package com.laozizhu.search.demo;

import net.paoding.analysis.analyzer.PaodingAnalyzer;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocCollector;
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;

/**
 * Lucene 2.4 + Highlighter 2.4 的分頁+高亮顯示代碼.<br>
 * 高亮的css自己寫吧。
 * 
 * @author 老紫竹研究室(laozizhu.com)
 */
public class TestLuceneHighlighter {
  private static final String FIELD_TITLE = "title";

  private static final String FIELD_BODY = "body";

  public synchronized Analyzer getAnalyzer() {
    return new PaodingAnalyzer();
  }

  public void test(String queryString, int begin, int number) {
    IndexSearcher isearcher = null;
    try {
      isearcher = new IndexSearcher("d:/index");
      /* 下面這個表示要同時搜索這兩個域，而且只要一個域里面有滿足我們搜索的內(nèi)容就行 */
      BooleanClause.Occur[] clauses = { BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD };
      TopDocCollector collector = new TopDocCollector(10);
      Query query = MultiFieldQueryParser.parse(queryString, new String[] { FIELD_TITLE, FIELD_BODY }, clauses, getAnalyzer());
      isearcher.search(query, collector);
      ScoreDoc[] hits = collector.topDocs().scoreDocs;
      // 用這個進(jìn)行高亮顯示，默認(rèn)是<b>..</b>
      // 用這個指定<read>..</read>
      SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<read>", "</read>");
      // 構(gòu)造高亮
      // 指定高亮的格式
      // 指定查詢評分
      Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query));
      // 這個一般等于你要返回的，高亮的數(shù)據(jù)長度
      // 如果太小，則只有數(shù)據(jù)的開始部分被解析并高亮，且返回的數(shù)據(jù)也少
      // 太大，有時太浪費(fèi)了。
      highlighter.setTextFragmenter(new SimpleFragmenter(Integer.MAX_VALUE));
      for (int i = begin; i < hits.length && i < begin + number; i++) {
        Document doc = isearcher.doc(hits[i].doc);
        // 有三個參數(shù)
        // 分析器
        // 要解析的字段名
        // 要解析的數(shù)據(jù)
        System.out.println(highlighter.getBestFragment(getAnalyzer(), FIELD_TITLE, doc.get(FIELD_TITLE)));
      }
    } catch (Exception e) {
      e.printStackTrace();
    } finally {
      if (isearcher != null) {
        try {
          isearcher.close();
        } catch (Exception e) {
          e.printStackTrace();
        }
      }
    }
  }
}