1.从Hadoop URL读取数据
类似cat命令
public class URLCat {
static{
URL.setURLStreamHandlerFactory(new FsUrlStreamHandlerFactory());
}
public static void main(String[] args) throws Exception {
InputStream in=null;
try{
in=new URL(args[0]).openStream();
IOUtils.copyBytes(in, System.out, 4096,false);
}finally{
IOUtils.closeStream(in);
}
}
}
2.通过FileSystem API读取数据
public class FileSystemCat {
public static void main(String[] args) throws Exception {
String uri = args[0];
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(uri), conf);
InputStream in = null;
try {
in = fs.open(new Path(uri));
IOUtils.copyBytes(in, System.out, 4096, false);
} finally {
IOUtils.closeStream(in);
}
}
}
3.将本地文件复制到Hadoop文件系统
public class FileCopyWithProgress {
public static void main(String[] args) throws Exception {
String localSrc = args[0];
String dst = args[1];
InputStream in = new BufferedInputStream(new FileInputStream(localSrc));
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(dst), conf);
OutputStream out = fs.create(new Path(dst), new Progressable() {
public void progress() {
System.out.print(".");
}
});
IOUtils.copyBytes(in, out, 4096, true);
}
}
4.显示hadoop文件系统中一组路径的文件信息
public class ListStatus {
public static void main(String[] args) throws Exception {
String uri = args[0];
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(uri), conf);
Path[] paths = new Path[args.length];
for (int i = 0; i < paths.length; i++) {
paths[i] = new Path(args[i]);
}
FileStatus[] status = fs.listStatus(paths);
Path[] listedPaths = FileUtil.stat2Paths(status);
for (Path p : listedPaths) {
System.out.println(p);
}
}
}