Lucene学习

中文分词器pom

<dependency>
		<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-analyzers-smartcn</artifactId>
		<version>5.3.1</version>
	</dependency>

搜索高亮pom

<dependency>
		<groupId>org.apache.lucene</groupId>
		<artifactId>lucene-highlighter</artifactId>
		<version>5.3.1</version>
	</dependency>

中文分词代码

SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
		IndexWriterConfig iwc=new IndexWriterConfig(analyzer);
		IndexWriter writer=new IndexWriter(dir, iwc);

中文检索以及高亮代码

public static void search(String indexDir,String q)throws Exception{
		Directory dir=FSDirectory.open(Paths.get(indexDir));
		IndexReader reader=DirectoryReader.open(dir);
		IndexSearcher is=new IndexSearcher(reader);
		// 中文分词器
		SmartChineseAnalyzer analyzer=new SmartChineseAnalyzer();
		QueryParser parser=new QueryParser("desc", analyzer);
		Query query=parser.parse(q);
		long start=System.currentTimeMillis();
		TopDocs hits=is.search(query, 10);
		long end=System.currentTimeMillis();
		System.out.println("匹配 "+q+" ，总共花费"+(end-start)+"毫秒"+"查询到"+hits.totalHits+"个记录");
		
		
		QueryScorer scorer=new QueryScorer(query);
		Fragmenter fragmenter=new SimpleSpanFragmenter(scorer);
		SimpleHTMLFormatter simpleHTMLFormatter=new SimpleHTMLFormatter("<b><font color='red'>","</font></b>");
		Highlighter highlighter=new Highlighter(simpleHTMLFormatter, scorer);
		highlighter.setTextFragmenter(fragmenter);
		for(ScoreDoc scoreDoc:hits.scoreDocs){
			Document doc=is.doc(scoreDoc.doc);
			System.out.println(doc.get("city"));
			System.out.println(doc.get("desc"));
			String desc=doc.get("desc");
			if(desc!=null){
				TokenStream tokenStream=analyzer.tokenStream("desc", new StringReader(desc));
				System.out.println(highlighter.getBestFragment(tokenStream, desc));
			}
		}
		reader.close();
	}