Apache flink Confluent org.apache.avro.generic.GenericData$Record cannot be cast to java.lang.String

I have a Apache Flink Application, where I want to filter the data by Country which gets read from topic v01 and write the filtered data into the topic v02.

My Code:

package org.example;

import org.apache.avro.Schema;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.formats.avro.registry.confluent.ConfluentRegistryAvroDeserializationSchema;
import org.apache.flink.formats.avro.registry.confluent.ConfluentRegistryAvroSerializationSchema;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer;
import org.apache.flink

.streaming.connectors.kafka.FlinkKafkaProducer;
import java.util.Properties;

public class KafkaRead {

public static void main(String[] args) throws Exception {

    Properties properties = new Properties();
    properties.setProperty("bootstrap.servers", "192.168.100.100:9092");

    properties.setProperty("group.id", "luft");
    String schemaRegistryUrl = "http://192.168.100.100:8081";

    String valueSchema = "{\"connect.name\":\"com.github.jcustenborder.kafka.connect.model.Value\",\"fields\":[{\"default\":null,\"name\":\"Datum\",\"type\":[\"null\",\"string\"]},{\"default\":null,\"name\":\"Country\",\"type\":[\"null\",\"string\"]},{\"default\":null,\"name\":\"City\",\"type\":[\"null\",\"string\"]},{\"default\":null,\"name\":\"Specie\",\"type\":[\"null\",\"string\"]},{\"default\":null,\"name\":\"count\",\"type\":[\"null\",\"string\"]},{\"default\":null,\"name\":\"min\",\"type\":[\"null\",\"string\"]},{\"default\":null,\"name\":\"max\",\"type\":[\"null\",\"string\"]},{\"default\":null,\"name\":\"median\",\"type\":[\"null\",\"string\"]},{\"default\":null,\"name\":\"variance\",\"type\":[\"null\",\"string\"]}],\"name\":\"Value\",\"namespace\":\"com.github.jcustenborder.kafka.connect.model\",\"type\":\"record\"}";
    Schema schema = new Schema.Parser().parse(valueSchema);

    final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

    FlinkKafkaConsumer kafkaConsumer = new FlinkKafkaConsumer<> ("v01", ConfluentRegistryAvroDeserializationSchema.forGeneric(schema, schemaRegistryUrl) , properties);
    kafkaConsumer.setStartFromEarliest();
    
    DataStream<String> streamIn = env.addSource(kafkaConsumer);

    FlinkKafkaProducer kafkaProducer = new FlinkKafkaProducer("v02",ConfluentRegistryAvroSerializationSchema.forGeneric("v02-value",schema,schemaRegistryUrl),properties);

    DataStream<String> streamOut = streamIn.map(new MapFunction<String, String>() { //<--Error in this line
        @Override
        public String map(String value) throws Exception {
            return value.toUpperCase();
        }
    });
    streamOut.addSink(kafkaProducer);
    env.execute("Flink Streaming In/Out Kafka");
}

}

When executing I get following error:

Caused by: java.lang.ClassCastException: org.apache.avro.generic.GenericData$Record cannot be cast to java.lang.String
at org.example.KafkaRead$1.map(KafkaRead.java:45)

It works without problems if I dont use a map function and use my Input as my Output:

DataStream<String> streamOut = streamIn;

For Context:

The data that gets read in the first place looks like this

Date,Country,City,Specie,count,min,max,median,variance
2020-03-24,DE,Hamburg,humidity,288,26.0,54.0,36.5,966.48
2020-03-26,DE,Hamburg,humidity,288,25.0,71.5,44.0,1847.14
2020-04-01,DE,Hamburg,humidity,288,61.0,83.0,75.0,418.07

Complete Error:

    Exception in thread "main" org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
    at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:147)
    at org.apache.flink.runtime.minicluster.MiniClusterJobClient.lambda$getJobExecutionResult$2(MiniClusterJobClient.java:119)
    at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616)
    at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
    at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
    at org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$0(AkkaInvocationHandler.java:229)
    at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
    at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
    at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
    at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
    at org.apache.flink.runtime.concurrent.FutureUtils$1.onComplete(FutureUtils.java:996)
    at akka.dispatch.OnComplete.internal(Future.scala:264)
    at akka.dispatch.OnComplete.internal(Future.scala:261)
    at akka.dispatch.japi$CallbackBridge.apply(Future.scala:191)
    at akka.dispatch.japi$CallbackBridge.apply(Future.scala:188)
    at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36)
    at org.apache.flink.runtime.concurrent.Executors$DirectExecutionContext.execute(Executors.java:74)
    at scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:44)
    at scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:252)
    at akka.pattern.PromiseActorRef.$bang(AskSupport.scala:572)
    at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:22)
    at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:21)
    at scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:436)
    at scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:435)
    at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36)
    at akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:55)
    at akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply$mcV$sp(BatchingExecutor.scala:91)
    at akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91)
    at akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91)
    at scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:72)
    at akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:90)
    at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40)
    at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44)
    at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
    at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
    at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
    at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
    at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:116)
    at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:78)
    at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:224)
    at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:217)
    at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:208)
    at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:610)
    at org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:89)
    at org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:419)
    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)
    at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:286)
    at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:201)
    at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
    at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:154)
    at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
    at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
    at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)
    at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
    at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)
    at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
    at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
    at akka.actor.Actor$class.aroundReceive(Actor.scala:517)
    at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
    at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
    at akka.actor.ActorCell.invoke(ActorCell.scala:561)
    at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
    at akka.dispatch.Mailbox.run(Mailbox.scala:225)
    at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
    ... 4 more
Caused by: java.lang.ClassCastException: org.apache.avro.generic.GenericData$Record cannot be cast to java.lang.String
    at org.example.KafkaRead$1.map(KafkaRead.java:45)
    at org.apache.flink.streaming.api.operators.StreamMap.processElement(StreamMap.java:41)
    at org.apache.flink.streaming.runtime.tasks.CopyingChainingOutput.pushToOperator(CopyingChainingOutput.java:71)
    at org.apache.flink.streaming.runtime.tasks.CopyingChainingOutput.collect(CopyingChainingOutput.java:46)
    at org.apache.flink.streaming.runtime.tasks.CopyingChainingOutput.collect(CopyingChainingOutput.java:26)
    at org.apache.flink.streaming.api.operators.CountingOutput.collect(CountingOutput.java:52)
    at org.apache.flink.streaming.api.operators.CountingOutput.collect(CountingOutput.java:30)
    at org.apache.flink.streaming.api.operators.StreamSourceContexts$ManualWatermarkContext.processAndCollectWithTimestamp(StreamSourceContexts.java:310)
    at org.apache.flink.streaming.api.operators.StreamSourceContexts$WatermarkContext.collectWithTimestamp(StreamSourceContexts.java:409)
    at org.apache.flink.streaming.connectors.kafka.internals.AbstractFetcher.emitRecordsWithTimestamps(AbstractFetcher.java:352)
    at org.apache.flink.streaming.connectors.kafka.internals.KafkaFetcher.partitionConsumerRecordsHandler(KafkaFetcher.java:181)
    at org.apache.flink.streaming.connectors.kafka.internals.KafkaFetcher.runFetchLoop(KafkaFetcher.java:137)
    at org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumerBase.run(FlinkKafkaConsumerBase.java:761)
    at org.apache.flink.streaming.api.operators.StreamSource.run(StreamSource.java:100)
    at org.apache.flink.streaming.api.operators.StreamSource.run(StreamSource.java:63)
    at org.apache.flink.streaming.runtime.tasks.SourceStreamTask$LegacySourceFunctionThread.run(SourceStreamTask.java:215)


Read more here: https://stackoverflow.com/questions/67382809/apache-flink-confluent-org-apache-avro-generic-genericdatarecord-cannot-be-cast

Content Attribution

This content was originally published by J. Doe at Recent Questions - Stack Overflow, and is syndicated here via their RSS feed. You can read the original post over there.

%d bloggers like this: