c

org.apache.spark.sql.delta.files

TahoeFileIndex

abstract class TahoeFileIndex extends FileIndex with SupportsRowIndexFilters with SnapshotDescriptor

A FileIndex that generates the list of files managed by the Tahoe protocol.

Linear Supertypes
SnapshotDescriptor, SupportsRowIndexFilters, FileIndex, AnyRef, Any
Known Subclasses
CdcAddFileIndex, TahoeBatchFileIndex, TahoeChangeFileIndex, TahoeFileIndexWithSnapshotDescriptor, TahoeLogFileIndex, TahoeRemoveFileIndex, PreparedDeltaFileIndex
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. TahoeFileIndex
  2. SnapshotDescriptor
  3. SupportsRowIndexFilters
  4. FileIndex
  5. AnyRef
  6. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new TahoeFileIndex(spark: SparkSession, deltaLog: DeltaLog, path: Path)

Abstract Value Members

  1. abstract def inputFiles: Array[String]
    Definition Classes
    FileIndex
  2. abstract def matchingFiles(partitionFilters: Seq[Expression], dataFilters: Seq[Expression]): Seq[AddFile]

    Returns all matching/valid files by the given partitionFilters and dataFilters.

    Returns all matching/valid files by the given partitionFilters and dataFilters. Implementations may avoid evaluating data filters when doing so would be expensive, but *must* evaluate the partition filters; wrong results will be produced if AddFile entries which don't match the partition filters are returned.

  3. abstract def metadata: Metadata
    Definition Classes
    SnapshotDescriptor
  4. abstract def numOfFilesIfKnown: Option[Long]
    Attributes
    protected[delta]
    Definition Classes
    SnapshotDescriptor
  5. abstract def protocol: Protocol
    Definition Classes
    SnapshotDescriptor
  6. abstract def refresh(): Unit
    Definition Classes
    FileIndex
  7. abstract def sizeInBytes: Long
    Definition Classes
    FileIndex
  8. abstract def sizeInBytesIfKnown: Option[Long]
    Attributes
    protected[delta]
    Definition Classes
    SnapshotDescriptor
  9. abstract def version: Long
    Definition Classes
    SnapshotDescriptor

Concrete 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. def absolutePath(child: String): Path
  5. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  6. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  7. val deltaLog: DeltaLog
    Definition Classes
    TahoeFileIndex → SnapshotDescriptor
  8. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  9. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  10. def fileStatusWithMetadataFromAddFile(addFile: AddFile): FileStatusWithMetadata

    Generates a FileStatusWithMetadata using data extracted from a given AddFile.

  11. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  12. def getBasePath(filePath: Path): Option[Path]

    Returns the path of the base directory of the given file path (i.e.

    Returns the path of the base directory of the given file path (i.e. its parent directory with all the partition directories stripped off).

  13. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  14. def getPartitionValuesRow(partitionValues: Map[String, String]): GenericInternalRow
    Attributes
    protected
  15. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  16. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  17. def listFiles(partitionFilters: Seq[Expression], dataFilters: Seq[Expression]): Seq[PartitionDirectory]
    Definition Classes
    TahoeFileIndex → FileIndex
  18. def listPartitionsAsAddFiles(partitionFilters: Seq[Expression], dataFilters: Seq[Expression]): (Seq[(InternalRow, Seq[AddFile])], Seq[AddFile])

    Returns (i) tuples of partition directories to their respective AddFile actions and (ii) a collection of matched AddFiles.

    Returns (i) tuples of partition directories to their respective AddFile actions and (ii) a collection of matched AddFiles. The matched AddFiles are those that meet the criteria set by the partition and data filters. Essentially, this is a collection of all the files associated with the identified partitions.

  19. def makePartitionDirectories(partitionValuesToFiles: Seq[(InternalRow, Seq[AddFile])]): Seq[PartitionDirectory]
  20. def metadataOpsTimeNs: Option[Long]
    Definition Classes
    FileIndex
  21. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  22. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  23. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  24. def partitionSchema: StructType
    Definition Classes
    TahoeFileIndex → FileIndex
  25. val path: Path
  26. def rootPaths: Seq[Path]
    Definition Classes
    TahoeFileIndex → FileIndex
  27. def rowIndexFilters: Option[Map[String, RowIndexFilterType]]

    If we know a-priori which exact rows we want to read (e.g., from a previous scan) find the per-file filter here, which must be passed down to the appropriate reader.

    If we know a-priori which exact rows we want to read (e.g., from a previous scan) find the per-file filter here, which must be passed down to the appropriate reader.

    returns

    a mapping from file names to the row index filter for that file.

    Definition Classes
    SupportsRowIndexFilters
  28. def schema: StructType
    Definition Classes
    SnapshotDescriptor
  29. val spark: SparkSession
  30. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  31. def toString(): String
    Definition Classes
    TahoeFileIndex → FileIndex → AnyRef → Any
  32. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  33. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  34. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()

Inherited from SnapshotDescriptor

Inherited from SupportsRowIndexFilters

Inherited from FileIndex

Inherited from AnyRef

Inherited from Any

Ungrouped