创新引导工具结果lucene高亮显示

搜索引擎展示的结果中对用户的输入信息进行了配色方面的处理，这种区分正常文本和输入内容的效果即是高亮显示；

这样做的好处：

·视觉上让人便于查找有搜索对应的文本块；
·界面展示更友好；
·lucene提供了highlighter插件来体现类似的效果；

highlighter对查询关键字高亮处理：

import com.example.springboot.entity.Patent;
import org.apache.commons.lang.StringUtils;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.*;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;


/**
 * @Description: TODO
 * @author: dell
 * @date: 2022年04月05日 15:16
 */
public class DataBaseSearcher {

    public static final String INDEXPATH = "D:\\lucene-4.6.0\\indexAndDocs\\index";
    private static int TOP_NUM = 100; // 显示记录数
    
    public static List<Patent> searchData(String queryString) {
        Directory dir = null;
        List<Patent> patentList = new ArrayList<>();
        try {
            //索引地址
            File f = new File(INDEXPATH);
            dir = FSDirectory.open(f);
            IndexReader reader = DirectoryReader.open(dir);
            //添加reader
            IndexSearcher searcher = new IndexSearcher(reader);
            //lucene系统分词处理
            Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_46);
            //添加查找的字段
            String fieldString1 = "name";
            String fieldString2 = "abstract";
            //String fieldString3 = "zqx";
            String[] fields = {fieldString1, fieldString2};
            //搜索多个字段，多条件搜索
            //QueryParser parser = new QueryParser(Version.LUCENE_46,fieldString2, analyzer);
            QueryParser parser = new MultiFieldQueryParser(Version.LUCENE_46, fields, analyzer);
            parser.setDefaultOperator(QueryParser.AND_OPERATOR);
            Query query = parser.parse(queryString);
            //Query query = parser.parse(queryStr);
            QueryScorer scorer = new QueryScorer(query, fieldString2);
            SimpleHTMLFormatter fors = new SimpleHTMLFormatter("<span style=\"color:yellow;\">", "</span>");
            Highlighter highlighter = new Highlighter(fors, scorer);
            TopDocs hits = searcher.search(query, 1000); // 查找操作，显示n条数据，现在是5
            for (ScoreDoc scoreDoc : hits.scoreDocs) {
                TokenStream tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), scoreDoc.doc, fieldString1, analyzer);
                Document doc = searcher.doc(scoreDoc.doc); // 根据文档打分得到文档的内容
                Fragmenter fragment = new SimpleSpanFragmenter(scorer, doc.get("abstract").length());
                highlighter.setTextFragmenter(fragment);
                //高亮news_title域
                String name = highlighter.getBestFragment(tokenStream, doc.get("name"));//获取高亮的片段，可以对其数量进行限制
                tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), scoreDoc.doc, fieldString2, analyzer);
                String _abstarct = highlighter.getBestFragment(tokenStream, doc.get("abstract"));//获取高亮的片段，可以对其数量进行限制
                Patent patent = new Patent();
                patent.setId(doc.get("id"));
                if(name != null){
                    patent.setName(name);
                }else{
                    patent.setName("<span>"+doc.get("name")+"</span>");
                }
                if(_abstarct != null){
                    patent.setContent(_abstarct);
                }else{
                    patent.setName("<span>"+doc.get("abstract")+"</span>");
                }
                patent.setType(doc.get("type"));
                patent.setSqrq(doc.get("sqrq"));
                patent.setGkr(doc.get("gkr"));
                patent.setGkh(doc.get("gkh"));
                patent.setZflh(doc.get("zflh"));
                patent.setFlh(doc.get("flh"));
                patent.setFmr(doc.get("fmr"));
                patent.setZldljg(doc.get("zldljg"));
                patent.setDlr(doc.get("dlr"));
                patent.setSsdm(doc.get("ssdm"));
                patent.setFlzt(doc.get("flzt"));
                patent.setUrl(doc.get("url"));
                patent.setField(doc.get("field"));
                patent.setWeight((int) (1000 * (scoreDoc.score)));
                patentList.add(patent);
            }

        } catch (IOException | ParseException | InvalidTokenOffsetsException e) {
            e.printStackTrace();
        }
        return patentList;
    }

}