Lucene4：创建查询，并高亮查询关键词

1. 要求

环境：

　　Lucene 4.1版本/IKAnalyzer 2012 FF版本/mmseg4j 1.9版本
功能：
　　1).高亮查询演示

注意：

此篇文章开始，索引目录将不再使用示范目录，而是使用真实的数据。即LUCENE_INDEX_DIR = "C:\\lucene\\data"改到了LUCENE_INDEX_DIR = "C:\\solr\\news\\data\\index"。

2. 实现代码

package com.clzhang.sample.lucene;

import java.io.*;

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.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
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.TermQuery;
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.SimpleSpanFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.search.highlight.TokenSources;
import org.apache.lucene.util.Version;

import com.chenlb.mmseg4j.Dictionary;
import com.chenlb.mmseg4j.analysis.SimpleAnalyzer;
import com.chenlb.mmseg4j.analysis.ComplexAnalyzer;

import org.junit.Test;

/**
 * 环境：Lucene 4.1版本/IKAnalyzer 2012 FF版本/mmseg4j 1.9版本
 * 功能：
 * 1.高亮查询演示
 * @author Administrator
 *
 */
public class HighlightDemo {
    // mmseg4j字典路径
    private static final String MMSEG4J_DICT_PATH = "C:\\solr\\news\\conf";
    private static Dictionary dictionary = Dictionary.getInstance(MMSEG4J_DICT_PATH);
    
    // Lucene索引存放路径 
    private static final String LUCENE_INDEX_DIR = "C:\\solr\\news\\data\\index";

    @Test
    public void testHighlighting() throws Exception {
        // 独立测试Highlighting的代码
        String text = "台保钓人士拟起诉日当局 感谢大陆海监船驰援";
        TermQuery query = new TermQuery(new Term("title", "当局"));

        TokenStream tokenStream = new ComplexAnalyzer(dictionary).tokenStream(
                "title", new StringReader(text));
        QueryScorer scorer = new QueryScorer(query, "title");
        Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
        Highlighter highlighter = new Highlighter(scorer);
        highlighter.setTextFragmenter(fragmenter);
        String hlText = highlighter.getBestFragment(tokenStream, text);
        
        System.out.println(hlText);
        System.out.println("--------------------------");
    }
    
    @Test
    public void doHighlightQuery() throws Exception {
        // 实例化IKAnalyzer分词器
//        Analyzer analyzer = new IKAnalyzer();
        
        // 实例化mmseg4j分词器
        Analyzer analyzer = new SimpleAnalyzer(dictionary);

        // 实例化搜索器
        Directory directory = FSDirectory.open(new File(LUCENE_INDEX_DIR));
        DirectoryReader reader = DirectoryReader.open(directory);
        IndexSearcher searcher = new IndexSearcher(reader);
        final String FIELD_NAME = "webTitle";
        String keyword = "记者";

        // 使用QueryParser查询分析器构造Query对象
        QueryParser qp = new QueryParser(Version.LUCENE_41, FIELD_NAME, analyzer);
        Query query = qp.parse(keyword);
        
        // 搜索相似度最高的5条记录
        TopDocs hits = searcher.search(query, 5);
        System.out.println("命中：" + hits.totalHits);

        // 高亮代码1
        QueryScorer scorer = new QueryScorer(query, FIELD_NAME);
        // 下面是指定高亮代码样式的代码
        SimpleHTMLFormatter simpleHtmlFormatter = new SimpleHTMLFormatter("<EM>", "</EM>"); 
        Highlighter highlighter = new Highlighter(simpleHtmlFormatter, scorer);
        highlighter.setTextFragmenter(
                       new SimpleSpanFragmenter(scorer));

        // 输出结果
        for (ScoreDoc scoreDoc : hits.scoreDocs) {
            Document doc = searcher.doc(scoreDoc.doc);
            String title = doc.get(FIELD_NAME);
            
            // 高亮代码2
            TokenStream stream = TokenSources.getAnyTokenStream(
                    searcher.getIndexReader(), scoreDoc.doc, FIELD_NAME, doc, analyzer);
            String fragment = highlighter.getBestFragment(stream, title);
            System.out.println(fragment);
        }
        reader.close();
        directory.close();

        System.out.println("--------------------------");
    }
}

输出：

台保钓人士拟起诉日<B>当局</B> 感谢大陆海监船驰援
--------------------------
命中：125
浙江杭州一男子涉嫌殴打<EM>记者</EM>被警方抓获
领导快看；<EM>记者</EM>曝光！
[视频]节前聚焦烟花爆竹安全 居民楼内存花炮 <EM>记者</EM>举报无人监管 20130203
老夫看过<EM>记者</EM>关于肖某勒索的调查视频，可以说，“胁从犯罪”的证据极为明显——问题就在于，曾经处理方哦，算是结了案，再次处理，法理上有疑问
<EM>记者</EM>调查:重庆忠县一桩疑窦重生的受贿案(转载)
--------------------------