Issue #15528: Add weakref.finalize to support finalization using

weakref callbacks.

This is 2e446e87ac5b except that collections/__init__.py has been
modified to import proxy from _weakref instead of weakref.  This
eliminates an import cycle which seems to cause a problem on Unix but
not Windows.

1 files changed, 136 insertions, 1 deletions

diff --git a/Lib/weakref.py b/Lib/weakref.py
index 8f9c107..4c0b26e 100644
--- a/Lib/weakref.py
+++ b/Lib/weakref.py
@@ -21,13 +21,16 @@ from _weakref import (
 from _weakrefset import WeakSet, _IterationGuard
 
 import collections  # Import after _weakref to avoid circular import.
+import sys
+import itertools
+import atexit
 
 ProxyTypes = (ProxyType, CallableProxyType)
 
 __all__ = ["ref", "proxy", "getweakrefcount", "getweakrefs",
            "WeakKeyDictionary", "ReferenceType", "ProxyType",
            "CallableProxyType", "ProxyTypes", "WeakValueDictionary",
-           "WeakSet", "WeakMethod"]
+           "WeakSet", "WeakMethod", "finalize"]
 
 
 class WeakMethod(ref):
@@ -436,3 +439,135 @@ class WeakKeyDictionary(collections.MutableMapping):
                 d[ref(key, self._remove)] = value
         if len(kwargs):
             self.update(kwargs)
+
+
+class finalize:
+    """Class for finalization of weakrefable objects
+
+    finalize(obj, func, *args, **kwargs) returns a callable finalizer
+    object which will be called when obj is garbage collected. The
+    first time the finalizer is called it evaluates func(*arg, **kwargs)
+    and returns the result. After this the finalizer is dead, and
+    calling it just returns None.
+
+    When the program exits any remaining finalizers for which the
+    atexit attribute is true will be run in reverse order of creation.
+    By default atexit is true.
+    """
+
+    # Finalizer objects don't have any state of their own.  They are
+    # just used as keys to lookup _Info objects in the registry.  This
+    # ensures that they cannot be part of a ref-cycle.
+
+    __slots__ = ()
+    _registry = {}
+    _shutdown = False
+    _index_iter = itertools.count()
+    _dirty = False
+
+    class _Info:
+        __slots__ = ("weakref", "func", "args", "kwargs", "atexit", "index")
+
+    def __init__(self, obj, func, *args, **kwargs):
+        info = self._Info()
+        info.weakref = ref(obj, self)
+        info.func = func
+        info.args = args
+        info.kwargs = kwargs or None
+        info.atexit = True
+        info.index = next(self._index_iter)
+        self._registry[self] = info
+        finalize._dirty = True
+
+    def __call__(self, _=None):
+        """If alive then mark as dead and return func(*args, **kwargs);
+        otherwise return None"""
+        info = self._registry.pop(self, None)
+        if info and not self._shutdown:
+            return info.func(*info.args, **(info.kwargs or {}))
+
+    def detach(self):
+        """If alive then mark as dead and return (obj, func, args, kwargs);
+        otherwise return None"""
+        info = self._registry.get(self)
+        obj = info and info.weakref()
+        if obj is not None and self._registry.pop(self, None):
+            return (obj, info.func, info.args, info.kwargs or {})
+
+    def peek(self):
+        """If alive then return (obj, func, args, kwargs);
+        otherwise return None"""
+        info = self._registry.get(self)
+        obj = info and info.weakref()
+        if obj is not None:
+            return (obj, info.func, info.args, info.kwargs or {})
+
+    @property
+    def alive(self):
+        """Whether finalizer is alive"""
+        return self in self._registry
+
+    @property
+    def atexit(self):
+        """Whether finalizer should be called at exit"""
+        info = self._registry.get(self)
+        return bool(info) and info.atexit
+
+    @atexit.setter
+    def atexit(self, value):
+        info = self._registry.get(self)
+        if info:
+            info.atexit = bool(value)
+
+    def __repr__(self):
+        info = self._registry.get(self)
+        obj = info and info.weakref()
+        if obj is None:
+            return '<%s object at %#x; dead>' % (type(self).__name__, id(self))
+        else:
+            return '<%s object at %#x; for %r at %#x>' % \
+                (type(self).__name__, id(self), type(obj).__name__, id(obj))
+
+    @classmethod
+    def _select_for_exit(cls):
+        # Return live finalizers marked for exit, oldest first
+        L = [(f,i) for (f,i) in cls._registry.items() if i.atexit]
+        L.sort(key=lambda item:item[1].index)
+        return [f for (f,i) in L]
+
+    @classmethod
+    def _exitfunc(cls):
+        # At shutdown invoke finalizers for which atexit is true.
+        # This is called once all other non-daemonic threads have been
+        # joined.
+        reenable_gc = False
+        try:
+            if cls._registry:
+                import gc
+                if gc.isenabled():
+                    reenable_gc = True
+                    gc.disable()
+                pending = None
+                while True:
+                    if pending is None or finalize._dirty:
+                        pending = cls._select_for_exit()
+                        finalize._dirty = False
+                    if not pending:
+                        break
+                    f = pending.pop()
+                    try:
+                        # gc is disabled, so (assuming no daemonic
+                        # threads) the following is the only line in
+                        # this function which might trigger creation
+                        # of a new finalizer
+                        f()
+                    except Exception:
+                        sys.excepthook(*sys.exc_info())
+                    assert f not in cls._registry
+        finally:
+            # prevent any more finalizers from executing during shutdown
+            finalize._shutdown = True
+            if reenable_gc:
+                gc.enable()
+
+atexit.register(finalize._exitfunc)