Mapreduce中自定义OutputFormat

OutputFormat接口实现类

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toString0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-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

为了实现控制最终文件的输出路径和输出格式，可以自定义OutputFormat。比如要在一个MR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。

自定义OutputFormat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()

自定义OutputFormat

1. 需求分析
   过滤输入的数据，将包含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

2. 输入数据
   

3. 编写Mapper类

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

4. 编写Reducer类

package com.atguigu.mr.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 FileReducer extends Reducer<Text, NullWritable,Text,NullWritable> {
    Text k = new Text();
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context)		throws IOException, InterruptedException {
        // 1 获取一行
        String line = key.toString();
        // 2 拼接
        line = line + "\r\n";
        // 3 设置key
        k.set(line);
        // 4 输出
        context.write(k, NullWritable.get());
    }
}

5. 编写RecordWriter类

package com.atguigu.mr.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 FileRecordWriter extends RecordWriter<Text, NullWritable> {
    FSDataOutputStream atguiguOut = null;
    FSDataOutputStream otherOut = null;
    public FileRecordWriter(TaskAttemptContext job) {
        // 1 获取文件系统
        FileSystem fs;
        try {
            fs = FileSystem.get(job.getConfiguration());
            // 2 创建输出文件路径
            Path atguiguPath = new Path("D:\\idea project\\MapReduce\\atguigu.log");
            Path otherPath = new Path("D:\\idea project\\MapReduce\\other.log");
            // 3 创建输出流
            atguiguOut = fs.create(atguiguPath);
            otherOut = fs.create(otherPath);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {

        // 判断是否包含“atguigu”输出到不同文件
        if (key.toString().contains("atguigu")) {
            atguiguOut.write(key.toString().getBytes());
        } else {
            otherOut.write(key.toString().getBytes());
        }
    }
    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {
        // 关闭资源
        IOUtils.closeStream(atguiguOut);
        IOUtils.closeStream(otherOut);	}
}

6. 自定义一个OutputFormat类

package com.atguigu.mr.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 File_OutputFormat extends FileOutputFormat<Text, NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job)throws IOException, InterruptedException {
        // 创建一个RecordWriter
        return new FileRecordWriter(job);
    }
}

7. 编写Driver类

package com.atguigu.mr.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 FileDriver {
    public static void main(String[] args) throws Exception {
        //1 获取Job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        //2 设置jar存储位置
        job.setJarByClass(FileDriver.class);

        //3 关联Mapper和Reducer类
        job.setMapperClass(FileMapper.class);
        job.setReducerClass(FileReducer.class);

        //4 设置map阶段输出的kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        //5 设置最终的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //6 要将自定义的输出格式组件设置到job中
        job.setOutputFormatClass(File_OutputFormat.class);

        //7 设置输入输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\idea project\\MapReduce\\web.txt"));
        // 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("D:\\idea project\\MapReduce\\output777"));

        //8 提交Job
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}

8. 查看结果