lucene 高亮显示

来源：互联网发布：ssl模块编译进nginx 编辑：程序博客网时间：2024/05/01 23:21

package src;

import java.io.StringReader;
import java.util.Date;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.SimpleAnalyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.cjk.CJKAnalyzer;
import org.apache.lucene.analysis.cn.ChineseAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;

import java.util.Date;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
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;

public class LuceneSearch {
public static void main(String[] args) throws Exception{
  LuceneSearch test = new LuceneSearch();
  //
  Hits h = null;
  h = test.search("显示 ");
  test.printResult(h);


  h = test.search("jy*");
  test.printResult(h);

  h = test.search("djy");
  test.printResult(h);


}
public LuceneSearch(){
  try{
   searcher = new IndexSearcher(IndexReader.open("E://lucene//test4//index"));
  }catch(Exception e){
   e.printStackTrace();
  }
}
//声明一个IndexSearcher对象
private IndexSearcher searcher = null;
//声明一个Query对象
private Query query = null;
ChineseAnalyzer analyzer = new ChineseAnalyzer();
Highlighter highlighter = null;
public final Hits search(String keyword){
  System.out.println("正在检索关键字:"+keyword);
  try{
   QueryParser qp = new QueryParser("title",analyzer);
   query = qp.parse(keyword);

   Term term = new Term("content",keyword);
   FuzzyQuery fq = new FuzzyQuery(term);
   Date start = new Date();

   //Hits hits = searcher.search(query);
   Hits hits = searcher.search(query);


   //高亮显示设置
   SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<read>","</read>");
   highlighter = new Highlighter(simpleHTMLFormatter,new QueryScorer(query));
   highlighter.setTextFragmenter(new SimpleFragmenter(10));//这个100是指定关键字字符串的context的长度，你可以自己设定，因为不可能返回整篇正文内容



   Date end = new Date();
   System.out.println("检索完成,用时"+(end.getTime()-start.getTime())+"毫秒");
   return hits;
  }catch(Exception e){
   e.printStackTrace();
   return null;
  }

}

public void printResult(Hits h){
  if(h.length() == 0){
   System.out.println("对不起,没有找到您要的结果.");
  }else{
   for(int i = 0; i < h.length(); i++){
    try{
     Document doc = h.doc(i);
     System.out.println("这个是"+(i+1)+"个结果:"+doc.get("id")+" title:"+doc.get("title")+"        content:"+doc.get("content"));

     //高亮出显示
     TokenStream tokenStream =analyzer.tokenStream("content", new StringReader(doc.get("title")));
     System.out.println(highlighter.getBestFragment(tokenStream,h.doc(i).get("title")));

     //System.out.println(doc.get("path"));
    }catch(Exception e){
     e.printStackTrace();
    }
   }
  }
  System.out.println("--------------------------------------");
}
}

private void printResult(Hits h) {
      if (h.length() > 0) {
         for (int i = 0; i < h.length(); i++) {
            SearchResultModel resultModel = new SearchResultModel();
            try {
                  Document doc = h.doc(i);
                  resultModel.setId(i);
                  resultModel.setFileName(doc.get("filename"));
                  resultModel.setUrl(doc.get("path"));
                  resultModel.setDateTime(doc.get("datetime"));
                  // 高亮出显示
                  /*需要注意的是，如果标题或者内容中没有需要高亮显示的关键字，那么标题或者内容是为null,所以做了下面的处理。判断标题或者内容是否空，如果空，截取前面的部分字符。*/
                  TokenStream tokenStream1 = analyzer.tokenStream("title",
                        new StringReader(doc.get("title")));
                  String sTitle = highlighter.getBestFragment(tokenStream1,doc.get("title"));
                  String sTitle2 = doc.get("title");
                  resultModel.setTitle(sTitle!=null?sTitle:sTitle2);
                  TokenStream tokenStream = analyzer.tokenStream("contents",
                        new StringReader(doc.get("contents")));
                  String sContent = highlighter.getBestFragment(tokenStream,
                        doc.get("contents"));
                  String sContent2 = doc.get("contents");
                  resultModel.setContent(sContent!=null?sContent:sContent2.substring(0,100)+"...");
            } catch (Exception e) {
                  e.printStackTrace();
            }
            this.mapResult.put(i, resultModel);
         }
      }
}