"""``YAMLDataset`` loads/saves data from/to a YAML file using an underlying
filesystem (e.g.: local, S3, GCS). It uses PyYAML to handle the YAML file.
"""
from __future__ import annotations
from copy import deepcopy
from pathlib import PurePosixPath
from typing import Any
import fsspec
import yaml
from kedro.io.core import (
AbstractVersionedDataset,
DatasetError,
Version,
get_filepath_str,
get_protocol_and_path,
)
[docs]
class YAMLDataset(AbstractVersionedDataset[dict, dict]):
"""``YAMLDataset`` loads/saves data from/to a YAML file using an underlying
filesystem (e.g.: local, S3, GCS). It uses PyYAML to handle the YAML file.
Example usage for the
`YAML API <https://kedro.readthedocs.io/en/stable/data/\
data_catalog_yaml_examples.html>`_:
.. code-block:: yaml
cars:
type: yaml.YAMLDataset
filepath: cars.yaml
Example usage for the
`Python API <https://kedro.readthedocs.io/en/stable/data/\
advanced_data_catalog_usage.html>`_:
.. code-block:: pycon
>>> from kedro_datasets.yaml import YAMLDataset
>>>
>>> data = {"col1": [1, 2], "col2": [4, 5], "col3": [5, 6]}
>>>
>>> dataset = YAMLDataset(filepath=tmp_path / "test.yaml")
>>> dataset.save(data)
>>> reloaded = dataset.load()
>>> assert data == reloaded
"""
DEFAULT_SAVE_ARGS: dict[str, Any] = {"default_flow_style": False}
[docs]
def __init__( # noqa: PLR0913
self,
*,
filepath: str,
save_args: dict[str, Any] | None = None,
version: Version | None = None,
credentials: dict[str, Any] | None = None,
fs_args: dict[str, Any] | None = None,
metadata: dict[str, Any] | None = None,
) -> None:
"""Creates a new instance of ``YAMLDataset`` pointing to a concrete YAML file
on a specific filesystem.
Args:
filepath: Filepath in POSIX format to a YAML file prefixed with a protocol like `s3://`.
If prefix is not provided, `file` protocol (local filesystem) will be used.
The prefix should be any protocol supported by ``fsspec``.
Note: `http(s)` doesn't support versioning.
save_args: PyYAML options for saving YAML files (arguments passed
into ```yaml.dump``). Here you can find all available arguments:
https://pyyaml.org/wiki/PyYAMLDocumentation
All defaults are preserved, but "default_flow_style", which is set to False.
version: If specified, should be an instance of
``kedro.io.core.Version``. If its ``load`` attribute is
None, the latest version will be loaded. If its ``save``
attribute is None, save version will be autogenerated.
credentials: Credentials required to get access to the underlying filesystem.
E.g. for ``GCSFileSystem`` it should look like `{"token": None}`.
fs_args: Extra arguments to pass into underlying filesystem class constructor
(e.g. `{"project": "my-project"}` for ``GCSFileSystem``), as well as
to pass to the filesystem's `open` method through nested keys
`open_args_load` and `open_args_save`.
Here you can find all available arguments for `open`:
https://filesystem-spec.readthedocs.io/en/latest/api.html#fsspec.spec.AbstractFileSystem.open
All defaults are preserved, except `mode`, which is set to `r` when loading
and to `w` when saving.
metadata: Any arbitrary metadata.
This is ignored by Kedro, but may be consumed by users or external plugins.
"""
_fs_args = deepcopy(fs_args) or {}
_fs_open_args_load = _fs_args.pop("open_args_load", {})
_fs_open_args_save = _fs_args.pop("open_args_save", {})
_credentials = deepcopy(credentials) or {}
protocol, path = get_protocol_and_path(filepath, version)
if protocol == "file":
_fs_args.setdefault("auto_mkdir", True)
self._protocol = protocol
self._fs = fsspec.filesystem(self._protocol, **_credentials, **_fs_args)
self.metadata = metadata
super().__init__(
filepath=PurePosixPath(path),
version=version,
exists_function=self._fs.exists,
glob_function=self._fs.glob,
)
# Handle default save arguments
self._save_args = deepcopy(self.DEFAULT_SAVE_ARGS)
if save_args is not None:
self._save_args.update(save_args)
_fs_open_args_save.setdefault("mode", "w")
self._fs_open_args_load = _fs_open_args_load
self._fs_open_args_save = _fs_open_args_save
def _describe(self) -> dict[str, Any]:
return {
"filepath": self._filepath,
"protocol": self._protocol,
"save_args": self._save_args,
"version": self._version,
}
def _load(self) -> dict:
load_path = get_filepath_str(self._get_load_path(), self._protocol)
with self._fs.open(load_path, **self._fs_open_args_load) as fs_file:
return yaml.safe_load(fs_file)
def _save(self, data: dict) -> None:
save_path = get_filepath_str(self._get_save_path(), self._protocol)
with self._fs.open(save_path, **self._fs_open_args_save) as fs_file:
yaml.dump(data, fs_file, **self._save_args)
self._invalidate_cache()
def _exists(self) -> bool:
try:
load_path = get_filepath_str(self._get_load_path(), self._protocol)
except DatasetError:
return False
return self._fs.exists(load_path)
def _release(self) -> None:
super()._release()
self._invalidate_cache()
def _invalidate_cache(self) -> None:
"""Invalidate underlying filesystem caches."""
filepath = get_filepath_str(self._filepath, self._protocol)
self._fs.invalidate_cache(filepath)
