hadoop2.2编程：从default mapreduce program 来理解mapreduce

下面写一个default mapreduce 的程序：

 1 import org.apache.hadoop.mapreduce.Mapper;

 2 import org.apache.hadoop.mapreduce.Reducer;

 3 import org.apache.hadoop.conf.Configuration;

 4 import org.apache.hadoop.conf.Configured;

 5 import org.apache.hadoop.fs.Path;

 6 import org.apache.hadoop.util.Tool;

 7 import org.apache.hadoop.util.ToolRunner;

 8 import org.apache.hadoop.mapreduce.Job;

 9 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

10 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 

11 

12 

13 public class DefaultMapReduce extends Configured implements Tool {

14     @Override

15     public int run(String[] args) throws Exception {

16         Configuration conf = getConf();

17         Job job = Job.getInstance(conf);

18         job.setJarByClass(getClass());

19         job.setNumReduceTasks(10);

20         

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

22         FileOutputFormat.setOutputPath(job, new Path(args[1]));

23         

24         return job.waitForCompletion(true) ? 0 : 1;

25     }

26     

27     public static void main(String[] args) throws Exception {

28         ToolRunner.run(new DefaultMapReduce(), args);

29     }

30 }