[SPARK-10943] NullType Column cannot be written to Parquet

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Won't Fix
• Component/s: SQL
• Assignee: Unassigned
• Reporter: Jason Pohl
• Created: 06/Oct/15 05:17
• Updated: 03/May/18 17:08
• Resolved: 15/Oct/15 18:21

Description

var data02 = sqlContext.sql("select 1 as id, \"cat in the hat\" as text, null as comments")

//FAIL - Try writing a NullType column (where all the values are NULL)

data02.write.parquet("/tmp/test/dataset2")

	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$$anonfun$execute$5.apply(SparkPlan.scala:138)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
	at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:138)
	at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:933)
	at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:933)
	at org.apache.spark.sql.execution.datasources.ResolvedDataSource$.apply(ResolvedDataSource.scala:197)
	at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:146)
	at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:137)
	at org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:304)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 179.0 failed 4 times, most recent failure: Lost task 0.3 in stage 179.0 (TID 39924, 10.0.196.208): org.apache.spark.sql.AnalysisException: Unsupported data type StructField(comments,NullType,true).dataType;
	at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:524)
	at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:312)
	at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:305)
	at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter$$anonfun$convert$1.apply(CatalystSchemaConverter.scala:305)
	at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
	at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
	at scala.collection.Iterator$class.foreach(Iterator.scala:727)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
	at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
	at org.apache.spark.sql.types.StructType.foreach(StructType.scala:92)
	at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
	at org.apache.spark.sql.types.StructType.map(StructType.scala:92)
	at org.apache.spark.sql.execution.datasources.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:305)
	at org.apache.spark.sql.execution.datasources.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypesConverter.scala:58)
	at org.apache.spark.sql.execution.datasources.parquet.RowWriteSupport.init(ParquetTableSupport.scala:55)
	at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:288)
	at org.apache.parquet.hadoop.ParquetOutputFormat.getRecordWriter(ParquetOutputFormat.java:262)
	at org.apache.spark.sql.execution.datasources.parquet.ParquetOutputWriter.<init>(ParquetRelation.scala:94)
	at org.apache.spark.sql.execution.datasources.parquet.ParquetRelation$$anon$3.newInstance(ParquetRelation.scala:272)
	at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:233)
	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:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)