viirya commented on code in PR #100:
URL:
https://github.com/apache/arrow-datafusion-comet/pull/100#discussion_r1505528298
##########
spark/src/main/scala/org/apache/spark/sql/comet/CometExecUtils.scala:
##########
@@ -21,15 +21,40 @@ package org.apache.spark.sql.comet
import scala.collection.JavaConverters.asJavaIterableConverter
+import org.apache.spark.{Partition, SparkContext, TaskContext}
+import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.expressions.{Attribute, NamedExpression,
SortOrder}
import org.apache.spark.sql.execution.SparkPlan
+import org.apache.spark.sql.vectorized.ColumnarBatch
import org.apache.comet.serde.OperatorOuterClass
import org.apache.comet.serde.OperatorOuterClass.Operator
import org.apache.comet.serde.QueryPlanSerde.{exprToProto, serializeDataType}
object CometExecUtils {
+ /**
+ * Create an empty ColumnarBatch RDD with a single partition.
+ */
+ def createEmptyColumnarRDDWithSinglePartition(
+ sparkContext: SparkContext): RDD[ColumnarBatch] = {
+ new EmptyRDDWithPartitions(sparkContext, 1)
+ }
+
+ /**
+ * Transform the given RDD into a new RDD that takes the first `limit`
elements of each
+ * partition. The limit operation is performed on the native side.
+ */
+ def toNativeLimitedPerPartition(
Review Comment:
The method name is not good to me.
Maybe simply `getNativeLimitRDD`.
--
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]
