JAVA-API 简单实现MapReduce统计单词

(一) JAVA-API 简单实现MapReduce统计单词

()这是要处理的文件

1.导入maven依赖

​

		<dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.8.1</version>
        </dependency>

2.创建Mapper类继承类 org.apache.hadoop.mapreduce.Mapper

package org.zsw.hadoop;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * @description:
 * @author: zsw
 * @date: Created in 2019/12/31 20:30
 * @version: 1
 * @modified By:
 */
public class WordCountMap extends Mapper<LongWritable, Text,Text, LongWritable> {
   

//    由于map方法的调用频率是按行调用，所以其参数表示的意义基本和行相关
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
   
//        key一般来说都是LongWritable类型，表示当前行的起始偏移量，从0开始
//        value 值得是这一行具体内容
//        context指的是上下文对象，上承接框架底层输入,下启shuffle阶段的输入(通常会说作为reduce阶段的输入)。
        String line = value.toString();
        String[] vals = line.split(" ");
        for (String val : vals) {
   
            context.write(new Text(val