[jira] [Assigned] (SPARK-24879) NPE in Hive partition filter pushdown for `partCol IN (NULL, ....)`
[ 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 >
[jira] [Assigned] (SPARK-24879) NPE in Hive partition filter pushdown for `partCol IN (NULL, ....)`
[ https://issues.apache.org/jira/browse/SPARK-24879?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Apache Spark reassigned SPARK-24879: Assignee: (was: Apache Spark) > 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 >Priority: Major > > 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$$anonfun$execute$1.apply(SparkPlan.scala:131) >
[jira] [Assigned] (SPARK-24879) NPE in Hive partition filter pushdown for `partCol IN (NULL, ....)`
[ https://issues.apache.org/jira/browse/SPARK-24879?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Apache Spark reassigned SPARK-24879: Assignee: Apache Spark > NPE in Hive partition filter pushdown for `partCol IN (NULL, )` > --- > > Key: SPARK-24879 > URL: https://issues.apache.org/jira/browse/SPARK-24879 > Project: Spark > Issue Type: Bug > Components: SQL >Affects Versions: 2.3.0, 2.3.1 >Reporter: William Sheu >Assignee: Apache Spark >Priority: Major > > The following query triggers a NPE: > {code:java} > create table foo (col1 int) partitioned by (col2 int); > select * from foo where col2 in (1, NULL); > {code} > We try to push down the filter to Hive in order to do partition pruning, but > the filter converter breaks on a `null`. > Here's the stack: > {code:java} > java.lang.NullPointerException > at > org.apache.spark.sql.hive.client.Shim_v0_13$ExtractableLiteral$2$.unapply(HiveShim.scala:601) > at > org.apache.spark.sql.hive.client.Shim_v0_13$ExtractableLiterals$2$$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 >