Lucene查询结果高亮

代码

package com.baifan.lucene.index;

import com.baifan.lucene.ik.IKAnalyzer6x;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
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.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.search.highlight.SimpleSpanFragmenter;
import org.apache.lucene.search.highlight.TokenSources;
import org.apache.lucene.store.FSDirectory;

import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

/**
 * @author: baifan
 * @date: 2021/6/17
 */
public class HighlighterTest {

	public static void main(String[] args) throws IOException, ParseException, InvalidTokenOffsetsException {
		String field = "title";
		Path indexdir = Paths.get("indexdir");
		FSDirectory directory = FSDirectory.open(indexdir);
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Analyzer analyzer = new IKAnalyzer6x();
		QueryParser parser = new QueryParser(field, analyzer);
		Query query = parser.parse("北大");
		System.out.println("Query:" + query.toString());
		QueryScorer score = new QueryScorer(query, field);
		//定制高亮标签
		SimpleHTMLFormatter fors = new SimpleHTMLFormatter("<span style=\"color:red;\">", "</span>");
		//高亮分词器
		Highlighter highlighter = new Highlighter(fors, score);
		// 返回前10条
		TopDocs tds = searcher.search(query, 10);
		for (ScoreDoc sd : tds.scoreDocs) {
			Document doc = searcher.doc(sd.doc);
			System.out.println("DocID:" + sd.doc);
			System.out.println("id:" + doc.get("id"));
			System.out.println("title:" + doc.get("title"));
			//获取 tokenStream
			TokenStream tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), sd.doc, field, analyzer);
			Fragmenter fragments = new SimpleSpanFragmenter(score);
			highlighter.setTextFragmenter(fragments);
			//获取高亮的片段
			String str = highlighter.getBestFragment(tokenStream, doc.get(field));
			System.out.println("高亮的片段:" + str);
		}
		directory.close();
		reader.close();
	}
}

运行结果:

加载扩展词典：ext.dic
加载扩展停止词典：stopword.dic
加载扩展停止词典：ext_stopword.dic
Query:title:北大
DocID:1
id:2
title:北大迎4380名新生 农村学生700多人近年最多
高亮的片段:<span style="color:red;">北大</span>迎4380名新生 农村学生700多人近年最多