Luence 课程1----索引和搜索的建立

最新推荐文章于 2022-06-26 21:48:48 发布

原创最新推荐文章于 2022-06-26 21:48:48 发布 · 433 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#索引 #搜索 #lucence

lucence 专栏收录该内容

1 篇文章

订阅专栏

本文介绍如何使用Lucene进行文档的索引建立及搜索操作。具体包括使用StandardAnalyzer进行文档分析，通过IndexWriter将指定目录下的文件内容建立索引，并演示了如何通过QueryParser构建查询表达式来实现基于内容的文档搜索。

package com.lucence;

import java.io.File;
import java.io.FileReader;
import java.io.IOException;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.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.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;

public class HelloLucence {
   /**
   * 建立索引
   * @throws IOException
   * @throws LockObtainFailedException
   * @throws CorruptIndexException
   */
   public void index() {
       //2、创建IndexWriter(写索引)
       IndexWriter writer=null;
       try {
           //1、创建Directory(内存or硬盘)
           //   Directory directory=new RAMDirectory();//建立在内存中
           Directory directory=FSDirectory.open(new File("E:/lucence/index01"));//创建在硬盘上
           writer=new IndexWriter(directory,
                   new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
           //3、创建Document对象(文档或者数据表，包含名称，路径，大小等)
           Document doc=null;
           //4、为Document添加Field
           File f=new File("E:/lucence");
           for(File file:f.listFiles()){
               doc=new Document();
               doc.add(new Field("content", new FileReader(file)));
               doc.add(new Field("filename",file.getName(),Field.Store.YES,Field.Index.NOT_ANALYZED));
               doc.add(new Field("path",file.getAbsolutePath(),Field.Store.YES,Field.Index.NOT_ANALYZED));
           }
           //5、通过IndexWriter添加文档到索引中

       } catch (CorruptIndexException e) {
           // TODO Auto-generated catch block
           e.printStackTrace();
       } catch (LockObtainFailedException e) {
           // TODO Auto-generated catch block
           e.printStackTrace();
       } catch (IOException e) {
           // TODO Auto-generated catch block
           e.printStackTrace();
       }finally{
           try {
               writer.close();
           } catch (CorruptIndexException e) {
               // TODO Auto-generated catch block
               e.printStackTrace();
           } catch (IOException e) {
               // TODO Auto-generated catch block
               e.printStackTrace();
           }
       }
   }

   /**
   * 搜索
   */
   public void searcher(){
       try {
           //1、创建Directory
           Directory directory=FSDirectory.open(new File("E:/lucence/index01"));
           //2、创建IndexReader
           IndexReader reader=IndexReader.open(directory);
           //3、根据IndexReader创建IndexSearcher
           IndexSearcher searcher=new IndexSearcher(reader);
           //4、创建搜索的Query
           //创建parse来确定要搜索文件的内容，第二个参数表示搜索的域
           QueryParser parser=new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35));
           //创建query，表示搜索域为content中包含Java的文档
           Query query=parser.parse("java");//搜索内容中包含Java的
           //5、根据seacher搜索并且返回TopDocs
           TopDocs tds=searcher.search(query,10);
           //6、根据TopDocs获取scoreDoc对象
           ScoreDoc[] sds=tds.scoreDocs;
           for(ScoreDoc sd:sds){
               //7、根据seacher和ScoreDoc对象
               Document d=searcher.doc(sd.doc);
               //8、根据Document对象获取需要的值
               System.out.print(d.get("filename")+"["+d.get("path")+"]");
           }
           //9、关闭reader
           reader.close();
       } catch (IOException e) {
           // TODO Auto-generated catch block
           e.printStackTrace();

       } catch (ParseException e) {
           // TODO Auto-generated catch block
           e.printStackTrace();
       }
   }

}