viirya commented on code in PR #581:
URL: https://github.com/apache/datafusion-comet/pull/581#discussion_r1645054647
##########
spark/src/main/spark-3.x/org/apache/spark/sql/comet/shims/ShimCometScanExec.scala:
##########
@@ -21,51 +21,35 @@ package org.apache.spark.sql.comet.shims
import org.apache.comet.shims.ShimFileFormat
-import scala.language.implicitConversions
-
import org.apache.hadoop.fs.{FileStatus, Path}
-import org.apache.spark.{SparkContext, SparkException}
+import org.apache.spark.SparkException
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.AttributeReference
-import org.apache.spark.sql.connector.read.{InputPartition,
PartitionReaderFactory}
+import org.apache.spark.sql.execution.datasources.parquet.ParquetOptions
import org.apache.spark.sql.execution.{FileSourceScanExec, PartitionedFileUtil}
import org.apache.spark.sql.execution.datasources.{FilePartition, FileScanRDD,
HadoopFsRelation, PartitionDirectory, PartitionedFile}
-import org.apache.spark.sql.execution.datasources.parquet.ParquetOptions
-import org.apache.spark.sql.execution.datasources.v2.DataSourceRDD
-import org.apache.spark.sql.execution.metric.SQLMetric
import org.apache.spark.sql.types.{LongType, StructField, StructType}
trait ShimCometScanExec {
def wrapped: FileSourceScanExec
- // TODO: remove after dropping Spark 3.2 support and directly call
wrapped.metadataColumns
+ // TODO: remove after dropping Spark 3.3 support
lazy val metadataColumns: Seq[AttributeReference] =
wrapped.getClass.getDeclaredMethods
.filter(_.getName == "metadataColumns")
.map { a => a.setAccessible(true); a }
.flatMap(_.invoke(wrapped).asInstanceOf[Seq[AttributeReference]])
- // TODO: remove after dropping Spark 3.2 and 3.3 support and directly call
+ // TODO: remove after dropping Spark 3.3 support and directly call
// wrapped.fileConstantMetadataColumns
lazy val fileConstantMetadataColumns: Seq[AttributeReference] =
wrapped.getClass.getDeclaredMethods
.filter(_.getName == "fileConstantMetadataColumns")
.map { a => a.setAccessible(true); a }
.flatMap(_.invoke(wrapped).asInstanceOf[Seq[AttributeReference]])
- // TODO: remove after dropping Spark 3.2 support and directly call new
DataSourceRDD
- protected def newDataSourceRDD(
- sc: SparkContext,
- inputPartitions: Seq[Seq[InputPartition]],
- partitionReaderFactory: PartitionReaderFactory,
- columnarReads: Boolean,
- customMetrics: Map[String, SQLMetric]): DataSourceRDD = {
- implicit def flattenSeq(p: Seq[Seq[InputPartition]]): Seq[InputPartition]
= p.flatten
- new DataSourceRDD(sc, inputPartitions, partitionReaderFactory,
columnarReads, customMetrics)
- }
-
- // TODO: remove after dropping Spark 3.2 support and directly call new
FileScanRDD
+ // TODO: remove after dropping Spark 3.4 support and directly call new
FileScanRDD
Review Comment:
How about 3.3? Is it also different to Spark 3.4?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
