建立连接获取hadoop下的文件信息

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.BlockLocation;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocatedFileStatus;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.RemoteIterator;public class ListFile {public static void main(String [] args) throws IOException, Exception,URISyntaxException{FileSystem file = FileSystem.get(new URI("hdfs://虚拟机IP地址:9000"),new Configuration(),"hadoop");//获取FileSystem对象RemoteIterator<LocatedFileStatus> iterator = file.listFiles(new Path("/"), true);//调用listFiles 获取 /目录下所有的文件信息while(iterator.hasNext()) {//遍历 / 文件夹LocatedFileStatus fileStatus =  iterator.next();//获取文件状态对象Path path = fileStatus.getPath();//获取决定路径String name = path.getName();//获取名字System.out.println(path.toString()+"       "+path.getName());BlockLocation[] locations = fileStatus.getBlockLocations();//获取文件块的信息System.out.println("block"+locations.length);//输出文件块的大小}}
}

编写hadoop连接工具类

package com.clouddisk.cloud.util;import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;public class HDFSUtils {private static Configuration conf ;private static FileSystem fs ;private static String address = "hdfs://192.168.43.60:9000";public FileSystem getConf() throws URISyntaxException, IOException, InterruptedException {conf = new Configuration();fs = FileSystem.get(new URI(address),conf,"hadoop");return fs;}public void release() throws IOException {fs.close();}public String getAddress(){return address;}
}