MapReduce之通过Debug的方式了解偏移量及重构代码

1、在WordCountMapper.java中打断点

String[] words = value.toString().split("\t");

2、在WordCountApp.java中，以Debug“WordCountApp.main()”方式运行程序

map(LongWritable key, Text value, Context context)

（1）key是每一行起始位置的偏移量。第一行为0，第二行为20

（2）value是每一行的内容值

3、代码重构

（1）主要任务是：删除在HDFS中重复性生成的output文件夹

（2）WordCountApp.java

package com.imooc.bigdata.hadoop.mapreduce.wordcount;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.net.URI;

/*
 * Driver类：配置Mapper和Reducer的相关属性
 * 通过WordCountApp.java将Mapper和Reducer关联起来
 * 使用MapReduce统计HDFS上的文件对应的词频
 *
 * 提交到本地运行：开发过程中使用
 */

public class WordCountApp {

    public static void main(String[] args) throws Exception{

        //设置权限
        System.setProperty("HADOOP_USER_NAME", "hadoop");

        Configuration configuration = new Configuration();
        //在configuration里设置一些东西：
        configuration.set("fs.defaultFS", "hdfs://192.168.126.101:8020");

        //创建一个Job
        //将configuration传进来
        Job job = Job.getInstance(configuration);

        //设置Job对应的参数：主类
        job.setJarByClass(WordCountApp.class);

        //设置Job对应的参数：设置自定义的Mapper和Reducer处理类
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //设置Job对应的参数：Mapper输出key和value的类型
        //不需要关注Mapper输入
        //Mapper<LongWritable, Text, Text, IntWritable>
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //设置Job对应的参数：Reducer输出key和value的类型
        //不需要关注Reducer输入
        //Reducer<Text, IntWritable, Text, IntWritable>
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //如果输出目录已经存在，则先删除
        FileSystem fileSystem = FileSystem.get(new URI("hdfs://192.168.126.101:8020"), configuration, "hadoop");
        Path outputPath = new Path("/wordcount/output");
        if(fileSystem.exists(outputPath)) {
            fileSystem.delete(outputPath, true);
        }

        //设置Job对应的参数：Mapper输出key和value的类型：作业输入和输出的路径
        FileInputFormat.setInputPaths(job, new Path("/wordcount/input"));
        FileOutputFormat.setOutputPath(job, outputPath);

        //提交job
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : -1);

    }
    //若输出失败，添加以下代码
    static {

        try {
            //G:\BaiduNetdiskDownload\hadoop2.7.6\bin\hadoop.dll
            System.load("G:\\BaiduNetdiskDownload\\hadoop2.7.6\\bin\\hadoop.dll");

        } catch (UnsatisfiedLinkError e) {

            System.err.println("Native code library failed to load.\n" + e);

            System.exit(1);

        }

    }
}