自定义OutputFormat案例

FilterMapper
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
package 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 java.io.IOException;

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

FilterReducer
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
package outputformat;

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

import java.io.IOException;

public class FilterReducer extends Reducer<Text, NullWritable,Text,NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        String line=key.toString();
        line=line+"\n";
        //防止有重复的数据
        for (NullWritable nullWritable:
             values) {
            context.write(new Text(line),NullWritable.get());
        }
    }
}

FilterOutputFormat
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
package outputformat;

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 FilterOutputFormat extends FileOutputFormat<Text,NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        return new FRecordWriter(taskAttemptContext);
    }
}

FRecordWriter
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
package outputformat;

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 FRecordWriter extends RecordWriter<Text, NullWritable> {

    FSDataOutputStream fos_xiaojia;
    FSDataOutputStream fos_other;

    public FRecordWriter(TaskAttemptContext taskAttemptContext) {
        try {
            FileSystem fs=FileSystem.get(taskAttemptContext.getConfiguration());
            fos_xiaojia = fs.create(new Path("d://xiaojia.log"));
            fos_other = fs.create(new Path("d://other.log"));

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

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {
        if(key.toString().contains("xiaojia")){
            fos_xiaojia.write(key.toString().getBytes());
        }else{
            fos_other.write(key.toString().getBytes());
        }
    }

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

FilterDriver
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
package outputformat;

import org.apache.hadoop.conf.Configuration;
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.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 {
        Configuration conf=new Configuration();
        Job job=Job.getInstance(conf);
        FileSystem fs = FileSystem.get(conf);
        Path out=new Path("d://test/output");
        if(fs.exists(out)){
            fs.delete(out,true);
        }
        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);
        job.setOutputFormatClass(FilterOutputFormat.class);
        FileInputFormat.setInputPaths(job,new Path("d://test/input/*"));
        FileOutputFormat.setOutputPath(job,out);
        boolean result = job.waitForCompletion(true);
        System.exit(result?0:1);
    }
}