Lucene为数据库建索引

    如果要构建一个全文检索系统,并且文章全部保存在数据库中,那下面的例子会有很大的帮助.
package gzu.lyq.db;
import java.sql.*;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
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.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

//Lucene为数据库建索引实例
public class LuceneDB {
    Connection conn = null;
    //操作 Oracle 数据库
    private final String URL = "jdbc:oracle:thin:@localhost:1521:ORCL";
    public LuceneDB(){
        try {
            Class.forName("oracle.jdbc.driver.OracleDriver");
            //Oracle连接用户名:scott 密码:tiger
            conn = DriverManager.getConnection(URL,"scott","tiger");
        } catch (ClassNotFoundException e) {
            e.printStackTrace();
        } catch (SQLException e) {
            e.printStackTrace();
        }
    }

    public Connection getConnection(){
        return this.conn;
    }//获取数据库连接

    public void close(){
        try {
            this.conn.close();
        } catch (SQLException e) {
            e.printStackTrace();
        }
    }//关闭数据库连接

    public static void main(String args[]) throws Exception {  
        LuceneDB lucene = new LuceneDB();
        IndexWriter writer = null;
        Connection conn = lucene.getConnection();
        String sql = "SELECT * FROM student";
        writer = new IndexWriter("D:\\index",new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
        PreparedStatement ps = conn.prepareStatement(sql);
        ResultSet rs = ps.executeQuery();
        while(rs.next()){
            Document doc = new Document();
            //为字段 sname 建索引
            doc.add(new Field("sname",rs.getString("sname"),Field.Store.YES,Field.Index.ANALYZED));
            writer.addDocument(doc);  
        }
        rs.close();        //关闭记录集
        conn.close();      //关闭数据库连接
        writer.optimize(); //索引优化
        writer.close();    //关闭读写器
  
        Directory dir = FSDirectory.getDirectory("D:\\index");
        IndexSearcher searcher = new IndexSearcher(dir);
  
        //选择姓名中包含张字的记录
        QueryParser parser = new QueryParser("sname", new StandardAnalyzer());
        Query query = parser.parse("张");
        
        TopDocs topDocs = searcher.search(query, 100);
        ScoreDoc[] hits = topDocs.scoreDocs;
        for(int i=0;i< hits.length;i++){
            int DocId = hits.doc;
            Document doc = searcher.doc(DocId);
            System.out.println(doc.get("sname")); //张立            
        }
    }
}

其中,Student表的内容如下:
    SNO   SNAME      SS       SAGE SDEPT
    ----- ---------- -- ---------- ----------
    95001 李勇       男         20 CS
    95002 刘晨       女         19 IS
    95003 王敏       女         18 MA
    95004 张立       男         19 IS

评论

2 楼 FX夜归人 2014-03-19  

1 楼 lin23871 2010-02-28  

注意这句：“Student表的内容如下”