Java SparkSession.sparkContext方法代码示例

import org.apache.spark.sql.SparkSession; //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.sql.SparkSession; //导入方法依赖的package包/类
public static void main(String[] args) {

		SparkSession sparkSession = SparkSession.builder().master("local").appName("My App")
				.config("spark.sql.warehouse.dir", "file:////C:/Users/sgulati/spark-warehouse").getOrCreate();

		JavaSparkContext jsc = new JavaSparkContext(sparkSession.sparkContext());

		JavaPairRDD<String, String> userIdToCityId = jsc.parallelizePairs(
				Arrays.asList(new Tuple2<String, String>("1", "101"), new Tuple2<String, String>("2", "102"),
						new Tuple2<String, String>("3", "107"), new Tuple2<String, String>("4", "103"),
						new Tuple2<String, String>("11", "101"), new Tuple2<String, String>("12", "102"),
						new Tuple2<String, String>("13", "107"), new Tuple2<String, String>("14", "103")));

		JavaPairRDD<String, String> cityIdToCityName = jsc.parallelizePairs(
				Arrays.asList(new Tuple2<String, String>("101", "India"), new Tuple2<String, String>("102", "UK"),
						new Tuple2<String, String>("103", "Germany"), new Tuple2<String, String>("107", "USA")));

		Broadcast<Map<String, String>> citiesBroadcasted = jsc.broadcast(cityIdToCityName.collectAsMap());

		JavaRDD<Tuple3<String, String, String>> joined = userIdToCityId.map(
				v1 -> new Tuple3<String, String, String>(v1._1(), v1._2(), citiesBroadcasted.value().get(v1._2())));

		System.out.println(joined.collect());

	}
 

import org.apache.spark.sql.SparkSession; //导入方法依赖的package包/类
/**
 * Pushes an "in_valueset" UDF that uses the given {@link BroadcastableValueSets} for its content.
 *
 * @param spark the spark session
 * @param valueSets the valuesets to use in the UDF
 */
public static synchronized void pushUdf(SparkSession spark, BroadcastableValueSets valueSets) {

  JavaSparkContext ctx = new JavaSparkContext(spark.sparkContext());

  Broadcast<BroadcastableValueSets> broadcast = ctx.broadcast(valueSets);

  spark.udf()
      .register("in_valueset",
          new InValuesetUdf(broadcast),
          DataTypes.BooleanType);

  // Push the broadcast variable
  valueSetStack.push(broadcast);
}
 

import org.apache.spark.sql.SparkSession; //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();
	}