My class has a dict, for example:
class MyClass(object):
def __init__(self):
self.data = {'a': 'v1', 'b': 'v2'}
Then I want to use the dict's key with MyClass instance to access the dict, for example:
ob = MyClass()
v = ob.a # Here I expect ob.a returns 'v1'
I know this should be implemented by __getattr__, but I'm new to Python, I don't exactly know how to implement it.
class MyClass(object):
def __init__(self):
self.data = {'a': 'v1', 'b': 'v2'}
def __getattr__(self, attr):
return self.data[attr]
>>> ob = MyClass()
>>> v = ob.a
>>> v
'v1'
Be careful when implementing __setattr__ though, you will need to make a few modifications:
class MyClass(object):
def __init__(self):
# prevents infinite recursion from self.data = {'a': 'v1', 'b': 'v2'}
# as now we have __setattr__, which will call __getattr__ when the line
# self.data[k] tries to access self.data, won't find it in the instance
# dictionary and return self.data[k] will in turn call __getattr__
# for the same reason and so on.... so we manually set data initially
super(MyClass, self).__setattr__('data', {'a': 'v1', 'b': 'v2'})
def __setattr__(self, k, v):
self.data[k] = v
def __getattr__(self, k):
# we don't need a special call to super here because getattr is only
# called when an attribute is NOT found in the instance's dictionary
try:
return self.data[k]
except KeyError:
raise AttributeError
>>> ob = MyClass()
>>> ob.c = 1
>>> ob.c
1
If you don't need to set attributes just use a namedtuple
eg.
>>> from collections import namedtuple
>>> MyClass = namedtuple("MyClass", ["a", "b"])
>>> ob = MyClass(a=1, b=2)
>>> ob.a
1
If you want the default arguments you can just write a wrapper class around it:
class MyClass(namedtuple("MyClass", ["a", "b"])):
def __new__(cls, a="v1", b="v2"):
return super(MyClass, cls).__new__(cls, a, b)
or maybe it looks nicer as a function:
def MyClass(a="v1", b="v2", cls=namedtuple("MyClass", ["a", "b"])):
return cls(a, b)
>>> ob = MyClass()
>>> ob.a
'v1'
Late to the party, but found two really good resources that explain this better (IMHO).
As explained here, you should use self.__dict__ to access fields from within __getattr__, in order to avoid infinite recursion. The example provided is:
def __getattr__(self, attrName):
if not self.__dict__.has_key(attrName):
value = self.fetchAttr(attrName) # computes the value
self.__dict__[attrName] = value
return self.__dict__[attrName]
Note: in the second line (above), a more Pythonic way would be (has_key apparently was even removed in Python 3):
if attrName not in self.__dict__:
The other resource explains that the __getattr__ is invoked only when the attribute is not found in the object, and that hasattr always returns True if there is an implementation for __getattr__. It provides the following example, to demonstrate:
class Test(object):
def __init__(self):
self.a = 'a'
self.b = 'b'
def __getattr__(self, name):
return 123456
t = Test()
print 'object variables: %r' % t.__dict__.keys()
#=> object variables: ['a', 'b']
print t.a
#=> a
print t.b
#=> b
print t.c
#=> 123456
print getattr(t, 'd')
#=> 123456
print hasattr(t, 'x')
#=> True
class A(object):
def __init__(self):
self.data = {'a': 'v1', 'b': 'v2'}
def __getattr__(self, attr):
try:
return self.data[attr]
except Exception:
return "not found"
>>>a = A()
>>>print a.a
v1
>>>print a.c
not found
I like to take this therefore.
I took it from somewhere, but I don't remember where.
class A(dict):
def __init__(self, *a, **k):
super(A, self).__init__(*a, **k)
self.__dict__ = self
This makes the __dict__ of the object the same as itself, so that attribute and item access map to the same dict:
a = A()
a['a'] = 2
a.b = 5
print a.a, a['b'] # prints 2 5
I figured out an extension to #glglgl's answer that handles nested dictionaries and dictionaries insides lists that are in the original dictionary:
class d(dict):
def __init__(self, *a, **k):
super(d, self).__init__(*a, **k)
self.__dict__ = self
for k in self.__dict__:
if isinstance(self.__dict__[k], dict):
self.__dict__[k] = d(self.__dict__[k])
elif isinstance(self.__dict__[k], list):
for i in range(len(self.__dict__[k])):
if isinstance(self.__dict__[k][i], dict):
self.__dict__[k][i] = d(self.__dict__[k][i])
A simple approach to solving your __getattr__()/__setattr__() infinite recursion woes
Implementing one or the other of these magic methods can usually be easy. But when overriding them both, it becomes trickier. This post's examples apply mostly to this more difficult case.
When implementing both these magic methods, it's not uncommon to get stuck figuring out a strategy to get around recursion in the __init__() constructor of classes. This is because variables need to be initialized for the object, but every attempt to read or write those variables go through __get/set/attr__(), which could have more unset variables in them, incurring more futile recursive calls.
Up front, a key point to remember is that __getattr__() only gets called by the runtime if the attribute can't be found on the object already. The trouble is to get attributes defined without tripping these functions recursively.
Another point is __setattr__() will get called no matter what. That's an important distinction between the two functions, which is why implementing both attribute methods can be tricky.
This is one basic pattern that solves the problem.
class AnObjectProxy:
_initialized = False # *Class* variable 'constant'.
def __init__(self):
self._any_var = "Able to access instance vars like usual."
self._initialized = True # *instance* variable.
def __getattr__(self, item):
if self._initialized:
pass # Provide the caller attributes in whatever ways interest you.
else:
try:
return self.__dict__[item] # Transparent access to instance vars.
except KeyError:
raise AttributeError(item)
def __setattr__(self, key, value):
if self._initialized:
pass # Provide caller ways to set attributes in whatever ways.
else:
self.__dict__[key] = value # Transparent access.
While the class is initializing and creating it's instance vars, the code in both attribute functions permits access to the object's attributes via the __dict__ dictionary transparently - your code in __init__() can create and access instance attributes normally. When the attribute methods are called, they only access self.__dict__ which is already defined, thus avoiding recursive calls.
In the case of self._any_var, once it's assigned, __get/set/attr__() won't be called to find it again.
Stripped of extra code, these are the two pieces that are most important.
... def __getattr__(self, item):
... try:
... return self.__dict__[item]
... except KeyError:
... raise AttributeError(item)
...
... def __setattr__(self, key, value):
... self.__dict__[key] = value
Solutions can build around these lines accessing the __dict__ dictionary. To implement an object proxy, two modes were implemented: initialization and post-initialization in the code before this - a more detailed example of the same is below.
There are other examples in answers that may have differing levels of effectiveness in dealing with all aspects of recursion. One effective approach is accessing __dict__ directly in __init__() and other places that need early access to instance vars. This works but can be a little verbose. For instance,
self.__dict__['_any_var'] = "Setting..."
would work in __init__().
My posts tend to get a little long-winded.. after this point is just extra. You should already have the idea with the examples above.
A drawback to some other approaches can be seen with debuggers in IDE's. They can be overzealous in their use of introspection and produce warning and error recovery messages as you're stepping through code. You can see this happening even with solutions that work fine standalone. When I say all aspects of recursion, this is what I'm talking about.
The examples in this post only use a single class variable to support 2-modes of operation, which is very maintainable.
But please NOTE: the proxy class required two modes of operation to set up and proxy for an internal object. You don't have to have two modes of operation.
You could simply incorporate the code to access the __dict__ as in these examples in whatever ways suit you.
If your requirements don't include two modes of operation, you may not need to declare any class variables at all. Just take the basic pattern and customize it.
Here's a closer to real-world (but by no means complete) example of a 2-mode proxy that follows the pattern:
>>> class AnObjectProxy:
... _initialized = False # This class var is important. It is always False.
... # The instances will override this with their own,
... # set to True.
... def __init__(self, obj):
... # Because __getattr__ and __setattr__ access __dict__, we can
... # Initialize instance vars without infinite recursion, and
... # refer to them normally.
... self._obj = obj
... self._foo = 123
... self._bar = 567
...
... # This instance var overrides the class var.
... self._initialized = True
...
... def __setattr__(self, key, value):
... if self._initialized:
... setattr(self._obj, key, value) # Proxying call to wrapped obj.
... else:
... # this block facilitates setting vars in __init__().
... self.__dict__[key] = value
...
... def __getattr__(self, item):
... if self._initialized:
... attr = getattr(self._obj, item) # Proxying.
... return attr
... else:
... try:
... # this block facilitates getting vars in __init__().
... return self.__dict__[item]
... except KeyError:
... raise AttributeError(item)
...
... def __call__(self, *args, **kwargs):
... return self._obj(*args, **kwargs)
...
... def __dir__(self):
... return dir(self._obj) + list(self.__dict__.keys())
The 2-mode proxy only needs a bit of "bootstrapping" to access vars in its own scope at initialization before any of its vars are set. After initialization, the proxy has no reason to create more vars for itself, so it will fare fine by deferring all attribute calls to it's wrapped object.
Any attribute the proxy itself owns will still be accessible to itself and other callers since the magic attribute functions only get called if an attribute can't be found immediately on the object.
Hopefully this approach can be of benefit to anyone who appreciates a direct approach to resolving their __get/set/attr__() __init__() frustrations.
You can initialize your class dictionary through the constructor:
def __init__(self,**data):
And call it as follows:
f = MyClass(**{'a': 'v1', 'b': 'v2'})
All of the instance attributes being accessed (read) in __setattr__, need to be declared using its parent (super) method, only once:
super().__setattr__('NewVarName1', InitialValue)
Or
super().__setattr__('data', dict())
Thereafter, they can be accessed or assigned to in the usual manner:
self.data = data
And instance attributes not being accessed in __setattr__, can be declared in the usual manner:
self.x = 1
The overridden __setattr__ method must now call the parent method inside itself, for new variables to be declared:
super().__setattr__(key,value)
A complete class would look as follows:
class MyClass(object):
def __init__(self, **data):
# The variable self.data is used by method __setattr__
# inside this class, so we will need to declare it
# using the parent __setattr__ method:
super().__setattr__('data', dict())
self.data = data
# These declarations will jump to
# super().__setattr__('data', dict())
# inside method __setattr__ of this class:
self.x = 1
self.y = 2
def __getattr__(self, name):
# This will callback will never be called for instance variables
# that have beed declared before being accessed.
if name in self.data:
# Return a valid dictionary item:
return self.data[name]
else:
# So when an instance variable is being accessed, and
# it has not been declared before, nor is it contained
# in dictionary 'data', an attribute exception needs to
# be raised.
raise AttributeError
def __setattr__(self, key, value):
if key in self.data:
# Assign valid dictionary items here:
self.data[key] = value
else:
# Assign anything else as an instance attribute:
super().__setattr__(key,value)
Test:
f = MyClass(**{'a': 'v1', 'b': 'v2'})
print("f.a = ", f.a)
print("f.b = ", f.b)
print("f.data = ", f.data)
f.a = 'c'
f.d = 'e'
print("f.a = ", f.a)
print("f.b = ", f.b)
print("f.data = ", f.data)
print("f.d = ", f.d)
print("f.x = ", f.x)
print("f.y = ", f.y)
# Should raise attributed Error
print("f.g = ", f.g)
Output:
f.a = v1
f.b = v2
f.data = {'a': 'v1', 'b': 'v2'}
f.a = c
f.b = v2
f.data = {'a': 'c', 'b': 'v2'}
f.d = e
f.x = 1
f.y = 2
Traceback (most recent call last):
File "MyClass.py", line 49, in <module>
print("f.g = ", f.g)
File "MyClass.py", line 25, in __getattr__
raise AttributeError
AttributeError
I think this implement is cooler
class MyClass(object):
def __init__(self):
self.data = {'a': 'v1', 'b': 'v2'}
def __getattr__(self,key):
return self.data.get(key,None)
Although I have never needed this, it just struck me that making an immutable object in Python could be slightly tricky. You can't just override __setattr__, because then you can't even set attributes in the __init__. Subclassing a tuple is a trick that works:
class Immutable(tuple):
def __new__(cls, a, b):
return tuple.__new__(cls, (a, b))
#property
def a(self):
return self[0]
#property
def b(self):
return self[1]
def __str__(self):
return "<Immutable {0}, {1}>".format(self.a, self.b)
def __setattr__(self, *ignored):
raise NotImplementedError
def __delattr__(self, *ignored):
raise NotImplementedError
But then you have access to the a and b variables through self[0] and self[1], which is annoying.
Is this possible in Pure Python? If not, how would I do it with a C extension?
(Answers that work only in Python 3 are acceptable).
Update:
As of Python 3.7, the way to go is to use the #dataclass decorator, see the newly accepted answer.
Yet another solution I just thought of: The simplest way to get the same behaviour as your original code is
Immutable = collections.namedtuple("Immutable", ["a", "b"])
It does not solve the problem that attributes can be accessed via [0] etc., but at least it's considerably shorter and provides the additional advantage of being compatible with pickle and copy.
namedtuple creates a type similar to what I described in this answer, i.e. derived from tuple and using __slots__. It is available in Python 2.6 or above.
The easiest way to do this is using __slots__:
class A(object):
__slots__ = []
Instances of A are immutable now, since you can't set any attributes on them.
If you want the class instances to contain data, you can combine this with deriving from tuple:
from operator import itemgetter
class Point(tuple):
__slots__ = []
def __new__(cls, x, y):
return tuple.__new__(cls, (x, y))
x = property(itemgetter(0))
y = property(itemgetter(1))
p = Point(2, 3)
p.x
# 2
p.y
# 3
Edit: If you want to get rid of indexing either, you can override __getitem__():
class Point(tuple):
__slots__ = []
def __new__(cls, x, y):
return tuple.__new__(cls, (x, y))
#property
def x(self):
return tuple.__getitem__(self, 0)
#property
def y(self):
return tuple.__getitem__(self, 1)
def __getitem__(self, item):
raise TypeError
Note that you can't use operator.itemgetter for the properties in thise case, since this would rely on Point.__getitem__() instead of tuple.__getitem__(). Fuerthermore this won't prevent the use of tuple.__getitem__(p, 0), but I can hardly imagine how this should constitute a problem.
I don't think the "right" way of creating an immutable object is writing a C extension. Python usually relies on library implementers and library users being consenting adults, and instead of really enforcing an interface, the interface should be clearly stated in the documentation. This is why I don't consider the possibility of circumventing an overridden __setattr__() by calling object.__setattr__() a problem. If someone does this, it's on her own risk.
Using a Frozen Dataclass
For Python 3.7+ you can use a Data Class with a frozen=True option, which is a very pythonic and maintainable way to do what you want.
It would look something like that:
from dataclasses import dataclass
#dataclass(frozen=True)
class Immutable:
a: Any
b: Any
As type hinting is required for dataclasses' fields, I have used Any from the typing module.
Reasons NOT to use a Namedtuple
Before Python 3.7 it was frequent to see namedtuples being used as immutable objects. It can be tricky in many ways, one of them is that the __eq__ method between namedtuples does not consider the objects' classes. For example:
from collections import namedtuple
ImmutableTuple = namedtuple("ImmutableTuple", ["a", "b"])
ImmutableTuple2 = namedtuple("ImmutableTuple2", ["a", "c"])
obj1 = ImmutableTuple(a=1, b=2)
obj2 = ImmutableTuple2(a=1, c=2)
obj1 == obj2 # will be True
As you see, even if the types of obj1 and obj2 are different, even if their fields' names are different, obj1 == obj2 still gives True. That's because the __eq__ method used is the tuple's one, which compares only the values of the fields given their positions. That can be a huge source of errors, specially if you are subclassing these classes.
..howto do it "properly" in C..
You could use Cython to create an extension type for Python:
cdef class Immutable:
cdef readonly object a, b
cdef object __weakref__ # enable weak referencing support
def __init__(self, a, b):
self.a, self.b = a, b
It works both Python 2.x and 3.
Tests
# compile on-the-fly
import pyximport; pyximport.install() # $ pip install cython
from immutable import Immutable
o = Immutable(1, 2)
assert o.a == 1, str(o.a)
assert o.b == 2
try: o.a = 3
except AttributeError:
pass
else:
assert 0, 'attribute must be readonly'
try: o[1]
except TypeError:
pass
else:
assert 0, 'indexing must not be supported'
try: o.c = 1
except AttributeError:
pass
else:
assert 0, 'no new attributes are allowed'
o = Immutable('a', [])
assert o.a == 'a'
assert o.b == []
o.b.append(3) # attribute may contain mutable object
assert o.b == [3]
try: o.c
except AttributeError:
pass
else:
assert 0, 'no c attribute'
o = Immutable(b=3,a=1)
assert o.a == 1 and o.b == 3
try: del o.b
except AttributeError:
pass
else:
assert 0, "can't delete attribute"
d = dict(b=3, a=1)
o = Immutable(**d)
assert o.a == d['a'] and o.b == d['b']
o = Immutable(1,b=3)
assert o.a == 1 and o.b == 3
try: object.__setattr__(o, 'a', 1)
except AttributeError:
pass
else:
assert 0, 'attributes are readonly'
try: object.__setattr__(o, 'c', 1)
except AttributeError:
pass
else:
assert 0, 'no new attributes'
try: Immutable(1,c=3)
except TypeError:
pass
else:
assert 0, 'accept only a,b keywords'
for kwd in [dict(a=1), dict(b=2)]:
try: Immutable(**kwd)
except TypeError:
pass
else:
assert 0, 'Immutable requires exactly 2 arguments'
If you don't mind indexing support then collections.namedtuple suggested by #Sven Marnach is preferrable:
Immutable = collections.namedtuple("Immutable", "a b")
Another idea would be to completely disallow __setattr__ and use object.__setattr__ in the constructor:
class Point(object):
def __init__(self, x, y):
object.__setattr__(self, "x", x)
object.__setattr__(self, "y", y)
def __setattr__(self, *args):
raise TypeError
def __delattr__(self, *args):
raise TypeError
Of course you could use object.__setattr__(p, "x", 3) to modify a Point instance p, but your original implementation suffers from the same problem (try tuple.__setattr__(i, "x", 42) on an Immutable instance).
You can apply the same trick in your original implementation: get rid of __getitem__(), and use tuple.__getitem__() in your property functions.
You could create a #immutable decorator that either overrides the __setattr__ and change the __slots__ to an empty list, then decorate the __init__ method with it.
Edit: As the OP noted, changing the __slots__ attribute only prevents the creation of new attributes, not the modification.
Edit2: Here's an implementation:
Edit3: Using __slots__ breaks this code, because if stops the creation of the object's __dict__. I'm looking for an alternative.
Edit4: Well, that's it. It's a but hackish, but works as an exercise :-)
class immutable(object):
def __init__(self, immutable_params):
self.immutable_params = immutable_params
def __call__(self, new):
params = self.immutable_params
def __set_if_unset__(self, name, value):
if name in self.__dict__:
raise Exception("Attribute %s has already been set" % name)
if not name in params:
raise Exception("Cannot create atribute %s" % name)
self.__dict__[name] = value;
def __new__(cls, *args, **kws):
cls.__setattr__ = __set_if_unset__
return super(cls.__class__, cls).__new__(cls, *args, **kws)
return __new__
class Point(object):
#immutable(['x', 'y'])
def __new__(): pass
def __init__(self, x, y):
self.x = x
self.y = y
p = Point(1, 2)
p.x = 3 # Exception: Attribute x has already been set
p.z = 4 # Exception: Cannot create atribute z
I don't think it is entirely possible except by using either a tuple or a namedtuple. No matter what, if you override __setattr__() the user can always bypass it by calling object.__setattr__() directly. Any solution that depends on __setattr__ is guaranteed not to work.
The following is about the nearest you can get without using some sort of tuple:
class Immutable:
__slots__ = ['a', 'b']
def __init__(self, a, b):
object.__setattr__(self, 'a', a)
object.__setattr__(self, 'b', b)
def __setattr__(self, *ignored):
raise NotImplementedError
__delattr__ = __setattr__
but it breaks if you try hard enough:
>>> t = Immutable(1, 2)
>>> t.a
1
>>> object.__setattr__(t, 'a', 2)
>>> t.a
2
but Sven's use of namedtuple is genuinely immutable.
Update
Since the question has been updated to ask how to do it properly in C, here's my answer on how to do it properly in Cython:
First immutable.pyx:
cdef class Immutable:
cdef object _a, _b
def __init__(self, a, b):
self._a = a
self._b = b
property a:
def __get__(self):
return self._a
property b:
def __get__(self):
return self._b
def __repr__(self):
return "<Immutable {0}, {1}>".format(self.a, self.b)
and a setup.py to compile it (using the command setup.py build_ext --inplace:
from distutils.core import setup
from distutils.extension import Extension
from Cython.Distutils import build_ext
ext_modules = [Extension("immutable", ["immutable.pyx"])]
setup(
name = 'Immutable object',
cmdclass = {'build_ext': build_ext},
ext_modules = ext_modules
)
Then to try it out:
>>> from immutable import Immutable
>>> p = Immutable(2, 3)
>>> p
<Immutable 2, 3>
>>> p.a = 1
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: attribute 'a' of 'immutable.Immutable' objects is not writable
>>> object.__setattr__(p, 'a', 1)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
AttributeError: attribute 'a' of 'immutable.Immutable' objects is not writable
>>> p.a, p.b
(2, 3)
>>>
I've made immutable classes by overriding __setattr__, and allowing the set if the caller is __init__:
import inspect
class Immutable(object):
def __setattr__(self, name, value):
if inspect.stack()[2][3] != "__init__":
raise Exception("Can't mutate an Immutable: self.%s = %r" % (name, value))
object.__setattr__(self, name, value)
This isn't quite enough yet, since it allows anyone's ___init__ to change the object, but you get the idea.
Here's an elegant solution:
class Immutable(object):
def __setattr__(self, key, value):
if not hasattr(self, key):
super().__setattr__(key, value)
else:
raise RuntimeError("Can't modify immutable object's attribute: {}".format(key))
Inherit from this class, initialize your fields in the constructor, and you'e all set.
In addition to the excellent other answers I like to add a method for python 3.4 (or maybe 3.3). This answer builds upon several previouse answers to this question.
In python 3.4, you can use properties without setters to create class members that cannot be modified. (In earlier versions assigning to properties without a setter was possible.)
class A:
__slots__=['_A__a']
def __init__(self, aValue):
self.__a=aValue
#property
def a(self):
return self.__a
You can use it like this:
instance=A("constant")
print (instance.a)
which will print "constant"
But calling instance.a=10 will cause:
AttributeError: can't set attribute
Explaination: properties without setters are a very recent feature of python 3.4 (and I think 3.3). If you try to assign to such a property, an Error will be raised.
Using slots I restrict the membervariables to __A_a (which is __a).
Problem: Assigning to _A__a is still possible (instance._A__a=2). But if you assign to a private variable, it is your own fault...
This answer among others, however, discourages the use of __slots__. Using other ways to prevent attribute creation might be preferrable.
So, I am writing respective of python 3:
I) with the help of data class decorator and set frozen=True.
we can create immutable objects in python.
for this need to import data class from data classes lib and needs to set frozen=True
ex.
from dataclasses import dataclass
#dataclass(frozen=True)
class Location:
name: str
longitude: float = 0.0
latitude: float = 0.0
o/p:
>>> l = Location("Delhi", 112.345, 234.788)
>>> l.name
'Delhi'
>>> l.longitude
112.345
>>> l.latitude
234.788
>>> l.name = "Kolkata"
dataclasses.FrozenInstanceError: cannot assign to field 'name'
>>>
Source: https://realpython.com/python-data-classes/
If you are interested in objects with behavior, then namedtuple is almost your solution.
As described at the bottom of the namedtuple documentation, you can derive your own class from namedtuple; and then, you can add the behavior you want.
For example (code taken directly from the documentation):
class Point(namedtuple('Point', 'x y')):
__slots__ = ()
#property
def hypot(self):
return (self.x ** 2 + self.y ** 2) ** 0.5
def __str__(self):
return 'Point: x=%6.3f y=%6.3f hypot=%6.3f' % (self.x, self.y, self.hypot)
for p in Point(3, 4), Point(14, 5/7):
print(p)
This will result in:
Point: x= 3.000 y= 4.000 hypot= 5.000
Point: x=14.000 y= 0.714 hypot=14.018
This approach works for both Python 3 and Python 2.7 (tested on IronPython as well).
The only downside is that the inheritance tree is a bit weird; but this is not something you usually play with.
As of Python 3.7, you can use the #dataclass decorator in your class and it will be immutable like a struct! Though, it may or may not add a __hash__() method to your class. Quote:
hash() is used by built-in hash(), and when objects are added to hashed collections such as dictionaries and sets. Having a hash() implies that instances of the class are immutable. Mutability is a complicated property that depends on the programmer’s intent, the existence and behavior of eq(), and the values of the eq and frozen flags in the dataclass() decorator.
By default, dataclass() will not implicitly add a hash() method unless it is safe to do so. Neither will it add or change an existing explicitly defined hash() method. Setting the class attribute hash = None has a specific meaning to Python, as described in the hash() documentation.
If hash() is not explicit defined, or if it is set to None, then dataclass() may add an implicit hash() method. Although not recommended, you can force dataclass() to create a hash() method with unsafe_hash=True. This might be the case if your class is logically immutable but can nonetheless be mutated. This is a specialized use case and should be considered carefully.
Here the example from the docs linked above:
#dataclass
class InventoryItem:
'''Class for keeping track of an item in inventory.'''
name: str
unit_price: float
quantity_on_hand: int = 0
def total_cost(self) -> float:
return self.unit_price * self.quantity_on_hand
Just Like a dict
I have an open source library where I'm doing things in a functional way so moving data around in an immutable object is helpful. However, I don't want to have to transform my data object for the client to interact with them. So, I came up with this - it gives you a dict like object thats immutable + some helper methods.
Credit to Sven Marnach in his answer for the basic implementation of restricting property updating and deleting.
import json
# ^^ optional - If you don't care if it prints like a dict
# then rip this and __str__ and __repr__ out
class Immutable(object):
def __init__(self, **kwargs):
"""Sets all values once given
whatever is passed in kwargs
"""
for k,v in kwargs.items():
object.__setattr__(self, k, v)
def __setattr__(self, *args):
"""Disables setting attributes via
item.prop = val or item['prop'] = val
"""
raise TypeError('Immutable objects cannot have properties set after init')
def __delattr__(self, *args):
"""Disables deleting properties"""
raise TypeError('Immutable objects cannot have properties deleted')
def __getitem__(self, item):
"""Allows for dict like access of properties
val = item['prop']
"""
return self.__dict__[item]
def __repr__(self):
"""Print to repl in a dict like fashion"""
return self.pprint()
def __str__(self):
"""Convert to a str in a dict like fashion"""
return self.pprint()
def __eq__(self, other):
"""Supports equality operator
immutable({'a': 2}) == immutable({'a': 2})"""
if other is None:
return False
return self.dict() == other.dict()
def keys(self):
"""Paired with __getitem__ supports **unpacking
new = { **item, **other }
"""
return self.__dict__.keys()
def get(self, *args, **kwargs):
"""Allows for dict like property access
item.get('prop')
"""
return self.__dict__.get(*args, **kwargs)
def pprint(self):
"""Helper method used for printing that
formats in a dict like way
"""
return json.dumps(self,
default=lambda o: o.__dict__,
sort_keys=True,
indent=4)
def dict(self):
"""Helper method for getting the raw dict value
of the immutable object"""
return self.__dict__
Helper methods
def update(obj, **kwargs):
"""Returns a new instance of the given object with
all key/val in kwargs set on it
"""
return immutable({
**obj,
**kwargs
})
def immutable(obj):
return Immutable(**obj)
Examples
obj = immutable({
'alpha': 1,
'beta': 2,
'dalet': 4
})
obj.alpha # 1
obj['alpha'] # 1
obj.get('beta') # 2
del obj['alpha'] # TypeError
obj.alpha = 2 # TypeError
new_obj = update(obj, alpha=10)
new_obj is not obj # True
new_obj.get('alpha') == 10 # True
This way doesn't stop object.__setattr__ from working, but I've still found it useful:
class A(object):
def __new__(cls, children, *args, **kwargs):
self = super(A, cls).__new__(cls)
self._frozen = False # allow mutation from here to end of __init__
# other stuff you need to do in __new__ goes here
return self
def __init__(self, *args, **kwargs):
super(A, self).__init__()
self._frozen = True # prevent future mutation
def __setattr__(self, name, value):
# need to special case setting _frozen.
if name != '_frozen' and self._frozen:
raise TypeError('Instances are immutable.')
else:
super(A, self).__setattr__(name, value)
def __delattr__(self, name):
if self._frozen:
raise TypeError('Instances are immutable.')
else:
super(A, self).__delattr__(name)
you may need to override more stuff (like __setitem__) depending on the use case.
Classes which inherit from the following Immutable class are immutable, as are their instances, after their __init__ method finishes executing. Since it's pure python, as others have pointed out, there's nothing stopping someone from using the mutating special methods from the base object and type, but this is enough to stop anyone from mutating a class/instance by accident.
It works by hijacking the class-creation process with a metaclass.
"""Subclasses of class Immutable are immutable after their __init__ has run, in
the sense that all special methods with mutation semantics (in-place operators,
setattr, etc.) are forbidden.
"""
# Enumerate the mutating special methods
mutation_methods = set()
# Arithmetic methods with in-place operations
iarithmetic = '''add sub mul div mod divmod pow neg pos abs bool invert lshift
rshift and xor or floordiv truediv matmul'''.split()
for op in iarithmetic:
mutation_methods.add('__i%s__' % op)
# Operations on instance components (attributes, items, slices)
for verb in ['set', 'del']:
for component in '''attr item slice'''.split():
mutation_methods.add('__%s%s__' % (verb, component))
# Operations on properties
mutation_methods.update(['__set__', '__delete__'])
def checked_call(_self, name, method, *args, **kwargs):
"""Calls special method method(*args, **kw) on self if mutable."""
self = args[0] if isinstance(_self, object) else _self
if not getattr(self, '__mutable__', True):
# self told us it's immutable, so raise an error
cname= (self if isinstance(self, type) else self.__class__).__name__
raise TypeError('%s is immutable, %s disallowed' % (cname, name))
return method(*args, **kwargs)
def method_wrapper(_self, name):
"Wrap a special method to check for mutability."
method = getattr(_self, name)
def wrapper(*args, **kwargs):
return checked_call(_self, name, method, *args, **kwargs)
wrapper.__name__ = name
wrapper.__doc__ = method.__doc__
return wrapper
def wrap_mutating_methods(_self):
"Place the wrapper methods on mutative special methods of _self"
for name in mutation_methods:
if hasattr(_self, name):
method = method_wrapper(_self, name)
type.__setattr__(_self, name, method)
def set_mutability(self, ismutable):
"Set __mutable__ by using the unprotected __setattr__"
b = _MetaImmutable if isinstance(self, type) else Immutable
super(b, self).__setattr__('__mutable__', ismutable)
class _MetaImmutable(type):
'''The metaclass of Immutable. Wraps __init__ methods via __call__.'''
def __init__(cls, *args, **kwargs):
# Make class mutable for wrapping special methods
set_mutability(cls, True)
wrap_mutating_methods(cls)
# Disable mutability
set_mutability(cls, False)
def __call__(cls, *args, **kwargs):
'''Make an immutable instance of cls'''
self = cls.__new__(cls)
# Make the instance mutable for initialization
set_mutability(self, True)
# Execute cls's custom initialization on this instance
self.__init__(*args, **kwargs)
# Disable mutability
set_mutability(self, False)
return self
# Given a class T(metaclass=_MetaImmutable), mutative special methods which
# already exist on _MetaImmutable (a basic type) cannot be over-ridden
# programmatically during _MetaImmutable's instantiation of T, because the
# first place python looks for a method on an object is on the object's
# __class__, and T.__class__ is _MetaImmutable. The two extant special
# methods on a basic type are __setattr__ and __delattr__, so those have to
# be explicitly overridden here.
def __setattr__(cls, name, value):
checked_call(cls, '__setattr__', type.__setattr__, cls, name, value)
def __delattr__(cls, name, value):
checked_call(cls, '__delattr__', type.__delattr__, cls, name, value)
class Immutable(object):
"""Inherit from this class to make an immutable object.
__init__ methods of subclasses are executed by _MetaImmutable.__call__,
which enables mutability for the duration.
"""
__metaclass__ = _MetaImmutable
class T(int, Immutable): # Checks it works with multiple inheritance, too.
"Class for testing immutability semantics"
def __init__(self, b):
self.b = b
#classmethod
def class_mutation(cls):
cls.a = 5
def instance_mutation(self):
self.c = 1
def __iadd__(self, o):
pass
def not_so_special_mutation(self):
self +=1
def immutabilityTest(f, name):
"Call f, which should try to mutate class T or T instance."
try:
f()
except TypeError, e:
assert 'T is immutable, %s disallowed' % name in e.args
else:
raise RuntimeError('Immutability failed!')
immutabilityTest(T.class_mutation, '__setattr__')
immutabilityTest(T(6).instance_mutation, '__setattr__')
immutabilityTest(T(6).not_so_special_mutation, '__iadd__')
The third party attr module provides this functionality.
Edit: python 3.7 has adopted this idea into the stdlib with #dataclass.
$ pip install attrs
$ python
>>> #attr.s(frozen=True)
... class C(object):
... x = attr.ib()
>>> i = C(1)
>>> i.x = 2
Traceback (most recent call last):
...
attr.exceptions.FrozenInstanceError: can't set attribute
attr implements frozen classes by overriding __setattr__ and has a minor performance impact at each instantiation time, according to the documentation.
If you're in the habit of using classes as datatypes, attr may be especially useful as it takes care of the boilerplate for you (but doesn't do any magic). In particular, it writes nine dunder (__X__) methods for you (unless you turn any of them off), including repr, init, hash and all the comparison functions.
attr also provides a helper for __slots__.
You can override setattr and still use init to set the variable. You would use super class setattr. here is the code.
class Immutable:
__slots__ = ('a','b')
def __init__(self, a , b):
super().__setattr__('a',a)
super().__setattr__('b',b)
def __str__(self):
return "".format(self.a, self.b)
def __setattr__(self, *ignored):
raise NotImplementedError
def __delattr__(self, *ignored):
raise NotImplementedError
I found a way to do it without subclassing tuple, namedtuple etc. All you need to do is to disable setattr and delattr (and also setitem and delitem if you want to make a collection immutable) after the initiation:
def __init__(self, *args, **kwargs):
# something here
self.lock()
where lock can look like this:
#classmethod
def lock(cls):
def raiser(*a):
raise TypeError('this instance is immutable')
cls.__setattr__ = raiser
cls.__delattr__ = raiser
if hasattr(cls, '__setitem__'):
cls.__setitem__ = raiser
cls.__delitem__ = raiser
So you can create class Immutable with this method and use it the way I showed.
If you don't want to write self.lock() in every single init you can make it automatically with metaclasses:
class ImmutableType(type):
#classmethod
def change_init(mcs, original_init_method):
def __new_init__(self, *args, **kwargs):
if callable(original_init_method):
original_init_method(self, *args, **kwargs)
cls = self.__class__
def raiser(*a):
raise TypeError('this instance is immutable')
cls.__setattr__ = raiser
cls.__delattr__ = raiser
if hasattr(cls, '__setitem__'):
cls.__setitem__ = raiser
cls.__delitem__ = raiser
return __new_init__
def __new__(mcs, name, parents, kwargs):
kwargs['__init__'] = mcs.change_init(kwargs.get('__init__'))
return type.__new__(mcs, name, parents, kwargs)
class Immutable(metaclass=ImmutableType):
pass
Test
class SomeImmutableClass(Immutable):
def __init__(self, some_value: int):
self.important_attr = some_value
def some_method(self):
return 2 * self.important_attr
ins = SomeImmutableClass(3)
print(ins.some_method()) # 6
ins.important_attr += 1 # TypeError
ins.another_attr = 2 # TypeError
The basic solution below addresses the following scenario:
__init__() can be written accessing the attributes as usual.
AFTER that the OBJECT is frozen for attributes changes only:
The idea is to override __setattr__ method and replace its implementation each time the object frozen status is changed.
So we need some method (_freeze) which stores those two implementations and switches between them when requested.
This mechanism may be implemented inside the user class or inherited from a special Freezer class as shown below:
class Freezer:
def _freeze(self, do_freeze=True):
def raise_sa(*args):
raise AttributeError("Attributes are frozen and can not be changed!")
super().__setattr__('_active_setattr', (super().__setattr__, raise_sa)[do_freeze])
def __setattr__(self, key, value):
return self._active_setattr(key, value)
class A(Freezer):
def __init__(self):
self._freeze(False)
self.x = 10
self._freeze()
I needed this a little while ago and decided to make a Python package for it. The initial version is on PyPI now:
$ pip install immutable
To use:
>>> from immutable import ImmutableFactory
>>> MyImmutable = ImmutableFactory.create(prop1=1, prop2=2, prop3=3)
>>> MyImmutable.prop1
1
Full docs here: https://github.com/theengineear/immutable
Hope it helps, it wraps a namedtuple as has been discussed, but makes instantiation much simpler.
An alternative approach is to create a wrapper which makes an instance immutable.
class Immutable(object):
def __init__(self, wrapped):
super(Immutable, self).__init__()
object.__setattr__(self, '_wrapped', wrapped)
def __getattribute__(self, item):
return object.__getattribute__(self, '_wrapped').__getattribute__(item)
def __setattr__(self, key, value):
raise ImmutableError('Object {0} is immutable.'.format(self._wrapped))
__delattr__ = __setattr__
def __iter__(self):
return object.__getattribute__(self, '_wrapped').__iter__()
def next(self):
return object.__getattribute__(self, '_wrapped').next()
def __getitem__(self, item):
return object.__getattribute__(self, '_wrapped').__getitem__(item)
immutable_instance = Immutable(my_instance)
This is useful in situations where only some instances have to be immutable (like default arguments of function calls).
Can also be used in immutable factories like:
#classmethod
def immutable_factory(cls, *args, **kwargs):
return Immutable(cls.__init__(*args, **kwargs))
Also protects from object.__setattr__, but fallable to other tricks due to Python's dynamic nature.
I used the same idea as Alex: a meta-class and an "init marker", but in combination with over-writing __setattr__:
>>> from abc import ABCMeta
>>> _INIT_MARKER = '_#_in_init_#_'
>>> class _ImmutableMeta(ABCMeta):
...
... """Meta class to construct Immutable."""
...
... def __call__(cls, *args, **kwds):
... obj = cls.__new__(cls, *args, **kwds)
... object.__setattr__(obj, _INIT_MARKER, True)
... cls.__init__(obj, *args, **kwds)
... object.__delattr__(obj, _INIT_MARKER)
... return obj
...
>>> def _setattr(self, name, value):
... if hasattr(self, _INIT_MARKER):
... object.__setattr__(self, name, value)
... else:
... raise AttributeError("Instance of '%s' is immutable."
... % self.__class__.__name__)
...
>>> def _delattr(self, name):
... raise AttributeError("Instance of '%s' is immutable."
... % self.__class__.__name__)
...
>>> _im_dict = {
... '__doc__': "Mix-in class for immutable objects.",
... '__copy__': lambda self: self, # self is immutable, so just return it
... '__setattr__': _setattr,
... '__delattr__': _delattr}
...
>>> Immutable = _ImmutableMeta('Immutable', (), _im_dict)
Note: I'm calling the meta-class directly to make it work both for Python 2.x and 3.x.
>>> class T1(Immutable):
...
... def __init__(self, x=1, y=2):
... self.x = x
... self.y = y
...
>>> t1 = T1(y=8)
>>> t1.x, t1.y
(1, 8)
>>> t1.x = 7
AttributeError: Instance of 'T1' is immutable.
It does work also with slots ...:
>>> class T2(Immutable):
...
... __slots__ = 's1', 's2'
...
... def __init__(self, s1, s2):
... self.s1 = s1
... self.s2 = s2
...
>>> t2 = T2('abc', 'xyz')
>>> t2.s1, t2.s2
('abc', 'xyz')
>>> t2.s1 += 'd'
AttributeError: Instance of 'T2' is immutable.
... and multiple inheritance:
>>> class T3(T1, T2):
...
... def __init__(self, x, y, s1, s2):
... T1.__init__(self, x, y)
... T2.__init__(self, s1, s2)
...
>>> t3 = T3(12, 4, 'a', 'b')
>>> t3.x, t3.y, t3.s1, t3.s2
(12, 4, 'a', 'b')
>>> t3.y -= 3
AttributeError: Instance of 'T3' is immutable.
Note, however, that mutable attributes stay to be mutable:
>>> t3 = T3(12, [4, 7], 'a', 'b')
>>> t3.y.append(5)
>>> t3.y
[4, 7, 5]
One thing that's not really included here is total immutability... not just the parent object, but all the children as well. tuples/frozensets may be immutable for instance, but the objects that it's part of may not be. Here's a small (incomplete) version that does a decent job of enforcing immutability all the way down:
# Initialize lists
a = [1,2,3]
b = [4,5,6]
c = [7,8,9]
l = [a,b]
# We can reassign in a list
l[0] = c
# But not a tuple
t = (a,b)
#t[0] = c -> Throws exception
# But elements can be modified
t[0][1] = 4
t
([1, 4, 3], [4, 5, 6])
# Fix it back
t[0][1] = 2
li = ImmutableObject(l)
li
[[1, 2, 3], [4, 5, 6]]
# Can't assign
#li[0] = c will fail
# Can reference
li[0]
[1, 2, 3]
# But immutability conferred on returned object too
#li[0][1] = 4 will throw an exception
# Full solution should wrap all the comparison e.g. decorators.
# Also, you'd usually want to add a hash function, i didn't put
# an interface for that.
class ImmutableObject(object):
def __init__(self, inobj):
self._inited = False
self._inobj = inobj
self._inited = True
def __repr__(self):
return self._inobj.__repr__()
def __str__(self):
return self._inobj.__str__()
def __getitem__(self, key):
return ImmutableObject(self._inobj.__getitem__(key))
def __iter__(self):
return self._inobj.__iter__()
def __setitem__(self, key, value):
raise AttributeError, 'Object is read-only'
def __getattr__(self, key):
x = getattr(self._inobj, key)
if callable(x):
return x
else:
return ImmutableObject(x)
def __hash__(self):
return self._inobj.__hash__()
def __eq__(self, second):
return self._inobj.__eq__(second)
def __setattr__(self, attr, value):
if attr not in ['_inobj', '_inited'] and self._inited == True:
raise AttributeError, 'Object is read-only'
object.__setattr__(self, attr, value)
You can just override setAttr in the final statement of init. THen you can construct but not change. Obviously you can still override by usint object.setAttr but in practice most languages have some form of reflection so immutablility is always a leaky abstraction. Immutability is more about preventing clients from accidentally violating the contract of an object. I use:
=============================
The original solution offered was incorrect, this was updated based on the comments using the solution from here
The original solution is wrong in an interesting way, so it is included at the bottom.
===============================
class ImmutablePair(object):
__initialised = False # a class level variable that should always stay false.
def __init__(self, a, b):
try :
self.a = a
self.b = b
finally:
self.__initialised = True #an instance level variable
def __setattr__(self, key, value):
if self.__initialised:
self._raise_error()
else :
super(ImmutablePair, self).__setattr__(key, value)
def _raise_error(self, *args, **kw):
raise NotImplementedError("Attempted To Modify Immutable Object")
if __name__ == "__main__":
immutable_object = ImmutablePair(1,2)
print immutable_object.a
print immutable_object.b
try :
immutable_object.a = 3
except Exception as e:
print e
print immutable_object.a
print immutable_object.b
Output :
1
2
Attempted To Modify Immutable Object
1
2
======================================
Original Implementation:
It was pointed out in the comments, correctly, that this does not in fact work, as it prevents the creation of more than one object as you are overriding the class setattr method, which means a second cannot be created as self.a = will fail on the second initialisation.
class ImmutablePair(object):
def __init__(self, a, b):
self.a = a
self.b = b
ImmutablePair.__setattr__ = self._raise_error
def _raise_error(self, *args, **kw):
raise NotImplementedError("Attempted To Modify Immutable Object")
I've created a small class decorator decorator to make class immutable (except inside __init__). As part of https://github.com/google/etils.
from etils import epy
#epy.frozen
class A:
def __init__(self):
self.x = 123 # Inside `__init__`, attribute can be assigned
a = A()
a.x = 456 # AttributeError
This support inheritance too.
Implementation:
_Cls = TypeVar('_Cls')
def frozen(cls: _Cls) -> _Cls:
"""Class decorator which prevent mutating attributes after `__init__`."""
if not isinstance(cls, type):
raise TypeError(f'{cls.__name__} is not a class.')
cls.__init__ = _wrap_init(cls.__init__)
cls.__setattr__ = _wrap_setattr(cls.__setattr__)
return cls
def _wrap_init(init_fn):
"""`__init__` wrapper."""
#functools.wraps(init_fn)
def new_init(self, *args, **kwargs):
if hasattr(self, '_epy_is_init_done'):
# `_epy_is_init_done` already created, so it means we're
# a `super().__init__` call.
return init_fn(self, *args, **kwargs)
object.__setattr__(self, '_epy_is_init_done', False)
init_fn(self, *args, **kwargs)
object.__setattr__(self, '_epy_is_init_done', True)
return new_init
def _wrap_setattr(setattr_fn):
"""`__setattr__` wrapper."""
#functools.wraps(setattr_fn)
def new_setattr(self, name, value):
if not hasattr(self, '_epy_is_init_done'):
raise ValueError(
'Child of `#epy.frozen` class should be `#epy.frozen` too. (Error'
f' raised by {type(self)})'
)
if not self._epy_is_init_done: # pylint: disable=protected-access
return setattr_fn(self, name, value)
else:
raise AttributeError(
f'Cannot assign {name!r} in `#epy.frozen` class {type(self)}'
)
return new_setattr