Support WebHDFS (2/2): Python binding

python/kvikio/kvikio/_lib/remote_handle.pyx

@@ -53,6 +53,9 @@ cdef extern from "<kvikio/remote_handle.hpp>" nogil:
             size_t file_offset
         ) except +
 
+cdef extern from "<kvikio/hdfs.hpp>" nogil:
+    cdef cppclass cpp_WebHdfsEndpoint "kvikio::WebHdfsEndpoint"(cpp_RemoteEndpoint):
+        cpp_WebHdfsEndpoint(string url) except +
 
 cdef string _to_string(str s):
     """Convert Python object to a C++ string (if None, return the empty string)"""
@@ -157,6 +160,18 @@ cdef class RemoteFile:
             nbytes
         )
 
+    @staticmethod
+    def open_webhdfs(
+        url: str,
+        nbytes: Optional[int],
+    ):
+        return RemoteFile._from_endpoint(
+            cast_to_remote_endpoint(
+                make_unique[cpp_WebHdfsEndpoint](_to_string(url))
+            ),
+            nbytes
+        )
+
     def __str__(self) -> str:
         cdef string ep_str = deref(self._handle).endpoint().str()
         return f'<{self.__class__.__name__} "{ep_str.decode()}">'

python/kvikio/kvikio/remote_file.py

@@ -164,6 +164,27 @@ def open_s3_presigned_url(
             )
         )
 
+    @classmethod
+    def open_webhdfs(
+        cls,
+        url: str,
+        nbytes: Optional[int] = None,
+    ) -> RemoteFile:
+        """Open a file on Apache Hadoop Distributed File System (HDFS) using WebHDFS.
+
+        If KvikIO is run within a Docker, the argument ``--network host`` needs to be
+        passed to the ``docker run`` command.
+
+        Parameters
+        ----------
+        url
+            URL to the remote file.
+        nbytes
+            The size of the file. If None, KvikIO will ask the server for the file
+            size.
+        """
+        return RemoteFile(_get_remote_module().RemoteFile.open_webhdfs(url, nbytes))
+
     def close(self) -> None:
         """Close the file"""
         pass