java分词算法的实现，自定义词典

	        
package com.rshare.utils;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.util.ArrayList;
import java.util.List;
import org.apache.commons.lang.StringUtils;

/**
 * www.wouuz.com
 * @author jspanjsp
 *
 */
public class WordTest {

		public static void main(String args[]){
			String path = "C:\Users\jspanjsp\Desktop\word1.txt";
			WordTest wordTest = new WordTest();
			List<String> words = wordTest.getWordDictionary(path);			//分词词典
			List<String> wordList = wordTest.getWordList("查询粉刺字典分词地址",words);	//查询语句分词
			StringBuilder sb1 = new StringBuilder();
			for (String string : wordList) {
				sb1.append(string).append(",");
			}
			System.out.println("查询关键字："+sb1.toString());
		}
		
		//判断当前查询标题包含的关键词密度
		public int getkeywordDensity(List<String> words,List<String> title) {
			int num = 0;
			for (String string : title) {
				if(words.contains(string)) {
					num += 1;
				}
			}
			return num;
		}
		
		//获取词典
		public List<String> getWordDictionary(String wordPath){
			List<String> wordList = new ArrayList<String>();	//词典
			BufferedReader br = null;
			try {
				File file = new File(wordPath);
				br = new BufferedReader(new InputStreamReader(new FileInputStream(file),"utf-8"));
				String temp = null;
				while((temp=br.readLine())!=null) {
					if(temp.contains(";")) {
						String[] word = temp.split(";");
						for (int i = 0; i < word.length; i++) {
							wordList.add(word[i]);
						}
					}else {
						wordList.add(temp);
					}
				}
			} catch (Exception e) {
				e.printStackTrace();
			}
			return wordList;
		}
		
		public List<String> getWordList(String a,List<String> wordList){
			List<String> splitWords = new ArrayList<String>();
			if(StringUtils.isBlank(a)) {
				return splitWords;
			}
			//String[] cs =  {"你好","请问","什么","名字","springboot","java","mysql","CentOS","编译","Python3","Python2","句子"};//词典
			a = a.toLowerCase();
			String[] cs2 = new String[100]; //结果数组
			int jud=0;//找到匹配字符串与否的标志
			int j=0;
			String temp=null;//初始化临时字符串
			for(;a.length()>0;)
			{
				for(int i = 0;i<a.length();i++)
				{
					temp = a.substring(i);//每次截取掉首个字符
					if(isin(wordList,temp) == true)//如果目标字符串在数组中
					{
						cs2[j] = temp;
						jud = 1;
						int number = temp.length();
						a = a.substring(0,a.length()-number);
					}
				}
				if(jud == 0)//没有找到匹配字符串
				{
					cs2[j] = a.substring(a.length()-1,a.length());//将最后一个元素放在cs2里面
					a = a.substring(0, a.length()-1);//截掉最后一个元素继续循环。	
				}
				jud = 0;
				j++;
			}
			
			for(;j >= 0;j--){
				if(cs2[j] != null) {
					if(cs2[j].length()>=2) {
						//System.out.print(cs2[j]+"	");
						splitWords.add(cs2[j]);
					}	
				}	
			}	
			return splitWords;
		}
		
		/*
		 * 下面为判断字符串是否在词典中的函数方法
		*/
		
		static public boolean isin(List<String> wordList,String temp)//判断目标字符串是否在对比字符串数组中
		{
			int i;
			for(i = 0;i<wordList.size();)
			{
				if(temp.equals(wordList.get(i)))
					i = wordList.size()+1;
				else
					i++;
			}
			if(i == wordList.size()+1)
				return true;
			else
				return false;
		}
}