WordCount经典案例及源码分析

package com.ruozedata.bigdata.hadoop.mapreduce.wc;

import com.ruozedata.bigdata.hadoop.utils.FileUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.NLineInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class WordCountApp {
//套路编程
    public static void main(String[] args) throws Exception{
        //获取job对象
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        String input="data/wc.data";
        String output="out/";
        FileUtils.deleteTarget(output,configuration);

        //设置jar相关信息
        job.setJarByClass(WordCountApp.class);

        //设置自定义的mapper跟Reducer
        job.setMapperClass(MyMapper.class);
        job.setReducerClass(MyReducer.class);
        //设置map端做一个类似reduce的操作
        job.setCombinerClass(MyReducer.class);

        //设置mapper阶段输出的key跟value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //设置reducer阶段输出的key跟vlaue类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path(input));
        FileOutputFormat.setOutputPath(job,new Path(output));

        //提交job
        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);

    }

    public static class MyMapper extends Mapper<LongWritable, Text,Text, IntWritable>{
        IntWritable ONE= new IntWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
             String[] splits = value.toString().split(",");

            for(String split:splits){
                context.write(new Text(split),ONE);
            }
        }
    }
    public static class MyReducer extends Reducer<Text, IntWritable,Text, IntWritable>{
        @Override
        protected void reduce(Text word, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

            int count = 0;
            for(IntWritable value:values){
                count += value.get();
            }
            context.write(word,new IntWritable(count));
        }
    }
}

WordCount源码分析

waitForCompletion{
    submit(){
        connect(); // 其实就是为了拿到一个cluster（Local YARN）

        submitJobInternal(){
            checkSpecs(job);  // 为了检查输出目录是否存在

            // 创建一个staging目录
            Path jobStagingArea = JobSubmissionFiles.getStagingDir(cluster, conf);

            // 获取该Job的id
            JobID jobId = submitClient.getNewJobID();
            job.setJobID(jobId);

            // 本Job对应的目录: staging + jobid
            Path submitJobDir = new Path(jobStagingArea, jobId.toString());

            // 本Job的信息
            copyAndConfigureFiles(job, submitJobDir);

            // 获取该Job对应的map数量
            int maps = writeSplits(job, submitJobDir);

            // 本Job的信息写入到指定的文件中去
            writeConf(conf, submitJobFile);

            // 删除该Job对应的文件目录中的信息
            jtFs.delete(submitJobDir, true);
        }
    }
}