SolrRDD

Instance Constructors

new SolrRDD(zkHost: String, collection: String, sc: SparkContext, requestHandler: Option[String] = None, query: Option[String] = None, fields: Option[Array[String]] = None, rows: Option[Int] = None, splitField: Option[String] = None, splitsPerShard: Option[Int] = None, solrQuery: Option[SolrQuery] = None, uKey: Option[String] = None)(implicit arg0: ClassTag[T])

Abstract Value Members

abstract def buildQuery: SolrQuery
abstract def compute(split: Partition, context: TaskContext): Iterator[T]

Definition Classes
RDD
Annotations
@DeveloperApi()
abstract def doSplits(): SolrRDD[T]
abstract def getPartitions: Array[Partition]

Attributes
protected
Definition Classes
RDD
abstract def query(solrQuery: SolrQuery): SolrRDD[T]
abstract def query(q: String): SolrRDD[T]
abstract def requestHandler(requestHandler: String): SolrRDD[T]
abstract def rows(rows: Int): SolrRDD[T]
abstract def select(fl: Array[String]): SolrRDD[T]
abstract def select(fl: String): SolrRDD[T]
abstract def splitField(field: String): SolrRDD[T]
abstract def splitsPerShard(splitsPerShard: Int): SolrRDD[T]

Concrete Value Members

final def !=(arg0: Any): Boolean

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

Definition Classes
AnyRef → Any
def ++(other: RDD[T]): RDD[T]

Definition Classes
RDD
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def aggregate[U](zeroValue: U)(seqOp: (U, T) ⇒ U, combOp: (U, U) ⇒ U)(implicit arg0: ClassTag[U]): U

Definition Classes
RDD
final def asInstanceOf[T0]: T0

Definition Classes
Any
def barrier(): RDDBarrier[T]

Definition Classes
RDD
Annotations
@Experimental() @Since( "2.4.0" )
def cache(): SolrRDD.this.type

Definition Classes
RDD
def calculateSplitsPerShard(solrQuery: SolrQuery, shardSize: Int, replicaSize: Int, docsPerTask: Int = 10000, maxRows: Option[Int] = None): Int
def cartesian[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(T, U)]

Definition Classes
RDD
def checkpoint(): Unit

Definition Classes
RDD
def clearDependencies(): Unit

Attributes
protected
Definition Classes
RDD
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def coalesce(numPartitions: Int, shuffle: Boolean, partitionCoalescer: Option[PartitionCoalescer])(implicit ord: Ordering[T]): RDD[T]

Definition Classes
RDD
def collect[U](f: PartialFunction[T, U])(implicit arg0: ClassTag[U]): RDD[U]

Definition Classes
RDD
def collect(): Array[T]

Definition Classes
RDD
val collection: String
def context: SparkContext

Definition Classes
RDD
def count(): Long

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

Definition Classes
RDD
def countApproxDistinct(relativeSD: Double): Long

Definition Classes
RDD
def countApproxDistinct(p: Int, sp: Int): Long

Definition Classes
RDD
def countByValue()(implicit ord: Ordering[T]): Map[T, Long]

Definition Classes
RDD
def countByValueApprox(timeout: Long, confidence: Double)(implicit ord: Ordering[T]): PartialResult[Map[T, BoundedDouble]]

Definition Classes
RDD
final def dependencies: Seq[Dependency[_]]

Definition Classes
RDD
def distinct(): RDD[T]

Definition Classes
RDD
def distinct(numPartitions: Int)(implicit ord: Ordering[T]): RDD[T]

Definition Classes
RDD
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def filter(f: (T) ⇒ Boolean): RDD[T]

Definition Classes
RDD
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def first(): T

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

Attributes
protected[org.apache.spark]
Definition Classes
RDD
def flatMap[U](f: (T) ⇒ TraversableOnce[U])(implicit arg0: ClassTag[U]): RDD[U]

Definition Classes
RDD
def fold(zeroValue: T)(op: (T, T) ⇒ T): T

Definition Classes
RDD
def foreach(f: (T) ⇒ Unit): Unit

Definition Classes
RDD
def foreachPartition(f: (Iterator[T]) ⇒ Unit): Unit

Definition Classes
RDD
def getCheckpointFile: Option[String]

Definition Classes
RDD
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getDependencies: Seq[Dependency[_]]

Attributes
protected
Definition Classes
RDD
final def getNumPartitions: Int

Definition Classes
RDD
Annotations
@Since( "1.6.0" )
def getOutputDeterministicLevel: org.apache.spark.rdd.DeterministicLevel.Value

Attributes
protected
Definition Classes
RDD
Annotations
@DeveloperApi()
def getPreferredLocations(split: Partition): Seq[String]

Definition Classes
SolrRDD → RDD
def getReplicaToQuery(partition: SolrRDDPartition, attempt_no: Int): String
def getStorageLevel: StorageLevel

Definition Classes
RDD
def glom(): RDD[Array[T]]

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

Definition Classes
RDD
def groupBy[K](f: (T) ⇒ K, numPartitions: Int)(implicit kt: ClassTag[K]): RDD[(K, Iterable[T])]

Definition Classes
RDD
def groupBy[K](f: (T) ⇒ K)(implicit kt: ClassTag[K]): RDD[(K, Iterable[T])]

Definition Classes
RDD
def hashCode(): Int

Definition Classes
AnyRef → Any
val id: Int

Definition Classes
RDD
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

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

Attributes
protected
Definition Classes
Logging
def intersection(other: RDD[T], numPartitions: Int): RDD[T]

Definition Classes
RDD
def intersection(other: RDD[T], partitioner: Partitioner)(implicit ord: Ordering[T]): RDD[T]

Definition Classes
RDD
def intersection(other: RDD[T]): RDD[T]

Definition Classes
RDD
lazy val isBarrier_: Boolean

Attributes
protected
Definition Classes
RDD
def isCheckpointed: Boolean

Definition Classes
RDD
def isEmpty(): Boolean

Definition Classes
RDD
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
final def iterator(split: Partition, context: TaskContext): Iterator[T]

Definition Classes
RDD
def keyBy[K](f: (T) ⇒ K): RDD[(K, T)]

Definition Classes
RDD
def localCheckpoint(): SolrRDD.this.type

Definition Classes
RDD
def log: org.slf4j.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
lazy val logger: Logger

Attributes
protected
Definition Classes
LazyLogging
def map[U](f: (T) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]

Definition Classes
RDD
def mapPartitions[U](f: (Iterator[T]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

Definition Classes
RDD
def mapPartitionsWithIndex[U](f: (Int, Iterator[T]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]

Definition Classes
RDD
def max()(implicit ord: Ordering[T]): T

Definition Classes
RDD
def min()(implicit ord: Ordering[T]): T

Definition Classes
RDD
var name: String

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

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

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

Attributes
protected[org.apache.spark]
Definition Classes
RDD
val partitioner: Option[Partitioner]

Definition Classes
RDD
final def partitions: Array[Partition]

Definition Classes
RDD
def persist(): SolrRDD.this.type

Definition Classes
RDD
def persist(newLevel: StorageLevel): SolrRDD.this.type

Definition Classes
RDD
def pipe(command: Seq[String], env: Map[String, String], printPipeContext: ((String) ⇒ Unit) ⇒ Unit, printRDDElement: (T, (String) ⇒ Unit) ⇒ Unit, separateWorkingDir: Boolean, bufferSize: Int, encoding: String): RDD[String]

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

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

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

Definition Classes
RDD
def randomSplit(weights: Array[Double], seed: Long): Array[RDD[T]]

Definition Classes
RDD
def reduce(f: (T, T) ⇒ T): T

Definition Classes
RDD
def repartition(numPartitions: Int)(implicit ord: Ordering[T]): RDD[T]

Definition Classes
RDD
def sample(withReplacement: Boolean, fraction: Double, seed: Long): RDD[T]

Definition Classes
RDD
def saveAsObjectFile(path: String): Unit

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

Definition Classes
RDD
def saveAsTextFile(path: String): Unit

Definition Classes
RDD
def setName(_name: String): SolrRDD.this.type

Definition Classes
RDD
def solrCount: BigInt
def sortBy[K](f: (T) ⇒ K, ascending: Boolean, numPartitions: Int)(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[T]

Definition Classes
RDD
def sparkContext: SparkContext

Definition Classes
RDD
def subtract(other: RDD[T], p: Partitioner)(implicit ord: Ordering[T]): RDD[T]

Definition Classes
RDD
def subtract(other: RDD[T], numPartitions: Int): RDD[T]

Definition Classes
RDD
def subtract(other: RDD[T]): RDD[T]

Definition Classes
RDD
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def take(num: Int): Array[T]

Definition Classes
RDD
def takeOrdered(num: Int)(implicit ord: Ordering[T]): Array[T]

Definition Classes
RDD
def takeSample(withReplacement: Boolean, num: Int, seed: Long): Array[T]

Definition Classes
RDD
def toDebugString: String

Definition Classes
RDD
def toJavaRDD(): JavaRDD[T]

Definition Classes
RDD
def toLocalIterator: Iterator[T]

Definition Classes
RDD
def toString(): String

Definition Classes
RDD → AnyRef → Any
def top(num: Int)(implicit ord: Ordering[T]): Array[T]

Definition Classes
RDD
def treeAggregate[U](zeroValue: U)(seqOp: (U, T) ⇒ U, combOp: (U, U) ⇒ U, depth: Int)(implicit arg0: ClassTag[U]): U

Definition Classes
RDD
def treeReduce(f: (T, T) ⇒ T, depth: Int): T

Definition Classes
RDD
def union(other: RDD[T]): RDD[T]

Definition Classes
RDD
val uniqueKey: String
def unpersist(blocking: Boolean): SolrRDD.this.type

Definition Classes
RDD
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 zip[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[(T, U)]

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

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

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

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

Definition Classes
RDD
def zipPartitions[B, V](rdd2: RDD[B])(f: (Iterator[T], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]

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

Definition Classes
RDD
def zipWithIndex(): RDD[(T, Long)]

Definition Classes
RDD
def zipWithUniqueId(): RDD[(T, Long)]

Definition Classes
RDD
val zkHost: String

Related Docs: object SolrRDD | package rdd

abstract class SolrRDD[T] extends RDD[T] with LazyLogging

Instance Constructors

Abstract Value Members

abstract def buildQuery: SolrQuery

abstract def compute(split: Partition, context: TaskContext): Iterator[T]

abstract def doSplits(): SolrRDD[T]

abstract def getPartitions: Array[Partition]

abstract def query(solrQuery: SolrQuery): SolrRDD[T]

abstract def query(q: String): SolrRDD[T]

abstract def requestHandler(requestHandler: String): SolrRDD[T]

abstract def rows(rows: Int): SolrRDD[T]

abstract def select(fl: Array[String]): SolrRDD[T]

abstract def select(fl: String): SolrRDD[T]

abstract def splitField(field: String): SolrRDD[T]

abstract def splitsPerShard(splitsPerShard: Int): SolrRDD[T]

Concrete Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

def ++(other: RDD[T]): RDD[T]

final def ==(arg0: Any): Boolean

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

final def asInstanceOf[T0]: T0

def barrier(): RDDBarrier[T]

def cache(): SolrRDD.this.type

def calculateSplitsPerShard(solrQuery: SolrQuery, shardSize: Int, replicaSize: Int, docsPerTask: Int = 10000, maxRows: Option[Int] = None): Int

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

def checkpoint(): Unit

def clearDependencies(): Unit

def clone(): AnyRef

def coalesce(numPartitions: Int, shuffle: Boolean, partitionCoalescer: Option[PartitionCoalescer])(implicit ord: Ordering[T]): RDD[T]

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

def collect(): Array[T]

val collection: String

def context: SparkContext

def count(): Long

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[T]): Map[T, Long]

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

final def dependencies: Seq[Dependency[_]]

def distinct(): RDD[T]

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

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def filter(f: (T) ⇒ Boolean): RDD[T]

def finalize(): Unit

def first(): T

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

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

def fold(zeroValue: T)(op: (T, T) ⇒ T): T

def foreach(f: (T) ⇒ Unit): Unit

def foreachPartition(f: (Iterator[T]) ⇒ Unit): Unit

def getCheckpointFile: Option[String]

final def getClass(): Class[_]

def getDependencies: Seq[Dependency[_]]

final def getNumPartitions: Int

def getOutputDeterministicLevel: org.apache.spark.rdd.DeterministicLevel.Value

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

def getReplicaToQuery(partition: SolrRDDPartition, attempt_no: Int): String

def getStorageLevel: StorageLevel

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

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

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

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

def hashCode(): Int

val id: Int

def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

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

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

def intersection(other: RDD[T]): RDD[T]

lazy val isBarrier_: Boolean

def isCheckpointed: Boolean

def isEmpty(): Boolean

final def isInstanceOf[T0]: Boolean

def isTraceEnabled(): Boolean

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