基于lucene搜索引擎的java源码

package com.wind.model; import java.io.BufferedReader; import java.io.File; import java.io.IOException; import java.io.Reader; import java.io.StringReader; import java.util.ArrayList; import java.util.Date; import java.util.List; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.demo.html.HTMLParser; 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.ParseException; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.search.Hits; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.Searcher; public class DBdemo { // 创建索引 public void indexFiles() { // 创建索引文件存放路径 File indexDir = new File("D:\\lucene\\index"); try { Date start = new Date(); // 创建分析器,主要用于从文本中抽取那些需要建立索引的内容,把不需要参与建索引的文本内容去掉. // 比如去掉一些a the之类的常用词,还有决定是否大小写敏感. StandardAnalyzer standardAnalyzer = new StandardAnalyzer(); // 参数true用于确定是否覆盖原有索引的 IndexWriter indexWriter = new IndexWriter(indexDir, standardAnalyzer, true); indexWriter.setMergeFactor(100); indexWriter.setMaxBufferedDocs(100); // 只索引这个Field的前5000个字，默认为10000 indexWriter.setMaxFieldLength(5000); // 从数据库取出所有纪录 List<News> newsList = NewsManager.getNewss(); for (int i = 0; i < newsList.size(); i++) { News news = (News) newsList.get(i); // 在Document方法是创建索引的具体代码 Document doc = Document(news); indexWriter.addDocument(doc); } // Optimize的过程就是要减少剩下的Segment的数量,尽量让它们处于一个文件中. indexWriter.optimize(); indexWriter.close(); Date end = new Date(); System.out .println("create index: " + (end.getTime() - start.getTime()) + " total milliseconds"); } catch (IOException e) { System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage()); } } public static Document Document(News news) throws java.io.IOException { Document doc = new Document(); // 为news表的主健创建索引，关于Field的几个参数下面有详细解释 Field fieldId = new Field("uid", news.getNewsId().toString(), Field.Store.YES, Field.Index.UN_TOKENIZED, Field.TermVector.YES); // 为detail字段创建索引，detail在DB中是clob字段，内容为html文本 String contentHtml = news.getContent(); if (contentHtml == null) { contentHtml = ""; } contentHtml = contentHtml.replaceAll("&nbsp;", ""); contentHtml = contentHtml.replaceAll("<[^<>]*>", ""); Reader read = new StringReader(contentHtml); // 用HTMLParser把detail字段中的HTML分析成文本在索引 // HTMLParser这个类可以在lucene的demo中找到 HTMLParser htmlParser = new HTMLParser(read); BufferedReader breader = new BufferedReader(htmlParser.getReader()); String htmlContent = ""; String tempContent = breader.readLine(); while (tempContent != null && tempContent.length() > 0) { htmlContent = htmlContent + tempContent; tempContent = breader.readLine(); } Field fieldContents = new Field("content", htmlContent, Field.Store.COMPRESS, Field.Index.TOKENIZED, Field.TermVector.YES); // db中的每条纪录对应一个doc，每个字段对应一个field doc.add(fieldId); doc.add(fieldContents); return doc; } // 搜索文件，keyword是你在页面上输入的查找关键字，这里查找的是detail字段 public List<News> searchFiles(String keyword) throws ParseException { String index = "D:\\lucene\\index"; // hitsList用来保存db的纪录，这些纪录可以通过查询结果取到 List<News> hitsList = new ArrayList<News>(); try { Date start = new Date(); IndexReader reader = IndexReader.open(index); Searcher searcher = new IndexSearcher(reader); Analyzer analyzer = new StandardAnalyzer(); QueryParser parser = new QueryParser("content", analyzer); // 解析查询关键字，比如输入的是以空格等分开的多个查询关键字，这里解析后，可以多条件查询 Query query = parser.parse(keyword); // hits用来保存查询结果，这里的hits相当于sql中的result Hits hits = searcher.search(query); for (int i = 0; i < hits.length(); i++) { Document doc = hits.doc(i); // 获得news表的主健 String id = doc.get("uid"); // 根据主健去db中取纪录，返回到hitsList中 News news = null; news = NewsManager.getNews(id); // 如果没有找到该纪录，表示该纪录已经不存在，不必添加到hitsList中 System.out.println("ID-------------" + id); System.out.println("content------------" + doc.get("content")); System.out.println("score------------" + hits.score(i)); if (news != null) hitsList.add(news); } System.out.println("--------------" + hits.length()); searcher.close(); reader.close(); Date end = new Date(); System.out .println("search files: " + (end.getTime() - start.getTime()) + " total milliseconds"); } catch (IOException e) { System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage()); } return hitsList; } // 删除索引 public void deleteIndex() { String index = "D:\\lucene\\index"; try { Date start = new Date(); IndexReader reader = IndexReader.open(index); int numFiles = reader.numDocs(); for (int i = 0; i < numFiles; i++) { // 这里的删除只是给文档做一个删除标记，你可以看到执行deleteDocument后会产生一个del后缀的文件， // 用来记录这些标记过的文件 reader.deleteDocument(i); } reader.close(); Date end = new Date(); System.out .println("delete index: " + (end.getTime() - start.getTime()) + " total milliseconds"); } catch (IOException e) { System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage()); } } // 恢复已删除的索引 public void unDeleteIndex() { String index = "D:\\lucene\\index"; try { IndexReader reader = IndexReader.open(index); reader.undeleteAll(); reader.close(); } catch (IOException e) { System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage()); } } public static void main(String[] args) { DBdemo demo = new DBdemo(); List<News> aa = new ArrayList(); try { aa= demo.searchFiles("高"); System.err.println(aa.size()); } catch (ParseException e) { // TODO Auto-generated catch block e.printStackTrace(); } } }