def generate_from_dict()

in src/datasets/features/features.py [0:0]

• 21 lines of code
• 16 McCabe index (conditional complexity)

def generate_from_dict(obj: Any):
    """Regenerate the nested feature object from a deserialized dict.
    We use the '_type' fields to get the dataclass name to load.

    generate_from_dict is the recursive helper for Features.from_dict, and allows for a convenient constructor syntax
    to define features from deserialized JSON dictionaries. This function is used in particular when deserializing
    a :class:`DatasetInfo` that was dumped to a JSON object. This acts as an analogue to
    :meth:`Features.from_arrow_schema` and handles the recursive field-by-field instantiation, but doesn't require any
    mapping to/from pyarrow, except for the fact that it takes advantage of the mapping of pyarrow primitive dtypes
    that :class:`Value` automatically performs.
    """
    # Nested structures: we allow dict, list/tuples, sequences
    if isinstance(obj, list):
        return [generate_from_dict(value) for value in obj]
    # Otherwise we have a dict or a dataclass
    if "_type" not in obj or isinstance(obj["_type"], dict):
        return {key: generate_from_dict(value) for key, value in obj.items()}
    obj = dict(obj)
    _type = obj.pop("_type")
    class_type = _FEATURE_TYPES.get(_type, None) or globals().get(_type, None)

    if class_type is None:
        raise ValueError(f"Feature type '{_type}' not found. Available feature types: {list(_FEATURE_TYPES.keys())}")

    if class_type == LargeList:
        feature = obj.pop("feature")
        return LargeList(generate_from_dict(feature), **obj)
    if class_type == List:
        feature = obj.pop("feature")
        return List(generate_from_dict(feature), **obj)
    if class_type == Sequence:  # backward compatibility, this translates to a List or a dict
        feature = obj.pop("feature")
        return Sequence(feature=generate_from_dict(feature), **obj)

    field_names = {f.name for f in fields(class_type)}
    return class_type(**{k: v for k, v in obj.items() if k in field_names})