Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/18747#discussion_r145139806 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryTableScanExec.scala --- @@ -23,21 +23,58 @@ import org.apache.spark.sql.catalyst.dsl.expressions._ import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.plans.QueryPlan import org.apache.spark.sql.catalyst.plans.physical.{HashPartitioning, Partitioning} -import org.apache.spark.sql.execution.LeafExecNode -import org.apache.spark.sql.execution.metric.SQLMetrics -import org.apache.spark.sql.types.UserDefinedType +import org.apache.spark.sql.execution.{ColumnarBatchScan, LeafExecNode} +import org.apache.spark.sql.execution.vectorized._ +import org.apache.spark.sql.types.{StructType, UserDefinedType} case class InMemoryTableScanExec( attributes: Seq[Attribute], predicates: Seq[Expression], @transient relation: InMemoryRelation) - extends LeafExecNode { + extends LeafExecNode with ColumnarBatchScan { override protected def innerChildren: Seq[QueryPlan[_]] = Seq(relation) ++ super.innerChildren - override lazy val metrics = Map( - "numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number of output rows")) + override def vectorTypes: Option[Seq[String]] = + Option(Seq.fill(attributes.length)(classOf[OnHeapColumnVector].getName)) + + override val supportCodegen: Boolean = relation.useColumnarBatches + + private val columnIndices = + attributes.map(a => relation.output.map(o => o.exprId).indexOf(a.exprId)).toArray + + private val relationSchema = relation.schema.toArray + + private lazy val columnarBatchSchema = new StructType(columnIndices.map(i => relationSchema(i))) + + private def createAndDecompressColumn(cachedColumnarBatch: CachedBatch): ColumnarBatch = { + val rowCount = cachedColumnarBatch.numRows + val columnVectors = OnHeapColumnVector.allocateColumns(rowCount, columnarBatchSchema) + val columnarBatch = new ColumnarBatch( + columnarBatchSchema, columnVectors.asInstanceOf[Array[ColumnVector]], rowCount) + columnarBatch.setNumRows(rowCount) + + for (i <- 0 until attributes.length) { + val index = if (columnIndices.length == 0) i else columnIndices(i) + ColumnAccessor.decompress( + cachedColumnarBatch.buffers(index), + columnarBatch.column(i).asInstanceOf[WritableColumnVector], + columnarBatchSchema.fields(i).dataType, rowCount) + } + return columnarBatch --- End diff -- nit: remove `return`
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org