org.apache.spark.util.CollectionsUtils Scala Examples

The following examples show how to use org.apache.spark.util.CollectionsUtils. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.
Example 1
Source File: HBasePartitioner.scala    From Backup-Repo   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.hbase

import java.io.{IOException, ObjectInputStream, ObjectOutputStream}

import org.apache.hadoop.hbase.util.Bytes
import org.apache.spark.serializer.JavaSerializer
import org.apache.spark.util.{CollectionsUtils, Utils}
import org.apache.spark.{Partitioner, SparkEnv}

object HBasePartitioner {
  implicit object HBaseRawOrdering extends Ordering[HBaseRawType] {
    def compare(a: HBaseRawType, b: HBaseRawType) = Bytes.compareTo(a, b)
  }
}

class HBasePartitioner (var splitKeys: Array[HBaseRawType]) extends Partitioner {
  import HBasePartitioner.HBaseRawOrdering

  type t = HBaseRawType

  lazy private val len = splitKeys.length

  // For pre-split table splitKeys(0) = bytes[0], to remove it,
  // otherwise partition 0 always be empty and
  // we will miss the last region's date when bulk load
  lazy private val realSplitKeys = if (splitKeys.isEmpty) splitKeys else splitKeys.tail

  def numPartitions = if (len == 0) 1 else len

  @transient private val binarySearch: ((Array[t], t) => Int) = CollectionsUtils.makeBinarySearch[t]

  def getPartition(key: Any): Int = {
    val k = key.asInstanceOf[t]
    var partition = 0
    if (len <= 128 && len > 0) {
      // If we have less than 128 partitions naive search
      val ordering = implicitly[Ordering[t]]
      while (partition < realSplitKeys.length && ordering.gt(k, realSplitKeys(partition))) {
        partition += 1
      }
    } else {
      // Determine which binary search method to use only once.
      partition = binarySearch(realSplitKeys, k)
      // binarySearch either returns the match location or -[insertion point]-1
      if (partition < 0) {
        partition = -partition - 1
      }
      if (partition > realSplitKeys.length) {
        partition = realSplitKeys.length
      }
    }
    partition
  }

  override def equals(other: Any): Boolean = other match {
    case r: HBasePartitioner =>
      r.splitKeys.sameElements(splitKeys)
    case _ =>
      false
  }

  override def hashCode(): Int = {
    val prime = 31
    var result = 1
    var i = 0
    while (i < splitKeys.length) {
      result = prime * result + splitKeys(i).hashCode
      i += 1
    }
    result = prime * result
    result
  }
}
Example 2
Source File: HBasePartitioner.scala    From Heracles   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.hbase

import org.apache.hadoop.hbase.util.Bytes
import org.apache.spark.Partitioner
import org.apache.spark.util.CollectionsUtils

object HBasePartitioner {
  implicit object HBaseRawOrdering extends Ordering[HBaseRawType] {
    def compare(a: HBaseRawType, b: HBaseRawType) = Bytes.compareTo(a, b)
  }
}

class HBasePartitioner (val splitKeys: Array[HBaseRawType]) extends Partitioner {
  import HBasePartitioner.HBaseRawOrdering

  type t = HBaseRawType

  lazy private val len = splitKeys.length

  // For pre-split table splitKeys(0) = bytes[0], to remove it,
  // otherwise partition 0 always be empty and
  // we will miss the last region's date when bulk load
  lazy private val realSplitKeys = if (splitKeys.isEmpty) splitKeys else splitKeys.tail

  override def numPartitions = if (len == 0) 1 else len

  @transient private lazy val binarySearch: ((Array[t], t) => Int) = CollectionsUtils.makeBinarySearch[t]

  override def getPartition(key: Any): Int = {
    val k = key.asInstanceOf[t]
    var partition = 0
    if (len <= 128 && len > 0) {
      // If we have less than 128 partitions naive search
      val ordering = implicitly[Ordering[t]]
      while (partition < realSplitKeys.length && ordering.gt(k, realSplitKeys(partition))) {
        partition += 1
      }
    } else {
      // Determine which binary search method to use only once.
      partition = binarySearch(realSplitKeys, k)
      // binarySearch either returns the match location or -[insertion point]-1
      if (partition < 0) {
        partition = -partition - 1
      }
      if (partition > realSplitKeys.length) {
        partition = realSplitKeys.length
      }
    }
    partition
  }

  override def equals(other: Any): Boolean = other match {
    case r: HBasePartitioner =>
      r.splitKeys.sameElements(splitKeys)
    case _ =>
      false
  }

  override def hashCode(): Int = {
    val prime = 31
    var result = 1
    var i = 0
    while (i < splitKeys.length) {
      result = prime * result + splitKeys(i).hashCode
      i += 1
    }
    result = prime * result
    result
  }
}
Example 3
Source File: HBasePartitioner.scala    From Spark-SQL-on-HBase   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.hbase

import org.apache.hadoop.hbase.util.Bytes
import org.apache.spark.Partitioner
import org.apache.spark.util.CollectionsUtils

object HBasePartitioner {
  implicit object HBaseRawOrdering extends Ordering[HBaseRawType] {
    def compare(a: HBaseRawType, b: HBaseRawType) = Bytes.compareTo(a, b)
  }
}

class HBasePartitioner (var splitKeys: Array[HBaseRawType]) extends Partitioner {
  import HBasePartitioner.HBaseRawOrdering

  type t = HBaseRawType

  lazy private val len = splitKeys.length

  // For pre-split table splitKeys(0) = bytes[0], to remove it,
  // otherwise partition 0 always be empty and
  // we will miss the last region's date when bulk load
  lazy private val realSplitKeys = if (splitKeys.isEmpty) splitKeys else splitKeys.tail

  def numPartitions = if (len == 0) 1 else len

  @transient private lazy val binarySearch: ((Array[t], t) => Int) = CollectionsUtils.makeBinarySearch[t]

  def getPartition(key: Any): Int = {
    val k = key.asInstanceOf[t]
    var partition = 0
    if (len <= 128 && len > 0) {
      // If we have less than 128 partitions naive search
      val ordering = implicitly[Ordering[t]]
      while (partition < realSplitKeys.length && ordering.gt(k, realSplitKeys(partition))) {
        partition += 1
      }
    } else {
      // Determine which binary search method to use only once.
      partition = binarySearch(realSplitKeys, k)
      // binarySearch either returns the match location or -[insertion point]-1
      if (partition < 0) {
        partition = -partition - 1
      }
      if (partition > realSplitKeys.length) {
        partition = realSplitKeys.length
      }
    }
    partition
  }

  override def equals(other: Any): Boolean = other match {
    case r: HBasePartitioner =>
      r.splitKeys.sameElements(splitKeys)
    case _ =>
      false
  }

  override def hashCode(): Int = {
    val prime = 31
    var result = 1
    var i = 0
    while (i < splitKeys.length) {
      result = prime * result + splitKeys(i).hashCode
      i += 1
    }
    result = prime * result
    result
  }
}
Example 4
Source File: RangeDPartitioner.scala    From Simba   with Apache License 2.0 5 votes vote down vote up 
package org.apache.spark.sql.simba.partitioner

import org.apache.spark.util.CollectionsUtils
import org.apache.spark.{Partitioner, SparkEnv}
import org.apache.spark.rdd.{RDD, ShuffledRDD}
import org.apache.spark.shuffle.sort.SortShuffleManager
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.util.MutablePair

import scala.reflect.ClassTag


object RangeDPartition {
  def sortBasedShuffleOn: Boolean = SparkEnv.get.shuffleManager.isInstanceOf[SortShuffleManager]

  def apply[K: Ordering: ClassTag, T](origin: RDD[(K, (T, InternalRow))],
                                      range_bounds: Array[K]): RDD[(K, (T, InternalRow))] = {
    val rdd = if (sortBasedShuffleOn) {
      origin.mapPartitions {iter => iter.map(row => (row._1, (row._2._1, row._2._2.copy())))}
    } else {
      origin.mapPartitions {iter =>
        val mutablePair = new MutablePair[K, (T, InternalRow)]()
        iter.map(row => mutablePair.update(row._1, (row._2._1, row._2._2.copy())))
      }
    }

    val part = new RangeDPartitioner(range_bounds, ascending = true)
    new ShuffledRDD[K, (T, InternalRow), (T, InternalRow)](rdd, part)
  }
}

class RangeDPartitioner[K: Ordering: ClassTag](range_bounds: Array[K],
                                               ascending: Boolean) extends Partitioner {
  def numPartitions: Int = range_bounds.length + 1

  private val binarySearch: ((Array[K], K) => Int) = CollectionsUtils.makeBinarySearch[K]

  def getPartition(key: Any): Int = {
    val k = key.asInstanceOf[K]
    var partition = 0
    if (range_bounds.length < 128) {
      while (partition < range_bounds.length && Ordering[K].gt(k, range_bounds(partition)))
        partition += 1
    } else {
      partition = binarySearch(range_bounds, k)
      if (partition < 0) partition = -partition - 1
      if (partition > range_bounds.length) partition = range_bounds.length
    }
    if (ascending) partition
    else range_bounds.length - partition
  }
}