lucene学习第一篇

本文章转自http://blog.youkuaiyun.com/karldoenitz/article/details/7913505，这篇文章是根据晚上http://www.tudou.com/programs/view/dutIgfATXf4/的视频来做的，视频有些模糊，也可以在优酷网上搜到，但是会不全。我是照着视频做的，自己第一次做的时候老是错误，原来是因为writer.adddocument（doc）时候把这句放在了for循环的外边，导致索引只建立了最后一条的，不能正确索引。

下面是我的源代码，用了lucene.core-3.5.0.jar和junit-4.7.jar俩个包

这是索引和搜索的：

package cn.edu.hit.lx;

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

import javax.swing.text.AbstractDocument.Content;

import org.apache.commons.io.FileUtils;
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;


public class hellolucene {

	public void index() {
		//1.创建Directory
		//创建在内存中
//		Directory directory = new RAMDirectory();
		
		
		//2.创建IndexWriter
		IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35));
		IndexWriter writer = null;
		try {
			//创建在硬盘上
			Directory directory = FSDirectory.open(new File("d:/lucene/index01"));
			writer = new IndexWriter(directory, iwc);
			
			//3.创建Document对象
			Document doc = null;
			
			//4.为Document添加Field
			File f = new File("d:/lucene/examples");
			for(File file:f.listFiles()) {
				doc = new Document();
//				String content=FileUtils.readFileToString(file);
//				System.out.println(content);
//				doc.add(new Field("content",content,Field.Store.NO,Field.Index.NOT_ANALYZED));
				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
				
				writer.addDocument(doc);
				System.out.println(file.getName()+" has Indexed!");  
			}
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (LockObtainFailedException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			if(writer!=null) {
				try {
					writer.close();
				} catch (CorruptIndexException e) {
					e.printStackTrace();
				} catch (IOException e) {
					e.printStackTrace();
				}
			}
		}
		
	}
	
	public void searcher() {
		//1.创建Directory
		//创建在硬盘上
		
		IndexReader reader  = null;
		try {
			Directory directory = FSDirectory.open(new File("d:/lucene/index01"));
			//2.创建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parser来确定要搜索文件的内容，第二个参数表示要搜索的域
			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("software");
			//5.根据searcher搜索并返回TopDocs,这里设置返回十条
			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searcher和ScoredDoc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")+"]");
			}
			
		} catch (IOException e) {
			e.printStackTrace();
		} catch (ParseException e) {
			e.printStackTrace();
		} finally {
			//关闭reader
				try {
					if(reader!=null)
						reader.close();
				} catch (IOException e) {
					e.printStackTrace();
				}
		}
		
	}
}

测试代码：

package cn.edu.hit.lx;

import org.junit.Test;

public class testlucene {

    @Test
    public void testindex(){
	hellolucene hl=new hellolucene();
	hl.index();
    }
    @Test
    public void testsearch(){
	hellolucene hl=new hellolucene();
	hl.searcher();
    }
}