Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Nicer fix for lru_cache() that does not require meta_path trickery

Browse Source
This commit is contained in:
Kovid Goyal 2019-04-13 10:01:46 +05:30
parent b968cbdb5d
commit b177f0a109
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
5 changed files with 203 additions and 195 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

0
src/backports/__init__.py Normal file
View File

199
src/backports/functools_lru_cache.py Normal file
View File

@ -0,0 +1,199 @@
#!/usr/bin/env python2
# vim:fileencoding=utf-8
# License: GPL v3 Copyright: 2019, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
import functools
from collections import namedtuple
from threading import RLock
_CacheInfo = namedtuple("CacheInfo", ["hits", "misses", "maxsize", "currsize"])
@functools.wraps(functools.update_wrapper)
def update_wrapper(
wrapper,
wrapped,
assigned=functools.WRAPPER_ASSIGNMENTS,
updated=functools.WRAPPER_UPDATES
):
"""
Patch two bugs in functools.update_wrapper.
"""
# workaround for http://bugs.python.org/issue3445
assigned = tuple(attr for attr in assigned if hasattr(wrapped, attr))
wrapper = functools.update_wrapper(wrapper, wrapped, assigned, updated)
# workaround for https://bugs.python.org/issue17482
wrapper.__wrapped__ = wrapped
return wrapper
class _HashedSeq(list):
__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=set([int, str, frozenset, type(None)]),
sorted=sorted,
tuple=tuple,
type=type,
len=len
):
'Make a cache key from optionally typed positional and keyword arguments'
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)
def lru_cache(maxsize=100, typed=False):
"""Least-recently-used cache decorator.
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
"""
# 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).
def decorating_function(user_function):
cache = dict()
stats = [0, 0] # make statistics updateable non-locally
HITS, MISSES = 0, 1 # names for the stats fields
make_key = _make_key
cache_get = cache.get # bound method to lookup key or return None
_len = len # localize the global len() function
lock = RLock() # because linkedlist updates aren't threadsafe
root = [] # root of the circular doubly linked list
root[:] = [root, root, None, None] # initialize by pointing to self
nonlocal_root = [root] # make updateable non-locally
PREV, NEXT, KEY, RESULT = 0, 1, 2, 3 # names for the link fields
if maxsize == 0:
def wrapper(*args, **kwds):
# no caching, just do a statistics update after a successful call
result = user_function(*args, **kwds)
stats[MISSES] += 1
return result
elif maxsize is None:
def wrapper(*args, **kwds):
# simple caching without ordering or size limit
key = make_key(args, kwds, typed)
result = cache_get(
key, root
) # root used here as a unique not-found sentinel
if result is not root:
stats[HITS] += 1
return result
result = user_function(*args, **kwds)
cache[key] = result
stats[MISSES] += 1
return result
else:
def wrapper(*args, **kwds):
# size limited caching that tracks accesses by recency
key = make_key(args, kwds, typed) if kwds or typed else args
with lock:
link = cache_get(key)
if link is not None:
# record recent use of the key by moving it to the front of the list
root, = nonlocal_root
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
stats[HITS] += 1
return result
result = user_function(*args, **kwds)
with lock:
root, = nonlocal_root
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 _len(cache) >= maxsize:
# 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
root = nonlocal_root[0] = oldroot[NEXT]
oldkey = root[KEY]
root[KEY] = root[RESULT] = None
# now update the cache dictionary for the new links
del cache[oldkey]
cache[key] = oldroot
else:
# put result in a new link at the front of the list
last = root[PREV]
link = [last, root, key, result]
last[NEXT] = root[PREV] = cache[key] = link
stats[MISSES] += 1
return result
def cache_info():
"""Report cache statistics"""
with lock:
return _CacheInfo(stats[HITS], stats[MISSES], maxsize, len(cache))
def cache_clear():
"""Clear the cache and cache statistics"""
with lock:
cache.clear()
root = nonlocal_root[0]
root[:] = [root, root, None, None]
stats[:] = [0, 0]
wrapper.__wrapped__ = user_function
wrapper.cache_info = cache_info
wrapper.cache_clear = cache_clear
return update_wrapper(wrapper, user_function)
return decorating_function

4
src/calibre/startup.py
View File

@ -56,14 +56,12 @@ if not _run_once:
else: else:
def find_module(self, fullname, path=None): def find_module(self, fullname, path=None):
if fullname in ('calibre.web.feeds.feedparser', 'backports.functools_lru_cache') or fullname.startswith('calibre.ebooks.markdown'): if fullname == 'calibre.web.feeds.feedparser' or fullname.startswith('calibre.ebooks.markdown'):
return self return self
def load_module(self, fullname): def load_module(self, fullname):
if fullname == 'calibre.web.feeds.feedparser': if fullname == 'calibre.web.feeds.feedparser':
return import_module('feedparser') return import_module('feedparser')
if fullname == 'backports.functools_lru_cache':
return import_module('polyglot.functools')
return import_module(fullname[len('calibre.ebooks.'):]) return import_module(fullname[len('calibre.ebooks.'):])
sys.meta_path.insert(0, DeVendor()) sys.meta_path.insert(0, DeVendor())

3
src/calibre/test_build.py
View File

@ -74,9 +74,8 @@ class BuildTest(unittest.TestCase):
parse('<p>xxx') parse('<p>xxx')
def test_soupsieve(self): def test_soupsieve(self):
import calibre.startup as s
import soupsieve import soupsieve
del soupsieve, s del soupsieve
def test_plugins(self): def test_plugins(self):
exclusions = set() exclusions = set()

192
src/polyglot/functools.py
View File

@ -8,194 +8,6 @@ from polyglot.builtins import is_py3
if is_py3: if is_py3:
from functools import lru_cache from functools import lru_cache
else: else:
import functools from backports.functools_lru_cache import lru_cache
from collections import namedtuple
from threading import RLock
_CacheInfo = namedtuple("CacheInfo", ["hits", "misses", "maxsize", "currsize"]) lru_cache
@functools.wraps(functools.update_wrapper)
def update_wrapper(
wrapper,
wrapped,
assigned=functools.WRAPPER_ASSIGNMENTS,
updated=functools.WRAPPER_UPDATES
):
"""
Patch two bugs in functools.update_wrapper.
"""
# workaround for http://bugs.python.org/issue3445
assigned = tuple(attr for attr in assigned if hasattr(wrapped, attr))
wrapper = functools.update_wrapper(wrapper, wrapped, assigned, updated)
# workaround for https://bugs.python.org/issue17482
wrapper.__wrapped__ = wrapped
return wrapper
class _HashedSeq(list):
__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=set([int, str, frozenset, type(None)]),
sorted=sorted,
tuple=tuple,
type=type,
len=len
):
'Make a cache key from optionally typed positional and keyword arguments'
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)
def lru_cache(maxsize=100, typed=False):
"""Least-recently-used cache decorator.
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
"""
# 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).
def decorating_function(user_function):
cache = dict()
stats = [0, 0] # make statistics updateable non-locally
HITS, MISSES = 0, 1 # names for the stats fields
make_key = _make_key
cache_get = cache.get # bound method to lookup key or return None
_len = len # localize the global len() function
lock = RLock() # because linkedlist updates aren't threadsafe
root = [] # root of the circular doubly linked list
root[:] = [root, root, None, None] # initialize by pointing to self
nonlocal_root = [root] # make updateable non-locally
PREV, NEXT, KEY, RESULT = 0, 1, 2, 3 # names for the link fields
if maxsize == 0:
def wrapper(*args, **kwds):
# no caching, just do a statistics update after a successful call
result = user_function(*args, **kwds)
stats[MISSES] += 1
return result
elif maxsize is None:
def wrapper(*args, **kwds):
# simple caching without ordering or size limit
key = make_key(args, kwds, typed)
result = cache_get(
key, root
) # root used here as a unique not-found sentinel
if result is not root:
stats[HITS] += 1
return result
result = user_function(*args, **kwds)
cache[key] = result
stats[MISSES] += 1
return result
else:
def wrapper(*args, **kwds):
# size limited caching that tracks accesses by recency
key = make_key(args, kwds, typed) if kwds or typed else args
with lock:
link = cache_get(key)
if link is not None:
# record recent use of the key by moving it to the front of the list
root, = nonlocal_root
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
stats[HITS] += 1
return result
result = user_function(*args, **kwds)
with lock:
root, = nonlocal_root
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 _len(cache) >= maxsize:
# 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
root = nonlocal_root[0] = oldroot[NEXT]
oldkey = root[KEY]
root[KEY] = root[RESULT] = None
# now update the cache dictionary for the new links
del cache[oldkey]
cache[key] = oldroot
else:
# put result in a new link at the front of the list
last = root[PREV]
link = [last, root, key, result]
last[NEXT] = root[PREV] = cache[key] = link
stats[MISSES] += 1
return result
def cache_info():
"""Report cache statistics"""
with lock:
return _CacheInfo(
stats[HITS], stats[MISSES], maxsize, len(cache)
)
def cache_clear():
"""Clear the cache and cache statistics"""
with lock:
cache.clear()
root = nonlocal_root[0]
root[:] = [root, root, None, None]
stats[:] = [0, 0]
wrapper.__wrapped__ = user_function
wrapper.cache_info = cache_info
wrapper.cache_clear = cache_clear
return update_wrapper(wrapper, user_function)
return decorating_function