def __call__(
self,
chunk_size: int = None,
name: str = None,
mime_type: str = None,
metadata: Dict[str, Any] = None,
asset_ids: List[int] = None,
source: str = None,
created_time: Dict[str, Any] = None,
last_updated_time: Dict[str, Any] = None,
source_created_time: Dict[str, Any] = None,
source_modified_time: Dict[str, Any] = None,
uploaded_time: Dict[str, Any] = None,
external_id_prefix: str = None,
uploaded: bool = None,
limit: int = None,
) -> Generator[Union[FileMetadata, FileMetadataList], None, None]:
"""Iterate over files
Fetches file metadata objects as they are iterated over, so you keep a limited number of metadata objects in memory.
Args:
chunk_size (int, optional): Number of files to return in each chunk. Defaults to yielding one event a time.
name (str): Name of the file.
mime_type (str): File type. E.g. text/plain, application/pdf, ..
metadata (Dict[str, Any]): Custom, application specific metadata. String key -> String value
asset_ids (List[int]): Only include files that reference these specific asset IDs.
source (str): The source of this event.
source_created_time (Dict[str, Any]): Filter for files where the sourceCreatedTime field has been set and is within the specified range.
source_modified_time (Dict[str, Any]): Filter for files where the sourceModifiedTime field has been set and is within the specified range.
created_time (Dict[str, Any]): Range between two timestamps
last_updated_time (Dict[str, Any]): Range between two timestamps
uploaded_time (Dict[str, Any]): Range between two timestamps
external_id_prefix (str): External Id provided by client. Should be unique within the project.
uploaded (bool): Whether or not the actual file is uploaded. This field is returned only by the API, it has no effect in a post body.
limit (int, optional): Maximum number of assets to return. Defaults to 25. Set to -1, float("inf") or None
to return all items.
Yields:
Union[FileMetadata, FileMetadataList]: yields FileMetadata one by one if chunk is not specified, else FileMetadataList objects.
"""
filter = FileMetadataFilter(
name,
mime_type,
metadata,
asset_ids,
source,
created_time,
last_updated_time,
uploaded_time,
source_created_time,
source_modified_time,
external_id_prefix,
uploaded,
).dump(camel_case=True)
return self._list_generator(method="POST",
chunk_size=chunk_size,
filter=filter,
limit=limit)
def test_search(self, mock_files_response):
res = FILES_API.search(filter=FileMetadataFilter(
external_id_prefix="abc"))
assert mock_files_response.calls[0].response.json(
)["items"] == res.dump(camel_case=True)
assert {
"search": {
"name": None
},
"filter": {
"externalIdPrefix": "abc"
},
"limit": 100
} == jsgz_load(mock_files_response.calls[0].request.body)
def test_search(self):
res = COGNITE_CLIENT.files.search(
name="big.txt", filter=FileMetadataFilter(created_time={"min": 0}))
assert len(res) > 0
def test_aggregate(self):
res = COGNITE_CLIENT.files.aggregate(filter=FileMetadataFilter(
name="big.txt"))
assert res[0].count > 0
def list(
self,
name: str = None,
mime_type: str = None,
metadata: Dict[str, Any] = None,
asset_ids: List[int] = None,
root_asset_ids: List[int] = None,
root_asset_external_ids: List[str] = None,
source: str = None,
created_time: Dict[str, Any] = None,
last_updated_time: Dict[str, Any] = None,
source_created_time: Dict[str, Any] = None,
source_modified_time: Dict[str, Any] = None,
uploaded_time: Dict[str, Any] = None,
external_id_prefix: str = None,
uploaded: bool = None,
limit: int = 25,
) -> FileMetadataList:
"""List files
Args:
name (str): Name of the file.
mime_type (str): File type. E.g. text/plain, application/pdf, ..
metadata (Dict[str, Any]): Custom, application specific metadata. String key -> String value
asset_ids (List[int]): Only include files that reference these specific asset IDs.
root_asset_ids (List[int]): The IDs of the root assets that the related assets should be children of.
root_asset_external_ids (List[str]): The external IDs of the root assets that the related assets should be children of.
source (str): The source of this event.
created_time (Dict[str, Any]): Range between two timestamps
last_updated_time (Dict[str, Any]): Range between two timestamps
uploaded_time (Dict[str, Any]): Range between two timestamps
source_created_time (Dict[str, Any]): Filter for files where the sourceCreatedTime field has been set and is within the specified range.
source_modified_time (Dict[str, Any]): Filter for files where the sourceModifiedTime field has been set and is within the specified range.
external_id_prefix (str): External Id provided by client. Should be unique within the project.
uploaded (bool): Whether or not the actual file is uploaded. This field is returned only by the API, it has no effect in a post body.
limit (int, optional): Max number of files to return. Defaults to 25. Set to -1, float("inf") or None
to return all items.
Returns:
FileMetadataList: The requested files.
Examples:
List files metadata and filter on external id prefix::
>>> from cognite.client import CogniteClient
>>> c = CogniteClient()
>>> file_list = c.files.list(limit=5, external_id_prefix="prefix")
Iterate over files metadata::
>>> from cognite.client import CogniteClient
>>> c = CogniteClient()
>>> for file_metadata in c.files:
... file_metadata # do something with the file metadata
Iterate over chunks of files metadata to reduce memory load::
>>> from cognite.client import CogniteClient
>>> c = CogniteClient()
>>> for file_list in c.files(chunk_size=2500):
... file_list # do something with the files
"""
if root_asset_ids or root_asset_external_ids:
root_asset_ids = self._process_ids(root_asset_ids,
root_asset_external_ids,
wrap_ids=True)
filter = FileMetadataFilter(
name=name,
mime_type=mime_type,
metadata=metadata,
asset_ids=asset_ids,
root_asset_ids=root_asset_ids,
source=source,
created_time=created_time,
last_updated_time=last_updated_time,
uploaded_time=uploaded_time,
source_created_time=source_created_time,
source_modified_time=source_modified_time,
external_id_prefix=external_id_prefix,
uploaded=uploaded,
).dump(camel_case=True)
return self._list(method="POST", limit=limit, filter=filter)
def __call__(
self,
chunk_size: int = None,
name: str = None,
mime_type: str = None,
metadata: Dict[str, str] = None,
asset_ids: List[int] = None,
asset_external_ids: List[str] = None,
root_asset_ids: List[int] = None,
root_asset_external_ids: List[str] = None,
asset_subtree_ids: List[int] = None,
asset_subtree_external_ids: List[str] = None,
data_set_ids: List[int] = None,
data_set_external_ids: List[str] = None,
source: str = None,
created_time: Union[Dict[str, Any], TimestampRange] = None,
last_updated_time: Union[Dict[str, Any], TimestampRange] = None,
source_created_time: Union[Dict[str, Any], TimestampRange] = None,
source_modified_time: Union[Dict[str, Any], TimestampRange] = None,
uploaded_time: Union[Dict[str, Any], TimestampRange] = None,
external_id_prefix: str = None,
uploaded: bool = None,
limit: int = None,
) -> Generator[Union[FileMetadata, FileMetadataList], None, None]:
"""Iterate over files
Fetches file metadata objects as they are iterated over, so you keep a limited number of metadata objects in memory.
Args:
chunk_size (int, optional): Number of files to return in each chunk. Defaults to yielding one event a time.
name (str): Name of the file.
mime_type (str): File type. E.g. text/plain, application/pdf, ..
metadata (Dict[str, str]): Custom, application specific metadata. String key -> String value
asset_ids (List[int]): Only include files that reference these specific asset IDs.
asset_subtree_external_ids (List[str]): Only include files that reference these specific asset external IDs.
root_asset_ids (List[int]): The IDs of the root assets that the related assets should be children of.
root_asset_external_ids (List[str]): The external IDs of the root assets that the related assets should be children of.
asset_subtree_ids (List[int]): List of asset subtrees ids to filter on.
asset_subtree_external_ids (List[str]): List of asset subtrees external ids to filter on.
data_set_ids (List[int]): Return only files in the specified data sets with these ids.
data_set_external_ids (List[str]): Return only files in the specified data sets with these external ids.
source (str): The source of this event.
source_created_time (Union[Dict[str, Any], TimestampRange]): Filter for files where the sourceCreatedTime field has been set and is within the specified range.
source_modified_time (Union[Dict[str, Any], TimestampRange]): Filter for files where the sourceModifiedTime field has been set and is within the specified range.
created_time (Union[Dict[str, int], TimestampRange]): Range between two timestamps. Possible keys are `min` and `max`, with values given as time stamps in ms.
last_updated_time (Union[Dict[str, int], TimestampRange]): Range between two timestamps. Possible keys are `min` and `max`, with values given as time stamps in ms.
uploaded_time (Union[Dict[str, Any], TimestampRange]): Range between two timestamps
external_id_prefix (str): External Id provided by client. Should be unique within the project.
uploaded (bool): Whether or not the actual file is uploaded. This field is returned only by the API, it has no effect in a post body.
limit (int, optional): Maximum number of files to return. Defaults to return all items.
Yields:
Union[FileMetadata, FileMetadataList]: yields FileMetadata one by one if chunk is not specified, else FileMetadataList objects.
"""
if root_asset_ids or root_asset_external_ids:
root_asset_ids = self._process_ids(root_asset_ids,
root_asset_external_ids,
wrap_ids=True)
if asset_subtree_ids or asset_subtree_external_ids:
asset_subtree_ids = self._process_ids(asset_subtree_ids,
asset_subtree_external_ids,
wrap_ids=True)
if data_set_ids or data_set_external_ids:
data_set_ids = self._process_ids(data_set_ids,
data_set_external_ids,
wrap_ids=True)
filter = FileMetadataFilter(
name=name,
mime_type=mime_type,
metadata=metadata,
asset_ids=asset_ids,
asset_external_ids=asset_external_ids,
root_asset_ids=root_asset_ids,
asset_subtree_ids=asset_subtree_ids,
source=source,
created_time=created_time,
last_updated_time=last_updated_time,
uploaded_time=uploaded_time,
source_created_time=source_created_time,
source_modified_time=source_modified_time,
external_id_prefix=external_id_prefix,
uploaded=uploaded,
data_set_ids=data_set_ids,
).dump(camel_case=True)
return self._list_generator(method="POST",
chunk_size=chunk_size,
filter=filter,
limit=limit)