DataSkippingUtils

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. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

5. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

6. final def eq(arg0: AnyRef): Boolean

   

   Definition Classes

   AnyRef

7. def equals(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

8. def finalize(): Unit

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( classOf[java.lang.Throwable] )

9. final def getClass(): Class[_]

   

   Definition Classes

   AnyRef → Any

10. def getFileFilter(fileIndex: FileIndex, tid: String, metadataStoreManager: MetadataStoreManager, sparkSession: SparkSession, evaluate: Boolean = false): DataSkippingFileFilter

    

    Gets the DataSkippingFileFilter relevant for this tid, FileIndex and backend

    Gets the DataSkippingFileFilter relevant for this tid, FileIndex and backend

    fileIndex

    the fileIndex for which we create a DataSkippingFileFilter

    tid

    the table identifier

    metadataStoreManager

    the backend to be used to create the DataSkippingFileFilter

    sparkSession

    the spark session

    evaluate

    whether we create an evaluate DataSkippingFileFilter which only report skipping stats

11. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

12. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

    

    Attributes

    protected

    Definition Classes

    Logging

13. def initializeLogIfNecessary(isInterpreter: Boolean): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

14. def injectRuleExtendedOperatorOptimizationRule(sparkSession: SparkSession, rule: Rule[LogicalPlan]): Unit

    

    Inject a rule as part extendedOperatorOptimizationRule

15. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

16. def isTraceEnabled(): Boolean

    

    Attributes

    protected

    Definition Classes

    Logging

17. def log: Logger

    

    Attributes

    protected

    Definition Classes

    Logging

18. def logDebug(msg: ⇒ String, throwable: Throwable): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

19. def logDebug(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

20. def logError(msg: ⇒ String, throwable: Throwable): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

21. def logError(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

22. def logInfo(msg: ⇒ String, throwable: Throwable): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

23. def logInfo(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

24. def logName: String

    

    Attributes

    protected

    Definition Classes

    Logging

25. def logTrace(msg: ⇒ String, throwable: Throwable): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

26. def logTrace(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

27. def logWarning(msg: ⇒ String, throwable: Throwable): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

28. def logWarning(msg: ⇒ String): Unit

    

    Attributes

    protected

    Definition Classes

    Logging

29. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

30. final def notify(): Unit

    

    Definition Classes

    AnyRef

31. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

32. def recreateFileStatusCache(spark: SparkSession, inMemoryFileIndex: PartitioningAwareFileIndex): FileStatusCache

    

    Gets an inMemoryFileIndex and reconstructs the FileStatusCache The way the FileStatusCache is implemented in spark makes it to not be shareable between instances meaning that calling FileStatusCache.getOrCreate(spark) will result in an empty cache and thus will require a new listing when the FileIndex is being replaced with a data skipping FileIndex.

    Gets an inMemoryFileIndex and reconstructs the FileStatusCache The way the FileStatusCache is implemented in spark makes it to not be shareable between instances meaning that calling FileStatusCache.getOrCreate(spark) will result in an empty cache and thus will require a new listing when the FileIndex is being replaced with a data skipping FileIndex. To avoid this code reconstructs the cache using the existing FileIndex and then it can be used by the new FileIndex. Note: the reason we can't get the FileStatusCache of the original inMemoryFileIndex is because it is handed over to it in the constructor and is not defined there as var/val so we can't access it once we have an instance of inMemoryFileIndex

    spark

    a spark session - used to get a new cache

    inMemoryFileIndex

    the inMemoryFileIndex to construct the cache from

    returns

    a FileStatusCache populated with the root paths from the given inMemoryFileIndex

33. final def synchronized[T0](arg0: ⇒ T0): T0

    

    Definition Classes

    AnyRef

34. def toString(): String

    

    Definition Classes

    AnyRef → Any

35. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

36. final def wait(arg0: Long, arg1: Int): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

37. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )