c

io.smartdatalake.workflow

ActionPipelineContext

case class ActionPipelineContext(feed: String, application: String, executionId: SDLExecutionId, instanceRegistry: InstanceRegistry, referenceTimestamp: Option[LocalDateTime] = None, appConfig: SmartDataLakeBuilderConfig, runStartTime: LocalDateTime = LocalDateTime.now(), attemptStartTime: LocalDateTime = LocalDateTime.now(), simulation: Boolean = false, phase: ExecutionPhase = ExecutionPhase.Prepare, dataFrameReuseStatistics: Map[(DataObjectId, Seq[PartitionValues]), Seq[ActionId]] = mutable.Map(), actionsSelected: Seq[ActionId] = Seq(), actionsSkipped: Seq[ActionId] = Seq(), serializableHadoopConf: SerializableHadoopConfiguration, globalConfig: GlobalConfig) extends SmartDataLakeLogger with Product with Serializable

ActionPipelineContext contains start and runtime information about a SmartDataLake run.

feed

feed selector of the run

application

application name of the run

executionId

SDLExecutionId of this runs. Contains runId and attemptId. Both stay 1 if state is not enabled.

instanceRegistry

registry of all SmartDataLake objects parsed from the config

referenceTimestamp

timestamp used as reference in certain actions (e.g. HistorizeAction)

appConfig

the command line parameters parsed into a SmartDataLakeBuilderConfig object

runStartTime

start time of the run

attemptStartTime

start time of attempt

simulation

true if this is a simulation run

phase

current execution phase

dataFrameReuseStatistics

Counter how many times a DataFrame of a SparkSubFeed is reused by an Action later in the pipeline. The counter is increased during ExecutionPhase.Init when preparing the SubFeeds for an Action and it is decreased in ExecutionPhase.Exec to unpersist the DataFrame after there is no need for it anymore.

actionsSelected

actions selected for execution by command line parameter --feed-sel

actionsSkipped

actions selected but skipped in current attempt because they already succeeded in a previous attempt.

Annotations
@Scaladoc() @DeveloperApi()
Linear Supertypes
Serializable, Serializable, Product, Equals, SmartDataLakeLogger, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. ActionPipelineContext
  2. Serializable
  3. Serializable
  4. Product
  5. Equals
  6. SmartDataLakeLogger
  7. AnyRef
  8. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new ActionPipelineContext(feed: String, application: String, executionId: SDLExecutionId, instanceRegistry: InstanceRegistry, referenceTimestamp: Option[LocalDateTime] = None, appConfig: SmartDataLakeBuilderConfig, runStartTime: LocalDateTime = LocalDateTime.now(), attemptStartTime: LocalDateTime = LocalDateTime.now(), simulation: Boolean = false, phase: ExecutionPhase = ExecutionPhase.Prepare, dataFrameReuseStatistics: Map[(DataObjectId, Seq[PartitionValues]), Seq[ActionId]] = mutable.Map(), actionsSelected: Seq[ActionId] = Seq(), actionsSkipped: Seq[ActionId] = Seq(), serializableHadoopConf: SerializableHadoopConfiguration, globalConfig: GlobalConfig)

    feed

    feed selector of the run

    application

    application name of the run

    executionId

    SDLExecutionId of this runs. Contains runId and attemptId. Both stay 1 if state is not enabled.

    instanceRegistry

    registry of all SmartDataLake objects parsed from the config

    referenceTimestamp

    timestamp used as reference in certain actions (e.g. HistorizeAction)

    appConfig

    the command line parameters parsed into a SmartDataLakeBuilderConfig object

    runStartTime

    start time of the run

    attemptStartTime

    start time of attempt

    simulation

    true if this is a simulation run

    phase

    current execution phase

    dataFrameReuseStatistics

    Counter how many times a DataFrame of a SparkSubFeed is reused by an Action later in the pipeline. The counter is increased during ExecutionPhase.Init when preparing the SubFeeds for an Action and it is decreased in ExecutionPhase.Exec to unpersist the DataFrame after there is no need for it anymore.

    actionsSelected

    actions selected for execution by command line parameter --feed-sel

    actionsSkipped

    actions selected but skipped in current attempt because they already succeeded in a previous attempt.

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. val actionsSelected: Seq[ActionId]
  5. val actionsSkipped: Seq[ActionId]
  6. val appConfig: SmartDataLakeBuilderConfig
  7. val application: String
  8. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  9. val attemptStartTime: LocalDateTime
  10. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native() @HotSpotIntrinsicCandidate()
  11. val dataFrameReuseStatistics: Map[(DataObjectId, Seq[PartitionValues]), Seq[ActionId]]
  12. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  13. val executionId: SDLExecutionId
  14. val feed: String
  15. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  16. val globalConfig: GlobalConfig
  17. def hadoopConf: Configuration

    helper method to access hadoop configuration

    helper method to access hadoop configuration

    Annotations
    @Scaladoc()
  18. def hasSparkSession: Boolean

    True if a SparkSession has been created in this job

    True if a SparkSession has been created in this job

    Annotations
    @Scaladoc()
  19. val instanceRegistry: InstanceRegistry
  20. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  21. lazy val logger: Logger
    Attributes
    protected
    Definition Classes
    SmartDataLakeLogger
    Annotations
    @transient()
  22. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  23. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  24. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  25. var phase: ExecutionPhase
  26. val referenceTimestamp: Option[LocalDateTime]
  27. val runStartTime: LocalDateTime
  28. val serializableHadoopConf: SerializableHadoopConfiguration
  29. val simulation: Boolean
  30. def sparkSession: SparkSession

    helper method to access spark session

    helper method to access spark session

    Annotations
    @Scaladoc()
  31. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  32. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  33. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  34. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Deprecated Value Members

  1. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] ) @Deprecated
    Deprecated

Inherited from Serializable

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from SmartDataLakeLogger

Inherited from AnyRef

Inherited from Any

Ungrouped