使用Lucene开发自己的搜索引擎

1、下载Lucene开发包，请到：http://lucene.apache.org/

2、在myeclipse环境部署该开发包：

3、代码编写：

package Lucene;

import java.io.File;
import java.io.FileFilter;
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.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

/**
 * 建立索引
 * @author Administrator
 *
 */
public class Indexer {

	/**
	 * @param args
	 */
	public static void main(String[] args) throws Exception{
	
		String indexDir = "E:\index";///在指定目录创建索引文件夹
		String dataDir = "E:\dataSource";///对指定目录中的“.txt”文件进行索引
		
		long start = System.currentTimeMillis();
		Indexer indexer = new Indexer(indexDir);
		int numIndexed;
		try{
			numIndexed = indexer.index(dataDir, new TextFilesFilter());
		}finally{
			indexer.close();
		}
		long end = System.currentTimeMillis();
		
		System.out.println("索引 "+ numIndexed + " 文件花费 "+
		(end - start) + "ms");
		
	}
	
	
	private IndexWriter writer;
	
	//创建Lucene Index Writer
	public Indexer(String indexDir)throws IOException{
		Directory dir = FSDirectory.open(new File(indexDir));
		/*
		 * Version.LUCENE_30:是版本号参数，Lucene会根据输入的版本值，
		 * 针对该值对应的版本进行环境和行为匹配
		 */
		writer = new IndexWriter(dir, new StandardAnalyzer(Version.LUCENE_30), true,
				IndexWriter.MaxFieldLength.UNLIMITED);
	}
	
	//关闭Index Writer
	public void close()throws IOException{
		writer.close();
	}
	
	
	//返回被索引文档文档数
	public int index(String dataDir, FileFilter filter)throws Exception{
		File[] files = new File(dataDir).listFiles();
		
		for(File f:files){
			if(!f.isDirectory() &&
					!f.isHidden()&&
					f.exists()&&
					f.canRead()&&
					(filter == null || filter.accept(f))){
				indexFile(f);
			}
		}
		return writer.numDocs();
	}
	
	//只索引.txt文件，采用FileFilter
	private static class TextFilesFilter implements FileFilter{

		@Override
		public boolean accept(File pathname) {
			// TODO Auto-generated method stub
			return pathname.getName().toLowerCase().endsWith(".txt");
		}
		
	}
	
	protected Document getDocument(File f) throws Exception{
		Document doc = new Document();
		doc.add(new Field("contents", new FileReader(f)));//索引文件内容
		doc.add(new Field("filename", f.getName(),//索引文件名
				Field.Store.YES, Field.Index.NOT_ANALYZED));
		doc.add(new Field("fullpath", f.getCanonicalPath(),//索引文件完整路径
				Field.Store.YES, Field.Index.NOT_ANALYZED));
		
		return doc;
	}
	
	//向Lucene索引中添加文档
	private void indexFile(File f) throws Exception{
		System.out.println("Indexing "+f.getCanonicalPath());
		Document doc = getDocument(f);
		writer.addDocument(doc);
	}

}

这时编译运行代码，如果没出错的话，会出现下面的结果：

Indexing E:dataSource1.txt
Indexing E:dataSource2.txt
Indexing E:dataSource3.txt
Indexing E:dataSource4.txt
索引 4 文件花费 259ms

参考：http://biancheng.dnbcw.info/1000wen/448393.html