（1）添加必要的hadoop jar包。
A、首先将Hadoop1.1.2.tar.gz解压到某一个磁盘下。
B、右键选择工程，选择build path....， build configure path；
C、将hadoop1.1.2文件夹下的jar包添加进去；
还有lib文件夹下的所有jar包（注意：jasper-compiler-5.5.12.jar和jasper-runtime-5.5.12.jar不要引进，否则会报错）
注意：在build path引入这些jar包后，还需要将这些jar包复制到WEB-INF/lib目录下，可以通过下面操作实现：
选择工程，右键“Properties”，选择Deployment Assembly。
点击Add，选择Java Build Path Entries。
然后把你刚刚引进的Jar包全部选上，点击finishes。
D 、创建java工程
创建HdfsDAO类：
package com.model;
import java.io.IOException;
import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapred.JobConf;
public class HdfsDAO {
//HDFS访问地址
private static final String HDFS = "hdfs://192.168.1.104:9000";
public HdfsDAO(Configuration conf) {
this(HDFS, conf);
}
public HdfsDAO(String hdfs, Configuration conf) {
this.hdfsPath = hdfs;
this.conf = conf;
}
//hdfs路径
private String hdfsPath;
//Hadoop系统配置
private Configuration conf;
//启动函数
public static void main(String[] args) throws IOException {
JobConf conf = config();
HdfsDAO hdfs = new HdfsDAO(conf);
//hdfs.mkdirs("/Tom");
//hdfs.copyFile("C:\\files", "/wgc/");
hdfs.ls("hdfs://192.168.1.104:9000/wgc/files");
//hdfs.rmr("/wgc/files");
//hdfs.download("/wgc/（3）windows下hadoop+eclipse环境搭建.docx", "c:\\");
//System.out.println("success!");
}
//加载Hadoop配置文件
public static JobConf config(){
JobConf conf = new JobConf(HdfsDAO.class);
conf.setJobName("HdfsDAO");
conf.addResource("classpath:/hadoop/core-site.xml");
conf.addResource("classpath:/hadoop/hdfs-site.xml");
conf.addResource("classpath:/hadoop/mapred-site.xml");
return conf;
}
//在根目录下创建文件夹
public void mkdirs(String folder) throws IOException {
Path path = new Path(folder);
FileSystem fs = FileSystem.get(URI.create(hdfsPath), conf);
if (!fs.exists(path)) {
fs.mkdirs(path);
System.out.println("Create: " + folder);
}
fs.close();
}
//某个文件夹的文件列表
public FileStatus[] ls(String folder) throws IOException {
Path path = new Path(folder);
FileSystem fs = FileSystem.get(URI.create(hdfsPath), conf);
FileStatus[] list = fs.listStatus(path);
System.out.println("ls: " + folder);
System.out.println("==========================================================");
if(list != null)
for (FileStatus f : list) {
//System.out.printf("name: %s, folder: %s, size: %d\n", f.getPath(), f.isDir(), f.getLen());
System.out.printf("%s, folder: %s, 大小: %dK\n", f.getPath().getName(), (f.isDir()?"目录":"文件"), f.getLen()/1024);
}
System.out.println("==========================================================");
fs.close();
return list;
}
public void copyFile(String local, String remote) throws IOException {
FileSystem fs = FileSystem.get(URI.create(hdfsPath), conf);
//remote---/用户/用户下的文件或文件夹
fs.copyFromLocalFile(new Path(local), new Path(remote));
System.out.println("copy from: " + local + " to " + remote);
fs.close();
}
//删除文件或文件夹
public void rmr(String folder) throws IOException {
Path path = new Path(folder);
FileSystem fs = FileSystem.get(URI.create(hdfsPath), conf);
fs.deleteOnExit(path);
System.out.println("Delete: " + folder);
fs.close();
}
//下载文件到本地系统
public void download(String remote, String local) throws IOException {
Path path = new Path(remote);
FileSystem fs = FileSystem.get(URI.create(hdfsPath), conf);
fs.copyToLocalFile(path, new Path(local));
System.out.println("download: from" + remote + " to " + local);
fs.close();
}
}
运行测试该程序：
其他函数测试也成功，这里就不一一列举了。
打开Uploadservlet文件，修改：
package com.controller;
import java.io.File;
import java.io.IOException;
import java.util.Iterator;
import java.util.List;
import javax.servlet.ServletContext;
import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;
import javax.servlet.jsp.PageContext;
import org.apache.commons.fileupload.DiskFileUpload;
import org.apache.commons.fileupload.FileItem;
import org.apache.commons.fileupload.disk.DiskFileItemFactory;
import org.apache.commons.fileupload.servlet.ServletFileUpload;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.mapred.JobConf;
import com.model.HdfsDAO;
/**
* Servlet implementation class UploadServlet
*/
public class UploadServlet extends HttpServlet {
/**
* @see HttpServlet#doGet(HttpServletRequest request, HttpServletResponse response)
*/
protected void doGet(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
this.doPost(request, response);
}
/**
* @see HttpServlet#doPost(HttpServletRequest request, HttpServletResponse response)
*/
protected void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
request.setCharacterEncoding("UTF-8");
File file ;
int maxFileSize = 50 * 1024 *1024; //50M
int maxMemSize = 50 * 1024 *1024; //50M
ServletContext context = getServletContext();
String filePath = context.getInitParameter("file-upload");
System.out.println("source file path:"+filePath+"");
// 验证上传内容了类型
String contentType = request.getContentType();
if ((contentType.indexOf("multipart/form-data") >= 0)) {
DiskFileItemFactory factory = new DiskFileItemFactory();
// 设置内存中存储文件的最大值
factory.setSizeThreshold(maxMemSize);
// 本地存储的数据大于 maxMemSize.
factory.setRepository(new File("c:\\temp"));
// 创建一个新的文件上传处理程序
ServletFileUpload upload = new ServletFileUpload(factory);
// 设置最大上传的文件大小
upload.setSizeMax( maxFileSize );
try{
// 解析获取的文件
List fileItems = upload.parseRequest(request);
// 处理上传的文件
Iterator i = fileItems.iterator();
System.out.println("begin to upload file to tomcat server</p>");
while ( i.hasNext () )
{
FileItem fi = (FileItem)i.next();
if ( !fi.isFormField () )
{
// 获取上传文件的参数
String fieldName = fi.getFieldName();
String fileName = fi.getName();
String fn = fileName.substring( fileName.lastIndexOf("\\")+1);
System.out.println("<br>"+fn+"<br>");
boolean isInMemory = fi.isInMemory();
long sizeInBytes = fi.getSize();
// 写入文件
if( fileName.lastIndexOf("\\") >= 0 ){
file = new File( filePath ,
fileName.substring( fileName.lastIndexOf("\\"))) ;
//out.println("filename"+fileName.substring( fileName.lastIndexOf("\\"))+"||||||");
}else{
file = new File( filePath ,
fileName.substring(fileName.lastIndexOf("\\")+1)) ;
}
fi.write( file ) ;
System.out.println("upload file to tomcat server success!");
<span style="color:#ff0000;"> System.out.println("begin to upload file to hadoop hdfs</p>");
//将tomcat上的文件上传到hadoop上
JobConf conf = HdfsDAO.config();
HdfsDAO hdfs = new HdfsDAO(conf);
hdfs.copyFile(filePath+"\\"+fn, "/wgc/"+fn);
System.out.println("upload file to hadoop hdfs success!");</span>
request.getRequestDispatcher("index.jsp").forward(request, response);
}
}
}catch(Exception ex) {
System.out.println(ex);
}
}else{
System.out.println("<p>No file uploaded</p>");
}
}
}
在上传前，hdfs下的wgc文件夹列表如下：
接下来我们上传：（4）通过调用hadoop的java api实现本地文件上传到hadoop文件系统上.docx
在tomcat服务器上，我们可以看到刚刚上传的文件：
打开http://hadoop:50070/查看文件系统，可以看到新上传的文件：
那么，到此，一个简陋的网盘上传功能就实现了，接下来我们就对这个简陋的网盘做一些美工，让它看起来更漂亮些。
参考资料：
http://blog.fens.me/hadoop-hdfs-api/
（6）基于hadoop的简单网盘应用实现2,布布扣,bubuko.com
原文：http://blog.csdn.net/wen294299195/article/details/38660451
