spark的wordcount（scala与java版本）

Scala与java版本的WordCount

1.Scala版本

-涉及算子

• textFile,非算子，读取数据，生成一个RDD，RDD的每个元素是文件的一行
• flatmap算子：一对一的映射
• map算子：一对多的映射
• reduceByKey算子：先分组，再reduce
• sortBy算子:参数1指定排序字段，参数2指定正反序（Java的pairRDD不存在该算子）
• sortByKey算子：参数指定正反序
• 注意：Java中要将RDD变为pairRDD需要使用xxxToPair方法

package com.qiuyang.scala

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

/**
  * Created by qiuyang on 2018/11/28.
  */
object WordCountScala {
  def main(args: Array[String]) {
    val conf: SparkConf = new SparkConf()
    conf.setAppName("WordCountScala").setMaster("local")

    val sc: SparkContext = new SparkContext(conf)

    val lines: RDD[String] = sc.textFile("/Users/qiuyang/githublib/qiuyang-spark-scala/src/word")

    val words: RDD[String] = lines.flatMap(x => {x.split(" ")})

    val pairRDD: RDD[(String, Int)] = words.map(x => {new Pair(x,1)})

    val res: RDD[(String, Int)] = pairRDD.reduceByKey((x:Int, y:Int) => {x+y})

    //法1: 指定sortBy函数按照指定字段进行排序
//    val res2: RDD[(String, Int)] = res.sortBy(x=>{x._2},false)

    //法2: 颠倒K-V的值,排序后再换回来
    val swapRDD: RDD[(Int, String)] = res.map(x => x.swap)
    val res2: RDD[(String, Int)] = swapRDD.sortByKey(false).map(_.swap)

    res2.foreach(println)
  }
}

2. Java版本的wordcount

package com.qiuyang.java;

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;

/**
 * Created by qiuyang on 2018/11/28.
 * java版本的wordcount
 */
public class WordCountJava {

    public static void main(String[] args){
        SparkConf conf = new SparkConf();
        conf.setAppName("WordCountJava").setMaster("local");

        JavaSparkContext sc = new JavaSparkContext(conf);

        JavaRDD<String> lines = sc.textFile("/Users/qiuyang/githublib/qiuyang-spark-scala/src/word");

        /***
         * 将数据行RDD转换为单词的RDD
         */
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterable<String> call(String s) throws Exception {
                return Arrays.asList(s.split(" "));
            }
        });

        /**
         * 将RDD变为pairRDD（即键-值对RDD,即K-V）, 必须用xxxToPair类型的方法
         * new PairFunction<String, String, Integer>
         *     第一个String为:源RDD的类型
         *     第二个String为:要转为pairRDD的键的类型
         *     Integer为:要转为pairRDD的值的类型
         */
        JavaPairRDD<String, Integer> pairRDD = words.mapToPair(new PairFunction<String, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(String s) throws Exception {
                return new Tuple2<String, Integer>(s, 1);
            }
        });

        /**
         * reduceByKey操作,先groupByKey,再reduce
         * new Function2<Integer, Integer, Integer>
         *     第一个Integer表示某组的第一个参数类型,第二个表示第二个参数类型,第三个代表reduce的参数类型
         * 注意:pairRDD里泛型为JavaPairRDD<String, Integer>,而非Tuple2
         */
        JavaPairRDD<String, Integer> res = pairRDD.reduceByKey(new Function2<Integer, Integer, Integer>() {
            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {
                return v1 + v2;
            }
        });

        /**
         * 交换pairRDD的K-V
         */
        JavaPairRDD<Integer, String> sort1RDD = res.mapToPair(new PairFunction<Tuple2<String, Integer>, Integer, String>() {
            @Override
            public Tuple2<Integer, String> call(Tuple2<String, Integer> tuple2) throws Exception {
                return new Tuple2<Integer, String>(tuple2._2, tuple2._1);
            }
        });
        /**
         * sortByKey实现排序
         *
         */
        JavaPairRDD<Integer, String> sort2RDD = sort1RDD.sortByKey(false);
        /**
         * 换回pairRDD的K-V
         */
        JavaPairRDD<String, Integer> res1 = sort2RDD.mapToPair(new PairFunction<Tuple2<Integer, String>, String, Integer>() {
            @Override
            public Tuple2<String, Integer> call(Tuple2<Integer, String> tuple2) throws Exception {
                return new Tuple2<String, Integer>(tuple2._2, tuple2._1);
            }
        });

        /**
         * 遍历:里面是Tuple2泛型
         */
        res1.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            @Override
            public void call(Tuple2<String, Integer> tuple2) throws Exception {
                System.out.println(tuple2);
            }
        });
    }
}