[SPARK-16748] Errors thrown by UDFs cause TreeNodeException when the query has an ORDER BY clause

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 2.0.1, 2.1.0
• Component/s: SQL
• Assignee: Tathagata Das
• Reporter: Yin Huai
• Created: 27/Jul/16 05:19
• Updated: 30/Jul/16 03:00
• Resolved: 30/Jul/16 03:00

Description

import org.apache.spark.sql.functions._
val myUDF = udf((c: String) => s"""${c.take(5)}""")
spark.sql("SELECT cast(null as string) as a").select(myUDF($"a").as("b")).orderBy($"b").collect

org.apache.spark.sql.catalyst.errors.package$TreeNodeException: execute, tree:
Exchange rangepartitioning(b#345 ASC, 200)
+- *Project [UDF(null) AS b#345]
   +- Scan OneRowRelation[]

	at org.apache.spark.sql.catalyst.errors.package$.attachTree(package.scala:50)
	at org.apache.spark.sql.execution.exchange.ShuffleExchange.doExecute(ShuffleExchange.scala:113)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
	at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
	at org.apache.spark.sql.execution.InputAdapter.inputRDDs(WholeStageCodegenExec.scala:233)
	at org.apache.spark.sql.execution.SortExec.inputRDDs(SortExec.scala:113)
	at org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:361)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:115)
	at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:136)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:133)
	at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:114)
	at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:225)
	at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:272)
	at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2183)
	at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
	at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2532)
	at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2182)
	at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$collect$1.apply(Dataset.scala:2187)
	at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$collect$1.apply(Dataset.scala:2187)
	at org.apache.spark.sql.Dataset.withCallback(Dataset.scala:2545)
	at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2187)
	at org.apache.spark.sql.Dataset.collect(Dataset.scala:2163)

Issue Links

• links to: [Github] Pull Request #14395 (tdas)