TableUtils

Instance Constructors

new TableUtils(sparkSession: SparkSession)

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
val aggregationParallelism: Int
def allPartitions(tableName: String, partitionColumnsFilter: Seq[String] = Seq.empty): Seq[Map[String, String]]
def alterTableProperties(tableName: String, properties: Map[String, String], unsetProperties: Seq[String] = Seq()): Unit
def archiveOrDropTableIfExists(tableName: String, timestamp: Option[Instant]): Unit
def archiveTableIfExists(tableName: String, timestamp: Option[Instant]): Unit
final def asInstanceOf[T0]: T0

Definition Classes
Any
val backfillValidationEnforced: Boolean
val blockingCacheEviction: Boolean
val bloomFilterThreshold: Long
val cacheLevel: Option[StorageLevel]
val cacheLevelString: String
def checkTablePermission(tableName: String, fallbackPartition: String = ..., partitionColOpt: Option[String] = None): Boolean
def chunk(partitions: Set[String]): Seq[PartitionRange]
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def columnSizeEstimator(dataType: DataType): Long
def createDatabase(database: String): Boolean
def dropPartitionRange(tableName: String, startDate: String, endDate: String, subPartitionFilters: Map[String, String] = Map.empty): Unit
def dropPartitions(tableName: String, partitions: Seq[String], partitionColumn: String = partitionColumn, subPartitionFilters: Map[String, String] = Map.empty): Unit
def dropTableIfExists(tableName: String): Unit
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def firstAvailablePartition(tableName: String, subPartitionFilters: Map[String, String] = Map.empty, partitionColOpt: Option[String] = None): Option[String]
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getColumnsFromQuery(query: String): Seq[String]
def getFieldNames(schema: StructType): Seq[String]
def getPartitionColumn(columnOpt: Option[String] = None): String
def getPartitionColumn(q: Query): String
def getSchemaFromTable(tableName: String): StructType
def getTableProperties(tableName: String): Option[Map[String, String]]
def insertPartitions(df: DataFrame, tableName: String, tableProperties: Map[String, String] = null, partitionColumns: Seq[String] = Seq(partitionColumn), saveMode: SaveMode = SaveMode.Overwrite, fileFormat: String = "PARQUET", autoExpand: Boolean = false, stats: Option[DfStats] = None, sortByCols: Seq[String] = Seq.empty): Unit
def insertUnPartitioned(df: DataFrame, tableName: String, tableProperties: Map[String, String] = null, saveMode: SaveMode = SaveMode.Overwrite, fileFormat: String = "PARQUET"): Unit
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isPartitioned(tableName: String, partitionColOpt: Option[String] = None): Boolean
val joinPartParallelism: Int
def lastAvailablePartition(tableName: String, subPartitionFilters: Map[String, String] = Map.empty, partitionColOpt: Option[String] = None): Option[String]
def loadEntireTable(tableName: String): DataFrame
lazy val logger: Logger
val maxWait: Int
val minWriteShuffleParallelism: Int
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
val partitionColumn: String
val partitionSpec: PartitionSpec
def partitions(tableName: String, subPartitionsFilter: Map[String, String] = Map.empty, partitionColOpt: Option[String] = None): Seq[String]
def preAggRepartition(rdd: RDD[Row]): RDD[Row]
def preAggRepartition(df: DataFrame): DataFrame
val smallModeNumRowsCutoff: Int
val smallModelEnabled: Boolean
val sparkSession: SparkSession
def sql(query: String): DataFrame
def sqlWithDefaultPartitionColumn(query: String, existingPartitionColumn: String): DataFrame
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def tableExists(tableName: String): Boolean
def tableReadFormat(tableName: String): Format
def unfilledRanges(outputTable: String, outputPartitionRange: PartitionRange, inputTables: Option[Seq[String]] = None, inputTableToSubPartitionFiltersMap: Map[String, Map[String, String]] = Map.empty, inputTableToPartitionColumnsMap: Map[String, String] = Map.empty, inputToOutputShift: Int = 0, skipFirstHole: Boolean = true): Option[Seq[PartitionRange]]
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( ... )
def wrapWithCache[T](opString: String, dataFrame: DataFrame)(func: ⇒ T): Try[T]

Deprecated Value Members

def dropPartitionsAfterHole(inputTable: String, outputTable: String, partitionRange: PartitionRange, subPartitionFilters: Map[String, String] = Map.empty): Option[String]

Annotations
@deprecated
Deprecated

Related Doc: package spark

case class TableUtils(sparkSession: SparkSession) extends Product with Serializable

Instance Constructors

new TableUtils(sparkSession: SparkSession)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

val aggregationParallelism: Int

def allPartitions(tableName: String, partitionColumnsFilter: Seq[String] = Seq.empty): Seq[Map[String, String]]

def alterTableProperties(tableName: String, properties: Map[String, String], unsetProperties: Seq[String] = Seq()): Unit

def archiveOrDropTableIfExists(tableName: String, timestamp: Option[Instant]): Unit

def archiveTableIfExists(tableName: String, timestamp: Option[Instant]): Unit

final def asInstanceOf[T0]: T0

val backfillValidationEnforced: Boolean

val blockingCacheEviction: Boolean

val bloomFilterThreshold: Long

val cacheLevel: Option[StorageLevel]

val cacheLevelString: String

def checkTablePermission(tableName: String, fallbackPartition: String = ..., partitionColOpt: Option[String] = None): Boolean

def chunk(partitions: Set[String]): Seq[PartitionRange]

def clone(): AnyRef

def columnSizeEstimator(dataType: DataType): Long

def createDatabase(database: String): Boolean

def dropPartitionRange(tableName: String, startDate: String, endDate: String, subPartitionFilters: Map[String, String] = Map.empty): Unit

def dropPartitions(tableName: String, partitions: Seq[String], partitionColumn: String = partitionColumn, subPartitionFilters: Map[String, String] = Map.empty): Unit

def dropTableIfExists(tableName: String): Unit

final def eq(arg0: AnyRef): Boolean

def finalize(): Unit

def firstAvailablePartition(tableName: String, subPartitionFilters: Map[String, String] = Map.empty, partitionColOpt: Option[String] = None): Option[String]

final def getClass(): Class[_]

def getColumnsFromQuery(query: String): Seq[String]

def getFieldNames(schema: StructType): Seq[String]

def getPartitionColumn(columnOpt: Option[String] = None): String

def getPartitionColumn(q: Query): String

def getSchemaFromTable(tableName: String): StructType

def getTableProperties(tableName: String): Option[Map[String, String]]

def insertUnPartitioned(df: DataFrame, tableName: String, tableProperties: Map[String, String] = null, saveMode: SaveMode = SaveMode.Overwrite, fileFormat: String = "PARQUET"): Unit

final def isInstanceOf[T0]: Boolean

def isPartitioned(tableName: String, partitionColOpt: Option[String] = None): Boolean

val joinPartParallelism: Int

def lastAvailablePartition(tableName: String, subPartitionFilters: Map[String, String] = Map.empty, partitionColOpt: Option[String] = None): Option[String]

def loadEntireTable(tableName: String): DataFrame

lazy val logger: Logger

val maxWait: Int

val minWriteShuffleParallelism: Int

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

val partitionColumn: String

val partitionSpec: PartitionSpec

def partitions(tableName: String, subPartitionsFilter: Map[String, String] = Map.empty, partitionColOpt: Option[String] = None): Seq[String]

def preAggRepartition(rdd: RDD[Row]): RDD[Row]

def preAggRepartition(df: DataFrame): DataFrame

val smallModeNumRowsCutoff: Int

val smallModelEnabled: Boolean

val sparkSession: SparkSession

def sql(query: String): DataFrame

def sqlWithDefaultPartitionColumn(query: String, existingPartitionColumn: String): DataFrame

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

def tableExists(tableName: String): Boolean

def tableReadFormat(tableName: String): Format

final def wait(): Unit

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

final def wait(arg0: Long): Unit

def wrapWithCache[T](opString: String, dataFrame: DataFrame)(func: ⇒ T): Try[T]

Deprecated Value Members

def dropPartitionsAfterHole(inputTable: String, outputTable: String, partitionRange: PartitionRange, subPartitionFilters: Map[String, String] = Map.empty): Option[String]

Inherited from Serializable

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from AnyRef

Inherited from Any

Ungrouped