Packages

c

com.datastax.spark.connector.rdd

CassandraMergeJoinRDD

class CassandraMergeJoinRDD[L, R] extends RDD[(Seq[L], Seq[R])]

A RDD which pulls from two separate CassandraTableScanRDDs which share partition keys and keyspaces. These tables will be joined on READ using a merge iterator. As long as we join on the token of the partition key the two iterators should be read in order.

Linear Supertypes
RDD[(Seq[L], Seq[R])], Logging, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. CassandraMergeJoinRDD
  2. RDD
  3. Logging
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new CassandraMergeJoinRDD(sc: SparkContext, leftScanRDD: CassandraTableScanRDD[L], rightScanRDD: CassandraTableScanRDD[R])(implicit leftClassTag: ClassTag[L], rightClassTag: ClassTag[R])

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. def ++(other: RDD[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  4. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  5. val TokenColumn: String
  6. def aggregate[U](zeroValue: U)(seqOp: (U, (Seq[L], Seq[R])) ⇒ U, combOp: (U, U) ⇒ U)(implicit arg0: ClassTag[U]): U
    Definition Classes
    RDD
  7. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  8. def barrier(): RDDBarrier[(Seq[L], Seq[R])]
    Definition Classes
    RDD
    Annotations
    @Experimental() @Since( "2.4.0" )
  9. def cache(): CassandraMergeJoinRDD.this.type
    Definition Classes
    RDD
  10. def cartesian[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[((Seq[L], Seq[R]), U)]
    Definition Classes
    RDD
  11. def checkValidMergeJoin(): Unit
  12. def checkpoint(): Unit
    Definition Classes
    RDD
  13. def cleanShuffleDependencies(blocking: Boolean): Unit
    Definition Classes
    RDD
    Annotations
    @Experimental() @DeveloperApi() @Since( "3.1.0" )
  14. def clearDependencies(): Unit
    Attributes
    protected
    Definition Classes
    RDD
  15. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native() @HotSpotIntrinsicCandidate()
  16. def coalesce(numPartitions: Int, shuffle: Boolean, partitionCoalescer: Option[PartitionCoalescer])(implicit ord: Ordering[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  17. def collect[U](f: PartialFunction[(Seq[L], Seq[R]), U])(implicit arg0: ClassTag[U]): RDD[U]
    Definition Classes
    RDD
  18. def collect(): Array[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  19. def compute(split: Partition, context: TaskContext): Iterator[(Seq[L], Seq[R])]
    Definition Classes
    CassandraMergeJoinRDD → RDD
    Annotations
    @DeveloperApi()
  20. val connector: CassandraConnector
  21. def context: SparkContext
    Definition Classes
    RDD
  22. def count(): Long
    Definition Classes
    RDD
  23. def countApprox(timeout: Long, confidence: Double): PartialResult[BoundedDouble]
    Definition Classes
    RDD
  24. def countApproxDistinct(relativeSD: Double): Long
    Definition Classes
    RDD
  25. def countApproxDistinct(p: Int, sp: Int): Long
    Definition Classes
    RDD
  26. def countByValue()(implicit ord: Ordering[(Seq[L], Seq[R])]): Map[(Seq[L], Seq[R]), Long]
    Definition Classes
    RDD
  27. def countByValueApprox(timeout: Long, confidence: Double)(implicit ord: Ordering[(Seq[L], Seq[R])]): PartialResult[Map[(Seq[L], Seq[R]), BoundedDouble]]
    Definition Classes
    RDD
  28. final def dependencies: Seq[Dependency[_]]
    Definition Classes
    RDD
  29. def distinct(): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  30. def distinct(numPartitions: Int)(implicit ord: Ordering[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  31. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  32. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  33. def filter(f: ((Seq[L], Seq[R])) ⇒ Boolean): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  34. def first(): (Seq[L], Seq[R])
    Definition Classes
    RDD
  35. def firstParent[U](implicit arg0: ClassTag[U]): RDD[U]
    Attributes
    protected[org.apache.spark]
    Definition Classes
    RDD
  36. def flatMap[U](f: ((Seq[L], Seq[R])) ⇒ TraversableOnce[U])(implicit arg0: ClassTag[U]): RDD[U]
    Definition Classes
    RDD
  37. def fold(zeroValue: (Seq[L], Seq[R]))(op: ((Seq[L], Seq[R]), (Seq[L], Seq[R])) ⇒ (Seq[L], Seq[R])): (Seq[L], Seq[R])
    Definition Classes
    RDD
  38. def foreach(f: ((Seq[L], Seq[R])) ⇒ Unit): Unit
    Definition Classes
    RDD
  39. def foreachPartition(f: (Iterator[(Seq[L], Seq[R])]) ⇒ Unit): Unit
    Definition Classes
    RDD
  40. def getCheckpointFile: Option[String]
    Definition Classes
    RDD
  41. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  42. def getDependencies: Seq[Dependency[_]]
    Attributes
    protected
    Definition Classes
    RDD
  43. final def getNumPartitions: Int
    Definition Classes
    RDD
    Annotations
    @Since( "1.6.0" )
  44. def getOutputDeterministicLevel: org.apache.spark.rdd.DeterministicLevel.Value
    Attributes
    protected
    Definition Classes
    RDD
    Annotations
    @DeveloperApi()
  45. def getPartitionKey(connector: CassandraConnector, keyspaceName: String, tableName: String): Seq[ColumnDef]
  46. def getPartitions: Array[Partition]
    Attributes
    protected
    Definition Classes
    CassandraMergeJoinRDD → RDD
  47. def getPreferredLocations(split: Partition): Seq[String]
    Definition Classes
    CassandraMergeJoinRDD → RDD
  48. def getResourceProfile(): ResourceProfile
    Definition Classes
    RDD
    Annotations
    @Experimental() @Since( "3.1.0" )
  49. def getStorageLevel: StorageLevel
    Definition Classes
    RDD
  50. def glom(): RDD[Array[(Seq[L], Seq[R])]]
    Definition Classes
    RDD
  51. def groupBy[K](f: ((Seq[L], Seq[R])) ⇒ K, p: Partitioner)(implicit kt: ClassTag[K], ord: Ordering[K]): RDD[(K, Iterable[(Seq[L], Seq[R])])]
    Definition Classes
    RDD
  52. def groupBy[K](f: ((Seq[L], Seq[R])) ⇒ K, numPartitions: Int)(implicit kt: ClassTag[K]): RDD[(K, Iterable[(Seq[L], Seq[R])])]
    Definition Classes
    RDD
  53. def groupBy[K](f: ((Seq[L], Seq[R])) ⇒ K)(implicit kt: ClassTag[K]): RDD[(K, Iterable[(Seq[L], Seq[R])])]
    Definition Classes
    RDD
  54. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  55. val id: Int
    Definition Classes
    RDD
  56. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  57. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  58. def intersection(other: RDD[(Seq[L], Seq[R])], numPartitions: Int): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  59. def intersection(other: RDD[(Seq[L], Seq[R])], partitioner: Partitioner)(implicit ord: Ordering[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  60. def intersection(other: RDD[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  61. lazy val isBarrier_: Boolean
    Attributes
    protected
    Definition Classes
    RDD
    Annotations
    @transient()
  62. def isCheckpointed: Boolean
    Definition Classes
    RDD
  63. def isEmpty(): Boolean
    Definition Classes
    RDD
  64. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  65. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  66. final def iterator(split: Partition, context: TaskContext): Iterator[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  67. def keyBy[K](f: ((Seq[L], Seq[R])) ⇒ K): RDD[(K, (Seq[L], Seq[R]))]
    Definition Classes
    RDD
  68. def localCheckpoint(): CassandraMergeJoinRDD.this.type
    Definition Classes
    RDD
  69. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  70. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  76. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  77. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  81. def map[U](f: ((Seq[L], Seq[R])) ⇒ U)(implicit arg0: ClassTag[U]): RDD[U]
    Definition Classes
    RDD
  82. def mapPartitions[U](f: (Iterator[(Seq[L], Seq[R])]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]
    Definition Classes
    RDD
  83. def mapPartitionsWithIndex[U](f: (Int, Iterator[(Seq[L], Seq[R])]) ⇒ Iterator[U], preservesPartitioning: Boolean)(implicit arg0: ClassTag[U]): RDD[U]
    Definition Classes
    RDD
  84. def max()(implicit ord: Ordering[(Seq[L], Seq[R])]): (Seq[L], Seq[R])
    Definition Classes
    RDD
  85. def min()(implicit ord: Ordering[(Seq[L], Seq[R])]): (Seq[L], Seq[R])
    Definition Classes
    RDD
  86. var name: String
    Definition Classes
    RDD
  87. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  88. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  89. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @HotSpotIntrinsicCandidate()
  90. def parent[U](j: Int)(implicit arg0: ClassTag[U]): RDD[U]
    Attributes
    protected[org.apache.spark]
    Definition Classes
    RDD
  91. val partitioner: Option[Partitioner]
    Definition Classes
    RDD
  92. final def partitions: Array[Partition]
    Definition Classes
    RDD
  93. def persist(): CassandraMergeJoinRDD.this.type
    Definition Classes
    RDD
  94. def persist(newLevel: StorageLevel): CassandraMergeJoinRDD.this.type
    Definition Classes
    RDD
  95. def pipe(command: Seq[String], env: Map[String, String], printPipeContext: ((String) ⇒ Unit) ⇒ Unit, printRDDElement: ((Seq[L], Seq[R]), (String) ⇒ Unit) ⇒ Unit, separateWorkingDir: Boolean, bufferSize: Int, encoding: String): RDD[String]
    Definition Classes
    RDD
  96. def pipe(command: String, env: Map[String, String]): RDD[String]
    Definition Classes
    RDD
  97. def pipe(command: String): RDD[String]
    Definition Classes
    RDD
  98. final def preferredLocations(split: Partition): Seq[String]
    Definition Classes
    RDD
  99. def randomSplit(weights: Array[Double], seed: Long): Array[RDD[(Seq[L], Seq[R])]]
    Definition Classes
    RDD
  100. def reduce(f: ((Seq[L], Seq[R]), (Seq[L], Seq[R])) ⇒ (Seq[L], Seq[R])): (Seq[L], Seq[R])
    Definition Classes
    RDD
  101. def repartition(numPartitions: Int)(implicit ord: Ordering[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  102. def sample(withReplacement: Boolean, fraction: Double, seed: Long): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  103. def saveAsObjectFile(path: String): Unit
    Definition Classes
    RDD
  104. def saveAsTextFile(path: String, codec: Class[_ <: CompressionCodec]): Unit
    Definition Classes
    RDD
  105. def saveAsTextFile(path: String): Unit
    Definition Classes
    RDD
  106. def setName(_name: String): CassandraMergeJoinRDD.this.type
    Definition Classes
    RDD
  107. def sortBy[K](f: ((Seq[L], Seq[R])) ⇒ K, ascending: Boolean, numPartitions: Int)(implicit ord: Ordering[K], ctag: ClassTag[K]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  108. def sparkContext: SparkContext
    Definition Classes
    RDD
  109. def subtract(other: RDD[(Seq[L], Seq[R])], p: Partitioner)(implicit ord: Ordering[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  110. def subtract(other: RDD[(Seq[L], Seq[R])], numPartitions: Int): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  111. def subtract(other: RDD[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  112. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  113. def take(num: Int): Array[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  114. def takeOrdered(num: Int)(implicit ord: Ordering[(Seq[L], Seq[R])]): Array[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  115. def takeSample(withReplacement: Boolean, num: Int, seed: Long): Array[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  116. def toDebugString: String
    Definition Classes
    RDD
  117. def toJavaRDD(): JavaRDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  118. def toLocalIterator: Iterator[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  119. def toString(): String
    Definition Classes
    RDD → AnyRef → Any
  120. def tokenExtractor(row: Row): Token
  121. def top(num: Int)(implicit ord: Ordering[(Seq[L], Seq[R])]): Array[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  122. def treeAggregate[U](zeroValue: U)(seqOp: (U, (Seq[L], Seq[R])) ⇒ U, combOp: (U, U) ⇒ U, depth: Int)(implicit arg0: ClassTag[U]): U
    Definition Classes
    RDD
  123. def treeReduce(f: ((Seq[L], Seq[R]), (Seq[L], Seq[R])) ⇒ (Seq[L], Seq[R]), depth: Int): (Seq[L], Seq[R])
    Definition Classes
    RDD
  124. def union(other: RDD[(Seq[L], Seq[R])]): RDD[(Seq[L], Seq[R])]
    Definition Classes
    RDD
  125. def unpersist(blocking: Boolean): CassandraMergeJoinRDD.this.type
    Definition Classes
    RDD
  126. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  127. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  128. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  129. def withResources(rp: ResourceProfile): CassandraMergeJoinRDD.this.type
    Definition Classes
    RDD
    Annotations
    @Experimental() @Since( "3.1.0" )
  130. def zip[U](other: RDD[U])(implicit arg0: ClassTag[U]): RDD[((Seq[L], Seq[R]), U)]
    Definition Classes
    RDD
  131. def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D])(f: (Iterator[(Seq[L], Seq[R])], 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
  132. def zipPartitions[B, C, D, V](rdd2: RDD[B], rdd3: RDD[C], rdd4: RDD[D], preservesPartitioning: Boolean)(f: (Iterator[(Seq[L], Seq[R])], 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
  133. def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C])(f: (Iterator[(Seq[L], Seq[R])], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]
    Definition Classes
    RDD
  134. def zipPartitions[B, C, V](rdd2: RDD[B], rdd3: RDD[C], preservesPartitioning: Boolean)(f: (Iterator[(Seq[L], Seq[R])], Iterator[B], Iterator[C]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[C], arg2: ClassTag[V]): RDD[V]
    Definition Classes
    RDD
  135. def zipPartitions[B, V](rdd2: RDD[B])(f: (Iterator[(Seq[L], Seq[R])], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]
    Definition Classes
    RDD
  136. def zipPartitions[B, V](rdd2: RDD[B], preservesPartitioning: Boolean)(f: (Iterator[(Seq[L], Seq[R])], Iterator[B]) ⇒ Iterator[V])(implicit arg0: ClassTag[B], arg1: ClassTag[V]): RDD[V]
    Definition Classes
    RDD
  137. def zipWithIndex(): RDD[((Seq[L], Seq[R]), Long)]
    Definition Classes
    RDD
  138. def zipWithUniqueId(): RDD[((Seq[L], Seq[R]), Long)]
    Definition Classes
    RDD

Deprecated Value Members

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

    (Since version ) see corresponding Javadoc for more information.

Inherited from RDD[(Seq[L], Seq[R])]

Inherited from Logging

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped