def _copy_single_object(
self,
gcs_hook: GCSHook,
sftp_hook: SFTPHook,
source_object: str,
destination_path: str,
) -> None:
"""
Helper function to copy single object.
"""
self.log.info(
"Executing copy of gs://%s/%s to %s",
self.source_bucket,
source_object,
destination_path,
)
dir_path = os.path.dirname(destination_path)
sftp_hook.create_directory(dir_path)
with NamedTemporaryFile("w") as tmp:
gcs_hook.download(
bucket_name=self.source_bucket,
object_name=source_object,
filename=tmp.name,
)
sftp_hook.store_file(destination_path, tmp.name)
if self.move_object:
self.log.info("Executing delete of gs://%s/%s", self.source_bucket,
source_object)
gcs_hook.delete(self.source_bucket, source_object)
def execute(self, context):
hook = GCSHook(google_cloud_storage_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
if self.objects:
objects = self.objects
else:
objects = hook.list(bucket_name=self.bucket_name,
prefix=self.prefix)
self.log.info("Deleting %s objects from %s", len(objects),
self.bucket_name)
for object_name in objects:
hook.delete(bucket_name=self.bucket_name, object_name=object_name)
class GCSToGoogleDriveOperator(BaseOperator):
"""
Copies objects from a Google Cloud Storage service service to Google Drive service, with renaming
if requested.
Using this operator requires the following OAuth 2.0 scope:
.. code-block:: none
https://www.googleapis.com/auth/drive
:param source_bucket: The source Google Cloud Storage bucket where the object is. (templated)
:type source_bucket: str
:param source_object: The source name of the object to copy in the Google cloud
storage bucket. (templated)
You can use only one wildcard for objects (filenames) within your bucket. The wildcard can appear
inside the object name or at the end of the object name. Appending a wildcard to the bucket name
is unsupported.
:type source_object: str
:param destination_object: The destination name of the object in the destination Google Drive
service. (templated)
If a wildcard is supplied in the source_object argument, this is the prefix that will be prepended
to the final destination objects' paths.
Note that the source path's part before the wildcard will be removed;
if it needs to be retained it should be appended to destination_object.
For example, with prefix ``foo/*`` and destination_object ``blah/``, the file ``foo/baz`` will be
copied to ``blah/baz``; to retain the prefix write the destination_object as e.g. ``blah/foo``, in
which case the copied file will be named ``blah/foo/baz``.
:type destination_object: str
:param move_object: When move object is True, the object is moved instead of copied to the new location.
This is the equivalent of a mv command as opposed to a cp command.
:type move_object: bool
:param gcp_conn_id: (Optional) The connection ID used to connect to Google Cloud Platform.
:type gcp_conn_id: str
:param delegate_to: The account to impersonate, if any.
For this to work, the service account making the request must have domain-wide delegation enabled.
:type delegate_to: str
"""
template_fields = ("source_bucket", "source_object", "destination_object")
ui_color = "#f0eee4"
@apply_defaults
def __init__(self,
source_bucket: str,
source_object: str,
destination_object: Optional[str] = None,
move_object: bool = False,
gcp_conn_id: str = "google_cloud_default",
delegate_to: Optional[str] = None,
*args,
**kwargs):
super().__init__(*args, **kwargs)
self.source_bucket = source_bucket
self.source_object = source_object
self.destination_object = destination_object
self.move_object = move_object
self.gcp_conn_id = gcp_conn_id
self.delegate_to = delegate_to
self.gcs_hook = None # type: Optional[GCSHook]
self.gdrive_hook = None # type: Optional[GoogleDriveHook]
def execute(self, context):
self.gcs_hook = GCSHook(google_cloud_storage_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
self.gdrive_hook = GoogleDriveHook(gcp_conn_id=self.gcp_conn_id,
delegate_to=self.delegate_to)
if WILDCARD in self.source_object:
total_wildcards = self.source_object.count(WILDCARD)
if total_wildcards > 1:
error_msg = (
"Only one wildcard '*' is allowed in source_object parameter. "
"Found {} in {}.".format(total_wildcards,
self.source_object))
raise AirflowException(error_msg)
prefix, delimiter = self.source_object.split(WILDCARD, 1)
objects = self.gcs_hook.list(self.source_bucket,
prefix=prefix,
delimiter=delimiter)
for source_object in objects:
if self.destination_object is None:
destination_object = source_object
else:
destination_object = source_object.replace(
prefix, self.destination_object, 1)
self._copy_single_object(source_object=source_object,
destination_object=destination_object)
else:
self._copy_single_object(
source_object=self.source_object,
destination_object=self.destination_object)
def _copy_single_object(self, source_object, destination_object):
self.log.info(
"Executing copy of gs://%s/%s to gdrive://%s",
self.source_bucket,
source_object,
destination_object,
)
with tempfile.NamedTemporaryFile() as file:
filename = file.name
self.gcs_hook.download(bucket_name=self.source_bucket,
object_name=source_object,
filename=filename)
self.gdrive_hook.upload_file(local_location=filename,
remote_location=destination_object)
if self.move_object:
self.gcs_hook.delete(self.source_bucket, source_object)