Hadoop案例（五）过滤日志及自定义日志输出路径（自定义OutputFormat)

过滤日志及自定义日志输出路径（自定义OutputFormat）

1.需求分析

过滤输入的log日志中是否包含xyg

（1）包含xyg的网站输出到e:/xyg.log

（2）不包含xyg的网站输出到e:/other.log

2.数据准备

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

输出预期：

http://www.xyg.com

http://cn.bing.com
http://www.baidu.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

3.代码实现

（1）自定义一个outputformat

package com.xyg.mapreduce.outputformat;

import java.io.IOException;
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;

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);
    }
}

（2）具体的写数据RecordWriter

package com.xyg.mapreduce.outputformat;

import java.io.IOException;
import org.apache.hadoop.fs.FSDataOutputStream;
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.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;

public class FilterRecordWriter extends RecordWriter<Text, NullWritable> {
    FSDataOutputStream atguiguOut = 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 atguiguPath = new Path("e:/xyg.log");
            Path otherPath = new Path("e:/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“xyg”输出到不同文件
        if (key.toString().contains("xyg")) {
            atguiguOut.write(key.toString().getBytes());
        } else {
            otherOut.write(key.toString().getBytes());
        }
    }

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {
        // 关闭资源
        if (atguiguOut != null) {
            atguiguOut.close();
        }
        
        if (otherOut != null) {
            otherOut.close();
        }
    }
}

（3）编写FilterMapper

package com.xyg.mapreduce.outputformat;

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class FilterMapper extends Mapper<LongWritable, Text, Text, NullWritable>{
    
    Text k = new Text();
    
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 1 获取一行
        String line = value.toString();
        
        k.set(line);
        
        // 3 写出
        context.write(k, NullWritable.get());
    }
}

（4）编写FilterReducer

package com.xyg.mapreduce.outputformat;

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

public class FilterReducer extends Reducer<Text, NullWritable, Text, NullWritable> {

    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {

        String k = key.toString();
        k = k + "\r\n";

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

（5）编写FilterDriver

package com.xyg.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;

public class FilterDriver {
    public static void main(String[] args) throws Exception {

        args = new String[] { "e:/inputoutputformat", "e:/output2" };

        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);

        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);
    }
}