Scala与java的wordCount

scala实现

package com.bjsxt.myscalacode

import org.apache.spark.{SparkConf, SparkContext}

object SparkWordCount {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf()
    conf.setMaster("local")
    conf.setAppName("sparkwordcount")
    val sc = new SparkContext(conf)
    val lines = sc.textFile(".idea/data/words")
    val words = lines.flatMap(line =>{line.split(" ")})
    val pairWords = words.map(word =>{new Tuple2(word,1)})
    val result = pairWords.reduceByKey((v1,v2) =>{v1+v2})
    result.sortBy(tp=>{tp._2},false).foreach(println)
   /* result.foreach(tuple =>{
      println(tuple)
    })*/

    sc.stop()
  }

}

简化：

 val conf = new SparkConf().setMaster("local").setAppName("sparkwordcount")
   val sc = new SparkContext(conf)
    sc.textFile("./data/words").flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).foreach(println)

java实现

package com.bjsxt.myjavacode;

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.*;
import scala.Tuple2;

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

public class JavaWordCount {
    public static void main(String[] args) {
        SparkConf sparkConf = new SparkConf();
        sparkConf.setMaster("local");
        sparkConf.setAppName("wc");
        JavaSparkContext sparkContext = new JavaSparkContext(sparkConf);

        JavaRDD<String> lines = sparkContext.textFile(".idea/data/words");
        JavaRDD<String> flatMap = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String s) throws Exception {
                return Arrays.asList(s.split(" ")).iterator();
            }
        });
        JavaPairRDD<String, Integer> pairRDD = flatMap.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> reduceByKey = pairRDD.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v, Integer v2) throws Exception {
                return v + v2;
            }
        });
        reduceByKey.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> tuple2) throws Exception {
                System.out.println(tuple2);
            }
        });



    }
}

简化

 SparkConf conf = new SparkConf();
       conf.setMaster("local");
       conf.setAppName("wc");
       JavaSparkContext sc = new JavaSparkContext(conf);
       JavaRDD<String> lines = sc.textFile("./data/words");
       JavaRDD<String> words = lines.flatMap(line -> Arrays.asList(line.split(" ")).iterator());

       JavaPairRDD<String, Integer> pairWords = words.mapToPair(word -> new Tuple2<>(word, 1));

       JavaPairRDD<String, Integer> result = pairWords.reduceByKey((v1, v2) -> v1 + v2);
        result.foreach(tuple2 -> System.out.println(tuple2));
       sc.stop();