lucene中文分词搜索的核心代码

Posted 2020-09-13 编世界

    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);
        // Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
        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();
    }