cfmcgrady commented on code in PR #4662:
URL: https://github.com/apache/kyuubi/pull/4662#discussion_r1160102923
##########
externals/kyuubi-spark-sql-engine/src/main/scala/org/apache/spark/sql/kyuubi/SparkDatasetHelper.scala:
##########
@@ -17,18 +17,68 @@
package org.apache.spark.sql.kyuubi
+import scala.collection.mutable.ArrayBuffer
+
+import org.apache.spark.TaskContext
+import org.apache.spark.network.util.{ByteUnit, JavaUtils}
import org.apache.spark.rdd.RDD
-import org.apache.spark.sql.{DataFrame, Dataset, Row}
+import org.apache.spark.sql.{DataFrame, Dataset, Row, SparkSession}
+import org.apache.spark.sql.execution.{CollectLimitExec, SparkPlan,
SQLExecution}
+import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec
+import org.apache.spark.sql.execution.arrow.{ArrowConverters,
KyuubiArrowConverters}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._
+import org.apache.kyuubi.engine.spark.KyuubiSparkUtil
import org.apache.kyuubi.engine.spark.schema.RowSet
+import org.apache.kyuubi.reflection.DynMethods
object SparkDatasetHelper {
+
+ def executeCollect(df: DataFrame): Array[Array[Byte]] =
withNewExecutionId(df) {
+ executeArrowBatchCollect(df.queryExecution.executedPlan)
+ }
+
+ def executeArrowBatchCollect: SparkPlan => Array[Array[Byte]] = {
+ case adaptiveSparkPlan: AdaptiveSparkPlanExec =>
+ executeArrowBatchCollect(finalPhysicalPlan(adaptiveSparkPlan))
+ case collectLimit: CollectLimitExec =>
Review Comment:
updated, the `offset > 0` support will be added in the separate PR.
--
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]
