Hadoop 统计专利被引用次数（二）

一、在（一）中，我们计算出专利被那些专利所引用，在此基础上计算被引用的次数，不难实现。我们用两种方法来完成。代码（1）如下：

 

import java.io.IOException;

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.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.KeyValueTextInputFormat;
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 PatentCitationsCount extends Configured implements Tool{
	
	public static class PatentCitationsCountMapper extends Mapper<Text, Text, Text, IntWritable> {
		private final IntWritable length = new IntWritable();
		@Override
		protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
			String[] array = value.toString().split("[,]");
			length.set(array.length);
			context.write(key, length);
		}
	}
	
	public static class PatentCitationsCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
		private final IntWritable sumResult = new IntWritable();
		@Override
		protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
			int sum = 0;
			for (IntWritable intWritable : values) {
				sum += intWritable.get();
			}
			sumResult.set(sum);
			context.write(key, sumResult);
		}
	}
	
	@Override
	public int run(String[] args) throws Exception {
		Job job = new Job(getConf());
		job.setJarByClass(getClass());
		job.setJobName("patentcitationscount");
		
		job.setMapperClass(PatentCitationsCountMapper.class);
		job.setReducerClass(PatentCitationsCountReducer.class);
		job.setCombinerClass(PatentCitationsCountReducer.class);
		
		job.setInputFormatClass(KeyValueTextInputFormat.class);
		job.setOutputKeyClass(TextOutputFormat.class);
		
		FileInputFormat.setInputPaths(job, new Path("/patent/test/input/patentcitationscount.txt"));
		FileOutputFormat.setOutputPath(job, new Path("/patent/test/outnput"));
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		boolean success = job.waitForCompletion(true);
		return success ? 0 : 1;
	}

	public static void main(String[] args) throws Exception {
		int result = ToolRunner.run(new PatentCitationsCount(), args);
		System.exit(result);
	}
	
}

 代码2如下：

import java.io.IOException;

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.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.KeyValueTextInputFormat;
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 PatentCitationsCountOther extends Configured implements Tool {

	public static class CountOtherMapper extends Mapper<Text, Text, Text, Text> {

		@Override
		protected void map(Text key, Text value, Context context)
				throws IOException, InterruptedException {
			context.write(key, value);
		}
	}

	public static class CountOtherReducer extends
			Reducer<Text, Text, Text, IntWritable> {
		private IntWritable result = new IntWritable();

		@Override
		protected void reduce(Text key, Iterable<Text> values, Context context)
				throws IOException, InterruptedException {
			int sum = 0;
			for (Text text : values) {
				String[] array = text.toString().split("[,]");
				sum += array.length;
			}
			result.set(sum);
			context.write(key, result);
		}
	}

	@Override
	public int run(String[] args) throws Exception {
		Job job = new Job(getConf());
		job.setJarByClass(getClass());
		job.setJobName("patentcitationscountother");

		job.setMapperClass(CountOtherMapper.class);
		job.setReducerClass(CountOtherReducer.class);

		job.setInputFormatClass(KeyValueTextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);

		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);

		FileInputFormat.setInputPaths(job, new Path(
				"/patent/test/input/patentcitationscount.txt"));
		FileOutputFormat.setOutputPath(job, new Path("/patent/test/outnput"));

		boolean success = job.waitForCompletion(true);

		return success ? 0 : 1;
	}

	public static void main(String[] args) throws Exception {
		int result = ToolRunner.run(new PatentCitationsCountOther(), args);
		System.exit(result);
	}
}

 都可以实现相同的功能。但我不知道谁更好？