Github user marmbrus commented on a diff in the pull request:
https://github.com/apache/spark/pull/5208#discussion_r28198952
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoin.scala
---
@@ -0,0 +1,163 @@
+/*
+ * 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.rdd.RDD
+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],
+ left: SparkPlan,
+ right: SparkPlan) extends BinaryNode {
+
+ override def output: Seq[Attribute] = left.output ++ right.output
+
+ override def outputPartitioning: Partitioning = left.outputPartitioning
+
+ override def requiredChildDistribution: Seq[Distribution] =
+ ClusteredDistribution(leftKeys) :: ClusteredDistribution(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)
+
+ private def requiredOrders(keys: Seq[Expression], side: SparkPlan):
Seq[SortOrder] = keys.map {
+ k => SortOrder(BindReferences.bindReference(k, side.output,
allowFailures = false), Ascending)
+ }
+
+ override def outputOrdering: Seq[SortOrder] = requiredOrders(leftKeys,
left)
+
+ override def requiredInPartitionOrdering: Seq[Seq[SortOrder]] =
+ requiredOrders(leftKeys, left) :: requiredOrders(rightKeys, right) ::
Nil
+
+ @transient protected lazy val leftKeyGenerator = newProjection(leftKeys,
left.output)
+ @transient protected lazy val rightKeyGenerator =
newProjection(rightKeys, right.output)
+
+ override def execute(): RDD[Row] = {
+ 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 rightMatches: CompactBuffer[Row] = _
+ private[this] var rightPosition: Int = -1
+ private[this] var stop: Boolean = false
+ private[this] var matchKey: Row = _
+
+ override final def hasNext: Boolean = nextMatchingPair()
+
+ override final def next(): Row = {
+ if (hasNext) {
+ val joinedRow = joinRow(leftElement,
rightMatches(rightPosition))
+ rightPosition += 1
+ if (rightPosition >= rightMatches.size) {
+ rightPosition = 0
+ fetchLeft()
+ if (leftElement == null || ordering.compare(leftKey,
matchKey) != 0) {
+ stop = false
+ rightMatches = null
+ }
+ }
+ joinedRow
+ } else {
+ // according to Scala doc, this is undefined
+ null
+ }
+ }
+
+ private def fetchLeft() = {
+ if (leftIter.hasNext) {
+ leftElement = leftIter.next()
+ leftKey = leftKeyGenerator(leftElement)
+ } else {
+ leftElement = null
+ }
+ }
+
+ private def fetchRight() = {
+ if (rightIter.hasNext) {
+ rightElement = rightIter.next()
+ rightKey = rightKeyGenerator(rightElement)
+ } else {
+ rightElement = null
+ }
+ }
+
+ private def initialize() = {
+ fetchLeft()
+ fetchRight()
+ }
+ // initialize iterator
+ initialize()
--- End diff --
It might be better to put this up at the top, right after the `var`s.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
