Hadoop学习—— OutputFormat数据输出

文本输出TextOutputFormat
默认的输出格式是TextOutputFormat,他把每条记录写为文本行，他的键和值可以是任意类型，因为TextOutputFormat 调用toString() 方法把他们转换为字符串
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
OutputFormat
用户还可以自定义OutputFormat

自定义OutputFormat

使用场景
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
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

• 自定义一个类继承FileOutputFormat
• 改写RecordWriter ，具体改写输出数据的方法write()

(1)编写FilterMapper类

package com.hadwinling.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;

/**
 * @author :HadwinLing
 * @version 1.0
 * @description: TODO
 * @date 2020/11/22 下午2:49
 */
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());


    }
}

（2）编写FilterReducer类

package com.hadwinling.mapreduce.outputformat;

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

import java.io.IOException;

/**
 * @author :HadwinLing
 * @version 1.0
 * @description: TODO
 * @date 2020/11/22 下午2:58
 */
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 {

        String line = key.toString();

        line = line +"\t\n";

        k.set(line);

        // 防止有重复的数据
        for (NullWritable nullWritable : values) {

            context.write(k, NullWritable.get());
        }
    }
}

（3）自定义一个OutputFormat类

package com.hadwinling.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;

/**
 * @author :HadwinLing
 * @version 1.0
 * @description: TODO
 * @date 2020/11/22 下午3:01
 */
public class FilterOutputFormat extends FileOutputFormat<Text, NullWritable>{

    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job)
            throws IOException, InterruptedException {

        return new FRecordWriter(job);
    }
}

（4）编写RecordWriter类

package com.hadwinling.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;

/**
 * @author :HadwinLing
 * @version 1.0
 * @description: TODO
 * @date 2020/11/22 下午3:03
 */
public class FRecordWriter extends RecordWriter<Text, NullWritable> {

    FSDataOutputStream fosatguigu;
    FSDataOutputStream fosother;

    public FRecordWriter(TaskAttemptContext job) {
        try {
            // 1 获取文件系统
            FileSystem fs = FileSystem.get(job.getConfiguration());

            // 2 创建输出到atguigu.log的输出流
            fosatguigu = fs.create(new Path("e:/atguigu.log"));

            // 3 创建输出到other.log的输出流
            fosother = fs.create(new Path("e:/other.log"));

        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {
        // 判断key当中是否有atguigu,如果有写出到atguigu.log  如果没有写出到other.log

        if (key.toString().contains("atguigu")) {
            // atguigu输出流
            fosatguigu.write(key.toString().getBytes());
        }else {
            fosother.write(key.toString().getBytes());
        }
    }

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {
        IOUtils.closeStream(fosatguigu);
        IOUtils.closeStream(fosother);
    }
}

（5）编写FilterDriver类

package com.hadwinling.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;

/**
 * @author :HadwinLing
 * @version 1.0
 * @description: TODO
 * @date 2020/11/22 下午3:04
 */
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.setJarByClass(FilterMapper.class);
        job.setJarByClass(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);

        FileInputFormat.setInputPaths(job, new Path(args[0]));

        // 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(args[1]));

        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);


    }
}