SuccinctRDDImpl

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

def ++(other: RDD[Array[Byte]]): RDD[Array[Byte]]

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

def aggregate[U](zeroValue: U)(seqOp: (U, Array[Byte]) ⇒ U, combOp: (U, U) ⇒ U)(implicit arg0: ClassTag[U]): U

final def asInstanceOf[T0]: T0

def cache(): SuccinctRDDImpl.this.type

Persists the Succinct partitions at targetStorageLevel, which defaults to MEMORY_ONLY.

def cartesian[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(Array[Byte], U)]

def checkpoint(): Unit

def clearDependencies(): Unit

def clone(): AnyRef

def coalesce(numPartitions: Int, shuffle: Boolean)(implicit ord: Ordering[Array[Byte]]): RDD[Array[Byte]]

def collect[U](f: PartialFunction[Array[Byte], U])(implicit arg0: ClassTag[U]): RDD[U]

def collect(): Array[Array[Byte]]

def compute(split: Partition, context: TaskContext): Iterator[Array[Byte]]

Overrides the compute function to return iterator over Succinct records.

def context: SparkContext

def count(): Long

Count the number of records in the SuccinctRDD.

def countApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble]

def countApproxDistinct(relativeSD: Double): Long

def countApproxDistinct(p: Int, sp: Int): Long

def countByValue()(implicit ord: Ordering[Array[Byte]]): Map[Array[Byte], Long]

def countByValueApprox(timeout: Long, confidence: Double)(implicit ord: Ordering[Array[Byte]]): PartialResult[Map[Array[Byte], BoundedDouble]]

def countOffsets(query: String): Long

Counts for all occurrences of a query in the RDD.

def countOffsets(query: Array[Byte]): Long

Counts for all occurrences of a query in the RDD.

final def dependencies: Seq[Dependency[_]]

def distinct(): RDD[Array[Byte]]

def distinct(numPartitions: Int)(implicit ord: Ordering[Array[Byte]]): RDD[Array[Byte]]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def extract(offset: Long, length: Int): Array[Byte]

Extract data from an RDD *

def filter(f: (Array[Byte]) ⇒ Boolean): RDD[Array[Byte]]

def finalize(): Unit

def first(): Array[Byte]

def firstParent[U](implicit arg0: ClassTag[U]): RDD[U]

def flatMap[U](f: (Array[Byte]) ⇒ TraversableOnce[U])(implicit arg0: ClassTag[U]): RDD[U]

def fold(zeroValue: Array[Byte])(op: (Array[Byte], Array[Byte]) ⇒ Array[Byte]): Array[Byte]

def foreach(f: (Array[Byte]) ⇒ Unit): Unit

def foreachPartition(f: (Iterator[Array[Byte]]) ⇒ Unit): Unit

def getCheckpointFile: Option[String]

final def getClass(): Class[_]

def getDependencies: Seq[Dependency[_]]

def getFirstParent: RDD[SuccinctPartition]

Returns first parent of the RDD.

def getPartitions: Array[Partition]

Returns the array of partitions.

def getPreferredLocations(split: Partition): Seq[String]

def getStorageLevel: StorageLevel

def glom(): RDD[Array[Array[Byte]]]

def groupBy[K](f: (Array[Byte]) ⇒ K, p: Partitioner)(implicit kt: ClassTag[K], ord: Ordering[K]): RDD[(K, Iterable[Array[Byte]])]

def groupBy[K](f: (Array[Byte]) ⇒ K, numPartitions: Int)(implicit kt: ClassTag[K]): RDD[(K, Iterable[Array[Byte]])]

def groupBy[K](f: (Array[Byte]) ⇒ K)(implicit kt: ClassTag[K]): RDD[(K, Iterable[Array[Byte]])]

def hashCode(): Int

val id: Int

def intersection(other: RDD[Array[Byte]], numPartitions: Int): RDD[Array[Byte]]

def intersection(other: RDD[Array[Byte]], partitioner: Partitioner)(implicit ord: Ordering[Array[Byte]]): RDD[Array[Byte]]

def intersection(other: RDD[Array[Byte]]): RDD[Array[Byte]]

def isCheckpointed: Boolean

def isEmpty(): Boolean

final def isInstanceOf[T0]: Boolean

def isTraceEnabled(): Boolean

final def iterator(split: Partition, context: TaskContext): Iterator[Array[Byte]]

def keyBy[K](f: (Array[Byte]) ⇒ K): RDD[(K, Array[Byte])]

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 map[U](f: (Array[Byte]) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

def mapPartitions[U](f: (Iterator[Array[Byte]]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapPartitionsWithIndex[U](f: (Int, Iterator[Array[Byte]]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def max()(implicit ord: Ordering[Array[Byte]]): Array[Byte]

def min()(implicit ord: Ordering[Array[Byte]]): Array[Byte]

var name: String

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def parent[U](j: Int)(implicit arg0: ClassTag[U]): RDD[U]

val partitionOffsetRanges: Array[Range]

val partitioner: Option[Partitioner]

final def partitions: Array[Partition]

val partitionsRDD: RDD[SuccinctPartition]

The input RDD of partitions.

def persist(newLevel: StorageLevel): SuccinctRDDImpl.this.type

Persists the Succinct partitions at the specified storage level, ignoring any existing target storage level.

def persist(): SuccinctRDDImpl.this.type

def pipe(command: Seq[String], env: Map[String, String], printPipeContext: ((String) ⇒ Unit) ⇒ Unit, printRDDElement: (Array[Byte], (String) ⇒ Unit) ⇒ Unit, separateWorkingDir: Boolean): RDD[String]

def pipe(command: String, env: Map[String, String]): RDD[String]

def pipe(command: String): RDD[String]

final def preferredLocations(split: Partition): Seq[String]

def randomSplit(weights: Array[Double], seed: Long): Array[RDD[Array[Byte]]]

def reduce(f: (Array[Byte], Array[Byte]) ⇒ Array[Byte]): Array[Byte]

def regexSearch(query: String): RDD[Array[Byte]]

Searches of all records that contains a regular expression search query and returns all such records.

def regexSearchOffsets(query: String): RDD[RegExMatch]

Searches for the input regular expression within each RDD and returns results as (offset, length) pairs.

def repartition(numPartitions: Int)(implicit ord: Ordering[Array[Byte]]): RDD[Array[Byte]]

def sample(withReplacement: Boolean, fraction: Double, seed: Long): RDD[Array[Byte]]

def save(location: String): Unit

Saves the SuccinctRDD at the specified path.

def saveAsObjectFile(path: String): Unit

def saveAsTextFile(path: String, codec: Class[_ <: CompressionCodec]): Unit

def saveAsTextFile(path: String): Unit

def search(query: String): SearchRecordIdResultsRDD

Searches for all records that match a query and returns results as recordIds relative to each partition.

def search(query: Array[Byte]): SearchRecordIdResultsRDD

Searches for all records that match a query and returns results as recordIds relative to each partition.

def searchOffsets(query: String): RDD[Long]

Search for all occurrences of a query string within the RDD.

def searchOffsets(query: Array[Byte]): RDD[Long]

Search for all occurrences of a query within the RDD.

def setName(_name: String): SuccinctRDDImpl.this.type

Set the name for the RDD; By default set to "SuccinctRDD"

def sortBy[K](f: (Array[Byte]) ⇒ K, ascending: Boolean, numPartitions: Int)(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[Array[Byte]]

def sparkContext: SparkContext

def subtract(other: RDD[Array[Byte]], p: Partitioner)(implicit ord: Ordering[Array[Byte]]): RDD[Array[Byte]]

def subtract(other: RDD[Array[Byte]], numPartitions: Int): RDD[Array[Byte]]

def subtract(other: RDD[Array[Byte]]): RDD[Array[Byte]]

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

def take(num: Int): Array[Array[Byte]]

def takeOrdered(num: Int)(implicit ord: Ordering[Array[Byte]]): Array[Array[Byte]]

def takeSample(withReplacement: Boolean, num: Int, seed: Long): Array[Array[Byte]]

val targetStorageLevel: StorageLevel

The storage level for the RDD.

def toDebugString: String

def toJavaRDD(): JavaRDD[Array[Byte]]

def toLocalIterator: Iterator[Array[Byte]]

def toString(): String

def top(num: Int)(implicit ord: Ordering[Array[Byte]]): Array[Array[Byte]]

def treeAggregate[U](zeroValue: U)(seqOp: (U, Array[Byte]) ⇒ U, combOp: (U, U) ⇒ U, depth: Int)(implicit arg0: ClassTag[U]): U

def treeReduce(f: (Array[Byte], Array[Byte]) ⇒ Array[Byte], depth: Int): Array[Byte]

def union(other: RDD[Array[Byte]]): RDD[Array[Byte]]

def unpersist(blocking: Boolean = true): SuccinctRDDImpl.this.type

Un-persists the Succinct partitions using the specified blocking mode.

final def wait(): Unit

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

final def wait(arg0: Long): Unit

def zip[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(Array[Byte], U)]

def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D])(f: (Iterator[Array[Byte]], Iterator[B], Iterator[C], Iterator[D]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[D], arg3: ClassTag[V]): RDD[V]

def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D], preservesPartitioning: Boolean)(f: (Iterator[Array[Byte]], Iterator[B], Iterator[C], Iterator[D]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[D], arg3: ClassTag[V]): RDD[V]

def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C])(f: (Iterator[Array[Byte]], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C], preservesPartitioning: Boolean)(f: (Iterator[Array[Byte]], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]

def zipPartitions[B, V](rdd2: RDD[B])(f: (Iterator[Array[Byte]], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

def zipPartitions[B, V](rdd2: RDD[B], preservesPartitioning: Boolean)(f: (Iterator[Array[Byte]], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

def zipWithIndex(): RDD[(Array[Byte], Long)]

def zipWithUniqueId(): RDD[(Array[Byte], Long)]

def filterWith[A](constructA: (Int) ⇒ A)(p: (Array[Byte], A) ⇒ Boolean): RDD[Array[Byte]]

def flatMapWith[A, U](constructA: (Int) ⇒ A, preservesPartitioning: Boolean)(f: (Array[Byte], A) ⇒ Seq[U])(implicit arg0: ClassTag[U]): RDD[U]

def foreachWith[A](constructA: (Int) ⇒ A)(f: (Array[Byte], A) ⇒ Unit): Unit

def mapPartitionsWithContext[U](f: (TaskContext, Iterator[Array[Byte]]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapPartitionsWithSplit[U](f: (Int, Iterator[Array[Byte]]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

def mapWith[A, U](constructA: (Int) ⇒ A, preservesPartitioning: Boolean)(f: (Array[Byte], A) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

def toArray(): Array[Array[Byte]]