lucene实现 源代码，里面还含有索引创建，搜索等功能

package com.engine.lucene.query; import java.io.IOException; import java.io.StringReader; import java.util.ArrayList; import java.util.Date; import java.util.List; import jeasy.analysis.MMAnalyzer; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.Term; import org.apache.lucene.index.TermDocs; import org.apache.lucene.queryParser.MultiFieldQueryParser; 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; import org.apache.lucene.search.TermQuery; import org.apache.lucene.search.highlight.Highlighter; import org.apache.lucene.search.highlight.QueryScorer; import org.apache.lucene.search.highlight.SimpleHTMLFormatter; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.mira.lucene.analysis.IK_CAnalyzer; import com.common.context.AppContext; import com.engine.lucene.process.LoadIndexDir; import com.knowledge.po.Knowledge; public class Search { public static List searchFiles(String keyword) { Knowledge knowledge = new Knowledge(); // hitsList用来保存db的纪录，这些纪录可以通过查询结果取到 List hitsList = new ArrayList(); try { //根据类型获取存储创建的索引文件存放的位置 LoadIndexDir lid = new LoadIndexDir(); String INDEX_STORE_PATH = lid.getINDEX_STORE_PATH(); Date start = new Date(); Directory fsDir = FSDirectory.getDirectory(INDEX_STORE_PATH); IndexReader reader = IndexReader.open(fsDir); Searcher searcher = new IndexSearcher(INDEX_STORE_PATH); IK_CAnalyzer analyzer = new IK_CAnalyzer(); 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knowledge表的主健 String id = doc.get("uid"); // 根据主健去db中取纪录，返回到hitsList中 try { //根据ID调用在数据库里面获取信息的方法 knowledge = AppContext.getKnowledgeDAOProxy().findKnowledgeById(new Long(id)); } catch (Exception e) { knowledge = null; } // 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 if (knowledge != null) { hitsList.add(knowledge); } } 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()); } catch (ParseException e) { System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage()); } return hitsList; } public static Hits doSearch(String key) { Hits hits = null; try { //根据类型获取存储创建的索引文件存放的位置 LoadIndexDir lid = new LoadIndexDir(); String INDEX_STORE_PATH = lid.getINDEX_STORE_PATH(); Directory fsDir = FSDirectory.getDirectory(INDEX_STORE_PATH); IndexReader reader = IndexReader.open(fsDir); Searcher search = new IndexSearcher(INDEX_STORE_PATH); String fields[] = {"content" }; IK_CAnalyzer analyzer = new IK_CAnalyzer(); QueryParser parser = new MultiFieldQueryParser(fields, analyzer); Query query = parser.parse(key); hits = search.search(query); for (int i = 0; i < hits.length(); i++) { Document doc = hits.doc(i); String text = hits.doc(i).get("content"); SimpleHTMLFormatter sHtmlF = new SimpleHTMLFormatter( "<b><font color='red'>", "</font></b>"); Highlighter highlighter = new Highlighter(sHtmlF, new QueryScorer(parser.parse(key))); //highlighter.setTextFragmenter(new SimpleFragmenter(100)); TokenStream tokenStream = new StandardAnalyzer().tokenStream( "content", new StringReader(text)); // Get 3 best fragments and seperate with a "..." String result = highlighter.getBestFragments(tokenStream, text, 3, "..."); System.out.println(result); Field tempField = new Field("content", result, Field.Store.NO, Field.Index.TOKENIZED, Field.TermVector.YES); doc.removeField("content"); doc.add(tempField); } } catch (Exception e) { e.printStackTrace(); } System.out.println("搜索结果:" + hits.length()); return hits; } public static void indexSearch(String searchType, String searchKey) { try { LoadIndexDir lid = new LoadIndexDir(); String INDEX_STORE_PATH = lid.getINDEX_STORE_PATH(); // 根据索引位置建立IndexSearcher IndexSearcher searcher = new IndexSearcher(INDEX_STORE_PATH); // 建立搜索单元，searchType代表要搜索的Filed，searchKey代表关键字 Term t = new Term(searchType, searchKey); // 由Term生成一个Query Query q = new TermQuery(t); // 搜索开始时间 Date beginTime = new Date(); // 获取一个<document, frequency>的枚举对象TermDocs TermDocs termDocs = searcher.getIndexReader().termDocs(t); while (termDocs.next()) { // 输出在文档中出现关键词的次数 System.out.println(termDocs.freq()); // 输出搜索到关键词的文档 System.out.println(searcher.getIndexReader().document(termDocs.doc())); } // 搜索完成时间 Date endTime = new Date(); // 搜索所耗时间 long timeOfSearch = endTime.getTime() - beginTime.getTime(); System.out .println("The time For indexsearch is " + timeOfSearch + " ms"); } catch (IOException e) { e.printStackTrace(); } } }