下面是myrss.easyjf.com相关代码!

 

 一、索引管理(建立及维护)
　　索引管理类MyRssIndexManage主要实现根据网站信息库中的数据建立索引，维护索引等。由于索引的过程需要消耗一定的时间，因此，索引管理类实现Runnable接口，使得我们可以在程序中开新线程来运行。
package com.easyjf.lucene;

import java.util.Date;
import java.util.List;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Searcher;

import com.easyjf.dbo.EasyJDB;
import com.easyjf.news.business.NewsDir;
import com.easyjf.news.business.NewsDoc;
import com.easyjf.news.business.NewsUtil;
import com.easyjf.web.tools.IPageList;
public class MyRssIndexManage implements Runnable {
 private String indexDir;
 private String indexType="add"; 
 public void run() {
  // TODO Auto-generated method stub
  if("add".equals(indexType))
   normalIndex();
  else if ("init".equals(indexType)) reIndexAll();
 }
 public void normalIndex()
 {
  try{
   Date start = new Date();
   int num=0;
   IndexWriter writer=new IndexWriter(indexDir,new StandardAnalyzer(),false);   
   //NewsDir dir=NewsDir.readBySn();   
   String scope="(needIndex<2) or(needIndex is null)";
   IPageList pList=NewsUtil.pageList(scope,1,50);
   for(int p=0;p<pList.getPages();p++)
   {
   pList=NewsUtil.pageList(scope,p,100);
   List list=pList.getResult();
   for(int i=0;i<list.size();i++)
   {
    NewsDoc doc=(NewsDoc)list.get(i);     
    writer.addDocument(newsdoc2lucenedoc(doc));   
    num++;
   }
   }
   writer.optimize();
   writer.close();
   EasyJDB.getInstance().execute("update NewsDoc set needIndex=2 where "+scope);
   Date end = new Date();
   System.out.print("新增索引"+num+"条信息，一共花："+(end.getTime() - start.getTime())/60000+"分钟!");  
   }
   catch(Exception e)
   {
    e.printStackTrace();
   }
 }
 public void reIndexAll()
 {
  try{
   Date start = new Date();
   int num=0;
   IndexWriter writer=new IndexWriter(indexDir,new StandardAnalyzer(),true);   
   NewsDir dir=NewsDir.readBySn("easyjf");   
   IPageList pList=NewsUtil.pageList(dir,1,50);
   for(int p=0;p<pList.getPages();p++)
   {
   pList=NewsUtil.pageList(dir,p,100);
   List list=pList.getResult();
   for(int i=0;i<list.size();i++)
   {    
    NewsDoc doc=(NewsDoc)list.get(i);     
    writer.addDocument(newsdoc2lucenedoc(doc));
    num++;
   }
   }
   writer.optimize();
   writer.close();
   EasyJDB.getInstance().execute("update NewsDoc set needIndex=2 where dirPath like 'easyjf%'");
   Date end = new Date();
   System.out.print("全部重新做了一次索引，一共处理了"+num+"条信息，花："+(end.getTime() - start.getTime())/60000+"分钟!");  
   }
   catch(Exception e)
   {
    e.printStackTrace();
   }
 }
 private Document newsdoc2lucenedoc(NewsDoc doc)
 {
  Document lDoc=new Document();     
  lDoc.add(new Field("title",doc.getTitle(),Field.Store.YES,Field.Index.TOKENIZED));
  lDoc.add(new Field("content",doc.getContent(),Field.Store.YES,Field.Index.TOKENIZED));
  lDoc.add(new Field("url",doc.getRemark(),Field.Store.YES,Field.Index.NO));    
  lDoc.add(new Field("cid",doc.getCid(),Field.Store.YES,Field.Index.NO));
  lDoc.add(new Field("source",doc.getSource(),Field.Store.YES,Field.Index.NO));
  lDoc.add(new Field("inputTime",doc.getInputTime().toString(),Field.Store.YES,Field.Index.NO));
  return lDoc;
 }
 public String getIndexDir() {
  return indexDir;
 }
 public void setIndexDir(String indexDir) {
  this.indexDir = indexDir;
 }
 
 public String getIndexType() {
  return indexType;
 }
 public void setIndexType(String indexType) {
  this.indexType = indexType;
 }
}