Python: code duplication on class attribute definition - python

I'm trying to implement a simple ORM in python. I'm facing a code duplication issue and I do not know how to solve it.
Here is a simplified example of a class in my project:
class Person:
TABLE_NAME = 'person'
FIELDS = [
('name', 'VARCHAR(50)'),
('age', 'INTEGER')
]
# CODE DUPLICATION: the two next lines shoudl be genereated with FIELDS not hard coded...
name: str
age: int
def __init__(self, **kwargs):
self.__dict__ = kwargs
#classmethod
def create_sql_table(cls):
# use TABLE_NAME and FIELDS to create sql table
pass
alice = Person(name='Alice', age=25)
print(alice.name)
If I remove the two lines name: strand age: int I lose auto-completion and I get a mypy error on the print line (Error: Person has no attribute name)
But If I keep it, I have code duplication (I write twice each field name).
Is there a way to avoid the code duplication (by generating this two lines using FIELDS variable for instance) ?
Or another way to implement this class that avoid code duplication (without mypy error and auto-completion loss) ?

You can use descriptors:
from typing import Generic, TypeVar, Any, overload, Union
T = TypeVar('T')
class Column(Generic[T]):
sql_type: str # the field type used for this column
def __init__(self) -> None:
self.name = '' # the name of the column
# this is called when the Person class (not the instance) is created
def __set_name__(self, owner: Any, name: str) -> None:
self.name = name # now contains the name of the attribute in the class
# the overload for the case: Person.name -> Column[str]
#overload
def __get__(self, instance: None, owner: Any) -> 'Column[T]': ...
# the overload for the case: Person().name -> str
#overload
def __get__(self, instance: Any, owner: Any) -> T: ...
# the implementation of attribute access
def __get__(self, instance: Any, owner: Any) -> Union[T, 'Column[T]']:
if instance is None:
return self
# implement your attribute access here
return getattr(instance, f'_{self.name}') # type: ignore
# the implementation for setting attributes
def __set__(self, instance: Any, value: T) -> None:
# maybe check here that the type matches
setattr(instance, f'_{self.name}', value)
Now we can create specializations for each column type:
class Integer(Column[int]):
sql_type = 'INTEGER'
class VarChar(Column[str]):
def __init__(self, size: int) -> None:
self.sql_type = f'VARCHAR({size})'
super().__init__()
And when you define the Person class we can use the column types
class Person:
TABLE_NAME = 'person'
name = VarChar(50)
age = Integer()
def __init__(self, **kwargs: Any) -> None:
for key, value in kwargs.items():
setattr(self, key, value)
#classmethod
def create_sql_table(cls) -> None:
print("CREATE TABLE", cls.TABLE_NAME)
for key, value in vars(cls).items():
if isinstance(value, Column):
print(key, value.sql_type)
Person.create_sql_table()
p = Person(age=10)
print(p.age)
p.age = 20
print(p.age)
This prints:
CREATE TABLE person
name VARCHAR(50)
age INTEGER
10
20
You should probably also create a base Model class that contains the __init__ and the class method of Person
You can also extend the Column class to allow nullable columns and add default values.
Mypy does not complain and can correctly infer the types for Person.name to str and Person.age to int.

Ok, I ended up with that
class Person:
# this is not full, you need to fill other types you use it with the correct relationship
types = {
str: 'VARCHAR(50)',
int: 'INTEGER',
} # you should extract that out if you use it elsewhere
TABLE_NAME = 'person'
# NOTE: the only annotated fields should be these. if you annotate anything else, It will break
name: str
age: int
def __init__(self, **kwargs):
self.__dict__ = kwargs
#property
def FIELDS(cls):
return [(key, cls.types[value]) for key, value in cls.__annotations__.items()]
alice = Person(name='Alice', age=25)
print(alice.FIELDS) # [('name', 'VARCHAR(50)'), ('age', 'INTEGER')]
And
>>> mypy <module>
>>> Success: no issues found in 1 source file

In the class Person try to add data type in constructor

Related

Creating value type that raises exception on reading

How do I create a value type that raises an exception when read?
For example:
from dataclasses import dataclass, field
Missing = ...
#dataclass
class A:
a: int = field(default=None) # <- value can be None
b: int = field(default=Missing) # <- can be Missing until you try to access it
def print(self):
for i in [self.a, self.b]:
print(i) # <- raises ValueError if i is Missing
In Python, it seems there is always a way for anything :-)
It appears you can solve this by a clever use of a descriptor value as a dataclass field, as illustrated below. I would also read more on the section on Validators to understand a little bit more about how descriptors work.
from dataclasses import dataclass
# create `_MissingType` class
_MissingType = type('_MissingType', (), {'__bool__': lambda self: False})
# create a singleton for that class
Missing = _MissingType()
class MissingValidator:
__slots__ = ('default', 'private_name')
# You may or may not want a default value
def __init__(self, default=Missing):
self.default = default
def __set_name__(self, owner, name):
self.private_name = '_' + name
# override __get__() to return a default value if one is not passed in to __init__()
def __get__(self, obj, obj_type=None):
try:
value = getattr(obj, self.private_name)
if value is Missing:
cls_name = obj_type.__qualname__
public_name = self.private_name.lstrip('_')
raise ValueError(f'Missing value for field `{public_name}` in class `{cls_name}`')
return value
except AttributeError:
return self.default
def __set__(self, obj, value):
setattr(obj, self.private_name, value)
#dataclass
class A:
a: int = None # <- value can be None
b: int = MissingValidator() # <- can be Missing until you try to access it
def print(self):
for i in [self.a, self.b]:
print(i) # <- raises ValueError if i is Missing
A(b=3).print()
# None
# 3
A(a=42).print()
# raises:
# ValueError: Missing value for field `b` in class `A`

Python can't infer static type of subclass when using a handler factory

I would like to use a general HandlerFactory class like the one described here (see Solution 2: Metaprogramming).
Let me use an example:
Suppose we have the following classes:
class Person:
name: str
#PersonHandlerFactory.register
class Mark(Person):
name = "Mark"
job = "scientist"
#PersonHandlerFactory.register
class Charles(Person):
name = "Charles"
hobby = "football"
You may have noticed that the subclasses contain a decorator. This decorator is used to register these classes into the following PersonHandlerFactory class, which returns a specific class given the person name:
from typing import Dict, Type
class PersonHandlerFactory:
handlers: Dict[str, Type[Person]] = {}
#classmethod
def register(cls, handler_cls: Type[Person]):
cls.handlers[handler_cls.name] = handler_cls
return handler_cls
#classmethod
def get(cls, name: str):
return cls.handlers[name]
As you can see, I used the type Type[Person], because I want this method to be used for any subclass of Person.
But somehow Python interprets the static type of an instance of any subclass as the class Parent:
mark = Mark() # Static type of 'mark' is 'Person' :S
print(mark.job) # Python can't find the type of 'job'
I don't want to change Type[Person] for Mark | Charles because the class PersonHandlerFactory should not know about the subclasses of Person.
Use a bound TypeVar, this allows the correct subclass to be inferred.
from typing import Dict, Type, TypeVar
class Person:
name: str
T = TypeVar("T", bound=Person)
class PersonHandlerFactory:
handlers: Dict[str, Type[Person]] = {}
#classmethod
def register(cls, handler_cls: Type[T]) -> Type[T]:
cls.handlers[handler_cls.name] = handler_cls
return handler_cls
#classmethod
def get(cls, name: str):
return cls.handlers[name]
#PersonHandlerFactory.register
class Mark(Person):
name = "Mark"
job = "scientist"
mark = Mark() # Static type of 'mark' is 'Mark' :)
The class returned by PersonHandlerFactory.get will however always be inferred as Type[Person]

Python type-checking Protocols and Descriptors

I observe a behavior about typing.Protocol when Descriptors are involved which I do not quite fully understand. Consider the following code:
import typing as t
T = t.TypeVar('T')
class MyDescriptor(t.Generic[T]):
def __set_name__(self, owner, name):
self.name = name
def __set__(self, instance, value: T):
instance.__dict__[self.name] = value
def __get__(self, instance, owner) -> T:
return instance.__dict__[self.name]
class Named(t.Protocol):
first_name: str
class Person:
first_name = MyDescriptor[str]()
age: int
def __init__(self):
self.first_name = 'John'
def greet(obj: Named):
print(f'Hello {obj.first_name}')
person = Person()
greet(person)
Is the class Person implicitly implementing the Named protocol? According to mypy, it isn't:
error: Argument 1 to "greet" has incompatible type "Person"; expected "Named"
note: Following member(s) of "Person" have conflicts:
note: first_name: expected "str", got "MyDescriptor[str]"
I guess that's because mypy quickly concludes that str and MyDescriptor[str] are simply 2 different types. Fair enough.
However, using a plain str for first_name or wrapping it in a descriptor that gets and sets a str is just an implementation detail. Duck-typing here tells me that the way we will use first_name (the interface) won't change.
In other words, Person implements Named.
As a side note, PyCharm's type-checker does not complain in this particular case (though I am not sure if it's by design or by chance).
According to the intended use of typing.Protocol, is my understanding wrong?
I'm struggling to find a reference for it, but I think MyPy struggles a little with some of the finer details of descriptors (you can sort of understand why, there's a fair bit of magic going on there). I think a workaround here would just be to use typing.cast:
import typing as t
T = t.TypeVar('T')
class MyDescriptor(t.Generic[T]):
def __set_name__(self, owner, name: str) -> None:
self.name = name
def __set__(self, instance, value: T) -> None:
instance.__dict__[self.name] = value
def __get__(self, instance, owner) -> T:
name = instance.__dict__[self.name]
return t.cast(T, name)
class Named(t.Protocol):
first_name: str
class Person:
first_name = t.cast(str, MyDescriptor[str]())
age: int
def __init__(self) -> None:
self.first_name = 'John'
def greet(obj: Named) -> None:
print(f'Hello {obj.first_name}')
person = Person()
greet(person)
This passes MyPy.

Class attribute not updating when using property decorators

I am trying to use property decorator to validate python object.
Following is my class
'''Contains all model classes. Each class corresponds to a database table'''
from validation import company_legal_type, max_len
class Company():
'''A class to represent a company and its basic information'''
def __init__(self, ref, name, currency, legal_type, business):
self._ref = int(ref)
self._name = name
self._currency = str(currency) # i.e. The functional currency
self._legal_type = str(legal_type)
self._business = str(business)
def __str__(self):
return f"Company object for '{self._name}'"
# Validate object attributes
#property # Prevents change to ref after company object has been created
def ref(self):
return self._ref
#property # The following two functions permit changes but set validation checks for name
def name(self):
return self._name
#name.setter
def name(self, value):
if type(value) != str:
raise TypeError("Company name must be a string.")
if len(value) > max_len['company_name']:
raise ValueError(f"Company name must not be longer than {str(max_len['company_name'])} characters.")
Following is validation.py
# data length validation
max_len = {
'company_name': 200,
'company_business': 200,
}
And finally here is how I am using the class:
# Import custom modules
from models import Company, Currency
company = Company(23, 'ABC Limited', 'PKR', 'pvt_ltd', 'manufacturing')
company.name = 'ABCD Limited'
print(company.name)
This prints 'ABC Limited' instead of 'ABCD Limited'.
If I break a validation condition like use an integer instead of a string when updating company.name, it correctly results in an error. But if I break it when creating the object, no error is raised.
What am I doing wrong?
The problem is your setter doesn't set anything. It merely raises errors on bad input. So you have to actually set something, or else how do you expect it to modify self._name? So:
#name.setter
def name(self, value):
if type(value) != str:
raise TypeError("Company name must be a string.")
if len(value) > max_len['company_name']:
raise ValueError(f"Company name must not be longer than {str(max_len['company_name'])} characters.")
self._name = value
If I break a validation condition like use an integer instead of a string when updating company.name, it correctly results in an error. But if I break it when creating the object, no error is raised.
Because you don't use the property in __init__. Generally if you have validation property setters, you want to use those in __init__. So your __init__ should be something like:
def __init__(self, ref, name, currency, legal_type, business):
self._ref = int(ref)
self.name = name
self._currency = str(currency) # i.e. The functional currency
self._legal_type = str(legal_type)
self._business = str(business)

Dataclasses and property decorator

I've been reading up on Python 3.7's dataclass as an alternative to namedtuples (what I typically use when having to group data in a structure). I was wondering if dataclass is compatible with the property decorator to define getter and setter functions for the data elements of the dataclass. If so, is this described somewhere? Or are there examples available?
It sure does work:
from dataclasses import dataclass
#dataclass
class Test:
_name: str="schbell"
#property
def name(self) -> str:
return self._name
#name.setter
def name(self, v: str) -> None:
self._name = v
t = Test()
print(t.name) # schbell
t.name = "flirp"
print(t.name) # flirp
print(t) # Test(_name='flirp')
In fact, why should it not? In the end, what you get is just a good old class, derived from type:
print(type(t)) # <class '__main__.Test'>
print(type(Test)) # <class 'type'>
Maybe that's why properties are nowhere mentioned specifically. However, the PEP-557's Abstract mentions the general usability of well-known Python class features:
Because Data Classes use normal class definition syntax, you are free
to use inheritance, metaclasses, docstrings, user-defined methods,
class factories, and other Python class features.
TWO VERSIONS THAT SUPPORT DEFAULT VALUES
Most published approaches don't provide a readable way to set a default value for the property, which is quite an important part of dataclass. Here are two possible ways to do that.
The first way is based on the approach referenced by #JorenV. It defines the default value in _name = field() and utilises the observation that if no initial value is specified, then the setter is passed the property object itself:
from dataclasses import dataclass, field
#dataclass
class Test:
name: str
_name: str = field(init=False, repr=False, default='baz')
#property
def name(self) -> str:
return self._name
#name.setter
def name(self, value: str) -> None:
if type(value) is property:
# initial value not specified, use default
value = Test._name
self._name = value
def main():
obj = Test(name='foo')
print(obj) # displays: Test(name='foo')
obj = Test()
obj.name = 'bar'
print(obj) # displays: Test(name='bar')
obj = Test()
print(obj) # displays: Test(name='baz')
if __name__ == '__main__':
main()
The second way is based on the same approach as #Conchylicultor: bypassing the dataclass machinery by overwriting the field outside the class definition.
Personally I think this way is cleaner and more readable than the first because it follows the normal dataclass idiom to define the default value and requires no 'magic' in the setter.
Even so I'd prefer everything to be self-contained... perhaps some clever person can find a way to incorporate the field update in dataclass.__post_init__() or similar?
from dataclasses import dataclass
#dataclass
class Test:
name: str = 'foo'
#property
def _name(self):
return self._my_str_rev[::-1]
#_name.setter
def _name(self, value):
self._my_str_rev = value[::-1]
# --- has to be called at module level ---
Test.name = Test._name
def main():
obj = Test()
print(obj) # displays: Test(name='foo')
obj = Test()
obj.name = 'baz'
print(obj) # displays: Test(name='baz')
obj = Test(name='bar')
print(obj) # displays: Test(name='bar')
if __name__ == '__main__':
main()
A solution with minimal additional code and no hidden variables is to override the __setattr__ method to do any checks on the field:
#dataclass
class Test:
x: int = 1
def __setattr__(self, prop, val):
if prop == "x":
self._check_x(val)
super().__setattr__(prop, val)
#staticmethod
def _check_x(x):
if x <= 0:
raise ValueError("x must be greater than or equal to zero")
An #property is typically used to store a seemingly public argument (e.g. name) into a private attribute (e.g. _name) through getters and setters, while dataclasses generate the __init__() method for you.
The problem is that this generated __init__() method should interface through the public argument name, while internally setting the private attribute _name.
This is not done automatically by dataclasses.
In order to have the same interface (through name) for setting values and creation of the object, the following strategy can be used (Based on this blogpost, which also provides more explanation):
from dataclasses import dataclass, field
#dataclass
class Test:
name: str
_name: str = field(init=False, repr=False)
#property
def name(self) -> str:
return self._name
#name.setter
def name(self, name: str) -> None:
self._name = name
This can now be used as one would expect from a dataclass with a data member name:
my_test = Test(name='foo')
my_test.name = 'bar'
my_test.name('foobar')
print(my_test.name)
The above implementation does the following things:
The name class member will be used as the public interface, but it actually does not really store anything
The _name class member stores the actual content. The assignment with field(init=False, repr=False) makes sure that the #dataclass decorator ignores it when constructing the __init__() and __repr__() methods.
The getter/setter for name actually returns/sets the content of _name
The initializer generated through the #dataclass will use the setter that we just defined. It will not initialize _name explicitly, because we told it not to do so.
Currently, the best way I found was to overwrite the dataclass fields by property in a separate child class.
from dataclasses import dataclass, field
#dataclass
class _A:
x: int = 0
class A(_A):
#property
def x(self) -> int:
return self._x
#x.setter
def x(self, value: int):
self._x = value
The class behave like a regular dataclass. And will correctly define the __repr__ and __init__ field (A(x=4) instead of A(_x=4). The drawback is that the properties cannot be read-only.
This blog post, tries to overwrite the wheels dataclass attribute by the property of the same name.
However, the #property overwrite the default field, which leads to unexpected behavior.
from dataclasses import dataclass, field
#dataclass
class A:
x: int
# same as: `x = property(x) # Overwrite any field() info`
#property
def x(self) -> int:
return self._x
#x.setter
def x(self, value: int):
self._x = value
A() # `A(x=<property object at 0x7f0cf64e5fb0>)` Oups
print(A.__dataclass_fields__) # {'x': Field(name='x',type=<class 'int'>,default=<property object at 0x>,init=True,repr=True}
One way solve this, while avoiding inheritance would be to overwrite the field outside the class definition, after the dataclass metaclass has been called.
#dataclass
class A:
x: int
def x_getter(self):
return self._x
def x_setter(self, value):
self._x = value
A.x = property(x_getter)
A.x = A.x.setter(x_setter)
print(A(x=1))
print(A()) # missing 1 required positional argument: 'x'
It should probably possible to overwrite this automatically by creating some custom metaclass and setting some field(metadata={'setter': _x_setter, 'getter': _x_getter}).
Here's what I did to define the field as a property in __post_init__. This is a total hack, but it works with dataclasses dict-based initialization and even with marshmallow_dataclasses.
from dataclasses import dataclass, field, asdict
#dataclass
class Test:
name: str = "schbell"
_name: str = field(init=False, repr=False)
def __post_init__(self):
# Just so that we don't create the property a second time.
if not isinstance(getattr(Test, "name", False), property):
self._name = self.name
Test.name = property(Test._get_name, Test._set_name)
def _get_name(self):
return self._name
def _set_name(self, val):
self._name = val
if __name__ == "__main__":
t1 = Test()
print(t1)
print(t1.name)
t1.name = "not-schbell"
print(asdict(t1))
t2 = Test("llebhcs")
print(t2)
print(t2.name)
print(asdict(t2))
This would print:
Test(name='schbell')
schbell
{'name': 'not-schbell', '_name': 'not-schbell'}
Test(name='llebhcs')
llebhcs
{'name': 'llebhcs', '_name': 'llebhcs'}
I actually started off from this blog post mentioned somewhere in this SO, but ran into the issue that the dataclass field was being set to type property because the decorator is applied to the class. That is,
#dataclass
class Test:
name: str = field(default='something')
_name: str = field(init=False, repr=False)
#property
def name():
return self._name
#name.setter
def name(self, val):
self._name = val
would make name to be of type property and not str. So, the setter will actually receive property object as the argument instead of the field default.
Some wrapping could be good:
# DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
# Version 2, December 2004
#
# Copyright (C) 2020 Xu Siyuan <inqb#protonmail.com>
#
# Everyone is permitted to copy and distribute verbatim or modified
# copies of this license document, and changing it is allowed as long
# as the name is changed.
#
# DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
# TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
#
# 0. You just DO WHAT THE FUCK YOU WANT TO.
from dataclasses import dataclass, field
MISSING = object()
__all__ = ['property_field', 'property_dataclass']
class property_field:
def __init__(self, fget=None, fset=None, fdel=None, doc=None, **kwargs):
self.field = field(**kwargs)
self.property = property(fget, fset, fdel, doc)
def getter(self, fget):
self.property = self.property.getter(fget)
return self
def setter(self, fset):
self.property = self.property.setter(fset)
return self
def deleter(self, fdel):
self.property = self.property.deleter(fdel)
return self
def property_dataclass(cls=MISSING, / , **kwargs):
if cls is MISSING:
return lambda cls: property_dataclass(cls, **kwargs)
remembers = {}
for k in dir(cls):
if isinstance(getattr(cls, k), property_field):
remembers[k] = getattr(cls, k).property
setattr(cls, k, getattr(cls, k).field)
result = dataclass(**kwargs)(cls)
for k, p in remembers.items():
setattr(result, k, p)
return result
You can use it like this:
#property_dataclass
class B:
x: int = property_field(default_factory=int)
#x.getter
def x(self):
return self._x
#x.setter
def x(self, value):
self._x = value
Here's another way which allows you to have fields without a leading underscore:
from dataclasses import dataclass
#dataclass
class Person:
name: str = property
#name
def name(self) -> str:
return self._name
#name.setter
def name(self, value) -> None:
self._name = value
def __post_init__(self) -> None:
if isinstance(self.name, property):
self.name = 'Default'
The result is:
print(Person().name) # Prints: 'Default'
print(Person('Joel').name) # Prints: 'Joel'
print(repr(Person('Jane'))) # Prints: Person(name='Jane')
This method of using properties in dataclasses also works with asdict and is simpler too. Why? Fields that are typed with ClassVar are ignored by the dataclass, but we can still use them in our properties.
#dataclass
def SomeData:
uid: str
_uid: ClassVar[str]
#property
def uid(self) -> str:
return self._uid
#uid.setter
def uid(self, uid: str) -> None:
self._uid = uid
Ok, so this is my first attempt at having everything self-contained within the class.
I tried a couple different approaches, including having a class decorator right next to #dataclass above the class definition. The issue with the decorator version is that my IDE complains if I decide to use it, and then I lose most of the type hints that the dataclass decorator provides. For example, if I'm trying to pass a field name into the constructor method, it doesn't auto-complete anymore when I add a new class decorator. I suppose that makes sense since the IDE assumes a decorator overwrites the original definition in some important way, however that succeeded in convincing me not to try with the decorator approach.
I ended up adding a metaclass to update the properties associated with dataclass fields to check if the value passed to the setter is a property object as mentioned by a few other solutions, and that seems to be working well enough now. Either of the two approaches below should work for testing (based on #Martin CR's solution)
from dataclasses import dataclass, field
#dataclass
class Test(metaclass=dataclass_property_support):
name: str = property
_name: str = field(default='baz', init=False, repr=False)
#name
def name(self) -> str:
return self._name
#name.setter
def name(self, value: str) -> None:
self._name = value
# --- other properties like these should not be affected ---
#property
def other_prop(self) -> str:
return self._other_prop
#other_prop.setter
def other_prop(self, value):
self._other_prop = value
And here is an approach which (implicitly) maps the property _name that begins with an underscore to the dataclass field name:
#dataclass
class Test(metaclass=dataclass_property_support):
name: str = 'baz'
#property
def _name(self) -> str:
return self._name[::-1]
#_name.setter
def _name(self, value: str):
self._name = value[::-1]
I personally prefer the latter approach, because it looks a little cleaner in my opinion and also the field _name doesn't show up when invoking the dataclass helper function asdict for example.
The below should work for testing purposes with either of the approaches above. The best part is my IDE doesn't complain about any of the code either.
def main():
obj = Test(name='foo')
print(obj) # displays: Test(name='foo')
obj = Test()
obj.name = 'bar'
print(obj) # displays: Test(name='bar')
obj = Test()
print(obj) # displays: Test(name='baz')
if __name__ == '__main__':
main()
Finally, here is the definition for the metaclass dataclass_property_support that now seems to be working:
from dataclasses import MISSING, Field
from functools import wraps
from typing import Dict, Any, get_type_hints
def dataclass_property_support(*args, **kwargs):
"""Adds support for using properties with default values in dataclasses."""
cls = type(*args, **kwargs)
# the args passed in to `type` will be a tuple of (name, bases, dict)
cls_dict: Dict[str, Any] = args[2]
# this accesses `__annotations__`, but should also work with sub-classes
annotations = get_type_hints(cls)
def get_default_from_annotation(field_: str):
"""Get the default value for the type annotated on a field"""
default_type = annotations.get(field_)
try:
return default_type()
except TypeError:
return None
for f, val in cls_dict.items():
if isinstance(val, property):
public_f = f.lstrip('_')
if val.fset is None:
# property is read-only, not settable
continue
if f not in annotations and public_f not in annotations:
# adding this to check if it's a regular property (not
# associated with a dataclass field)
continue
try:
# Get the value of the field named without a leading underscore
default = getattr(cls, public_f)
except AttributeError:
# The public field is probably type-annotated but not defined
# i.e. my_var: str
default = get_default_from_annotation(public_f)
else:
if isinstance(default, property):
# The public field is a property
# Check if the value of underscored field is a dataclass
# Field. If so, we can use the `default` if one is set.
f_val = getattr(cls, '_' + f, None)
if isinstance(f_val, Field) \
and f_val.default is not MISSING:
default = f_val.default
else:
default = get_default_from_annotation(public_f)
def wrapper(fset, initial_val):
"""
Wraps the property `setter` method to check if we are passed
in a property object itself, which will be true when no
initial value is specified (thanks to #Martin CR).
"""
#wraps(fset)
def new_fset(self, value):
if isinstance(value, property):
value = initial_val
fset(self, value)
return new_fset
# Wraps the `setter` for the property
val = val.setter(wrapper(val.fset, default))
# Replace the value of the field without a leading underscore
setattr(cls, public_f, val)
# Delete the property if the field name starts with an underscore
# This is technically not needed, but it supports cases where we
# define an attribute with the same name as the property, i.e.
# #property
# def _wheels(self)
# return self._wheels
if f.startswith('_'):
delattr(cls, f)
return cls
Update (10/2021):
I've managed to encapsulate the above logic - including support for additional edge cases - into the helper library dataclass-wizard, in case this is of interest to anyone. You can find out more about using field properties in the linked documentation as well. Happy coding!
Update (11/2021):
A more performant approach is to use a metaclass to generate a __post_init__() on the class that only runs once to fix field properties so it works with dataclasses. You can check out the gist here which I added. I was able to test it out and when creating multiple class instances, this approach is optimized as it sets everything up properly the first time __post_init__() is run.
Following a very thorough post about data classes and properties that can be found here the TL;DR version which solves some very ugly cases where you have to call MyClass(_my_var=2) and strange __repr__ outputs:
from dataclasses import field, dataclass
#dataclass
class Vehicle:
wheels: int
_wheels: int = field(init=False, repr=False)
def __init__(self, wheels: int):
self._wheels = wheels
#property
def wheels(self) -> int:
return self._wheels
#wheels.setter
def wheels(self, wheels: int):
self._wheels = wheels
Just put the field definition after the property:
#dataclasses.dataclass
class Test:
#property
def driver(self):
print("In driver getter")
return self._driver
#driver.setter
def driver(self, value):
print("In driver setter")
self._driver = value
_driver: typing.Optional[str] =\
dataclasses.field(init=False, default=None, repr=False)
driver: typing.Optional[str] =\
dataclasses.field(init=False, default=driver)
>>> t = Test(1)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
TypeError: __init__() takes 1 positional argument but 2 were given
>>> t = Test()
>>> t._driver is None
True
>>> t.driver is None
In driver getter
True
>>> t.driver = "asdf"
In driver setter
>>> t._driver == "asdf"
True
>>> t
In driver getter
Test(driver='asdf')
I'm surprised this isn't already an answer but I question its wisdom. The only reason for this answer is to include the property in the representation - because the property's backing store (_driver) is already included in comparison tests and equality tests and so on. For example, this is a common idiom:
class Test:
def __init__(self):
self._driver = "default"
#property
def driver(self):
if self._driver == "default":
self._driver = "new"
return self._driver
>>> t = Test()
>>> t
<__main__.Test object at 0x6fffffec11f0>
>>> t._driver
'default'
>>> t.driver
'new'
Here is the dataclass equivalent - except that it adds the property to the representation. In the standard class, the result of (t._driver,t.driver) is ("default","new"). Notice that the result from the dataclass is instead ("new","new"). This is a very simple example but you must recognize that including properties with possible side effects in special methods may not be the best idea.
#dataclasses.dataclass
class Test:
#property
def driver(self):
print("In driver getter")
if self._driver == "default":
self._driver = "new"
return self._driver
_driver: typing.Optional[str] =\
dataclasses.field(init=False, default="default", repr=False)
driver: typing.Optional[str] =\
dataclasses.field(init=False, default=driver)
>>> t = Test()
>>> t
In driver getter
Test(driver='new')
>>> t._driver
'new'
>>> t.driver
In driver getter
'new'
So I would recommend just using:
#dataclasses.dataclass
class Test:
_driver: typing.Optional[str] =\
dataclasses.field(init=False, default="default", repr=False)
#property
def driver(self):
print("In driver getter")
if self._driver == "default":
self._driver = "new"
return self._driver
>>> t
Test()
>>> t._driver
'default'
>>> t.driver
In driver getter
'new'
And you can sidestep the entire issue, avoiding dataclasses for initialization, by simply using hasattr in the property getter.
#dataclasses.dataclass
class Test:
#property
def driver(self):
print("In driver getter")
if not hasattr(self, "_driver"):
self._driver = "new"
return self._driver
Or by using __post_init__:
#dataclasses.dataclass
class Test:
def __post_init__(self):
self._driver = None
#property
def driver(self):
print("In driver getter")
if self._driver is None:
self._driver = "new"
return self._driver
Why do this? Because init=False dataclass defaults are stored only on the class and not the instance.
From the ideas from above, I created a class decorator function resolve_abc_prop that creates a new class containing the getter and setter functions as suggested
by #shmee.
def resolve_abc_prop(cls):
def gen_abstract_properties():
""" search for abstract properties in super classes """
for class_obj in cls.__mro__:
for key, value in class_obj.__dict__.items():
if isinstance(value, property) and value.__isabstractmethod__:
yield key, value
abstract_prop = dict(gen_abstract_properties())
def gen_get_set_properties():
""" for each matching data and abstract property pair,
create a getter and setter method """
for class_obj in cls.__mro__:
if '__dataclass_fields__' in class_obj.__dict__:
for key, value in class_obj.__dict__['__dataclass_fields__'].items():
if key in abstract_prop:
def get_func(self, key=key):
return getattr(self, f'__{key}')
def set_func(self, val, key=key):
return setattr(self, f'__{key}', val)
yield key, property(get_func, set_func)
get_set_properties = dict(gen_get_set_properties())
new_cls = type(
cls.__name__,
cls.__mro__,
{**cls.__dict__, **get_set_properties},
)
return new_cls
Here we define a data class AData and a mixin AOpMixin implementing operations
on the data.
from dataclasses import dataclass, field, replace
from abc import ABC, abstractmethod
class AOpMixin(ABC):
#property
#abstractmethod
def x(self) -> int:
...
def __add__(self, val):
return replace(self, x=self.x + val)
Finally, the decorator resolve_abc_prop is then used to create a new class
with the data from AData and the operations from AOpMixin.
#resolve_abc_prop
#dataclass
class A(AOpMixin):
x: int
A(x=4) + 2 # A(x=6)
EDIT #1: I created a python package that makes it possible to overwrite abstract properties with a dataclass: dataclass-abc
After trying different suggestions from this thread I've come with a little modified version of #Samsara Apathika answer. In short: I removed the "underscore" field variable from the __init__ (so it is available for internal use, but not seen by asdict() or by __dataclass_fields__).
from dataclasses import dataclass, InitVar, field, asdict
#dataclass
class D:
a: float = 10. # Normal attribut with a default value
b: InitVar[float] = 20. # init-only attribute with a default value
c: float = field(init=False) # an attribute that will be defined in __post_init__
def __post_init__(self, b):
if not isinstance(getattr(D, "a", False), property):
print('setting `a` to property')
self._a = self.a
D.a = property(D._get_a, D._set_a)
print('setting `c`')
self.c = self.a + b
self.d = 50.
def _get_a(self):
print('in the getter')
return self._a
def _set_a(self, val):
print('in the setter')
self._a = val
if __name__ == "__main__":
d1 = D()
print(asdict(d1))
print('\n')
d2 = D()
print(asdict(d2))
Gives:
setting `a` to property
setting `c`
in the getter
in the getter
{'a': 10.0, 'c': 30.0}
in the setter
setting `c`
in the getter
in the getter
{'a': 10.0, 'c': 30.0}
I use this idiom to get around the default value during __init__ problem. Returning None from __set__ if a property object is passed in (as is the case during __init__) will keep the initial default value untouched. Defining the default value of the private attribute as that of the previously defined public attribute, ensures the private attribute is available. Type hints are shown with the correct default value, and the comments silence the pylint and mypy warnings:
from dataclasses import dataclass, field
from pprint import pprint
from typing import Any
class dataclass_property(property): # pylint: disable=invalid-name
def __set__(self, __obj: Any, __value: Any) -> None:
if isinstance(__value, self.__class__):
return None
return super().__set__(__obj, __value)
#dataclass
class Vehicle:
wheels: int = 1
_wheels: int = field(default=wheels, init=False, repr=False)
#dataclass_property # type: ignore
def wheels(self) -> int:
print("Get wheels")
return self._wheels
#wheels.setter # type: ignore
def wheels(self, val: int):
print("Set wheels to", val)
self._wheels = val
if __name__ == "__main__":
pprint(Vehicle())
pprint('#####')
pprint(Vehicle(wheels=4))
Output:
└─ $ python wheels.py
Get wheels
Vehicle(wheels=1)
'#####'
Set wheels to 4
Get wheels
Vehicle(wheels=4)
Type hint:
Type hint with correct default value
I went through the previous comments, and although most of them answer thet need to tweak the dataclass itself.
I came up with an approach using a decorator which I think is more concise:
from dataclasses import dataclass
import wrapt
def dataclass_properties(cls, property_starts='_'):
#wrapt.decorator
def wrapper(wrapped, instance, args, kwargs):
properties = [prop for prop in dir(cls) if isinstance(getattr(cls, prop), property)]
new_kwargs = {f"{property_starts}{k}" if k in properties else k: v for k, v in kwargs.items()}
return wrapped(*args, **new_kwargs)
return wrapt.FunctionWrapper(cls, wrapper)()
#dataclass_properties
#dataclass
class State:
_a: int
b: int
_c: int
#property
def a(self):
return self._a
#a.setter
def time(self, value):
self._a = value
if __name__=='__main__':
s = State(b=1,a=2,_c=1)
print(s) # returns: State(_a=2, b=1, _c=1)
print(s.a) # returns: 2
It can filter between properties and those variables that are not properties but start by "_".
It also supports the instantiation providing the property true name. In this case "_a".
if __name__=='__main__':
s = State(b=1,_a=2,_c=1)
print(s) # returns: State(_a=2, b=1, _c=1)
I does not solve the problem of the representation though.
For the use case that brought me to this page, namely to have a dataclass that is immutable, there is a simple option to use #dataclass(frozen=True). This removes all the rather verbose explicit definition of getters and setters. The option eq=True is helpful too.
Credit: a reply from joshorr to this post, linked in a comment to the accepted answer. Also a bit of a classical case of RTFM.

Categories

Resources