MapReduce 按照Value值进行排序输出，mapreducevalue
文件输入：
A 1
B 5
C 4
E 1
D 3
W 9
P 7
Q 2
文件输出：
W 9
P 7
B 5
C 4
D 3
Q 2
E 1
A 1
代码如下：
package comparator;
import java.io.IOException;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.IntWritable.Comparator;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class comparator{
/**
* @param args
* @throws IOException
* @throws IllegalArgumentException
* @throws InterruptedException
* @throws ClassNotFoundException
*/
public static class myComparator extends Comparator {
@SuppressWarnings("rawtypes")
public int compare( WritableComparable a,WritableComparable b){
return -super.compare(a, b);
}
public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) {
return -super.compare(b1, s1, l1, b2, s2, l2);
}
}
public static class Map extends Mapper<Object,Text,IntWritable,Text>{
public void map(Object key,Text value,Context context) throws NumberFormatException, IOException, InterruptedException{
String[] split = value.toString().split("\t");
context.write(new IntWritable(Integer.parseInt(split[1])),new Text(split[0]) );
}
}
public static class Reduce extends Reducer<IntWritable,Text,Text,IntWritable>{
public void reduce(IntWritable key,Iterable<Text>values,Context context) throws IOException, InterruptedException{
for (Text text : values) {
context.write( text,key);
}
}
}
public static void main(String[] args) throws IllegalArgumentException, IOException, ClassNotFoundException, InterruptedException {
// TODO Auto-generated method stub
Job job = new Job();
job.setJarByClass(comparator.class);
job.setNumReduceTasks(1); //设置reduce进程为1个，即output生成一个文件
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setMapOutputKeyClass(IntWritable.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class); //为job的输出数据设置key类
job.setOutputValueClass(IntWritable.class); //为job的输出设置value类
job.setSortComparatorClass( myComparator.class); //自定义排序
FileInputFormat.addInputPath(job, new Path(args[0])); //设置输入文件的目录
FileOutputFormat.setOutputPath(job,new Path(args[1])); //设置输出文件的目录
System.exit(job.waitForCompletion(true)?0:1); //提交任务
}
}
版权声明：本文为博主原创文章，未经博主允许不得转载。