[编程实例] Lucene Demo 小实例

发布时间：2020-12-12 16:01:44 所属栏目：MsSql教程来源：网络整理

导读：首先是文件索引：先用爬虫爬几个页面放在特定目录下，我挑取了 google,baidu,yahoo 的代码来做例子：） Writer.java public ? class ?Writer? ... { ???? public ? static void ?main(String[]?args)? throws ?Exception ???? ... { ???????? // fileDir?is

Table users
PK id ? name ? pass ? updatetime
DBIndexer.java
?DBIndexer?

private?String?drivercom.microsoft.sqlserver.jdbc.SQLServerDriver;

?????String?urljdbc:sqlserver://localhost:1433;databaseName=mydb;?String?usersa?String?pass123456?Connection?conn?Statement?st?ResultSet?rs?String?indexUrlD:/work/index/mydb;

?????ResultSet?getResult()??Exception{????????

????????try?{

????????????Class.forName(driver);

????????????conn??DriverManager.getConnection(url,?user,?pass);

????????????String?sql?select?*?from?users;

????????????st??conn.createStatement();

????????????rs??st.executeQuery(sql);

????????????while?(rs.next())?{

????????????????System.out.print(rs.getInt("id")?+?" ");

????????????????System.out.print(rs.getString("name")?+?" ");

????????????????System.out.print(rs.getString("pass")?+?" ");

????????????????System.out.print(rs.getDate("updatetime")?+?" ");

????????????}

????????}

????????catch?(Exception?e)?{

????????????e.printStackTrace();

????????}

????????return?rs;

????}

?????executeIndex(ResultSet?rs,?IndexWriter?indexWriter)??Exception?i;

????????while(rs.next()){

?????????????id??rs.getInt(id);

????????????String?name??rs.getString(name);

????????????String?time?updatetime);

????????????

????????????Document?doc??Document();

????????????Field?idField

????????????Field?nameField

????????????Field?timeFieldtime

????????????doc.add(idField);

????????????doc.add(nameField);

????????????doc.add(timeField);

????????????indexWriter.addDocument(doc);

????????????i;

????????}this.close();

????????System.out.println(共处理记录：i);

????}

?????close()??Exception.rs.close();

????????.st.close();

????????.conn.close();

????}

?????createIndex()??Exception?get?data?ResultSet????????ResultSet?rs.getResult();

????????Analyzer?chineseAnalyzer?=?new?ChineseAnalyzer();????????Analyzer?chineseAnalyzer??IndexWriter(.indexUrl,?chineseAnalyzer,0);">);

????????indexWriter.setMergeFactor(100);

????????indexWriter.setMaxBufferedDocs();

????????java.util.Date?startDate?java.util.Date();

????????System.out.println(开始索引时间：?startDate);

????????executeIndex(rs,?indexWriter);

????????indexWriter.optimize();

????????indexWriter.close();

????????java.util.Date?endDate索引结束时间：?endDate);

????????System.out.println(共花费：?(endDate.getTime()startDate.getTime())?ms);

????}

????

?????main?(String?args[])??Exception?{

????????DBIndexer?oIndexer??DBIndexer();

????????oIndexer.createIndex();

????}

}
DBSearcher.java

?DBSearcher?{

????

????;

?????Exception?{

????????

????????/*建立索引代码，查找时注释*/Index?index=new?Index();

????????index.createIndex();

????????File?indexDir??File(indexUrl);

????????FSDirectory?fdir??FSDirectory.getDirectory(indexDir);

????????IndexSearcher?searcher??IndexSearcher(fdir);

????????对中文建立解析（必须）

?StandardAnalyzer();

????????QueryParser?parser?

????????Query?query??parser.parse(石头);

????????Date?startDate??Date();

????????System.out.println(检索开始时间：startDate);

????????Hits?result??searcher.search(query);

????????;?iresult.length();?i){

????????????Document?doc??result.doc(i);

????????????System.out.println(用户ID：?doc.get()??更新时间：));

????????}

????????Date?endDate?Date();

????????System.out.println(共有记录：?result.length());

????????System.out.println(

}

（编辑：李大同）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!

首先是文件索引：

先用爬虫爬几个页面放在特定目录下，我挑取了 google,baidu,yahoo 的代码来做例子：）

Writer.java

public ? class ?Writer?

{

????public?staticvoid?main(String[]?args)?throws?Exception

????{

????????//fileDir?is?the?directory?that?contains?the?text?files?to?be?indexed

????????File?fileDir?=new?File("D:/work/source);

????????indexDir?is?the?directory?that?hosts?Lucene's?index?files????????File?indexDir?D:/work/index);

????????Analyzer?luceneAnalyzer??StandardAnalyzer();

????????IndexWriter?indexWriter??IndexWriter(indexDir,luceneAnalyzer,true);

????????File[]?textFiles??fileDir.listFiles();

????????System.out.println(Total?indexed?"+?textFiles.length?"?files?! );

????????

????????long?startTime??Date().getTime();

????????Add?documents?to?the?index

????????for(int?i?0;?i?<?textFiles.length;?i++){

????????????if?(textFiles[i].isFile()?&&?textFiles[i].getName().endsWith(.htm))?{

????????????????System.out.println(File??textFiles[i].getCanonicalPath()??is?being?indexed);

????????????????Reader?textReader??FileReader(textFiles[i]);

????????????????Document?document??Document();

????????????????document.add(?Field(content,textReader));

????????????????document.add(path

????????????????indexWriter.addDocument(document);

????????????}

????????}

????????indexWriter.optimize();

????????indexWriter.close();

?????????endTime??Date().getTime();

????????System.out.println( It?took??(endTime?-?startTime)

?????????????milliseconds?to?create?an?index?for?the?files?in?the?directory?

?????????????fileDir.getPath());

????}

}
Searcher.java
?Searcher?

final?String?path?;

????

?????Exception

????{

????????IndexSearcher?searcher??IndexSearcher(path);

????????Hits?hits?null;

????????Query?query?;

????????QueryParser?qp??QueryParser(?StandardAnalyzer());

????????

????????String?searchText?yahoo?job?google?baidu;

????????

????????query??qp.parse(searchText);

????????hits??searcher.search(query);

????????System.out.println(Search?"?searchText?"?total??hits.length()??result?! );

?????????(Iterator?it??hits.iterator();?it.hasNext();?)?{

????????????Hit?hit??(Hit)?it.next();

????????????System.out.println(hit.getDocument().getField().stringValue());

????????}

????}

} ?
以下是一个 DB 索引的例子，大家可以看看：

数据库环境：SQL Server 2005
数据库名称：mydb
数据库表：users
表结构：