Btukfyl

The standard library in 3.7 can recursively convert a dataclass into a dict (example from the docs):

from dataclasses import dataclass, asdict

from typing import List



@dataclass

class Point:

     x: int

     y: int



@dataclass

class C:

     mylist: List[Point]



p = Point(10, 20)

assert asdict(p) == {'x': 10, 'y': 20}



c = C([Point(0, 0), Point(10, 4)])

tmp = {'mylist': [{'x': 0, 'y': 0}, {'x': 10, 'y': 4}]}

assert asdict(c) == tmp

I am looking for a way to turn a dict back into a dataclass when there is nesting. Something like C(**tmp) only works if the fields of the data class are simple types and not themselves dataclasses. I am familiar with jsonpickle, which however comes with a prominent security warning.

Below is the CPython implementation of asdict
– or specifically, the internal recursive helper function _asdict_inner that it uses:

# Source: https://github.com/python/cpython/blob/master/Lib/dataclasses.py



def _asdict_inner(obj, dict_factory):

    if _is_dataclass_instance(obj):

        result = 

        for f in fields(obj):

            value = _asdict_inner(getattr(obj, f.name), dict_factory)

            result.append((f.name, value))

        return dict_factory(result)

    elif isinstance(obj, tuple) and hasattr(obj, '_fields'):

        # [large block of author comments]

        return type(obj)(*[_asdict_inner(v, dict_factory) for v in obj])

    elif isinstance(obj, (list, tuple)):

        # [ditto]

        return type(obj)(_asdict_inner(v, dict_factory) for v in obj)

    elif isinstance(obj, dict):

        return type(obj)((_asdict_inner(k, dict_factory),

                          _asdict_inner(v, dict_factory))

                         for k, v in obj.items())

    else:

        return copy.deepcopy(obj)

asdict simply calls the above with some assertions, and dict_factory=dict by default.

How can this be adapted to create an output dictionary with the required type-tagging, as mentioned in the comments?

1. Adding type information

My attempt involved creating a custom return wrapper inheriting from dict:

class TypeDict(dict):

    def __init__(self, t, *args, **kwargs):

        super(TypeDict, self).__init__(*args, **kwargs)



        if not isinstance(t, type):

            raise TypeError("t must be a type")



        self._type = t



    @property

    def type(self):

        return self._type

Looking at the original code, only the first clause needs to be modified to use this wrapper, as the other clauses only handle containers of dataclass-es:

# only use dict for now; easy to add back later

def _todict_inner(obj):

    if is_dataclass_instance(obj):

        result = 

        for f in fields(obj):

            value = _todict_inner(getattr(obj, f.name))

            result.append((f.name, value))

        return TypeDict(type(obj), result)



    elif isinstance(obj, tuple) and hasattr(obj, '_fields'):

        return type(obj)(*[_todict_inner(v) for v in obj])

    elif isinstance(obj, (list, tuple)):

        return type(obj)(_todict_inner(v) for v in obj)

    elif isinstance(obj, dict):

        return type(obj)((_todict_inner(k), _todict_inner(v))

                         for k, v in obj.items())

    else:

        return copy.deepcopy(obj)

Imports:

from dataclasses import dataclass, fields, is_dataclass



# thanks to Patrick Haugh

from typing import *



# deepcopy 

import copy

Functions used:

# copy of the internal function _is_dataclass_instance

def is_dataclass_instance(obj):

    return is_dataclass(obj) and not is_dataclass(obj.type)



# the adapted version of asdict

def todict(obj):

    if not is_dataclass_instance(obj):

         raise TypeError("todict() should be called on dataclass instances")

    return _todict_inner(obj)

Tests with the example dataclasses:

c = C([Point(0, 0), Point(10, 4)])



print(c)

cd = todict(c)



print(cd)

# {'mylist': [{'x': 0, 'y': 0}, {'x': 10, 'y': 4}]}



print(cd.type)

# <class '__main__.C'>

Results are as expected.

2. Converting back to a dataclass

The recursive routine used by asdict can be re-used for the reverse process, with some relatively minor changes:

def _fromdict_inner(obj):

    # reconstruct the dataclass using the type tag

    if is_dataclass_dict(obj):

        result = {}

        for name, data in obj.items():

            result[name] = _fromdict_inner(data)

        return obj.type(**result)



    # exactly the same as before (without the tuple clause)

    elif isinstance(obj, (list, tuple)):

        return type(obj)(_fromdict_inner(v) for v in obj)

    elif isinstance(obj, dict):

        return type(obj)((_fromdict_inner(k), _fromdict_inner(v))

                         for k, v in obj.items())

    else:

        return copy.deepcopy(obj)

Functions used:

def is_dataclass_dict(obj):

    return isinstance(obj, TypeDict)



def fromdict(obj):

    if not is_dataclass_dict(obj):

        raise TypeError("fromdict() should be called on TypeDict instances")

    return _fromdict_inner(obj)

Test:

c = C([Point(0, 0), Point(10, 4)])

cd = todict(c)

cf = fromdict(cd)



print(c)

# C(mylist=[Point(x=0, y=0), Point(x=10, y=4)])



print(cf)

# C(mylist=[Point(x=0, y=0), Point(x=10, y=4)])

Again as expected.

I'm the author of dacite - the tool that simplifies creation of data classes from dictionaries.

This library has only one function from_dict - this is a quick example of usage:

from dataclasses import dataclass

from dacite import from_dict



@dataclass

class User:

    name: str

    age: int

    is_active: bool



data = {

    'name': 'john',

    'age': 30,

    'is_active': True,

}



user = from_dict(data_class=User, data=data)



assert user == User(name='john', age=30, is_active=True)

Moreover dacite supports following features:

• nested structures


• (basic) types checking


• optional fields (i.e. typing.Optional)


• unions


• collections


• values casting and transformation


• remapping of fields names

... and it's well tested - 100% code coverage!

To install dacite, simply use pip (or pipenv):

$ pip install dacite

You can use mashumaro for creating dataclass object from a dict according to the scheme. Mixin from this library adds convenient from_dict and to_dict methods to dataclasses:

from dataclasses import dataclass

from typing import List

from mashumaro import DataClassDictMixin



@dataclass

class Point(DataClassDictMixin):

     x: int

     y: int



@dataclass

class C(DataClassDictMixin):

     mylist: List[Point]



p = Point(10, 20)

tmp = {'x': 10, 'y': 20}

assert p.to_dict() == tmp

assert Point.from_dict(tmp) == p



c = C([Point(0, 0), Point(10, 4)])

tmp = {'mylist': [{'x': 0, 'y': 0}, {'x': 10, 'y': 4}]}

assert c.to_dict() == tmp

assert C.from_dict(tmp) == c

If your goal is to produce JSON from and to existing, predefined dataclasses, then just write custom encoder and decoder hooks. Do not use dataclasses.asdict() here, instead record in JSON a (safe) reference to the original dataclass.

jsonpickle is not safe because it stores references to arbitrary Python objects and passes in data to their constructors. With such references I can get jsonpickle to reference internal Python data structures and create and execute functions, classes and modules at will. But that doesn't mean you can't handle such references unsafely. Just verify that you only import (not call) and then verify that the object is an actual dataclass type, before you use it.

The framework can be made generic enough but still limited only to JSON-serialisable types plus dataclass-based instances:

import dataclasses

import importlib

import sys



def dataclass_object_dump(ob):

    datacls = type(ob)

    if not dataclasses.is_dataclass(datacls):

        raise TypeError(f"Expected dataclass instance, got '{datacls!r}' object")

    mod = sys.modules.get(datacls.__module__)

    if mod is None or not hasattr(mod, datacls.__qualname__):

        raise ValueError(f"Can't resolve '{datacls!r}' reference")

    ref = f"{datacls.__module__}.{datacls.__qualname__}"

    fields = (f.name for f in dataclasses.fields(ob))

    return {**{f: getattr(ob, f) for f in fields}, '__dataclass__': ref}



def dataclass_object_load(d):

    ref = d.pop('__dataclass__', None)

    if ref is None:

        return d

    try:

        modname, hasdot, qualname = ref.rpartition('.')

        module = importlib.import_module(modname)

        datacls = getattr(module, qualname)

        if not dataclasses.is_dataclass(datacls) or not isinstance(datacls, type):

            raise ValueError

        return datacls(**d)

    except (ModuleNotFoundError, ValueError, AttributeError, TypeError):

        raise ValueError(f"Invalid dataclass reference {ref!r}") from None

This uses JSON-RPC-style class hints to name the dataclass, and on loading this is verified to still be a data class with the same fields. No type checking is done on the values of the fields (as that's a whole different kettle of fish).

Use these as the default and object_hook arguments to json.dump[s]() and json.dump[s]():

>>> print(json.dumps(c, default=dataclass_object_dump, indent=4))

{

    "mylist": [

        {

            "x": 0,

            "y": 0,

            "__dataclass__": "__main__.Point"

        },

        {

            "x": 10,

            "y": 4,

            "__dataclass__": "__main__.Point"

        }

    ],

    "__dataclass__": "__main__.C"

}

>>> json.loads(json.dumps(c, default=dataclass_object_dump), object_hook=dataclass_object_load)

C(mylist=[Point(x=0, y=0), Point(x=10, y=4)])

>>> json.loads(json.dumps(c, default=dataclass_object_dump), object_hook=dataclass_object_load) == c

True

or create instances of the JSONEncoder and JSONDecoder classes with those same hooks.

Instead of using fully qualifying module and class names, you could also use a separate registry to map permissible type names; check against the registry on encoding, and again on decoding to ensure you don't forget to register dataclasses as you develop.