Luncene之三 使用Quartz 定时更新索引

 首先重构LunceneUtil.java。往里面添加两个方法

 

 

package com.lunceneTest.util; import java.io.IOException; import java.io.StringReader; import java.net.URLDecoder; import java.util.ArrayList; import java.util.List; import net.paoding.analysis.analyzer.PaodingAnalyzer; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.queryParser.MultiFieldQueryParser; import org.apache.lucene.search.BooleanClause; import org.apache.lucene.search.Hits; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.Searcher; import org.apache.lucene.search.highlight.Fragmenter; import org.apache.lucene.search.highlight.Highlighter; import org.apache.lucene.search.highlight.QueryScorer; import org.apache.lucene.search.highlight.SimpleFragmenter; import org.apache.lucene.search.highlight.SimpleHTMLFormatter; import org.apache.lucene.store.FSDirectory; import com.lunceneTest.Model.News; import com.lunceneTest.servlet.AnalyzerServlet; public class LunceneUtil { public static List<News> search(String path,String keyword) { List<News> list = new ArrayList<News>(); IndexReader reader=null; try { FSDirectory directory = FSDirectory.getDirectory(path); reader = IndexReader.open(directory); Searcher searcher = new IndexSearcher(directory); //要查询的字段 String [] fields = {News.TITLE,News.CONTENT}; //要查询字段之间的关系(与或非) BooleanClause.Occur [] flags = new BooleanClause.Occur[]{ BooleanClause.Occur.MUST,BooleanClause.Occur.SHOULD }; // 分词时用的分词器 Analyzer analyzer = new PaodingAnalyzer(); Query query =MultiFieldQueryParser.parse(keyword, fields, flags, analyzer); // 由于我们目前使用的查询是多字段查询，需要匹配度的排序 // QueryScorer内置计分器 query.rewrite(reader);//用于重写query对象，目的能过让计费器识别当前的query； Hits hits = searcher.search(query); int length = hits.length(); for(int i=0; i < length; i++) { Document doc = hits.doc(i); News n = new News(); int id =Integer.valueOf(doc.get(News.ID)); String title = doc.get(News.TITLE); //查询关键字高亮 String content = doc.get(News.CONTENT); SimpleHTMLFormatter format = new SimpleHTMLFormatter("<font color=red>","</font>"); //高亮 ，计分器 Highlighter highlighter = new Highlighter(format,new QueryScorer(query)); //关键字附近字符串的截取，截取200个字符 Fragmenter fragmenter = new SimpleFragmenter(150); highlighter.setTextFragmenter(fragmenter); //针对某个关键字的高亮以及截取 TokenStream title_tokenStream = analyzer.tokenStream(News.TITLE, new StringReader(title)); title = highlighter.getBestFragment(title_tokenStream, title); TokenStream content_tokenStream = analyzer.tokenStream(News.CONTENT, new StringReader(content)); content = highlighter.getBestFragment(content_tokenStream, content); n.setId(id); n.setTitle(title); n.setContent(content); list.add(n); } } catch (Exception e) { // TODO: handle exception } finally { try { reader.close(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } } return list; } /** * * 创建索引 * @param list要创建索引的新闻列表 * @param override 是否覆盖 * @throws Exception */ public static void createIndex(List<News> list,boolean override) throws Exception { //实例化分词器，使用中文分词器 Analyzer analyzer =new PaodingAnalyzer(); String path = URLDecoder.decode(AnalyzerServlet.class.getResource("/data/index").toString(),"utf-8").replace("file:/",""); FSDirectory directory = FSDirectory.getDirectory(path); // true表示覆盖原来已经创建的索引,如果是false表示不覆盖，而是继续添加索引 IndexWriter writer = new IndexWriter(directory,analyzer,override); for (News news : list) { Document doc = new Document(); //Field.Index.UN_TOKENIZED 不分词 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(); } public static void createIndex(News news) throws Exception { List<News> list = new ArrayList<News>(); list.add(news); createIndex(list,false); } }

 

然后往NewsDao.java里面添加方法：

package com.lunceneTest.db; import java.sql.Connection; import java.sql.PreparedStatement; import java.sql.ResultSet; import java.util.ArrayList; import java.util.LinkedList; import java.util.List; import com.lunceneTest.Model.News; public class NewsDao{ public static void addNews(News news) { Connection conn =null; PreparedStatement pre=null; try { String sql ="insert into News values(?,?)"; conn = ConnectionManager.getConnection(); pre = conn.prepareStatement(sql); pre.setString(1, news.getTitle()); pre.setString(2, news.getContent()); pre.executeUpdate(); } catch(Exception ex) { ex.printStackTrace(); } finally { ConnectionManager.close(null, pre, null, conn); } } public static List<News> getAllNews() { List<News> list = null; Connection con = null; PreparedStatement pre = null; ResultSet res=null; try { String sql="select * from News"; con = ConnectionManager.getConnection(); pre = con.prepareStatement(sql); res = pre.executeQuery(); list = new ArrayList<News>(); while(res.next()) { News n = new News(); n.setId(res.getInt("ID_")); n.setTitle(res.getString("Title_")); n.setContent(res.getString("Content_")); list.add(n); } } catch(Exception ex) { ex.printStackTrace(); } finally { ConnectionManager.close(res, pre, null, con); } return list; } public static List<News> getNewsFromMaxId(int maxID) { List<News> list = null; Connection con = null; PreparedStatement pre = null; ResultSet res=null; try { String sql="select * from News where ID_>" +maxID; con = ConnectionManager.getConnection(); pre = con.prepareStatement(sql); res = pre.executeQuery(); list = new LinkedList<News>(); while(res.next()) { News n = new News(); n.setId(res.getInt("ID_")); n.setTitle(res.getString("Title_")); n.setContent(res.getString("Content_")); list.add(n); } } catch(Exception ex) { ex.printStackTrace(); } finally { ConnectionManager.close(res, pre, null, con); } return list; } }

 

 

 

 

 

因为 Spring 已经集成了对Quartz的支持,所以我们只要在项目中添加Spring框架就可以了。添加的步骤就不细说了。

完成之后往lib目录下添加quartz-all-1.6.5.jar 这个是Quartz的核心包

 

 

到这一步呢，我们得创建一个用来定时更新所有的工作类了。

在Util包下新建一个CreateIndexUtil.java

 package com.lunceneTest.util; import java.util.List; import com.lunceneTest.Model.News; import com.lunceneTest.db.NewsDao; public class CreateIndexUtil { public void crateIndex() { try { String maxId = FileUtil.readText(); // 从文件中读取最大ID int id=maxId==null?0:"".equals(maxId)?0:Integer.parseInt(maxId); List<News> list = NewsDao.getNewsFromMaxId(id); LunceneUtil.createIndex(list,true); // 把最大Id写 到文件中去，以便下次使用 FileUtil.writerText(list.get(list.size()-1).getId() + ""); } catch (Exception e) { e.printStackTrace(); } } }

 

 读写文件的工具类,FileUtil.java

 

package com.lunceneTest.util; import java.io.BufferedWriter; import java.io.File; import java.io.FileInputStream; import java.io.FileWriter; import java.io.IOException; import java.io.InputStreamReader; import java.io.Reader; import java.net.URLDecoder; public class FileUtil { /** * 从文件中读取最大的ID * @return */ public static String readText() { String content = ""; Reader re=null; FileInputStream fis=null; try { //maxID.txt 这个文件必须存在，否则会报异常 String path = URLDecoder.decode(FileUtil.class.getResource("/data/index/maxID.txt").toString().replace("file:/", ""), "utf-8"); File file = new File(path); /*if(!file.exists()) { file.createNewFile(); }*/ fis =new FileInputStream(file); re = new InputStreamReader(fis,"UTF-8"); char[] chs = new char[1024]; int count; while((count = re.read(chs)) != -1) { content += new String(chs,0,count); } } catch (Exception e) { e.printStackTrace(); } finally { try { if (null != fis) { fis.close(); } if(null != re) { re.close(); } } catch (Exception e) { } } return content; } /** * 问文件中写入最大ID * @param maxId */ public static void writerText(String maxId) { BufferedWriter bw = null; try { //maxID.txt 这个文件必须存在，否则会报异常 String path = URLDecoder.decode(FileUtil.class .getResource("/data/index/maxID.txt").toString(),"UTF-8").substring(6); File file = new File(path); bw = new BufferedWriter(new FileWriter(file)); bw.write(maxId); } catch (Exception e) { e.printStackTrace(); } finally { if(bw != null) { try { bw.close(); } catch (IOException e) { } } } } }

 

 

 到这里该做的工作都应该做了吧，下面开始配置Quartz了。

在Spring配置文件中加入以下代码：

<?xml version="1.0" encoding="UTF-8"?> <beans xmlns="http://www.springframework.org/schema/beans" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans-2.5.xsd"> <bean id="createIndex" class="com.lunceneTest.util.CreateIndexUtil"></bean> <!-- 指定时间工作的具体类--> <bean id="CreateIndexJob" class="org.springframework.scheduling.quartz.MethodInvokingJobDetailFactoryBean"> <property name="targetObject" ref="createIndex" /> <property name="targetMethod" value="crateIndex" /> <property name="concurrent" value="false" /> <!--将并发设置为false--> </bean> <!-- 定制任务 --> <bean id="scheedulerFactoryBean" class="org.springframework.scheduling.quartz.SchedulerFactoryBean"> <property name="triggers"> <list> <ref bean="timeTrigger"/> </list> </property> <property name="configLocation" value="classpath:quartz.properties"/> </bean> <!-- 设定触发任务时间 --> <bean id="timeTrigger" class="org.springframework.scheduling.quartz.CronTriggerBean"> <property name="jobDetail"> <ref bean="CreateIndexJob"/> </property> <property name="cronExpression"> <value>0 0 02 * * ?</value> <!--每天凌晨2点执行任务 --> </property> </bean> </beans>