Source code for kedro.extras.datasets.text.text_dataset

"""``TextDataSet`` loads/saves data from/to a text file using an underlying
filesystem (e.g.: local, S3, GCS).
"""
from copy import deepcopy
from pathlib import PurePosixPath
from typing import Any, Dict

import fsspec

from kedro.io.core import (
    AbstractVersionedDataSet,
    DataSetError,
    Version,
    get_filepath_str,
    get_protocol_and_path,
)

# NOTE: kedro.extras.datasets will be removed in Kedro 0.19.0.
# Any contribution to datasets should be made in kedro-datasets
# in kedro-plugins (https://github.com/kedro-org/kedro-plugins)


[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 adding a catalog entry with YAML API: .. code-block:: yaml >>> alice_book: >>> type: text.TextDataSet >>> filepath: data/01_raw/alice.txt Example using Python API: :: >>> from kedro.extras.datasets.text import TextDataSet >>> >>> string_to_write = "This will go in a file." >>> >>> data_set = TextDataSet(filepath="test.md") >>> data_set.save(string_to_write) >>> reloaded = data_set.load() >>> assert string_to_write == reloaded """
[docs] def __init__( self, filepath: str, version: Version = None, credentials: Dict[str, Any] = None, fs_args: 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. """ _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) 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 dict( 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)