bpo-21145: Add cached_property decorator in functools (#6982)

carljm · ncoghlan · commit d658deac6060 · 2018-08-28T17:11:56.000+10:00
Robust caching of calculated properties is
harder than it looks at first glance, so add
a solid, well-tested implementation to the
standard library.
diff --git a/Doc/library/functools.rst b/Doc/library/functools.rst
@@ -20,6 +20,39 @@ function for the purposes of this module.
 
 The :mod:`functools` module defines the following functions:
 
+.. decorator:: cached_property(func)
+
+   Transform a method of a class into a property whose value is computed once
+   and then cached as a normal attribute for the life of the instance. Similar
+   to :func:`property`, with the addition of caching. Useful for expensive
+   computed properties of instances that are otherwise effectively immutable.
+
+   Example::
+
+       class DataSet:
+           def __init__(self, sequence_of_numbers):
+               self._data = sequence_of_numbers
+
+           @cached_property
+           def stdev(self):
+               return statistics.stdev(self._data)
+
+           @cached_property
+           def variance(self):
+               return statistics.variance(self._data)
+
+   .. versionadded:: 3.8
+
+   .. note::
+
+      This decorator requires that the ``__dict__`` attribute on each instance
+      be a mutable mapping. This means it will not work with some types, such as
+      metaclasses (since the ``__dict__`` attributes on type instances are
+      read-only proxies for the class namespace), and those that specify
+      ``__slots__`` without including ``__dict__`` as one of the defined slots
+      (as such classes don't provide a ``__dict__`` attribute at all).
+
+
 .. function:: cmp_to_key(func)
 
    Transform an old-style comparison function to a :term:`key function`.  Used
diff --git a/Lib/functools.py b/Lib/functools.py
@@ -868,3 +868,58 @@ def _method(*args, **kwargs):
     @property
     def __isabstractmethod__(self):
         return getattr(self.func, '__isabstractmethod__', False)
+
+
+################################################################################
+### cached_property() - computed once per instance, cached as attribute
+################################################################################
+
+_NOT_FOUND = object()
+
+
+class cached_property:
+    def __init__(self, func):
+        self.func = func
+        self.attrname = None
+        self.__doc__ = func.__doc__
+        self.lock = RLock()
+
+    def __set_name__(self, owner, name):
+        if self.attrname is None:
+            self.attrname = name
+        elif name != self.attrname:
+            raise TypeError(
+                "Cannot assign the same cached_property to two different names "
+                f"({self.attrname!r} and {name!r})."
+            )
+
+    def __get__(self, instance, owner):
+        if instance is None:
+            return self
+        if self.attrname is None:
+            raise TypeError(
+                "Cannot use cached_property instance without calling __set_name__ on it.")
+        try:
+            cache = instance.__dict__
+        except AttributeError:  # not all objects have __dict__ (e.g. class defines slots)
+            msg = (
+                f"No '__dict__' attribute on {type(instance).__name__!r} "
+                f"instance to cache {self.attrname!r} property."
+            )
+            raise TypeError(msg) from None
+        val = cache.get(self.attrname, _NOT_FOUND)
+        if val is _NOT_FOUND:
+            with self.lock:
+                # check if another thread filled cache while we awaited lock
+                val = cache.get(self.attrname, _NOT_FOUND)
+                if val is _NOT_FOUND:
+                    val = self.func(instance)
+                    try:
+                        cache[self.attrname] = val
+                    except TypeError:
+                        msg = (
+                            f"The '__dict__' attribute on {type(instance).__name__!r} instance "
+                            f"does not support item assignment for caching {self.attrname!r} property."
+                        )
+                        raise TypeError(msg) from None
+        return val
diff --git a/Lib/test/test_functools.py b/Lib/test/test_functools.py
@@ -2313,5 +2313,171 @@ def f(*args):
         with self.assertRaisesRegex(TypeError, msg):
             f()
 
+
+class CachedCostItem:
+    _cost = 1
+
+    def __init__(self):
+        self.lock = py_functools.RLock()
+
+    @py_functools.cached_property
+    def cost(self):
+        """The cost of the item."""
+        with self.lock:
+            self._cost += 1
+        return self._cost
+
+
+class OptionallyCachedCostItem:
+    _cost = 1
+
+    def get_cost(self):
+        """The cost of the item."""
+        self._cost += 1
+        return self._cost
+
+    cached_cost = py_functools.cached_property(get_cost)
+
+
+class CachedCostItemWait:
+
+    def __init__(self, event):
+        self._cost = 1
+        self.lock = py_functools.RLock()
+        self.event = event
+
+    @py_functools.cached_property
+    def cost(self):
+        self.event.wait(1)
+        with self.lock:
+            self._cost += 1
+        return self._cost
+
+
+class CachedCostItemWithSlots:
+    __slots__ = ('_cost')
+
+    def __init__(self):
+        self._cost = 1
+
+    @py_functools.cached_property
+    def cost(self):
+        raise RuntimeError('never called, slots not supported')
+
+
+class TestCachedProperty(unittest.TestCase):
+    def test_cached(self):
+        item = CachedCostItem()
+        self.assertEqual(item.cost, 2)
+        self.assertEqual(item.cost, 2) # not 3
+
+    def test_cached_attribute_name_differs_from_func_name(self):
+        item = OptionallyCachedCostItem()
+        self.assertEqual(item.get_cost(), 2)
+        self.assertEqual(item.cached_cost, 3)
+        self.assertEqual(item.get_cost(), 4)
+        self.assertEqual(item.cached_cost, 3)
+
+    def test_threaded(self):
+        go = threading.Event()
+        item = CachedCostItemWait(go)
+
+        num_threads = 3
+
+        orig_si = sys.getswitchinterval()
+        sys.setswitchinterval(1e-6)
+        try:
+            threads = [
+                threading.Thread(target=lambda: item.cost)
+                for k in range(num_threads)
+            ]
+            with support.start_threads(threads):
+                go.set()
+        finally:
+            sys.setswitchinterval(orig_si)
+
+        self.assertEqual(item.cost, 2)
+
+    def test_object_with_slots(self):
+        item = CachedCostItemWithSlots()
+        with self.assertRaisesRegex(
+                TypeError,
+                "No '__dict__' attribute on 'CachedCostItemWithSlots' instance to cache 'cost' property.",
+        ):
+            item.cost
+
+    def test_immutable_dict(self):
+        class MyMeta(type):
+            @py_functools.cached_property
+            def prop(self):
+                return True
+
+        class MyClass(metaclass=MyMeta):
+            pass
+
+        with self.assertRaisesRegex(
+            TypeError,
+            "The '__dict__' attribute on 'MyMeta' instance does not support item assignment for caching 'prop' property.",
+        ):
+            MyClass.prop
+
+    def test_reuse_different_names(self):
+        """Disallow this case because decorated function a would not be cached."""
+        with self.assertRaises(RuntimeError) as ctx:
+            class ReusedCachedProperty:
+                @py_functools.cached_property
+                def a(self):
+                    pass
+
+                b = a
+
+        self.assertEqual(
+            str(ctx.exception.__context__),
+            str(TypeError("Cannot assign the same cached_property to two different names ('a' and 'b')."))
+        )
+
+    def test_reuse_same_name(self):
+        """Reusing a cached_property on different classes under the same name is OK."""
+        counter = 0
+
+        @py_functools.cached_property
+        def _cp(_self):
+            nonlocal counter
+            counter += 1
+            return counter
+
+        class A:
+            cp = _cp
+
+        class B:
+            cp = _cp
+
+        a = A()
+        b = B()
+
+        self.assertEqual(a.cp, 1)
+        self.assertEqual(b.cp, 2)
+        self.assertEqual(a.cp, 1)
+
+    def test_set_name_not_called(self):
+        cp = py_functools.cached_property(lambda s: None)
+        class Foo:
+            pass
+
+        Foo.cp = cp
+
+        with self.assertRaisesRegex(
+                TypeError,
+                "Cannot use cached_property instance without calling __set_name__ on it.",
+        ):
+            Foo().cp
+
+    def test_access_from_class(self):
+        self.assertIsInstance(CachedCostItem.cost, py_functools.cached_property)
+
+    def test_doc(self):
+        self.assertEqual(CachedCostItem.cost.__doc__, "The cost of the item.")
+
+
 if __name__ == '__main__':
     unittest.main()
diff --git a/Misc/NEWS.d/next/Library/2018-05-18-22-52-34.bpo-21145.AiQMDx.rst b/Misc/NEWS.d/next/Library/2018-05-18-22-52-34.bpo-21145.AiQMDx.rst
@@ -0,0 +1,2 @@
+Add ``functools.cached_property`` decorator, for computed properties cached
+for the life of the instance.

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	+Add ``functools.cached_property`` decorator, for computed properties cached
	`2`	`+for the life of the instance.`