"""The MIT License (MIT)
Copyright (c) 2013 abarnert
Permission is hereby granted, free of charge, to any person obtaining a copy of
this software and associated documentation files (the "Software"), to deal in
the Software without restriction, including without limitation the rights to
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
the Software, and to permit persons to whom the Software is furnished to do so,
subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
"""
"""persistent_lru_cache.py - A persistent LRU cache decorator
"""
# Based on lru_cache from functools in the standard library, which
# was written by Nick Coghlan <ncochlan at gmail.com> and
# Raymond Hettinger <python at rcn.com>. Persistence added by
# Andrew Barnert <abarnert at yahoo.com>.
__all__ = ["persistent_lru_cache"]
try:
import atexit
import pickle
from functools import update_wrapper
from collections import namedtuple
from _thread import RLock
except BaseException:
class RLock:
"Dummy reentrant lock for builds without threads"
def __enter__(self):
pass
def __exit__(self, exctype, excinst, exctb):
pass
################################################################################
# LRU Cache function decorator
################################################################################
_CacheInfo = namedtuple("CacheInfo", ["hits", "misses", "maxsize", "currsize"])
class _HashedSeq(list):
"""This class guarantees that hash() will be called no more than once
per element. This is important because the lru_cache() will hash
the key multiple times on a cache miss.
"""
__slots__ = "hashvalue"
def __init__(self, tup, hash=hash):
self[:] = tup
self.hashvalue = hash(tup)
def __hash__(self):
return self.hashvalue
def _make_key(
args,
kwds,
typed,
kwd_mark=(object(),),
fasttypes={int, str, frozenset, type(None)},
sorted=sorted,
tuple=tuple,
type=type,
len=len,
):
"""Make a cache key from optionally typed positional and keyword arguments
The key is constructed in a way that is flat as possible rather than
as a nested structure that would take more memory.
If there is only a single argument and its data type is known to cache
its hash value, then that argument is returned without a wrapper. This
saves space and improves lookup speed.
"""
key = args
if kwds:
sorted_items = sorted(kwds.items())
key += kwd_mark
for item in sorted_items:
key += item
if typed:
key += tuple(type(v) for v in args)
if kwds:
key += tuple(type(v) for k, v in sorted_items)
elif len(key) == 1 and type(key[0]) in fasttypes:
return key[0]
return _HashedSeq(key)
[docs]def persistent_lru_cache(filename, save_every=1, maxsize=128, typed=False):
"""Least-recently-used cache decorator.
*filename* is a path to a pickle file that will store the cache
between runs.
If *save_every* is set to None, the cache will only be saved at exit
(or when wrapper.cache_save is explicitly callde). If it's a number N,
the cache will be saved every N cache misses.
If *maxsize* is set to None, the LRU features are disabled and the cache
can grow without bound.
If *typed* is True, arguments of different types will be cached separately.
For example, f(3.0) and f(3) will be treated as distinct calls with
distinct results.
Arguments to the cached function must be hashable.
View the cache statistics named tuple (hits, misses, maxsize, currsize)
with f.cache_info(). Clear the cache and statistics with f.cache_clear().
Access the underlying function with f.__wrapped__.
See: http://en.wikipedia.org/wiki/Cache_algorithms#Least_Recently_Used
"""
# TODO: Maybe add cache save info to info?
# Users should only access the lru_cache through its public API:
# cache_info, cache_clear, and f.__wrapped__
# The internals of the lru_cache are encapsulated for thread safety and
# to allow the implementation to change (including a possible C version).
# Constants shared by all lru cache instances:
sentinel = object() # unique object used to signal cache misses
make_key = _make_key # build a key from the function arguments
PREV, NEXT, KEY, RESULT = 0, 1, 2, 3 # names for the link fields
def decorating_function(user_function):
lock = RLock() # because linkedlist updates aren't threadsafe
try:
with open(filename, "rb") as f:
cache = pickle.load(f)
except BaseException:
cache = {}
def cache_save():
with lock:
with open(filename, "wb") as f:
pickle.dump(cache, f)
atexit.register(cache_save)
hits = misses = 0
full = False
cache_get = cache.get # bound method to lookup a key or return None
root = [] # root of the circular doubly linked list
root[:] = [root, root, None, None] # initialize by pointing to self
if maxsize == 0:
def wrapper(*args, **kwds):
# No caching -- just a statistics update after a successful call
nonlocal misses
result = user_function(*args, **kwds)
misses += 1
return result
elif maxsize is None:
def wrapper(*args, **kwds):
# Simple caching without ordering or size limit
nonlocal hits, misses
key = make_key(args, kwds, typed)
result = cache_get(key, sentinel)
if result is not sentinel:
hits += 1
return result
result = user_function(*args, **kwds)
cache[key] = result
misses += 1
if save_every and not misses % save_every:
cache_save()
return result
else:
def wrapper(*args, **kwds):
# Size limited caching that tracks accesses by recency
nonlocal root, hits, misses, full
key = make_key(args, kwds, typed)
with lock:
link = cache_get(key)
if link is not None:
# Move the link to the front of the circular queue
link_prev, link_next, _key, result = link
link_prev[NEXT] = link_next
link_next[PREV] = link_prev
last = root[PREV]
last[NEXT] = root[PREV] = link
link[PREV] = last
link[NEXT] = root
hits += 1
return result
result = user_function(*args, **kwds)
with lock:
if key in cache:
# Getting here means that this same key was added to the
# cache while the lock was released. Since the link
# update is already done, we need only return the
# computed result and update the count of misses.
pass
elif full:
# Use the old root to store the new key and result.
oldroot = root
oldroot[KEY] = key
oldroot[RESULT] = result
# Empty the oldest link and make it the new root.
# Keep a reference to the old key and old result to
# prevent their ref counts from going to zero during the
# update. That will prevent potentially arbitrary object
# clean-up code (i.e. __del__) from running while we're
# still adjusting the links.
root = oldroot[NEXT]
oldkey = root[KEY]
_ = root[RESULT] # noqa: F841
root[KEY] = root[RESULT] = None
# Now update the cache dictionary.
del cache[oldkey]
# Save the potentially reentrant cache[key] assignment
# for last, after the root and links have been put in
# a consistent state.
cache[key] = oldroot
else:
# Put result in a new link at the front of the queue.
last = root[PREV]
link = [last, root, key, result]
last[NEXT] = root[PREV] = cache[key] = link
full = len(cache) >= maxsize
misses += 1
if save_every and not misses % save_every:
cache_save()
return result
def cache_info():
"""Report cache statistics"""
with lock:
return _CacheInfo(hits, misses, maxsize, len(cache))
def cache_clear():
"""Clear the cache and cache statistics"""
nonlocal hits, misses, full
with lock:
cache.clear()
root[:] = [root, root, None, None]
hits = misses = 0
full = False
wrapper.cache_info = cache_info
wrapper.cache_clear = cache_clear
wrapper.cache_save = cache_save
wrapper.cache_filename = filename
return update_wrapper(wrapper, user_function)
return decorating_function