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

2019-11-18 15:03:40

字體：大中小

來源：轉載

供稿：網友

索引源代碼：
package lUCene;

/**
* Title: 
* Description: 
* Copyright: Copyright (c) 2003
* Company: 
* @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 [索引輸出目錄] [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徑
 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;
 //用指定的語言分析器構造一個新的寫索引器（第3個參數表示是否為追加索引）
 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]);

 //構造包含2個字段Field的Document對象
 //一個是路徑path字段，不索引，只存儲
 //一個是內容body字段，進行全文索引，并存儲
 Document doc = new Document();
 doc.add(Field.UnIndexed("path", args[i]));
 doc.add(Field.Text("body", (Reader) new InputStreamReader(is)));
 //將文檔寫入索引

上一篇：一步一步學習midp2。0游戲編程（三）

下一篇：About UBB with java has a bug.