Java Code Examples for org.apache.spark.streaming.api.java.JavaPairDStream#map()

/**
 * Method to get window traffic counts of different type of vehicles for each route.
 * Window duration = 30 seconds and Slide interval = 10 seconds
 * 
 * @param filteredIotDataStream IoT data stream
 */
public void processWindowTrafficData(JavaDStream<IoTData> filteredIotDataStream) {

	// reduce by key and window (30 sec window and 10 sec slide).
	JavaPairDStream<AggregateKey, Long> countDStreamPair = filteredIotDataStream
			.mapToPair(iot -> new Tuple2<>(new AggregateKey(iot.getRouteId(), iot.getVehicleType()), 1L))
			.reduceByKeyAndWindow((a, b) -> a + b, Durations.seconds(30), Durations.seconds(10));

	// Transform to dstream of TrafficData
	JavaDStream<WindowTrafficData> trafficDStream = countDStreamPair.map(windowTrafficDataFunc);

	// 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", "window_traffic",
			CassandraJavaUtil.mapToRow(WindowTrafficData.class, columnNameMappings)).saveToCassandra();
}
 

/**
 * Method to get window traffic counts of different type of vehicles for each route.
 * Window duration = 30 seconds and Slide interval = 10 seconds
 *
 * @param filteredIotDataStream IoT data stream
 */
public void processWindowTrafficData(JavaDStream<IoTData> filteredIotDataStream) {

    // reduce by key and window (30 sec window and 10 sec slide).
    JavaPairDStream<AggregateKey, Long> countDStreamPair = filteredIotDataStream
            .mapToPair(iot -> new Tuple2<>(
                    new AggregateKey(iot.getRouteId(), iot.getVehicleType()),
                    1L
            ))
            .reduceByKeyAndWindow((a, b) -> a + b,
                    Durations.seconds(30),
                    Durations.seconds(10)
            );

    // Transform to dstream of TrafficData
    JavaDStream<WindowTrafficData> trafficDStream = countDStreamPair.map(windowTrafficDataFunc);

    // 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",
            "window_traffic",
            CassandraJavaUtil.mapToRow(WindowTrafficData.class, columnNameMappings)
    ).saveToCassandra();
}
 

/**
 * Method to get the vehicles which are in radius of POI and their distance from POI.
 *
 * @param nonFilteredIotDataStream original IoT data stream
 * @param broadcastPOIValues       variable containing POI coordinates, route and vehicle types to monitor.
 */
public void processPOIData(
        JavaDStream<IoTData> nonFilteredIotDataStream,
        Broadcast<Tuple3<POIData, String, String>> broadcastPOIValues
) {

    // Filter by routeId,vehicleType and in POI range
    JavaDStream<IoTData> iotDataStreamFiltered = nonFilteredIotDataStream
            .filter(iot -> (iot.getRouteId().equals(broadcastPOIValues.value()._2())
                    && iot.getVehicleType().contains(broadcastPOIValues.value()._3())
                    && GeoDistanceCalculator.isInPOIRadius(Double.valueOf(iot.getLatitude()),
                    Double.valueOf(iot.getLongitude()), broadcastPOIValues.value()._1().getLatitude(),
                    broadcastPOIValues.value()._1().getLongitude(),
                    broadcastPOIValues.value()._1().getRadius())));

    // pair with poi
    JavaPairDStream<IoTData, POIData> poiDStreamPair = iotDataStreamFiltered.mapToPair(
            iot -> new Tuple2<>(iot, broadcastPOIValues.value()._1())
    );

    // Transform to dstream of POITrafficData
    JavaDStream<POITrafficData> trafficDStream = poiDStreamPair.map(poiTrafficDataFunc);

    // Map Cassandra table column
    Map<String, String> columnNameMappings = new HashMap<String, String>();
    columnNameMappings.put("vehicleId", "vehicleid");
    columnNameMappings.put("distance", "distance");
    columnNameMappings.put("vehicleType", "vehicletype");
    columnNameMappings.put("timeStamp", "timestamp");

    // call CassandraStreamingJavaUtil function to save in DB
    javaFunctions(trafficDStream)
            .writerBuilder(
                    "traffickeyspace",
                    "poi_traffic",
                    CassandraJavaUtil.mapToRow(POITrafficData.class, columnNameMappings)
            )
            .withConstantTTL(120)//keeping data for 2 minutes
            .saveToCassandra();
}
 

/**
 * Method to get the vehicles which are in radius of POI and their distance from POI.
 * 
 * @param nonFilteredIotDataStream original IoT data stream
 * @param broadcastPOIValues variable containing POI coordinates, route and vehicle types to monitor.
 */
public void processPOIData(JavaDStream<IoTData> nonFilteredIotDataStream,Broadcast<Tuple3<POIData, String, String>> broadcastPOIValues) {
	 
	// Filter by routeId,vehicleType and in POI range
	JavaDStream<IoTData> iotDataStreamFiltered = nonFilteredIotDataStream
			.filter(iot -> (iot.getRouteId().equals(broadcastPOIValues.value()._2())
					&& iot.getVehicleType().contains(broadcastPOIValues.value()._3())
					&& GeoDistanceCalculator.isInPOIRadius(Double.valueOf(iot.getLatitude()),
							Double.valueOf(iot.getLongitude()), broadcastPOIValues.value()._1().getLatitude(),
							broadcastPOIValues.value()._1().getLongitude(),
							broadcastPOIValues.value()._1().getRadius())));

	// pair with poi
	JavaPairDStream<IoTData, POIData> poiDStreamPair = iotDataStreamFiltered
			.mapToPair(iot -> new Tuple2<>(iot, broadcastPOIValues.value()._1()));

	// Transform to dstream of POITrafficData
	JavaDStream<POITrafficData> trafficDStream = poiDStreamPair.map(poiTrafficDataFunc);

	// Map Cassandra table column
	Map<String, String> columnNameMappings = new HashMap<String, String>();
	columnNameMappings.put("vehicleId", "vehicleid");
	columnNameMappings.put("distance", "distance");
	columnNameMappings.put("vehicleType", "vehicletype");
	columnNameMappings.put("timeStamp", "timestamp");

	// call CassandraStreamingJavaUtil function to save in DB
	javaFunctions(trafficDStream)
			.writerBuilder("traffickeyspace", "poi_traffic",CassandraJavaUtil.mapToRow(POITrafficData.class, columnNameMappings))
			.withConstantTTL(120)//keeping data for 2 minutes
			.saveToCassandra();
}
 

private JavaDStream<HeatMapData> getHeatMap(JavaPairDStream<Coordinate, Integer> tuples) throws IOException {
    return tuples.map(tuple -> {
        Coordinate coordinate = tuple._1();
        return new HeatMapData(coordinate.getLatitude(), coordinate.getLongitude(), tuple._2(), new Date());
    });
}
 

/** Transform a pair stream into a value stream. */
public static <T1, T2> JavaDStream<T2> dStreamValues(JavaPairDStream<T1, T2> pairDStream) {
  return pairDStream.map(Tuple2::_2);
}
 

private void configureActionContext(JavaStreamingContext context) {
    Map<String, Integer> baseTopicMap = new HashMap<>();


    String topicName = InternalTopic.TOPIC_ACTION.getTopicName();
    if (configurationContext.isClusteringEnabled() && configurationContext.getGroupId()!=null){
        topicName = topicName.concat("_").concat(configurationContext.getGroupId());
    }
    baseTopicMap.put(topicName, 1);

    kafkaTopicService.createTopicIfNotExist(topicName, configurationContext.getKafkaReplicationFactor(),
            configurationContext.getKafkaPartitions());

    HashMap<String, String> kafkaParams = new HashMap<>();
    kafkaParams.put("zookeeper.connect", configurationContext.getZookeeperHostsQuorumWithPath());
    kafkaParams.put("group.id", configurationContext.getGroupId());
    /*
    groupId must be the cluster groupId. Kafka assigns each partition of a topic to one, and one only, consumer of
    the group.
    Decision topics has only one partition (by default), so if we have two o more decision instances (consumers) reading the
    same topic with the same groupId, only one instance will be able to read from the topic
    */
    JavaPairDStream<String, byte[]> messages = KafkaUtils.createStream(context, String.class, byte[].class,
            kafka.serializer.StringDecoder.class, kafka.serializer.DefaultDecoder.class, kafkaParams, baseTopicMap,
            StorageLevel.MEMORY_AND_DISK_SER());

    AvroDeserializeMessageFunction avroDeserializeMessageFunction = new AvroDeserializeMessageFunction();
    JavaDStream<StratioStreamingMessage>  parsedDataDstream = messages.map(avroDeserializeMessageFunction);

    JavaPairDStream<StreamAction, StratioStreamingMessage> pairedDataDstream = parsedDataDstream
            .mapPartitionsToPair(new PairDataFunction());

    JavaPairDStream<StreamAction, Iterable<StratioStreamingMessage>> groupedDataDstream = pairedDataDstream
            .groupByKey();

    groupedDataDstream.persist(StorageLevel.MEMORY_AND_DISK_SER());

    try {

        SaveToCassandraActionExecutionFunction saveToCassandraActionExecutionFunction = new SaveToCassandraActionExecutionFunction(configurationContext.getCassandraHostsQuorum(),
                configurationContext.getCassandraPort(), configurationContext.getCassandraMaxBatchSize(),
                configurationContext.getCassandraBatchType(), saveToCassandraOperationsService);
        if (saveToCassandraActionExecutionFunction.check()) {
            log.info("Cassandra is configured properly");
            groupedDataDstream.filter(new FilterDataFunction(StreamAction.SAVE_TO_CASSANDRA)).foreachRDD(
                    saveToCassandraActionExecutionFunction);
        } else {
            log.warn("Cassandra is NOT configured properly");
        }

        SaveToMongoActionExecutionFunction saveToMongoActionExecutionFunction = new SaveToMongoActionExecutionFunction(configurationContext.getMongoHosts(),
                configurationContext.getMongoUsername(), configurationContext
                .getMongoPassword(), configurationContext.getMongoMaxBatchSize(), mongoClient, mongoDB);
        if (saveToMongoActionExecutionFunction.check()) {
            log.info("MongoDB is configured properly");
            groupedDataDstream.filter(new FilterDataFunction(StreamAction.SAVE_TO_MONGO)).foreachRDD(
                    saveToMongoActionExecutionFunction);
        } else {
            log.warn("MongoDB is NOT configured properly");
        }

        SaveToElasticSearchActionExecutionFunction saveToElasticSearchActionExecutionFunction = new SaveToElasticSearchActionExecutionFunction(configurationContext.getElasticSearchHosts(),
                configurationContext.getElasticSearchClusterName(), configurationContext
                .getElasticSearchMaxBatchSize(), elasticsearchClient);
        if (saveToElasticSearchActionExecutionFunction.check()) {
            log.info("ElasticSearch is configured properly");
            groupedDataDstream.filter(new FilterDataFunction(StreamAction.SAVE_TO_ELASTICSEARCH)).foreachRDD(saveToElasticSearchActionExecutionFunction);
        } else {
            log.warn("ElasticSearch is NOT configured properly");
        }

        SaveToSolrActionExecutionFunction saveToSolrActionExecutionFunction = new
                SaveToSolrActionExecutionFunction(configurationContext.getSolrHost(), configurationContext
                .getSolrCloudZkHost(),
                configurationContext.getSolrCloud(),
                configurationContext.getSolrDataDir(), configurationContext.getSolrMaxBatchSize(), solrOperationsService);
        if (saveToSolrActionExecutionFunction.check()) {
            log.info("Solr is configured properly");
            groupedDataDstream.filter(new FilterDataFunction(StreamAction.SAVE_TO_SOLR)).foreachRDD(
                    saveToSolrActionExecutionFunction);
        } else {
            log.warn("Solr is NOT configured properly");
        }

        groupedDataDstream.filter(new FilterDataFunction(StreamAction.LISTEN)).foreachRDD(
                new SendToKafkaActionExecutionFunction(configurationContext.getKafkaHostsQuorum()));
    } catch (Exception e) {
        e.printStackTrace();
    }

}
 

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();
    }