lucene 检索数据库索引

 

进入正题：工程目录在com.lucene下建立data包

DataConnection.java 相关数据库链接的信息

SqlService.java 数据库操作类

index.java  索引类

search.java 检索类

test.java 测试类

 

package com.lunece.data;

public class DataConnection {
    public static DataConnection getDataConnection(){
     return new DataConnection();
    }
    public static String dbDriver="com.mysql.jdbc.Driver";
    public static String dbUrl="jdbc:mysql://localhost:3306/test";
    public static String dbUser="root";
    public static String dbPassword="******";
}

package com.lunece.data;

import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.PreparedStatement;
import java.sql.ResultSet;
import java.sql.Statement;

public class SqlServer {
    private Connection conn=null;
    private Statement sta=null;
    //private PreparedStatement pre=null;
    //全局通用连接相关信息
    public static DataConnection connection=DataConnection.getDataConnection();
   
    public SqlServer() throws Exception{
     Class.forName(connection.dbDriver);
     conn = DriverManager.getConnection(connection.dbUrl, connection.dbUser, connection.dbPassword);
     sta=conn.createStatement();     
    }
    public boolean executeSQL(String sql) throws Exception{     
     return  sta.execute(sql);     
    }
    public ResultSet QueryData(String sql) throws Exception{
     return sta.executeQuery(sql);
    }
}

 

package com.lunece.data;

import java.io.File;
import java.io.IOException;
import java.io.Writer;
import java.sql.ResultSet;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Fieldable;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class index {
 
   public static String INDEXPATH="D:/lunece/index";
  
   public static int createindex(ResultSet rs) throws IOException{
    System.out.println("create index loading...");
    IndexWriter writer = new IndexWriter(FSDirectory.open(new File(INDEXPATH)),getAnalyzer(),IndexWriter.MaxFieldLength.LIMITED);
    try {       
   while (rs.next()) {
   Document doc = new Document();
   doc.add(new Field("id",rs.getInt("id")+"",Field.Store.YES,Field.Index.ANALYZED));
   doc.add(new Field("name",rs.getString("name"),Field.Store.YES,Field.Index.ANALYZED));
   doc.add(new Field("address",rs.getString("address"),Field.Store.YES,Field.Index.ANALYZED));
   writer.addDocument(doc);
    }
  } catch (Exception e) {
     System.out.println("create index failed....");
  }
  int numberindex=writer.numDocs();
  writer.optimize(); 
  writer.close(); 
  return numberindex;
   }
  
   public static StandardAnalyzer getAnalyzer(){
    return new StandardAnalyzer(Version.LUCENE_CURRENT);
   }
}

package com.lunece.data;

import java.io.File;
import java.io.IOException;
import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class search {
   private static int TOP_NUM=100;//显示前top_num条数据
   public static void searchData(File indexDir,String search) throws CorruptIndexException, IOException, ParseException{
    IndexSearcher searcher= new IndexSearcher(FSDirectory.open(indexDir),true);
    String fieldString="name";
    QueryParser parser= new QueryParser(Version.LUCENE_CURRENT,fieldString,new StandardAnalyzer(Version.LUCENE_CURRENT));
    Query query= parser.parse(search);
   
    TopScoreDocCollector collector=TopScoreDocCollector.create(TOP_NUM,false);
    long start=new Date().getTime();
   
    searcher.search(query, collector);
    ScoreDoc [] hits =collector.topDocs().scoreDocs; 
    for (int i = 0; i < hits.length; i++) {
   Document document= searcher.doc(i);
   System.out.println(document.getField("id")+ "   " +document.getField("name")+"    "+document.getField("address"));
    }
    long end=new Date().getTime();
    System.out.println("Found "+collector.getTotalHits()+" document(s) (in "+(end-start)+" milliseconds) that matched query '"+ search+"';");
   }
}
package com.lunece.data;

import java.io.File;
import java.sql.Connection;
import java.sql.ResultSet;

public class test {

 
    public static String INDEXPATH="D:/lunece/index";
 public static void main(String[] args) throws Exception {
  SqlServer server=new SqlServer();
  ResultSet rs = server.QueryData("select * from user");
  int number = index.createindex(rs);
  if(number > 0){
   System.out.println("create index success...");
  }else{
   System.out.println("create index failed...");
  }
  
  search.searchData(new File(INDEXPATH),"张三");
  
 }

}
结果

介于本人使用的是lucene3.0.0版本，故与2.X版本有些地方不一样，请仔细查阅相关版本API。

 

如果需要索引海量数据库，需要对数据库进行分块，分段处理，减轻内存压力~~