通过java代码实现spark的计算排序

1、导入spark相关依赖：

<properties>
       <java.version>1.8</java.version>
        <spark.version>2.1.0</spark.version>
        <scala.version>2.11</scala.version>
</properties>
<dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
         <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.11.11</version>
        </dependency>
</dependencies>

2、用java代码操作spark框架，对热词进行分析（取出排名前十的热点数据）

package com.spark.test;

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.Function2;
import org.apache.spark.api.java.function.PairFunction;
import scala.Tuple2;

import java.util.List;

public class SparkTest<res> {
    public static void main(String[] args) {
    //1、设置spark运行环境
    SparkConf conf=new SparkConf().setAppName("HotWords").setMaster("local[2]");
    //2、生成SparkContext对象
    JavaSparkContext context=new JavaSparkContext(conf);
    //3、加载数据生成Rdd
    JavaRDD<String> firstRdd=context.textFile("C:\\Users\\spectre\\Desktop\\Sogou.sample",1);
    //4、封装结果(将关键词封装MAP)
    JavaPairRDD<String,Integer> secondRdd= firstRdd.mapToPair(new PairFunction<String,String,Integer>(){
        public Tuple2<String,Integer> call(String s) throws Exception{
            //按制表符切割，取出第三个下标数据
            String word = s.split("\t")[2];
            //将数据以（key，1）的方式返回
            return new Tuple2<String,Integer>(word,1);
        }
    });
    //将map中的value值相加
    JavaPairRDD<String,Integer> thirdRdd=secondRdd.reduceByKey(new Function2<Integer,Integer,Integer>(){
        public Integer call(Integer v1,Integer v2) throws Exception {
            return v1+v2;
        }
    });
    JavaPairRDD<Integer, String> fourRdd=thirdRdd.mapToPair(new PairFunction<Tuple2<String,Integer>,Integer,String>(){
        public Tuple2<Integer,String> call(Tuple2<String,Integer> stringIntegerTuple2) throws Exception{
        //将map中的key和value值交换位置
            return stringIntegerTuple2.swap();
        }
    });
    //按照key值的大小进行降序排序
    JavaPairRDD<Integer, String> fiveRdd=fourRdd.sortByKey(false);
    //取出排名前十的数据，封装成List
    List<Tuple2<Integer,String>> res=fiveRdd.take(10);
    //循环取出前十的数据
        for(Tuple2<Integer,String> ret : res){
            System.out.println(ret._2+"++++++"+ret._1);
        }
    }

}