创建索引(Luncene + paoding)

 

一、先去网上Down下来 paoding-analysis-2.0.4-beta，解压，在lib目录找到lucene-core-2.2.0.jar，lucene-highlighter-2.2.0.jar，commons-logging.jar 这几个Jar包放到项目当中。

二、添加Paoding。 在项目中使用发现，直接添加paoding-analysis.jar会发生异常。所以我们不直接添加这个Jar，而是把Src目录下的所有文件(也就是源代码) copy 都我们项目的Src目录下;

三、把dic(词典)目录也copy 到我们项目的src下，并在Src目录新建一个包data.index,主要是用来存放生成的索引文件;

四、修改 paoding-dic-home.properties 这个属性文件

#values are "system-env" or "this";
#if value is "this" , using the paoding.dic.home as dicHome if configed!
#paoding.dic.home.config-fisrt=system-env

#dictionary home (directory)
#"classpath:xxx" means dictionary home is in classpath.
#e.g "classpath:dic" means dictionaries are in "classes/dic" directory or any other classpath directory
#paoding.dic.home=dic

#seconds for dic modification detection
#paoding.dic.detector.interval=60
paoding.dic.home=classpath:dic // dic 所在目录
paoding.dic.home.config-fisrt=this //应用当前的配置

 

五、在 package   net.paoding.analysis.knife 下找到PaodingMaker类， Ctrl + S + O 定位到

private static void setDicHomeProperties(Properties p) 这个方法，修改

private static void setDicHomeProperties(Properties p) {
   String dicHomeAbsultePath = p
     .getProperty("paoding.dic.home.absolute.path");
   if (dicHomeAbsultePath != null) {
    return;
   }
   // 获取词典安装目录配置：
   // 如配置了PAODING_DIC_HOME环境变量，则将其作为字典的安装主目录
   // 否则使用属性文件的paoding.dic.home配置
   // 但是如果属性文件中强制配置paoding.dic.home.config-first=this，
   // 则优先考虑属性文件的paoding.dic.home配置，
   // 此时只有当属性文件没有配置paoding.dic.home时才会采用环境变量的配置
   String dicHomeBySystemEnv = null;
   try {
    dicHomeBySystemEnv = getSystemEnv(Constants.ENV_PAODING_DIC_HOME);
   } catch (Error e) {
    log.warn("System.getenv() is not supported in JDK1.4. ");
   }
   String dicHome = getProperty(p, Constants.DIC_HOME);
   if (dicHomeBySystemEnv != null) {
    String first = getProperty(p, Constants.DIC_HOME_CONFIG_FIRST);
    if (first != null && first.equalsIgnoreCase("this")) {
     if (dicHome == null) {
      dicHome = dicHomeBySystemEnv;
     }
    } else {
     dicHome = dicHomeBySystemEnv;
    }
   }
   // 如果环境变量和属性文件都没有配置词典安转目录
   // 则尝试在当前目录和类路径下寻找是否有dic目录，
   // 若有，则采纳他为paoding.dic.home
   // 如果尝试后均失败，则抛出PaodingAnalysisException异常
   if (dicHome == null) {
    File f = new File("dic");
    if (f.exists()) {
     dicHome = "dic/";
    } else {
     URL url = PaodingMaker.class.getClassLoader()
       .getResource("dic");
     if (url != null) {
      dicHome = "classpath:dic/";
     }
    }
   }
   if (dicHome == null) {
    throw new PaodingAnalysisException(
      "please set a system env PAODING_DIC_HOME or Config paoding.dic.home in paoding-dic-home.properties point to the dictionaries!");
   }
   // 规范化dicHome，并设置到属性文件对象中
   dicHome = dicHome.replace('\\', '/');
   if (!dicHome.endsWith("/")) {
    dicHome = dicHome + "/";
   }
   p.setProperty(Constants.DIC_HOME, dicHome);// writer to the properites
   //修改部分
   String path="";
   try {
   
    path = URLDecoder.decode(getFile(dicHome).getPath(), "utf-8");
   } catch (Exception e) {
    // TODO Auto-generated catch block
    e.printStackTrace();
   }
  
   // object
   // 将dicHome转化为一个系统唯一的绝对路径，记录在属性对象中
   File dicHomeFile = getFile(path);
//修改部分结束
   if (!dicHomeFile.exists()) {
    throw new PaodingAnalysisException(
      "not found the dic home dirctory! "
        + dicHomeFile.getAbsolutePath());
   }
   if (!dicHomeFile.isDirectory()) {
    throw new PaodingAnalysisException(
      "dic home should not be a file, but a directory!");
   }
   p.setProperty("paoding.dic.home.absolute.path", dicHomeFile
     .getAbsolutePath());
}

 

六、创建一个Servlet：AnalyzerServlet

 

package com.lunceneTest.servlet;

import java.io.IOException;
import java.net.URLDecoder;
import java.util.List;

import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;


import net.paoding.analysis.analyzer.PaodingAnalyzer;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.FSDirectory;

import com.lunceneTest.Model.News;
import com.lunceneTest.db.NewsDao;

public class AnalyzerServlet extends HttpServlet {

/**
* 
*/
private static final long serialVersionUID = -822638045647816348L;

public void doPost(HttpServletRequest request, HttpServletResponse response)
    throws ServletException, IOException {

  
  
}
public void doGet(HttpServletRequest request, HttpServletResponse response)
throws ServletException, IOException {


   try
   {
    this.createIndex();
   
   } catch (Exception e)
   {
    e.printStackTrace();
   }
}


public void createIndex() throws Exception
{
   //实例化分词器，使用中文分词器
   Analyzer analyzer =new PaodingAnalyzer();
  
  
   String path = URLDecoder.decode(AnalyzerServlet.class.getResource("/data/index").toString(),"UTF-8").replace("file:/","");
  
   System.out.println(path);
  
   FSDirectory directory = FSDirectory.getDirectory(path);
  
   // true表示覆盖原来已经创建的索引,如果是false表示不覆盖，而是继续添加索引
  
   IndexWriter writer = new IndexWriter(directory,analyzer,true);
  
  
   List<News> list = NewsDao.getAllNews(); // Dao层获取数据库新闻列表的方法
  
   for (News news : list) {
   
    Document doc = new Document();
   
    //Field.Index.UN_TOKENIZED 不分词
    Field id_filed = new Field(News.ID,String.valueOf(news.getId()),Field.Store.YES,Field.Index.UN_TOKENIZED);
    Field title_field = new Field(News.TITLE,news.getTitle(),Field.Store.YES,Field.Index.TOKENIZED);
    Field content_field = new Field(News.CONTENT,news.getContent(),Field.Store.YES,Field.Index.TOKENIZED);
   
    doc.add(id_filed);
    doc.add(title_field);
    doc.add(content_field);

    writer.addDocument(doc);
   }
   writer.optimize();
   writer.close();
}

}

 

到这里就基本完成了，运行后会发现data.index这个目录下多了很多文件

http://apps.hi.baidu.com/share/detail/24048347