Java Code Examples for org.apache.spark.streaming.api.java.JavaStreamingContext#checkpoint()

public static void main(String[] args) {
    SparkConf sparkConf = new SparkConf().setAppName("KafkaWordCount").setMaster("local[2]");
    JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(10000));
    //设置检查点
    streamingContext.checkpoint("HDFS URL");
    Map<String, Integer> topicThread = new HashMap<>(1);
    topicThread.put(TOPIC, THREAD);
    JavaPairInputDStream<String, String> dStream = KafkaUtils.createStream(streamingContext, HOST, GROP, topicThread);

    JavaDStream<String> words = dStream.flatMap((FlatMapFunction<Tuple2<String, String>, String>) stringStringTuple2 -> Arrays.asList(SPACE.split(stringStringTuple2._2)).iterator());

    //统计
    JavaPairDStream<String, Integer> result = words.mapToPair((PairFunction<String, String, Integer>) s -> new Tuple2<>(s, 1)).reduceByKey((Function2<Integer, Integer, Integer>) (v1, v2) -> v1 + v2);

    try {
        result.print();
        streamingContext.start();
        streamingContext.awaitTermination();
    } catch (InterruptedException e) {
        e.printStackTrace();
    }
}
 

public static void main(String[] args) {
    SparkConf sparkConf = new SparkConf().setAppName("window").setMaster("local[2]");
    JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(10));
    //检查点设置
    streamingContext.checkpoint("hdfs://localhost:9300");

    JavaDStream<String> dStream = streamingContext.socketTextStream("localhost", 8080);

    JavaDStream<String> winDstream = dStream.window(Durations.seconds(30), Durations.seconds(20));

    JavaDStream<Long> result = winDstream.count();

    try {
        streamingContext.start();
        streamingContext.awaitTermination();
    } catch (InterruptedException e) {
        e.printStackTrace();
    }
}
 

public static void main(String[] args) {
    SparkConf sparkConf = new SparkConf().setAppName("reduceByKeyAndWindow").setMaster("local[2]");
    JavaStreamingContext streamingContext = new JavaStreamingContext(sparkConf, Durations.seconds(10));
    //检查点设置
    streamingContext.checkpoint("hdfs://localhost:9300");
    //数据源
    JavaDStream<String> dStream = streamingContext.socketTextStream("localhost", 8080);

    JavaPairDStream<String, Long> ipPairDstream = dStream.mapToPair(new GetIp());

    JavaPairDStream<String, Long> result = ipPairDstream.reduceByKeyAndWindow(new AddLongs(),
            new SubtractLongs(), Durations.seconds(30), Durations.seconds(10));

    try {
        streamingContext.start();
        streamingContext.awaitTermination();
    } catch (InterruptedException e) {
        e.printStackTrace();
    }
}
 

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

        System.setProperty("hadoop.home.dir", HADOOP_HOME_DIR_VALUE);

        final SparkConf conf = new SparkConf()
                .setMaster(RUN_LOCAL_WITH_AVAILABLE_CORES)
                .setAppName(APPLICATION_NAME)
                .set("spark.mongodb.output.uri", MONGODB_OUTPUT_URI)
                .set("spark.streaming.kafka.consumer.cache.enabled", "false");

        final JavaStreamingContext streamingContext
                = new JavaStreamingContext(conf, new Duration(BATCH_DURATION_INTERVAL_MS));

        streamingContext.checkpoint(CHECKPOINT_FOLDER);

        final JavaInputDStream<ConsumerRecord<String, String>> meetupStream =
                KafkaUtils.createDirectStream(
                        streamingContext,
                        LocationStrategies.PreferConsistent(),
                        ConsumerStrategies.<String, String>Subscribe(TOPICS, KAFKA_CONSUMER_PROPERTIES)
                );
                
        // transformations, streaming algorithms, etc
        JavaDStream<Long> countStream  
            = meetupStream.countByWindow(
                 new Duration(WINDOW_LENGTH_MS), 
                 new Duration(SLIDING_INTERVAL_MS));        

        countStream.foreachRDD((JavaRDD<Long> countRDD) -> {                
            MongoSpark.save(        
                    countRDD.map(
                        r -> Document.parse("{\"rsvps_count\":\"" + String.valueOf(r) + "\"}")
                    )
            );            
        });
        
        // some time later, after outputs have completed
        meetupStream.foreachRDD((JavaRDD<ConsumerRecord<String, String>> meetupRDD) -> {        
            OffsetRange[] offsetRanges = ((HasOffsetRanges) meetupRDD.rdd()).offsetRanges();            

            ((CanCommitOffsets) meetupStream.inputDStream())
                .commitAsync(offsetRanges, new MeetupOffsetCommitCallback());
        });
        
        streamingContext.start();
        streamingContext.awaitTermination();    
    }
 

private void checkpoint(JavaStreamingContext jssc, CheckpointDir checkpointDir) {
  Path rootCheckpointPath = checkpointDir.getRootCheckpointDir();
  Path sparkCheckpointPath = checkpointDir.getSparkCheckpointDir();
  Path beamCheckpointPath = checkpointDir.getBeamCheckpointDir();

  try {
    FileSystem fileSystem =
        rootCheckpointPath.getFileSystem(jssc.sparkContext().hadoopConfiguration());
    if (!fileSystem.exists(rootCheckpointPath)) {
      fileSystem.mkdirs(rootCheckpointPath);
    }
    if (!fileSystem.exists(sparkCheckpointPath)) {
      fileSystem.mkdirs(sparkCheckpointPath);
    }
    if (!fileSystem.exists(beamCheckpointPath)) {
      fileSystem.mkdirs(beamCheckpointPath);
    }
  } catch (IOException e) {
    throw new RuntimeException("Failed to create checkpoint dir", e);
  }

  jssc.checkpoint(sparkCheckpointPath.toString());
}
 

@Override
public void setup() {
	// Create a StreamingContext with a SparkConf configuration
	SparkConf sparkConf = new SparkConf(false)
			.setAppName("JaiSpark")
			.setSparkHome("target/sparkhome")
			.setMaster("local")
			.set("spark.executor.memory", "128m")
			.set("spark.local.dir",
					new File("target/sparkhome/tmp").getAbsolutePath())
			.set("spark.cores.max", "2").set("spark.akka.threads", "2")
			.set("spark.akka.timeout", "60").set("spark.logConf", "true")
			.set("spark.cleaner.delay", "3700")
			.set("spark.cleaner.ttl", "86400")
			.set("spark.shuffle.spill", "false")
			.set("spark.driver.host", "localhost")
			.set("spark.driver.port", "43214");
	jssc = new JavaStreamingContext(sparkConf, new Duration(5000));

	String checkpointDir = hadoopClusterService.getHDFSUri()
			+ "/sparkcheckpoint";
	jssc.checkpoint(checkpointDir);
	startFlumeStream();
}
 

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;
}
 

public static void main(String[] args) {
   	//Window Specific property if Hadoop is not instaalled or HADOOP_HOME is not set
	 System.setProperty("hadoop.home.dir", "E:\\hadoop");
   	//Logger rootLogger = LogManager.getRootLogger();
  		//rootLogger.setLevel(Level.WARN); 
       SparkConf conf = new SparkConf().setAppName("KafkaExample").setMaster("local[*]");
       
    
       JavaSparkContext sc = new JavaSparkContext(conf);
       JavaStreamingContext streamingContext = new JavaStreamingContext(sc, Durations.minutes(2));
       streamingContext.checkpoint("E:\\hadoop\\checkpoint");
       Logger rootLogger = LogManager.getRootLogger();
  		rootLogger.setLevel(Level.WARN); 
  		
  	 List<Tuple2<String, Integer>> tuples = Arrays.asList(new Tuple2<>("hello", 10), new Tuple2<>("world", 10));
    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 );
   
    wordCounts.print();
    wordCounts.window(Durations.minutes(8)).countByValue()
      .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
    wordCounts.window(Durations.minutes(8),Durations.minutes(2)).countByValue()
      .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
    wordCounts.window(Durations.minutes(12),Durations.minutes(8)).countByValue()
      .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
    wordCounts.window(Durations.minutes(2),Durations.minutes(2)).countByValue()
      .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
    wordCounts.window(Durations.minutes(12),Durations.minutes(12)).countByValue()
      .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
      
    //comment these two operation to make it run
    wordCounts.window(Durations.minutes(5),Durations.minutes(2)).countByValue()
      .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
    wordCounts.window(Durations.minutes(10),Durations.minutes(1)).countByValue()
      .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
      
       streamingContext.start();
       try {
		streamingContext.awaitTermination();
	} catch (InterruptedException e) {
		// TODO Auto-generated catch block
		e.printStackTrace();
	}
}
 

public static void main(String[] args) {
  	//Window Specific property if Hadoop is not instaalled or HADOOP_HOME is not set
 System.setProperty("hadoop.home.dir", "E:\\hadoop");
  	//Logger rootLogger = LogManager.getRootLogger();
 		//rootLogger.setLevel(Level.WARN); 
      SparkConf conf = new SparkConf().setAppName("KafkaExample").setMaster("local[*]");    
      JavaSparkContext sc = new JavaSparkContext(conf);
      JavaStreamingContext streamingContext = new JavaStreamingContext(sc, Durations.minutes(2));
      streamingContext.checkpoint("E:\\hadoop\\checkpoint");
      Logger rootLogger = LogManager.getRootLogger();
 		rootLogger.setLevel(Level.WARN); 
      Map<String, Object> kafkaParams = new HashMap<>();
      kafkaParams.put("bootstrap.servers", "10.0.75.1:9092");
      kafkaParams.put("key.deserializer", StringDeserializer.class);
      kafkaParams.put("value.deserializer", StringDeserializer.class);
      kafkaParams.put("group.id", "use_a_separate_group_id_for_each_strea");
      kafkaParams.put("auto.offset.reset", "latest");
     // kafkaParams.put("enable.auto.commit", false);

      Collection<String> topics = Arrays.asList("mytopic", "anothertopic");

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

      JavaPairDStream<String, String> pairRDD = stream.mapToPair(record-> new Tuple2<>(record.key(), record.value()));
     
      pairRDD.foreachRDD(pRDD-> { pRDD.foreach(tuple-> System.out.println(new Date()+" :: Kafka msg key ::"+tuple._1() +" the val is ::"+tuple._2()));});
     
      JavaDStream<String> tweetRDD = pairRDD.map(x-> x._2()).map(new TweetText());
      
      tweetRDD.foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" :: "+x)));
      
     JavaDStream<String> hashtagRDD = tweetRDD.flatMap(twt-> Arrays.stream(twt.split(" ")).filter(str-> str.contains("#")).collect(Collectors.toList()).iterator() );
 
      hashtagRDD.foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(x)));
      
      JavaPairDStream<String, Long> cntByVal = hashtagRDD.countByValue();
      
      cntByVal.foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The count tag is ::"+x._1() +" and the val is ::"+x._2())));
      
     /* hashtagRDD.window(Durations.seconds(60), Durations.seconds(30))
                .countByValue()
               .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
      
     hashtagRDD.countByValueAndWindow(Durations.seconds(60), Durations.seconds(30))
               .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println("The window&count tag is ::"+x._1() +" and the val is ::"+x._2())));
      */
     hashtagRDD.window(Durations.minutes(8)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     hashtagRDD.window(Durations.minutes(8),Durations.minutes(2)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     hashtagRDD.window(Durations.minutes(12),Durations.minutes(8)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     hashtagRDD.window(Durations.minutes(2),Durations.minutes(2)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     hashtagRDD.window(Durations.minutes(12),Durations.minutes(12)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));
     
     /*hashtagRDD.window(Durations.minutes(5),Durations.minutes(2)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));*/
     /* hashtagRDD.window(Durations.minutes(10),Durations.minutes(1)).countByValue()
     .foreachRDD(tRDD -> tRDD.foreach(x->System.out.println(new Date()+" ::The window count tag is ::"+x._1() +" and the val is ::"+x._2())));*/
     
      streamingContext.start();
      try {
	streamingContext.awaitTermination();
} catch (InterruptedException e) {
	// TODO Auto-generated catch block
	e.printStackTrace();
}
  }
 

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 != 3) {
    System.err.println("Usage: JavaStreamingTestExample " +
      "<dataDir> <batchDuration> <numBatchesTimeout>");
      System.exit(1);
  }

  String dataDir = args[0];
  Duration batchDuration = Seconds.apply(Long.parseLong(args[1]));
  int numBatchesTimeout = Integer.parseInt(args[2]);

  SparkConf conf = new SparkConf().setMaster("local").setAppName("StreamingTestExample");
  JavaStreamingContext ssc = new JavaStreamingContext(conf, batchDuration);

  ssc.checkpoint(Utils.createTempDir(System.getProperty("java.io.tmpdir"), "spark").toString());

  // $example on$
  JavaDStream<BinarySample> data = ssc.textFileStream(dataDir).map(
    new Function<String, BinarySample>() {
      @Override
      public BinarySample call(String line) {
        String[] ts = line.split(",");
        boolean label = Boolean.parseBoolean(ts[0]);
        double value = Double.parseDouble(ts[1]);
        return new BinarySample(label, value);
      }
    });

  StreamingTest streamingTest = new StreamingTest()
    .setPeacePeriod(0)
    .setWindowSize(0)
    .setTestMethod("welch");

  JavaDStream<StreamingTestResult> out = streamingTest.registerStream(data);
  out.print();
  // $example off$

  // Stop processing if test becomes significant or we time out
  timeoutCounter = numBatchesTimeout;

  out.foreachRDD(new VoidFunction<JavaRDD<StreamingTestResult>>() {
    @Override
    public void call(JavaRDD<StreamingTestResult> rdd) {
      timeoutCounter -= 1;

      boolean anySignificant = !rdd.filter(new Function<StreamingTestResult, Boolean>() {
        @Override
        public Boolean call(StreamingTestResult v) {
          return v.pValue() < 0.05;
        }
      }).isEmpty();

      if (timeoutCounter <= 0 || anySignificant) {
        rdd.context().stop();
      }
    }
  });

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

private static JavaStreamingContext createContext(String ip,
                                                  int port,
                                                  String checkpointDirectory,
                                                  String outputPath) {

  // If you do not see this printed, that means the StreamingContext has been loaded
  // from the new checkpoint
  System.out.println("Creating new context");
  final File outputFile = new File(outputPath);
  if (outputFile.exists()) {
    outputFile.delete();
  }
  SparkConf sparkConf = new SparkConf().setAppName("JavaRecoverableNetworkWordCount");
  // Create the context with a 1 second batch size
  JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, Durations.seconds(1));
  ssc.checkpoint(checkpointDirectory);

  // Create a socket stream on target ip:port and count the
  // words in input stream of \n delimited text (eg. generated by 'nc')
  JavaReceiverInputDStream<String> lines = ssc.socketTextStream(ip, port);
  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> wordCounts = words.mapToPair(
    new PairFunction<String, String, Integer>() {
      @Override
      public Tuple2<String, Integer> call(String s) {
        return new Tuple2<>(s, 1);
      }
    }).reduceByKey(new Function2<Integer, Integer, Integer>() {
      @Override
      public Integer call(Integer i1, Integer i2) {
        return i1 + i2;
      }
    });

  wordCounts.foreachRDD(new VoidFunction2<JavaPairRDD<String, Integer>, Time>() {
    @Override
    public void call(JavaPairRDD<String, Integer> rdd, Time time) throws IOException {
      // Get or register the blacklist Broadcast
      final Broadcast<List<String>> blacklist =
          JavaWordBlacklist.getInstance(new JavaSparkContext(rdd.context()));
      // Get or register the droppedWordsCounter Accumulator
      final LongAccumulator droppedWordsCounter =
          JavaDroppedWordsCounter.getInstance(new JavaSparkContext(rdd.context()));
      // Use blacklist to drop words and use droppedWordsCounter to count them
      String counts = rdd.filter(new Function<Tuple2<String, Integer>, Boolean>() {
        @Override
        public Boolean call(Tuple2<String, Integer> wordCount) {
          if (blacklist.value().contains(wordCount._1())) {
            droppedWordsCounter.add(wordCount._2());
            return false;
          } else {
            return true;
          }
        }
      }).collect().toString();
      String output = "Counts at time " + time + " " + counts;
      System.out.println(output);
      System.out.println("Dropped " + droppedWordsCounter.value() + " word(s) totally");
      System.out.println("Appending to " + outputFile.getAbsolutePath());
      Files.append(output + "\n", outputFile, Charset.defaultCharset());
    }
  });

  return ssc;
}
 

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 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();
    }