[jira] [Commented] (SPARK-18536) Failed to save to hive table when case class with empty field

["Thomas Sebastian (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-18536?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15708442#comment-15708442 ] 

Thomas Sebastian commented on SPARK-18536:
------------------------------------------

[~pin_zhang] and [~rxin]
In this case, what we need to do is to stop performing saveAsTable operation, rather check the schema class having empty fields. and throw a different exception early on.
Please advise.

> Failed to save to hive table when case class with empty field
> -------------------------------------------------------------
>
>                 Key: SPARK-18536
>                 URL: https://issues.apache.org/jira/browse/SPARK-18536
>             Project: Spark
>          Issue Type: Bug
>          Components: SQL
>    Affects Versions: 2.0.1
>            Reporter: pin_zhang
>
> import scala.collection.mutable.Queue
> import org.apache.spark.SparkConf
> import org.apache.spark.SparkContext
> import org.apache.spark.sql.SaveMode
> import org.apache.spark.sql.SparkSession
> import org.apache.spark.streaming.Seconds
> import org.apache.spark.streaming.StreamingContext
> 1. Test code
> case class EmptyC()
> case class EmptyCTable(dimensions: EmptyC, timebin: java.lang.Long)
> object EmptyTest {
>   def main(args: Array[String]): Unit = {
>     val conf = new SparkConf().setAppName("scala").setMaster("local[2]")
>     val ctx = new SparkContext(conf)
>     val spark = SparkSession.builder().enableHiveSupport().config(conf).getOrCreate()
>     val seq = Seq(EmptyCTable(EmptyC(), 1000000L))
>     val rdd = ctx.makeRDD[EmptyCTable](seq)
>     val ssc = new StreamingContext(ctx, Seconds(1))
>     val queue = Queue(rdd)
>     val s = ssc.queueStream(queue, false);
>     s.foreachRDD((rdd, time) => {
>       if (!rdd.isEmpty) {
>         import spark.sqlContext.implicits._
>         rdd.toDF.write.mode(SaveMode.Overwrite).saveAsTable("empty_table")
>       }
>     })
>     ssc.start()
>     ssc.awaitTermination()
>   }
> }
> 2. Exception
> Caused by: java.lang.IllegalStateException: Cannot build an empty group
> 	at org.apache.parquet.Preconditions.checkState(Preconditions.java:91)
> 	at org.apache.parquet.schema.Types$GroupBuilder.build(Types.java:554)
> 	at org.apache.parquet.schema.Types$GroupBuilder.build(Types.java:426)
> 	at org.apache.parquet.schema.Types$Builder.named(Types.java:228)
> 	at org.apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter.convertField(ParquetSchemaConverter.scala:527)
> 	at org.apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter.convertField(ParquetSchemaConverter.scala:321)
> 	at org.apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter$$anonfun$convert$1.apply(ParquetSchemaConverter.scala:313)
> 	at org.apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter$$anonfun$convert$1.apply(ParquetSchemaConverter.scala:313)
> 	at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> 	at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> 	at scala.collection.Iterator$class.foreach(Iterator.scala:893)
> 	at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
> 	at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
> 	at org.apache.spark.sql.types.StructType.foreach(StructType.scala:95)
> 	at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> 	at org.apache.spark.sql.types.StructType.map(StructType.scala:95)
> 	at org.apache.spark.sql.execution.datasources.parquet.ParquetSchemaConverter.convert(ParquetSchemaConverter.scala:313)
> 	at org.apache.spark.sql.execution.datasources.parquet.ParquetWriteSupport.init(ParquetWriteSupport.scala:85)
> 	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>(ParquetFileFormat.scala:562)
> 	at org.apache.spark.sql.execution.datasources.parquet.ParquetFileFormat$$anon$1.newInstance(ParquetFileFormat.scala:139)
> 	at org.apache.spark.sql.execution.datasources.BaseWriterContainer.newOutputWriter(WriterContainer.scala:131)
> 	at org.apache.spark.sql.execution.datasources.DefaultWriterContainer.writeRows(WriterContainer.scala:247)
> 	at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply(InsertIntoHadoopFsRelationCommand.scala:143)
> 	at org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply(InsertIntoHadoopFsRelationCommand.scala:143)
> 	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
> 	at org.apache.spark.scheduler.Task.run(Task.scala:86)
> 	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
> 	... 3 more
>  



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org