lucene 学习一

 

索引工具的三部分
　　1.索引部分
　　2.分词部分
　　3.搜索部分

 

查看索引的工具：luke   java -jar fileName.jar

 

目标：为文件夹的所有的文档生成索引并搜索它

package com.lucene;

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.util.Version;

// lucene 使用的版本为 3.5
public class HelloLucene {

    
    public static void main(String[] args) {
        HelloLucene hl = new HelloLucene();
        hl.index();
        hl.search();
    }
    
    /**
     * 建立文档索引
     */
    public void index() {
        
        IndexWriter writer = null;
        
        try {
            //1.创建Director(确定索引建立的位置)
//            Directory directory = new RAMDirectory(); //在内存中建立
            Directory directory = FSDirectory.open(new File("d:/index_01"));
            
            //2.通过 IndexWriter 写索引
            IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35));
            writer = new IndexWriter(directory, iwc);
            
            //3.创建 Document 对象
            Document doc = null;
            File f = new File("G:/lucene/");
            for(File file : f.listFiles()){
                //4.为文档 添加Field （文档的每个属性比如名称可以称之为文档的一个Field）
                doc = new  Document();
                doc.add(new Field("content", new FileReader(file)));
                doc.add(new Field("filename", file.getName(), Field.Store.YES, Field.Index.ANALYZED_NO_NORMS));
                doc.add(new Field("path", file.getAbsolutePath(), Field.Store.YES, Field.Index.ANALYZED_NO_NORMS));
                
                //5.通过IndexWrite添加文档到索引中
                writer.addDocument(doc);
                
                // 在索引库没有建立并且没有索引文件的时候首先要commit一下让他建立一个 索引库的版本信息  
                writer.commit();
            }

        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
                try {
                    if(writer != null) writer.close();
                } catch (CorruptIndexException e1) {
                    e1.printStackTrace();
                } catch (IOException e1) {
                    e1.printStackTrace();
                }
            e.printStackTrace();
        }
        
    }

    
    /**
     * 搜索
     */
    public void search(){
        
        try {
            //1.创建Directory
            Directory directory = FSDirectory.open(new File("d:/index_01"));
            
            //2.创建IndexReader
            IndexReader reader = IndexReader.open(directory);
            
            //3.根据IndexReader创建IndexSearcher
            IndexSearcher searcher = new IndexSearcher(reader);
            
            //4.创建搜索的的Query
            QueryParser parser = new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35));
            
            //要搜索的内容
            Query query = parser.parse("document");
            
            //5.根据searcher搜索并返回TopDocs
            TopDocs tds = searcher.search(query, 100);
            
            //6.根据TopDocs获取scoreDocs对象
            ScoreDoc[] sds = tds.scoreDocs;
            
            for(ScoreDoc sd:sds)
            {
                //7.根据Search和ScoreDoc对象获取具体的Document对象
                Document  d = searcher.doc(sd.doc);
                
                //8.根据document对象获取需要的值                
                System.out.println(d.get("filename")+"|"+d.get("path"));
            }
            
            System.out.println(sds.length);    
            
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (ParseException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
        
        //2.
    }

}