trait HashJoin {val leftKeys: Seq[Expression]val rightKeys: Seq[Expression]val buildSide: BuildSideval left: SparkPlanval right: SparkPlanlazy val (buildPlan, streamedPlan) = buildSide match {  //模式匹配，将physical plan封装形成Tuple2，假设是buildLeft。那么就是(left,right)，否则是(right,left)case BuildLeft => (left, right)case BuildRight => (right, left)}lazy val (buildKeys, streamedKeys) = buildSide match { //模式匹配，将expression进行封装<span style="font-family: Arial, Helvetica, sans-serif;">Tuple2</span>case BuildLeft => (leftKeys, rightKeys)case BuildRight => (rightKeys, leftKeys)}def output = left.output ++ right.output@transient lazy val buildSideKeyGenerator = new Projection(buildKeys, buildPlan.output) //生成buildSideKey来依据Expression来计算Row返回结果@transient lazy val streamSideKeyGenerator = //<span style="font-family: Arial, Helvetica, sans-serif;">生成</span><span style="font-family: Arial, Helvetica, sans-serif;">streamSideKeyGenerator</span><span style="font-family: Arial, Helvetica, sans-serif;">来依据Expression来计算Row返回结果</span>() => new MutableProjection(streamedKeys, streamedPlan.output)def joinIterators(buildIter: Iterator[Row], streamIter: Iterator[Row]): Iterator[Row] = { //把build表的Iterator[Row]和streamIterator[Row]进行join操作返回Join后的Iterator[Row]// TODO: Use Spark's HashMap implementation.val hashTable = new java.util.HashMap[Row, ArrayBuffer[Row]]() //匹配主要使用HashMap实现var currentRow: Row = null// Create a mapping of buildKeys -> rows while (buildIter.hasNext) { //眼下仅仅对build Iterator进行迭代，形成rowKey，Rows，相似wordCount，可是这里不是累加Value，而是Row的集合。

currentRow = buildIter.next() val rowKey = buildSideKeyGenerator(currentRow) //计算rowKey作为HashMap的key if(!rowKey.anyNull) { val existingMatchList = hashTable.get(rowKey) val matchList = if (existingMatchList == null) { val newMatchList = new ArrayBuffer[Row]() hashTable.put(rowKey, newMatchList) //(rowKey, matchedRowList) newMatchList } else { existingMatchList } matchList += currentRow.copy() //返回matchList } } new Iterator[Row] { //最后用streamedRow的Key来匹配buildSide端的HashMap private[this] var currentStreamedRow: Row = _ private[this] var currentHashMatches: ArrayBuffer[Row] = _ private[this] var currentMatchPosition: Int = -1 // Mutable per row objects. private[this] val joinRow = new JoinedRow private[this] val joinKeys = streamSideKeyGenerator() override final def hasNext: Boolean = (currentMatchPosition != -1 && currentMatchPosition < currentHashMatches.size) || (streamIter.hasNext && fetchNext()) override final def next() = { val ret = buildSide match { case BuildRight => joinRow(currentStreamedRow, currentHashMatches(currentMatchPosition)) //右连接的话，streamedRow放左边。匹配到的key的Row放到右表 case BuildLeft => joinRow(currentHashMatches(currentMatchPosition), currentStreamedRow) //左连接的话，相反。

} currentMatchPosition += 1 ret } /** * Searches the streamed iterator for the next row that has at least one match in hashtable. * * @return true if the search is successful, and false if the streamed iterator runs out of * tuples. */ private final def fetchNext(): Boolean = { currentHashMatches = null currentMatchPosition = -1 while (currentHashMatches == null && streamIter.hasNext) { currentStreamedRow = streamIter.next() if (!joinKeys(currentStreamedRow).anyNull) { currentHashMatches = hashTable.get(joinKeys.currentValue) //streamedRow从buildSide里的HashTable里面匹配rowKey } } if (currentHashMatches == null) { false } else { currentMatchPosition = 0 true } } } } }

class JoinedRow extends Row {private[this] var row1: Row = _private[this] var row2: Row = _.........def copy() = {val totalSize = row1.size + row2.size val copiedValues = new Array[Any](totalSize)var i = 0while(i < totalSize) {copiedValues(i) = apply(i)i += 1}new GenericRow(copiedValues) //返回一个新的合并后的Row}

case class LeftSemiJoinHash(leftKeys: Seq[Expression],rightKeys: Seq[Expression],left: SparkPlan,right: SparkPlan) extends BinaryNode with HashJoin {val buildSide = BuildRight //buildSide是以右表为基准override def requiredChildDistribution =ClusteredDistribution(leftKeys) :: ClusteredDistribution(rightKeys) :: Niloverride def output = left.outputdef execute() = {buildPlan.execute().zipPartitions(streamedPlan.execute()) { (buildIter, streamIter) => //右表的物理计划运行后生成RDD，利用zipPartitions对Partition进行合并。然后用上述方法实现。val hashSet = new java.util.HashSet[Row]()var currentRow: Row = null// Create a Hash set of buildKeyswhile (buildIter.hasNext) {currentRow = buildIter.next()val rowKey = buildSideKeyGenerator(currentRow)if(!rowKey.anyNull) {val keyExists = hashSet.contains(rowKey)if (!keyExists) {hashSet.add(rowKey)}}}val joinKeys = streamSideKeyGenerator()streamIter.filter(current => {!joinKeys(current).anyNull && hashSet.contains(joinKeys.currentValue)})}}
}

2.2、BroadcastHashJoin

case class BroadcastHashJoin(leftKeys: Seq[Expression],rightKeys: Seq[Expression],buildSide: BuildSide,left: SparkPlan,right: SparkPlan)(@transient sqlContext: SQLContext) extends BinaryNode with HashJoin {override def otherCopyArgs = sqlContext :: Niloverride def outputPartitioning: Partitioning = left.outputPartitioningoverride def requiredChildDistribution =UnspecifiedDistribution :: UnspecifiedDistribution :: Nil@transientlazy val broadcastFuture = future {  //利用SparkContext广播表sqlContext.sparkContext.broadcast(buildPlan.executeCollect())}def execute() = {val broadcastRelation = Await.result(broadcastFuture, 5.minute)streamedPlan.execute().mapPartitions { streamedIter =>joinIterators(broadcastRelation.value.iterator, streamedIter) //调用joinIterators对每一个分区map}}
}

2.3、ShuffleHashJoin

然后利用SparkContext里的zipPartitions方法对每一个分区进行zip。

case class ShuffledHashJoin(leftKeys: Seq[Expression],rightKeys: Seq[Expression],buildSide: BuildSide,left: SparkPlan,right: SparkPlan) extends BinaryNode with HashJoin {override def outputPartitioning: Partitioning = left.outputPartitioningoverride def requiredChildDistribution =ClusteredDistribution(leftKeys) :: ClusteredDistribution(rightKeys) :: Nildef execute() = {buildPlan.execute().zipPartitions(streamedPlan.execute()) {(buildIter, streamIter) => joinIterators(buildIter, streamIter)}}
}