StreamingExamples.setStreamingLogLevels();
// Create the context with a 1 second batch size
SparkConf sparkConf = new SparkConf().setAppName("JavaNetworkWordCount");
JavaStreamingContext ssc = new JavaStreamingContext(sparkConf, new Duration(1000));
// Create a JavaReceiverInputDStream on target ip:port and count the
// words in input stream of \n delimited text (eg. generated by 'nc')
// Note that no duplication in storage level only for running locally.
// Replication necessary in distributed scenario for fault tolerance.
JavaReceiverInputDStream<String> lines = ssc.socketTextStream(
args[0], Integer.parseInt(args[1]), StorageLevels.MEMORY_AND_DISK_SER);
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();
ssc.start();
ssc.awaitTermination();
}