1.Copy a file from the local file system to HDFS
The srcFile variable needs to contain the full name (path + file name) of the file in the local file system.
The dstFile variable needs to contain the desired full name of the file in the Hadoop file system.
| Configuration config = new Configuration();
FileSystem hdfs = FileSystem.get(config);
Path srcPath = new Path(srcFile);
Path dstPath = new Path(dstFile);
hdfs.copyFromLocalFile(srcPath, dstPath);
|
2.Create HDFS file
The fileName variable contains the file name and path in the Hadoop file system.
The content of the file is the buff variable which is an array of bytes.
| //byte[] buff - The content of the file
Configuration config = new Configuration();
FileSystem hdfs = FileSystem.get(config);
Path path = new Path(fileName);
FSDataOutputStream outputStream = hdfs.create(path);
outputStream.write(buff, 0, buff.length);
|
3.Rename HDFS file
In order to rename a file in Hadoop file system, we need the full name (path + name) of
the file we want to rename. The rename method returns true if the file was renamed, otherwise false.
| Configuration config = new Configuration();
FileSystem hdfs = FileSystem.get(config);
Path fromPath = new Path(fromFileName);
Path toPath = new Path(toFileName);
boolean isRenamed = hdfs.rename(fromPath, toPath);
|
4.Delete HDFS file
In order to delete a file in Hadoop file system, we need the full name (path + name)
of the file we want to delete. The delete method returns true if the file was deleted, otherwise false.
| Configuration config = new Configuration();
FileSystem hdfs = FileSystem.get(config);
Path path = new Path(fileName);
boolean isDeleted = hdfs.delete(path, false);
Recursive delete:
Configuration config = new Configuration();
FileSystem hdfs = FileSystem.get(config);
Path path = new Path(fileName);
boolean isDeleted = hdfs.delete(path, true);
|
5.Get HDFS file last modification time
In order to get the last modification time of a file in Hadoop file system,
we need the full name (path + name) of the file.
| Configuration config = new Configuration();
FileSystem hdfs = FileSystem.get(config);
Path path = new Path(fileName);
FileStatus fileStatus = hdfs.getFileStatus(path);
long modificationTime = fileStatus.getModificationTime
|
6.Check if a file exists in HDFS
In order to check the existance of a file in Hadoop file system,
we need the full name (path + name) of the file we want to check.
The exists methods returns true if the file exists, otherwise false.
| Configuration config = new Configuration();
FileSystem hdfs = FileSystem.get(config);
Path path = new Path(fileName);
boolean isExists = hdfs.exists(path);
|
7.Get the locations of a file in the HDFS cluster
A file can exist on more than one node in the Hadoop file system cluster for two reasons:
Based on the HDFS cluster configuration, Hadoop saves parts of files on different nodes in the cluster.
Based on the HDFS cluster configuration, Hadoop saves more than one copy of each file on different nodes for redundancy (The default is three).
| Configuration config = new Configuration();
FileSystem hdfs = FileSystem.get(config);
Path path = new Path(fileName);
FileStatus fileStatus = hdfs.getFileStatus(path);
BlockLocation[] blkLocations = hdfs.getFileBlockLocations(path, 0, fileStatus.getLen());
BlockLocation[] blkLocations = hdfs.getFileBlockLocations(fileStatus, 0, fileStatus.getLen());
//这个地方，作者写错了，需要把path改为fileStatus
int blkCount = blkLocations.length;
for (int i=0; i < blkCount; i++) {
String[] hosts = blkLocations[i].getHosts();
// Do something with the block hosts
}
|
8. Get a list of all the nodes host names in the HDFS cluster
his method casts the FileSystem Object to a DistributedFileSystem Object.
This method will work only when Hadoop is configured as a cluster.
Running Hadoop on the local machine only, in a non cluster configuration will
cause this method to throw an Exception.
| Configuration config = new Configuration();
FileSystem fs = FileSystem.get(config);
DistributedFileSystem hdfs = (DistributedFileSystem) fs;
DatanodeInfo[] dataNodeStats = hdfs.getDataNodeStats();
String[] names = new String[dataNodeStats.length];
for (int i = 0; i < dataNodeStats.length; i++) {
names[i] = dataNodeStats[i].getHostName();
}
|
程序实例
| /*
*
* 演示操作HDFS的java接口
*
* */
import org.apache.hadoop.conf.*;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.hdfs.*;
import org.apache.hadoop.hdfs.protocol.*;
import java.util.Date;
public class DFSOperater {
/**
* @param args
*/
public static void main(String[] args) {
Configuration conf = new Configuration();
try {
// Get a list of all the nodes host names in the HDFS cluster
FileSystem fs = FileSystem.get(conf);
DistributedFileSystem hdfs = (DistributedFileSystem)fs;
DatanodeInfo[] dataNodeStats = hdfs.getDataNodeStats();
String[] names = new String[dataNodeStats.length];
System.out.println("list of all the nodes in HDFS cluster:"); //print info
for(int i=0; i < dataNodeStats.length; i++){
names[i] = dataNodeStats[i].getHostName();
System.out.println(names[i]); //print info
}
Path f = new Path("/user/cluster/dfs.txt");
//check if a file exists in HDFS
boolean isExists = fs.exists(f);
System.out.println("The file exists? [" + isExists + "]");
//if the file exist, delete it
if(isExists){
boolean isDeleted = hdfs.delete(f, false);//fase : not recursive
if(isDeleted)System.out.println("now delete " + f.getName());
}
//create and write
System.out.println("create and write [" + f.getName() + "] to hdfs:");
FSDataOutputStream os = fs.create(f, true, 0);
for(int i=0; i<10; i++){
os.writeChars("test hdfs ");
}
os.writeChars("/n");
os.close();
//get the locations of a file in HDFS
System.out.println("locations of file in HDFS:");
FileStatus filestatus = fs.getFileStatus(f);
BlockLocation[] blkLocations = fs.getFileBlockLocations(filestatus, 0,filestatus.getLen());
int blkCount = blkLocations.length;
for(int i=0; i < blkCount; i++){
String[] hosts = blkLocations[i].getHosts();
//Do sth with the block hosts
System.out.println(hosts);
}
//get HDFS file last modification time
long modificationTime = filestatus.getModificationTime(); // measured in milliseconds since the epoch
Date d = new Date(modificationTime);
System.out.println(d);
//reading from HDFS
System.out.println("read [" + f.getName() + "] from hdfs:");
FSDataInputStream dis = fs.open(f);
System.out.println(dis.readUTF());
dis.close();
} catch (Exception e) {
// TODO: handle exception
e.printStackTrace();
}
}
}
|
