mapreduce——invertedindex

三个输入文件分别时3/2/2行：

hadoop@ubuntu:/usr/local/hadoop$ hdfs dfs -cat input/*

hadoop mapreduce spark
hadoop windows
linux windows
hadoop wordcount inverted index
class public
apache spark mapreduce
mapper reducer

结果如下：

apache 3.txt:1;
class 2.txt:1;
hadoop 2.txt:1;1.txt:2;
index 2.txt:1;
inverted 2.txt:1;
linux 1.txt:1;
mapper 3.txt:1;
mapreduce 3.txt:1;1.txt:1;
public 2.txt:1;
reducer 3.txt:1;
spark 3.txt:1;1.txt:1;
windows 1.txt:2;
wordcount 2.txt:1;

源码：

package hadoop.examples;

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class InvertedIndex
{
	
	public static class TokenizerMapper extends Mapper<Object, Text, Text, Text>
	{
		private Text keyInfo=new Text();
		private Text valueInfo=new Text();
		private FileSplit split;
		@Override
		public void map(Object key, Text value, Context context) throws IOException, InterruptedException
		{
			//获取<key value>对所属的FileSplit对象
			split=(FileSplit) context.getInputSplit();
			StringTokenizer iter=new StringTokenizer(value.toString());
			while(iter.hasMoreTokens())
			{
				keyInfo.set(iter.nextToken().toString()+":"+split.getPath().toString());
				valueInfo.set("1");
				context.write(keyInfo, valueInfo);
			}
		}
	}
	
	public static class IndexCombiner extends Reducer<Text, Text, Text, Text>
	{
		public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException
		{
			int sumCount=0;
			for(Text val:values)
			{
				sumCount+=Integer.parseInt(val.toString());
			}
			String keyInfo=key.toString().split(":")[0];
			String[] temp=key.toString().split("/");
			String valueInfo=temp[temp.length-1]+":"+sumCount;
			context.write(new Text(keyInfo), new Text(valueInfo));
		}
	}
	
	public static class IndexReducer extends Reducer<Text, Text, Text, Text>
	{
		public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException
		{
			String valueList=new String(); //不能写到外面去
			for(Text val:values)
			{
				valueList+=val.toString()+";";
			}
			context.write(key, new Text(valueList));
		}
	}
	
	public static void main(String[] args) throws Exception
	{
		Configuration conf=new Configuration();
		String[] otherArgs=new GenericOptionsParser(conf, args).getRemainingArgs();
		if(otherArgs.length!=2)
		{
			System.out.println("Usage: InvertedIndex <in> <out>");
			System.exit(2);
		}
		Path inputPath=new Path(args[0]);
		Path outputPath=new Path(args[1]);
		outputPath.getFileSystem(conf).delete(outputPath, true);
		
		//The constructor Job(Configuration conf, String jobName) is deprecated
		//Job job=new Job(conf, "Inverted Index");
		Job job=Job.getInstance(conf, "Inverted Index");
		job.setJarByClass(InvertedIndex.class);
		
		job.setMapperClass(TokenizerMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		
		job.setCombinerClass(IndexCombiner.class);
		
		job.setReducerClass(IndexReducer.class);		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		
		FileInputFormat.addInputPath(job, inputPath);
		FileOutputFormat.setOutputPath(job, outputPath);
		
		System.exit(job.waitForCompletion(true)? 0:1);
	}
	
}