MapReduce-day05-第三章框架原理-3.4OutputFormat机制

1：默认输出格式TextOutputFormat

2：自定义OutputFormat

      2.1：应用场景：输出数据到mysql/hbase/elasticsearch等存储框架中

      2.2：自定义步骤

               2.2.1：自定义一个类继承FileOutputFormat

               2.2.2：改写RecordWriter，具体改写输出数据的方法write()

3：自定义OutputFormat案例

   

 4：代码编写

LogDriver：

package com.atguigu.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 {

        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("F:\\input\\inputoutputformat"));
// 虽然我们自定义了outputformat ， 但是因为我们的outputformat 继承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("F:\\hadoop\\output111"));
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }

}

LogMapper

package com.atguigu.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 {

        //不做任何处理
        context.write(value,NullWritable.get());
    }
}

LogReducer

package com.atguigu.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 {
        for (NullWritable value : values) {
            context.write(key,NullWritable.get());
        }
    }
}

LogOutputFormatc

package com.atguigu.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;
    }
}

   LogRecordWriter

package com.atguigu.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 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("F:\\hadoop\\atguigu.log"));

            otherOut = fs.create(new Path("F:\\hadoop\\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 taskAttemptContext) throws IOException, InterruptedException {

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