Luncene 之一 ：創建索引(Luncene + paoding)

Luncene是什麼就不介紹了。

 

一、先去網上Down下來 paoding-analysis-2.0.4-beta，解壓，在lib目錄找到lucene-core-2.2.0.jar，lucene-highlighter-2.2.0.jar，commons-logging.jar 這幾個Jar包放到項目當中。

 

二、添加Paoding。 在項目中使用發現，直接添加paoding-analysis.jar會發生異常。所以我們不直接添加這個Jar，而是把Src目錄下的所有文件(也就是源代碼) copy 都我們項目的Src目錄下;

 

 

三、把dic(詞典)目錄也copy 到我們項目的src下，並在Src目錄新建一個包data.index,主要是用來存放生成的索引文件;

 

四、修改 paoding-dic-home.properties 這個屬性文件

 

  #values are "system-env" or "this"; #if value is "this" , using the paoding.dic.home as dicHome if configed! #paoding.dic.home.config-fisrt=system-env #dictionary home (directory) #"classpath:xxx" means dictionary home is in classpath. #e.g "classpath:dic" means dictionaries are in "classes/dic" directory or any other classpath directory #paoding.dic.home=dic #seconds for dic modification detection #paoding.dic.detector.interval=60 paoding.dic.home=classpath:dic // dic 所在目錄 paoding.dic.home.config-fisrt=this //應用當前的配置

 

五、在 package   net.paoding.analysis.knife 下找到PaodingMaker類， Ctrl + S + O 定位到

private static void setDicHomeProperties(Properties p) 這個方法，修改

private static void setDicHomeProperties(Properties p) { String dicHomeAbsultePath = p .getProperty("paoding.dic.home.absolute.path"); if (dicHomeAbsultePath != null) { return; } // 獲取詞典安裝目錄配置： // 如配置了PAODING_DIC_HOME環境變量，則將其作爲字典的安裝主目錄 // 否則使用屬性文件的paoding.dic.home配置 // 但是如果屬性文件中強制配置paoding.dic.home.config-first=this， // 則優先考慮屬性文件的paoding.dic.home配置， // 此時只有當屬性文件沒有配置paoding.dic.home時纔會採用環境變量的配置 String dicHomeBySystemEnv = null; try { dicHomeBySystemEnv = getSystemEnv(Constants.ENV_PAODING_DIC_HOME); } catch (Error e) { log.warn("System.getenv() is not supported in JDK1.4. "); } String dicHome = getProperty(p, Constants.DIC_HOME); if (dicHomeBySystemEnv != null) { String first = getProperty(p, Constants.DIC_HOME_CONFIG_FIRST); if (first != null && first.equalsIgnoreCase("this")) { if (dicHome == null) { dicHome = dicHomeBySystemEnv; } } else { dicHome = dicHomeBySystemEnv; } } // 如果環境變量和屬性文件都沒有配置詞典安轉目錄 // 則嘗試在當前目錄和類路徑下尋找是否有dic目錄， // 若有，則採納他爲paoding.dic.home // 如果嘗試後均失敗，則拋出PaodingAnalysisException異常 if (dicHome == null) { File f = new File("dic"); if (f.exists()) { dicHome = "dic/"; } else { URL url = PaodingMaker.class.getClassLoader() .getResource("dic"); if (url != null) { dicHome = "classpath:dic/"; } } } if (dicHome == null) { throw new PaodingAnalysisException( "please set a system env PAODING_DIC_HOME or Config paoding.dic.home in paoding-dic-home.properties point to the dictionaries!"); } // 規範化dicHome，並設置到屬性文件對象中 dicHome = dicHome.replace('//', '/'); if (!dicHome.endsWith("/")) { dicHome = dicHome + "/"; } p.setProperty(Constants.DIC_HOME, dicHome);// writer to the properites //修改部分 String path=""; try { path = URLDecoder.decode(getFile(dicHome).getPath(), "utf-8"); } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } // object // 將dicHome轉化爲一個系統唯一的絕對路徑，記錄在屬性對象中 File dicHomeFile = getFile(path); //修改部分結束 if (!dicHomeFile.exists()) { throw new PaodingAnalysisException( "not found the dic home dirctory! " + dicHomeFile.getAbsolutePath()); } if (!dicHomeFile.isDirectory()) { throw new PaodingAnalysisException( "dic home should not be a file, but a directory!"); } p.setProperty("paoding.dic.home.absolute.path", dicHomeFile .getAbsolutePath()); }

 

 

 

六、創建一個Servlet：AnalyzerServlet

 

 

package com.lunceneTest.servlet; import java.io.IOException; import java.net.URLDecoder; import java.util.List; import javax.servlet.ServletException; import javax.servlet.http.HttpServlet; import javax.servlet.http.HttpServletRequest; import javax.servlet.http.HttpServletResponse; import net.paoding.analysis.analyzer.PaodingAnalyzer; 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 com.lunceneTest.Model.News; import com.lunceneTest.db.NewsDao; public class AnalyzerServlet extends HttpServlet { /** * */ private static final long serialVersionUID = -822638045647816348L; public void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException { } public void doGet(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException { try { this.createIndex(); } catch (Exception e) { e.printStackTrace(); } } public void createIndex() throws Exception { //實例化分詞器，使用中文分詞器 Analyzer analyzer =new PaodingAnalyzer(); String path = URLDecoder.decode(AnalyzerServlet.class.getResource("/data/index").toString(),"UTF-8").replace("file:/",""); System.out.println(path); FSDirectory directory = FSDirectory.getDirectory(path); // true表示覆蓋原來已經創建的索引,如果是false表示不覆蓋，而是繼續添加索引 IndexWriter writer = new IndexWriter(directory,analyzer,true); List<News> list = NewsDao.getAllNews(); // Dao層獲取數據庫新聞列表的方法 for (News news : list) { Document doc = new Document(); //Field.Index.UN_TOKENIZED 不分詞 Field id_filed = new Field(News.ID,String.valueOf(news.getId()),Field.Store.YES,Field.Index.UN_TOKENIZED); Field title_field = new Field(News.TITLE,news.getTitle(),Field.Store.YES,Field.Index.TOKENIZED); Field content_field = new Field(News.CONTENT,news.getContent(),Field.Store.YES,Field.Index.TOKENIZED); doc.add(id_filed); doc.add(title_field); doc.add(content_field); writer.addDocument(doc); } writer.optimize(); writer.close(); } }

 

 

到這裏就基本完成了，運行後會發現data.index這個目錄下多了很多文件