Spark实现简单的WordCount

public class WordCountTest {

	public static void main(String[] args) {
		SparkConf conf = new SparkConf().setAppName("WordCountTest").setMaster("local");
		JavaSparkContext sc = new JavaSparkContext(conf);
		
		JavaRDD<String> lines = sc.textFile("wordcount.txt");
		JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>(){

			private static final long serialVersionUID = 1L;

			public Iterable<String> call(String line) throws Exception {
				String[] words = line.split(" ");
				return Arrays.asList(words);
			}
			
		});


		JavaPairRDD<String, Integer> pairs = words.mapToPair(new PairFunction<String, String, Integer>() {

			private static final long serialVersionUID = 1L;

			public Tuple2<String, Integer> call(String word) throws Exception {
				return new Tuple2<String, Integer>(word, 1);
			}
			
		});
		JavaPairRDD<String, Integer> wcs = pairs.reduceByKey(new Function2<Integer, Integer, Integer>(){
            private static final long serialVersionUID = 1L;

            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        wcs.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> tuple2) throws Exception {
                System.out.println(tuple2);
            }
        });
		
		sc.close();
	}
}