lunece建立索引遇到的问题

2007-05-31

关键字: lucene

最近对lucene的检索进行了肤浅的学习先是把论坛里大部分的lucene的帖子看了下大致了解了下lucene 决定学习在自己测试的时候发现在对大表的创建索引时耗费的时间实在太长想通过多线程来解决对一个表的总记录数来决定创建几个线程来创建索引，结果是报错：

D:\lucene\index\_a.fnm (系统找不到指定的文件。)

Lock obtain timed out: SimpleFSLock@D:\lucene\index\write.lock

之类

难道lucene创建索引耗费是太长的问题真的没有解决，因为是初学没有去研究源代码只是在自己的博客上发发感概无意看到我篇文章的朋友不要笑我肤浅啊鼓了勇气才敢来写第一篇博客的

我测试的代码：

主函数：

java 代码

package luceneTest;
import java.io.File;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;
import dataConnectionPool.DataConnectionPool;
public class TMain {
private String find = " select id,name from author";
private Connection con;
private Statement stmt;
private File indexFile;
private int count ;
public TMain(File indexFile)
{
this.indexFile = indexFile;
this.count = countD();
}
public int countD()
{
int count=0;
try {
con = DataConnectionPool.getBasicDataSource().getConnection();
stmt = con.createStatement(ResultSet.TYPE_SCROLL_INSENSITIVE,ResultSet.CONCUR_READ_ONLY);
ResultSet rs = stmt.executeQuery(find);
while(rs.next())
{
rs.last(); // 移动到最后一行
count = rs.getRow(); // 获得当前行号：此处即为最大记录数
}
System.out.println(" 表的总记录数："+count);
} catch (SQLException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return count;
}
public void create() throws InterruptedException
{
int num = count/10;
for(int i = 1;i<=num;i++)
{
System.out.println("main start :"+((i-1)*10+1));
CDataIndex cd = new CDataIndex(((i-1)*10+1),10,indexFile);
cd.start();
}
}
public void print(File indexFile, String markInfo)
{
FData fd = new FData(indexFile,markInfo);
fd.findData();
}
public static void main(String[] args) {
// TODO Auto-generated method stub
File indexFile = new File("D:/lucene/index");
String markInfo = "you";
TMain tm = new TMain(indexFile);
try {
tm.create();
tm.print(indexFile, markInfo);
} catch (InterruptedException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}

调用一个建立索引的类：

java 代码

package luceneTest;
import java.io.File;
import java.io.IOException;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.util.Date;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
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.store.FSDirectory;
import dataConnectionPool.DataConnectionPool;
public class CDataIndex extends Thread {
private Connection con;
private String find = " select id,name from author";
private PreparedStatement ps;
private int start = 0;
private int num = 0;
private File indexFile;
private boolean mark = false; //通过这个来控制是用增量索引还是全局索引
public CDataIndex(int start,int num,File indexFile)
{
this.start = start;
this.num = num;
this.indexFile = indexFile;
}
public void run()
{
System.out.println(" 开始索引！");
Date beginDate = new Date();
try {
FSDirectory fsd = FSDirectory.getDirectory(indexFile.getAbsolutePath(), mark);
if(IndexReader.isLocked(fsd)){ //这
IndexReader.unlock(fsd);;
}
IndexWriter writerF = new IndexWriter(fsd,new CJKAnalyzer());
// RAMDirectory ramD = new RAMDirectory();
// IndexWriter writerR = new IndexWriter(ramD,new StandardAnalyzer());
con = DataConnectionPool.getBasicDataSource().getConnection();
ps = con.prepareStatement(find,ResultSet.TYPE_SCROLL_INSENSITIVE,ResultSet.CONCUR_READ_ONLY);
ResultSet rs = ps.executeQuery();
System.out.println(" start :"+start);
rs.absolute(start);
rs.previous();
while(rs.next()&&num!=0)
{
Document doc = new Document();
doc.add(new Field("id",rs.getString(1),Field.Store.YES, Field.Index.UN_TOKENIZED));
doc.add(new Field("content",rs.getString(2), Field.Store.YES,Field.Index.TOKENIZED ));
//writerR.optimize();
//writerR.addDocument(doc);
writerF.optimize();
writerF.addDocument(doc);
num--;
}
// writerR.optimize();
// writerR.close();
writerF.close();
// writerF.addIndexes(new Directory[]{ramD});
Date endDate = new Date();
System.out.println("索引耗去的时间(毫秒) ："
+ (endDate.getTime() - beginDate.getTime()));
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (SQLException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}