Alin Treznai created SPARK-13230:
------------------------------------
Summary: HashMap.merged not working properly with Spark
Key: SPARK-13230
URL: https://issues.apache.org/jira/browse/SPARK-13230
Project: Spark
Issue Type: Bug
Components: Spark Core
Affects Versions: 1.6.0
Environment: Ubuntu 14.04.3, Scala 2.11.7, Spark 1.6.0
Reporter: Alin Treznai
Using HashMap.merged with Spark fails with NullPointerException.
import org.apache.spark.{SparkConf, SparkContext}
import scala.collection.immutable.HashMap
object MergeTest {
def mergeFn:(HashMap[String, Long], HashMap[String, Long]) => HashMap[String,
Long] = {
case (m1, m2) => m1.merged(m2){ case (x,y) => (x._1, x._2 + y._2) }
}
def empty = HashMap.empty[String,Long]
def main(args: Array[String]) = {
val input = Seq(HashMap("A" -> 1L), HashMap("A" -> 2L, "B" ->
3L),HashMap("A" -> 2L, "C" -> 4L))
val conf = new SparkConf().setAppName("MergeTest").setMaster("local[*]")
val sc = new SparkContext(conf)
val result = sc.parallelize(input).reduce(mergeFn)
println(s"Result=$result")
sc.stop()
}
}
Error message:
org.apache.spark.SparkDriverExecutionException: Execution error
at
org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:1169)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1637)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at
org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1952)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1025)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.reduce(RDD.scala:1007)
at MergeTest$.main(MergeTest.scala:21)
at MergeTest.main(MergeTest.scala)
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)
Caused by: java.lang.NullPointerException
at
MergeTest$$anonfun$mergeFn$1$$anonfun$apply$1.apply(MergeTest.scala:12)
at
MergeTest$$anonfun$mergeFn$1$$anonfun$apply$1.apply(MergeTest.scala:12)
at scala.collection.immutable.HashMap$$anon$2.apply(HashMap.scala:148)
at
scala.collection.immutable.HashMap$HashMap1.updated0(HashMap.scala:200)
at
scala.collection.immutable.HashMap$HashTrieMap.updated0(HashMap.scala:322)
at
scala.collection.immutable.HashMap$HashTrieMap.merge0(HashMap.scala:463)
at scala.collection.immutable.HashMap.merged(HashMap.scala:117)
at MergeTest$$anonfun$mergeFn$1.apply(MergeTest.scala:12)
at MergeTest$$anonfun$mergeFn$1.apply(MergeTest.scala:11)
at
org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:1020)
at
org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:1017)
at
org.apache.spark.scheduler.JobWaiter.taskSucceeded(JobWaiter.scala:56)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:1165)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1637)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
