我正在集群中运行Flink作业。作业已正确部署，但是，当收到任何消息时，它将失败，并出现以下异常：
java.lang.NullPointerException
at org.apache.flink.api.java.io.TextOutputFormat.writeRecord(TextOutputFormat.java:103)
at org.apache.flink.streaming.api.functions.sink.OutputFormatSinkFunction.invoke(OutputFormatSinkFunction.java:86)
at org.apache.flink.streaming.api.functions.sink.SinkFunction.invoke(SinkFunction.java:52)
at org.apache.flink.streaming.api.operators.StreamSink.processElement(StreamSink.java:56)
at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:558)
at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:533)
at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:513)
at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:679)
at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:657)
at org.apache.flink.streaming.api.operators.StreamMap.processElement(StreamMap.java:41)
at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:558)
at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:533)
at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:513)
at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:679)
at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:657)
at org.apache.flink.streaming.api.operators.StreamSourceContexts$NonTimestampContext.collect(StreamSourceContexts.java:104)
at org.apache.flink.streaming.api.operators.StreamSourceContexts$NonTimestampContext.collectWithTimestamp(StreamSourceContexts.java:111)
at org.apache.flink.streaming.connectors.kafka.internals.AbstractFetcher.emitRecordWithTimestamp(AbstractFetcher.java:398)
at org.apache.flink.streaming.connectors.kafka.internal.Kafka010Fetcher.emitRecord(Kafka010Fetcher.java:89)
at org.apache.flink.streaming.connectors.kafka.internal.Kafka09Fetcher.runFetchLoop(Kafka09Fetcher.java:154)
at org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumerBase.run(FlinkKafkaConsumerBase.java:738)
at org.apache.flink.streaming.api.operators.StreamSource.run(StreamSource.java:87)
at org.apache.flink.streaming.api.operators.StreamSource.run(StreamSource.java:56)
at org.apache.flink.streaming.runtime.tasks.SourceStreamTask.run(SourceStreamTask.java:99)
at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:306)
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:703)
at java.lang.Thread.run(Thread.java:748)
堆栈跟踪不包含我的文件。我在代码中所做的是使用ProcessBuilder在每条消息中运行一个简单的Python文件
def initPythonProcess(age: String, salary: String): String = {
val pb = new ProcessBuilder("python", "/home/ubuntu/scripts/classifier_test.py", age, salary)
val p = pb.start()
val reader = new BufferedReader(new InputStreamReader(p.getInputStream))
return reader.readLine
}
def main(args: Array[String]): Unit = {
val properties = new Properties()
properties.setProperty("bootstrap.servers", "localhost:9092")
properties.setProperty("group.id", "test")
val env = StreamExecutionEnvironment.getExecutionEnvironment
val stream = env.addSource(new FlinkKafkaConsumer011[String]("test", new SimpleStringSchema(), properties))
stream.map(in => {
val values = in.split(",")
val res = initPythonProcess(values(0), values(1))
res
}).writeAsText("/home/ubuntu/out.txt")
env.execute("Buyer Options Classifier")
}