Lucene 2.9 基础应用

在这里就不解释Lucene应用中的基本概念了，直接切入主题

 

一、添加索引过程

	public static void addDocument(String title,String content){
		Document doc = new Document();
		Field titleField = new Field("title",title,Store.YES, Field.Index.ANALYZED,Field.TermVector.WITH_POSITIONS_OFFSETS);
		Field contentField = new Field("content",content, Field.Store.NO, Field.Index.ANALYZED,Field.TermVector.WITH_POSITIONS_OFFSETS);
		Field content2Field = null;
		//CompressionTools 用于将 长文本 或二进制文件压缩存储
		content2Field = new Field("content",CompressionTools.compressString(content), Field.Store.YES);
		doc.add(titleField);
		doc.add(contentField);
		doc.add(content2Field);
		docmentList.add(doc);
	}
	
	public static void index(){
		try {
			//获取索引存放的路径
			FSDirectory indexDir = FSDirectory.open(new File(FilePathUtils.getIndexPath()));
			//实例化IKAnalyzer中文分词器
			Analyzer analyzer = new IKAnalyzer();
			IndexWriter indexWriter = new IndexWriter(indexDir, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);
			for (Document doc : docmentList) {
				indexWriter.addDocument(doc);
			}
			indexWriter.optimize();
			indexWriter.close();
			docmentList = new ArrayList<Document>();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

 二、检索过程

	public static void search(String keyword){
		try {
			//获取索引存放的路径
			FSDirectory indexDir = FSDirectory.open(new File(FilePathUtils.getIndexPath()));
			//集成IKAnalyzer中文分词器
			Analyzer analyzer = new IKAnalyzer();
			// 实例化搜索器
			IndexSearcher searcher = new IndexSearcher(indexDir,true);
			// 在索引器中使用 IKSimilarity 相似度评估器
			searcher.setSimilarity(new IKSimilarity());
			// 使用 IKQueryParser 查询分析器构造 Query 对象
			Query query = IKQueryParser.parse("title", keyword);//指定检索的字段
			//构建高亮显示格式
			SimpleHTMLFormatter sHtmlF = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
			//高亮对象
			Highlighter highlighter = new Highlighter(sHtmlF,new QueryScorer(query));
			//设置高亮附近的字数
			highlighter.setTextFragmenter(new SimpleFragmenter(100));
			//分页索取结果，每页显示5条记录
		    TopScoreDocCollector collector = TopScoreDocCollector.create(5, false);
	        //执行检索
		    searcher.search(query, collector);
	        ScoreDoc[] hits = collector.topDocs().scoreDocs;
	        int numTotalHits = collector.getTotalHits();
	        System.out.println("共检索到"+numTotalHits+"条记录");
			// 输出结果
			for (int i = 0; i < hits.length; i++) {
				Document targetDoc = searcher.doc(hits[i].doc);
				try {
					//highlighter.getBestFragment()获取高亮显示结果
					System.out.println(" 标题： " +  highlighter.getBestFragment(analyzer,"title",targetDoc.get("title")));
					Field contentField = targetDoc.getField("content");
					//CompressionTools.decompressString() 解压
					System.out.println(" 内容： " + CompressionTools.decompressString(contentField.getBinaryValue()));
				} catch (InvalidTokenOffsetsException e) {
					e.printStackTrace();
				} catch (DataFormatException e) {
					e.printStackTrace();
				}
			}
		} catch (IOException e) {
			e.printStackTrace();
		}
	}