You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Apache Spark (JIRA)" <ji...@apache.org> on 2016/03/17 02:12:33 UTC
[jira] [Assigned] (SPARK-13719) Bad JSON record raises java.lang.ClassCastException
[ https://issues.apache.org/jira/browse/SPARK-13719?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Apache Spark reassigned SPARK-13719:
------------------------------------
Assignee: Apache Spark
> Bad JSON record raises java.lang.ClassCastException
> ----------------------------------------------------
>
> Key: SPARK-13719
> URL: https://issues.apache.org/jira/browse/SPARK-13719
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.2, 1.6.0
> Environment: OS X, Linux
> Reporter: dmtran
> Assignee: Apache Spark
> Priority: Minor
>
> I have defined a JSON schema, using org.apache.spark.sql.types.StructType, that expects this kind of record :
> {noformat}
> {
> "request": {
> "user": {
> "id": 123
> }
> }
> }
> {noformat}
> There's a bad record in my dataset, that defines field "user" as an array, instead of a JSON object :
> {noformat}
> {
> "request": {
> "user": []
> }
> }
> {noformat}
> The following exception is raised because of that bad record :
> {noformat}
> Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 7 in stage 0.0 failed 4 times, most recent failure: Lost task 7.3 in stage 0.0 (TID 10, 192.168.1.170): java.lang.ClassCastException: org.apache.spark.sql.types.GenericArrayData cannot be cast to org.apache.spark.sql.catalyst.InternalRow
> at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow$class.getStruct(rows.scala:50)
> at org.apache.spark.sql.catalyst.expressions.GenericMutableRow.getStruct(rows.scala:247)
> at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificPredicate.eval(Unknown Source)
> at org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$$anonfun$create$2.apply(GeneratePredicate.scala:67)
> at org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$$anonfun$create$2.apply(GeneratePredicate.scala:67)
> at org.apache.spark.sql.execution.Filter$$anonfun$4$$anonfun$apply$4.apply(basicOperators.scala:117)
> at org.apache.spark.sql.execution.Filter$$anonfun$4$$anonfun$apply$4.apply(basicOperators.scala:115)
> at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390)
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1.org$apache$spark$sql$execution$aggregate$TungstenAggregate$$anonfun$$executePartition$1(TungstenAggregate.scala:97)
> at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:119)
> at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:119)
> at org.apache.spark.rdd.MapPartitionsWithPreparationRDD.compute(MapPartitionsWithPreparationRDD.scala:64)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:300)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:300)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:88)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> {noformat}
> Here's a code snippet that reproduces the exception :
> {noformat}
> import org.apache.spark.SparkContext
> import org.apache.spark.rdd.RDD
> import org.apache.spark.sql.{SQLContext, DataFrame}
> import org.apache.spark.sql.hive.HiveContext
> import org.apache.spark.sql.types.{StringType, StructField, StructType}
> object Snippet {
> def main(args : Array[String]): Unit = {
> val sc = new SparkContext()
> implicit val sqlContext = new HiveContext(sc)
> val rdd: RDD[String] = sc.parallelize(Seq(badRecord))
> val df: DataFrame = sqlContext.read.schema(schema).json(rdd)
> import sqlContext.implicits._
> df.select("request.user.id")
> .filter($"id".isNotNull)
> .count()
> }
> val badRecord =
> s"""{
> | "request": {
> | "user": []
> | }
> |}""".stripMargin.replaceAll("\n", " ") // Convert the multiline string to a signe line string
> val schema =
> StructType(
> StructField("request", StructType(
> StructField("user", StructType(
> StructField("id", StringType) :: Nil
> )) :: Nil
> )) :: Nil)
> }
> {noformat}
--
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