c

org.apache.spark.sql.delta.stats

PreparedDeltaFileIndex

case class PreparedDeltaFileIndex(spark: SparkSession, deltaLog: DeltaLog, path: Path, preparedScan: DeltaScan, versionScanned: Option[Long]) extends TahoeFileIndexWithSnapshotDescriptor with DeltaLogging with Product with Serializable

A TahoeFileIndex that uses a prepared scan to return the list of relevant files. This is injected into a query right before query planning by PrepareDeltaScan so that CBO and metering can accurately understand how much data will be read.

versionScanned

The version of the table that is being scanned, if a specific version has specifically been requested, e.g. by time travel.

Linear Supertypes
Serializable, Product, Equals, DeltaLogging, DatabricksLogging, DeltaProgressReporter, Logging, TahoeFileIndexWithSnapshotDescriptor, TahoeFileIndex, SnapshotDescriptor, SupportsRowIndexFilters, FileIndex, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. PreparedDeltaFileIndex
  2. Serializable
  3. Product
  4. Equals
  5. DeltaLogging
  6. DatabricksLogging
  7. DeltaProgressReporter
  8. Logging
  9. TahoeFileIndexWithSnapshotDescriptor
  10. TahoeFileIndex
  11. SnapshotDescriptor
  12. SupportsRowIndexFilters
  13. FileIndex
  14. AnyRef
  15. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Instance Constructors

  1. new PreparedDeltaFileIndex(spark: SparkSession, deltaLog: DeltaLog, path: Path, preparedScan: DeltaScan, versionScanned: Option[Long])

    versionScanned

    The version of the table that is being scanned, if a specific version has specifically been requested, e.g. by time travel.

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
    Attributes
    protected
    Definition Classes
    TahoeFileIndex
  5. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  6. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.CloneNotSupportedException]) @native()
  7. val deltaLog: DeltaLog
    Definition Classes
    PreparedDeltaFileIndex → TahoeFileIndex → SnapshotDescriptor
  8. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  9. def equals(other: Any): Boolean
    Definition Classes
    PreparedDeltaFileIndex → Equals → AnyRef → Any
  10. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.Throwable])
  11. 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).

    Definition Classes
    TahoeFileIndex
  12. final def getClass(): Class[_ <: AnyRef]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  13. def getCommonTags(deltaLog: DeltaLog, tahoeId: String): Map[TagDefinition, String]
    Definition Classes
    DeltaLogging
  14. def getPartitionValuesRow(partitionValues: Map[String, String]): GenericInternalRow
    Attributes
    protected
    Definition Classes
    TahoeFileIndex
  15. def hashCode(): Int
    Definition Classes
    PreparedDeltaFileIndex → AnyRef → Any
  16. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  17. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  18. def inputFiles: Array[String]

    Returns the list of files that will be read when scanning this relation.

    Returns the list of files that will be read when scanning this relation. This call may be very expensive for large tables.

    Definition Classes
    PreparedDeltaFileIndex → FileIndex
  19. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  20. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  21. def listFiles(partitionFilters: Seq[Expression], dataFilters: Seq[Expression]): Seq[PartitionDirectory]
    Definition Classes
    TahoeFileIndex → FileIndex
  22. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  23. def logConsole(line: String): Unit
    Definition Classes
    DatabricksLogging
  24. def logDebug(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  25. def logDebug(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  26. def logError(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  27. def logError(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  28. def logInfo(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  29. def logInfo(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  30. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  31. def logTrace(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  32. def logTrace(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  33. def logWarning(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  34. def logWarning(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  35. 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

    Definition Classes
    PreparedDeltaFileIndex → TahoeFileIndex
  36. def metadata: Metadata
    Definition Classes
    TahoeFileIndexWithSnapshotDescriptor → SnapshotDescriptor
  37. def metadataOpsTimeNs: Option[Long]
    Definition Classes
    FileIndex
  38. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  39. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  40. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  41. def numOfFilesIfKnown: Option[Long]
    Attributes
    protected[delta]
    Definition Classes
    TahoeFileIndexWithSnapshotDescriptor → SnapshotDescriptor
  42. def partitionSchema: StructType
    Definition Classes
    TahoeFileIndex → FileIndex
  43. val path: Path
    Definition Classes
    PreparedDeltaFileIndex → TahoeFileIndex
  44. val preparedScan: DeltaScan
  45. def productElementNames: Iterator[String]
    Definition Classes
    Product
  46. def protocol: Protocol
    Definition Classes
    TahoeFileIndexWithSnapshotDescriptor → SnapshotDescriptor
  47. def recordDeltaEvent(deltaLog: DeltaLog, opType: String, tags: Map[TagDefinition, String] = Map.empty, data: AnyRef = null, path: Option[Path] = None): Unit

    Used to record the occurrence of a single event or report detailed, operation specific statistics.

    Used to record the occurrence of a single event or report detailed, operation specific statistics.

    path

    Used to log the path of the delta table when deltaLog is null.

    Attributes
    protected
    Definition Classes
    DeltaLogging
  48. def recordDeltaOperation[A](deltaLog: DeltaLog, opType: String, tags: Map[TagDefinition, String] = Map.empty)(thunk: => A): A

    Used to report the duration as well as the success or failure of an operation on a deltaLog.

    Used to report the duration as well as the success or failure of an operation on a deltaLog.

    Attributes
    protected
    Definition Classes
    DeltaLogging
  49. def recordDeltaOperationForTablePath[A](tablePath: String, opType: String, tags: Map[TagDefinition, String] = Map.empty)(thunk: => A): A

    Used to report the duration as well as the success or failure of an operation on a tahoePath.

    Used to report the duration as well as the success or failure of an operation on a tahoePath.

    Attributes
    protected
    Definition Classes
    DeltaLogging
  50. def recordEvent(metric: MetricDefinition, additionalTags: Map[TagDefinition, String] = Map.empty, blob: String = null, trimBlob: Boolean = true): Unit
    Definition Classes
    DatabricksLogging
  51. def recordFrameProfile[T](group: String, name: String)(thunk: => T): T
    Attributes
    protected
    Definition Classes
    DeltaLogging
  52. def recordOperation[S](opType: OpType, opTarget: String = null, extraTags: Map[TagDefinition, String], isSynchronous: Boolean = true, alwaysRecordStats: Boolean = false, allowAuthTags: Boolean = false, killJvmIfStuck: Boolean = false, outputMetric: MetricDefinition = METRIC_OPERATION_DURATION, silent: Boolean = true)(thunk: => S): S
    Definition Classes
    DatabricksLogging
  53. def recordProductEvent(metric: MetricDefinition with CentralizableMetric, additionalTags: Map[TagDefinition, String] = Map.empty, blob: String = null, trimBlob: Boolean = true): Unit
    Definition Classes
    DatabricksLogging
  54. def recordProductUsage(metric: MetricDefinition with CentralizableMetric, quantity: Double, additionalTags: Map[TagDefinition, String] = Map.empty, blob: String = null, forceSample: Boolean = false, trimBlob: Boolean = true, silent: Boolean = false): Unit
    Definition Classes
    DatabricksLogging
  55. def recordUsage(metric: MetricDefinition, quantity: Double, additionalTags: Map[TagDefinition, String] = Map.empty, blob: String = null, forceSample: Boolean = false, trimBlob: Boolean = true, silent: Boolean = false): Unit
    Definition Classes
    DatabricksLogging
  56. def refresh(): Unit

    Refresh any cached file listings

    Refresh any cached file listings

    Definition Classes
    PreparedDeltaFileIndex → FileIndex
  57. def rootPaths: Seq[Path]
    Definition Classes
    TahoeFileIndex → FileIndex
  58. 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
  59. def schema: StructType
    Definition Classes
    SnapshotDescriptor
  60. def sizeInBytes: Long

    Sum of table file sizes, in bytes

    Sum of table file sizes, in bytes

    Definition Classes
    PreparedDeltaFileIndex → FileIndex
  61. def sizeInBytesIfKnown: Option[Long]
    Attributes
    protected[delta]
    Definition Classes
    TahoeFileIndexWithSnapshotDescriptor → SnapshotDescriptor
  62. val spark: SparkSession
    Definition Classes
    PreparedDeltaFileIndex → TahoeFileIndex
  63. final def synchronized[T0](arg0: => T0): T0
    Definition Classes
    AnyRef
  64. def toString(): String
    Definition Classes
    TahoeFileIndex → FileIndex → AnyRef → Any
  65. def version: Long
    Definition Classes
    TahoeFileIndexWithSnapshotDescriptor → SnapshotDescriptor
  66. val versionScanned: Option[Long]
  67. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  68. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  69. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException]) @native()
  70. def withStatusCode[T](statusCode: String, defaultMessage: String, data: Map[String, Any] = Map.empty)(body: => T): T

    Report a log to indicate some command is running.

    Report a log to indicate some command is running.

    Definition Classes
    DeltaProgressReporter

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from DeltaLogging

Inherited from DatabricksLogging

Inherited from DeltaProgressReporter

Inherited from Logging

Inherited from TahoeFileIndexWithSnapshotDescriptor

Inherited from TahoeFileIndex

Inherited from SnapshotDescriptor

Inherited from SupportsRowIndexFilters

Inherited from FileIndex

Inherited from AnyRef

Inherited from Any

Ungrouped