自定义InputFormat和OutputFormat

1. 自定义InputFormat合并小文件

1.1 需求

无论hdfs还是mapreduce，对于小文件都有损效率，实践中，又难免面临处理大量小文件的场景，此时，就需要有相应解决方案

1.2 分析

小文件的优化无非以下几种方式：

1、 在数据采集的时候，就将小文件或小批数据合成大文件再上传HDFS

2、 在业务处理之前，在HDFS上使用mapreduce程序对小文件进行合并

3、 在mapreduce处理时，可采用combineInputFormat提高效率

1.3 实现

本节实现的是上述第二种方式

程序的核心机制：

自定义一个InputFormat

改写RecordReader，实现一次读取一个完整文件封装为KV

在输出时使用SequenceFileOutPutFormat输出合并文件

代码如下：

自定义InputFromat

package demo01;


import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;


import java.io.IOException;

public class MyinputFormat extends FileInputFormat<NullWritable, BytesWritable> {
    //
    @Override
    public RecordReader<NullWritable, BytesWritable> createRecordReader(InputSplit inputSplit, TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        //1.创建自定义RecordReader对象
        MyRecordReader myRecordReader=new MyRecordReader();

        //2.将inputSplit和context 对象传给RecordReader
        myRecordReader.initialize(inputSplit, taskAttemptContext);
        return myRecordReader;
    }

    //设置文件是否可以被切割
    @Override
    protected boolean isSplitable(JobContext context, Path filename) {
        return false;
    }
}

自定义RecordReader

package demo01;

import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

public class MyRecordReader  extends RecordReader<NullWritable, BytesWritable> {
    private Configuration configuration=null;
    private FileSplit fileSplit=null;
    private boolean processed=false;
    private BytesWritable bytesWritable = new BytesWritable();
    private FileSystem fileSystem=null;
    private FSDataInputStream inputStream=null;
    //初始化
    @Override
    public void initialize(InputSplit inputSplit, TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
    //获取configuration对象
        configuration=taskAttemptContext.getConfiguration();
    //获取文件的切片
         fileSplit=(FileSplit)inputSplit;

    }
    //该方法用于获取K1和V1
    /*
    * K1：NullWritable
    * V2:BytesWritable
    * */
    @Override
    public boolean nextKeyValue() throws IOException, InterruptedException {
        if(!processed) {
            //1.读取源文件的字节输入流
            //1.1 获取源文件的文件系统(FileSystem)
            fileSystem = FileSystem.get(configuration);
            //1.2 通过FileSystem，获取文件字节输入流
            inputStream = fileSystem.open(fileSplit.getPath());

            //2.读取源文件数据到普通的字节数组(byte[])
            byte[] bytes = new byte[(int) fileSplit.getLength()];
            IOUtils.readFully(inputStream, bytes, 0, (int) fileSplit.getLength());
            //3.将字节数组中数据封装到BytesWritable,得到V1

            bytesWritable.set(bytes, 0, (int) fileSplit.getLength());

            processed=true;
            return processed;
        }
        return false;
    }

    //返回K1
    @Override
    public NullWritable getCurrentKey() throws IOException, InterruptedException {
        return NullWritable.get();
    }
    //返回v1
    @Override
    public BytesWritable getCurrentValue() throws IOException, InterruptedException {
        return bytesWritable ;
    }
    //获取文件读取进度
    @Override
    public float getProgress() throws IOException, InterruptedException {
        return 0;
    }
    //进行资源释放
    @Override
    public void close() throws IOException {
        inputStream.close();
        fileSystem.close();
    }
}

Mapper类:

package demo01;

import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

public class SequenceFileMapper extends Mapper<NullWritable, BytesWritable,Text,BytesWritable> {
    //1.获取文件的名字,作为K2
   
    @Override
    protected void map(NullWritable key, BytesWritable value, Context context) throws IOException, InterruptedException {
        FileSplit fileSplit= (FileSplit)context.getInputSplit();
        String filename =fileSplit.getPath().getName();

        //2.将k2和v2写入上下文当中
        context.write(new Text(filename),value);
    }
}

主类:

package demo01;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class JobMain extends Configured implements Tool {
    @Override
    public int run(String[] strings) throws Exception {

        Job job = Job.getInstance(super.getConf(), "qequence_file_job");
        //2.设置job任务
            //第一步：设置输入类和输入的路径
        job.setInputFormatClass(MyinputFormat.class);
        MyinputFormat.addInputPath(job,new Path("file:///D:\\input\\myInputformat_input"));
            //第二步：设置Mapper类和数据类型
        job.setMapperClass(SequenceFileMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(BytesWritable.class);
            //....

            //第七步:不设置reducer类，设置数据类型

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(BytesWritable.class);
        //第八步：设置输出类和输出路径
        job.setOutputFormatClass(SequenceFileOutputFormat.class);
        SequenceFileOutputFormat.setOutputPath(job,new Path("file:///D:\\out\\myinputformat"));

        boolean b = job.waitForCompletion(true);

        //3.等待job任务执行结束
        return  b ?0:1;

    }

    public static void main(String[] args) throws Exception {
        Configuration configuration =new Configuration();
        int run = ToolRunner.run(configuration, new JobMain(), args);
        System.exit(run);
    }
}

2.1 需求

现在有一些订单的评论数据，需求，将订单的好评与差评进行区分开来，将最终的数据分开到不同的文件夹下面去，数据内容参见资料文件夹，其中数据第九个字段表示好评，中评，差评。0：好评，1：中评，2：差评

2.2 分析

程序的关键点是要在一个mapreduce程序中根据数据的不同输出两类结果到不同目录，这类灵活的输出需求可以通过自定义outputformat来实现

2.3 实现

实现要点：

1、 在mapreduce中访问外部资源

2、 自定义outputformat，改写其中的recordwriter，改写具体输出数据的方法write()

MyOutputFormat类:

第一步：自定义MyOutputFormat

public class MyOutputFormat extends FileOutputFormat<Text,NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        //1:获取目标文件的输出流(两个)
        FileSystem fileSystem = FileSystem.get(taskAttemptContext.getConfiguration());
        FSDataOutputStream goodCommentsOutputStream = fileSystem.create(new Path("file:///D:\\out\\good_comments\\good_comments.txt"));
        FSDataOutputStream badCommentsOutputStream = fileSystem.create(new Path("file:///D:\\out\\bad_comments\\bad_comments.txt"));

        //2:将输出流传给MyRecordWriter
        MyRecordWriter myRecordWriter = new MyRecordWriter(goodCommentsOutputStream,badCommentsOutputStream);

        return myRecordWriter;
    }
}

MyRecordReader类:

public class MyRecordWriter extends RecordWriter<Text,NullWritable> {
    private FSDataOutputStream goodCommentsOutputStream;
    private FSDataOutputStream badCommentsOutputStream;

    public MyRecordWriter() {
    }

    public MyRecordWriter(FSDataOutputStream goodCommentsOutputStream, FSDataOutputStream badCommentsOutputStream) {
        this.goodCommentsOutputStream = goodCommentsOutputStream;
        this.badCommentsOutputStream = badCommentsOutputStream;
    }

    /**
     *
     * @param text  行文本内容
     * @param nullWritable
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    public void write(Text text, NullWritable nullWritable) throws IOException, InterruptedException {
        //1:从行文本数据中获取第9个字段
        String[] split = text.toString().split("\t");
        String numStr = split[9];

        //2:根据字段的值,判断评论的类型,然后将对应的数据写入不同的文件夹文件中
        if(Integer.parseInt(numStr) <= 1){
            //好评或者中评
            goodCommentsOutputStream.write(text.toString().getBytes());
            goodCommentsOutputStream.write("\r\n".getBytes());
        }else{
            //差评
            badCommentsOutputStream.write(text.toString().getBytes());
            badCommentsOutputStream.write("\r\n".getBytes());
        }

    }

    @Override
    public void close(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        IOUtils.closeStream(goodCommentsOutputStream);
        IOUtils.closeStream(badCommentsOutputStream);
    }
}

第二步：自定义Mapper类

public class MyOutputFormatMapper extends Mapper<LongWritable,Text,Text,NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        context.write(value, NullWritable.get());
    }
}

第三步:主类JobMain

public class JobMain extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {
        //1:获取job对象
        Job job = Job.getInstance(super.getConf(), "myoutputformat_job");

        //2:设置job任务
            //第一步:设置输入类和输入的路径
            job.setInputFormatClass(TextInputFormat.class);
            TextInputFormat.addInputPath(job, new Path("file:///D:\\input\\myoutputformat_input"));

            //第二步:设置Mapper类和数据类型
            job.setMapperClass(MyOutputFormatMapper.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(NullWritable.class);

            //第八步:设置输出类和输出的路径
            job.setOutputFormatClass(MyOutputFormat.class);
            MyOutputFormat.setOutputPath(job, new Path("file:///D:\\out\\myoutputformat_out"));


        //3:等待任务结束
        boolean bl = job.waitForCompletion(true);
        return bl ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        Configuration configuration = new Configuration();
        int run = ToolRunner.run(configuration, new JobMain(), args);
        System.exit(run);
    }
}