"""``TextDataset`` loads/saves data from/to a text file using an underlying
filesystem (e.g.: local, S3, GCS).
"""
import warnings
from copy import deepcopy
from pathlib import PurePosixPath
from typing import Any, Dict
import fsspec
from kedro.io.core import Version, get_filepath_str, get_protocol_and_path
from kedro_datasets import KedroDeprecationWarning
from kedro_datasets._io import AbstractVersionedDataset, DatasetError
[docs]class TextDataset(AbstractVersionedDataset[str, str]):
"""``TextDataset`` loads/saves data from/to a text file using an underlying
filesystem (e.g.: local, S3, GCS)
Example usage for the
`YAML API <https://kedro.readthedocs.io/en/stable/data/\
data_catalog_yaml_examples.html>`_:
.. code-block:: yaml
alice_book:
type: text.TextDataset
filepath: data/01_raw/alice.txt
Example usage for the
`Python API <https://kedro.readthedocs.io/en/stable/data/\
advanced_data_catalog_usage.html>`_:
::
>>> from kedro_datasets.text import TextDataset
>>>
>>> string_to_write = "This will go in a file."
>>>
>>> dataset = TextDataset(filepath="test.md")
>>> dataset.save(string_to_write)
>>> reloaded = dataset.load()
>>> assert string_to_write == reloaded
"""
[docs] def __init__( # noqa: PLR0913
self,
filepath: str,
version: Version = None,
credentials: Dict[str, Any] = None,
fs_args: Dict[str, Any] = None,
metadata: Dict[str, Any] = None,
) -> None:
"""Creates a new instance of ``TextDataset`` pointing to a concrete text file
on a specific filesystem.
Args:
filepath: Filepath in POSIX format to a text 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.
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,
)
_fs_open_args_load.setdefault("mode", "r")
_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,
"version": self._version,
}
def _load(self) -> str:
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 fs_file.read()
def _save(self, data: str) -> 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:
fs_file.write(data)
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)
_DEPRECATED_CLASSES = {
"TextDataSet": TextDataset,
}
def __getattr__(name):
if name in _DEPRECATED_CLASSES:
alias = _DEPRECATED_CLASSES[name]
warnings.warn(
f"{repr(name)} has been renamed to {repr(alias.__name__)}, "
f"and the alias will be removed in Kedro-Datasets 2.0.0",
KedroDeprecationWarning,
stacklevel=2,
)
return alias
raise AttributeError(f"module {repr(__name__)} has no attribute {repr(name)}")