package?com.Test4;

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.lib.input.FileInputFormat;
import?org.apache.hadoop.mapreduce.lib.input.FileSplit;
import?org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import?org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;

import?java.io.FileInputStream;
import?java.io.IOException;
import?java.net.URI;
import?java.util.ArrayList;
import?java.util.List;
import?java.util.Scanner;
import?java.util.Set;
import?java.util.StringTokenizer;
import?java.util.TreeSet;
import?java.util.regex.Matcher;
import?java.util.regex.Pattern;

public?class?InvertedIndex?{
	public?static?class?myMap?extends?Mapperject?Text?Text?IntWritable>{
		private?final?static?IntWritable?one?=?new?IntWritable（1）;
		private?URI[]?remoteFiles;?//?存放停用詞txt文檔統(tǒng)一資源標(biāo)識(shí)符?
		private?Set?stopwords;?//存放停用詞?
		public?void?setup（Context?context）?throws?IOException?InterruptedException{
			Configuration?conf?=?context.getConfiguration（）;
			?remoteFiles?=?Job.getInstance（conf）.getCacheFiles（）;//獲取stop_words.txt?
			?stopwords?=?new?TreeSet（）;?//對(duì)于URI列表里的每一個(gè)停用詞表?
			?for?（int?i?=?0;?i?				?FileInputStream?in?=new?FileInputStream（new?Path（remoteFiles[i].getPath（））.getName（）.toString（））;
				?//讀取文件的每一行?
				?Scanner?sc?=new?Scanner（in）;?
				?while?（sc.hasNextLine（））?{
					?String?line?=?sc.nextLine（）;
					?String[]?split?=?line.trim（）.split（“?“）;?//trim（）:去掉空格?制表符等，split（“?“）:依據(jù)文件格式可用可不用‘
					?for?（int?j?=?0;?j?						?stopwords.add（split[j]）;?
					?}
				}
				sc.close（）;
			?}
????	}
		
		public?void?map（object?key?Text?value?Context?context）?throws?IOException?InterruptedException?{
			FileSplit?inputSplit?=?（FileSplit）?context.getInputSplit（）;?
			String?filename=inputSplit.getPath（）.getName（）;?//獲取文件名?
			//正則表達(dá)式去除特殊字符
			String?str?=?“\\w+“;//字母或數(shù)字或下劃線或漢字
			Pattern?pattern?=?Pattern.compile（str）;
			String?line?=?value.toString（）.toLowerCase（）;
			StringTokenizer?itr?=?new?StringTokenizer（line）;
			String?temp?=?new?String（）;
			for（;?itr.hasMoreTokens（）;）?{
				temp?=?itr.nextToken（）;
				Matcher?ma?=?pattern.matcher（temp）;
				while（ma.find（））?{
					String?word?=?ma.group（）;
					if（!stopwords.contains（word））?{
						Text?text?=?new?Text（）;
						text.set（word+“#“+filename）;?//key?=?word+#+filename
						context.write（text?one）;
					}
				}
			}
		}
	}
	public?static?class?myCombiner?extends?Reducer{
		public?void?reduce（Text?key?Iterable?values?Context?context）?throws?IOException?InterruptedException?{
			int?sum?=?0;
			for?（IntWritable?val?:?values）?{