五十三、Mapreduce之自定义outputformat案例

案例需求：

        过滤输出的log日志，包含tuomasi的网址输出到 tuomasi.log文件，不包含 tuomasi 的网址输出到 other.log文件

输入数据：

 

期望输出数据：

 

         注：通过观察可以看到存在 tuomasi 字符的网址已经被存放在 tuomasi.log 文件中，其余网址则被存放在 other.log 文件中

程序编写：

        程序主体架构：

 

（1）LogMapper编写

package org.example.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;

public class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        context.write(value, NullWritable.get());
    }

}

（2）LogReducer编写

package org.example.mapreduce.outputformat;

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

import java.io.IOException;

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

        //为防止输入相同网址输出一条数据，进行循环迭代
        for (NullWritable value : values) {
            context.write(key, NullWritable.get());
        }
    }
}

（3）LogOutputFormat编写

package org.example.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;

public class LogOutputFormat extends FileOutputFormat<Text, NullWritable> {

    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        LogRecordWriter lrw = new LogRecordWriter(job);

        return lrw;
    }
}

（4）LogRecordWriter编写

package org.example.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;

public class LogRecordWriter extends RecordWriter<Text, NullWritable> {
    private FSDataOutputStream tuomasiOut;
    private FSDataOutputStream otherOut;

    public LogRecordWriter(TaskAttemptContext job) {
        //创建流
        try {
            FileSystem fs = FileSystem.get(job.getConfiguration());
            tuomasiOut = fs.create(new Path("E:\\output\\outputformats\\tuomasi.log"));

            otherOut = fs.create(new Path("E:\\output\\outputformats\\other.log"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {
        String log = key.toString();
        //具体流程
        if (log.contains("tuomasi")) {
            tuomasiOut.writeBytes(log+"\n");
        } else {
            otherOut.writeBytes(log+"\n");
        }
    }

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {
        //关闭流
        IOUtils.closeStream(tuomasiOut);
        IOUtils.closeStream(otherOut);
    }
}

（5）LogDriver编写

package org.example.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;

public class LogDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //设置jar包路径
        job.setJarByClass(LogDriver.class);

        //关联mapper和reducer
        job.setMapperClass(LogMapper.class);
        job.setReducerClass(LogReducer.class);

        //设置mapper输出的k,v类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        //设置最终输出的K,V类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //设置自定义的outputformat
        job.setOutputFormatClass(LogOutputFormat.class);

        //设置输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("E:\\input\\inputoutputformat"));
        FileOutputFormat.setOutputPath(job, new Path("E:\\output\\outputformats\\outputformat"));

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

数据分析：

 

        注：程序结果与预期效果一致

概论

OutputFormat接口实现类：

自定义outputformat:

        总结：自定义outputformat可以更加便捷的控制输出文件的路径和格式，使程序更加人性化

Mapreduce之自定义outputformat案例完成

文章来源: tuomasi.blog.csdn.net，作者：托马斯-酷涛，版权归原作者所有，如需转载，请联系作者。

原文链接：tuomasi.blog.csdn.net/article/details/121796937