Hadoop--引用记数直方图

package com.smartmap.example;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.Reducer.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class CitationHistogram {
	public static class MapClass extends Mapper<Text, Text, IntWritable, IntWritable> {
		private final static IntWritable uno = new IntWritable(1);
		private IntWritable citationCount = new IntWritable();

		public void map(Text key, Text value, Context context) throws IOException, InterruptedException {
			try {
				if (Integer.parseInt(value.toString()) > 0) 
				{
					citationCount.set(Integer.parseInt(value.toString()));
					context.write(citationCount, uno);
				}
			} catch (NumberFormatException e) {
			}
		}
	}

	public static class ReduceClass extends
			Reducer<IntWritable, IntWritable, IntWritable, IntWritable> {
		public void reduce(IntWritable key, Iterable<IntWritable> values,
				Context context) throws IOException, InterruptedException {
			int count = 0;
			for (IntWritable val : values) {
				count += val.get();
			}
			context.write(key, new IntWritable(count));
		}
	}

	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		String[] otherArgs = new GenericOptionsParser(conf, args)
				.getRemainingArgs();
		if (otherArgs.length != 2) {
			System.err.println("Usage: CiteCount <int> <out>");
			System.exit(2);
		}
		conf.set("key.value.separator.in.input.line", ",");
		Path in = new Path(args[0]);
		Path out = new Path(args[1]);
		Job job = new Job(conf);
		job.setJarByClass(CitationHistogram.class);
		job.setMapperClass(MapClass.class);
		job.setReducerClass(ReduceClass.class);
		job.setInputFormatClass(KeyValueTextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);
		job.setOutputKeyClass(IntWritable.class);
		job.setOutputValueClass(IntWritable.class);
		FileInputFormat.addInputPath(job, in);
		FileOutputFormat.setOutputPath(job, out);
		System.exit(job.waitForCompletion(true) ? 0 : 1);

	}
}

-----------------------------------------------------------------------------------------------------

hdfs://192.168.1.30:9000/data/cite /opt/eclipse/workspace/data/out