cache.py

# Written by Nick Coghlan <ncoghlan at gmail.com>,
# Raymond Hettinger <python at rcn.com>,
# and Łukasz Langa <lukasz at langa.pl>.
# Copyright (C) 2006-2013 Python Software Foundation.
# Modified to allow a custom key hash function.

from _thread import RLock
from collections import namedtuple

WRAPPER_ASSIGNMENTS = ('__module__', '__name__', '__qualname__', '__doc__', '__annotations__')
WRAPPER_UPDATES = ('__dict__',)

def update_wrapper(wrapper, wrapped, assigned=WRAPPER_ASSIGNMENTS, updated=WRAPPER_UPDATES):
    """
    Update a wrapper function to look like the wrapped function.

    wrapper is the function to be updated
    wrapped is the original function
    assigned is a tuple naming the attributes assigned directly from the wrapped function to the
    wrapper function (defaults to WRAPPER_ASSIGNMENTS)
    updated is a tuple naming the attributes of the wrapper that are updated with the corresponding
    attribute from the wrapped function (defaults to WRAPPER_UPDATES)
    """

    for attr in assigned:
        try:
            value = getattr(wrapped, attr)
        except AttributeError:
            pass
        else:
            setattr(wrapper, attr, value)
    for attr in updated:
        getattr(wrapper, attr).update(getattr(wrapped, attr, {}))
    # Issue #17482: set __wrapped__ last so we don't inadvertently copy it
    # from the wrapped function when updating __dict__
    wrapper.__wrapped__ = wrapped
    # Return the wrapper so this can be used as a decorator via partial()
    return wrapper

_CacheInfo = namedtuple("CacheInfo", ["hits", "misses", "maxsize", "currsize"])
_kwd_mark = (object(),)
_fasttypes = {int, str}

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 hash_key(*args, **kwds):
    """
    Make a cache key from 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:
        key += _kwd_mark
        for item in kwds.items():
            key += item
    if len(key) == 1 and type(key[0]) in _fasttypes:
        return key[0]
    return _HashedSeq(key)

def lru_cache(maxsize=128, key=hash_key):
    """
    Least-recently-used cache decorator.

    If *maxsize* is set to None, the LRU features are disabled and the cache
    can grow without bound.

    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:  https://en.wikipedia.org/wiki/Cache_replacement_policies#Least_recently_used_(LRU)
    """

    if isinstance(maxsize, int):
        # Negative maxsize is treated as 0
        if maxsize < 0:
            maxsize = 0
    elif maxsize is not None:
        raise TypeError(
            'Expected first argument to be an integer or None')

    def decorating_function(user_function):
        wrapper = _lru_cache_wrapper(user_function, maxsize, key, _CacheInfo)
        wrapper.cache_parameters = lambda: {'maxsize': maxsize, 'key': key}
        return update_wrapper(wrapper, user_function)

    return decorating_function

def _lru_cache_wrapper(user_function, maxsize, make_key, _CacheInfo):
    # Constants shared by all lru cache instances:
    sentinel = object()  # unique object used to signal cache misses
    PREV, NEXT, KEY, RESULT = 0, 1, 2, 3  # names for the link fields

    cache = {}
    hits = misses = 0
    full = False
    cache_get = cache.get  # bound method to lookup a key or return None
    cache_len = cache.__len__  # get cache size without calling len()
    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

    if maxsize == 0:
        def wrapper(*args, **kwds):
            # No caching -- just a statistics update
            nonlocal misses
            misses += 1
            result = user_function(*args, **kwds)
            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)
            result = cache_get(key, sentinel)
            if result is not sentinel:
                hits += 1
                return result
            misses += 1
            result = user_function(*args, **kwds)
            cache[key] = result
            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)
            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
                misses += 1
            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]
                    oldresult = root[RESULT]
                    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
                    # Use the cache_len bound method instead of the len() function
                    # which could potentially be wrapped in an lru_cache itself.
                    full = (cache_len() >= maxsize)
            return result

    def cache_info():
        """Report cache statistics"""
        with lock:
            return _CacheInfo(hits, misses, maxsize, cache_len())

    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
    return wrapper