MapReduce案例六：自定义输出路径

目录

• 一、数据样例
• 二、需求
• 三、分析
• 四、代码实现

一、数据样例

http://cn.bing.com
http://www.baidu.com
http://www.google.com
http://www.itstar.com
http://www.itstar.comhttp://www.baidu.com
http://www.sin2a.com
http://www.sin2a.comw.google.com
http://www.sin2desa.com
http://www.sin2desa.comw.google.com
http://www.sina.com
http://www.sindsafa.com
http://www.sohu.com

二、需求

• 过滤输入的log日志中是否包含itstar？包含itstar的网站输出到一个文件中，不包含itstar的网站输出到另一个文件中。

三、分析

• 自定义outputformat，在自定义输出路径中进行数据操作。

四、代码实现

• 1、创建FilterRecordWriter 类：

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 itstarOut = 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 itstarPath = new Path("D:\\大数据API\\itstar.log");
            Path otherPath = new Path("D:\\大数据API\\other.log");

            // 3 创建输出流
            itstarOut = fs.create(itstarPath);
            otherOut = fs.create(otherPath);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
@Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {

       
        if (key.toString().contains("itstar")) {
            itstarOut.write(key.toString().getBytes());
        } else {
            otherOut.write(key.toString().getBytes());
        }
    }

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

• 2、创建FilterOutputFormat 类：

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 FileOutptFormat<Text, NullWritable>{

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

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

• 3、创建FilterMapper 类：

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、创建FilterReducer 类：

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、创建FilterDriver 类：

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[]{"D:\\大数据API\\datas.log","D:\\大数据API\\data"};

        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);
    }
}

• 输出结果：

itstar.log文件：

http://www.itstar.com
http://www.itstar.comhttp://www.baidu.com

other.log文件：

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