bak hadoop

import java.io.IOException;

import java.util.StringTokenizer;

 

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.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 WordCount extends Configured implements Tool {

 

    public static class Map extends

            Mapper<LongWritable, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);

        private Text word = new Text();

 

        public void map(LongWritable key, Text value, Context context)

                throws IOException, InterruptedException {

            String line = value.toString();

            StringTokenizer tokenizer = new StringTokenizer(line);

 

            while (tokenizer.hasMoreTokens()) {

                // if has tokens

                word.set(tokenizer.nextToken());

                context.write(word, one);

            }

        }

    }

 

    public static class Reduce extends

            Reducer<Text, IntWritable, Text, IntWritable> {

 

        public void reduce(Text key, Iterable<IntWritable> values,

                Context context) throws IOException, InterruptedException {

            int sum = 0;

            for (IntWritable value : values) {

                sum += value.get();

            }

            context.write(key, new IntWritable(sum));

        }

 

    }

 

    @Override

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

        // set the job configuration and its name

        Job job = new Job(this.getConf());

        job.setJarByClass(WordCount.class);

        job.setJobName("WordCount");

 

        // set the data output format

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);

 

        // set mapper and reducer

        job.setMapperClass(Map.class);

        job.setReducerClass(Reduce.class);

 

        // set intput and output format

        job.setInputFormatClass(TextInputFormat.class);

        job.setOutputFormatClass(TextOutputFormat.class);

 

        // set input and output path

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

        System.out.println(args[0]);

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

        System.out.println(args[1]);

 

        boolean success = job.waitForCompletion(true);

        return success ? 0 : 1;

    }

 

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

        System.out.println("test");

        int ret = ToolRunner.run(new Configuration(), new WordCount(), args);

        System.exit(ret);

    }

}