recordIndex": { "type": "string", "format": "int64", "description": "Position is a record index." }, "concatPosition": { "$ref": "ConcatPosition", "description": "CloudPosition is a concat position." } } }, "SourceSplitOptions": { "description": "Hints for splitting a Source into bundles (parts for parallel processing) using SourceSplitRequest.", "id": "SourceSplitOptions", "type": "object", "properties": { "desiredBundleSizeBytes": { "description": "The source should be split into a set of bundles where the estimated size of each is approximately this many bytes.", "format": "int64", "type": "string" }, "desiredShardSizeBytes": { "type": "string", "description": "DEPRECATED in favor of desired_bundle_size_bytes.", "deprecated": true, "format": "int64" } } }, "ApproximateSplitRequest": { "type": "object", "description": "A suggestion by the service to the worker to dynamically split the WorkItem.", "id": "ApproximateSplitRequest", "properties": { "position": { "description": "A Position at which to split the work item.", "$ref": "Position" }, "fractionConsumed": { "description": "A fraction at which to split the work item, from 0.0 (beginning of the input) to 1.0 (end of the input).", "format": "double", "type": "number" }, "fractionOfRemainder": { "description": "The fraction of the remainder of work to split the work item at, from 0.0 (split at the current position) to 1.0 (end of the input).", "type": "number", "format": "double" } } }, "SourceOperationResponse": { "description": "The result of a SourceOperationRequest, specified in ReportWorkItemStatusRequest.source_operation when the work item is completed.", "properties": { "getMetadata": { "description": "A response to a request to get metadata about a source.", "$ref": "SourceGetMetadataResponse" }, "split": { "$ref": "SourceSplitResponse", "description": "A response to a request to split a source." } }, "id": "SourceOperationResponse", "type": "object" }, "StructuredMessage": { "properties": { "messageText": { "description": "Human-readable version of message.", "type": "string" }, "messageKey": { "type": "string", "description": "Identifier for this message type. Used by external systems to internationalize or personalize message." }, "parameters": { "items": { "$ref": "Parameter" }, "description": "The structured data associated with this message.", "type": "array" } }, "type": "object", "description": "A rich message format, including a human readable string, a key for identifying the message, and structured data associated with the message for programmatic consumption.", "id": "StructuredMessage" }, "BigTableIODetails": { "properties": { "tableId": { "type": "string", "description": "TableId accessed in the connection." }, "instanceId": { "description": "InstanceId accessed in the connection.", "type": "string" }, "projectId": { "type": "string", "description": "ProjectId accessed in the connection." } }, "description": "Metadata for a Cloud Bigtable connector used by the job.", "type": "object", "id": "BigTableIODetails" }, "WorkerMessage": { "description": "WorkerMessage provides information to the backend about a worker.", "properties": { "workerMessageCode": { "$ref": "WorkerMessageCode", "description": "A worker message code." }, "workerMetrics": { "description": "Resource metrics reported by workers.", "$ref": "ResourceUtilizationReport" }, "labels": { "additionalProperties": { "type": "string" }, "type": "object", "description": "Labels are used to group WorkerMessages. For example, a worker_message about a particular container might have the labels: { \"JOB_ID\": \"2015-04-22\", \"WORKER_ID\": \"wordcount-vm-2015…\" \"CONTAINER_TYPE\": \"worker\", \"CONTAINER_ID\": \"ac1234def\"} Label tags typically correspond to Label enum values. However, for ease of development other strings can be used as tags. LABEL_UNSPECIFIED should not be used here." }, "dataSamplingReport": { "description": "Optional. Contains metrics related to go/dataflow-data-sampling-telemetry.", "$ref": "DataSamplingReport" }, "workerLifecycleEvent": { "description": "Record of worker lifecycle events.", "$ref": "WorkerLifecycleEvent" }, "workerThreadScalingReport": { "description": "Thread scaling information reported by workers.", "$ref": "WorkerThreadScalingReport" }, "workerHealthReport": { "$ref": "WorkerHealthReport", "description": "The health of a worker." }, "time": { "description": "The timestamp of the worker_message.", "format": "google-datetime", "type": "string" }, "workerShutdownNotice": { "description": "Shutdown notice by workers.", "$ref": "WorkerShutdownNotice" }, "perWorkerMetrics": { "$ref": "PerWorkerMetrics", "description": "System defined metrics for this worker." }, "streamingScalingReport": { "description": "Contains per-user worker telemetry used in streaming autoscaling.", "$ref": "StreamingScalingReport" } }, "id": "WorkerMessage", "type": "object" }, "StreamingSetupTask": { "description": "A task which initializes part of a streaming Dataflow job.", "id": "StreamingSetupTask", "properties": { "receiveWorkPort": { "type": "integer", "description": "The TCP port on which the worker should listen for messages from other streaming computation workers.", "format": "int32" }, "snapshotConfig": { "description": "Configures streaming appliance snapshot.", "$ref": "StreamingApplianceSnapshotConfig" }, "drain": { "description": "The user has requested drain.", "type": "boolean" }, "streamingComputationTopology": { "description": "The global topology of the streaming Dataflow job.", "$ref": "TopologyConfig" }, "workerHarnessPort": { "description": "The TCP port used by the worker to communicate with the Dataflow worker harness.", "format": "int32", "type": "integer" } }, "type": "object" }, "CounterStructuredName": { "id": "CounterStructuredName", "description": "Identifies a counter within a per-job namespace. Counters whose structured names are the same get merged into a single value for the job.", "properties": { "name": { "type": "string", "description": "Counter name. Not necessarily globally-unique, but unique within the context of the other fields. Required." }, "inputIndex": { "type": "integer", "description": "Index of an input collection that's being read from/written to as a side input. The index identifies a step's side inputs starting by 1 (e.g. the first side input has input_index 1, the third has input_index 3). Side inputs are identified by a pair of (original_step_name, input_index). This field helps uniquely identify them.", "format": "int32" }, "originalStepName": { "description": "System generated name of the original step in the user's graph, before optimization.", "type": "string" }, "originNamespace": { "description": "A string containing a more specific namespace of the counter's origin.", "type": "string" }, "origin": { "description": "One of the standard Origins defined above.", "type": "string", "enumDescriptions": [ "Counter was created by the Dataflow system.", "Counter was created by the user." ], "enum": [ "SYSTEM", "USER" ] }, "componentStepName": { "description": "Name of the optimized step being executed by the workers.", "type": "string" }, "portion": { "type": "string", "description": "Portion of this counter, either key or value.", "enum": [ "ALL", "KEY", "VALUE" ], "enumDescriptions": [ "Counter portion has not been set.", "Counter reports a key.", "Counter reports a value." ] }, "workerId": { "type": "string", "description": "ID of a particular worker." }, "executionStepName": { "description": "Name of the stage. An execution step contains multiple component steps.", "type": "string" }, "originalRequestingStepName": { "type": "string", "description": "The step name requesting an operation, such as GBK. I.e. the ParDo causing a read/write from shuffle to occur, or a read from side inputs." } }, "type": "object" }, "LaunchTemplateParameters": { "type": "object", "description": "Parameters to provide to the template being launched. Note that the [metadata in the pipeline code] (https://cloud.google.com/dataflow/docs/guides/templates/creating-templates#metadata) determines which runtime parameters are valid.", "id": "LaunchTemplateParameters", "properties": { "jobName": { "type": "string", "description": "Required. The job name to use for the created job. The name must match the regular expression `[a-z]([-a-z0-9]{0,1022}[a-z0-9])?`" }, "environment": { "description": "The runtime environment for the job.", "$ref": "RuntimeEnvironment" }, "parameters": { "additionalProperties": { "type": "string" }, "type": "object", "description": "The runtime parameters to pass to the job." }, "transformNameMapping": { "additionalProperties": { "type": "string" }, "description": "Only applicable when updating a pipeline. Map of transform name prefixes of the job to be replaced to the corresponding name prefixes of the new job.", "type": "object" }, "update": { "description": "If set, replace the existing pipeline with the name specified by jobName with this pipeline, preserving state.", "type": "boolean" } } }, "IntegerMean": { "description": "A representation of an integer mean metric contribution.", "properties": { "sum": { "description": "The sum of all values being aggregated.", "$ref": "SplitInt64" }, "count": { "description": "The number of values being aggregated.", "$ref": "SplitInt64" } }, "type": "object", "id": "IntegerMean" }, "ReadInstruction": { "type": "object", "description": "An instruction that reads records. Takes no inputs, produces one output.", "properties": { "source": { "description": "The source to read from.", "$ref": "Source" } }, "id": "ReadInstruction" }, "StreamingStragglerInfo": { "properties": { "workerName": { "description": "Name of the worker where the straggler was detected.", "type": "string" }, "dataWatermarkLag": { "type": "string", "format": "google-duration", "description": "The event-time watermark lag at the time of the straggler detection." }, "endTime": { "description": "End time of this straggler.", "format": "google-datetime", "type": "string" }, "systemWatermarkLag": { "format": "google-duration", "type": "string", "description": "The system watermark lag at the time of the straggler detection." }, "startTime": { "description": "Start time of this straggler.", "format": "google-datetime", "type": "string" } }, "description": "Information useful for streaming straggler identification and debugging.", "id": "StreamingStragglerInfo", "type": "object" }, "StringList": { "description": "A metric value representing a list of strings.", "id": "StringList", "properties": { "elements": { "items": { "type": "string" }, "description": "Elements of the list.", "type": "array" } }, "type": "object" }, "SdkBug": { "type": "object", "id": "SdkBug", "properties": { "type": { "enumDescriptions": [ "Unknown issue with this SDK.", "Catch-all for SDK bugs that don't fit in the below categories.", "Using this version of the SDK may result in degraded performance.", "Using this version of the SDK may cause data loss." ], "enum": [ "TYPE_UNSPECIFIED", "GENERAL", "PERFORMANCE", "DATALOSS" ], "readOnly": true, "type": "string", "description": "Output only. Describes the impact of this SDK bug." }, "severity": { "enumDescriptions": [ "A bug of unknown severity.", "A minor bug that that may reduce reliability or performance for some jobs. Impact will be minimal or non-existent for most jobs.", "A bug that has some likelihood of causing performance degradation, data loss, or job failures.", "A bug with extremely significant impact. Jobs may fail erroneously, performance may be severely degraded, and data loss may be very likely." ], "readOnly": true, "type": "string", "description": "Output only. How severe the SDK bug is.", "enum": [ "SEVERITY_UNSPECIFIED", "NOTICE", "WARNING", "SEVERE" ] }, "uri": { "type": "string", "readOnly": true, "description": "Output only. Link to more information on the bug." } }, "description": "A bug found in the Dataflow SDK." }, "AutoscalingSettings": { "description": "Settings for WorkerPool autoscaling.", "properties": { "algorithm": { "enumDescriptions": [ "The algorithm is unknown, or unspecified.", "Disable autoscaling.", "Increase worker count over time to reduce job execution time." ], "type": "string", "enum": [ "AUTOSCALING_ALGORITHM_UNKNOWN", "AUTOSCALING_ALGORITHM_NONE", "AUTOSCALING_ALGORITHM_BASIC" ], "description": "The algorithm to use for autoscaling." }, "maxNumWorkers": { "description": "The maximum number of workers to cap scaling at.", "format": "int32", "type": "integer" } }, "id": "AutoscalingSettings", "type": "object" }, "WorkerThreadScalingReportResponse": { "id": "WorkerThreadScalingReportResponse", "type": "object", "description": "Contains the thread scaling recommendation for a worker from the backend.", "properties": { "recommendedThreadCount": { "format": "int32", "description": "Recommended number of threads for a worker.", "type": "integer" } } }, "PerWorkerMetrics": { "properties": { "perStepNamespaceMetrics": { "description": "Optional. Metrics for a particular unfused step and namespace.", "items": { "$ref": "PerStepNamespaceMetrics" }, "type": "array" } }, "type": "object", "id": "PerWorkerMetrics", "description": "Per worker metrics." }, "LeaseWorkItemResponse": { "properties": { "workItems": { "type": "array", "description": "A list of the leased WorkItems.", "items": { "$ref": "WorkItem" } }, "unifiedWorkerResponse": { "type": "object", "description": "Untranslated bag-of-bytes WorkResponse for UnifiedWorker.", "additionalProperties": { "type": "any", "description": "Properties of the object. Contains field @type with type URL." } } }, "id": "LeaseWorkItemResponse", "description": "Response to a request to lease WorkItems.", "type": "object" }, "SeqMapTask": { "description": "Describes a particular function to invoke.", "properties": { "systemName": { "description": "System-defined name of the SeqDo operation. Unique across the workflow.", "type": "string" }, "stageName": { "type": "string", "description": "System-defined name of the stage containing the SeqDo operation. Unique across the workflow." }, "inputs": { "items": { "$ref": "SideInputInfo" }, "type": "array", "description": "Information about each of the inputs." }, "userFn": { "type": "object", "additionalProperties": { "description": "Properties of the object.", "type": "any" }, "description": "The user function to invoke." }, "name": { "description": "The user-provided name of the SeqDo operation.", "type": "string" }, "outputInfos": { "description": "Information about each of the outputs.", "items": { "$ref": "SeqMapTaskOutputInfo" }, "type": "array" } }, "id": "SeqMapTask", "type": "object" }, "ConcatPosition": { "type": "object", "properties": { "index": { "type": "integer", "format": "int32", "description": "Index of the inner source." }, "position": { "$ref": "Position", "description": "Position within the inner source." } }, "id": "ConcatPosition", "description": "A position that encapsulates an inner position and an index for the inner position. A ConcatPosition can be used by a reader of a source that encapsulates a set of other sources." }, "ParameterMetadataEnumOption": { "id": "ParameterMetadataEnumOption", "description": "ParameterMetadataEnumOption specifies the option shown in the enum form.", "type": "object", "properties": { "value": { "description": "Required. The value of the enum option.", "type": "string" }, "label": { "description": "Optional. The label to display for the enum option.", "type": "string" }, "description": { "type": "string", "description": "Optional. The description to display for the enum option." } } }, "SDKInfo": { "id": "SDKInfo", "description": "SDK Information.", "properties": { "language": { "enumDescriptions": [ "UNKNOWN Language.", "Java.", "Python.", "Go.", "YAML." ], "type": "string", "enum": [ "UNKNOWN", "JAVA", "PYTHON", "GO", "YAML" ], "description": "Required. The SDK Language." }, "version": { "type": "string", "description": "Optional. The SDK version." } }, "type": "object" }, "CreateJobFromTemplateRequest": { "id": "CreateJobFromTemplateRequest", "description": "A request to create a Cloud Dataflow job from a template.", "type": "object", "properties": { "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request.", "type": "string" }, "parameters": { "type": "object", "additionalProperties": { "type": "string" }, "description": "The runtime parameters to pass to the job." }, "jobName": { "type": "string", "description": "Required. The job name to use for the created job." }, "environment": { "description": "The runtime environment for the job.", "$ref": "RuntimeEnvironment" }, "gcsPath": { "description": "Required. A Cloud Storage path to the template from which to create the job. Must be a valid Cloud Storage URL, beginning with `gs://`.", "type": "string" } } }, "PipelineDescription": { "type": "object", "description": "A descriptive representation of submitted pipeline as well as the executed form. This data is provided by the Dataflow service for ease of visualizing the pipeline and interpreting Dataflow provided metrics.", "id": "PipelineDescription", "properties": { "executionPipelineStage": { "description": "Description of each stage of execution of the pipeline.", "items": { "$ref": "ExecutionStageSummary" }, "type": "array" }, "stepNamesHash": { "type": "string", "description": "A hash value of the submitted pipeline portable graph step names if exists." }, "originalPipelineTransform": { "type": "array", "items": { "$ref": "TransformSummary" }, "description": "Description of each transform in the pipeline and collections between them." }, "displayData": { "items": { "$ref": "DisplayData" }, "description": "Pipeline level display data.", "type": "array" } } }, "ComponentSource": { "type": "object", "id": "ComponentSource", "description": "Description of an interstitial value between transforms in an execution stage.", "properties": { "userName": { "description": "Human-readable name for this transform; may be user or system generated.", "type": "string" }, "originalTransformOrCollection": { "description": "User name for the original user transform or collection with which this source is most closely associated.", "type": "string" }, "name": { "description": "Dataflow service generated name for this source.", "type": "string" } } }, "StreamLocation": { "properties": { "pubsubLocation": { "description": "The stream is a pubsub stream.", "$ref": "PubsubLocation" }, "sideInputLocation": { "$ref": "StreamingSideInputLocation", "description": "The stream is a streaming side input." }, "customSourceLocation": { "description": "The stream is a custom source.", "$ref": "CustomSourceLocation" }, "streamingStageLocation": { "description": "The stream is part of another computation within the current streaming Dataflow job.", "$ref": "StreamingStageLocation" } }, "id": "StreamLocation", "type": "object", "description": "Describes a stream of data, either as input to be processed or as output of a streaming Dataflow job." }, "SdkHarnessContainerImage": { "type": "object", "properties": { "containerImage": { "description": "A docker container image that resides in Google Container Registry.", "type": "string" }, "useSingleCorePerContainer": { "description": "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.", "type": "boolean" }, "environmentId": { "description": "Environment ID for the Beam runner API proto Environment that corresponds to the current SDK Harness.", "type": "string" }, "capabilities": { "items": { "type": "string" }, "type": "array", "description": "The set of capabilities enumerated in the above Environment proto. See also [beam_runner_api.proto](https://github.com/apache/beam/blob/master/model/pipeline/src/main/proto/org/apache/beam/model/pipeline/v1/beam_runner_api.proto)" } }, "description": "Defines an SDK harness container for executing Dataflow pipelines.", "id": "SdkHarnessContainerImage" }, "SdkVersion": { "description": "The version of the SDK used to run the job.", "properties": { "version": { "type": "string", "description": "The version of the SDK used to run the job." }, "sdkSupportStatus": { "description": "The support status for this SDK version.", "enum": [ "UNKNOWN", "SUPPORTED", "STALE", "DEPRECATED", "UNSUPPORTED" ], "enumDescriptions": [ "Cloud Dataflow is unaware of this version.", "This is a known version of an SDK, and is supported.", "A newer version of the SDK family exists, and an update is recommended.", "This version of the SDK is deprecated and will eventually be unsupported.", "Support for this SDK version has ended and it should no longer be used." ], "type": "string" }, "bugs": { "readOnly": true, "type": "array", "description": "Output only. Known bugs found in this SDK version.", "items": { "$ref": "SdkBug" } }, "versionDisplayName": { "type": "string", "description": "A readable string describing the version of the SDK." } }, "id": "SdkVersion", "type": "object" }, "MapTask": { "type": "object", "id": "MapTask", "properties": { "instructions": { "items": { "$ref": "ParallelInstruction" }, "type": "array", "description": "The instructions in the MapTask." }, "systemName": { "type": "string", "description": "System-defined name of this MapTask. Unique across the workflow." }, "counterPrefix": { "description": "Counter prefix that can be used to prefix counters. Not currently used in Dataflow.", "type": "string" }, "stageName": { "description": "System-defined name of the stage containing this MapTask. Unique across the workflow.", "type": "string" } }, "description": "MapTask consists of an ordered set of instructions, each of which describes one particular low-level operation for the worker to perform in order to accomplish the MapTask's WorkItem. Each instruction must appear in the list before any instructions which depends on its output." }, "ListJobMessagesResponse": { "description": "Response to a request to list job messages.", "properties": { "autoscalingEvents": { "items": { "$ref": "AutoscalingEvent" }, "type": "array", "description": "Autoscaling events in ascending timestamp order." }, "nextPageToken": { "description": "The token to obtain the next page of results if there are more.", "type": "string" }, "jobMessages": { "items": { "$ref": "JobMessage" }, "type": "array", "description": "Messages in ascending timestamp order." } }, "id": "ListJobMessagesResponse", "type": "object" }, "IntegerGauge": { "id": "IntegerGauge", "description": "A metric value representing temporal values of a variable.", "type": "object", "properties": { "timestamp": { "format": "google-datetime", "description": "The time at which this value was measured. Measured as msecs from epoch.", "type": "string" }, "value": { "$ref": "SplitInt64", "description": "The value of the variable represented by this gauge." } } }, "StreamingComputationConfig": { "description": "Configuration information for a single streaming computation.", "type": "object", "properties": { "instructions": { "type": "array", "items": { "$ref": "ParallelInstruction" }, "description": "Instructions that comprise the computation." }, "computationId": { "description": "Unique identifier for this computation.", "type": "string" }, "stageName": { "description": "Stage name of this computation.", "type": "string" }, "systemName": { "type": "string", "description": "System defined name for this computation." }, "transformUserNameToStateFamily": { "description": "Map from user name of stateful transforms in this stage to their state family.", "additionalProperties": { "type": "string" }, "type": "object" } }, "id": "StreamingComputationConfig" }, "BucketOptions": { "type": "object", "id": "BucketOptions", "properties": { "linear": { "$ref": "Linear", "description": "Bucket boundaries grow linearly." }, "exponential": { "$ref": "Base2Exponent", "description": "Bucket boundaries grow exponentially." } }, "description": "`BucketOptions` describes the bucket boundaries used in the histogram." }, "FloatingPointMean": { "type": "object", "properties": { "count": { "$ref": "SplitInt64", "description": "The number of values being aggregated." }, "sum": { "type": "number", "description": "The sum of all values being aggregated.", "format": "double" } }, "description": "A representation of a floating point mean metric contribution.", "id": "FloatingPointMean" }, "WorkerShutdownNotice": { "id": "WorkerShutdownNotice", "type": "object", "description": "Shutdown notification from workers. This is to be sent by the shutdown script of the worker VM so that the backend knows that the VM is being shut down.", "properties": { "reason": { "description": "The reason for the worker shutdown. Current possible values are: \"UNKNOWN\": shutdown reason is unknown. \"PREEMPTION\": shutdown reason is preemption. Other possible reasons may be added in the future.", "type": "string" } } }, "DebugOptions": { "description": "Describes any options that have an effect on the debugging of pipelines.", "properties": { "dataSampling": { "$ref": "DataSamplingConfig", "description": "Configuration options for sampling elements from a running pipeline." }, "enableHotKeyLogging": { "description": "Optional. When true, enables the logging of the literal hot key to the user's Cloud Logging.", "type": "boolean" } }, "type": "object", "id": "DebugOptions" }, "Disk": { "description": "Describes the data disk used by a workflow job.", "properties": { "mountPoint": { "description": "Directory in a VM where disk is mounted.", "type": "string" }, "diskType": { "description": "Disk storage type, as defined by Google Compute Engine. This must be a disk type appropriate to the project and zone in which the workers will run. If unknown or unspecified, the service will attempt to choose a reasonable default. For example, the standard persistent disk type is a resource name typically ending in \"pd-standard\". If SSD persistent disks are available, the resource name typically ends with \"pd-ssd\". The actual valid values are defined the Google Compute Engine API, not by the Cloud Dataflow API; consult the Google Compute Engine documentation for more information about determining the set of available disk types for a particular project and zone. Google Compute Engine Disk types are local to a particular project in a particular zone, and so the resource name will typically look something like this: compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-standard", "type": "string" }, "sizeGb": { "type": "integer", "description": "Size of disk in GB. If zero or unspecified, the service will attempt to choose a reasonable default.", "format": "int32" } }, "type": "object", "id": "Disk" }, "ListConfigStoreSettingsResponse": { "properties": { "configStoreSettings": { "type": "array", "items": { "$ref": "ConfigStoreSetting" }, "description": "The list of ConfigStoreSettings." }, "nextPageToken": { "type": "string", "description": "A token that can be sent as `page_token` to retrieve the next page." } }, "description": "Response message for ListConfigStoreSettings.", "type": "object", "id": "ListConfigStoreSettingsResponse" }, "LaunchFlexTemplateResponse": { "properties": { "job": { "$ref": "Job", "description": "The job that was launched, if the request was not a dry run and the job was successfully launched." } }, "description": "Response to the request to launch a job from Flex Template.", "type": "object", "id": "LaunchFlexTemplateResponse" }, "JobExecutionDetails": { "type": "object", "description": "Information about the execution of a job.", "id": "JobExecutionDetails", "properties": { "stages": { "type": "array", "items": { "$ref": "StageSummary" }, "description": "The stages of the job execution." }, "nextPageToken": { "description": "If present, this response does not contain all requested tasks. To obtain the next page of results, repeat the request with page_token set to this value.", "type": "string" } } }, "Snapshot": { "id": "Snapshot", "properties": { "pubsubMetadata": { "items": { "$ref": "PubsubSnapshotMetadata" }, "description": "Pub/Sub snapshot metadata.", "type": "array" }, "region": { "description": "Cloud region where this snapshot lives in, e.g., \"us-central1\".", "type": "string" }, "state": { "enum": [ "UNKNOWN_SNAPSHOT_STATE", "PENDING", "RUNNING", "READY", "FAILED", "DELETED" ], "enumDescriptions": [ "Unknown state.", "Snapshot intent to create has been persisted, snapshotting of state has not yet started.", "Snapshotting is being performed.", "Snapshot has been created and is ready to be used.", "Snapshot failed to be created.", "Snapshot has been deleted." ], "description": "State of the snapshot.", "type": "string" }, "creationTime": { "format": "google-datetime", "description": "The time this snapshot was created.", "type": "string" }, "id": { "type": "string", "description": "The unique ID of this snapshot." }, "sourceJobId": { "description": "The job this snapshot was created from.", "type": "string" }, "diskSizeBytes": { "type": "string", "description": "The disk byte size of the snapshot. Only available for snapshots in READY state.", "format": "int64" }, "projectId": { "description": "The project this snapshot belongs to.", "type": "string" }, "ttl": { "format": "google-duration", "type": "string", "description": "The time after which this snapshot will be automatically deleted." }, "description": { "description": "User specified description of the snapshot. Maybe empty.", "type": "string" } }, "type": "object", "description": "Represents a snapshot of a job." } }, "ownerName": "Google", "version": "v1b3", "ownerDomain": "google.com", "resources": { "organizations": { "resources": { "locations": { "resources": { "configStoreSettings": { "methods": { "resolve": { "path": "v1b3/{+name}:resolve", "id": "dataflow.organizations.locations.configStoreSettings.resolve", "httpMethod": "POST", "parameters": { "name": { "type": "string", "pattern": "^organizations/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$", "location": "path", "description": "Required. The name of the setting to resolve.", "required": true } }, "response": { "$ref": "ResolveConfigStoreSettingResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "flatPath": "v1b3/organizations/{organizationsId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}:resolve", "description": "Resolves effective value of a ConfigStoreSetting.", "request": { "$ref": "ResolveConfigStoreSettingRequest" }, "parameterOrder": [ "name" ] }, "get": { "description": "Gets a ConfigStoreSetting.", "response": { "$ref": "ConfigStoreSetting" }, "path": "v1b3/{+name}", "parameterOrder": [ "name" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "id": "dataflow.organizations.locations.configStoreSettings.get", "flatPath": "v1b3/organizations/{organizationsId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}", "httpMethod": "GET", "parameters": { "name": { "description": "Required. The name of the ConfigStoreSetting to retrieve.", "pattern": "^organizations/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$", "location": "path", "required": true, "type": "string" } } }, "create": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "flatPath": "v1b3/organizations/{organizationsId}/locations/{locationsId}/configStoreSettings", "request": { "$ref": "ConfigStoreSetting" }, "path": "v1b3/{+parent}/configStoreSettings", "httpMethod": "POST", "response": { "$ref": "ConfigStoreSetting" }, "parameters": { "parent": { "pattern": "^organizations/[^/]+/locations/[^/]+$", "required": true, "description": "Required. The parent resource where this setting will be created.", "type": "string", "location": "path" }, "configStoreSettingId": { "type": "string", "description": "Required. The ID to use for the setting.", "location": "query" } }, "id": "dataflow.organizations.locations.configStoreSettings.create", "description": "Creates a new ConfigStoreSetting.", "parameterOrder": [ "parent" ] }, "list": { "response": { "$ref": "ListConfigStoreSettingsResponse" }, "id": "dataflow.organizations.locations.configStoreSettings.list", "description": "Lists ConfigStoreSettings.", "parameterOrder": [ "parent" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameters": { "pageToken": { "type": "string", "description": "Optional. A page token, received from a previous `ListConfigStoreSettings` call.", "location": "query" }, "pageSize": { "format": "int32", "description": "Optional. The maximum number of settings to return.", "location": "query", "type": "integer" }, "parent": { "location": "path", "description": "Required. The parent resource whose settings are being listed.", "type": "string", "required": true, "pattern": "^organizations/[^/]+/locations/[^/]+$" } }, "path": "v1b3/{+parent}/configStoreSettings", "httpMethod": "GET", "flatPath": "v1b3/organizations/{organizationsId}/locations/{locationsId}/configStoreSettings" }, "delete": { "parameters": { "name": { "type": "string", "location": "path", "required": true, "description": "Required. The name of the ConfigStoreSetting to delete.", "pattern": "^organizations/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$" } }, "response": { "$ref": "Empty" }, "httpMethod": "DELETE", "description": "Deletes an existing ConfigStoreSetting.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "id": "dataflow.organizations.locations.configStoreSettings.delete", "flatPath": "v1b3/organizations/{organizationsId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}", "parameterOrder": [ "name" ], "path": "v1b3/{+name}" } } } } } } }, "folders": { "resources": { "locations": { "resources": { "configStoreSettings": { "methods": { "resolve": { "request": { "$ref": "ResolveConfigStoreSettingRequest" }, "parameters": { "name": { "required": true, "description": "Required. The name of the setting to resolve.", "type": "string", "location": "path", "pattern": "^folders/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$" } }, "parameterOrder": [ "name" ], "flatPath": "v1b3/folders/{foldersId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}:resolve", "description": "Resolves effective value of a ConfigStoreSetting.", "httpMethod": "POST", "id": "dataflow.folders.locations.configStoreSettings.resolve", "response": { "$ref": "ResolveConfigStoreSettingResponse" }, "path": "v1b3/{+name}:resolve", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] }, "get": { "httpMethod": "GET", "response": { "$ref": "ConfigStoreSetting" }, "parameterOrder": [ "name" ], "parameters": { "name": { "description": "Required. The name of the ConfigStoreSetting to retrieve.", "required": true, "pattern": "^folders/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$", "type": "string", "location": "path" } }, "id": "dataflow.folders.locations.configStoreSettings.get", "description": "Gets a ConfigStoreSetting.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/{+name}", "flatPath": "v1b3/folders/{foldersId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}" }, "delete": { "path": "v1b3/{+name}", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameterOrder": [ "name" ], "flatPath": "v1b3/folders/{foldersId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}", "description": "Deletes an existing ConfigStoreSetting.", "httpMethod": "DELETE", "id": "dataflow.folders.locations.configStoreSettings.delete", "parameters": { "name": { "type": "string", "pattern": "^folders/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$", "location": "path", "description": "Required. The name of the ConfigStoreSetting to delete.", "required": true } }, "response": { "$ref": "Empty" } }, "list": { "parameters": { "parent": { "description": "Required. The parent resource whose settings are being listed.", "pattern": "^folders/[^/]+/locations/[^/]+$", "location": "path", "type": "string", "required": true }, "pageToken": { "description": "Optional. A page token, received from a previous `ListConfigStoreSettings` call.", "location": "query", "type": "string" }, "pageSize": { "description": "Optional. The maximum number of settings to return.", "location": "query", "type": "integer", "format": "int32" } }, "response": { "$ref": "ListConfigStoreSettingsResponse" }, "path": "v1b3/{+parent}/configStoreSettings", "id": "dataflow.folders.locations.configStoreSettings.list", "httpMethod": "GET", "parameterOrder": [ "parent" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "flatPath": "v1b3/folders/{foldersId}/locations/{locationsId}/configStoreSettings", "description": "Lists ConfigStoreSettings." }, "create": { "response": { "$ref": "ConfigStoreSetting" }, "request": { "$ref": "ConfigStoreSetting" }, "parameterOrder": [ "parent" ], "parameters": { "configStoreSettingId": { "description": "Required. The ID to use for the setting.", "type": "string", "location": "query" }, "parent": { "required": true, "type": "string", "pattern": "^folders/[^/]+/locations/[^/]+$", "location": "path", "description": "Required. The parent resource where this setting will be created." } }, "description": "Creates a new ConfigStoreSetting.", "flatPath": "v1b3/folders/{foldersId}/locations/{locationsId}/configStoreSettings", "id": "dataflow.folders.locations.configStoreSettings.create", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "httpMethod": "POST", "path": "v1b3/{+parent}/configStoreSettings" } } } } } } }, "projects": { "methods": { "deleteSnapshots": { "description": "Deletes a snapshot.", "flatPath": "v1b3/projects/{projectId}/snapshots", "parameterOrder": [ "projectId" ], "httpMethod": "DELETE", "parameters": { "location": { "type": "string", "location": "query", "description": "The location that contains this snapshot." }, "projectId": { "type": "string", "location": "path", "required": true, "description": "The ID of the Cloud Platform project that the snapshot belongs to." }, "snapshotId": { "description": "The ID of the snapshot.", "type": "string", "location": "query" } }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/projects/{projectId}/snapshots", "id": "dataflow.projects.deleteSnapshots", "response": { "$ref": "DeleteSnapshotResponse" } }, "workerMessages": { "response": { "$ref": "SendWorkerMessagesResponse" }, "id": "dataflow.projects.workerMessages", "httpMethod": "POST", "description": "Send a worker_message to the service.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/projects/{projectId}/WorkerMessages", "parameterOrder": [ "projectId" ], "parameters": { "projectId": { "location": "path", "required": true, "type": "string", "description": "The project to send the WorkerMessages to." } }, "request": { "$ref": "SendWorkerMessagesRequest" }, "flatPath": "v1b3/projects/{projectId}/WorkerMessages" } }, "resources": { "snapshots": { "methods": { "get": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "response": { "$ref": "Snapshot" }, "parameterOrder": [ "projectId", "snapshotId" ], "id": "dataflow.projects.snapshots.get", "path": "v1b3/projects/{projectId}/snapshots/{snapshotId}", "description": "Gets information about a snapshot.", "parameters": { "snapshotId": { "location": "path", "required": true, "type": "string", "description": "The ID of the snapshot." }, "location": { "location": "query", "description": "The location that contains this snapshot.", "type": "string" }, "projectId": { "type": "string", "location": "path", "required": true, "description": "The ID of the Cloud Platform project that the snapshot belongs to." } }, "httpMethod": "GET", "flatPath": "v1b3/projects/{projectId}/snapshots/{snapshotId}" }, "list": { "httpMethod": "GET", "parameters": { "location": { "location": "query", "type": "string", "description": "The location to list snapshots in." }, "projectId": { "type": "string", "location": "path", "required": true, "description": "The project ID to list snapshots for." }, "jobId": { "description": "If specified, list snapshots created from this job.", "type": "string", "location": "query" } }, "response": { "$ref": "ListSnapshotsResponse" }, "description": "Lists snapshots.", "id": "dataflow.projects.snapshots.list", "flatPath": "v1b3/projects/{projectId}/snapshots", "path": "v1b3/projects/{projectId}/snapshots", "parameterOrder": [ "projectId" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] } } }, "locations": { "methods": { "workerMessages": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "flatPath": "v1b3/projects/{projectId}/locations/{location}/WorkerMessages", "parameters": { "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job.", "location": "path", "required": true, "type": "string" }, "projectId": { "description": "The project to send the WorkerMessages to.", "location": "path", "required": true, "type": "string" } }, "parameterOrder": [ "projectId", "location" ], "httpMethod": "POST", "description": "Send a worker_message to the service.", "id": "dataflow.projects.locations.workerMessages", "request": { "$ref": "SendWorkerMessagesRequest" }, "path": "v1b3/projects/{projectId}/locations/{location}/WorkerMessages", "response": { "$ref": "SendWorkerMessagesResponse" } } }, "resources": { "templates": { "methods": { "launch": { "path": "v1b3/projects/{projectId}/locations/{location}/templates:launch", "request": { "$ref": "LaunchTemplateParameters" }, "response": { "$ref": "LaunchTemplateResponse" }, "id": "dataflow.projects.locations.templates.launch", "flatPath": "v1b3/projects/{projectId}/locations/{location}/templates:launch", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "description": "Launches a template. To launch a template, we recommend using `projects.locations.templates.launch` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.templates.launch` is not recommended, because jobs launched from the template will always start in `us-central1`. # IAM Permissions Requires the following IAM permission(s) on the project: - `dataflow.jobs.create` - `resourcemanager.projects.get`", "parameters": { "validateOnly": { "description": "If true, the request is validated but not actually executed. Defaults to false.", "type": "boolean", "location": "query" }, "gcsPath": { "description": "A Cloud Storage path to the template to use to create the job. Must be valid Cloud Storage URL, beginning with `gs://`.", "type": "string", "location": "query" }, "projectId": { "description": "Required. The ID of the Cloud Platform project that the job belongs to.", "type": "string", "location": "path", "required": true }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request.", "type": "string", "location": "path", "required": true }, "dynamicTemplate.gcsPath": { "location": "query", "type": "string", "description": "Path to the dynamic template specification file on Cloud Storage. The file must be a JSON serialized `DynamicTemplateFileSpec` object." }, "dynamicTemplate.stagingLocation": { "type": "string", "location": "query", "description": "Cloud Storage path for staging dependencies. Must be a valid Cloud Storage URL, beginning with `gs://`." } }, "parameterOrder": [ "projectId", "location" ], "httpMethod": "POST" }, "get": { "parameters": { "projectId": { "location": "path", "required": true, "description": "Required. The ID of the Cloud Platform project that the job belongs to.", "type": "string" }, "view": { "location": "query", "enumDescriptions": [ "Template view that retrieves only the metadata associated with the template." ], "enum": [ "METADATA_ONLY" ], "description": "The view to retrieve. Defaults to METADATA_ONLY.", "type": "string" }, "location": { "type": "string", "location": "path", "required": true, "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request." }, "gcsPath": { "location": "query", "description": "Required. A Cloud Storage path to the template from which to create the job. Must be valid Cloud Storage URL, beginning with 'gs://'.", "type": "string" } }, "response": { "$ref": "GetTemplateResponse" }, "httpMethod": "GET", "description": "Get the template associated with a template. To get the template, we recommend using `projects.locations.templates.get` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.templates.get` is not recommended, because only templates that are running in `us-central1` are retrieved. # IAM Permissions Requires the `resourcemanager.projects.get` permission on the project.", "parameterOrder": [ "projectId", "location" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/projects/{projectId}/locations/{location}/templates:get", "id": "dataflow.projects.locations.templates.get", "flatPath": "v1b3/projects/{projectId}/locations/{location}/templates:get" }, "create": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameters": { "projectId": { "description": "Required. The ID of the Cloud Platform project that the job belongs to.", "location": "path", "required": true, "type": "string" }, "location": { "type": "string", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request.", "location": "path", "required": true } }, "response": { "$ref": "Job" }, "httpMethod": "POST", "parameterOrder": [ "projectId", "location" ], "description": "Creates a Cloud Dataflow job from a template. Do not enter confidential information when you supply string values using the API. To create a job, we recommend using `projects.locations.templates.create` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.templates.create` is not recommended, because your job will always start in `us-central1`. # IAM Permissions Requires the following IAM permission(s) on the project: - `dataflow.jobs.create` - `resourcemanager.projects.get`", "id": "dataflow.projects.locations.templates.create", "flatPath": "v1b3/projects/{projectId}/locations/{location}/templates", "path": "v1b3/projects/{projectId}/locations/{location}/templates", "request": { "$ref": "CreateJobFromTemplateRequest" } } } }, "jobs": { "methods": { "update": { "response": { "$ref": "Job" }, "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}", "request": { "$ref": "Job" }, "httpMethod": "PUT", "parameterOrder": [ "projectId", "location", "jobId" ], "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}", "id": "dataflow.projects.locations.jobs.update", "description": "Updates the state of an existing Cloud Dataflow job. To update the state of an existing job, we recommend using `projects.locations.jobs.update` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.update` is not recommended, as you can only update the state of jobs that are running in `us-central1`. # IAM Permissions 1. Requires the `dataflow.jobs.cancel` permission to cancel a job. 2. Requires the `dataflow.jobs.updateContents` permission to update runtime parameters.", "parameters": { "updateMask": { "description": "The list of fields to update relative to Job. If empty, only RequestedJobState will be considered for update. If the FieldMask is not empty and RequestedJobState is none/empty, The fields specified in the update mask will be the only ones considered for update. If both RequestedJobState and update_mask are specified, an error will be returned as we cannot update both state and mask.", "location": "query", "type": "string", "format": "google-fieldmask" }, "jobId": { "location": "path", "required": true, "description": "The job ID.", "type": "string" }, "projectId": { "location": "path", "required": true, "type": "string", "description": "The ID of the Cloud Platform project that the job belongs to." }, "location": { "type": "string", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "location": "path", "required": true } }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] }, "getMetrics": { "parameterOrder": [ "projectId", "location", "jobId" ], "response": { "$ref": "JobMetrics" }, "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics", "description": "Request the job status. To request the status of a job, we recommend using `projects.locations.jobs.getMetrics` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.getMetrics` is not recommended, as you can only request the status of jobs that are running in `us-central1`. # IAM Permissions Requires the `dataflow.metrics.get` permission on the job.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "id": "dataflow.projects.locations.jobs.getMetrics", "parameters": { "location": { "location": "path", "required": true, "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id.", "type": "string" }, "projectId": { "type": "string", "description": "A project id.", "location": "path", "required": true }, "jobId": { "description": "The job to get metrics for.", "type": "string", "location": "path", "required": true }, "startTime": { "format": "google-datetime", "description": "Return only metric data that has changed since this time. Default is to return all information about all metrics for the job.", "type": "string", "location": "query" } }, "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/metrics", "httpMethod": "GET" }, "get": { "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}", "id": "dataflow.projects.locations.jobs.get", "parameters": { "projectId": { "type": "string", "location": "path", "required": true, "description": "The ID of the Cloud Platform project that the job belongs to." }, "jobId": { "type": "string", "location": "path", "required": true, "description": "The job ID." }, "view": { "description": "The level of information requested in response.", "location": "query", "type": "string", "enumDescriptions": [ "The job view to return isn't specified, or is unknown. Responses will contain at least the `JOB_VIEW_SUMMARY` information, and may contain additional information.", "Request summary information only: Project ID, Job ID, job name, job type, job status, start/end time, and Cloud SDK version details.", "Request all information available for this job. When the job is in `JOB_STATE_PENDING`, the job has been created but is not yet running, and not all job information is available. For complete job information, wait until the job in is `JOB_STATE_RUNNING`. For more information, see [JobState](https://cloud.google.com/dataflow/docs/reference/rest/v1b3/projects.jobs#jobstate).", "Request summary info and limited job description data for steps, labels and environment." ], "enum": [ "JOB_VIEW_UNKNOWN", "JOB_VIEW_SUMMARY", "JOB_VIEW_ALL", "JOB_VIEW_DESCRIPTION" ] }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "location": "path", "required": true, "type": "string" } }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "response": { "$ref": "Job" }, "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}", "description": "Gets the state of the specified Cloud Dataflow job. To get the state of a job, we recommend using `projects.locations.jobs.get` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.get` is not recommended, as you can only get the state of jobs that are running in `us-central1`. # IAM Permissions Requires the `dataflow.jobs.get` permission on the job.", "parameterOrder": [ "projectId", "location", "jobId" ], "httpMethod": "GET" }, "snapshot": { "parameterOrder": [ "projectId", "location", "jobId" ], "request": { "$ref": "SnapshotJobRequest" }, "id": "dataflow.projects.locations.jobs.snapshot", "response": { "$ref": "Snapshot" }, "httpMethod": "POST", "description": "Snapshot the state of a streaming job. # IAM Permissions Requires the `dataflow.jobs.snapshot` permission on the job.", "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}:snapshot", "parameters": { "location": { "description": "The location that contains this job.", "location": "path", "required": true, "type": "string" }, "projectId": { "type": "string", "location": "path", "required": true, "description": "The project which owns the job to be snapshotted." }, "jobId": { "description": "The job to be snapshotted.", "location": "path", "required": true, "type": "string" } }, "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}:snapshot", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] }, "getExecutionDetails": { "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/executionDetails", "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/executionDetails", "description": "Request detailed information about the execution status of the job. EXPERIMENTAL. This API is subject to change or removal without notice. # IAM Permissions Requires the `dataflow.metrics.get` permission on the job.", "parameterOrder": [ "projectId", "location", "jobId" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameters": { "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id.", "location": "path", "required": true, "type": "string" }, "projectId": { "type": "string", "location": "path", "required": true, "description": "A project id." }, "pageToken": { "location": "query", "type": "string", "description": "If supplied, this should be the value of next_page_token returned by an earlier call. This will cause the next page of results to be returned." }, "pageSize": { "format": "int32", "description": "If specified, determines the maximum number of stages to return. If unspecified, the service may choose an appropriate default, or may return an arbitrarily large number of results.", "location": "query", "type": "integer" }, "jobId": { "description": "The job to get execution details for.", "location": "path", "required": true, "type": "string" } }, "id": "dataflow.projects.locations.jobs.getExecutionDetails", "response": { "$ref": "JobExecutionDetails" }, "httpMethod": "GET" }, "list": { "description": "List the jobs of a project. To list the jobs of a project in a region, we recommend using `projects.locations.jobs.list` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). To list the all jobs across all regions, use `projects.jobs.aggregated`. Using `projects.jobs.list` is not recommended, because you can only get the list of jobs that are running in `us-central1`. `projects.locations.jobs.list` and `projects.jobs.list` support filtering the list of jobs by name. Filtering by name isn't supported by `projects.jobs.aggregated`. # IAM Permissions Requires the `dataflow.jobs.list` permission on the project.", "path": "v1b3/projects/{projectId}/locations/{location}/jobs", "parameterOrder": [ "projectId", "location" ], "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs", "response": { "$ref": "ListJobsResponse" }, "parameters": { "regionalFanoutRequested": { "description": "Optional.", "location": "query", "type": "boolean" }, "filter": { "enum": [ "UNKNOWN", "ALL", "TERMINATED", "ACTIVE" ], "location": "query", "description": "The kind of filter to use.", "enumDescriptions": [ "The filter isn't specified, or is unknown. This returns all jobs ordered on descending `JobUuid`.", "Returns all running jobs first ordered on creation timestamp, then returns all terminated jobs ordered on the termination timestamp.", "Filters the jobs that have a terminated state, ordered on the termination timestamp. Example terminated states: `JOB_STATE_STOPPED`, `JOB_STATE_UPDATED`, `JOB_STATE_DRAINED`, etc.", "Filters the jobs that are running ordered on the creation timestamp." ], "type": "string" }, "view": { "deprecated": true, "enum": [ "JOB_VIEW_UNKNOWN", "JOB_VIEW_SUMMARY", "JOB_VIEW_ALL", "JOB_VIEW_DESCRIPTION" ], "type": "string", "location": "query", "description": "Deprecated. ListJobs always returns summaries now. Use GetJob for other JobViews.", "enumDescriptions": [ "The job view to return isn't specified, or is unknown. Responses will contain at least the `JOB_VIEW_SUMMARY` information, and may contain additional information.", "Request summary information only: Project ID, Job ID, job name, job type, job status, start/end time, and Cloud SDK version details.", "Request all information available for this job. When the job is in `JOB_STATE_PENDING`, the job has been created but is not yet running, and not all job information is available. For complete job information, wait until the job in is `JOB_STATE_RUNNING`. For more information, see [JobState](https://cloud.google.com/dataflow/docs/reference/rest/v1b3/projects.jobs#jobstate).", "Request summary info and limited job description data for steps, labels and environment." ] }, "name": { "type": "string", "location": "query", "description": "Optional. The job name." }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "type": "string", "location": "path", "required": true }, "projectId": { "description": "The project which owns the jobs.", "type": "string", "location": "path", "required": true }, "pageToken": { "location": "query", "type": "string", "description": "Set this to the 'next_page_token' field of a previous response to request additional results in a long list." }, "pageSize": { "location": "query", "format": "int32", "description": "If there are many jobs, limit response to at most this many. The actual number of jobs returned will be the lesser of max_responses and an unspecified server-defined limit.", "type": "integer" } }, "id": "dataflow.projects.locations.jobs.list", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "httpMethod": "GET" }, "create": { "path": "v1b3/projects/{projectId}/locations/{location}/jobs", "response": { "$ref": "Job" }, "httpMethod": "POST", "id": "dataflow.projects.locations.jobs.create", "parameters": { "projectId": { "type": "string", "description": "The ID of the Cloud Platform project that the job belongs to.", "location": "path", "required": true }, "view": { "description": "The level of information requested in response.", "enumDescriptions": [ "The job view to return isn't specified, or is unknown. Responses will contain at least the `JOB_VIEW_SUMMARY` information, and may contain additional information.", "Request summary information only: Project ID, Job ID, job name, job type, job status, start/end time, and Cloud SDK version details.", "Request all information available for this job. When the job is in `JOB_STATE_PENDING`, the job has been created but is not yet running, and not all job information is available. For complete job information, wait until the job in is `JOB_STATE_RUNNING`. For more information, see [JobState](https://cloud.google.com/dataflow/docs/reference/rest/v1b3/projects.jobs#jobstate).", "Request summary info and limited job description data for steps, labels and environment." ], "enum": [ "JOB_VIEW_UNKNOWN", "JOB_VIEW_SUMMARY", "JOB_VIEW_ALL", "JOB_VIEW_DESCRIPTION" ], "type": "string", "location": "query" }, "replaceJobId": { "type": "string", "location": "query", "description": "Deprecated. This field is now in the Job message." }, "location": { "location": "path", "required": true, "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "type": "string" } }, "description": "Creates a Dataflow job. To create a job, we recommend using `projects.locations.jobs.create` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.create` is not recommended, as your job will always start in `us-central1`. Do not enter confidential information when you supply string values using the API. # IAM Permissions 1. Requires the `dataflow.jobs.create` permission on the project. 2. `resourcemanager.projects.get` (Specifically required for regional endpoints to resolve regional resource metadata)", "parameterOrder": [ "projectId", "location" ], "request": { "$ref": "Job" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs" } }, "resources": { "stages": { "methods": { "getExecutionDetails": { "description": "Request detailed information about the execution status of a stage of the job. EXPERIMENTAL. This API is subject to change or removal without notice. # IAM Permissions Requires the `dataflow.metrics.get` permission on the job.", "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/stages/{stageId}/executionDetails", "httpMethod": "GET", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameters": { "stageId": { "description": "The stage for which to fetch information.", "type": "string", "location": "path", "required": true }, "startTime": { "type": "string", "description": "Lower time bound of work items to include, by start time.", "format": "google-datetime", "location": "query" }, "endTime": { "format": "google-datetime", "description": "Upper time bound of work items to include, by start time.", "type": "string", "location": "query" }, "jobId": { "description": "The job to get execution details for.", "type": "string", "location": "path", "required": true }, "pageSize": { "description": "If specified, determines the maximum number of work items to return. If unspecified, the service may choose an appropriate default, or may return an arbitrarily large number of results.", "type": "integer", "location": "query", "format": "int32" }, "projectId": { "description": "A project id.", "type": "string", "location": "path", "required": true }, "pageToken": { "description": "If supplied, this should be the value of next_page_token returned by an earlier call. This will cause the next page of results to be returned.", "location": "query", "type": "string" }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id.", "location": "path", "required": true, "type": "string" } }, "response": { "$ref": "StageExecutionDetails" }, "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/stages/{stageId}/executionDetails", "id": "dataflow.projects.locations.jobs.stages.getExecutionDetails", "parameterOrder": [ "projectId", "location", "jobId", "stageId" ] } } }, "snapshots": { "methods": { "list": { "description": "Lists snapshots.", "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/snapshots", "httpMethod": "GET", "parameterOrder": [ "projectId", "location", "jobId" ], "parameters": { "projectId": { "type": "string", "location": "path", "required": true, "description": "The project ID to list snapshots for." }, "location": { "location": "path", "required": true, "type": "string", "description": "The location to list snapshots in." }, "jobId": { "description": "If specified, list snapshots created from this job.", "type": "string", "location": "path", "required": true } }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "id": "dataflow.projects.locations.jobs.snapshots.list", "response": { "$ref": "ListSnapshotsResponse" }, "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/snapshots" } } }, "debug": { "methods": { "getWorkerStacktraces": { "httpMethod": "POST", "id": "dataflow.projects.locations.jobs.debug.getWorkerStacktraces", "parameters": { "location": { "location": "path", "required": true, "type": "string", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id." }, "jobId": { "type": "string", "location": "path", "required": true, "description": "The job for which to get stacktraces." }, "projectId": { "type": "string", "description": "The project id.", "location": "path", "required": true } }, "response": { "$ref": "GetWorkerStacktracesResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/getWorkerStacktraces", "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/getWorkerStacktraces", "parameterOrder": [ "projectId", "location", "jobId" ], "request": { "$ref": "GetWorkerStacktracesRequest" }, "description": "Get worker stacktraces from debug capture." }, "getConfig": { "description": "Get encoded debug configuration for component. Not cacheable.", "id": "dataflow.projects.locations.jobs.debug.getConfig", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "request": { "$ref": "GetDebugConfigRequest" }, "response": { "$ref": "GetDebugConfigResponse" }, "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/getConfig", "httpMethod": "POST", "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/getConfig", "parameters": { "jobId": { "location": "path", "required": true, "description": "The job id.", "type": "string" }, "location": { "location": "path", "required": true, "type": "string", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id." }, "projectId": { "type": "string", "location": "path", "required": true, "description": "The project id." } }, "parameterOrder": [ "projectId", "location", "jobId" ] }, "sendCapture": { "id": "dataflow.projects.locations.jobs.debug.sendCapture", "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/sendCapture", "parameters": { "jobId": { "type": "string", "location": "path", "required": true, "description": "The job id." }, "location": { "location": "path", "required": true, "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id.", "type": "string" }, "projectId": { "location": "path", "required": true, "type": "string", "description": "The project id." } }, "response": { "$ref": "SendDebugCaptureResponse" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "request": { "$ref": "SendDebugCaptureRequest" }, "description": "Send encoded debug capture data for component.", "httpMethod": "POST", "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/debug/sendCapture", "parameterOrder": [ "projectId", "location", "jobId" ] } } }, "workItems": { "methods": { "lease": { "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "request": { "$ref": "LeaseWorkItemRequest" }, "parameterOrder": [ "projectId", "location", "jobId" ], "response": { "$ref": "LeaseWorkItemResponse" }, "parameters": { "projectId": { "description": "Identifies the project this worker belongs to.", "location": "path", "required": true, "type": "string" }, "jobId": { "description": "Identifies the workflow job this worker belongs to.", "location": "path", "required": true, "type": "string" }, "location": { "location": "path", "required": true, "type": "string", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the WorkItem's job." } }, "httpMethod": "POST", "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease", "id": "dataflow.projects.locations.jobs.workItems.lease", "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:lease", "description": "Leases a dataflow WorkItem to run." }, "reportStatus": { "parameterOrder": [ "projectId", "location", "jobId" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus", "request": { "$ref": "ReportWorkItemStatusRequest" }, "id": "dataflow.projects.locations.jobs.workItems.reportStatus", "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/workItems:reportStatus", "description": "Reports the status of dataflow WorkItems leased by a worker.", "response": { "$ref": "ReportWorkItemStatusResponse" }, "parameters": { "jobId": { "location": "path", "required": true, "description": "The job which the WorkItem is part of.", "type": "string" }, "location": { "type": "string", "location": "path", "required": true, "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the WorkItem's job." }, "projectId": { "location": "path", "required": true, "description": "The project which owns the WorkItem's job.", "type": "string" } }, "httpMethod": "POST" } } }, "messages": { "methods": { "list": { "id": "dataflow.projects.locations.jobs.messages.list", "path": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages", "flatPath": "v1b3/projects/{projectId}/locations/{location}/jobs/{jobId}/messages", "response": { "$ref": "ListJobMessagesResponse" }, "parameters": { "projectId": { "location": "path", "required": true, "description": "A project id.", "type": "string" }, "pageToken": { "location": "query", "type": "string", "description": "If supplied, this should be the value of next_page_token returned by an earlier call. This will cause the next page of results to be returned." }, "jobId": { "description": "The job to get messages about.", "location": "path", "required": true, "type": "string" }, "pageSize": { "type": "integer", "description": "If specified, determines the maximum number of messages to return. If unspecified, the service may choose an appropriate default, or may return an arbitrarily large number of results.", "format": "int32", "location": "query" }, "startTime": { "description": "If specified, return only messages with timestamps \u003e= start_time. The default is the job creation time (i.e. beginning of messages).", "location": "query", "format": "google-datetime", "type": "string" }, "minimumImportance": { "enum": [ "JOB_MESSAGE_IMPORTANCE_UNKNOWN", "JOB_MESSAGE_DEBUG", "JOB_MESSAGE_DETAILED", "JOB_MESSAGE_BASIC", "JOB_MESSAGE_WARNING", "JOB_MESSAGE_ERROR" ], "description": "Filter to only get messages with importance \u003e= level", "type": "string", "location": "query", "enumDescriptions": [ "The message importance isn't specified, or is unknown.", "The message is at the 'debug' level: typically only useful for software engineers working on the code the job is running. Typically, Dataflow pipeline runners do not display log messages at this level by default.", "The message is at the 'detailed' level: somewhat verbose, but potentially useful to users. Typically, Dataflow pipeline runners do not display log messages at this level by default. These messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'basic' level: useful for keeping track of the execution of a Dataflow pipeline. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'warning' level: indicating a condition pertaining to a job which may require human intervention. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'error' level: indicating a condition preventing a job from succeeding. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI." ] }, "endTime": { "type": "string", "description": "Return only messages with timestamps \u003c end_time. The default is now (i.e. return up to the latest messages available).", "format": "google-datetime", "location": "query" }, "location": { "location": "path", "required": true, "type": "string", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id." } }, "parameterOrder": [ "projectId", "location", "jobId" ], "description": "Request the job status. To request the status of a job, we recommend using `projects.locations.jobs.messages.list` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.messages.list` is not recommended, as you can only request the status of jobs that are running in `us-central1`. # IAM Permissions Requires the `dataflow.messages.list` permission on the job.", "httpMethod": "GET", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] } } } } }, "snapshots": { "methods": { "get": { "httpMethod": "GET", "parameters": { "snapshotId": { "location": "path", "required": true, "type": "string", "description": "The ID of the snapshot." }, "projectId": { "description": "The ID of the Cloud Platform project that the snapshot belongs to.", "location": "path", "required": true, "type": "string" }, "location": { "type": "string", "location": "path", "required": true, "description": "The location that contains this snapshot." } }, "path": "v1b3/projects/{projectId}/locations/{location}/snapshots/{snapshotId}", "response": { "$ref": "Snapshot" }, "description": "Gets information about a snapshot.", "flatPath": "v1b3/projects/{projectId}/locations/{location}/snapshots/{snapshotId}", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameterOrder": [ "projectId", "location", "snapshotId" ], "id": "dataflow.projects.locations.snapshots.get" }, "list": { "httpMethod": "GET", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameters": { "projectId": { "location": "path", "required": true, "description": "The project ID to list snapshots for.", "type": "string" }, "location": { "type": "string", "description": "The location to list snapshots in.", "location": "path", "required": true }, "jobId": { "location": "query", "type": "string", "description": "If specified, list snapshots created from this job." } }, "id": "dataflow.projects.locations.snapshots.list", "response": { "$ref": "ListSnapshotsResponse" }, "description": "Lists snapshots.", "parameterOrder": [ "projectId", "location" ], "flatPath": "v1b3/projects/{projectId}/locations/{location}/snapshots", "path": "v1b3/projects/{projectId}/locations/{location}/snapshots" }, "delete": { "parameters": { "location": { "type": "string", "location": "path", "required": true, "description": "The location that contains this snapshot." }, "projectId": { "description": "The ID of the Cloud Platform project that the snapshot belongs to.", "type": "string", "location": "path", "required": true }, "snapshotId": { "type": "string", "description": "The ID of the snapshot.", "location": "path", "required": true } }, "id": "dataflow.projects.locations.snapshots.delete", "parameterOrder": [ "projectId", "location", "snapshotId" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "response": { "$ref": "DeleteSnapshotResponse" }, "httpMethod": "DELETE", "flatPath": "v1b3/projects/{projectId}/locations/{location}/snapshots/{snapshotId}", "path": "v1b3/projects/{projectId}/locations/{location}/snapshots/{snapshotId}", "description": "Deletes a snapshot." } } }, "flexTemplates": { "methods": { "launch": { "request": { "$ref": "LaunchFlexTemplateRequest" }, "parameters": { "projectId": { "description": "Required. The ID of the Cloud Platform project that the job belongs to.", "location": "path", "required": true, "type": "string" }, "location": { "description": "Required. The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request. E.g., us-central1, us-west1.", "location": "path", "required": true, "type": "string" } }, "id": "dataflow.projects.locations.flexTemplates.launch", "flatPath": "v1b3/projects/{projectId}/locations/{location}/flexTemplates:launch", "parameterOrder": [ "projectId", "location" ], "httpMethod": "POST", "path": "v1b3/projects/{projectId}/locations/{location}/flexTemplates:launch", "response": { "$ref": "LaunchFlexTemplateResponse" }, "description": "Launch a job with a FlexTemplate. # IAM Permissions Requires the following IAM permission(s) on the resource: - `dataflow.jobs.create` - `resourcemanager.projects.get` - `iam.serviceAccounts.actAs` - `storage.buckets.get` - `storage.buckets.create` (Required if the default staging bucket must be created)", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] } } }, "configStoreSettings": { "methods": { "resolve": { "parameters": { "name": { "location": "path", "pattern": "^projects/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$", "required": true, "type": "string", "description": "Required. The name of the setting to resolve." } }, "request": { "$ref": "ResolveConfigStoreSettingRequest" }, "parameterOrder": [ "name" ], "response": { "$ref": "ResolveConfigStoreSettingResponse" }, "description": "Resolves effective value of a ConfigStoreSetting.", "httpMethod": "POST", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "flatPath": "v1b3/projects/{projectsId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}:resolve", "id": "dataflow.projects.locations.configStoreSettings.resolve", "path": "v1b3/{+name}:resolve" }, "get": { "response": { "$ref": "ConfigStoreSetting" }, "httpMethod": "GET", "id": "dataflow.projects.locations.configStoreSettings.get", "parameters": { "name": { "required": true, "pattern": "^projects/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$", "location": "path", "description": "Required. The name of the ConfigStoreSetting to retrieve.", "type": "string" } }, "parameterOrder": [ "name" ], "path": "v1b3/{+name}", "description": "Gets a ConfigStoreSetting.", "flatPath": "v1b3/projects/{projectsId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] }, "create": { "parameters": { "configStoreSettingId": { "type": "string", "description": "Required. The ID to use for the setting.", "location": "query" }, "parent": { "description": "Required. The parent resource where this setting will be created.", "location": "path", "pattern": "^projects/[^/]+/locations/[^/]+$", "required": true, "type": "string" } }, "flatPath": "v1b3/projects/{projectsId}/locations/{locationsId}/configStoreSettings", "httpMethod": "POST", "description": "Creates a new ConfigStoreSetting.", "path": "v1b3/{+parent}/configStoreSettings", "request": { "$ref": "ConfigStoreSetting" }, "parameterOrder": [ "parent" ], "response": { "$ref": "ConfigStoreSetting" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "id": "dataflow.projects.locations.configStoreSettings.create" }, "list": { "httpMethod": "GET", "path": "v1b3/{+parent}/configStoreSettings", "id": "dataflow.projects.locations.configStoreSettings.list", "response": { "$ref": "ListConfigStoreSettingsResponse" }, "parameters": { "pageToken": { "type": "string", "location": "query", "description": "Optional. A page token, received from a previous `ListConfigStoreSettings` call." }, "parent": { "location": "path", "required": true, "description": "Required. The parent resource whose settings are being listed.", "pattern": "^projects/[^/]+/locations/[^/]+$", "type": "string" }, "pageSize": { "description": "Optional. The maximum number of settings to return.", "format": "int32", "location": "query", "type": "integer" } }, "description": "Lists ConfigStoreSettings.", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "flatPath": "v1b3/projects/{projectsId}/locations/{locationsId}/configStoreSettings", "parameterOrder": [ "parent" ] }, "delete": { "path": "v1b3/{+name}", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "response": { "$ref": "Empty" }, "id": "dataflow.projects.locations.configStoreSettings.delete", "httpMethod": "DELETE", "description": "Deletes an existing ConfigStoreSetting.", "flatPath": "v1b3/projects/{projectsId}/locations/{locationsId}/configStoreSettings/{configStoreSettingsId}", "parameters": { "name": { "pattern": "^projects/[^/]+/locations/[^/]+/configStoreSettings/[^/]+$", "location": "path", "description": "Required. The name of the ConfigStoreSetting to delete.", "type": "string", "required": true } }, "parameterOrder": [ "name" ] } } } } }, "jobs": { "resources": { "debug": { "methods": { "sendCapture": { "id": "dataflow.projects.jobs.debug.sendCapture", "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/sendCapture", "parameterOrder": [ "projectId", "jobId" ], "description": "Send encoded debug capture data for component.", "httpMethod": "POST", "request": { "$ref": "SendDebugCaptureRequest" }, "response": { "$ref": "SendDebugCaptureResponse" }, "parameters": { "projectId": { "type": "string", "location": "path", "required": true, "description": "The project id." }, "jobId": { "location": "path", "required": true, "description": "The job id.", "type": "string" } } }, "getConfig": { "path": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig", "parameters": { "projectId": { "type": "string", "location": "path", "required": true, "description": "The project id." }, "jobId": { "type": "string", "location": "path", "required": true, "description": "The job id." } }, "response": { "$ref": "GetDebugConfigResponse" }, "parameterOrder": [ "projectId", "jobId" ], "request": { "$ref": "GetDebugConfigRequest" }, "httpMethod": "POST", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "description": "Get encoded debug configuration for component. Not cacheable.", "id": "dataflow.projects.jobs.debug.getConfig", "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/debug/getConfig" } } }, "messages": { "methods": { "list": { "response": { "$ref": "ListJobMessagesResponse" }, "parameters": { "pageSize": { "format": "int32", "location": "query", "type": "integer", "description": "If specified, determines the maximum number of messages to return. If unspecified, the service may choose an appropriate default, or may return an arbitrarily large number of results." }, "projectId": { "description": "A project id.", "location": "path", "required": true, "type": "string" }, "pageToken": { "type": "string", "location": "query", "description": "If supplied, this should be the value of next_page_token returned by an earlier call. This will cause the next page of results to be returned." }, "location": { "location": "query", "type": "string", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id." }, "endTime": { "description": "Return only messages with timestamps \u003c end_time. The default is now (i.e. return up to the latest messages available).", "format": "google-datetime", "location": "query", "type": "string" }, "startTime": { "type": "string", "location": "query", "description": "If specified, return only messages with timestamps \u003e= start_time. The default is the job creation time (i.e. beginning of messages).", "format": "google-datetime" }, "jobId": { "location": "path", "required": true, "type": "string", "description": "The job to get messages about." }, "minimumImportance": { "enum": [ "JOB_MESSAGE_IMPORTANCE_UNKNOWN", "JOB_MESSAGE_DEBUG", "JOB_MESSAGE_DETAILED", "JOB_MESSAGE_BASIC", "JOB_MESSAGE_WARNING", "JOB_MESSAGE_ERROR" ], "location": "query", "enumDescriptions": [ "The message importance isn't specified, or is unknown.", "The message is at the 'debug' level: typically only useful for software engineers working on the code the job is running. Typically, Dataflow pipeline runners do not display log messages at this level by default.", "The message is at the 'detailed' level: somewhat verbose, but potentially useful to users. Typically, Dataflow pipeline runners do not display log messages at this level by default. These messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'basic' level: useful for keeping track of the execution of a Dataflow pipeline. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'warning' level: indicating a condition pertaining to a job which may require human intervention. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI.", "The message is at the 'error' level: indicating a condition preventing a job from succeeding. Typically, Dataflow pipeline runners display log messages at this level by default, and these messages are displayed by default in the Dataflow monitoring UI." ], "description": "Filter to only get messages with importance \u003e= level", "type": "string" } }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "description": "Request the job status. To request the status of a job, we recommend using `projects.locations.jobs.messages.list` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.messages.list` is not recommended, as you can only request the status of jobs that are running in `us-central1`. # IAM Permissions Requires the `dataflow.messages.list` permission on the job.", "path": "v1b3/projects/{projectId}/jobs/{jobId}/messages", "httpMethod": "GET", "id": "dataflow.projects.jobs.messages.list", "parameterOrder": [ "projectId", "jobId" ], "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/messages" } } }, "workItems": { "methods": { "lease": { "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease", "description": "Leases a dataflow WorkItem to run.", "request": { "$ref": "LeaseWorkItemRequest" }, "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:lease", "id": "dataflow.projects.jobs.workItems.lease", "response": { "$ref": "LeaseWorkItemResponse" }, "parameters": { "jobId": { "type": "string", "description": "Identifies the workflow job this worker belongs to.", "location": "path", "required": true }, "projectId": { "location": "path", "required": true, "description": "Identifies the project this worker belongs to.", "type": "string" } }, "parameterOrder": [ "projectId", "jobId" ], "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "httpMethod": "POST" }, "reportStatus": { "parameters": { "jobId": { "type": "string", "location": "path", "required": true, "description": "The job which the WorkItem is part of." }, "projectId": { "type": "string", "description": "The project which owns the WorkItem's job.", "location": "path", "required": true } }, "httpMethod": "POST", "id": "dataflow.projects.jobs.workItems.reportStatus", "request": { "$ref": "ReportWorkItemStatusRequest" }, "description": "Reports the status of dataflow WorkItems leased by a worker.", "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus", "response": { "$ref": "ReportWorkItemStatusResponse" }, "parameterOrder": [ "projectId", "jobId" ], "path": "v1b3/projects/{projectId}/jobs/{jobId}/workItems:reportStatus", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] } } } }, "methods": { "get": { "parameterOrder": [ "projectId", "jobId" ], "path": "v1b3/projects/{projectId}/jobs/{jobId}", "id": "dataflow.projects.jobs.get", "response": { "$ref": "Job" }, "parameters": { "projectId": { "location": "path", "required": true, "type": "string", "description": "The ID of the Cloud Platform project that the job belongs to." }, "view": { "enum": [ "JOB_VIEW_UNKNOWN", "JOB_VIEW_SUMMARY", "JOB_VIEW_ALL", "JOB_VIEW_DESCRIPTION" ], "description": "The level of information requested in response.", "location": "query", "enumDescriptions": [ "The job view to return isn't specified, or is unknown. Responses will contain at least the `JOB_VIEW_SUMMARY` information, and may contain additional information.", "Request summary information only: Project ID, Job ID, job name, job type, job status, start/end time, and Cloud SDK version details.", "Request all information available for this job. When the job is in `JOB_STATE_PENDING`, the job has been created but is not yet running, and not all job information is available. For complete job information, wait until the job in is `JOB_STATE_RUNNING`. For more information, see [JobState](https://cloud.google.com/dataflow/docs/reference/rest/v1b3/projects.jobs#jobstate).", "Request summary info and limited job description data for steps, labels and environment." ], "type": "string" }, "jobId": { "location": "path", "required": true, "type": "string", "description": "The job ID." }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "location": "query", "type": "string" } }, "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}", "description": "Gets the state of the specified Cloud Dataflow job. To get the state of a job, we recommend using `projects.locations.jobs.get` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.get` is not recommended, as you can only get the state of jobs that are running in `us-central1`. # IAM Permissions Requires the `dataflow.jobs.get` permission on the job.", "httpMethod": "GET", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] }, "update": { "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}", "id": "dataflow.projects.jobs.update", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameters": { "jobId": { "description": "The job ID.", "location": "path", "required": true, "type": "string" }, "updateMask": { "format": "google-fieldmask", "location": "query", "description": "The list of fields to update relative to Job. If empty, only RequestedJobState will be considered for update. If the FieldMask is not empty and RequestedJobState is none/empty, The fields specified in the update mask will be the only ones considered for update. If both RequestedJobState and update_mask are specified, an error will be returned as we cannot update both state and mask.", "type": "string" }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "type": "string", "location": "query" }, "projectId": { "type": "string", "location": "path", "required": true, "description": "The ID of the Cloud Platform project that the job belongs to." } }, "parameterOrder": [ "projectId", "jobId" ], "request": { "$ref": "Job" }, "path": "v1b3/projects/{projectId}/jobs/{jobId}", "description": "Updates the state of an existing Cloud Dataflow job. To update the state of an existing job, we recommend using `projects.locations.jobs.update` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.update` is not recommended, as you can only update the state of jobs that are running in `us-central1`. # IAM Permissions 1. Requires the `dataflow.jobs.cancel` permission to cancel a job. 2. Requires the `dataflow.jobs.updateContents` permission to update runtime parameters.", "httpMethod": "PUT", "response": { "$ref": "Job" } }, "aggregated": { "httpMethod": "GET", "response": { "$ref": "ListJobsResponse" }, "parameters": { "view": { "enumDescriptions": [ "The job view to return isn't specified, or is unknown. Responses will contain at least the `JOB_VIEW_SUMMARY` information, and may contain additional information.", "Request summary information only: Project ID, Job ID, job name, job type, job status, start/end time, and Cloud SDK version details.", "Request all information available for this job. When the job is in `JOB_STATE_PENDING`, the job has been created but is not yet running, and not all job information is available. For complete job information, wait until the job in is `JOB_STATE_RUNNING`. For more information, see [JobState](https://cloud.google.com/dataflow/docs/reference/rest/v1b3/projects.jobs#jobstate).", "Request summary info and limited job description data for steps, labels and environment." ], "type": "string", "deprecated": true, "description": "Deprecated. ListJobs always returns summaries now. Use GetJob for other JobViews.", "enum": [ "JOB_VIEW_UNKNOWN", "JOB_VIEW_SUMMARY", "JOB_VIEW_ALL", "JOB_VIEW_DESCRIPTION" ], "location": "query" }, "name": { "type": "string", "description": "Optional. The job name.", "location": "query" }, "regionalFanoutRequested": { "description": "Optional.", "location": "query", "type": "boolean" }, "filter": { "enumDescriptions": [ "The filter isn't specified, or is unknown. This returns all jobs ordered on descending `JobUuid`.", "Returns all running jobs first ordered on creation timestamp, then returns all terminated jobs ordered on the termination timestamp.", "Filters the jobs that have a terminated state, ordered on the termination timestamp. Example terminated states: `JOB_STATE_STOPPED`, `JOB_STATE_UPDATED`, `JOB_STATE_DRAINED`, etc.", "Filters the jobs that are running ordered on the creation timestamp." ], "location": "query", "type": "string", "enum": [ "UNKNOWN", "ALL", "TERMINATED", "ACTIVE" ], "description": "The kind of filter to use." }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "location": "query", "type": "string" }, "projectId": { "location": "path", "required": true, "description": "The project which owns the jobs.", "type": "string" }, "pageToken": { "description": "Set this to the 'next_page_token' field of a previous response to request additional results in a long list.", "type": "string", "location": "query" }, "pageSize": { "type": "integer", "location": "query", "format": "int32", "description": "If there are many jobs, limit response to at most this many. The actual number of jobs returned will be the lesser of max_responses and an unspecified server-defined limit." } }, "description": "List the jobs of a project across all regions. **Note:** This method doesn't support filtering the list of jobs by name. # IAM Permissions Requires the `dataflow.jobs.list` permission on the project.", "path": "v1b3/projects/{projectId}/jobs:aggregated", "id": "dataflow.projects.jobs.aggregated", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameterOrder": [ "projectId" ], "flatPath": "v1b3/projects/{projectId}/jobs:aggregated" }, "list": { "response": { "$ref": "ListJobsResponse" }, "parameters": { "filter": { "location": "query", "description": "The kind of filter to use.", "type": "string", "enumDescriptions": [ "The filter isn't specified, or is unknown. This returns all jobs ordered on descending `JobUuid`.", "Returns all running jobs first ordered on creation timestamp, then returns all terminated jobs ordered on the termination timestamp.", "Filters the jobs that have a terminated state, ordered on the termination timestamp. Example terminated states: `JOB_STATE_STOPPED`, `JOB_STATE_UPDATED`, `JOB_STATE_DRAINED`, etc.", "Filters the jobs that are running ordered on the creation timestamp." ], "enum": [ "UNKNOWN", "ALL", "TERMINATED", "ACTIVE" ] }, "view": { "location": "query", "type": "string", "enumDescriptions": [ "The job view to return isn't specified, or is unknown. Responses will contain at least the `JOB_VIEW_SUMMARY` information, and may contain additional information.", "Request summary information only: Project ID, Job ID, job name, job type, job status, start/end time, and Cloud SDK version details.", "Request all information available for this job. When the job is in `JOB_STATE_PENDING`, the job has been created but is not yet running, and not all job information is available. For complete job information, wait until the job in is `JOB_STATE_RUNNING`. For more information, see [JobState](https://cloud.google.com/dataflow/docs/reference/rest/v1b3/projects.jobs#jobstate).", "Request summary info and limited job description data for steps, labels and environment." ], "deprecated": true, "description": "Deprecated. ListJobs always returns summaries now. Use GetJob for other JobViews.", "enum": [ "JOB_VIEW_UNKNOWN", "JOB_VIEW_SUMMARY", "JOB_VIEW_ALL", "JOB_VIEW_DESCRIPTION" ] }, "name": { "location": "query", "type": "string", "description": "Optional. The job name." }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "type": "string", "location": "query" }, "regionalFanoutRequested": { "type": "boolean", "location": "query", "description": "Optional." }, "projectId": { "location": "path", "required": true, "type": "string", "description": "The project which owns the jobs." }, "pageToken": { "location": "query", "type": "string", "description": "Set this to the 'next_page_token' field of a previous response to request additional results in a long list." }, "pageSize": { "location": "query", "format": "int32", "description": "If there are many jobs, limit response to at most this many. The actual number of jobs returned will be the lesser of max_responses and an unspecified server-defined limit.", "type": "integer" } }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/projects/{projectId}/jobs", "id": "dataflow.projects.jobs.list", "httpMethod": "GET", "parameterOrder": [ "projectId" ], "flatPath": "v1b3/projects/{projectId}/jobs", "description": "List the jobs of a project. To list the jobs of a project in a region, we recommend using `projects.locations.jobs.list` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). To list the all jobs across all regions, use `projects.jobs.aggregated`. Using `projects.jobs.list` is not recommended, because you can only get the list of jobs that are running in `us-central1`. `projects.locations.jobs.list` and `projects.jobs.list` support filtering the list of jobs by name. Filtering by name isn't supported by `projects.jobs.aggregated`. # IAM Permissions Requires the `dataflow.jobs.list` permission on the project." }, "getMetrics": { "response": { "$ref": "JobMetrics" }, "parameterOrder": [ "projectId", "jobId" ], "description": "Request the job status. To request the status of a job, we recommend using `projects.locations.jobs.getMetrics` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.getMetrics` is not recommended, as you can only request the status of jobs that are running in `us-central1`. # IAM Permissions Requires the `dataflow.metrics.get` permission on the job.", "id": "dataflow.projects.jobs.getMetrics", "parameters": { "jobId": { "location": "path", "required": true, "type": "string", "description": "The job to get metrics for." }, "location": { "type": "string", "location": "query", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id." }, "projectId": { "description": "A project id.", "type": "string", "location": "path", "required": true }, "startTime": { "format": "google-datetime", "type": "string", "location": "query", "description": "Return only metric data that has changed since this time. Default is to return all information about all metrics for the job." } }, "httpMethod": "GET", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/projects/{projectId}/jobs/{jobId}/metrics", "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}/metrics" }, "create": { "httpMethod": "POST", "id": "dataflow.projects.jobs.create", "flatPath": "v1b3/projects/{projectId}/jobs", "path": "v1b3/projects/{projectId}/jobs", "parameters": { "projectId": { "location": "path", "required": true, "description": "The ID of the Cloud Platform project that the job belongs to.", "type": "string" }, "view": { "location": "query", "type": "string", "enum": [ "JOB_VIEW_UNKNOWN", "JOB_VIEW_SUMMARY", "JOB_VIEW_ALL", "JOB_VIEW_DESCRIPTION" ], "description": "The level of information requested in response.", "enumDescriptions": [ "The job view to return isn't specified, or is unknown. Responses will contain at least the `JOB_VIEW_SUMMARY` information, and may contain additional information.", "Request summary information only: Project ID, Job ID, job name, job type, job status, start/end time, and Cloud SDK version details.", "Request all information available for this job. When the job is in `JOB_STATE_PENDING`, the job has been created but is not yet running, and not all job information is available. For complete job information, wait until the job in is `JOB_STATE_RUNNING`. For more information, see [JobState](https://cloud.google.com/dataflow/docs/reference/rest/v1b3/projects.jobs#jobstate).", "Request summary info and limited job description data for steps, labels and environment." ] }, "replaceJobId": { "description": "Deprecated. This field is now in the Job message.", "type": "string", "location": "query" }, "location": { "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job.", "location": "query", "type": "string" } }, "request": { "$ref": "Job" }, "parameterOrder": [ "projectId" ], "response": { "$ref": "Job" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "description": "Creates a Dataflow job. To create a job, we recommend using `projects.locations.jobs.create` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.jobs.create` is not recommended, as your job will always start in `us-central1`. Do not enter confidential information when you supply string values using the API. # IAM Permissions 1. Requires the `dataflow.jobs.create` permission on the project. 2. `resourcemanager.projects.get` (Specifically required for regional endpoints to resolve regional resource metadata)" }, "snapshot": { "flatPath": "v1b3/projects/{projectId}/jobs/{jobId}:snapshot", "request": { "$ref": "SnapshotJobRequest" }, "id": "dataflow.projects.jobs.snapshot", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "path": "v1b3/projects/{projectId}/jobs/{jobId}:snapshot", "parameterOrder": [ "projectId", "jobId" ], "description": "Snapshot the state of a streaming job. # IAM Permissions Requires the `dataflow.jobs.snapshot` permission on the job.", "httpMethod": "POST", "parameters": { "jobId": { "description": "The job to be snapshotted.", "type": "string", "location": "path", "required": true }, "projectId": { "type": "string", "description": "The project which owns the job to be snapshotted.", "location": "path", "required": true } }, "response": { "$ref": "Snapshot" } } } }, "templates": { "methods": { "launch": { "httpMethod": "POST", "flatPath": "v1b3/projects/{projectId}/templates:launch", "parameters": { "validateOnly": { "location": "query", "description": "If true, the request is validated but not actually executed. Defaults to false.", "type": "boolean" }, "gcsPath": { "type": "string", "location": "query", "description": "A Cloud Storage path to the template to use to create the job. Must be valid Cloud Storage URL, beginning with `gs://`." }, "projectId": { "type": "string", "location": "path", "required": true, "description": "Required. The ID of the Cloud Platform project that the job belongs to." }, "location": { "location": "query", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request.", "type": "string" }, "dynamicTemplate.stagingLocation": { "location": "query", "description": "Cloud Storage path for staging dependencies. Must be a valid Cloud Storage URL, beginning with `gs://`.", "type": "string" }, "dynamicTemplate.gcsPath": { "location": "query", "type": "string", "description": "Path to the dynamic template specification file on Cloud Storage. The file must be a JSON serialized `DynamicTemplateFileSpec` object." } }, "id": "dataflow.projects.templates.launch", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "description": "Launches a template. To launch a template, we recommend using `projects.locations.templates.launch` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.templates.launch` is not recommended, because jobs launched from the template will always start in `us-central1`. # IAM Permissions Requires the following IAM permission(s) on the project: - `dataflow.jobs.create` - `resourcemanager.projects.get`", "request": { "$ref": "LaunchTemplateParameters" }, "path": "v1b3/projects/{projectId}/templates:launch", "response": { "$ref": "LaunchTemplateResponse" }, "parameterOrder": [ "projectId" ] }, "get": { "httpMethod": "GET", "parameterOrder": [ "projectId" ], "response": { "$ref": "GetTemplateResponse" }, "parameters": { "gcsPath": { "description": "Required. A Cloud Storage path to the template from which to create the job. Must be valid Cloud Storage URL, beginning with 'gs://'.", "type": "string", "location": "query" }, "projectId": { "description": "Required. The ID of the Cloud Platform project that the job belongs to.", "type": "string", "location": "path", "required": true }, "view": { "location": "query", "type": "string", "enumDescriptions": [ "Template view that retrieves only the metadata associated with the template." ], "description": "The view to retrieve. Defaults to METADATA_ONLY.", "enum": [ "METADATA_ONLY" ] }, "location": { "type": "string", "location": "query", "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request." } }, "path": "v1b3/projects/{projectId}/templates:get", "description": "Get the template associated with a template. To get the template, we recommend using `projects.locations.templates.get` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.templates.get` is not recommended, because only templates that are running in `us-central1` are retrieved. # IAM Permissions Requires the `resourcemanager.projects.get` permission on the project.", "id": "dataflow.projects.templates.get", "flatPath": "v1b3/projects/{projectId}/templates:get", "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ] }, "create": { "id": "dataflow.projects.templates.create", "response": { "$ref": "Job" }, "path": "v1b3/projects/{projectId}/templates", "request": { "$ref": "CreateJobFromTemplateRequest" }, "scopes": [ "https://www.googleapis.com/auth/cloud-platform", "https://www.googleapis.com/auth/compute" ], "parameters": { "projectId": { "type": "string", "location": "path", "required": true, "description": "Required. The ID of the Cloud Platform project that the job belongs to." } }, "flatPath": "v1b3/projects/{projectId}/templates", "parameterOrder": [ "projectId" ], "description": "Creates a Cloud Dataflow job from a template. Do not enter confidential information when you supply string values using the API. To create a job, we recommend using `projects.locations.templates.create` with a [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints). Using `projects.templates.create` is not recommended, because your job will always start in `us-central1`. # IAM Permissions Requires the following IAM permission(s) on the project: - `dataflow.jobs.create` - `resourcemanager.projects.get`", "httpMethod": "POST" } } } } } }, "discoveryVersion": "v1", "revision": "20260831", "title": "Dataflow API", "parameters": { "callback": { "type": "string", "location": "query", "description": "JSONP" }, "prettyPrint": { "default": "true", "type": "boolean", "description": "Returns response with indentations and line breaks.", "location": "query" }, "access_token": { "type": "string", "description": "OAuth access token.", "location": "query" }, "uploadType": { "type": "string", "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").", "location": "query" }, "quotaUser": { "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.", "location": "query", "type": "string" }, "$.xgafv": { "description": "V1 error format.", "location": "query", "enum": [ "1", "2" ], "type": "string", "enumDescriptions": [ "v1 error format", "v2 error format" ] }, "upload_protocol": { "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").", "location": "query", "type": "string" }, "oauth_token": { "type": "string", "description": "OAuth 2.0 token for the current user.", "location": "query" }, "fields": { "location": "query", "type": "string", "description": "Selector specifying which fields to include in a partial response." }, "alt": { "enum": [ "json", "media", "proto" ], "enumDescriptions": [ "Responses with Content-Type of application/json", "Media download with context-dependent Content-Type", "Responses with Content-Type of application/x-protobuf" ], "default": "json", "description": "Data format for response.", "location": "query", "type": "string" }, "key": { "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.", "type": "string", "location": "query" } }, "icons": { "x16": "http://www.google.com/images/icons/product/search-16.gif", "x32": "http://www.google.com/images/icons/product/search-32.gif" }, "description": "Manages Google Cloud Dataflow projects on Google Cloud Platform.", "id": "dataflow:v1b3", "fullyEncodeReservedExpansion": true, "batchPath": "batch" }