自定义OutputFormat（附带可上手实例）

目录

OutputFormat的使用场景： 

需求：

需求分析：

代码实现：

输入结果：

---

OutputFormat的使用场景： 

需求：

过滤输入的log日志，包含isea的网站输出到e:/isea.log，不包含atguigu的网站输出到e:/other.log，输入的数据：

http://www.baidu.com
http://www.google.com
http://cn.bing.com
http://www.isea.com
http://www.sohu.com
http://www.sina.com
http://www.sin2a.com
http://www.sin2desa.com
http://www.sindsafa.com

需求分析：

代码实现：

package com.isea.output_format;

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

package com.isea.output_format;

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

import java.io.IOException;

public class OutputFormatReducer extends Reducer<Text, NullWritable,Text,NullWritable> {
    private Text k = new Text();

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

        String line = key.toString();
        line = line + "\n";
        k.set(line);

        for (NullWritable value : values) {
            context.write(k,NullWritable.get());
        }
    }
}

package com.isea.output_format;

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 FilterDriver{
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"g:/input/log.txt","g:/output"};

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

        job.setJarByClass(FilterDriver.class);

        job.setMapperClass(OutputFormatMapper.class);
        job.setReducerClass(OutputFormatReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        job.setOutputFormatClass(FilterOutPutFormat.class);

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

package com.isea.output_format;

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 FilterOutPutFormat extends FileOutputFormat<Text, NullWritable> {

    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        return new FRecordWriter(job);
    }
}

package com.isea.output_format;

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 FRecordWriter extends RecordWriter<Text, NullWritable> {
    FSDataOutputStream fosIsea;
    FSDataOutputStream fosOther;

    public FRecordWriter(TaskAttemptContext job) {
        try {
//        1，获取文件系统
            FileSystem fs = FileSystem.get(job.getConfiguration());

//        2，创建输出到isea.log的日志的输出流
             fosIsea = fs.create(new Path("g:/out_log/isea.log"));

//        3，创建输出到other.log的日志
             fosOther = fs.create(new Path("g:/out_log/other.log"));

        } catch (IOException e) {
            e.printStackTrace();
        }

    }

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {
//        判断日志中是否有isea， 如果有，输出到isea.log中去， 如果没有输出到other中去
        if (key.toString().contains("isea")){
            fosIsea.write(key.toString().getBytes());
        }else {
            fosOther.write(key.toString().getBytes());
        }
    }

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {
        IOUtils.closeStream(fosIsea);
        IOUtils.closeStream(fosOther);
    }
}

输入结果：

http://www.isea.com



http://cn.bing.com
http://www.baidu.com
http://www.google.com
http://www.sin2a.com
http://www.sin2desa.com
http://www.sina.com
http://www.sindsafa.com
http://www.sohu.com