hadoop mapreduce 模板

package seven.ili.patent;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class AgeStatistics extends Configured implements Tool {  
    public static class MapClass extends Mapper<LongWritable, Text, Text, Text> {    
        public void map(LongWritable key, Text value, Context context)  
            throws IOException, InterruptedException {  
            
            String[] str = value.toString().split("\t", -2);  
            String gender = str[2];
            context.write(new Text(gender), new Text(value));
        }  
    }  

    public static class Reduce extends Reducer<Text, Text, Text, IntWritable> {  
        public int max = -1; 
        public void reduce(Text key, Iterable<Text> values, Context context)  
                throws IOException, InterruptedException {  
            max = -1;
            for (Text val : values) {  
                String[] str = val.toString().split("\t", -2);
                if (Integer.parseInt(str[3]) > max)
                    max = Integer.parseInt(str[3]);
            }
            context.write(new Text(key), new IntWritable(max));
        }   
    }
    
    public static class AgePartitioner extends Partitioner<Text, Text>{
        @Override
        public int getPartition(Text key, Text value, int numReduceTasks) {
            String[] str = value.toString().split("\t");
            int age = Integer.parseInt(str[1]);
            if (numReduceTasks == 0){
                return 0;
            }
            if (age <= 20)
                return 0;
            else if (age > 20 && age <= 50)
                return 1 % numReduceTasks;
            else
                return 2 % numReduceTasks;
        }
    }
    

    public int run(String[] args) throws Exception {  
        Configuration conf = getConf();  
        Job job = new Job(conf, "TopKNum");  
        job.setJarByClass(AgeStatistics.class);  
        FileInputFormat.setInputPaths(job, new Path(args[0]));  
        FileOutputFormat.setOutputPath(job, new Path(args[1]));  
        job.setMapperClass(MapClass.class);  
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        //job.setCombinerClass(Reduce.class); 
        job.setPartitionerClass(AgePartitioner.class);
        job.setReducerClass(Reduce.class);  
        job.setNumReduceTasks(3);
        job.setInputFormatClass(TextInputFormat.class);  
        job.setOutputFormatClass(TextOutputFormat.class);  
        job.setOutputKeyClass(Text.class);  
        job.setOutputValueClass(IntWritable.class); 
        System.exit(job.waitForCompletion(true) ? 0 : 1);  
        return 0;  
    }  
    public static void main(String[] args) throws Exception {  
        int res = ToolRunner.run(new Configuration(), new AgeStatistics(), args);  
        System.exit(res);  
    }  

}