Packages

object FileSourceStrategy extends Strategy with PredicateHelper with Logging

A strategy for planning scans over collections of files that might be partitioned or bucketed by user specified columns.

At a high level planning occurs in several phases:

  • Split filters by when they need to be evaluated.
  • Prune the schema of the data requested based on any projections present. Today this pruning is only done on top level columns, but formats should support pruning of nested columns as well.
  • Construct a reader function by passing filters and the schema into the FileFormat.
  • Using a partition pruning predicates, enumerate the list of files that should be read.
  • Split the files into tasks and construct a FileScanRDD.
  • Add any projection or filters that must be evaluated after the scan.

Files are assigned into tasks using the following algorithm:

  • If the table is bucketed, group files by bucket id into the correct number of partitions.
  • If the table is not bucketed or bucketing is turned off:
    • If any file is larger than the threshold, split it into pieces based on that threshold
    • Sort the files by decreasing file size.
    • Assign the ordered files to buckets using the following algorithm. If the current partition is under the threshold with the addition of the next file, add it. If not, open a new bucket and add it. Proceed to the next file.
Linear Supertypes
PredicateHelper, AliasHelper, SparkStrategy, GenericStrategy[SparkPlan], Logging, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. FileSourceStrategy
  2. PredicateHelper
  3. AliasHelper
  4. SparkStrategy
  5. GenericStrategy
  6. Logging
  7. AnyRef
  8. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. Protected

Type Members

  1. implicit class LogStringContext extends AnyRef
    Definition Classes
    Logging

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 MDC(key: LogKey, value: Any): MDC
    Attributes
    protected
    Definition Classes
    Logging
  5. def apply(plan: LogicalPlan): Seq[SparkPlan]
    Definition Classes
    FileSourceStrategy → GenericStrategy
  6. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  7. def buildBalancedPredicate(expressions: Seq[Expression], op: (Expression, Expression) => Expression): Expression
    Attributes
    protected
    Definition Classes
    PredicateHelper
  8. def canEvaluate(expr: Expression, plan: LogicalPlan): Boolean
    Attributes
    protected
    Definition Classes
    PredicateHelper
  9. def canEvaluateWithinJoin(expr: Expression): Boolean
    Attributes
    protected
    Definition Classes
    PredicateHelper
  10. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.CloneNotSupportedException]) @IntrinsicCandidate() @native()
  11. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  12. def equals(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef → Any
  13. def extractPredicatesWithinOutputSet(condition: Expression, outputSet: AttributeSet): Option[Expression]
    Attributes
    protected
    Definition Classes
    PredicateHelper
  14. def findExpressionAndTrackLineageDown(exp: Expression, plan: LogicalPlan): Option[(Expression, LogicalPlan)]
    Definition Classes
    PredicateHelper
  15. def getAliasMap(exprs: Iterable[NamedExpression]): AttributeMap[Alias]
    Attributes
    protected
    Definition Classes
    AliasHelper
  16. def getAliasMap(plan: Aggregate): AttributeMap[Alias]
    Attributes
    protected
    Definition Classes
    AliasHelper
  17. def getAliasMap(plan: Project): AttributeMap[Alias]
    Attributes
    protected
    Definition Classes
    AliasHelper
  18. final def getClass(): Class[_ <: AnyRef]
    Definition Classes
    AnyRef → Any
    Annotations
    @IntrinsicCandidate() @native()
  19. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @IntrinsicCandidate() @native()
  20. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  21. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  22. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  23. def isLikelySelective(e: Expression): Boolean
    Definition Classes
    PredicateHelper
  24. def isNullIntolerant(expr: Expression): Boolean
    Attributes
    protected
    Definition Classes
    PredicateHelper
  25. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  26. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  27. def logBasedOnLevel(level: Level)(f: => MessageWithContext): Unit
    Attributes
    protected
    Definition Classes
    Logging
  28. def logDebug(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  29. def logDebug(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  30. def logDebug(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  31. def logDebug(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  32. def logError(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  33. def logError(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  34. def logError(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  35. def logError(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  36. def logInfo(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  37. def logInfo(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  38. def logInfo(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  39. def logInfo(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  40. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  41. def logTrace(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  42. def logTrace(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  43. def logTrace(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  44. def logTrace(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  45. def logWarning(msg: => String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  46. def logWarning(entry: LogEntry, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  47. def logWarning(entry: LogEntry): Unit
    Attributes
    protected
    Definition Classes
    Logging
  48. def logWarning(msg: => String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  49. final def mergeAliases(alias: Alias): Alias
    Attributes
    protected
    Definition Classes
    AliasHelper
  50. final def mergeAndTrimAliases(alias: Alias): Alias
    Attributes
    protected
    Definition Classes
    AliasHelper
    Annotations
    @tailrec()
  51. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  52. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @IntrinsicCandidate() @native()
  53. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @IntrinsicCandidate() @native()
  54. def outputWithNullability(output: Seq[Attribute], nonNullAttrExprIds: Seq[ExprId]): Seq[Attribute]
    Attributes
    protected
    Definition Classes
    PredicateHelper
  55. def planLater(plan: LogicalPlan): SparkPlan
    Attributes
    protected
    Definition Classes
    SparkStrategy → GenericStrategy
  56. def replaceAlias(expr: Expression, aliasMap: AttributeMap[Alias]): Expression
    Attributes
    protected
    Definition Classes
    AliasHelper
  57. def replaceAliasButKeepName(expr: NamedExpression, aliasMap: AttributeMap[Alias]): NamedExpression
    Attributes
    protected
    Definition Classes
    AliasHelper
  58. def splitConjunctivePredicates(condition: Expression): Seq[Expression]
    Attributes
    protected
    Definition Classes
    PredicateHelper
  59. def splitDisjunctivePredicates(condition: Expression): Seq[Expression]
    Attributes
    protected
    Definition Classes
    PredicateHelper
  60. final def synchronized[T0](arg0: => T0): T0
    Definition Classes
    AnyRef
  61. def toString(): String
    Definition Classes
    AnyRef → Any
  62. def trimAliases(e: Expression): Expression
    Attributes
    protected
    Definition Classes
    AliasHelper
  63. def trimNonTopLevelAliases[T <: Expression](e: T): T
    Attributes
    protected
    Definition Classes
    AliasHelper
  64. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  65. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException]) @native()
  66. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws(classOf[java.lang.InterruptedException])
  67. def withLogContext(context: Map[String, String])(body: => Unit): Unit
    Attributes
    protected
    Definition Classes
    Logging

Deprecated Value Members

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

    (Since version 9)

Inherited from PredicateHelper

Inherited from AliasHelper

Inherited from SparkStrategy

Inherited from GenericStrategy[SparkPlan]

Inherited from Logging

Inherited from AnyRef

Inherited from Any

Ungrouped