[ https://issues.apache.org/jira/browse/SPARK-24879?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Xiao Li reassigned SPARK-24879: ------------------------------- Assignee: William Sheu > NPE in Hive partition filter pushdown for `partCol IN (NULL, ....)` > ------------------------------------------------------------------- > > Key: SPARK-24879 > URL: https://issues.apache.org/jira/browse/SPARK-24879 > Project: Spark > Issue Type: Bug > Components: SQL > Affects Versions: 2.3.0, 2.3.1 > Reporter: William Sheu > Assignee: William Sheu > Priority: Major > Fix For: 2.3.2, 2.4.0 > > > The following query triggers a NPE: > {code:java} > create table foo (col1 int) partitioned by (col2 int); > select * from foo where col2 in (1, NULL); > {code} > We try to push down the filter to Hive in order to do partition pruning, but > the filter converter breaks on a `null`. > Here's the stack: > {code:java} > java.lang.NullPointerException > at > org.apache.spark.sql.hive.client.Shim_v0_13$ExtractableLiteral$2$.unapply(HiveShim.scala:601) > at > org.apache.spark.sql.hive.client.Shim_v0_13$ExtractableLiterals$2$$anonfun$5.apply(HiveShim.scala:609) > at > org.apache.spark.sql.hive.client.Shim_v0_13$ExtractableLiterals$2$$anonfun$5.apply(HiveShim.scala:609) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234) > at > scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234) > at > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) > at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) > at scala.collection.TraversableLike$class.map(TraversableLike.scala:234) > at scala.collection.AbstractTraversable.map(Traversable.scala:104) > at > org.apache.spark.sql.hive.client.Shim_v0_13$ExtractableLiterals$2$.unapply(HiveShim.scala:609) > at > org.apache.spark.sql.hive.client.Shim_v0_13.org$apache$spark$sql$hive$client$Shim_v0_13$$convert$1(HiveShim.scala:671) > at > org.apache.spark.sql.hive.client.Shim_v0_13$$anonfun$convertFilters$1.apply(HiveShim.scala:704) > at > org.apache.spark.sql.hive.client.Shim_v0_13$$anonfun$convertFilters$1.apply(HiveShim.scala:704) > at > scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) > at > scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) > at scala.collection.immutable.List.foreach(List.scala:392) > at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:241) > at scala.collection.immutable.List.flatMap(List.scala:355) > at > org.apache.spark.sql.hive.client.Shim_v0_13.convertFilters(HiveShim.scala:704) > at > org.apache.spark.sql.hive.client.Shim_v0_13.getPartitionsByFilter(HiveShim.scala:725) > at > org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getPartitionsByFilter$1.apply(HiveClientImpl.scala:678) > at > org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$getPartitionsByFilter$1.apply(HiveClientImpl.scala:676) > at > org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:275) > at > org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:213) > at > org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:212) > at > org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:258) > at > org.apache.spark.sql.hive.client.HiveClientImpl.getPartitionsByFilter(HiveClientImpl.scala:676) > at > org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$listPartitionsByFilter$1.apply(HiveExternalCatalog.scala:1221) > at > org.apache.spark.sql.hive.HiveExternalCatalog$$anonfun$listPartitionsByFilter$1.apply(HiveExternalCatalog.scala:1214) > at > org.apache.spark.sql.hive.HiveExternalCatalog.withClient(HiveExternalCatalog.scala:97) > at > org.apache.spark.sql.hive.HiveExternalCatalog.listPartitionsByFilter(HiveExternalCatalog.scala:1214) > at > org.apache.spark.sql.catalyst.catalog.ExternalCatalogWithListener.listPartitionsByFilter(ExternalCatalogWithListener.scala:254) > at > org.apache.spark.sql.catalyst.catalog.SessionCatalog.listPartitionsByFilter(SessionCatalog.scala:955) > at > org.apache.spark.sql.hive.execution.HiveTableScanExec.rawPartitions$lzycompute(HiveTableScanExec.scala:172) > at > org.apache.spark.sql.hive.execution.HiveTableScanExec.rawPartitions(HiveTableScanExec.scala:164) > at > org.apache.spark.sql.hive.execution.HiveTableScanExec$$anonfun$11.apply(HiveTableScanExec.scala:190) > at > org.apache.spark.sql.hive.execution.HiveTableScanExec$$anonfun$11.apply(HiveTableScanExec.scala:190) > at org.apache.spark.util.Utils$.withDummyCallSite(Utils.scala:2418) > at > org.apache.spark.sql.hive.execution.HiveTableScanExec.doExecute(HiveTableScanExec.scala:189) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) > at > org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) > at > org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) > at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) > at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) > at > org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:247) > at > org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:294) > at > org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:324) > at > org.apache.spark.sql.execution.QueryExecution.hiveResultString(QueryExecution.scala:122) > at > org.apache.spark.sql.hive.thriftserver.SparkSQLDriver$$anonfun$run$1.apply(SparkSQLDriver.scala:64) > at > org.apache.spark.sql.hive.thriftserver.SparkSQLDriver$$anonfun$run$1.apply(SparkSQLDriver.scala:64) > at > org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78) > at > org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125) > at > org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73) > at > org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:63) > at > org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:363) > at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376) > at > org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:272) > at > org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:498) > at > org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52) > at > org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:846) > at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:167) > at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:194) > at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86) > at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:921) > at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:932) > at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala) > {code} -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org