Apache spark 带Spark 3.0.0的ArrayIndexOutOfBoundsException读取ORC蜂箱表_Apache Spark_Hive_Apache Spark Sql_Orc

Apache spark 带Spark 3.0.0的ArrayIndexOutOfBoundsException读取ORC蜂箱表

apache-spark hive

Apache spark 带Spark 3.0.0的ArrayIndexOutOfBoundsException读取ORC蜂箱表,apache-spark,hive,apache-spark-sql,orc,Apache Spark,Hive,Apache Spark Sql,Orc,我正在尝试阅读Spark 3.0.0中的ORC Hive表，我在同一集群中阅读了Spark 1.6，没有任何问题。我正在使用hive1.2，并已从ApacheSpark发行版存档下载了spark-3.0.0-bin-hadoop2.7-hive1.2.tgz。查询是： val free_unit = sql("SELECT * from cdrs.pro_free_unit where ((aniomes= 202003 or month = 202004)) and sub_id

我正在尝试阅读Spark 3.0.0中的ORC Hive表，我在同一集群中阅读了Spark 1.6，没有任何问题。我正在使用hive1.2，并已从ApacheSpark发行版存档下载了spark-3.0.0-bin-hadoop2.7-hive1.2.tgz。查询是：

val free_unit = sql("SELECT * from cdrs.pro_free_unit where ((aniomes= 202003 or month = 202004)) and sub_id=100000000003637081 and free_unit_type_id=5052")
free_unit.select((Array("init_balance", "brandid","dia") ++ free_unit.columns.filter(_.startsWith("free_uni"))).map(free_unit(_)) : _*).show(50,false)

错误是：

20/09/10 16:28:07 WARN impl.SchemaEvolution: Column names are missing from this file. This is caused by a writer earlier than HIVE-4243. The reader will reconcile schemas based on index. File type: struct<_col0:bigint,_col1:bigint,_col2:varchar(1),_col3:varchar(1),_col4:varchar(1),_col5:timestamp,_col6:timestamp,_col7:varchar(4),_col8:varchar(64),_col9:varchar(4),_col10:varchar(64),_col11:varchar(128),_col12:varchar(32),_col13:bigint,_col14:varchar(1),_col15:bigint,_col16:varchar(64),_col17:varchar(64),_col18:varchar(4000),_col19:varchar(1),_col20:bigint,_col21:bigint,_col22:bigint,_col23:varchar(1),_col24:bigint,_col25:timestamp,_col26:timestamp,_col27:bigint,_col28:bigint,_col29:varchar(128),_col30:varchar(32),_col31:varchar(64),_col32:varchar(1),_col33:varchar(1),_col34:varchar(1),_col35:bigint,_col36:varchar(1),_col37:bigint,_col38:varchar(1),_col39:timestamp,_col40:timestamp,_col41:varchar(1),_col42:timestamp,_col43:varchar(1),_col44:bigint,_col45:int,_col46:varchar(45)>, reader type: struct<sub_id:bigint,free_unit_id:bigint,free_unit_owner_type:string,free_unit_type_id:bigint,free_unit_type_name:string,free_unit_type_code:string,init_balance:bigint,brandid:bigint,aniomes:string,dia:string>


Driver stacktrace:
  at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2023)
  at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:1972)
  at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:1971)
  at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
  at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
  at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
  at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1971)
  at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:950)
  at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:950)
  at scala.Option.foreach(Option.scala:407)
  at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:950)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2203)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2152)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2141)
  at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
  at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:752)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2093)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2114)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2133)
  at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:467)
  at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:420)
  at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:47)
  at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3625)
  at org.apache.spark.sql.Dataset.$anonfun$head$1(Dataset.scala:2695)
  at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3616)
  at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:100)
  at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:160)
  at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:87)
  at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:763)
  at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
  at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3614)
  at org.apache.spark.sql.Dataset.head(Dataset.scala:2695)
  at org.apache.spark.sql.Dataset.take(Dataset.scala:2902)
  at org.apache.spark.sql.Dataset.getRows(Dataset.scala:300)
  at org.apache.spark.sql.Dataset.showString(Dataset.scala:337)
  at org.apache.spark.sql.Dataset.show(Dataset.scala:826)
  ... 47 elided
Caused by: java.lang.ArrayIndexOutOfBoundsException: 13
  at org.apache.spark.sql.execution.datasources.orc.OrcColumnarBatchReader.initBatch(OrcColumnarBatchReader.java:183)
  at org.apache.spark.sql.execution.datasources.orc.OrcFileFormat.$anonfun$buildReaderWithPartitionValues$2(OrcFileFormat.scala:216)
  at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:116)
  at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:169)
  at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
  at org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:490)
  at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown Source)
  at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
  at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
  at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:729)
  at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:340)
  at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:872)
  at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:872)
  at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
  at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:349)
  at org.apache.spark.rdd.RDD.iterator(RDD.scala:313)
  at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
  at org.apache.spark.scheduler.Task.run(Task.scala:127)
  at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:444)
  at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1377)
  at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:447)
  at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
  at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
  at java.lang.Thread.run(Thread.java:745)

20/09/10 16:28:07警告impl.SchemaEvolution:此文件中缺少列名。这是由早于HIVE-4243的编写器造成的。读取器将根据索引协调模式。文件类型：struct，读取器类型：struct
驱动程序堆栈跟踪：
位于org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages（DAGScheduler.scala:2023）
位于org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2（DAGScheduler.scala:1972）
位于org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted（DAGScheduler.scala:1971）
位于scala.collection.mutable.resizeblearray.foreach（resizeblearray.scala:62）
位于scala.collection.mutable.resizeblearray.foreach$（resizeblearray.scala:55）
位于scala.collection.mutable.ArrayBuffer.foreach（ArrayBuffer.scala:49）
位于org.apache.spark.scheduler.DAGScheduler.abortStage（DAGScheduler.scala:1971）
位于org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1（DAGScheduler.scala:950）
位于org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted（DAGScheduler.scala:950）
位于scala.Option.foreach（Option.scala:407）
位于org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed（DAGScheduler.scala:950）
位于org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive（DAGScheduler.scala:2203）
位于org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive（DAGScheduler.scala:2152）
位于org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive（DAGScheduler.scala:2141）
位于org.apache.spark.util.EventLoop$$anon$1.run（EventLoop.scala:49）
位于org.apache.spark.scheduler.DAGScheduler.runJob（DAGScheduler.scala:752）
位于org.apache.spark.SparkContext.runJob（SparkContext.scala:2093）
位于org.apache.spark.SparkContext.runJob（SparkContext.scala:2114）
位于org.apache.spark.SparkContext.runJob（SparkContext.scala:2133）
位于org.apache.spark.sql.execution.SparkPlan.executeTake（SparkPlan.scala:467）
位于org.apache.spark.sql.execution.SparkPlan.executeTake（SparkPlan.scala:420）
位于org.apache.spark.sql.execution.CollectLimitExec.executeCollect（limit.scala:47）
位于org.apache.spark.sql.Dataset.collectFromPlan（Dataset.scala:3625）
位于org.apache.spark.sql.Dataset.$anonfun$head$1（Dataset.scala:2695）
位于org.apache.spark.sql.Dataset.$anonfun$和操作$1（Dataset.scala:3616）
位于org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5（SQLExecution.scala:100）
在org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated（SQLExecution.scala:160）
位于org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1（SQLExecution.scala:87）
位于org.apache.spark.sql.SparkSession.withActive（SparkSession.scala:763）
位于org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId（SQLExecution.scala:64）
位于org.apache.spark.sql.Dataset.withAction（Dataset.scala:3614）
位于org.apache.spark.sql.Dataset.head（Dataset.scala:2695）
位于org.apache.spark.sql.Dataset.take（Dataset.scala:2902）
位于org.apache.spark.sql.Dataset.getRows（Dataset.scala:300）
位于org.apache.spark.sql.Dataset.showString（Dataset.scala:337）
在org.apache.spark.sql.Dataset.show（Dataset.scala:826）上
... 47删去
原因：java.lang.ArrayIndexOutOfBoundsException:13
位于org.apache.spark.sql.execution.datasources.orc.OrcColumnarBatchReader.initBatch（OrcColumnarBatchReader.java:183）
位于org.apache.spark.sql.execution.datasources.orc.OrcFileFormat.$anonfun$buildreader，分区值为$2（OrcFileFormat.scala:216）
位于org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile（FileScanRDD.scala:116）
位于org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator（FileScanRDD.scala:169）
位于org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext（FileScanRDD.scala:93）
位于org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext（DataSourceScanExec.scala:490）
位于org.apache.spark.sql.catalyst.expressions.GeneratedClass$generatorforcodegenstage1.columnartorow_nextBatch_0$（未知来源）
位于org.apache.spark.sql.catalyst.expressions.GeneratedClass$GenerateEditorForCodeGenStage1.processNext（未知源）
位于org.apache.spark.sql.execution.BufferedRowIterator.hasNext（BufferedRowIterator.java:43）
位于org.apache.spark.sql.execution.whisttagecodegenexec$$anon$1.hasNext（whisttagecodegenexec.scala:729）
位于org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1（SparkPlan.scala:340）
位于org.apache.spark.rdd.rdd.$anonfun$mapPartitionsInternal$2（rdd.scala:872）
在org.apache.spark.rdd.rdd.$anonfun$mapPartitionsInternal$2$adapted（rdd.scala:872）
位于org.apache.spark.rdd.MapPartitionsRDD.compute（MapPartitionsRDD.scala:52）
在org.apache.spark.rdd.rdd.computeOrReadCheckpoint（rdd.scala:349）
位于org.apache.spark.rdd.rdd.iterator（rdd.scala:313）
位于org.apache.spark.scheduler.ResultTask.runTask（ResultTask.scala:90）
位于org.apache.spark.scheduler.Task.run（Task.scala:127）
在org.apache.spark.executor.executor$TaskRunner.$anonfun$run$3（executor.scala:444）
位于org.apache.spark.util.Utils$.tryWithSafeFinally（Utils.scala:1377）
位于org.apache.spark.executor.executor$TaskRunner.run（executor.scala:447）
位于java.util.concurrent.ThreadPoolExecutor.runWorker（ThreadPoolExecutor.java:1142）
位于java.util.concurrent.ThreadPoolExecutor$Worker.run（ThreadPoolExecutor.java:617）
运行（Thread.java:745）

有什么办法解决这个问题吗

提前谢谢