Spark java版本wordCount

创建文件

在这里插入图片描述

here where my your
hello world
test file
jump you can you jump

实现代码

package cn.tukk.sparkproject.test.testOrder;

import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
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 org.apache.spark.rdd.RDD;
import org.apache.spark.sql.types.IntegerType;
import scala.Tuple2;

import java.util.Arrays;

public class SparkWordCount {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("testWordCount").setMaster("local");
        JavaSparkContext sc = new JavaSparkContext(conf);
        JavaRDD<String> lines = sc.textFile("wordCount");
        JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() {

            private static final long serialVersionUID = 9166467038300894254L;

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

        JavaPairRDD<String, Integer> pairs = words.mapToPair(new PairFunction<String, String, Integer>() {

            private static final long serialVersionUID = -2575877317483490894L;

            @Override
            public Tuple2<String, Integer> call(String s) throws Exception {
                return new Tuple2<String,Integer>(s,1);
            }
        });

        JavaPairRDD<String, Integer> wordCounts = pairs.reduceByKey(new Function2<Integer, Integer, Integer>() {
            private static final long serialVersionUID = 1995267764597335108L;

            @Override
            public Integer call(Integer v1, Integer v2) throws Exception {

                return v1+v2;
            }
        });

        wordCounts.foreach(new VoidFunction<Tuple2<String, Integer>>() {
            private static final long serialVersionUID = 7339200658105284851L;

            @Override
            public void call(Tuple2<String, Integer> wordAndCount) throws Exception {
                System.out.println(wordAndCount._1+wordAndCount._2);
            }
        });

        sc.close();

    }

}














输出

在这里插入图片描述

  • 2
    点赞
  • 9
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值