InMemoryFileIndex

Instance Constructors

new InMemoryFileIndex(sparkSession: SparkSession, rootPathsSpecified: Seq[Path], parameters: Map[String, String], partitionSchema: Option[StructType], fileStatusCache: FileStatusCache = NoopCache)

rootPathsSpecified
the list of root table paths to scan (some of which might be filtered out later)
parameters
as set of options to control discovery
partitionSchema
an optional partition schema that will be use to provide types for the discovered partitions

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def allFiles(): Seq[FileStatus]

Definition Classes
PartitioningAwareFileIndex
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(other: Any): Boolean

Definition Classes
InMemoryFileIndex → AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
val hadoopConf: Configuration

Attributes
protected
Definition Classes
PartitioningAwareFileIndex
def hashCode(): Int

Definition Classes
InMemoryFileIndex → AnyRef → Any
def inferPartitioning(): PartitionSpec

Attributes
protected
Definition Classes
PartitioningAwareFileIndex
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
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.

Definition Classes
PartitioningAwareFileIndex → FileIndex
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
def leafDirToChildrenFiles: Map[Path, Array[FileStatus]]

Attributes
protected
Definition Classes
InMemoryFileIndex → PartitioningAwareFileIndex
def leafFiles: LinkedHashMap[Path, FileStatus]

Attributes
protected
Definition Classes
InMemoryFileIndex → PartitioningAwareFileIndex
def listFiles(partitionFilters: Seq[Expression], dataFilters: Seq[Expression]): Seq[PartitionDirectory]

Returns all valid files grouped into partitions when the data is partitioned.
Returns all valid files grouped into partitions when the data is partitioned. If the data is unpartitioned, this will return a single partition with no partition values.
partitionFilters
The filters used to prune which partitions are returned. These filters must only refer to partition columns and this method will only return files where these predicates are guaranteed to evaluate to true. Thus, these filters will not need to be evaluated again on the returned data.
dataFilters
Filters that can be applied on non-partitioned columns. The implementation does not need to guarantee these filters are applied, i.e. the execution engine will ensure these filters are still applied on the returned files.

Definition Classes
PartitioningAwareFileIndex → FileIndex
def listLeafFiles(paths: Seq[Path]): LinkedHashSet[FileStatus]

List leaf files of given paths.
List leaf files of given paths. This method will submit a Spark job to do parallel listing whenever there is a path having more files than the parallel partition discovery discovery threshold.
This is publicly visible for testing.
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def metadataOpsTimeNs: Option[Long]

Returns an optional metadata operation time, in nanoseconds, for listing files.
Returns an optional metadata operation time, in nanoseconds, for listing files.
We do file listing in query optimization (in order to get the proper statistics) and we want to account for file listing time in physical execution (as metrics). To do that, we save the file listing time in some implementations and physical execution calls it in this method to update the metrics.

Definition Classes
FileIndex
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def partitionSchema: StructType

Schema of the partitioning columns, or the empty schema if the table is not partitioned.
Schema of the partitioning columns, or the empty schema if the table is not partitioned.

Definition Classes
PartitioningAwareFileIndex → FileIndex
def partitionSpec(): PartitionSpec

Returns the specification of the partitions inferred from the data.
Returns the specification of the partitions inferred from the data.

Definition Classes
InMemoryFileIndex → PartitioningAwareFileIndex
def refresh(): Unit

Refresh any cached file listings
Refresh any cached file listings

Definition Classes
InMemoryFileIndex → FileIndex
val rootPaths: Seq[Path]

Returns the list of root input paths from which the catalog will get files.
Returns the list of root input paths from which the catalog will get files. There may be a single root path from which partitions are discovered, or individual partitions may be specified by each path.

Definition Classes
InMemoryFileIndex → FileIndex
def sizeInBytes: Long

Sum of table file sizes, in bytes
Sum of table file sizes, in bytes

Definition Classes
PartitioningAwareFileIndex → FileIndex
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Docs: object InMemoryFileIndex | package datasources

class InMemoryFileIndex extends PartitioningAwareFileIndex

Instance Constructors

new InMemoryFileIndex(sparkSession: SparkSession, rootPathsSpecified: Seq[Path], parameters: Map[String, String], partitionSchema: Option[StructType], fileStatusCache: FileStatusCache = NoopCache)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def allFiles(): Seq[FileStatus]

final def asInstanceOf[T0]: T0

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(other: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

val hadoopConf: Configuration

def hashCode(): Int

def inferPartitioning(): PartitionSpec

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

def inputFiles: Array[String]

final def isInstanceOf[T0]: Boolean

def isTraceEnabled(): Boolean

def leafDirToChildrenFiles: Map[Path, Array[FileStatus]]

def leafFiles: LinkedHashMap[Path, FileStatus]

def listFiles(partitionFilters: Seq[Expression], dataFilters: Seq[Expression]): Seq[PartitionDirectory]

def listLeafFiles(paths: Seq[Path]): LinkedHashSet[FileStatus]

def log: Logger

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

def logDebug(msg: ⇒ String): Unit

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

def logError(msg: ⇒ String): Unit

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

def logInfo(msg: ⇒ String): Unit

def logName: String

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

def logTrace(msg: ⇒ String): Unit

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

def logWarning(msg: ⇒ String): Unit

def metadataOpsTimeNs: Option[Long]

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def partitionSchema: StructType

def partitionSpec(): PartitionSpec

def refresh(): Unit

val rootPaths: Seq[Path]

def sizeInBytes: Long

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

def toString(): String

final def wait(): Unit

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

final def wait(arg0: Long): Unit

Inherited from PartitioningAwareFileIndex

Inherited from Logging

Inherited from FileIndex

Inherited from AnyRef

Inherited from Any

Ungrouped