lucene高亮demo

java 代码

package com.feedsky.lucene;

import java.io.StringReader;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.highlight.Highlighter;
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.store.Directory;
import org.apache.lucene.store.RAMDirectory;



public class HighLighterTest
{

    public static void main(String[] args)
    {
        String fieldName = "text";
        String text = "《越狱3》播出时间再次延期 急煞中国“狱友” 巨型变形金刚惊现北京 《龙珠Z》绝招威力排行 《不能说的秘密》清纯版 迅雷宽频合作发行 《越狱动画版》"; //检索内容

        //采用猎兔分词
        Analyzer analyzer = new CnAnalyzer();

        Directory directory = new RAMDirectory();

        try
        {
            //索引
            IndexWriter iwriter = new IndexWriter(directory, analyzer, true);
            iwriter.setMaxFieldLength(25000);
            Document doc = new Document();
            doc.add(new Field(fieldName, text, Field.Store.YES,
                    Field.Index.TOKENIZED,
                    Field.TermVector.WITH_POSITIONS_OFFSETS));
            iwriter.addDocument(doc);
            iwriter.close();

            IndexSearcher isearcher = new IndexSearcher(directory);

            QueryParser queryParse = new QueryParser(fieldName, analyzer);
            Query query = queryParse.parse("越狱");
            Hits hits = isearcher.search(query);
            for (int i = 0; i < hits.length(); i++) {
                Document docTemp = hits.doc(i);
                String value = docTemp.get(fieldName);
        //      对要高亮显示的字段格式化，这里只是加红色显示和加粗
                SimpleHTMLFormatter sHtmlF = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
                Highlighter highlighter = new Highlighter(sHtmlF,new QueryScorer(query));
                highlighter.setTextFragmenter(new SimpleFragmenter(10));

                if (value != null) {
                    TokenStream tokenStream = analyzer.tokenStream(fieldName,new StringReader(value));
                    String str = highlighter.getBestFragment(tokenStream, value);

                    System.out.println(str);
                }
           }

            isearcher.close();
            directory.close();
        }
        catch (Exception e)
        {
            e.printStackTrace();
        }
    }

}

 

 

运行结果为:

《<b><font color='red'>越狱</font></b>3》播出时间

分享到：

过滤Html标签（转） | hibernate 批量插入

• 2007-07-31 17:19
• 浏览 5165
• 评论(0)
• 查看更多