Validating detailed types in python dataclasses

Instead of checking for type equality, you should use isinstance. But you cannot use a parametrized generic type (typing.List[int]) to do so, you must use the “generic” version (typing.List). So you will be able to check for the container type but not the contained types. Parametrized generic types define an __origin__ attribute that you can use for that.

Contrary to Python 3.6, in Python 3.7 most type hints have a useful __origin__ attribute. Compare:

# Python 3.6
>>> import typing
>>> typing.List.__origin__
>>> typing.List[int].__origin__
typing.List

and

# Python 3.7
>>> import typing
>>> typing.List.__origin__
<class 'list'>
>>> typing.List[int].__origin__
<class 'list'>

Python 3.8 introduce even better support with the typing.get_origin() introspection function:

# Python 3.8
>>> import typing
>>> typing.get_origin(typing.List)
<class 'list'>
>>> typing.get_origin(typing.List[int])
<class 'list'>

Notable exceptions being typing.Any, typing.Union and typing.ClassVar… Well, anything that is a typing._SpecialForm does not define __origin__. Fortunately:

>>> isinstance(typing.Union, typing._SpecialForm)
True
>>> isinstance(typing.Union[int, str], typing._SpecialForm)
False
>>> typing.get_origin(typing.Union[int, str])
typing.Union

But parametrized types define an __args__ attribute that store their parameters as a tuple; Python 3.8 introduce the typing.get_args() function to retrieve them:

# Python 3.7
>>> typing.Union[int, str].__args__
(<class 'int'>, <class 'str'>)

# Python 3.8
>>> typing.get_args(typing.Union[int, str])
(<class 'int'>, <class 'str'>)

So we can improve type checking a bit:

for field_name, field_def in self.__dataclass_fields__.items():
    if isinstance(field_def.type, typing._SpecialForm):
        # No check for typing.Any, typing.Union, typing.ClassVar (without parameters)
        continue
    try:
        actual_type = field_def.type.__origin__
    except AttributeError:
        # In case of non-typing types (such as <class 'int'>, for instance)
        actual_type = field_def.type
    # In Python 3.8 one would replace the try/except with
    # actual_type = typing.get_origin(field_def.type) or field_def.type
    if isinstance(actual_type, typing._SpecialForm):
        # case of typing.Union[…] or typing.ClassVar[…]
        actual_type = field_def.type.__args__

    actual_value = getattr(self, field_name)
    if not isinstance(actual_value, actual_type):
        print(f"\t{field_name}: '{type(actual_value)}' instead of '{field_def.type}'")
        ret = False

This is not perfect as it won’t account for typing.ClassVar[typing.Union[int, str]] or typing.Optional[typing.List[int]] for instance, but it should get things started.


Next is the way to apply this check.

Instead of using __post_init__, I would go the decorator route: this could be used on anything with type hints, not only dataclasses:

import inspect
import typing
from contextlib import suppress
from functools import wraps


def enforce_types(callable):
    spec = inspect.getfullargspec(callable)

    def check_types(*args, **kwargs):
        parameters = dict(zip(spec.args, args))
        parameters.update(kwargs)
        for name, value in parameters.items():
            with suppress(KeyError):  # Assume un-annotated parameters can be any type
                type_hint = spec.annotations[name]
                if isinstance(type_hint, typing._SpecialForm):
                    # No check for typing.Any, typing.Union, typing.ClassVar (without parameters)
                    continue
                try:
                    actual_type = type_hint.__origin__
                except AttributeError:
                    # In case of non-typing types (such as <class 'int'>, for instance)
                    actual_type = type_hint
                # In Python 3.8 one would replace the try/except with
                # actual_type = typing.get_origin(type_hint) or type_hint
                if isinstance(actual_type, typing._SpecialForm):
                    # case of typing.Union[…] or typing.ClassVar[…]
                    actual_type = type_hint.__args__

                if not isinstance(value, actual_type):
                    raise TypeError('Unexpected type for \'{}\' (expected {} but found {})'.format(name, type_hint, type(value)))

    def decorate(func):
        @wraps(func)
        def wrapper(*args, **kwargs):
            check_types(*args, **kwargs)
            return func(*args, **kwargs)
        return wrapper

    if inspect.isclass(callable):
        callable.__init__ = decorate(callable.__init__)
        return callable

    return decorate(callable)

Usage being:

@enforce_types
@dataclasses.dataclass
class Point:
    x: float
    y: float

@enforce_types
def foo(bar: typing.Union[int, str]):
    pass

Appart from validating some type hints as suggested in the previous section, this approach still have some drawbacks:

  • type hints using strings (class Foo: def __init__(self: 'Foo'): pass) are not taken into account by inspect.getfullargspec: you may want to use typing.get_type_hints and inspect.signature instead;

  • a default value which is not the appropriate type is not validated:

     @enforce_type
     def foo(bar: int = None):
         pass
    
     foo()
    

    does not raise any TypeError. You may want to use inspect.Signature.bind in conjuction with inspect.BoundArguments.apply_defaults if you want to account for that (and thus forcing you to define def foo(bar: typing.Optional[int] = None));

  • variable number of arguments can’t be validated as you would have to define something like def foo(*args: typing.Sequence, **kwargs: typing.Mapping) and, as said at the beginning, we can only validate containers and not contained objects.


Update

After this answer got some popularity and a library heavily inspired by it got released, the need to lift the shortcomings mentioned above is becoming a reality. So I played a bit more with the typing module and will propose a few findings and a new approach here.

For starter, typing is doing a great job in finding when an argument is optional:

>>> def foo(a: int, b: str, c: typing.List[str] = None):
...   pass
... 
>>> typing.get_type_hints(foo)
{'a': <class 'int'>, 'b': <class 'str'>, 'c': typing.Union[typing.List[str], NoneType]}

This is pretty neat and definitely an improvement over inspect.getfullargspec, so better use that instead as it can also properly handle strings as type hints. But typing.get_type_hints will bail out for other kind of default values:

>>> def foo(a: int, b: str, c: typing.List[str] = 3):
...   pass
... 
>>> typing.get_type_hints(foo)
{'a': <class 'int'>, 'b': <class 'str'>, 'c': typing.List[str]}

So you may still need extra strict checking, even though such cases feels very fishy.

Next is the case of typing hints used as arguments for typing._SpecialForm, such as typing.Optional[typing.List[str]] or typing.Final[typing.Union[typing.Sequence, typing.Mapping]]. Since the __args__ of these typing._SpecialForms is always a tuple, it is possible to recursively find the __origin__ of the hints contained in that tuple. Combined with the above checks, we will then need to filter any typing._SpecialForm left.

Proposed improvements:

import inspect
import typing
from functools import wraps


def _find_type_origin(type_hint):
    if isinstance(type_hint, typing._SpecialForm):
        # case of typing.Any, typing.ClassVar, typing.Final, typing.Literal,
        # typing.NoReturn, typing.Optional, or typing.Union without parameters
        return

    actual_type = typing.get_origin(type_hint) or type_hint  # requires Python 3.8
    if isinstance(actual_type, typing._SpecialForm):
        # case of typing.Union[…] or typing.ClassVar[…] or …
        for origins in map(_find_type_origin, typing.get_args(type_hint)):
            yield from origins
    else:
        yield actual_type


def _check_types(parameters, hints):
    for name, value in parameters.items():
        type_hint = hints.get(name, typing.Any)
        actual_types = tuple(_find_type_origin(type_hint))
        if actual_types and not isinstance(value, actual_types):
            raise TypeError(
                    f"Expected type '{type_hint}' for argument '{name}'"
                    f" but received type '{type(value)}' instead"
            )


def enforce_types(callable):
    def decorate(func):
        hints = typing.get_type_hints(func)
        signature = inspect.signature(func)

        @wraps(func)
        def wrapper(*args, **kwargs):
            parameters = dict(zip(signature.parameters, args))
            parameters.update(kwargs)
            _check_types(parameters, hints)

            return func(*args, **kwargs)
        return wrapper

    if inspect.isclass(callable):
        callable.__init__ = decorate(callable.__init__)
        return callable

    return decorate(callable)


def enforce_strict_types(callable):
    def decorate(func):
        hints = typing.get_type_hints(func)
        signature = inspect.signature(func)

        @wraps(func)
        def wrapper(*args, **kwargs):
            bound = signature.bind(*args, **kwargs)
            bound.apply_defaults()
            parameters = dict(zip(signature.parameters, bound.args))
            parameters.update(bound.kwargs)
            _check_types(parameters, hints)

            return func(*args, **kwargs)
        return wrapper

    if inspect.isclass(callable):
        callable.__init__ = decorate(callable.__init__)
        return callable

    return decorate(callable)

Thanks to @Aran-Fey that helped me improve this answer.

Leave a Comment