spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From adrian-wang <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-2213] [SQL] sort merge join for spark s...
Date Fri, 10 Apr 2015 17:45:41 GMT
Github user adrian-wang commented on a diff in the pull request:

    https://github.com/apache/spark/pull/5208#discussion_r28165155
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoin.scala
---
    @@ -0,0 +1,164 @@
    +/*
    + * Licensed to the Apache Software Foundation (ASF) under one or more
    + * contributor license agreements.  See the NOTICE file distributed with
    + * this work for additional information regarding copyright ownership.
    + * The ASF licenses this file to You under the Apache License, Version 2.0
    + * (the "License"); you may not use this file except in compliance with
    + * the License.  You may obtain a copy of the License at
    + *
    + *    http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +
    +package org.apache.spark.sql.execution.joins
    +
    +import org.apache.spark.annotation.DeveloperApi
    +import org.apache.spark.sql.Row
    +import org.apache.spark.sql.catalyst.expressions._
    +import org.apache.spark.sql.catalyst.plans._
    +import org.apache.spark.sql.catalyst.plans.physical._
    +import org.apache.spark.sql.execution.{BinaryNode, SparkPlan}
    +import org.apache.spark.util.collection.CompactBuffer
    +
    +/**
    + * :: DeveloperApi ::
    + * Performs an sort merge join of two child relations.
    + */
    +@DeveloperApi
    +case class SortMergeJoin(
    +    leftKeys: Seq[Expression],
    +    rightKeys: Seq[Expression],
    +    joinType: JoinType,
    +    left: SparkPlan,
    +    right: SparkPlan) extends BinaryNode {
    +
    +  override def output: Seq[Attribute] = left.output ++ right.output
    +
    +  override def outputPartitioning: Partitioning = HashSortedPartitioning(leftKeys, 0)
    +
    +  override def requiredChildDistribution: Seq[Distribution] =
    +    ClusteredOrderedDistribution(leftKeys) :: ClusteredOrderedDistribution(rightKeys)
:: Nil
    +
    +  private val orders: Seq[SortOrder] = leftKeys.zipWithIndex.map {
    +    case(expr, index) => SortOrder(BoundReference(index, expr.dataType, expr.nullable),
Ascending)
    +  }
    +  private val ordering: RowOrdering = new RowOrdering(orders, left.output)
    +
    +  @transient protected lazy val leftKeyGenerator = newProjection(leftKeys, left.output)
    +  @transient protected lazy val rightKeyGenerator = newProjection(rightKeys, right.output)
    +
    +  override def execute() = {
    +    val leftResults = left.execute().map(_.copy())
    +    val rightResults = right.execute().map(_.copy())
    +
    +    leftResults.zipPartitions(rightResults) { (leftIter, rightIter) =>
    +      new Iterator[Row] {
    +        // Mutable per row objects.
    +        private[this] val joinRow = new JoinedRow5
    +        private[this] var leftElement: Row = _
    +        private[this] var rightElement: Row = _
    +        private[this] var leftKey: Row = _
    +        private[this] var rightKey: Row = _
    +        private[this] var leftMatches: CompactBuffer[Row] = _
    +        private[this] var rightMatches: CompactBuffer[Row] = _
    +        private[this] var leftPosition: Int = -1
    +        private[this] var rightPosition: Int = -1
    +
    +        override final def hasNext: Boolean = leftPosition != -1 || nextMatchingPair
    +
    +        override final def next(): Row = {
    +          if (hasNext) {
    +            val joinedRow = joinRow(leftMatches(leftPosition), rightMatches(rightPosition))
    +            rightPosition += 1
    +            if (rightPosition >= rightMatches.size) {
    +              leftPosition += 1
    +              rightPosition = 0
    +              if (leftPosition >= leftMatches.size) {
    +                leftPosition = -1
    +              }
    +            }
    +            joinedRow
    +          } else {
    +            // according to Scala doc, this is undefined
    +            null
    --- End diff --
    
    Throw an exception would change the return type of `def next()` and differ this function
from parent.


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message