public static void main(String[] args) { if (args.length < 4) { System.err.println("Usage: JavaKafkaWordCount <zkQuorum> <group> <topics> <numThreads>"); System.exit(1); } StreamingExamples.setStreamingLogLevels(); // SparkConf sparkConf = new SparkConf().setAppName("JavaKafkaWordCount"); // sparkConf.setMaster("spark://60f81dc6426c:7077"); // SparkConf sparkConf = new // SparkConf().setAppName("JavaKafkaWordCount").setMaster("spark://60f81dc6426c:7077"); // Create the context with a 1 second batch size JavaStreamingContext jssc = new JavaStreamingContext("local[4]", "JavaKafkaWordCount", new Duration(2000)); int numThreads = Integer.parseInt(args[3]); Logger.getLogger("org").setLevel(Level.OFF); Logger.getLogger("akka").setLevel(Level.OFF); Map<String, Integer> topicMap = new HashMap<String, Integer>(); String[] topics = args[2].split(","); for (String topic : topics) { topicMap.put(topic, numThreads); } /* for(String t: topic) { topicMap.put(t, new Integer(3)); }*/ // NotSerializable notSerializable = new NotSerializable(); // JavaRDD<String> rdd = sc.textFile("/tmp/myfile"); // rdd.map(s -> notSerializable.doSomething(s)).collect(); JavaPairReceiverInputDStream<String, String> messages = KafkaUtils.createStream(jssc, args[0], args[1], topicMap); // JavaPairReceiverInputDStream<String, String> kafkaStream = // KafkaUtils.createStream(jssc, "localhost:2181","streamingContext", // topicMap); System.out.println("Connection !!!!"); /*JavaDStream<String> data = messages.map(new Function<Tuple2<String, String>, String>() { public String call(Tuple2<String, String> message) { return message._2(); } } );*/ JavaDStream<String> lines = messages.map( new Function<Tuple2<String, String>, String>() { @Override public String call(Tuple2<String, String> tuple2) { return tuple2._2(); } }); JavaDStream<String> words = lines.flatMap( new FlatMapFunction<String, String>() { @Override public Iterable<String> call(String x) { return Lists.newArrayList(SPACE.split(x)); } }); JavaPairDStream<String, Integer> wordCounts = words .mapToPair( new PairFunction<String, String, Integer>() { @Override public Tuple2<String, Integer> call(String s) { return new Tuple2<String, Integer>(s, 1); } }) .reduceByKey( new Function2<Integer, Integer, Integer>() { @Override public Integer call(Integer i1, Integer i2) { return i1 + i2; } }); wordCounts.print(); jssc.start(); jssc.awaitTermination(); }