检索结果高亮

实现效果：

核心代码

package ucas.ir.lucene;import java.io.File;
import java.io.IOException;import javax.print.Doc;import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.KeywordAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryparser.classic.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
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.QueryScorer;
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;
import org.apache.lucene.util.Version;
import org.wltea.analyzer.lucene.IKAnalyzer;public class IndexSearch {public static void main(String[] args) {Directory directory = null;try {File indexpath = new File("/Users/yp/Documents/workspace/UCASIR/WebContent/index");if (indexpath.exists() != true) {indexpath.mkdirs();}// 设置要查询的索引目录directory = FSDirectory.open(indexpath);// 创建indexSearcherDirectoryReader dReader = DirectoryReader.open(directory);IndexSearcher searcher = new IndexSearcher(dReader);// 设置分词方式Analyzer analyze2 = new StandardAnalyzer(Version.LUCENE_43);// 标准分词Analyzer analyzer = new IKAnalyzer();// 设置查询域String field="news_title";QueryParser parser = new QueryParser(Version.LUCENE_43, field, analyzer);// 查询字符串Query query = parser.parse("阿法狗");QueryScorer scorer=new QueryScorer(query,field);SimpleHTMLFormatter fors=new SimpleHTMLFormatter("<span style=\"color:red;\">", "</span>");Highlighter highlighter=new Highlighter(fors, scorer);System.out.println("query:" + query.toString());// 返回前10条TopDocs topDocs = searcher.search(query, 10);if (topDocs != null) {System.out.println("符合条件第文档总数：" + topDocs.totalHits);for (int i = 0; i < topDocs.scoreDocs.length; i++) {Document doc = searcher.doc(topDocs.scoreDocs[i].doc);TokenStream tokenStream=TokenSources.getAnyTokenStream(searcher.getIndexReader(), topDocs.scoreDocs[i].doc, field, analyzer);Fragmenter  fragment=new SimpleSpanFragmenter(scorer);highlighter.setTextFragmenter(fragment); //高亮news_title域String str=highlighter.getBestFragment(tokenStream, doc.get("news_title"));//获取高亮的片段，可以对其数量进行限制  System.out.println("高亮title："+str);tokenStream=TokenSources.getAnyTokenStream(searcher.getIndexReader(), topDocs.scoreDocs[i].doc, "news_summary", analyzer);str=highlighter.getBestFragment(tokenStream, doc.get("news_summary"));//获取高亮的片段，可以对其数量进行限制  System.out.println("高亮summary："+str);}}directory.close();dReader.close();} catch (Exception e) {e.printStackTrace();}}}

结果：