首页 > 学院 > 开发设计 > 正文

A simple example about full-text search based Java:Lucene

2019-11-18 15:03:40
字体:
来源:转载
供稿:网友

  索引源代码:
package lUCene;

/**
* <p>Title: </p>
* <p>Description: </p>
* <p>Copyright: Copyright (c) 2003</p>
* <p>Company: </p>
* @author Shirley
* @version 1.0
*/

import org.apache.lucene.index.*;
import org.apache.lucene.analysis.*;
import java.io.*;
import org.apache.lucene.document.*;

public class IndexFiles {
  //使用方法:: IndexFiles [索引输出目录] [索引的文件列表] ...
  public static void main(String[] arg) throws Exception {
    String[] args = new String[2];
    //索引后存放索引信息的路径
    args[0] = System.getPRoperty("java.io.tmpdir", "tmp") + System.getProperty("file.separator") + "index-1";
    //待索引文件
    args[1] = "E://AppWork//lucene//rfc2047.txt";
    args[2] = "E://AppWork//cyberOffice//CO//Sheldon Java Mail.htm";
    args[3] = "E://AppWork//lucene//englishtest.doc";
    args[4] = "E://AppWork//cyberoffice//CO//xls1.xls";
    args[5] = "E://AppWork//cyberoffice//CO//PPT1.ppt";

    String indeXPath = args[0];
    IndexWriter writer;
    //用指定的语言分析器构造一个新的写索引器(第3个参数表示是否为追加索引)
    writer = new IndexWriter(indexPath, new SimpleAnalyzer(), false);

    for (int i=1; i<args.length; i++) {
      System.out.println("Indexing file " + args[i]);
      InputStream is = new FileInputStream(args[i]);

      //构造包含2个字段Field的Document对象
      //一个是路径path字段,不索引,只存储
      //一个是内容body字段,进行全文索引,并存储
      Document doc = new Document();
      doc.add(Field.UnIndexed("path", args[i]));
      doc.add(Field.Text("body", (Reader) new InputStreamReader(is)));
      //将文档写入索引


发表评论 共有条评论
用户名: 密码:
验证码: 匿名发表