Spark Java WordCount

package com.xzdream;

import com.google.common.base.Splitter;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.api.java.function.VoidFunction;
import scala.Tuple2;

import java.util.Arrays;
import java.util.Iterator;

public class WordCount {
    public static void main(String[] args) {
        SparkConf sparkConf = new SparkConf().setAppName("WordCount").setMaster("local");
        JavaSparkContext sc = new JavaSparkContext(sparkConf);
        JavaRDD<String> lines = sc.textFile("file:/Users/zhudechao/gitee/bigdata/xzdream_spark/input/a.txt");
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {

            @Override
            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.split(" ")).iterator();
            }
        });

        JavaPairRDD<String,Integer> pairRDD = words.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String word) throws Exception {
                return new Tuple2<String, Integer>(word,1);
            }
        });

        JavaPairRDD<String,Integer> wordCounts = pairRDD.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        wordCounts.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> wordcount) throws Exception {
                System.out.println(wordcount._1 + ":"+wordcount._2);
            }
        });
    }
}

输入数据

输出数据