大資料hadoop入門案例4–OutputFormat接口輸出不同檔案中

大資料hadoop入門案例4–OutputFormat接口輸出不同檔案中

此部落格作為本文學習hadoop大資料内容，内容可能存在不夠全面或者存在偏差。

文章目錄

• • 1.OutputFormat
  • 2.代碼
  • • 2.1Mapper
    • 2.2Reducer
    • 2.3OutputFormat
    • 2.4LogLogRecordWriter
    • 2.5Driver
  • 3.輸入+輸出
  • • 3.1輸入
    • 3.2輸出

1.OutputFormat

MapReducer有預設的檔案輸出流，但是當需要根據輸入内容輸出到不同的檔案中，需要重新編寫OutputFormat。

輸出檔案繼承FileOutputFormat類，建立一個類繼承RecordWriter，還需藥傳入getConfiguration。

2.代碼

2.1Mapper

輸入索引和value輸出value和Null。

package com.root.logoutformat1;

import org.apache.hadoop.io.IntWritable;
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 {
        context.write(value,NullWritable.get());
    }
}

           

2.2Reducer

輸入，輸出都是value和Null。

package com.root.logoutformat1;

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

import java.io.IOException;

public class reducer extends Reducer<Text, NullWritable,Text,NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        for (NullWritable value : values) {
            context.write(key,value);
        }
    }
}

           

2.3OutputFormat

建立一個logoutput檔案繼承FileOutputFormat，向檔案輸出内容，但是還要實作RecordWriter類。

package com.root.logoutformat1;

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 logoutput extends FileOutputFormat<Text, NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        LogRecordWriter lrw =new LogRecordWriter(job);
        return lrw;
    }
}

           

2.4LogLogRecordWriter

在LogRecordWriter中繼承RecordWriter，并建立輸出檔案的兩條流，在write類中根據相關條件輸出資料，close類中關閉流。

package com.root.logoutformat1;

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> {

    private FSDataOutputStream baidu;
    private FSDataOutputStream other;

    public LogRecordWriter(TaskAttemptContext job) {
        //建立兩條流
        try {
            FileSystem fs = FileSystem.get(job.getConfiguration());
            baidu = fs.create(new Path("E:\\testhadoop\\output\\outlogbaidu\\baidu.log"));
            other = fs.create(new Path("E:\\testhadoop\\output\\outlogother1\\other1.log"));

        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {
        //寫檔案
        String log = key.toString();
        if (log.contains("baidu")){
            baidu.writeBytes(log);
        }else {
            other.writeBytes(log+'\n');
        }

    }

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {

        //關流
        IOUtils.closeStream(baidu);
        IOUtils.closeStream(other);
    }
}
           

2.5Driver

添加logoutput類

package com.root.logoutformat1;

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.CombineTextInputFormat;
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, InterruptedException, ClassNotFoundException {
        //1.擷取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2.設定jar包路徑
        job.setJarByClass(logdriver.class);
        //3.關聯mapper和reducer
        job.setMapperClass(logmapper.class);
        job.setReducerClass(reducer.class);
        //4.設定最終輸出的KV類型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        //5.設定map輸出<k,v>類型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        job.setOutputFormatClass(logoutput.class);
        //6.設定輸入路徑和輸出路徑
        FileInputFormat.setInputPaths(job,new Path("E:\\testhadoop\\input\\inputlog"));
        FileOutputFormat.setOutputPath(job,new Path("E:\\testhadoop\\output\\outputlog1"));
        //7.送出job
        boolean result =job.waitForCompletion(true);
        System.exit(result ? 0:1);
    }
}

           

3.輸入+輸出

3.1輸入

3.2輸出