MapReduce的自定义OutputFormat

OutputFormat类

import org.apache.hadoop.conf.Configuration;
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;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class MyOutputFormat extends FileOutputFormat<Text,NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext context) throws IOException, InterruptedException {
        Configuration conf = context.getConfiguration();
        FileSystem fileSystem = FileSystem.get(conf);
        //好评输出流
        FSDataOutputStream fsDataOutputStreamGood = fileSystem.create(new Path("将结果1写入那个文件"));
        //中差评输出流
        FSDataOutputStream fsDataOutputStreamBad = fileSystem.create(new Path("将结果2写入那个文件"));
        MyRW myRW = new MyRW(fsDataOutputStreamGood,fsDataOutputStreamBad);
        return myRW;
    }
}

RecordWriter类

import org.apache.hadoop.fs.FSDataOutputStream;
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 MyRW extends RecordWriter<Text, NullWritable> {
    FSDataOutputStream fsDataOutputStreamGood=null;
    FSDataOutputStream fsDataOutputStreamBad=null;

    @Override
    public void write(Text text, NullWritable nullWritable) throws IOException, InterruptedException {
        String[] split = text.toString().split("\t");
        if (split[9].equals("0")){
            fsDataOutputStreamGood.write(text.toString().getBytes());
            fsDataOutputStreamGood.write("\r\n".getBytes());
        }else{
            fsDataOutputStreamBad.write(text.toString().getBytes());
            fsDataOutputStreamBad.write("\r\n".getBytes());
        }
    }
    @Override
    public void close(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        if (fsDataOutputStreamGood!=null){
            fsDataOutputStreamGood.close();
        }
        if (fsDataOutputStreamBad!=null){
            fsDataOutputStreamBad.close();
        }
    }
    public MyRW(FSDataOutputStream fsDataOutputStreamGood,FSDataOutputStream fsDataOutputStreamBad) {
        this.fsDataOutputStreamGood=fsDataOutputStreamGood;
        this.fsDataOutputStreamBad=fsDataOutputStreamBad;
    }
    public MyRW() {
    }
}

map类

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

驱动类

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.TextInputFormat;

public class MyDriver {
    public static void main(String[] args) throws Exception {
        Configuration conf= new Configuration();
        Job job= Job.getInstance(conf);
        job.setJarByClass(MyDriver.class);
        job.setMapperClass(MyMap.class);
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("C:\\Users\\Administrator\\Desktop\\aaa"));
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        job.setOutputFormatClass(MyOutputFormat.class);
        MyOutputFormat.setOutputPath(job,new Path("C:\\Users\\Administrator\\Desktop\\output"));
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        System.exit(job.waitForCompletion(true)?0:1);


    }
}