OutputFormat数据输出

OutputFormat数据输出

OutputFormat是MapReduce输出的基类，所有实现MapReduce输出都实现了 OutputFormat接口。

1.文本输出TextOutputFormat

 默认的输出格式是TextOutputFormat，它把每条记录写为文本行。
 它的键和值可以是任意类型，因为TextOutputFormat调用toString()方法把它们转换为字符串。

2.SequenceFileOutputFormat

 将SequenceFileOutputFormat输出作为后续 MapReduce任务的输入，这便是一种好的输出格式，
 因为它的格式紧凑，很容易被压缩。

3.自定义OutputFormat

 根据用户需求，自定义实现输出。

使用场景

控制最终文件的输出路径和输出格式

     例如：要在一个MapReduce程序中根据数据的不同输出两类结果到不同目录，
     这类灵活的输出需求可以通过自定义OutputFormat来实现。

步骤

（1）自定义一个类继承FileOutputFormat。

（2）改写RecordWriter，具体改写输出数据的方法write()。

案例

1．需求

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

（1）输入数据

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

（2）期望输出数据

http://www.atguigu.com

两个文件
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

2.需求分许

3.代码实现

OutputFormat类

package com.saddam.bigdata.ShangGuiGu.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;

//继承reducer输出
public class FilterOutputFormat extends FileOutputFormat<Text, NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        return new FRecordWriter(job);
    }
}

FRecordWriter类

package com.saddam.bigdata.ShangGuiGu.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 FRecordWriter extends RecordWriter<Text, NullWritable> {
    FSDataOutputStream fosAtguigu;
    FSDataOutputStream fosOther;

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {
        //判断key当中是否有atguigu，若有写入到atguigu.log,没有就other
        if (key.toString().contains("atguigu")){
            fosAtguigu.write(key.toString().getBytes());
        }else {
            fosOther.write(key.toString().getBytes());
        }
    }

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

    public FRecordWriter(TaskAttemptContext job) {

        try {
            //获取文件系统
            FileSystem fs = FileSystem.get(job.getConfiguration());

            //创建输出流
             fosAtguigu = fs.create(new Path("D:\\MR\\MapReduce\\OutputDatas\\OutputFormat\\atguigu.log"));

             fosOther=fs.create(new Path("D:\\MR\\MapReduce\\OutputDatas\\OutputFormat\\Other.log"));

            //创建输出其他的输出流
        }catch (IOException e){
            e.printStackTrace();
        }
    }
}

Mapper类

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

Reducer类

package com.saddam.bigdata.ShangGuiGu.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 FilterReducer extends Reducer<Text, NullWritable,Text,NullWritable> {
    Text outK=new Text();
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {

        String line = key.toString();

        line=line+"\r\n";
        outK.set(line);
        //防止重复数据
        for (NullWritable nullWritable:values) {
            context.write(outK,NullWritable.get());
        }
    }
}

Driver类

package com.saddam.bigdata.ShangGuiGu.OutputFormat;

import com.saddam.bigdata.ShangGuiGu.Shuffle.sort.PartitionSort;
import com.saddam.bigdata.ShangGuiGu.Shuffle.sort.SortFlowBean;
import com.saddam.bigdata.ShangGuiGu.Shuffle.sort.SortFlowMapper;
import com.saddam.bigdata.ShangGuiGu.Shuffle.sort.SortFlowReducer;
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 org.apache.log4j.BasicConfigurator;

public class FilterDriver {
    public static void main(String[] args)throws Exception {
        BasicConfigurator.configure();

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

        job.setJarByClass(FilterDriver.class);

        job.setMapperClass(FilterMapper.class);
        job.setReducerClass(FilterReducer.class);

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

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

        job.setOutputFormatClass(FilterOutputFormat.class);

        FileInputFormat.setInputPaths(job,new Path("D:\\MR\\MapReduce\\InputDatas\\OutputFormat"));
        FileOutputFormat.setOutputPath(job,new Path("D:\\MR\\MapReduce\\OutputDatas\\OutputFormat\\output_outputformat"));

        job.waitForCompletion(true);
    }
}