遍历 HDFS 中所有文件
递归遍历
@Test
public void listFile() throws Exception{
FileSystem fileSystem = FileSystem.get(new URI("hdfs://192.168.52.100:8020"), new Configuration());
FileStatus[] fileStatuses = fileSystem.listStatus(new Path("/"));
for (FileStatus fileStatus : fileStatuses) {
if(fileStatus.isDirectory()){
Path path = fileStatus.getPath();
listAllFiles(fileSystem,path);
}else{
System.out.println("文件路径为"+fileStatus.getPath().toString());
}
}
}
public void listAllFiles(FileSystem fileSystem,Path path) throws Exception{
FileStatus[] fileStatuses = fileSystem.listStatus(path);
for (FileStatus fileStatus : fileStatuses) {
if(fileStatus.isDirectory()){
listAllFiles(fileSystem,fileStatus.getPath());
}else{
Path path1 = fileStatus.getPath();
System.out.println("文件路径为"+path1);
}
}
}
使用 API 遍历
@Test
public void listMyFiles()throws Exception{
//获取fileSystem类
FileSystem fileSystem = FileSystem.get(new URI("hdfs://192.168.52.250:8020"), new Configuration());
//获取RemoteIterator 得到所有的文件或者文件夹,第一个参数指定遍历的路径,第二个参数表示是否
要递归遍历
RemoteIterator<LocatedFileStatus> locatedFileStatusRemoteIterator =
fileSystem.listFiles(new Path("/"), true);
while (locatedFileStatusRemoteIterator.hasNext()){
LocatedFileStatus next = locatedFileStatusRemoteIterator.next();
System.out.println(next.getPath().toString());
}
fileSystem.close();
}