开发搜索引擎初步（一）建立索引（Lucene实现）

开发自己的搜索引擎完成了一段时间了&＃xff0c;现在准备开始梳理一下思路&＃xff0c;把以前的总结一下&＃xff0c;为以后做真正的“谷歌”埋下伏笔&＃xff0c;呵呵。。。。。。

一。Lucene的下载

牛逼的Apache旗下的Lucene&＃xff0c;呵呵&＃xff0c;无人不知啊&＃xff0c;http://lucene.apache.org/,去这个地址自己下载&＃xff0c;别说不会Dowmload

二.使用Lucene建立索引

将下载下来的包解压&＃xff0c;把里面的Core,memory,analyzer啥的都拿出来&＃xff0c;配置到自己的Eclipse上面&＃xff0c;下面的事情就是写代码了。

package com.dreamers.creatindex;import java.io.File;
import java.util.ArrayList;import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.FSDirectory;
import org.dom4j.DocumentException;
import org.wltea.analyzer.lucene.IKAnalyzer;import com.dreamers.xml.*;
import com.dreamers.read.*;/*** &＃64;category 创建所有XML索引* &＃64;author bird**/
public class CreatIndex {private String INDEX_STORE_PATH ;//创建索引&＃64;SuppressWarnings("deprecation")public void creatIndex(){try{GetPath path &＃61; new GetPath();INDEX_STORE_PATH &＃61; path.getIndexPath();File file &＃61; new File(INDEX_STORE_PATH);Analyzer analyzer &＃61; new IKAnalyzer();XmlReader xml &＃61; new XmlReader();FSDirectory directory &＃61; FSDirectory.open(file);IndexWriter writer &＃61; new IndexWriter(directory, analyzer, true,IndexWriter.MaxFieldLength.LIMITED);ArrayList lisId &＃61; xml.getId();ArrayList lisTitle &＃61; xml.getTitle();ArrayList lisKeyWords &＃61; xml.getKeyWords();ArrayList lisKind &＃61; xml.getKind();ArrayList lisDescribe &＃61; xml.getDescribe();ArrayList lisDate &＃61; xml.getDate();ArrayList lisUrl &＃61; xml.getUrl();ArrayList lisAuthor &＃61; xml.getAuthor();ArrayList lisPublisher &＃61; xml.getPublisher();//System.out.println(lisUrl.get(5));for (int i &＃61; 0; i }