googleapis

/** * Copyright 2019 Google LLC * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ import { OAuth2Client, JWT, Compute, UserRefreshClient } from 'google-auth-library'; import { GoogleConfigurable, MethodOptions, GlobalOptions, BodyResponseCallback, APIRequestContext } from 'googleapis-common'; import { GaxiosPromise } from 'gaxios'; export declare namespace dataflow_v1b3 { interface Options extends GlobalOptions { version: 'v1b3'; } interface StandardParameters { /** * V1 error format. */ '$.xgafv'?: string; /** * OAuth access token. */ access_token?: string; /** * Data format for response. */ alt?: string; /** * JSONP */ callback?: string; /** * Selector specifying which fields to include in a partial response. */ fields?: string; /** * API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token. */ key?: string; /** * OAuth 2.0 token for the current user. */ oauth_token?: string; /** * Returns response with indentations and line breaks. */ prettyPrint?: boolean; /** * Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters. */ quotaUser?: string; /** * Legacy upload protocol for media (e.g. "media", "multipart"). */ uploadType?: string; /** * Upload protocol for media (e.g. "raw", "multipart"). */ upload_protocol?: string; } /** * Dataflow API * * Manages Google Cloud Dataflow projects on Google Cloud Platform. * * @example * const {google} = require('googleapis'); * const dataflow = google.dataflow('v1b3'); * * @namespace dataflow * @type {Function} * @version v1b3 * @variation v1b3 * @param {object=} options Options for Dataflow */ class Dataflow { context: APIRequestContext; projects: Resource$Projects; constructor(options: GlobalOptions, google?: GoogleConfigurable); } /** * Obsolete in favor of ApproximateReportedProgress and ApproximateSplitRequest. */ interface Schema$ApproximateProgress { /** * Obsolete. */ percentComplete?: number; /** * Obsolete. */ position?: Schema$Position; /** * Obsolete. */ remainingTime?: string; } /** * A progress measurement of a WorkItem by a worker. */ interface Schema$ApproximateReportedProgress { /** * Total amount of parallelism in the portion of input of this task that has already been consumed and is no longer active. In the first two examples above (see remaining_parallelism), the value should be 29 or 2 respectively. The sum of remaining_parallelism and consumed_parallelism should equal the total amount of parallelism in this work item. If specified, must be finite. */ consumedParallelism?: Schema$ReportedParallelism; /** * Completion as fraction of the input consumed, from 0.0 (beginning, nothing consumed), to 1.0 (end of the input, entire input consumed). */ fractionConsumed?: number; /** * A Position within the work to represent a progress. */ position?: Schema$Position; /** * Total amount of parallelism in the input of this task that remains, (i.e. can be delegated to this task and any new tasks via dynamic splitting). Always at least 1 for non-finished work items and 0 for finished. "Amount of parallelism" refers to how many non-empty parts of the input can be read in parallel. This does not necessarily equal number of records. An input that can be read in parallel down to the individual records is called "perfectly splittable". An example of non-perfectly parallelizable input is a block-compressed file format where a block of records has to be read as a whole, but different blocks can be read in parallel. Examples: * If we are processing record #30 (starting at 1) out of 50 in a perfectly splittable 50-record input, this value should be 21 (20 remaining + 1 current). * If we are reading through block 3 in a block-compressed file consisting of 5 blocks, this value should be 3 (since blocks 4 and 5 can be processed in parallel by new tasks via dynamic splitting and the current task remains processing block 3). * If we are reading through the last block in a block-compressed file, or reading or processing the last record in a perfectly splittable input, this value should be 1, because apart from the current task, no additional remainder can be split off. */ remainingParallelism?: Schema$ReportedParallelism; } /** * A suggestion by the service to the worker to dynamically split the WorkItem. */ interface Schema$ApproximateSplitRequest { /** * A fraction at which to split the work item, from 0.0 (beginning of the input) to 1.0 (end of the input). */ fractionConsumed?: number; /** * The fraction of the remainder of work to split the work item at, from 0.0 (split at the current position) to 1.0 (end of the input). */ fractionOfRemainder?: number; /** * A Position at which to split the work item. */ position?: Schema$Position; } /** * A structured message reporting an autoscaling decision made by the Dataflow service. */ interface Schema$AutoscalingEvent { /** * The current number of workers the job has. */ currentNumWorkers?: string; /** * A message describing why the system decided to adjust the current number of workers, why it failed, or why the system decided to not make any changes to the number of workers. */ description?: Schema$StructuredMessage; /** * The type of autoscaling event to report. */ eventType?: string; /** * The target number of workers the worker pool wants to resize to use. */ targetNumWorkers?: string; /** * The time this event was emitted to indicate a new target or current num_workers value. */ time?: string; /** * A short and friendly name for the worker pool this event refers to, populated from the value of PoolStageRelation::user_pool_name. */ workerPool?: string; } /** * Settings for WorkerPool autoscaling. */ interface Schema$AutoscalingSettings { /** * The algorithm to use for autoscaling. */ algorithm?: string; /** * The maximum number of workers to cap scaling at. */ maxNumWorkers?: number; } /** * Metadata for a BigQuery connector used by the job. */ interface Schema$BigQueryIODetails { /** * Dataset accessed in the connection. */ dataset?: string; /** * Project accessed in the connection. */ projectId?: string; /** * Query used to access data in the connection. */ query?: string; /** * Table accessed in the connection. */ table?: string; } /** * Metadata for a BigTable connector used by the job. */ interface Schema$BigTableIODetails { /** * InstanceId accessed in the connection. */ instanceId?: string; /** * ProjectId accessed in the connection. */ projectId?: string; /** * TableId accessed in the connection. */ tableId?: string; } /** * Description of an interstitial value between transforms in an execution stage. */ interface Schema$ComponentSource { /** * Dataflow service generated name for this source. */ name?: string; /** * User name for the original user transform or collection with which this source is most closely associated. */ originalTransformOrCollection?: string; /** * Human-readable name for this transform; may be user or system generated. */ userName?: string; } /** * Description of a transform executed as part of an execution stage. */ interface Schema$ComponentTransform { /** * Dataflow service generated name for this source. */ name?: string; /** * User name for the original user transform with which this transform is most closely associated. */ originalTransform?: string; /** * Human-readable name for this transform; may be user or system generated. */ userName?: string; } /** * All configuration data for a particular Computation. */ interface Schema$ComputationTopology { /** * The ID of the computation. */ computationId?: string; /** * The inputs to the computation. */ inputs?: Schema$StreamLocation[]; /** * The key ranges processed by the computation. */ keyRanges?: Schema$KeyRangeLocation[]; /** * The outputs from the computation. */ outputs?: Schema$StreamLocation[]; /** * The state family values. */ stateFamilies?: Schema$StateFamilyConfig[]; /** * The system stage name. */ systemStageName?: string; } /** * 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. */ interface Schema$ConcatPosition { /** * Index of the inner source. */ index?: number; /** * Position within the inner source. */ position?: Schema$Position; } /** * CounterMetadata includes all static non-name non-value counter attributes. */ interface Schema$CounterMetadata { /** * Human-readable description of the counter semantics. */ description?: string; /** * Counter aggregation kind. */ kind?: string; /** * A string referring to the unit type. */ otherUnits?: string; /** * System defined Units, see above enum. */ standardUnits?: string; } /** * Identifies a counter within a per-job namespace. Counters whose structured names are the same get merged into a single value for the job. */ interface Schema$CounterStructuredName { /** * Name of the optimized step being executed by the workers. */ componentStepName?: string; /** * Name of the stage. An execution step contains multiple component steps. */ executionStepName?: string; /** * 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. */ inputIndex?: number; /** * Counter name. Not necessarily globally-unique, but unique within the context of the other fields. Required. */ name?: string; /** * One of the standard Origins defined above. */ origin?: string; /** * 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. */ originalRequestingStepName?: string; /** * System generated name of the original step in the user's graph, before optimization. */ originalStepName?: string; /** * A string containing a more specific namespace of the counter's origin. */ originNamespace?: string; /** * Portion of this counter, either key or value. */ portion?: string; /** * ID of a particular worker. */ workerId?: string; } /** * A single message which encapsulates structured name and metadata for a given counter. */ interface Schema$CounterStructuredNameAndMetadata { /** * Metadata associated with a counter */ metadata?: Schema$CounterMetadata; /** * Structured name of the counter. */ name?: Schema$CounterStructuredName; } /** * An update to a Counter sent from a worker. */ interface Schema$CounterUpdate { /** * Boolean value for And, Or. */ boolean?: boolean; /** * 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. */ cumulative?: boolean; /** * Distribution data */ distribution?: Schema$DistributionUpdate; /** * Floating point value for Sum, Max, Min. */ floatingPoint?: number; /** * List of floating point numbers, for Set. */ floatingPointList?: Schema$FloatingPointList; /** * Floating point mean aggregation value for Mean. */ floatingPointMean?: Schema$FloatingPointMean; /** * Integer value for Sum, Max, Min. */ integer?: Schema$SplitInt64; /** * Gauge data */ integerGauge?: Schema$IntegerGauge; /** * List of integers, for Set. */ integerList?: Schema$IntegerList; /** * Integer mean aggregation value for Mean. */ integerMean?: Schema$IntegerMean; /** * Value for internally-defined counters used by the Dataflow service. */ internal?: any; /** * Counter name and aggregation type. */ nameAndKind?: Schema$NameAndKind; /** * The service-generated short identifier for this counter. The short_id -> (name, metadata) mapping is constant for the lifetime of a job. */ shortId?: string; /** * List of strings, for Set. */ stringList?: Schema$StringList; /** * Counter structured name and metadata. */ structuredNameAndMetadata?: Schema$CounterStructuredNameAndMetadata; } /** * Modeled after information exposed by /proc/stat. */ interface Schema$CPUTime { /** * Average CPU utilization rate (% non-idle cpu / second) since previous sample. */ rate?: number; /** * Timestamp of the measurement. */ timestamp?: string; /** * Total active CPU time across all cores (ie., non-idle) in milliseconds since start-up. */ totalMs?: string; } /** * A request to create a Cloud Dataflow job from a template. */ interface Schema$CreateJobFromTemplateRequest { /** * The runtime environment for the job. */ environment?: Schema$RuntimeEnvironment; /** * Required. A Cloud Storage path to the template from which to create the job. Must be a valid Cloud Storage URL, beginning with `gs://`. */ gcsPath?: string; /** * Required. The job name to use for the created job. */ jobName?: string; /** * The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request. */ location?: string; /** * The runtime parameters to pass to the job. */ parameters?: { [key: string]: string; }; } /** * Identifies the location of a custom souce. */ interface Schema$CustomSourceLocation { /** * Whether this source is stateful. */ stateful?: boolean; } /** * Data disk assignment for a given VM instance. */ interface Schema$DataDiskAssignment { /** * Mounted data disks. The order is important a data disk's 0-based index in this list defines which persistent directory the disk is mounted to, for example the list of { "myproject-1014-104817-4c2-harness-0-disk-0" }, { "myproject-1014-104817-4c2-harness-0-disk-1" }. */ dataDisks?: string[]; /** * VM instance name the data disks mounted to, for example "myproject-1014-104817-4c2-harness-0". */ vmInstance?: string; } /** * Metadata for a Datastore connector used by the job. */ interface Schema$DatastoreIODetails { /** * Namespace used in the connection. */ namespace?: string; /** * ProjectId accessed in the connection. */ projectId?: string; } /** * Response from deleting a snapshot. */ interface Schema$DeleteSnapshotResponse { } /** * Specification of one of the bundles produced as a result of splitting a Source (e.g. when executing a SourceSplitRequest, or when splitting an active task using WorkItemStatus.dynamic_source_split), relative to the source being split. */ interface Schema$DerivedSource { /** * What source to base the produced source on (if any). */ derivationMode?: string; /** * Specification of the source. */ source?: Schema$Source; } /** * Describes the data disk used by a workflow job. */ interface Schema$Disk { /** * 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 */ diskType?: string; /** * Directory in a VM where disk is mounted. */ mountPoint?: string; /** * Size of disk in GB. If zero or unspecified, the service will attempt to choose a reasonable default. */ sizeGb?: number; } /** * Data provided with a pipeline or transform to provide descriptive info. */ interface Schema$DisplayData { /** * Contains value if the data is of a boolean type. */ boolValue?: boolean; /** * Contains value if the data is of duration type. */ durationValue?: string; /** * Contains value if the data is of float type. */ floatValue?: number; /** * Contains value if the data is of int64 type. */ int64Value?: string; /** * Contains value if the data is of java class type. */ javaClassValue?: string; /** * The key identifying the display data. This is intended to be used as a label for the display data when viewed in a dax monitoring system. */ key?: string; /** * An optional label to display in a dax UI for the element. */ label?: string; /** * The namespace for the key. This is usually a class name or programming language namespace (i.e. python module) which defines the display data. This allows a dax monitoring system to specially handle the data and perform custom rendering. */ namespace?: string; /** * A possible additional shorter value to display. For example a java_class_name_value of com.mypackage.MyDoFn will be stored with MyDoFn as the short_str_value and com.mypackage.MyDoFn as the java_class_name value. short_str_value can be displayed and java_class_name_value will be displayed as a tooltip. */ shortStrValue?: string; /** * Contains value if the data is of string type. */ strValue?: string; /** * Contains value if the data is of timestamp type. */ timestampValue?: string; /** * An optional full URL. */ url?: string; } /** * A metric value representing a distribution. */ interface Schema$DistributionUpdate { /** * The count of the number of elements present in the distribution. */ count?: Schema$SplitInt64; /** * (Optional) Histogram of value counts for the distribution. */ histogram?: Schema$Histogram; /** * The maximum value present in the distribution. */ max?: Schema$SplitInt64; /** * The minimum value present in the distribution. */ min?: Schema$SplitInt64; /** * 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. */ sum?: Schema$SplitInt64; /** * Use a double since the sum of squares is likely to overflow int64. */ sumOfSquares?: number; } /** * When a task splits using WorkItemStatus.dynamic_source_split, this message describes the two parts of the split relative to the description of the current task's input. */ interface Schema$DynamicSourceSplit { /** * Primary part (continued to be processed by worker). Specified relative to the previously-current source. Becomes current. */ primary?: Schema$DerivedSource; /** * Residual part (returned to the pool of work). Specified relative to the previously-current source. */ residual?: Schema$DerivedSource; } /** * Describes the environment in which a Dataflow Job runs. */ interface Schema$Environment { /** * 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". */ clusterManagerApiService?: string; /** * The dataset for the current project where various workflow related tables are stored. The supported resource type is: Google BigQuery: bigquery.googleapis.com/{dataset} */ dataset?: string; /** * The list of experiments to enable. */ experiments?: string[]; /** * Which Flexible Resource Scheduling mode to run in. */ flexResourceSchedulingGoal?: string; /** * Experimental settings. */ internalExperiments?: { [key: string]: any; }; /** * 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. */ sdkPipelineOptions?: { [key: string]: any; }; /** * Identity to run virtual machines as. Defaults to the default account. */ serviceAccountEmail?: string; /** * 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 */ serviceKmsKeyName?: string; /** * The prefix of the resources the system should use for temporary storage. The system will append the suffix "/temp-{JOBNAME} to this resource prefix, where {JOBNAME} is the value of the 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} */ tempStoragePrefix?: string; /** * A description of the process that generated the request. */ userAgent?: { [key: string]: any; }; /** * A structure describing which components and their versions of the service are required in order to run the job. */ version?: { [key: string]: any; }; /** * The worker pools. At least one "harness" worker pool must be specified in order for the job to have workers. */ workerPools?: Schema$WorkerPool[]; } /** * A message describing the state of a particular execution stage. */ interface Schema$ExecutionStageState { /** * The time at which the stage transitioned to this state. */ currentStateTime?: string; /** * The name of the execution stage. */ executionStageName?: string; /** * Executions stage states allow the same set of values as JobState. */ executionStageState?: string; } /** * Description of the composing transforms, names/ids, and input/outputs of a stage of execution. Some composing transforms and sources may have been generated by the Dataflow service during execution planning. */ interface Schema$ExecutionStageSummary { /** * Collections produced and consumed by component transforms of this stage. */ componentSource?: Schema$ComponentSource[]; /** * Transforms that comprise this execution stage. */ componentTransform?: Schema$ComponentTransform[]; /** * Dataflow service generated id for this stage. */ id?: string; /** * Input sources for this stage. */ inputSource?: Schema$StageSource[]; /** * Type of tranform this stage is executing. */ kind?: string; /** * Dataflow service generated name for this stage. */ name?: string; /** * Output sources for this stage. */ outputSource?: Schema$StageSource[]; } /** * Indicates which [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) failed to respond to a request for data. */ interface Schema$FailedLocation { /** * The name of the [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that failed to respond. */ name?: string; } /** * Metadata for a File connector used by the job. */ interface Schema$FileIODetails { /** * File Pattern used to access files by the connector. */ filePattern?: string; } /** * An instruction that copies its inputs (zero or more) to its (single) output. */ interface Schema$FlattenInstruction { /** * Describes the inputs to the flatten instruction. */ inputs?: Schema$InstructionInput[]; } /** * A metric value representing a list of floating point numbers. */ interface Schema$FloatingPointList { /** * Elements of the list. */ elements?: number[]; } /** * A representation of a floating point mean metric contribution. */ interface Schema$FloatingPointMean { /** * The number of values being aggregated. */ count?: Schema$SplitInt64; /** * The sum of all values being aggregated. */ sum?: number; } /** * Request to get updated debug configuration for component. */ interface Schema$GetDebugConfigRequest { /** * The internal component id for which debug configuration is requested. */ componentId?: string; /** * The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the job specified by job_id. */ location?: string; /** * The worker id, i.e., VM hostname. */ workerId?: string; } /** * Response to a get debug configuration request. */ interface Schema$GetDebugConfigResponse { /** * The encoded debug configuration for the requested component. */ config?: string; } /** * The response to a GetTemplate request. */ interface Schema$GetTemplateResponse { /** * The template metadata describing the template name, available parameters, etc. */ metadata?: Schema$TemplateMetadata; /** * The status of the get template request. Any problems with the request will be indicated in the error_details. */ status?: Schema$Status; } /** * 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. */ interface Schema$Histogram { /** * Counts of values in each bucket. For efficiency, prefix and trailing buckets with count = 0 are elided. Buckets can store the full range of values of an unsigned long, with ULLONG_MAX falling into the 59th bucket with range [1e19, 2e19). */ bucketCounts?: string[]; /** * Starting index of first stored bucket. The non-inclusive upper-bound of the ith bucket is given by: pow(10,(i-first_bucket_offset)/3) * (1,2,5)[(i-first_bucket_offset)%3] */ firstBucketOffset?: number; } /** * Proto describing a hot key detected on a given WorkItem. */ interface Schema$HotKeyDetection { /** * The age of the hot key measured from when it was first detected. */ hotKeyAge?: string; /** * System-defined name of the step containing this hot key. Unique across the workflow. */ systemName?: string; /** * User-provided name of the step that contains this hot key. */ userStepName?: string; } /** * An input of an instruction, as a reference to an output of a producer instruction. */ interface Schema$InstructionInput { /** * The output index (origin zero) within the producer. */ outputNum?: number; /** * The index (origin zero) of the parallel instruction that produces the output to be consumed by this input. This index is relative to the list of instructions in this input's instruction's containing MapTask. */ producerInstructionIndex?: number; } /** * An output of an instruction. */ interface Schema$InstructionOutput { /** * The codec to use to encode data being written via this output. */ codec?: { [key: string]: any; }; /** * The user-provided name of this output. */ name?: string; /** * For system-generated byte and mean byte metrics, certain instructions should only report the key size. */ onlyCountKeyBytes?: boolean; /** * For system-generated byte and mean byte metrics, certain instructions should only report the value size. */ onlyCountValueBytes?: boolean; /** * System-defined name for this output in the original workflow graph. Outputs that do not contribute to an original instruction do not set this. */ originalName?: string; /** * System-defined name of this output. Unique across the workflow. */ systemName?: string; } /** * A metric value representing temporal values of a variable. */ interface Schema$IntegerGauge { /** * The time at which this value was measured. Measured as msecs from epoch. */ timestamp?: string; /** * The value of the variable represented by this gauge. */ value?: Schema$SplitInt64; } /** * A metric value representing a list of integers. */ interface Schema$IntegerList { /** * Elements of the list. */ elements?: Schema$SplitInt64[]; } /** * A representation of an integer mean metric contribution. */ interface Schema$IntegerMean { /** * The number of values being aggregated. */ count?: Schema$SplitInt64; /** * The sum of all values being aggregated. */ sum?: Schema$SplitInt64; } /** * Defines a job to be run by the Cloud Dataflow service. */ interface Schema$Job { /** * 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. */ clientRequestId?: string; /** * If this is specified, the job's initial state is populated from the given snapshot. */ createdFromSnapshotId?: string; /** * The timestamp when the job was initially created. Immutable and set by the Cloud Dataflow service. */ createTime?: string; /** * The current state of the job. Jobs are created in the `JOB_STATE_STOPPED` state unless otherwise specified. A job in the `JOB_STATE_RUNNING` state may asynchronously enter a terminal state. After a job has reached a terminal state, no further state updates may be made. This field may be mutated by the Cloud Dataflow service; callers cannot mutate it. */ currentState?: string; /** * The timestamp associated with the current state. */ currentStateTime?: string; /** * The environment for the job. */ environment?: Schema$Environment; /** * Deprecated. */ executionInfo?: Schema$JobExecutionInfo; /** * The unique ID of this job. This field is set by the Cloud Dataflow service when the Job is created, and is immutable for the life of the job. */ id?: string; /** * 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. */ jobMetadata?: Schema$JobMetadata; /** * User-defined labels for this job. The labels map can contain no more than 64 entries. Entries of the labels map are UTF8 strings that comply with the following restrictions: * Keys must conform to regexp: \p{Ll}\p{Lo}{0,62} * Values must conform to regexp: [\p{Ll}\p{Lo}\p{N}_-]{0,63} * Both keys and values are additionally constrained to be <= 128 bytes in size. */ labels?: { [key: string]: string; }; /** * The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains this job. */ location?: string; /** * The user-specified Cloud Dataflow job name. Only one Job with a given name may exist in a project at any given time. If a caller attempts to create a Job with the same name as an already-existing Job, the attempt returns the existing Job. The name must match the regular expression `[a-z]([-a-z0-9]{0,38}[a-z0-9])?` */ name?: string; /** * Preliminary field: The format of this data may change at any time. A description of the user pipeline and stages through which it is executed. Created by Cloud Dataflow service. Only retrieved with JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL. */ pipelineDescription?: Schema$PipelineDescription; /** * The ID of the Cloud Platform project that the job belongs to. */ projectId?: string; /** * If another job is an update of this job (and thus, this job is in `JOB_STATE_UPDATED`), this field contains the ID of that job. */ replacedByJobId?: string; /** * 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. */ replaceJobId?: string; /** * The job's requested state. `UpdateJob` may be used to switch between the `JOB_STATE_STOPPED` and `JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may also be used to directly set a job's requested state to `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the job if it has not already reached a terminal state. */ requestedState?: string; /** * This field may be mutated by the Cloud Dataflow service; callers cannot mutate it. */ stageStates?: Schema$ExecutionStageState[]; /** * The timestamp when the job was started (transitioned to JOB_STATE_PENDING). Flexible resource scheduling jobs are started with some delay after job creation, so start_time is unset before start and is updated when the job is started by the Cloud Dataflow service. For other jobs, start_time always equals to create_time and is immutable and set by the Cloud Dataflow service. */ startTime?: string; /** * Exactly one of step or steps_location should be specified. The top-level steps that constitute the entire job. */ steps?: Schema$Step[]; /** * The GCS location where the steps are stored. */ stepsLocation?: string; /** * 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} */ tempFiles?: string[]; /** * The map of transform name prefixes of the job to be replaced to the corresponding name prefixes of the new job. */ transformNameMapping?: { [key: string]: string; }; /** * The type of Cloud Dataflow job. */ type?: string; } /** * Additional information about how a Cloud Dataflow job will be executed that isn't contained in the submitted job. */ interface Schema$JobExecutionInfo { /** * A mapping from each stage to the information about that stage. */ stages?: { [key: string]: Schema$JobExecutionStageInfo; }; } /** * Contains information about how a particular google.dataflow.v1beta3.Step will be executed. */ interface Schema$JobExecutionStageInfo { /** * The steps associated with the execution stage. Note that stages may have several steps, and that a given step might be run by more than one stage. */ stepName?: string[]; } /** * A particular message pertaining to a Dataflow job. */ interface Schema$JobMessage { /** * Deprecated. */ id?: string; /** * Importance level of the message. */ messageImportance?: string; /** * The text of the message. */ messageText?: string; /** * The timestamp of the message. */ time?: string; } /** * Metadata available primarily for filtering jobs. Will be included in the ListJob response and Job SUMMARY view. */ interface Schema$JobMetadata { /** * Identification of a BigQuery source used in the Dataflow job. */ bigqueryDetails?: Schema$BigQueryIODetails[]; /** * Identification of a BigTable source used in the Dataflow job. */ bigTableDetails?: Schema$BigTableIODetails[]; /** * Identification of a Datastore source used in the Dataflow job. */ datastoreDetails?: Schema$DatastoreIODetails[]; /** * Identification of a File source used in the Dataflow job. */ fileDetails?: Schema$FileIODetails[]; /** * Identification of a PubSub source used in the Dataflow job. */ pubsubDetails?: Schema$PubSubIODetails[]; /** * The SDK version used to run the job. */ sdkVersion?: Schema$SdkVersion; /** * Identification of a Spanner source used in the Dataflow job. */ spannerDetails?: Schema$SpannerIODetails[]; } /** * 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. 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. */ interface Schema$JobMetrics { /** * All metrics for this job. */ metrics?: Schema$MetricUpdate[]; /** * Timestamp as of which metric values are current. */ metricTime?: string; } /** * 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. */ interface Schema$KeyRangeDataDiskAssignment { /** * The name of the data disk where data for this range is stored. This name is local to the Google Cloud Platform project and uniquely identifies the disk within that project, for example "myproject-1014-104817-4c2-harness-0-disk-1". */ dataDisk?: string; /** * The end (exclusive) of the key range. */ end?: string; /** * The start (inclusive) of the key range. */ start?: string; } /** * Location information for a specific key-range of a sharded computation. Currently we only support UTF-8 character splits to simplify encoding into JSON. */ interface Schema$KeyRangeLocation { /** * 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". */ dataDisk?: string; /** * The physical location of this range assignment to be used for streaming computation cross-worker message delivery. */ deliveryEndpoint?: string; /** * DEPRECATED. The location of the persistent state for this range, as a persistent directory in the worker local filesystem. */ deprecatedPersistentDirectory?: string; /** * The end (exclusive) of the key range. */ end?: string; /** * The start (inclusive) of the key range. */ start?: string; } /** * Parameters to provide to the template being launched. */ interface Schema$LaunchTemplateParameters { /** * The runtime environment for the job. */ environment?: Schema$RuntimeEnvironment; /** * Required. The job name to use for the created job. */ jobName?: string; /** * The runtime parameters to pass to the job. */ parameters?: { [key: string]: string; }; /** * 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. */ transformNameMapping?: { [key: string]: string; }; /** * If set, replace the existing pipeline with the name specified by jobName with this pipeline, preserving state. */ update?: boolean; } /** * Response to the request to launch a template. */ interface Schema$LaunchTemplateResponse { /** * The job that was launched, if the request was not a dry run and the job was successfully launched. */ job?: Schema$Job; } /** * Request to lease WorkItems. */ interface Schema$LeaseWorkItemRequest { /** * The current timestamp at the worker. */ currentWorkerTime?: string; /** * The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that contains the WorkItem's job. */ location?: string; /** * The initial lease period. */ requestedLeaseDuration?: string; /** * Untranslated bag-of-bytes WorkRequest from UnifiedWorker. */ unifiedWorkerRequest?: { [key: string]: any; }; /** * Worker capabilities. WorkItems might be limited to workers with specific capabilities. */ workerCapabilities?: string[]; /** * Identifies the worker leasing work -- typically the ID of the virtual machine running the worker. */ workerId?: string; /** * Filter for WorkItem type. */ workItemTypes?: string[]; } /** * Response to a request to lease WorkItems. */ interface Schema$LeaseWorkItemResponse { /** * Untranslated bag-of-bytes WorkResponse for UnifiedWorker. */ unifiedWorkerResponse?: { [key: string]: any; }; /** * A list of the leased WorkItems. */ workItems?: Schema$WorkItem[]; } /** * Response to a request to list job messages. */ interface Schema$ListJobMessagesResponse { /** * Autoscaling events in ascending timestamp order. */ autoscalingEvents?: Schema$AutoscalingEvent[]; /** * Messages in ascending timestamp order. */ jobMessages?: Schema$JobMessage[]; /** * The token to obtain the next page of results if there are more. */ nextPageToken?: string; } /** * Response to a request to list Cloud Dataflow jobs. This may be a partial response, depending on the page size in the ListJobsRequest. */ interface Schema$ListJobsResponse { /** * Zero or more messages describing the [regional endpoints] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) that failed to respond.