读写HDFS的三种方式

1 HttpFS

Authenticator.setDefault(new MyAuthenticator());
URL url = new URL("http://dev.test.com:14000/webhdfs/v1/tmp/test?op=OPEN");
InputStream ins = url.openConnection().getInputStream();
BufferedReader reader = new BufferedReader(new InputStreamReader(ins));
String str;
while((str = reader.readLine()) != null)
    System.out.println(str);

2 Hadoop Java API

public void readFile(String file) throws IOException {
    Configuration conf = new Configuration();
    FileSystem fileSystem = FileSystem.get(conf);
    Path path = new Path(file);
    if (!fileSystem.exists(path)) {
        System.out.println("File " + file + " does not exists");
        return;
    }
    FSDataInputStream in = fileSystem.open(path);
    String filename = file.substring(file.lastIndexOf('/') + 1,
    file.length());
    OutputStream out = new BufferedOutputStream(new FileOutputStream(new File(filename)));
    byte[] b = new byte[1024];
    int numBytes = 0;
    while ((numBytes = in.read(b)) > 0) {
        out.write(b, 0, numBytes);
    }
    in.close();
    out.close();
    fileSystem.close();
} 

3 FileOutputFormat

FileOutputFormat.setOutputPath(job, new Path("file" + key));
context.write(key, result);

参考来源：
Hadoop官方教程