Hadoop案例：自定义OutputFormat数据输出

1.OutputFormat概述

目录

1.OutputFormat概述

2.自定义OutputFormat

2.1应用场景

2.2 自定义OutputFormat步骤

3.自定义OutputFormat案例

3.1需求

 3.2代码实现

（1）编写LogMapper类

（2）编写LogReducer类

（3）编写自定义LogOutputFormat继承OutputFormat

  (4)  编写LogRecordWriter类

（5）编写Driver类

---

OutputFormat是MapReduce输出的基类，所有实现了MapReduces输出都实现了OutputFormat接口。以下为OutputFormat的相关实现类。默认输出格式TextOutputFormat。

2.自定义OutputFormat

2.1应用场景

        例如：输出数据到到MySql/Hbase等存储框架中

2.2 自定义OutputFormat步骤

        首先自定义一个类继承FileOutputFormat

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

3.自定义OutputFormat案例

3.1需求

 3.2代码实现

（1）编写LogMapper类

package com.yangmin.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,直接写出一行 log 数据
        context.write(value, NullWritable.get());
    }
}

（2）编写LogReducer类

package com.yangmin.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) {
            // 防止有相同的数据,迭代写出
           context.write(key, value);
        }
    }
}

（3）编写自定义LogOutputFormat继承OutputFormat

package com.yangmin.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 logRecordWriter = new LogRecordWriter(job);
        return logRecordWriter;

    }
}

  (4)  编写LogRecordWriter类

package com.yangmin.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("C:\\ZProject\\bigdata\\output\\output-define-outputformat\\atguigu.log"));
            this.otherOut = fs.create(new Path("C:\\ZProject\\bigdata\\output\\output-define-outputformat\\other.log"));
            FSDataOutputStream otherOut = this.otherOut;
        } catch (IOException e) {
            e.printStackTrace();
        }

    }

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

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {
        IOUtils.closeStream(atguiguOut);
        IOUtils.closeStream(otherOut);

    }
}

（5）编写Driver类

package com.yangmin.mapreduce.outputFormat;

import com.yangmin.mapreduce.wordcount.WordCountDriver;
import com.yangmin.mapreduce.wordcount.WordCountMapper;
import com.yangmin.mapreduce.wordcount.WordCountReducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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 Driver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1. 获取配置信息以及获取job对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2. 设置jar包路径
        job.setJarByClass(Driver.class);

        //3. 关联mapper和reducer
        job.setMapperClass(LogMapper.class);
        job.setReducerClass(LogReducer.class);

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

        //5. 设置最终输出的kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //设置outputformat
        job.setOutputFormatClass(LogOutputFormat.class);

        //6.设置输出路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("C:\\ZProject\\bigdata\\input\\inputoutputformat"));
        FileOutputFormat.setOutputPath(job, new Path("C:\\ZProject\\bigdata\\output\\output-define-outputformat\\111"));

        //7.提交作业
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}