org.apache.spark.streaming.StateSpec Java Examples

private JavaDStream<IoTData> getVehicleNotProcessed(JavaDStream<IoTData> nonFilteredIotDataStream) {
    //We need filtered stream for total and traffic data calculation
    JavaPairDStream<String, IoTData> iotDataPairStream = nonFilteredIotDataStream
            .mapToPair(iot -> new Tuple2<>(iot.getVehicleId(), iot))
            .reduceByKey((a, b) -> a);

    // Check vehicle Id is already processed
    JavaMapWithStateDStream<String, IoTData, Boolean, Tuple2<IoTData, Boolean>> iotDStreamWithStatePairs =
            iotDataPairStream
                    .mapWithState(
                            StateSpec.function(processedVehicleFunc).timeout(Durations.seconds(3600))
                    );//maintain state for one hour

    // Filter processed vehicle ids and keep un-processed
    JavaDStream<Tuple2<IoTData, Boolean>> filteredIotDStreams = iotDStreamWithStatePairs
            .filter(tuple -> tuple._2.equals(Boolean.FALSE));

    // Get stream of IoTdata
    return filteredIotDStreams.map(tuple -> tuple._1);
}
 

/**
 * Method to get total traffic counts of different type of vehicles for each route.
 *
 * @param filteredIotDataStream IoT data stream
 */
public void processTotalTrafficData(JavaDStream<IoTData> filteredIotDataStream) {

    // We need to get count of vehicle group by routeId and vehicleType
    JavaPairDStream<AggregateKey, Long> countDStreamPair = filteredIotDataStream
            .mapToPair(iot -> new Tuple2<>(new AggregateKey(iot.getRouteId(), iot.getVehicleType()), 1L))
            .reduceByKey((a, b) -> a + b);

    // Need to keep state for total count
    StateSpec<AggregateKey, Long, Long, Tuple2<AggregateKey, Long>> stateSpec =
            StateSpec.function(totalSumFunc).timeout(Durations.seconds(3600));

    JavaMapWithStateDStream<AggregateKey, Long, Long, Tuple2<AggregateKey, Long>> countDStreamWithStatePair =
            countDStreamPair.mapWithState(stateSpec);//maintain state for one hour

    // Transform to dstream of TrafficData
    JavaDStream<Tuple2<AggregateKey, Long>> countDStream = countDStreamWithStatePair.map(tuple2 -> tuple2);
    JavaDStream<TotalTrafficData> trafficDStream = countDStream.map(totalTrafficDataFunc);

    // Map Cassandra table column
    Map<String, String> columnNameMappings = new HashMap<String, String>();
    columnNameMappings.put("routeId", "routeid");
    columnNameMappings.put("vehicleType", "vehicletype");
    columnNameMappings.put("totalCount", "totalcount");
    columnNameMappings.put("timeStamp", "timestamp");
    columnNameMappings.put("recordDate", "recorddate");

    // call CassandraStreamingJavaUtil function to save in DB
    javaFunctions(trafficDStream).writerBuilder(
            "traffickeyspace",
            "total_traffic",
            CassandraJavaUtil.mapToRow(TotalTrafficData.class, columnNameMappings)
    ).saveToCassandra();
}
 

public static void main(String[] args) throws Exception {
 System.setProperty("hadoop.home.dir", "E:\\hadoop");

   SparkConf sparkConf = new SparkConf().setAppName("WordCountSocketEx").setMaster("local[*]");
   JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(1));
   streamingContext.checkpoint("E:\\hadoop\\checkpoint");
// Initial state RDD input to mapWithState
   @SuppressWarnings("unchecked")
   List<Tuple2<String, Integer>> tuples =Arrays.asList(new Tuple2<>("hello", 1), new Tuple2<>("world", 1));
   JavaPairRDD<String, Integer> initialRDD = streamingContext.sparkContext().parallelizePairs(tuples);
   
   JavaReceiverInputDStream<String> StreamingLines = streamingContext.socketTextStream( "10.0.75.1", Integer.parseInt("9000"), StorageLevels.MEMORY_AND_DISK_SER);
   
   JavaDStream<String> words = StreamingLines.flatMap( str -> Arrays.asList(str.split(" ")).iterator() );
  
   JavaPairDStream<String, Integer> wordCounts = words.mapToPair(str-> new Tuple2<>(str, 1)).reduceByKey((count1,count2) ->count1+count2 );
  


  // Update the cumulative count function
  Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>> mappingFunc =
      new Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>>() {
        @Override
        public Tuple2<String, Integer> call(String word, Optional<Integer> one,
            State<Integer> state) {
          int sum = one.orElse(0) + (state.exists() ? state.get() : 0);
          Tuple2<String, Integer> output = new Tuple2<>(word, sum);
          state.update(sum);
          return output;
        }
      };

  // DStream made of get cumulative counts that get updated in every batch
  JavaMapWithStateDStream<String, Integer, Integer, Tuple2<String, Integer>> stateDstream = wordCounts.mapWithState(StateSpec.function(mappingFunc).initialState(initialRDD));

  stateDstream.print();
  streamingContext.start();
  streamingContext.awaitTermination();
}
 

protected static JavaStreamingContext createContext(String ip, int port, String checkpointDirectory) {
	SparkConf sparkConf = new SparkConf().setAppName("WordCountRecoverableEx").setMaster("local[*]");
	JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(1));
	streamingContext.checkpoint(checkpointDirectory);
	// Initial state RDD input to mapWithState
	@SuppressWarnings("unchecked")
	List<Tuple2<String, Integer>> tuples = Arrays.asList(new Tuple2<>("hello", 1), new Tuple2<>("world", 1));
	JavaPairRDD<String, Integer> initialRDD = streamingContext.sparkContext().parallelizePairs(tuples);

	JavaReceiverInputDStream<String> StreamingLines = streamingContext.socketTextStream(ip,port, StorageLevels.MEMORY_AND_DISK_SER);

	JavaDStream<String> words = StreamingLines.flatMap(str -> Arrays.asList(str.split(" ")).iterator());

	JavaPairDStream<String, Integer> wordCounts = words.mapToPair(str -> new Tuple2<>(str, 1))
			.reduceByKey((count1, count2) -> count1 + count2);

	// Update the cumulative count function
	Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>> mappingFunc = new Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>>() {
		@Override
		public Tuple2<String, Integer> call(String word, Optional<Integer> one, State<Integer> state) {
			int sum = one.orElse(0) + (state.exists() ? state.get() : 0);
			Tuple2<String, Integer> output = new Tuple2<>(word, sum);
			state.update(sum);
			return output;
		}
	};

	// DStream made of get cumulative counts that get updated in every batch
	JavaMapWithStateDStream<String, Integer, Integer, Tuple2<String, Integer>> stateDstream = wordCounts
			.mapWithState(StateSpec.function(mappingFunc).initialState(initialRDD));

	stateDstream.print();
	return streamingContext;
}
 

/**
 * Method to get total traffic counts of different type of vehicles for each route.
 * 
 * @param filteredIotDataStream IoT data stream
 */
public void processTotalTrafficData(JavaDStream<IoTData> filteredIotDataStream) {

	// We need to get count of vehicle group by routeId and vehicleType
	JavaPairDStream<AggregateKey, Long> countDStreamPair = filteredIotDataStream
			.mapToPair(iot -> new Tuple2<>(new AggregateKey(iot.getRouteId(), iot.getVehicleType()), 1L))
			.reduceByKey((a, b) -> a + b);
	
	// Need to keep state for total count
	JavaMapWithStateDStream<AggregateKey, Long, Long, Tuple2<AggregateKey, Long>> countDStreamWithStatePair = countDStreamPair
			.mapWithState(StateSpec.function(totalSumFunc).timeout(Durations.seconds(3600)));//maintain state for one hour

	// Transform to dstream of TrafficData
	JavaDStream<Tuple2<AggregateKey, Long>> countDStream = countDStreamWithStatePair.map(tuple2 -> tuple2);
	JavaDStream<TotalTrafficData> trafficDStream = countDStream.map(totalTrafficDataFunc);

	// Map Cassandra table column
	Map<String, String> columnNameMappings = new HashMap<String, String>();
	columnNameMappings.put("routeId", "routeid");
	columnNameMappings.put("vehicleType", "vehicletype");
	columnNameMappings.put("totalCount", "totalcount");
	columnNameMappings.put("timeStamp", "timestamp");
	columnNameMappings.put("recordDate", "recorddate");

	// call CassandraStreamingJavaUtil function to save in DB
	javaFunctions(trafficDStream).writerBuilder("traffickeyspace", "total_traffic",
			CassandraJavaUtil.mapToRow(TotalTrafficData.class, columnNameMappings)).saveToCassandra();
}
 

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();
	}
 

public static void main(String[] args) throws Exception {
  if (args.length < 2) {
    System.err.println("Usage: JavaStatefulNetworkWordCount <hostname> <port>");
    System.exit(1);
  }

  StreamingExamples.setStreamingLogLevels();

  // Create the context with a 1 second batch size
  SparkConf sparkConf = new SparkConf().setAppName("JavaStatefulNetworkWordCount");
  JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1));
  ssc.checkpoint(".");

  // Initial state RDD input to mapWithState
  @SuppressWarnings("unchecked")
  List<Tuple2<String, Integer>> tuples =
      Arrays.asList(new Tuple2<>("hello", 1), new Tuple2<>("world", 1));
  JavaPairRDD<String, Integer> initialRDD = ssc.sparkContext().parallelizePairs(tuples);

  JavaReceiverInputDStream<String> lines = ssc.socketTextStream(
          args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER_2);

  JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
    @Override
    public Iterator<String> call(String x) {
      return Arrays.asList(SPACE.split(x)).iterator();
    }
  });

  JavaPairDStream<String, Integer> wordsDstream = words.mapToPair(
      new PairFunction<String, String, Integer>() {
        @Override
        public Tuple2<String, Integer> call(String s) {
          return new Tuple2<>(s, 1);
        }
      });

  // Update the cumulative count function
  Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>> mappingFunc =
      new Function3<String, Optional<Integer>, State<Integer>, Tuple2<String, Integer>>() {
        @Override
        public Tuple2<String, Integer> call(String word, Optional<Integer> one,
            State<Integer> state) {
          int sum = one.orElse(0) + (state.exists() ? state.get() : 0);
          Tuple2<String, Integer> output = new Tuple2<>(word, sum);
          state.update(sum);
          return output;
        }
      };

  // DStream made of get cumulative counts that get updated in every batch
  JavaMapWithStateDStream<String, Integer, Integer, Tuple2<String, Integer>> stateDstream =
      wordsDstream.mapWithState(StateSpec.function(mappingFunc).initialState(initialRDD));

  stateDstream.print();
  ssc.start();
  ssc.awaitTermination();
}
 

public static void main(String[] args) throws Exception {
 //read Spark and Cassandra properties and create SparkConf
 Properties prop = PropertyFileReader.readPropertyFile();		
 SparkConf conf = new SparkConf()
		 .setAppName(prop.getProperty("com.iot.app.spark.app.name"))
		 .setMaster(prop.getProperty("com.iot.app.spark.master"))
		 .set("spark.cassandra.connection.host", prop.getProperty("com.iot.app.cassandra.host"))
		 .set("spark.cassandra.connection.port", prop.getProperty("com.iot.app.cassandra.port"))
		 .set("spark.cassandra.connection.keep_alive_ms", prop.getProperty("com.iot.app.cassandra.keep_alive"));		 
 //batch interval of 5 seconds for incoming stream		 
 JavaStreamingContext jssc = new JavaStreamingContext(conf, Durations.seconds(5));	
 //add check point directory
 jssc.checkpoint(prop.getProperty("com.iot.app.spark.checkpoint.dir"));
 
 //read and set Kafka properties
 Map<String, String> kafkaParams = new HashMap<String, String>();
 kafkaParams.put("zookeeper.connect", prop.getProperty("com.iot.app.kafka.zookeeper"));
 kafkaParams.put("metadata.broker.list", prop.getProperty("com.iot.app.kafka.brokerlist"));
 String topic = prop.getProperty("com.iot.app.kafka.topic");
 Set<String> topicsSet = new HashSet<String>();
 topicsSet.add(topic);
 //create direct kafka stream
 JavaPairInputDStream<String, IoTData> directKafkaStream = KafkaUtils.createDirectStream(
	        jssc,
	        String.class,
	        IoTData.class,
	        StringDecoder.class,
	        IoTDataDecoder.class,
	        kafkaParams,
	        topicsSet
	    );
 logger.info("Starting Stream Processing");
 
 //We need non filtered stream for poi traffic data calculation
 JavaDStream<IoTData> nonFilteredIotDataStream = directKafkaStream.map(tuple -> tuple._2());
 
 //We need filtered stream for total and traffic data calculation
 JavaPairDStream<String,IoTData> iotDataPairStream = nonFilteredIotDataStream.mapToPair(iot -> new Tuple2<String,IoTData>(iot.getVehicleId(),iot)).reduceByKey((a, b) -> a );

 // Check vehicle Id is already processed
 JavaMapWithStateDStream<String, IoTData, Boolean, Tuple2<IoTData,Boolean>> iotDStreamWithStatePairs = iotDataPairStream
					.mapWithState(StateSpec.function(processedVehicleFunc).timeout(Durations.seconds(3600)));//maintain state for one hour

 // Filter processed vehicle ids and keep un-processed
 JavaDStream<Tuple2<IoTData,Boolean>> filteredIotDStreams = iotDStreamWithStatePairs.map(tuple2 -> tuple2)
					.filter(tuple -> tuple._2.equals(Boolean.FALSE));

 // Get stream of IoTdata
 JavaDStream<IoTData> filteredIotDataStream = filteredIotDStreams.map(tuple -> tuple._1);
 
 //cache stream as it is used in total and window based computation
 filteredIotDataStream.cache();
 	 
 //process data
 IoTTrafficDataProcessor iotTrafficProcessor = new IoTTrafficDataProcessor();
 iotTrafficProcessor.processTotalTrafficData(filteredIotDataStream);
 iotTrafficProcessor.processWindowTrafficData(filteredIotDataStream);

 //poi data
 POIData poiData = new POIData();
 poiData.setLatitude(33.877495);
 poiData.setLongitude(-95.50238);
 poiData.setRadius(30);//30 km
 
 //broadcast variables. We will monitor vehicles on Route 37 which are of type Truck
 Broadcast<Tuple3<POIData, String, String>> broadcastPOIValues = jssc.sparkContext().broadcast(new Tuple3<>(poiData,"Route-37","Truck"));
 //call method  to process stream
 iotTrafficProcessor.processPOIData(nonFilteredIotDataStream,broadcastPOIValues);
 
 //start context
 jssc.start();            
 jssc.awaitTermination();  
}
 

public static <T, CheckpointMarkT extends CheckpointMark> UnboundedDataset<T> read(
    JavaStreamingContext jssc,
    SerializablePipelineOptions rc,
    UnboundedSource<T, CheckpointMarkT> source,
    String stepName) {

  SparkPipelineOptions options = rc.get().as(SparkPipelineOptions.class);
  Long maxRecordsPerBatch = options.getMaxRecordsPerBatch();
  SourceDStream<T, CheckpointMarkT> sourceDStream =
      new SourceDStream<>(jssc.ssc(), source, rc, maxRecordsPerBatch);

  JavaPairInputDStream<Source<T>, CheckpointMarkT> inputDStream =
      JavaPairInputDStream$.MODULE$.fromInputDStream(
          sourceDStream,
          JavaSparkContext$.MODULE$.fakeClassTag(),
          JavaSparkContext$.MODULE$.fakeClassTag());

  // call mapWithState to read from a checkpointable sources.
  JavaMapWithStateDStream<
          Source<T>, CheckpointMarkT, Tuple2<byte[], Instant>, Tuple2<Iterable<byte[]>, Metadata>>
      mapWithStateDStream =
          inputDStream.mapWithState(
              StateSpec.function(
                      StateSpecFunctions.<T, CheckpointMarkT>mapSourceFunction(rc, stepName))
                  .numPartitions(sourceDStream.getNumPartitions()));

  // set checkpoint duration for read stream, if set.
  checkpointStream(mapWithStateDStream, options);

  // report the number of input elements for this InputDStream to the InputInfoTracker.
  int id = inputDStream.inputDStream().id();
  JavaDStream<Metadata> metadataDStream = mapWithStateDStream.map(new Tuple2MetadataFunction());

  // register ReadReportDStream to report information related to this read.
  new ReadReportDStream(metadataDStream.dstream(), id, getSourceName(source, id), stepName)
      .register();

  // output the actual (deserialized) stream.
  WindowedValue.FullWindowedValueCoder<T> coder =
      WindowedValue.FullWindowedValueCoder.of(
          source.getOutputCoder(), GlobalWindow.Coder.INSTANCE);
  JavaDStream<WindowedValue<T>> readUnboundedStream =
      mapWithStateDStream
          .flatMap(new Tuple2byteFlatMapFunction())
          .map(CoderHelpers.fromByteFunction(coder));
  return new UnboundedDataset<>(readUnboundedStream, Collections.singletonList(id));
}
 

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

        Logger.getLogger("org")
            .setLevel(Level.OFF);
        Logger.getLogger("akka")
            .setLevel(Level.OFF);

        Map<String, Object> kafkaParams = new HashMap<>();
        kafkaParams.put("bootstrap.servers", "localhost:9092");
        kafkaParams.put("key.deserializer", StringDeserializer.class);
        kafkaParams.put("value.deserializer", StringDeserializer.class);
        kafkaParams.put("group.id", "use_a_separate_group_id_for_each_stream");
        kafkaParams.put("auto.offset.reset", "latest");
        kafkaParams.put("enable.auto.commit", false);

        Collection<String> topics = Arrays.asList("messages");

        SparkConf sparkConf = new SparkConf();
        sparkConf.setMaster("local[2]");
        sparkConf.setAppName("WordCountingAppWithCheckpoint");
        sparkConf.set("spark.cassandra.connection.host", "127.0.0.1");

        JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(1));

        sparkContext = streamingContext.sparkContext();

        streamingContext.checkpoint("./.checkpoint");

        JavaInputDStream<ConsumerRecord<String, String>> messages = KafkaUtils.createDirectStream(streamingContext, LocationStrategies.PreferConsistent(), ConsumerStrategies.<String, String> Subscribe(topics, kafkaParams));

        JavaPairDStream<String, String> results = messages.mapToPair(record -> new Tuple2<>(record.key(), record.value()));

        JavaDStream<String> lines = results.map(tuple2 -> tuple2._2());

        JavaDStream<String> words = lines.flatMap(x -> Arrays.asList(x.split("\\s+"))
            .iterator());

        JavaPairDStream<String, Integer> wordCounts = words.mapToPair(s -> new Tuple2<>(s, 1))
            .reduceByKey((Function2<Integer, Integer, Integer>) (i1, i2) -> i1 + i2);

        JavaMapWithStateDStream<String, Integer, Integer, Tuple2<String, Integer>> cumulativeWordCounts = wordCounts.mapWithState(StateSpec.function((word, one, state) -> {
            int sum = one.orElse(0) + (state.exists() ? state.get() : 0);
            Tuple2<String, Integer> output = new Tuple2<>(word, sum);
            state.update(sum);
            return output;
        }));

        cumulativeWordCounts.foreachRDD(javaRdd -> {
            List<Tuple2<String, Integer>> wordCountList = javaRdd.collect();
            for (Tuple2<String, Integer> tuple : wordCountList) {
                List<Word> wordList = Arrays.asList(new Word(tuple._1, tuple._2));
                JavaRDD<Word> rdd = sparkContext.parallelize(wordList);
                javaFunctions(rdd).writerBuilder("vocabulary", "words", mapToRow(Word.class))
                    .saveToCassandra();
            }
        });

        streamingContext.start();
        streamingContext.awaitTermination();
    }