爬虫系统Lucene分词

标签：uuid   store   val   close   lock   while   org   pac   ace   

思路：查询数据库中信息，查询出id和name把那么进行分词存入文件

package com.open1111.index;

import java.io.IOException;
import java.nio.file.Paths;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.ResultSet;

import org.apache.log4j.Logger;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

import com.open1111.util.DbUtil;
import com.open1111.util.PropertiesUtil;

public class JarsIndex {

private static Logger logger=Logger.getLogger(JarsIndex.class);

private static Connection con=null;

public static void main(String[] args) throws IOException{
logger.info("创建索引开始");
DbUtil dbUtil=new DbUtil();
try {
con=dbUtil.getCon();
logger.info("创建数据库连接成功");
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
logger.info("创建数据库连接失败");
}
Directory dir=FSDirectory.open(Paths.get(PropertiesUtil.getValue("indexFile")));
Analyzer analyzer=new StandardAnalyzer();
IndexWriterConfig conf=new IndexWriterConfig(analyzer);
IndexWriter writer=new IndexWriter(dir, conf);

String sql="select * from t_jar where indexState=0";
try{
PreparedStatement pstmt=con.prepareStatement(sql);
ResultSet rs=pstmt.executeQuery();
while(rs.next()){
String id=rs.getString("uuid");
String name=rs.getString("name");
Document doc=new Document();
doc.add(new StringField("id",id,Field.Store.YES));
doc.add(new TextField("name",name.replaceAll("-", " "),Field.Store.YES));
writer.addDocument(doc);

// 更新数据库indexState状态字段 改成1
String sql2="update t_jar set indexState=1 where uuid=‘"+id+"‘";
PreparedStatement pstmt2=con.prepareStatement(sql2);
pstmt2.executeUpdate();
}
}catch(Exception e){
logger.error("执行数据库报错", e);
}
try {
dbUtil.closeCon(con);
} catch (Exception e) {
logger.error("Exception", e);
}
writer.close(); // 关闭写入
logger.info("创建索引完成");
}
}

爬虫系统Lucene分词

标签：uuid   store   val   close   lock   while   org   pac   ace   

原文地址：http://www.cnblogs.com/csy666/p/6602424.html