查询
spark.sql("SELECT Trim(world_srvc_id) AS world_srvc_id,emp_eff_strt_dt AS emp_eff_strt_dt,emp_eff_end_dt AS emp_eff_end_dt,bus_site_id AS bus_site_id,dsgnt_cd AS dsgnt_cd,regexp_replace(Trim(emp_first_nm),'[^0-9a-zA-Z]',' ') AS emp_first_nm,regexp_replace(Trim(emp_mid_nm),'[^0-9a-zA-Z]',' ') AS emp_mid_nm, regexp_replace(Trim(emp_lst_nm),'[^0-9a-zA-Z]',' ') AS emp_lst_nm,Trim(mgr_world_srvc_id) AS mgr_world_srvc_id,Trim(cas_id) AS cas_id,CASE WHEN ((Trim(desktop_id) = '' AND Trim(cas_id) > ' ')) THEN (Upper(Trim(cas_id))) ELSE (Trim(desktop_id)) END AS desktop_id, func_incntv_care_grp_cd AS func_incntv_care_grp_cd,Cast(lang_id_tx AS String) AS lang_id_tx FROM table1")
错误
20/06/20 05:10:21 WARN TaskSetManager: Lost task 0.0 in stage 2.0 (TID 10, lgpbd152c.gso.aexp.com, executor 2): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:288)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:197)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:196)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 7
at org.apache.parquet.bytes.BytesUtils.bytesToLong(BytesUtils.java:251)
at org.apache.parquet.column.statistics.LongStatistics.setMinMaxFromBytes(LongStatistics.java:50)
at org.apache.parquet.column.statistics.Statistics$Builder.build(Statistics.java:65)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatisticsInternal(ParquetMetadataConverter.java:358)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatistics(ParquetMetadataConverter.java:365)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetMetadata(ParquetMetadataConverter.java:821)
at org.apache.parquet.format.converter.ParquetMetadataConverter.readParquetMetadata(ParquetMetadataConverter.java:798)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:484)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:445)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:401)
at org.apache.spark.sql.execution.datasources.parquet.SpecificParquetRecordReaderBase.initialize(SpecificParquetRecordReaderBase.java:106)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.initialize(VectorizedParquetRecordReader.java:133)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReaderWithPartitionValues$1.apply(ParquetFileFormat.scala:404)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReaderWithPartitionValues$1.apply(ParquetFileFormat.scala:345)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:128)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:182)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:109)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.scan_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$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:383)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:269)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:267)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1414)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:275)
... 8 more
20/06/20 05:10:22 ERROR TaskSetManager: Task 0 in stage 2.0 failed 4 times; aborting job
20/06/20 05:10:22 ERROR FileFormatWriter: Aborting job null.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 2.0 failed 4 times, most recent failure: Lost task 0.3 in stage 2.0 (TID 14, lgpbd152c.gso.aexp.com, executor 2): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:288)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:197)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:196)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 7
at org.apache.parquet.bytes.BytesUtils.bytesToLong(BytesUtils.java:251)
at org.apache.parquet.column.statistics.LongStatistics.setMinMaxFromBytes(LongStatistics.java:50)
at org.apache.parquet.column.statistics.Statistics$Builder.build(Statistics.java:65)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatisticsInternal(ParquetMetadataConverter.java:358)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatistics(ParquetMetadataConverter.java:365)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetMetadata(ParquetMetadataConverter.java:821)
at org.apache.parquet.format.converter.ParquetMetadataConverter.readParquetMetadata(ParquetMetadataConverter.java:798)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:484)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:445)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:401)
at org.apache.spark.sql.execution.datasources.parquet.SpecificParquetRecordReaderBase.initialize(SpecificParquetRecordReaderBase.java:106)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.initialize(VectorizedParquetRecordReader.java:133)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReaderWithPartitionValues$1.apply(ParquetFileFormat.scala:404)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReaderWithPartitionValues$1.apply(ParquetFileFormat.scala:345)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:128)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:182)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:109)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.scan_nextBatch_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:383)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:269)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:267)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1414)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:275)
... 8 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1651)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1639)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1638)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1638)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1872)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1821)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1810)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2034)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:194)
at org.apache.spark.sql.hive.execution.SaveAsHiveFile$class.saveAsHiveFile(SaveAsHiveFile.scala:86)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.saveAsHiveFile(InsertIntoHiveTable.scala:68)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.processInsert(InsertIntoHiveTable.scala:202)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.run(InsertIntoHiveTable.scala:101)
at org.apache.spark.sql.hive.execution.CreateHiveTableAsSelectCommand.run(CreateHiveTableAsSelectCommand.scala:86)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:115)
at org.apache.spark.sql.Dataset$$anonfun$6.apply(Dataset.scala:190)
at org.apache.spark.sql.Dataset$$anonfun$6.apply(Dataset.scala:190)
at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3259)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3258)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:190)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:75)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:288)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:197)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:196)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Caused by: java.lang.ArrayIndexOutOfBoundsException: 7
at org.apache.parquet.bytes.BytesUtils.bytesToLong(BytesUtils.java:251)
at org.apache.parquet.column.statistics.LongStatistics.setMinMaxFromBytes(LongStatistics.java:50)
at org.apache.parquet.column.statistics.Statistics$Builder.build(Statistics.java:65)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatisticsInternal(ParquetMetadataConverter.java:358)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatistics(ParquetMetadataConverter.java:365)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetMetadata(ParquetMetadataConverter.java:821)
at org.apache.parquet.format.converter.ParquetMetadataConverter.readParquetMetadata(ParquetMetadataConverter.java:798)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:484)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:445)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:401)
at org.apache.spark.sql.execution.datasources.parquet.SpecificParquetRecordReaderBase.initialize(SpecificParquetRecordReaderBase.java:106)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.initialize(VectorizedParquetRecordReader.java:133)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReaderWithPartitionValues$1.apply(ParquetFileFormat.scala:404)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReaderWithPartitionValues$1.apply(ParquetFileFormat.scala:345)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:128)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:182)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:109)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.scan_nextBatch_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:383)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:269)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:267)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1414)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:275)
... 8 more
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/opt/mapr/spark/spark-2.3.2/python/pyspark/sql/session.py", line 716, in sql
return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
File "/opt/mapr/spark/spark-2.3.2/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
File "/opt/mapr/spark/spark-2.3.2/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/opt/mapr/spark/spark-2.3.2/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o58.sql.
: org.apache.spark.SparkException: Job aborted.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:224)
at org.apache.spark.sql.hive.execution.SaveAsHiveFile$class.saveAsHiveFile(SaveAsHiveFile.scala:86)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.saveAsHiveFile(InsertIntoHiveTable.scala:68)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.processInsert(InsertIntoHiveTable.scala:202)
at org.apache.spark.sql.hive.execution.InsertIntoHiveTable.run(InsertIntoHiveTable.scala:101)
at org.apache.spark.sql.hive.execution.CreateHiveTableAsSelectCommand.run(CreateHiveTableAsSelectCommand.scala:86)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult$lzycompute(commands.scala:104)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.sideEffectResult(commands.scala:102)
at org.apache.spark.sql.execution.command.DataWritingCommandExec.executeCollect(commands.scala:115)
at org.apache.spark.sql.Dataset$$anonfun$6.apply(Dataset.scala:190)
at org.apache.spark.sql.Dataset$$anonfun$6.apply(Dataset.scala:190)
at org.apache.spark.sql.Dataset$$anonfun$52.apply(Dataset.scala:3259)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3258)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:190)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:75)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 2.0 failed 4 times, most recent failure: Lost task 0.3 in stage 2.0 (TID 14, lgpbd152c.gso.aexp.com, executor 2): org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:288)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:197)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:196)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: java.lang.ArrayIndexOutOfBoundsException: 7
at org.apache.parquet.bytes.BytesUtils.bytesToLong(BytesUtils.java:251)
at org.apache.parquet.column.statistics.LongStatistics.setMinMaxFromBytes(LongStatistics.java:50)
at org.apache.parquet.column.statistics.Statistics$Builder.build(Statistics.java:65)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatisticsInternal(ParquetMetadataConverter.java:358)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatistics(ParquetMetadataConverter.java:365)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetMetadata(ParquetMetadataConverter.java:821)
at org.apache.parquet.format.converter.ParquetMetadataConverter.readParquetMetadata(ParquetMetadataConverter.java:798)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:484)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:445)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:401)
at org.apache.spark.sql.execution.datasources.parquet.SpecificParquetRecordReaderBase.initialize(SpecificParquetRecordReaderBase.java:106)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.initialize(VectorizedParquetRecordReader.java:133)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReaderWithPartitionValues$1.apply(ParquetFileFormat.scala:404)
at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anonfun$buildReaderWithPartitionValues$1.apply(ParquetFileFormat.scala:345)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.org$apache$spark$sql$execution$datasources$FileScanRDD$$anon$$readCurrentFile(FileScanRDD.scala:128)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:182)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:109)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.scan_nextBatch_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$SingleDirectoryWriteTask.execute(FileFormatWriter.scala:383)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:269)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask$3.apply(FileFormatWriter.scala:267)
at org.apache.spark.util.Utils$.tryWithSafeFinallyAndFailureCallbacks(Utils.scala:1414)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:275)
... 8 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1651)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1639)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1638)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1638)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1872)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1821)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1810)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2034)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.write(FileFormatWriter.scala:194)
... 27 more
Caused by: org.apache.spark.SparkException: Task failed while writing rows.
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.org$apache$spark$sql$execution$datasources$FileFormatWriter$$executeTask(FileFormatWriter.scala:288)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:197)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$$anonfun$write$1.apply(FileFormatWriter.scala:196)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
... 1 more
Caused by: java.lang.ArrayIndexOutOfBoundsException: 7
at org.apache.parquet.bytes.BytesUtils.bytesToLong(BytesUtils.java:251)
at org.apache.parquet.column.statistics.LongStatistics.setMinMaxFromBytes(LongStatistics.java:50)
at org.apache.parquet.column.statistics.Statistics$Builder.build(Statistics.java:65)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatisticsInternal(ParquetMetadataConverter.java:358)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetStatistics(ParquetMetadataConverter.java:365)
at org.apache.parquet.format.converter.ParquetMetadataConverter.fromParquetMetadata(ParquetMetadataConverter.java:821)
at org.apache.parquet.format.converter.ParquetMetadataConverter.readParquetMetadata(ParquetMetadataConverter.java:798)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:484)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:445)
at org.apache.parquet.hadoop.ParquetFileReader.readFooter(ParquetFileReader.java:401)
at org.apache.spark.sql.execution.datasources.parquet.SpecificParquetRecordReaderBase.initialize(SpecificParquetRecordReaderBase.java:106)