渲染在頁面的關鍵字高亮, 以及適用於國內形式的中文分詞器.

    需要引用的jar 看Lucene的第一章的pom.xml

package com.zero.lucene;

import java.nio.file.Paths;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene
 
.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
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.Formatter;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;

/**
 * 搜尋的時候 關鍵字紅色
 * @author samuel
 *
 */
public class SearcherColor {

    private IndexReader indexReader;
    private IndexSearcher indexSearcher;

    /**
     * 搜尋索引
     * @throws Exception
     */
    public void searcher() throws Exception {
        String uri = "";
        Directory directory = FSDirectory.open(Paths.get(uri));
        indexReader = DirectoryReader.open(directory);
        indexSearcher = new IndexSearcher(indexReader);
        // 中文分詞
        Analyzer analyer = new SmartChineseAnalyzer();
        QueryParser parser = new QueryParser("title", analyer);
        Query query = parser.parse("pwd.txt");
        TopDocs topDocs = indexSearcher.search(query, 10);

        // 高亮部分

        QueryScorer queryScorer = new QueryScorer(query);
        // 設定關鍵的高亮度字型和顏色
        Formatter formatter = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
        Highlighter highligther = new Highlighter(formatter, queryScorer);
        Fragmenter fragmentScorer = new SimpleSpanFragmenter(queryScorer);
        highligther.setTextFragmenter(fragmentScorer);

        for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
            Document doc = indexReader.document(scoreDoc.doc);
            String title = doc.get("title");
            if (null != title) {
                // 拿到最高分數的內容片斷
                TokenStream tokenStream = analyer.tokenStream("title", "hahahah");
                String bestSpan = highligther.getBestFragment(tokenStream, title);
                System.out.println(bestSpan);
            }
        }


    }
}