Deserialize / Parse JSON for AbstractMethodError objects in Scala with spray in a spark cluster

I am trying to parse Scala JSON in Spark. It works locally with my tests, but failed on the remote cluster.

Relevant imports:

import com.fasterxml.jackson.databind.ObjectMapper
import com.fasterxml.jackson.module.scala.DefaultScalaModule
import com.fasterxml.jackson.module.scala.experimental.ScalaObjectMapper
import spray.json._

Classes:

case class Item(name: String,
                      siteType: String,
                      productCategoryType: String,
                      variants: List[VariantRange]) extends Serializable
case class VariantRange(name: String, start: Double, end: Double) extends Serializable

case class ItemList(items: List[Item])

object ItemJsonProtocol extends DefaultJsonProtocol {
  implicit val variantRangeFormat = jsonFormat(VariantRange, "name", "start", "end")
  implicit val itemFormat = jsonFormat(Item, "name", "siteType", "productCategoryType", "variants")

  implicit object itemListJsonFormat extends RootJsonFormat[ItemList] {
    override def write(obj: ItemList): JsValue = ???

    override def read(json: JsValue): ItemList = ItemList(json.convertTo[List[Item]])
  }
}

Parsing Code:

def parseItems(json: String) = {
  val mapper = new ObjectMapper() with ScalaObjectMapper
  mapper.registerModule(DefaultScalaModule)
  val jsonAst = json.parseJson

  import ItemJsonProtocol._
  jsonAst.convertTo[ItemList].items
}

def parseItems(): List[Item] = {
  parseItems(Source.fromInputStream(getClass.getResourceAsStream("/data/items.json")).mkString)
}

This test runs locally:

  test("Parses resources file") {
    val items = parseItems()
    items shouldNot be (null)
  }

But in Spark, this shows:

15/12/07 17:59:05 ERROR ApplicationMaster: User class threw exception: java.lang.AbstractMethodError: com.intentmedia.data.AggregationJob$$anon$1.com$fasterxml$jackson$module$scala$experimental$ScalaObjectMapper$_setter_$com$fasterxml$jackson$module$scala$experimental$ScalaObjectMapper$$typeCache_$eq(Lorg/spark-project/guava/cache/LoadingCache;)V
java.lang.AbstractMethodError: com.intentmedia.data.AggregationJob$$anon$1.com$fasterxml$jackson$module$scala$experimental$ScalaObjectMapper$_setter_$com$fasterxml$jackson$module$scala$experimental$ScalaObjectMapper$$typeCache_$eq(Lorg/spark-project/guava/cache/LoadingCache;)V
    at com.fasterxml.jackson.module.scala.experimental.ScalaObjectMapper$class.$init$(ScalaObjectMapper.scala:50)
    at com.intentmedia.data.AggregationJob$$anon$1.<init>(AggregationJob.scala:76)
    at com.intentmedia.data.AggregationJob$.parseExperiments(AggregationJob.scala:76)
    at com.intentmedia.data.AggregationJob$.parseExperiments(AggregationJob.scala:85)
    at com.intentmedia.data.AggregationJob$.runWorkflow(AggregationJob.scala:66)
    at com.intentmedia.spark.SparkJob$class.main(SparkJob.scala:43)
    at com.intentmedia.data.AggregationJob$.main(AggregationJob.scala:49)
    at com.intentmedia.data.AggregationJob.main(AggregationJob.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:525)
15/12/07 17:59:05 INFO ApplicationMaster: Final app status: FAILED, exitCode: 15, (reason: User class threw exception: java.lang.AbstractMethodError: com.intentmedia.data.AggregationJob$$anon$1.com$fasterxml$jackson$module$scala$experimental$ScalaObjectMapper$_setter_$com$fasterxml$jackson$module$scala$experimental$ScalaObjectMapper$$typeCache_$eq(Lorg/spark-project/guava/cache/LoadingCache;)V)

Do I need to use caching when reading objects? Am I not processing resource files correctly?

+4
source share

Source: https://habr.com/ru/post/1618928/


All Articles