Hadoop MapReduce开发--升序排序数据，且数据不去重

测试数据：

file1.txt

2
32
654
32
15
756
65223

file2.txt

5956
22
650
92

file3.txt

26
54
6

Mapper代码：

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 MyMapper extends Mapper<LongWritable, Text, IntWritable, NullWritable> {
    //private Text val = new Text("");
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //context.write(new IntWritable(Integer.valueOf(value.toString().trim())), val);
        context.write(new IntWritable(Integer.valueOf(value.toString().trim())), NullWritable.get());
    }
}

reduce代码：

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

import java.io.IOException;

public class MyReducer extends Reducer<IntWritable, NullWritable, IntWritable, IntWritable> {
    private IntWritable order = new IntWritable(1);

    @Override
    protected void reduce(IntWritable key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        for(NullWritable val : values) {
            context.write(order, key);
            order = new IntWritable(order.get() + 1);
        }
    }
}

 

main代码：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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;

import java.io.IOException;

/**
 * 把输入的数据，按照升序排序，并且每一行都有序号
 * 并且，相同的数据不能被去重（关键点是在reduce的for循环，如果不写for循环，则会去重）
 */
public class JobMain {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        if(args.length != 2) {
            System.err.println("Usage: SortDataExample<input path> <output path>");
            System.exit(-1);
        }

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf, "SortJob");
        job.setJarByClass(JobMain.class);

        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(IntWritable.class);
        //job.setMapOutputValueClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);

        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job, new Path(args[0]));

        Path path = new Path(args[1]);
        FileSystem fs = FileSystem.get(conf);
        if(fs.exists(path)) {
            fs.delete(path, true);
        }
        FileOutputFormat.setOutputPath(job, path);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

运行代码

把3个数据测试文件放到路径：C:…\mr_example\exp_03\下

在windows7环境下执行前需要设置HADOOP_CLASSPATH
set HADOOP_CLASSPATH=mr_example.jar
注：mr_example.jar是以上代码打成jar包的名称

执行命令
hadoop jar的全类名(包名+类名) 数据路径 输出路径

eg:
C:\hadoop-2.9.1\bin\hadoop jar的全类名（包名+类名） file:///C:…\mr_example\exp_03\*.txt C:…\mr_example\exp_03\out\

结果：

1    2
2    6
3    15
4    22
5    26
6    32
7    32
8    54
9    92
10    650
11    654
12    756
13    5956
14    65223