java 创建数据库索引_java基于lucene创建数据库索引

package com.cn.ninemax;

import java.sql.Connection;

import java.sql.DriverManager;

import java.sql.ResultSet;

import java.sql.SQLException;

import java.sql.Statement;

public class JDBCUtil {

public static Connection getConn(){

Connection conn=null;

try {

Class.forName("net.sourceforge.jtds.jdbc.Driver").newInstance();

String urlDB="jdbc:jtds:sqlserver://10.1.72.103:1433;DatabaseName=nstl_test";

conn = DriverManager.getConnection(urlDB,"sa","sa");

} catch (ClassNotFoundException e) {

// TODO Auto-generated catch block

e.printStackTrace();

} catch (SQLException e) {

// TODO Auto-generated catch block

e.printStackTrace();

} catch (InstantiationException e) {

// TODO Auto-generated catch block

e.printStackTrace();

} catch (IllegalAccessException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

return conn;

}

public static void close(Object object, Statement stmt, Connection conn) {

try {

stmt.close();

conn.close();

} catch (SQLException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

public static void rollback(Connection conn) {

try {

conn.rollback();

} catch (SQLException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

public static void commit(Connection conn) {

try {

conn.commit();

} catch (SQLException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

public static void main(String[] args) {

System.out.println(JDBCUtil.getConn());

}

}

package com.cn.ninemax;

import java.io.File;

import java.io.IOException;

import java.sql.Connection;

import java.sql.ResultSet;

import java.sql.SQLException;

import java.sql.Statement;

import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field;

import org.apache.lucene.document.Field.Index;

import org.apache.lucene.document.Field.Store;

import org.apache.lucene.index.CorruptIndexException;

import org.apache.lucene.index.IndexReader;

import org.apache.lucene.index.IndexWriter;

import org.apache.lucene.index.IndexWriterConfig;

import org.apache.lucene.index.Term;

import org.apache.lucene.search.IndexSearcher;

import org.apache.lucene.search.ScoreDoc;

import org.apache.lucene.search.TermQuery;

import org.apache.lucene.store.FSDirectory;

import org.apache.lucene.util.Version;

public class IndexerDB {

private String directory = "e://youyajie";

public static void main(String[] args) throws IOException, SQLException {

IndexerDB db = new IndexerDB();

// db.SearDataByIndex();

db.CreateDBIndex();

}

private void SearDataByIndex() throws IOException {

File file = new File(directory);

FSDirectory directory = FSDirectory.open(file);

IndexReader reader = IndexReader.open(directory);

// 简单索引

IndexSearcher searcher = new IndexSearcher(reader);

// Blood pyruvate curves of normal and obese subjects following the

// ingestion of carbohydrate.

Term t = new Term("ti", "obese");

TermQuery quenry = new TermQuery(t);

// 获得得分靠前的两个匹配记录

ScoreDoc[] docs = searcher.search(quenry, 3).scoreDocs;

for (int i = 0; i < docs.length; i++) {

Date start = new Date();

String ti = searcher.doc(docs[i].doc).get("ti");

Date end = new Date();

System.out.println(ti + (end.getTime() - start.getTime()) + "ms");

}

}

private int pageSize = 10000;

private int count = 0;

public void CreateDBIndex() throws IOException, SQLException {

Connection conn = JDBCUtil.getConn();

Statement st = conn.createStatement();

String sql = "select count(*) from dbo.pb18001949_test";

ResultSet rs = st.executeQuery(sql);

while (rs.next()) {

count = rs.getInt(1);

}

int thread = count / pageSize;

for (int i = 0; i < thread; i++) {

sql = "select top ("

+ pageSize

+ ") ti,ab from(select row_number() over(order by id asc) as rownumber,id,ti,kw,ab from dbo.pb18001949_test) as tb where rownumber>("

+ (i * pageSize) + ")";

rs = st.executeQuery(sql);

while (rs.next()) {

CreateFileIndex(rs.getString(1), rs.getString(2));

}

System.out.println("第" + (i + 1) + "批数据建立索引完成");

}

JDBCUtil.close(null, st, conn);

}

private void CreateFileIndex(String str1, String str2)

throws CorruptIndexException, IOException {

File file = new File(directory);

FSDirectory directory = FSDirectory.open(file);

// 用来创建索引

IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_36,

new StandardAnalyzer(Version.LUCENE_36));

IndexWriter writer = new IndexWriter(directory, conf);

Document doc = new Document();

Field f1 = null;

if (str1.length() > 0) {

f1 = new Field("ti", str1, Store.YES, Index.ANALYZED);

doc.add(f1);

}

if (str2 != null && str2.length() > 0) {

Field f2 = new Field("ab", str2, Store.YES, Index.ANALYZED);

doc.add(f2);

}

writer.addDocument(doc);

writer.close();

}

}主要的就是这两个类的  底层需要两个jar包 一个是jtds用来连接数据库的 还有一个就是lucene的核心jar包