Lucene关键词高亮显示

Lucene5 实现搜索引擎功能，高亮代码


package search.searchengine.cs.swjtu;

import java.io.IOException; 
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;

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.ParseException;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher; 
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopScoreDocCollector;
import org.apache.lucene.search.highlight.Formatter;
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.Directory;
import org.apache.lucene.store.FSDirectory;

public class Query { 

/*
* 
* 索引后，进行查询，将查询结果封装为QueryBean对象，加入session，为JSP提供页面结果
* 
* */

private static String lighterStr(org.apache.lucene.search.Query query,Analyzer a,String fieldName,String txt) throws IOException, InvalidTokenOffsetsException {
String str = null;//设定放回结果
QueryScorer queryScorer = new QueryScorer(query);//如果有需要，可以传入评分
//设置高亮标签
Formatter formatter = new SimpleHTMLFormatter("<span style='color:red;'>", "</span>");
//高亮分析器
Highlighter hl = new Highlighter(formatter, queryScorer);

Fragmenter fragmenter = new SimpleSpanFragmenter(queryScorer);
hl.setTextFragmenter(fragmenter);
//获取返回结果
str = hl.getBestFragment(a, fieldName,txt);
if(str == null){
return txt;
}
return str;
}

public static List query(String queryString,String indexUrl) throws IOException, ParseException, InvalidTokenOffsetsException { 
/**/ /* 这里放索引文件的位置 */ 
Path path = Paths.get(indexUrl);
Directory indexDir = FSDirectory.open(path); 


org.apache.lucene.search.Query query = null; 
IndexReader reader = DirectoryReader.open(indexDir);
IndexSearcher searcher = new IndexSearcher(reader); 

TopScoreDocCollector collector = TopScoreDocCollector.create(10);
Analyzer analyzer = new StandardAnalyzer(); 

QueryScorer queryScorer = new QueryScorer(query);//如果有需要，可以传入评分
//设置高亮标签
Formatter formatter = new SimpleHTMLFormatter("<span style='color:red;'>", "</span>");
//高亮分析器
Highlighter hl = new Highlighter(formatter, queryScorer);

Fragmenter fragmenter = new SimpleSpanFragmenter(queryScorer);
hl.setTextFragmenter(fragmenter);


try { 
QueryParser qp = new QueryParser( "content", analyzer); 
query = qp.parse(queryString); 
} catch (ParseException e) { 
} 

searcher.search(query, collector); 
ScoreDoc[] hits = collector.topDocs().scoreDocs;

List<String> rstList = new ArrayList<String>();//结果列表（已高亮处理）

System.out.println("Found " + hits.length + " hits.");
for(int i=0;i<hits.length;i++) {

int docId = hits[i].doc;
Document d = searcher.doc(docId);

String rst = "";

String title = d.get("title");
String content = d.get("content");

title = lighterStr(query, analyzer, "title", title);
content = lighterStr(query, analyzer, "content", content);

rst = d.get("url")+"\t"+title+"\t"+content;
rstList.add(rst);
//System.out.println((i + 1) +". " + d.get("url") +" "+title+"\t"+content);
System.out.println((i + 1) +". " + rst);

}
return rstList; 
} 

}