Hadoop案例（五）過濾日志及自定義日志輸出路徑（自定義OutputFormat)

過濾日志及自定義日志輸出路徑（自定義OutputFormat）

1.需求分析

過濾輸入的log日志中是否包含xyg

（1）包含xyg的網站輸出到e:/xyg.log

（2）不包含xyg的網站輸出到e:/other.log

2.數據准備

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

輸出預期：

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.代碼實現

（1）自定義一個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 {

        // 創建一個RecordWriter
        return new FilterRecordWriter(job);
    }
}

（2）具體的寫數據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 獲取文件系統
        FileSystem fs;

        try {
            fs = FileSystem.get(job.getConfiguration());

            // 2 創建輸出文件路徑
            Path atguiguPath = new Path("e:/xyg.log");
            Path otherPath = new Path("e:/other.log");

            // 3 創建輸出流
            atguiguOut = fs.create(atguiguPath);
            otherOut = fs.create(otherPath);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {

        // 判斷是否包含“xyg”輸出到不同文件
        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 {
        // 關閉資源
        if (atguiguOut != null) {
            atguiguOut.close();
        }
        
        if (otherOut != null) {
            otherOut.close();
        }
    }
}

（3）編寫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 獲取一行
        String line = value.toString();
        
        k.set(line);
        
        // 3 寫出
        context.write(k, NullWritable.get());
    }
}

（4）編寫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）編寫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);

        // 要將自定義的輸出格式組件設置到job中
        job.setOutputFormatClass(FilterOutputFormat.class);

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

        // 雖然我們自定義了outputformat，但是因為我們的outputformat繼承自fileoutputformat
        // 而fileoutputformat要輸出一個_SUCCESS文件，所以，在這還得指定一個輸出目錄
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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