addcharacter.java

java树型字典的建立,是中文分词 检索的基础

package ECDictionaryUtil;
import java.io.IOException;
import java.io.ObjectOutputStream;
import java.util.HashMap;
public class AddCharacter {
    
	/**
	 * 把字符串的汉字添加到词典中
	 */
	ObjectOutputStream os;
	
	HashMap hm0=null;
	static ObjectHead ohead;
	public static void setObjectHead(ObjectHead oheads){
		ohead=oheads;
	}
	public void setObjectStream(ObjectOutputStream os){
		this.os=os;
	}
	/*
	 * 以下代码是添加字符串头汉字到词典中
	 */
	public void addHead(String headChara) throws Exception{  //headChara有且只有一个汉字
	  try{
		  
		  HashMap hm=ohead.getHashMap();
		  if(hm.containsKey(new Integer(new CharaCode().getCharaCode(headChara)))){   //如果已经包含次头汉字，则取出此汉字的HashMap
			  CharacterObject charaOb=(CharacterObject)hm.get(new Integer(new CharaCode().getCharaCode(headChara)));
			  this.hm0=(HashMap)charaOb.getHashMap();
			  
		  }else{                          //不包含此头汉字，则新建一个汉字到词典中，并取出这个汉字的HashMap
			  CharacterObject charaOb=new CharacterObject();
			  charaOb.setChara(headChara);
			  hm.put(new Integer(new CharaCode().getCharaCode(headChara)),charaOb);
			  hm0=charaOb.getHashMap();
		  }
		  
	  }catch(IOException ee){
		  ee.printStackTrace();
	  }
	}
	/*
	 * * 以下代码是添加字符串中间汉字到词典中
	 */
	public void addMiddleChara(String middleChara) throws Exception{
		try{
			if(this.hm0.containsKey(new Integer(new CharaCode().getCharaCode(middleChara)))){   //如果已经包含次头汉字，则取出此汉字的HashMap
				  CharacterObject charaOb=(CharacterObject)this.hm0.get(new Integer(new CharaCode().getCharaCode(middleChara)));
				  this.hm0=(HashMap)charaOb.getHashMap();
				  
			  }else{                          //不包含此头汉字，则新建一个汉字到词典中，并取出这个汉字的HashMap
				  CharacterObject charaOb=new CharacterObject();
				  charaOb.setChara(middleChara);
				  this.hm0.put(new Integer(new CharaCode().getCharaCode(middleChara)),charaOb);
				  this.hm0=charaOb.getHashMap();
			  }
			
		
		}catch(Exception ee){
			ee.printStackTrace();
		}
	}		
		
	public void addTail(String tailChara){
		try{
			if(this.hm0.containsKey(new Integer(new CharaCode().getCharaCode(tailChara)))){   //如果已经包含次头汉字，则取出此汉字的HashMap
				  CharacterObject charaOb=(CharacterObject)this.hm0.get(new Integer(new CharaCode().getCharaCode(tailChara)));
				  charaOb.setIsEnd(true);
				  
			  }else{                          //不包含此头汉字，则新建一个汉字到词典中，并取出这个汉字的HashMap
				  CharacterObject charaOb=new CharacterObject();
				  charaOb.setChara(tailChara);
				  charaOb.setIsEnd(true);
				  this.hm0.put(new Integer(new CharaCode().getCharaCode(tailChara)),charaOb);
				  
			  }
			
		
		}catch(Exception ee){
			ee.printStackTrace();
		}
		
	}
	public void saveCharacter() throws IOException{
		try{
			os.writeObject(ohead);
			
		}catch(IOException ee){
			ee.printStackTrace();
		}
	}
	public static void main(String[] args) throws Exception {
		
		
	}

}