第3节 mapreduce高级：7、自定义outputformat实现输出到不同的文件夹下面

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

数据内容类似如下：

1 2018-03-15 22:29:06 2018-03-15 22:29:06 我想再来一个 \N 1 3 hello 来就来吧 0 2018-03-14 22:29:03
2 2018-03-15 22:42:08 2018-03-15 22:42:08 好的 \N 1 1 添加一个吧 说走咱就走啊 0 2018-03-14 22:42:04

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()

 代码：

MyOutputFormatMain ：

package cn.itcast.demo4.outputformat;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

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

        Job job = Job.getInstance(this.getConf(), MyOutputFormatMain.class.getSimpleName());
//        job.setJarByClass(MyInputFormatMain.class);
        job.setInputFormatClass(TextInputFormat.class);
        TextInputFormat.addInputPath(job,new Path("file:///D:\\Study\\BigData\\heima\\stage2\\5、大数据离线第五天\\自定义outputformat\\input"));

        job.setMapperClass(MyOutputFormatMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        job.setOutputFormatClass(MyOutputFormat.class);
        TextOutputFormat.setOutputPath(job,new Path("file:///D:\\Study\\BigData\\heima\\stage2\\5、大数据离线第五天\\自定义outputformat\\output"));

        boolean b = job.waitForCompletion(true);
        return b?0:1;
    }

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

MyOutputFormatMapper：

package cn.itcast.demo4.outputformat;

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 org.apache.hadoop.mapreduce.lib.input.FileSplit;

import java.io.IOException;

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());
    }
}

MyOutputFormat：

package cn.itcast.demo4.outputformat;

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);
        FSDataOutputStream goodComment = fileSystem.create(new Path("file:///D:\\Study\\BigData\\heima\\stage2\\5、大数据离线第五天\\自定义outputformat\\goodComment\\goodComment.txt"));

        FSDataOutputStream badComment = fileSystem.create(new Path("file:///D:\\Study\\BigData\\heima\\stage2\\5、大数据离线第五天\\自定义outputformat\\badComment\\badComment.txt"));

        MyRecordWriter myRecordWriter = new MyRecordWriter(goodComment, badComment);
        return myRecordWriter;
    }
}

MyRecordWriter：

package cn.itcast.demo4.outputformat;

import org.apache.commons.io.IOUtils;
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 MyRecordWriter extends RecordWriter<Text,NullWritable> {
    //定义我们两个输出流，分别输出到不同的文件夹下面去
    private FSDataOutputStream goodStream;
    private FSDataOutputStream badStream;

    public MyRecordWriter(FSDataOutputStream goodStream, FSDataOutputStream badStream) {
        this.goodStream = goodStream;
        this.badStream = badStream;
    }

    /**
     * 将我们的数据往外写
     * @param text  我们一行的评论数据
     * @param nullWritable
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    public void write(Text text, NullWritable nullWritable) throws IOException, InterruptedException {
        //1    2018-03-15 22:29:06    2018-03-15 22:29:06    我想再来一个 \N 1  3  hello  来就来吧   0  2018-03-14 22:29:03
        String[] split = text.toString().split("\t");
        Integer commentStatus = Integer.parseInt(split[9]);

        if(commentStatus<=1){//好评0、中评1数据
            //通过输出流，往外写出去数据
            goodStream.write(text.toString().getBytes());
            goodStream.write("\r\n".getBytes());//换行
        }else{//差评2数据
            badStream.write(text.toString().getBytes());
            badStream.write("\r\n".getBytes());
        }

    }

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {
        IOUtils.closeQuietly(goodStream);
        IOUtils.closeQuietly(badStream);
    }
}