[ 
https://issues.apache.org/jira/browse/SPARK-19509?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Herman van Hovell updated SPARK-19509:
--------------------------------------
    Summary: GROUPING SETS throws NullPointerException when use an empty column 
 (was: [SQL]GROUPING SETS throws NullPointerException when use an empty column)

> GROUPING SETS throws NullPointerException when use an empty column
> ------------------------------------------------------------------
>
>                 Key: SPARK-19509
>                 URL: https://issues.apache.org/jira/browse/SPARK-19509
>             Project: Spark
>          Issue Type: Bug
>          Components: SQL
>    Affects Versions: 2.1.0
>            Reporter: StanZhai
>
> {code:sql|title=A simple case}
> select count(1) from test group by e grouping sets(e)
> {code}
> {code:title=Schema of the test table}
> scala> spark.sql("desc test").show()
> +--------+---------+-------+
> |col_name|data_type|comment|
> +--------+---------+-------+
> |       e|   string|   null|
> +--------+---------+-------+
> {code}
> {code:sql|title=The column `e` is empty}
> scala> spark.sql("select e from test").show()
> +----+
> |   e|
> +----+
> |null|
> |null|
> +----+
> {code}
> {code:title=Exception}
> Driver stacktrace:
>   at 
> org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
>   at 
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
>   at 
> org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
>   at 
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
>   at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
>   at 
> org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
>   at 
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
>   at 
> org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
>   at scala.Option.foreach(Option.scala:257)
>   at 
> org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
>   at 
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
>   at 
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
>   at 
> org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
>   at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
>   at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
>   at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
>   at org.apache.spark.SparkContext.runJob(SparkContext.scala:1931)
>   at org.apache.spark.SparkContext.runJob(SparkContext.scala:1944)
>   at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:333)
>   at 
> org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
>   at 
> org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2371)
>   at 
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
>   at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2765)
>   at 
> org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2370)
>   at 
> org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2377)
>   at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2113)
>   at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2112)
>   at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2795)
>   at org.apache.spark.sql.Dataset.head(Dataset.scala:2112)
>   at org.apache.spark.sql.Dataset.take(Dataset.scala:2327)
>   at org.apache.spark.sql.Dataset.showString(Dataset.scala:248)
>   at org.apache.spark.sql.Dataset.show(Dataset.scala:636)
>   at org.apache.spark.sql.Dataset.show(Dataset.scala:595)
>   at org.apache.spark.sql.Dataset.show(Dataset.scala:604)
>   ... 48 elided
> Caused by: java.lang.NullPointerException
>   at 
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown
>  Source)
>   at 
> org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown
>  Source)
>   at 
> org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
>   at 
> org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
>   at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
>   at 
> org.apache.spark.shuffle.sort.BypassMergeSortShuffleWriter.write(BypassMergeSortShuffleWriter.java:126)
>   at 
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
>   at 
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
>   at org.apache.spark.scheduler.Task.run(Task.scala:99)
>   at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
>   at 
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
>   at 
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
>   at java.lang.Thread.run(Thread.java:745)
> {code}



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org

Reply via email to