Python dataclass from a nested dict
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
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.
All it takes is a five-liner:
def dataclass_from_dict(klass, d):
try:
fieldtypes = {f.name:f.type for f in dataclasses.fields(klass)}
return klass(**{f:dataclass_from_dict(fieldtypes[f],d[f]) for f in d})
except:
return d # Not a dataclass field
Sample usage:
from dataclasses import dataclass, asdict
@dataclass
class Point:
x: float
y: float
@dataclass
class Line:
a: Point
b: Point
line = Line(Point(1,2), Point(3,4))
assert line == dataclass_from_dict(Line, asdict(line))
Full code, including to/from json, here at gist: https://gist.github.com/gatopeich/1efd3e1e4269e1e98fae9983bb914f22