本文主要介绍了 HADOOP HDFS JAVA API 对HDFS中的文件操作,如:创建文件,将文件上传到HDFS,从HDFS下载文件到本地,HDFS文件删除等
话不多说,上代码:
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.net.URI;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
/**
* HADOOP HDFS 工具类
*
* @author
* @date 2013-4-13
*/
public class HdsfFileUtil {
/**
* 删除HDFS文件
*
* @param path
* 删除文件路径
* @throws IOException
* IO异常
*/
public static void deleteHdfsFile(String path) throws IOException {
// 加载配置文件
Configuration conf = new Configuration();
conf.addResource("conf/core-site.xml");
// 获取要删除的文件
Path delefPath = new Path(path);
FileSystem hdfs = delefPath.getFileSystem(conf);
boolean isDeleted = false;
// 检查文件是否存在,若存在,递归删除
if (hdfs.exists(delefPath)) {
isDeleted = hdfs.delete(delefPath, true);
// 递归删除
} else {
isDeleted = false;
System.out.println("文件不存在:删除失败");
}
System.out.println("Delete?" + isDeleted);
}
/**
* 将本地文件上传至HDFS
*
* @param local
* 本地路径
* @param hdfs
* hdfs路径
* @throws IOException
* IO异常
*/
public static void uploadToHdfs(String local, String hdfs)
throws IOException {
// 加载配置文件
Configuration config = new Configuration();
config.addResource("conf/core-site.xml");
// 获取HDFS文件系统
FileSystem fs = FileSystem.get(URI.create(hdfs), config);
// 读取本地文件
FileInputStream fis = new FileInputStream(new File(local));
OutputStream os = fs.create(new Path(hdfs));
// 复制
IOUtils.copyBytes(fis, os, 4096, true);
os.close();
fis.close();
System.out.println("拷贝完成...");
}
/**
* 读取HDFS文件
*
* @param fileName
* 源文件路径
* @param dest
* 写入文件路径
* @throws IOException
*/
public static void readFromHdfs(String fileName, String dest)
throws IOException {
// 加载配置文件
Configuration conf = new Configuration();
conf.addResource("conf/core-site.xml");
// 获取HDFS文件系统
FileSystem fs = FileSystem.get(URI.create(fileName), conf);
// 打开文件流
FSDataInputStream hdfsInStream = fs.open(new Path(fileName));
// 写入本地文件系统
OutputStream out = new FileOutputStream(dest);
byte[] ioBuffer = new byte[1024];
// 按行读取
int readLen = hdfsInStream.read(ioBuffer);
while (-1 != readLen) {
out.write(ioBuffer, 0, readLen);
System.out.println(new String(ioBuffer));
readLen = hdfsInStream.read(ioBuffer);
}
out.close();
hdfsInStream.close();
fs.close();
}
/**
* 列出HDFS目录
*
* @param path
* 路径
* @throws IOException
*/
public static void getDirectoryFromHdfs(String path) throws IOException {
// 加载配置文件
Configuration conf = new Configuration();
conf.addResource("conf/core-site.xml");
// 获取HDFS文件系统
FileSystem fs = FileSystem.get(URI.create(path), conf);
// 获取指定路径下的文件
FileStatus fileList[] = fs.listStatus(new Path(path));
int size = fileList.length;
// 循环输出文件
for (int i = 0; i < size; i++) {
System.out.println("name:" + fileList[i].getPath().getName()
+ "\t\tsize:" + fileList[i].getLen());
}
fs.close();
}
}