Java JavaReceiverInputDStream.map方法代码示例

import org.apache.spark.streaming.api.java.JavaReceiverInputDStream; //导入方法依赖的package包/类
private static JavaDStream<String> createDStream(JavaStreamingContext javaStreamingContext, String hostName, int port) {
        
        JavaReceiverInputDStream<SparkFlumeEvent> flumeEventStream = FlumeUtils.createStream(javaStreamingContext, hostName, port);
        
        // Set different storage level 
//        flumeEventStream.persist(StorageLevel.MEMORY_AND_DISK_SER());
        
        JavaDStream<String> dStream = flumeEventStream.map(new Function<SparkFlumeEvent, String>() {

            @Override
            public String call(SparkFlumeEvent sparkFlumeEvent) throws Exception {

                byte[] bodyArray = sparkFlumeEvent.event().getBody().array();
                String logTxt = new String(bodyArray, "UTF-8");
                logger.info(logTxt);

                return logTxt;
            }
        });
        // dStream.print();
        
        return dStream;
    }
 

import org.apache.spark.streaming.api.java.JavaReceiverInputDStream; //导入方法依赖的package包/类
public static void main(String[] args) throws InterruptedException {

		System.setProperty("hadoop.home.dir", "C:\\softwares\\Winutils");

		SparkSession sparkSession = SparkSession.builder().master("local[*]").appName("Stateful Streaming Example")
				.config("spark.sql.warehouse.dir", "file:////C:/Users/sgulati/spark-warehouse").getOrCreate();

		JavaStreamingContext jssc= new JavaStreamingContext(new JavaSparkContext(sparkSession.sparkContext()),
				Durations.milliseconds(1000));
		JavaReceiverInputDStream<String> inStream = jssc.socketTextStream("10.204.136.223", 9999);
		jssc.checkpoint("C:\\Users\\sgulati\\spark-checkpoint");

		JavaDStream<FlightDetails> flightDetailsStream = inStream.map(x -> {
			ObjectMapper mapper = new ObjectMapper();
			return mapper.readValue(x, FlightDetails.class);
		});
		
		

		JavaPairDStream<String, FlightDetails> flightDetailsPairStream = flightDetailsStream
				.mapToPair(f -> new Tuple2<String, FlightDetails>(f.getFlightId(), f));

		Function3<String, Optional<FlightDetails>, State<List<FlightDetails>>, Tuple2<String, Double>> mappingFunc = (
				flightId, curFlightDetail, state) -> {
			List<FlightDetails> details = state.exists() ? state.get() : new ArrayList<>();

			boolean isLanded = false;

			if (curFlightDetail.isPresent()) {
				details.add(curFlightDetail.get());
				if (curFlightDetail.get().isLanded()) {
					isLanded = true;
				}
			}
			Double avgSpeed = details.stream().mapToDouble(f -> f.getTemperature()).average().orElse(0.0);

			if (isLanded) {
				state.remove();
			} else {
				state.update(details);
			}
			return new Tuple2<String, Double>(flightId, avgSpeed);
		};

		JavaMapWithStateDStream<String, FlightDetails, List<FlightDetails>, Tuple2<String, Double>> streamWithState = flightDetailsPairStream
				.mapWithState(StateSpec.function(mappingFunc).timeout(Durations.minutes(5)));
		
		streamWithState.print();
		jssc.start();
		jssc.awaitTermination();
	}
 

import org.apache.spark.streaming.api.java.JavaReceiverInputDStream; //导入方法依赖的package包/类
public static void main(String s[]) {
	StreamNumberServer.startNumberGeneratorServer(9999);

	// Create a local StreamingContext with two working thread and batch interval of 1 second
	SparkConf conf = new SparkConf().setMaster("local[2]").setAppName("ConfigurableFilterApp");
	try (JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(1))) {
		
		
		JavaReceiverInputDStream<String> lines = jssc.socketTextStream("localhost", 9999);
		
		JavaDStream<SensorData> values = lines.map(line -> SensorData.fromString(line));
		
		values = values.map(new CfgFunction());
		
		values.print();
		
		jssc.start();              // Start the computation
		jssc.awaitTermination();   // Wait for the computation to terminate
	} 
}
 

import org.apache.spark.streaming.api.java.JavaReceiverInputDStream; //导入方法依赖的package包/类
public static void main(String[] args) throws InterruptedException {

		System.setProperty("hadoop.home.dir", "C:\\softwares\\Winutils");

		SparkSession sparkSession = SparkSession.builder().master("local[*]").appName("stateless Streaming Example")
				.config("spark.sql.warehouse.dir", "file:////C:/Users/sgulati/spark-warehouse").getOrCreate();

		JavaStreamingContext jssc = new JavaStreamingContext(new JavaSparkContext(sparkSession.sparkContext()),
				Durations.milliseconds(1000));
		JavaReceiverInputDStream<String> inStream = jssc.socketTextStream("10.204.136.223", 9999);

		JavaDStream<FlightDetails> flightDetailsStream = inStream.map(x -> {
			ObjectMapper mapper = new ObjectMapper();
			return mapper.readValue(x, FlightDetails.class);
		});
		
		
		
		//flightDetailsStream.print();
		
		//flightDetailsStream.foreachRDD((VoidFunction<JavaRDD<FlightDetails>>) rdd -> rdd.saveAsTextFile("hdfs://namenode:port/path"));
		
	   JavaDStream<FlightDetails> window = flightDetailsStream.window(Durations.minutes(5),Durations.minutes(1));
		
	    JavaPairDStream<String, Double> transfomedWindow = window.mapToPair(f->new Tuple2<String,Double>(f.getFlightId(),f.getTemperature())).
	    mapValues(t->new Tuple2<Double,Integer>(t,1))
	    .reduceByKey((t1, t2) -> new Tuple2<Double, Integer>(t1._1()+t2._1(), t1._2()+t2._2())).mapValues(t -> t._1()/t._2());
	    transfomedWindow.cache();
	    transfomedWindow.print();
	    
		jssc.start();
		jssc.awaitTermination();
	}