MapReduce过滤域名案例(自定义OutputFormat)基本实现

输入数据

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

Maven和log4j.properties配置

参考 MapReduce统计流量案例 中的配置  

自定义Mapper类实现(LogMapper)

package com.test.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 {
        // 直接将每行数据，写出。value为NULL即可
        context.write(value, NullWritable.get());
    }
}

自定义Reducer类实现(LogReducer)

package com.test.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 {
        // 防止有相同数据被过滤，迭代写出。
        for (NullWritable value : values) {
            context.write(key, value);
        }
    }
}

自定义FileOutputFormat类实现(LogOutputFormat)

package com.test.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 {
        // 创建并返回自定义LogRecordWriter(实现内部具体输出方法)
        LogRecordWriter logRecordWriter = new LogRecordWriter(job);
        return logRecordWriter;
    }
}

自定义RecordWriter类实现(LogRecordWriter)

package com.test.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> {

    // 定义两个输出对象
    private FSDataOutputStream baiduOut;
    private FSDataOutputStream otherOut;

    /**
     * 初始化方法
     */
    public LogRecordWriter(TaskAttemptContext job) {
        try {
            // 获取文件系统对象
            FileSystem fs = FileSystem.get(job.getConfiguration());
            // 用文件系统对象创建两个输出流对应不同目录
             baiduOut = fs.create(new Path("D:\\output\\baidu.log"));
             otherOut = fs.create(new Path("D:\\output\\other.log"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    /**
     * 重写write逻辑
     */
    @Override
    public void write(Text text, NullWritable nullWritable) throws IOException, InterruptedException {
        // 将输入数据转换为字符串
        String log = text.toString();

        // 包含baidu的往baidu.log输出，其他往other.log输出
        if (log.contains("baidu")) {
            baiduOut.writeBytes(log + "\n");
        }else {
            otherOut.writeBytes(log + "\n");
        }
    }

    /**
     * 重写close方法
     */
    @Override
    public void close(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        // 关闭文件对象
        IOUtils.closeStream(baiduOut);
        IOUtils.closeStream(otherOut);
    }
}

自定义Reducer类实现(LogDriver)

package com.test.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;

public class LogDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1.创建配置信息Configuration对象并获取Job单例对象
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2.设置关联本Driver程序的jar
        job.setJarByClass(LogDriver.class);

        // 3.设置关联Mapper和Reducer
        job.setMapperClass(LogMapper.class);
        job.setReducerClass(LogReducer.class);

        // 4.设置Mapper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);

        // 6.设置自定义的outputformat
        job.setOutputFormatClass(LogOutputFormat.class);

        // 7.设置数据输入路径
        FileInputFormat.setInputPaths(job, new Path("D:\\input"));

        // 8.设置_SUCCESS文件输出路径
        //虽然自定义了OutputFormat，但是因为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:\\output"));

        // 9.提交job
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

输出数据

baidu.log

http://www.baidu.com
http://www.baidu.com
https://www.baidu.com

other.log

http://cn.bing.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