hadoop对专利数据进行处理，输出专利号以及引用次数

对有如下专利数据

进行MapReduce进行处理，输出专利以及引用次数

package com.hadoop.test;

import java.io.IOException;
import java.util.Iterator;

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.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.KeyValueTextInputFormat;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * 统计每个专利被引用的次数
 * 
 * @author root 2014-12-28
 */
public class CountPatent extends Configured implements Tool {

	public static class MapClass extends MapReduceBase implements
			Mapper<Text, Text, Text, Text> {

		@Override
		public void map(Text key, Text value,
				OutputCollector<Text, Text> output, Reporter reporter)
				throws IOException {
			// TODO Auto-generated method stub
			output.collect(value, key);
		}

	}

	public static class Reduce extends MapReduceBase implements
			Reducer<Text, Text, Text, IntWritable> {

		@Override
		public void reduce(Text key, Iterator<Text> values,
				OutputCollector<Text, IntWritable> output, Reporter reporter)
				throws IOException {
			// TODO Auto-generated method stub
			int count = 0;
			while (values.hasNext()) {
				values.next();
				count++;
			}
			output.collect(key, new IntWritable(count));
		}

	}

	@Override
	public int run(String[] arg0) throws Exception {
		// TODO Auto-generated method stub
		Configuration conf = getConf();
		JobConf job = new JobConf(conf, CountPatent.class);

		Path in = new Path(arg0[0]);
		Path out = new Path(arg0[1]);

		FileInputFormat.setInputPaths(job, in);
		FileOutputFormat.setOutputPath(job, out);

		job.setJobName("CountPatent");
		job.setMapperClass(MapClass.class);
		job.setReducerClass(Reduce.class);
		
		job.setInputFormat(KeyValueTextInputFormat.class);
		job.setOutputFormat(TextOutputFormat.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		job.set("key.value.separator.in.input.line", ",");
		
		JobClient.runJob(job);
		return 0;
	}

	public static void main(String[] args) throws Exception {
		// 定义本地输入文件路径
		String inputPath = "/home/znb/test/cite75_99.txt";
		// 定义输出的HDFS文件路径
		String outputPath = "hdfs://znb:9000/output/CountPatent/";
		String[] args1 = { inputPath, outputPath };
		int res = ToolRunner.run(new Configuration(), new CountPatent(), args1);
		System.exit(res);
	}
}

实验结果如下图：