Github user hvanhovell commented on a diff in the pull request: https://github.com/apache/spark/pull/14241#discussion_r72427356 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala --- @@ -275,62 +271,152 @@ private[sql] case class RowDataSourceScanExec( |} """.stripMargin } + + // Ignore rdd when checking results + override def sameResult(plan: SparkPlan): Boolean = plan match { + case other: RowDataSourceScanExec => relation == other.relation && metadata == other.metadata + case _ => false + } } -/** Physical plan node for scanning data from a batched relation. */ -private[sql] case class BatchedDataSourceScanExec( +/** Physical plan node for scanning data from files. */ +private[sql] case class FileSourceScanExec( + @transient relation: HadoopFsRelation, output: Seq[Attribute], - rdd: RDD[InternalRow], - @transient relation: BaseRelation, - override val outputPartitioning: Partitioning, - override val metadata: Map[String, String], + outputSchema: StructType, + partitionFilters: Seq[Expression], + dataFilters: Seq[Filter], override val metastoreTableIdentifier: Option[TableIdentifier]) - extends DataSourceScanExec with CodegenSupport { + extends DataSourceScanExec { + + val supportsBatch = relation.fileFormat.supportBatch( + relation.sparkSession, StructType.fromAttributes(output)) + + val needsUnsafeRowConversion = if (relation.fileFormat.isInstanceOf[ParquetSource]) { + SparkSession.getActiveSession.get.sessionState.conf.parquetVectorizedReaderEnabled + } else { + false + } + + override val outputPartitioning = { + val bucketSpec = if (relation.sparkSession.sessionState.conf.bucketingEnabled) { + relation.bucketSpec + } else { + None + } + bucketSpec.map { spec => + val numBuckets = spec.numBuckets + val bucketColumns = spec.bucketColumnNames.flatMap { n => + output.find(_.name == n) + } + if (bucketColumns.size == spec.bucketColumnNames.size) { + HashPartitioning(bucketColumns, numBuckets) + } else { + UnknownPartitioning(0) + } + }.getOrElse { + UnknownPartitioning(0) + } + } + + override val metadata: Map[String, String] = Map( + "Format" -> relation.fileFormat.toString, + "ReadSchema" -> outputSchema.simpleString, + DataSourceScanExec.PUSHED_FILTERS -> dataFilters.mkString("[", ", ", "]"), + DataSourceScanExec.INPUT_PATHS -> relation.location.paths.mkString(", ")) + + private def buildScan(): RDD[InternalRow] = { + val selectedPartitions = relation.location.listFiles(partitionFilters) + + val readFile: (PartitionedFile) => Iterator[InternalRow] = + relation.fileFormat.buildReaderWithPartitionValues( + sparkSession = relation.sparkSession, + dataSchema = relation.dataSchema, + partitionSchema = relation.partitionSchema, + requiredSchema = outputSchema, + filters = dataFilters, + options = relation.options, + hadoopConf = relation.sparkSession.sessionState.newHadoopConfWithOptions(relation.options)) + + relation.bucketSpec match { + case Some(bucketing) if relation.sparkSession.sessionState.conf.bucketingEnabled => + createBucketedReadRDD(bucketing, readFile, selectedPartitions, relation) + case _ => + createNonBucketedReadRDD(readFile, selectedPartitions, relation) + } + } + + override def inputRDDs(): Seq[RDD[InternalRow]] = { + buildScan() :: Nil + } private[sql] override lazy val metrics = Map("numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number of output rows"), "scanTime" -> SQLMetrics.createTimingMetric(sparkContext, "scan time")) protected override def doExecute(): RDD[InternalRow] = { - // in the case of fallback, this batched scan should never fail because of: - // 1) only primitive types are supported - // 2) the number of columns should be smaller than spark.sql.codegen.maxFields - WholeStageCodegenExec(this).execute() + if (supportsBatch) { + // in the case of fallback, this batched scan should never fail because of: + // 1) only primitive types are supported + // 2) the number of columns should be smaller than spark.sql.codegen.maxFields + WholeStageCodegenExec(this).execute() + } else { + val unsafeRows = { --- End diff -- Is there are reasons why you have not moved this into the parent class?
--- 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