src/datasets/packaged_modules/csv/csv.py [148:168]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def _info(self):
        return datasets.DatasetInfo(features=self.config.features)

    def _split_generators(self, dl_manager):
        """We handle string, list and dicts in datafiles"""
        if not self.config.data_files:
            raise ValueError(f"At least one data file must be specified, but got data_files={self.config.data_files}")
        dl_manager.download_config.extract_on_the_fly = True
        data_files = dl_manager.download_and_extract(self.config.data_files)
        splits = []
        for split_name, files in data_files.items():
            if isinstance(files, str):
                files = [files]
            files = [dl_manager.iter_files(file) for file in files]
            splits.append(datasets.SplitGenerator(name=split_name, gen_kwargs={"files": files}))
        return splits

    def _cast_table(self, pa_table: pa.Table) -> pa.Table:
        if self.config.features is not None:
            schema = self.config.features.arrow_schema
            if all(not require_storage_cast(feature) for feature in self.config.features.values()):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/datasets/packaged_modules/text/text.py [31:55]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def _info(self):
        return datasets.DatasetInfo(features=self.config.features)

    def _split_generators(self, dl_manager):
        """The `data_files` kwarg in load_dataset() can be a str, List[str], Dict[str,str], or Dict[str,List[str]].

        If str or List[str], then the dataset returns only the 'train' split.
        If dict, then keys should be from the `datasets.Split` enum.
        """
        if not self.config.data_files:
            raise ValueError(f"At least one data file must be specified, but got data_files={self.config.data_files}")
        dl_manager.download_config.extract_on_the_fly = True
        data_files = dl_manager.download_and_extract(self.config.data_files)
        splits = []
        for split_name, files in data_files.items():
            if isinstance(files, str):
                files = [files]
            files = [dl_manager.iter_files(file) for file in files]
            splits.append(datasets.SplitGenerator(name=split_name, gen_kwargs={"files": files}))
        return splits

    def _cast_table(self, pa_table: pa.Table) -> pa.Table:
        if self.config.features is not None:
            schema = self.config.features.arrow_schema
            if all(not require_storage_cast(feature) for feature in self.config.features.values()):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -