Spark入门之Java实现WordCount

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 scala.Tuple2;

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

public class JavaWordCount {
    public static void main(String[] args) {
        if (args.length != 2) {
            System.out.println("Usage:clw.spark.day01.ScalaWordCount    <srcPath>,<desPath>");

            System.exit(-1);
        }

        SparkConf sparkConf = new SparkConf().setAppName("JavaWordCount").setMaster("local[*]");

        //创建sparkContext
        JavaSparkContext jsc = new JavaSparkContext(sparkConf);

        //指定从哪里读取数据
        JavaRDD<String> lines = jsc.textFile(args[0]);

        //将读取的数据切分压平
        //Java里面没有函数式编程,所以就用回调函数实现业务逻辑
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.split(",")).iterator();
            }
        });


        //将单词和1组合
        JavaPairRDD<String, Integer> wordAndOne = words.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String word) throws Exception {
                return new Tuple2<>(word, 1);
            }
        });

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

        //调换顺序
        JavaPairRDD<Integer, String> swaped = reduced.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tp) throws Exception {
                return tp.swap();
            }
        });

        //排序
        JavaPairRDD<Integer, String> sorted = swaped.sortByKey(false);

        //调换顺序
        JavaPairRDD<String, Integer> result = sorted.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tp) throws Exception {
                return tp.swap();
            }
        });

//        将数据存到hdfs
        result.saveAsTextFile(args[1]);

        //释放资源
        jsc.stop();
    }
}