自定义OutputFormat案例实操

未来影子

已于 2022-07-03 17:20:00 修改

阅读量238

点赞数

分类专栏： hadoop 文章标签： mapreduce hadoop big data

于 2022-01-16 16:01:54 首次发布

本文链接：https://blog.csdn.net/mynameisgt/article/details/122524299

版权

hadoop 专栏收录该内容

23 篇文章 0 订阅

订阅专栏

自定义OutputFormat案例实操

文章目录

1)需求

过滤输入的log日志，包含atguigu的网站输出到一个文件，不包含atguigu的网站输出到另一个文件

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-Ml9rPUka-1642320025738)(C:\Users\Admin\AppData\Roaming\Typora\typora-user-images\image-20220116145323462.png)]$

2)需求分析

$[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-OdylhT4g-1642320025740)(C:\Users\Admin\AppData\Roaming\Typora\typora-user-images\image-20220116145402204.png)]$

3)编程实现

1.创建Mapper类

package com.yingzi.mapreduce.outputformat;

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

import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-14-15:47
 **/
public class LogMapper extends Mapper<LongWritable, Text,Text, NullWritable> {

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, NullWritable>.Context context) throws IOException, InterruptedException {

        //  (http://www.google.com NullWritable)
        context.write(value,NullWritable.get());
    }
}

2.创建Reducer类

package com.yingzi.mapreduce.outputformat;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-14-15:51
 **/
public class LogReducer extends Reducer<Text, NullWritable,Text,NullWritable> {

    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Reducer<Text, NullWritable, Text, NullWritable>.Context context) throws IOException, InterruptedException {

        //  防止有相同数据，丢数据
        for (NullWritable value : values) {
            context.write(key,NullWritable.get());
        }
    }
}

3.创建OutputFormat类

package com.yingzi.mapreduce.outputformat;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

/**
 * @author 影子
 * @create 2022-01-14-16:08
 **/
public class LogOutputFormat extends FileOutputFormat<Text, NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        //  创建一个自定义的RecordWriter 返回
        LogRecordWriter lrw = new LogRecordWriter(job);

        return lrw;
    }
}

4.创建RecordWriter类

package com.yingzi.mapreduce.outputformat;

import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;

import java.io.IOException;


/**
 * @author 影子
 * @create 2022-01-14-16:20
 **/
public class LogRecordWriter extends RecordWriter<Text, NullWritable> {
    private FSDataOutputStream atguiguOut;
    private FSDataOutputStream otherOut;

    public LogRecordWriter(TaskAttemptContext job) {
        //  创建两条流
        try {
            FileSystem fs = FileSystem.get(job.getConfiguration());
            atguiguOut = fs.create(new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\_output\\LOG\\atguigu.log"));

            otherOut = fs.create(new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\_output\\LOG\\other.log"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {

        String log = key.toString();
        //  具体写
        if (log.contains("atguigu")){
            atguiguOut.writeBytes(log + "\n" );
        }else{
            otherOut.writeBytes(log + "\n");
        }

    }

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {

        //  关流
        IOUtils.closeStream(atguiguOut);
        IOUtils.closeStream(otherOut);
    }
}

5.创建Driver类

package com.yingzi.mapreduce.outputformat;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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.io.IOException;

/**
 * @author 影子
 * @create 2022-01-14-17:49
 **/
public class LogDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(LogDriver.class);

        job.setMapperClass(LogMapper.class);
        job.setReducerClass(LogReducer.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        //设置自定义的 outputformat
        job.setOutputFormatClass(LogOutputFormat.class);

        FileInputFormat.setInputPaths(job, new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\11_input\\inputoutputformat"));
        // 虽 然 我 们 自 定 义 了 outputformat ， 但 是 因 为 我 们 的 outputformat 继承自fileoutputformat
        //而 fileoutputformat 要输出一个_SUCCESS 文件，所以在这还得指定一个输出目录
        FileOutputFormat.setOutputPath(job, new Path("G:\\计算机资料\\大数据开发\\尚硅谷大数据技术之Hadoop3.x\\资料\\_output\\LOG\\logoutput"));
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}