src/datasets/packaged_modules/arrow/arrow.py [28:45]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        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]
            # Use `dl_manager.iter_files` to skip hidden files in an extracted archive
            files = [dl_manager.iter_files(file) for file in files]
            # Infer features if they are stored in the arrow schema
            if self.info.features is None:
                for file in itertools.chain.from_iterable(files):
                    with open(file, "rb") as f:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/datasets/packaged_modules/parquet/parquet.py [42:59]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        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]
            # Use `dl_manager.iter_files` to skip hidden files in an extracted archive
            files = [dl_manager.iter_files(file) for file in files]
            # Infer features if they are stored in the arrow schema
            if self.info.features is None:
                for file in itertools.chain.from_iterable(files):
                    with open(file, "rb") as f:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -