Details
-
Bug
-
Status: Resolved
-
Major
-
Resolution: Duplicate
-
1.5.0
-
None
-
None
Description
Cannot save data frames using nested UserDefinedType
I wrote a simple example to show the error.
It causes the following error java.lang.IllegalArgumentException: Nested type should be repeated: required group array {
required int32 num;
}
import org.apache.spark.sql.SaveMode import org.apache.spark.{SparkConf, SparkContext} import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.catalyst.expressions.GenericMutableRow import org.apache.spark.sql.types._ @SQLUserDefinedType(udt = classOf[AUDT]) case class A(list:Seq[B]) class AUDT extends UserDefinedType[A] { override def sqlType: DataType = StructType(Seq(StructField("list", ArrayType(BUDT, containsNull = false), nullable = true))) override def userClass: Class[A] = classOf[A] override def serialize(obj: Any): Any = obj match { case A(list) => val row = new GenericMutableRow(1) row.update(0, new GenericArrayData(list.map(_.asInstanceOf[Any]).toArray)) row } override def deserialize(datum: Any): A = { datum match { case row: InternalRow => new A(row.getArray(0).toArray(BUDT).toSeq) } } } object AUDT extends AUDT @SQLUserDefinedType(udt = classOf[BUDT]) case class B(num:Int) class BUDT extends UserDefinedType[B] { override def sqlType: DataType = StructType(Seq(StructField("num", IntegerType, nullable = false))) override def userClass: Class[B] = classOf[B] override def serialize(obj: Any): Any = obj match { case B(num) => val row = new GenericMutableRow(1) row.setInt(0, num) row } override def deserialize(datum: Any): B = { datum match { case row: InternalRow => new B(row.getInt(0)) } } } object BUDT extends BUDT object TestNested { def main(args:Array[String]) = { val col = Seq(new A(Seq(new B(1), new B(2))), new A(Seq(new B(3), new B(4)))) val sc = new SparkContext(new SparkConf().setMaster("local[1]").setAppName("TestSpark")) val sqlContext = new org.apache.spark.sql.SQLContext(sc) import sqlContext.implicits._ val df = sc.parallelize(1 to 2 zip col).toDF() df.show() df.write.mode(SaveMode.Overwrite).save(...) } }
The error log is shown below:
15/09/16 16:44:36 WARN : Your hostname, X resolves to a loopback/non-reachable address: fe80:0:0:0:c4c7:8c4b:4a24:f8a1%14, but we couldn't find any external IP address! 15/09/16 16:44:38 INFO deprecation: mapred.job.id is deprecated. Instead, use mapreduce.job.id 15/09/16 16:44:38 INFO deprecation: mapred.tip.id is deprecated. Instead, use mapreduce.task.id 15/09/16 16:44:38 INFO deprecation: mapred.task.id is deprecated. Instead, use mapreduce.task.attempt.id 15/09/16 16:44:38 INFO deprecation: mapred.task.is.map is deprecated. Instead, use mapreduce.task.ismap 15/09/16 16:44:38 INFO deprecation: mapred.task.partition is deprecated. Instead, use mapreduce.task.partition 15/09/16 16:44:38 INFO ParquetRelation: Using default output committer for Parquet: org.apache.parquet.hadoop.ParquetOutputCommitter 15/09/16 16:44:38 INFO DefaultWriterContainer: Using user defined output committer class org.apache.parquet.hadoop.ParquetOutputCommitter 15/09/16 16:44:38 INFO BlockManagerInfo: Removed broadcast_0_piece0 on localhost:50986 in memory (size: 1402.0 B, free: 973.6 MB) 15/09/16 16:44:38 INFO ContextCleaner: Cleaned accumulator 1 15/09/16 16:44:39 INFO SparkContext: Starting job: save at TestNested.scala:73 15/09/16 16:44:39 INFO DAGScheduler: Got job 1 (save at TestNested.scala:73) with 1 output partitions 15/09/16 16:44:39 INFO DAGScheduler: Final stage: ResultStage 1(save at TestNested.scala:73) 15/09/16 16:44:39 INFO DAGScheduler: Parents of final stage: List() 15/09/16 16:44:39 INFO DAGScheduler: Missing parents: List() 15/09/16 16:44:39 INFO DAGScheduler: Submitting ResultStage 1 (MapPartitionsRDD[1] at rddToDataFrameHolder at TestNested.scala:69), which has no missing parents 15/09/16 16:44:39 INFO MemoryStore: ensureFreeSpace(59832) called with curMem=0, maxMem=1020914565 15/09/16 16:44:39 INFO MemoryStore: Block broadcast_1 stored as values in memory (estimated size 58.4 KB, free 973.6 MB) 15/09/16 16:44:39 INFO MemoryStore: ensureFreeSpace(20794) called with curMem=59832, maxMem=1020914565 15/09/16 16:44:39 INFO MemoryStore: Block broadcast_1_piece0 stored as bytes in memory (estimated size 20.3 KB, free 973.5 MB) 15/09/16 16:44:39 INFO BlockManagerInfo: Added broadcast_1_piece0 in memory on localhost:50986 (size: 20.3 KB, free: 973.6 MB) 15/09/16 16:44:39 INFO SparkContext: Created broadcast 1 from broadcast at DAGScheduler.scala:861 15/09/16 16:44:39 INFO DAGScheduler: Submitting 1 missing tasks from ResultStage 1 (MapPartitionsRDD[1] at rddToDataFrameHolder at TestNested.scala:69) 15/09/16 16:44:39 INFO TaskSchedulerImpl: Adding task set 1.0 with 1 tasks 15/09/16 16:44:39 INFO TaskSetManager: Starting task 0.0 in stage 1.0 (TID 1, localhost, PROCESS_LOCAL, 2354 bytes) 15/09/16 16:44:39 INFO Executor: Running task 0.0 in stage 1.0 (TID 1) 15/09/16 16:44:39 INFO deprecation: mapred.output.key.class is deprecated. Instead, use mapreduce.job.output.key.class 15/09/16 16:44:39 INFO deprecation: mapred.output.value.class is deprecated. Instead, use mapreduce.job.output.value.class 15/09/16 16:44:39 INFO deprecation: mapreduce.outputformat.class is deprecated. Instead, use mapreduce.job.outputformat.class 15/09/16 16:44:39 INFO deprecation: mapred.output.dir is deprecated. Instead, use mapreduce.output.fileoutputformat.outputdir 15/09/16 16:44:39 INFO DefaultWriterContainer: Using user defined output committer class org.apache.parquet.hadoop.ParquetOutputCommitter 15/09/16 16:44:39 INFO CodecConfig: Compression: GZIP 15/09/16 16:44:39 INFO ParquetOutputFormat: Parquet block size to 134217728 15/09/16 16:44:39 INFO ParquetOutputFormat: Parquet page size to 1048576 15/09/16 16:44:39 INFO ParquetOutputFormat: Parquet dictionary page size to 1048576 15/09/16 16:44:39 INFO ParquetOutputFormat: Dictionary is on 15/09/16 16:44:39 INFO ParquetOutputFormat: Validation is off 15/09/16 16:44:39 INFO ParquetOutputFormat: Writer version is: PARQUET_1_0 15/09/16 16:44:39 ERROR Executor: Exception in task 0.0 in stage 1.0 (TID 1) java.lang.IllegalArgumentException: Nested type should be repeated: required group array { required int32 num; } at org.apache.parquet.schema.ConversionPatterns.listWrapper(ConversionPatterns.java:42) at org.apache.parquet.schema.ConversionPatterns.listType(ConversionPatterns.java:97) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:460) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:522) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:521) at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51) at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60) at scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:108) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:521) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:526) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.IterableLike$class.foreach(IterableLike.scala:72) at org.apache.spark.sql.types.StructType.foreach(StructType.scala:92) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at org.apache.spark.sql.types.StructType.map(StructType.scala:92) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58) at org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:288) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:262) at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94) at org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272) at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:234) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 15/09/16 16:44:39 WARN TaskSetManager: Lost task 0.0 in stage 1.0 (TID 1, localhost): java.lang.IllegalArgumentException: Nested type should be repeated: required group array { required int32 num; } at org.apache.parquet.schema.ConversionPatterns.listWrapper(ConversionPatterns.java:42) at org.apache.parquet.schema.ConversionPatterns.listType(ConversionPatterns.java:97) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:460) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:522) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:521) at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51) at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60) at scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:108) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:521) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:526) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.IterableLike$class.foreach(IterableLike.scala:72) at org.apache.spark.sql.types.StructType.foreach(StructType.scala:92) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at org.apache.spark.sql.types.StructType.map(StructType.scala:92) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58) at org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:288) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:262) at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94) at org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272) at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:234) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 15/09/16 16:44:39 ERROR TaskSetManager: Task 0 in stage 1.0 failed 1 times; aborting job 15/09/16 16:44:39 INFO TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool 15/09/16 16:44:39 INFO TaskSchedulerImpl: Cancelling stage 1 15/09/16 16:44:39 INFO DAGScheduler: ResultStage 1 (save at TestNested.scala:73) failed in 0.069 s 15/09/16 16:44:39 INFO DAGScheduler: Job 1 failed: save at TestNested.scala:73, took 0.097322 s 15/09/16 16:44:39 ERROR InsertIntoHadoopFsRelation: Aborting job. org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage 1.0 (TID 1, localhost): java.lang.IllegalArgumentException: Nested type should be repeated: required group array { required int32 num; } at org.apache.parquet.schema.ConversionPatterns.listWrapper(ConversionPatterns.java:42) at org.apache.parquet.schema.ConversionPatterns.listType(ConversionPatterns.java:97) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:460) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:522) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:521) at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51) at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60) at scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:108) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:521) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:526) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.IterableLike$class.foreach(IterableLike.scala:72) at org.apache.spark.sql.types.StructType.foreach(StructType.scala:92) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at org.apache.spark.sql.types.StructType.map(StructType.scala:92) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58) at org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:288) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:262) at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94) at org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272) at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:234) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:108) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57) at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138) at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927) at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927) at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137) at app.TestNested$.main(TestNested.scala:73) at app.TestNested.main(TestNested.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140) Caused by: java.lang.IllegalArgumentException: Nested type should be repeated: required group array { required int32 num; } at org.apache.parquet.schema.ConversionPatterns.listWrapper(ConversionPatterns.java:42) at org.apache.parquet.schema.ConversionPatterns.listType(ConversionPatterns.java:97) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:460) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:522) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:521) at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51) at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60) at scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:108) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:521) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:526) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.IterableLike$class.foreach(IterableLike.scala:72) at org.apache.spark.sql.types.StructType.foreach(StructType.scala:92) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at org.apache.spark.sql.types.StructType.map(StructType.scala:92) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58) at org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:288) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:262) at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94) at org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272) at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:234) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 15/09/16 16:44:40 ERROR DefaultWriterContainer: Job job_201509161644_0000 aborted. Exception in thread "main" org.apache.spark.SparkException: Job aborted. at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:156) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply(InsertIntoHadoopFsRelation.scala:108) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation.run(InsertIntoHadoopFsRelation.scala:108) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57) at org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57) at org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:69) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:140) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$5.apply(SparkPlan.scala:138) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138) at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:927) at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:927) at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137) at app.TestNested$.main(TestNested.scala:73) at app.TestNested.main(TestNested.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at com.intellij.rt.execution.application.AppMain.main(AppMain.java:140) Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage 1.0 (TID 1, localhost): java.lang.IllegalArgumentException: Nested type should be repeated: required group array { required int32 num; } at org.apache.parquet.schema.ConversionPatterns.listWrapper(ConversionPatterns.java:42) at org.apache.parquet.schema.ConversionPatterns.listType(ConversionPatterns.java:97) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:460) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:522) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:521) at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51) at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60) at scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:108) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:521) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:526) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.IterableLike$class.foreach(IterableLike.scala:72) at org.apache.spark.sql.types.StructType.foreach(StructType.scala:92) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at org.apache.spark.sql.types.StructType.map(StructType.scala:92) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58) at org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:288) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:262) at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94) at org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272) at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:234) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1.apply$mcV$sp(InsertIntoHadoopFsRelation.scala:150) ... 23 more Caused by: java.lang.IllegalArgumentException: Nested type should be repeated: required group array { required int32 num; } at org.apache.parquet.schema.ConversionPatterns.listWrapper(ConversionPatterns.java:42) at org.apache.parquet.schema.ConversionPatterns.listType(ConversionPatterns.java:97) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:460) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:522) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convertField$1.apply(CatalystSchemaConverter.scala:521) at scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:51) at scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:60) at scala.collection.mutable.ArrayOps$ofRef.foldLeft(ArrayOps.scala:108) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:521) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:526) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:318) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:311) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.IterableLike$class.foreach(IterableLike.scala:72) at org.apache.spark.sql.types.StructType.foreach(StructType.scala:92) at scala.collection.TraversableLike$class.map(TraversableLike.scala:244) at org.apache.spark.sql.types.StructType.map(StructType.scala:92) at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:311) at org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58) at org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:288) at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:262) at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94) at org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272) at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:234) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelation$$anonfun$run$1$$anonfun$apply$mcV$sp$3.apply(InsertIntoHadoopFsRelation.scala:150) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) at org.apache.spark.scheduler.Task.run(Task.scala:88) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745)
Attachments
Issue Links
- duplicates
-
-
- Resolved
-
- links to
