hdfs path

java 读取本地和hdfs文件夹

abloz 2013-03-14
2013-03-14

周海汉/文 abloz.com 2013.3.14

package my.test;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
/**
 *
 * @author zhouhh
 * @date 2013.3.14
 * merge files to hdfs
 */
public class testhdfspaths {
	public static void main(String[] args) throws IOException {
		String sourceFile = "";
		String targetFile = "";
		if (args.length < 2) {
			sourceFile = "/home/zhouhh/test";
			targetFile = "hdfs://hadoop48:54310/user/zhouhh";
		} else {
			sourceFile = args[0];
			targetFile = args[1];
		}
		Configuration conf = new Configuration();
		FileSystem hdfs = FileSystem.get(conf);
		FileSystem local = FileSystem.getLocal(conf);

		try {
			visitPath(local,sourceFile);
			visitPath(hdfs,targetFile);
		} catch (IOException e) {
			e.printStackTrace();
		}

	}

	public static void visitPath(FileSystem fs,String path) throws IOException
	{
		Path inputDir = new Path(path);
		FileStatus[] inputFiles = fs.listStatus(inputDir);
		if(inputFiles==null)
		{
			throw new IOException(" the path is not correct:" + path);
		}

		System.out.println("----------------path:"+path+"----------------");
		for (int i = 0; i < inputFiles.length; i++) {



			if(inputFiles[i].isDir())
			{
				System.out.println(inputFiles[i].getPath().getName()+" -dir-");
				visitPath(fs,inputFiles[i].getPath().toString());
			}
			else
			{
				System.out.println(inputFiles[i].getPath().getName()+",len:"+inputFiles[i].getLen());
			}

		}

	}

}

输出：

----------------path:/home/zhouhh/test----------------
HelloWorldApp.class,len:432
a.scm,len:99
jar -dir-
----------------path:file:/home/zhouhh/test/jar----------------
Test.jar,len:1040
name.txt,len:389211
jdk-6u38-linux-amd64.rpm,len:58727459
hbase_thrift.tar.gz,len:770987
src -dir-
...
----------------path:hdfs://hadoop48:54310/user/zhouhh----------------
README.txt,len:1399
a,len:0
fsimage,len:9358
gz -dir-
----------------path:hdfs://hadoop48:54310/user/zhouhh/gz----------------
abs.gz,len:309589
mytest.txt,len:20
output -dir-

如非注明转载, 均为原创. 本站遵循知识共享CC协议,转载请注明来源

FEATURED TAGS
css vc6 http automake linux make makefile voip 乱码 awk flash vista vi vim javascript pietty putty ssh posix subversion svn windows 删除 编译 多线程 wxwidgets ie ubuntu 开源 c python bash 备份 性能 scp 汉字 log ruby 中文 bug msn nginx php shell wordpress mqueue android eclipse java mac ios html5 js mysql protobuf apache hadoop install iocp twisted centos mapreduce hbase thrift tutorial hive erlang lucene hdfs sqoop utf8 filter 草原 yarn ganglia 恢复 scrapy django fsimage flume tail flume-ng mining scala go kafka gradle cassandra baas spring postgres maven mybatis mongodb https nodejs 镜像 心理学 机器学习 Keras theano anaconda docker spark akka-http json 群论 区块链 加密 抽象代数 离散对数 同余 欧拉函数 扩展欧几里德算法 ES6 node-inspect debug win10 vscode 挖矿
FRIENDS