Hadoop 自定义OutPutFormat 输出

自定义outputformat 案例练习代码实现思路(作用在Reduce之后）：

1. 根据需求，我们要将一个输入文件中的包含 hadoop 单词的数据放在一个输出文件中，
   不包含hadoop单词的数据放在另外一个输出文件中
2. 首先需要在mapper中，将读取的kv不做任何处理，直接写出
3. 然后自定义outputformat的实现类，在recordwriter方法中返回一个我们自定义的
   recordwriter类，这个类需要继承recordwriter
4. 在自定义的recordwriter中，先定义两个输出流 FSDataoutputStream，一个用于
   往外写包含hadoop单词的数据，一个用于往外写不包含hadoop单词的数据，在构造器中
   对这两个流对象做初始化操作
5. 将具体的判断和写数据的逻辑代码写在write方法中
6. 最后在driver中注册我们自定义的outputformat类即可

自定义 Mapper:

package com.mr.output1;

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;

/**
 * @author kate
 */
public class FilterMapper extends Mapper<LongWritable, Text,Text, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
         // 根据需求编写逻辑代码
        // 写出
        context.write(value, NullWritable.get());
    }
}

自定义 Reduce：

package com.mr.output1;

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

import java.io.IOException;

/**
 * @author kate
 */
public class FilterReducer 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 目的 输出文件自动换行
        line = line + "\r\n";

        // 3 设置key
        k.set(line);

        // 4 输出
        context.write(k, NullWritable.get());
    }
}

自定义OutPutFormat 类：

package com.mr.output1;


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 {

        // 创建一个RecordWriter
        return new FilterRecordWriter(job);
    }

}

自定义写出类：

package com.mr.output1;

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;

/**
 * @author kate
 */
public class FilterRecordWriter extends RecordWriter<Text, NullWritable> {

        FSDataOutputStream hadoopOut = null;
        FSDataOutputStream otherOut = null;

	public FilterRecordWriter(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 hadoopPath = new Path("F:/mapreduce/src/main/resources/output/hadoop.txt");
                Path otherPath = new Path("F:/mapreduce/src/main/resources/output/other.log");

                // 3 创建输出流
                hadoopOut = fs.create(hadoopPath);
                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“hadoop”输出到不同文件
            if (key.toString().contains("hadoop")) {
                hadoopOut.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(hadoopOut);
            IOUtils.closeStream(otherOut);
	}

}

自定义Driver类:

package com.mr.output1;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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;

/**
 * @author kate
 */
public class FilterDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        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);

        // 要将自定义的输出格式组件设置到job中
        job.setOutputFormatClass(FilterOutputFormat.class);
        //设置路径，包括了输入文件和输出路径
        FileInputFormat.setInputPaths(job, new Path("F:/mapreduce/src/main/resources/input/log.txt"));

        FileSystem fs = FileSystem.get(conf);
        Path path = new Path("F:/mapreduce/src/main/resources/output1");
        if (fs.exists(path)) {
            fs.delete(path, true);
        }

        //输出路径的文件夹不能存在，若存在，则报错。
        FileOutputFormat.setOutputPath(job, path);
        //提交job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}