Python 如何";完美地;推翻命令?
我怎样才能使dict的子类尽可能的“完美”?最终目标是有一个简单的dict,其中键是小写的 似乎应该有一组很小的原语我可以覆盖以使其工作,但根据我所有的研究和尝试,似乎情况并非如此:Python 如何";完美地;推翻命令?,python,inheritance,dictionary,get,set,Python,Inheritance,Dictionary,Get,Set,我怎样才能使dict的子类尽可能的“完美”?最终目标是有一个简单的dict,其中键是小写的 似乎应该有一组很小的原语我可以覆盖以使其工作,但根据我所有的研究和尝试,似乎情况并非如此: 如果是我,那么get/set不起作用。我怎样才能让它们工作?我当然不需要单独实现它们 我是否阻止酸洗工作,是否需要实施\uuuu setstate\uuuu等 是吗 我应该(似乎不应该使用UserDict 或DictMixin)?如果是,怎么做?这些文件并不是很有启发性 这是我的第一次尝试,get()不起作用,
- 如果是我,那么
/get
不起作用。我怎样才能让它们工作?我当然不需要单独实现它们set
- 我是否阻止酸洗工作,是否需要实施
等\uuuu setstate\uuuu
- 是吗
- 我应该(似乎不应该使用
或UserDict
)?如果是,怎么做?这些文件并不是很有启发性DictMixin
get()
不起作用,毫无疑问还有许多其他小问题:
class arbitrary_dict(dict):
"""A dictionary that applies an arbitrary key-altering function
before accessing the keys."""
def __keytransform__(self, key):
return key
# Overridden methods. List from
# https://stackoverflow.com/questions/2390827/how-to-properly-subclass-dict
def __init__(self, *args, **kwargs):
self.update(*args, **kwargs)
# Note: I'm using dict directly, since super(dict, self) doesn't work.
# I'm not sure why, perhaps dict is not a new-style class.
def __getitem__(self, key):
return dict.__getitem__(self, self.__keytransform__(key))
def __setitem__(self, key, value):
return dict.__setitem__(self, self.__keytransform__(key), value)
def __delitem__(self, key):
return dict.__delitem__(self, self.__keytransform__(key))
def __contains__(self, key):
return dict.__contains__(self, self.__keytransform__(key))
class lcdict(arbitrary_dict):
def __keytransform__(self, key):
return str(key).lower()
使用模块中的抽象基类,您可以很容易地编写一个行为类似于dict的对象。它甚至会告诉你是否错过了一个方法,所以下面是关闭ABC的最低版本
from collections.abc import MutableMapping
class TransformedDict(MutableMapping):
"""A dictionary that applies an arbitrary key-altering
function before accessing the keys"""
def __init__(self, *args, **kwargs):
self.store = dict()
self.update(dict(*args, **kwargs)) # use the free update to set keys
def __getitem__(self, key):
return self.store[self._keytransform(key)]
def __setitem__(self, key, value):
self.store[self._keytransform(key)] = value
def __delitem__(self, key):
del self.store[self._keytransform(key)]
def __iter__(self):
return iter(self.store)
def __len__(self):
return len(self.store)
def _keytransform(self, key):
return key
您可以从ABC获得一些免费方法:
class MyTransformedDict(TransformedDict):
def _keytransform(self, key):
return key.lower()
s = MyTransformedDict([('Test', 'test')])
assert s.get('TEST') is s['test'] # free get
assert 'TeSt' in s # free __contains__
# free setdefault, __eq__, and so on
import pickle
# works too since we just use a normal dict
assert pickle.loads(pickle.dumps(s)) == s
我不会直接将dict
(或其他内置项)子类化。这通常是没有意义的,因为您真正想要做的是实现dict
的接口。这正是ABC的目的
我怎样才能使dict的子类尽可能的“完美”?
最终目标是有一个简单的dict,其中键是小写的
- 如果我覆盖
/\uuuuGetItem\uuuuuuuuuuuuuuuu
,那么get/set不起作用。怎么 我能让它们工作吗?我当然不需要实施它们 单独的\uuuuuuuuuSetItem\uuuuuuuuuuuuuuuuuuuuuuuuuu
- 我是否阻止酸洗工作,是否需要实施
等\uuuu设置状态\uuuuu
- 我需要报告、更新和
初始化吗
- 我应该只使用
(似乎不应该使用mutablemapping
或UserDict
)?如果是,怎么做?这些文件并不是很有启发性DictMixin
dict
子类化,我将在这里这样做
被接受的答案有什么问题?
对我来说,这似乎是一个相当简单的要求:
我怎样才能使dict的子类尽可能的“完美”?
最终目标是有一个简单的dict,其中键是小写的
被接受的答案实际上不是dict的子类,对此的测试失败:
>>> isinstance(MyTransformedDict([('Test', 'test')]), dict)
False
理想情况下,任何类型检查代码都将针对我们期望的接口或抽象基类进行测试,但是如果我们的数据对象被传递到测试dict
的函数中,并且我们无法“修复”这些函数,那么这段代码将失败
人们可能会提出的其他质疑:
- 接受的答案也缺少classmethod:
李>fromkeys
- 接受的答案还有一个冗余的
——因此占用了更多的内存空间:\uuuuu dict\uuuuu
>>> s.foo = 'bar' >>> s.__dict__ {'foo': 'bar', 'store': {'test': 'test'}}
dict
我们可以通过继承重用dict方法。我们需要做的就是创建一个接口层,确保键以小写形式传递到dict中(如果它们是字符串)
如果我覆盖\uuuuGetItem\uuuuuuuuuuuuuuuu
/\uuuuuuuuuSetItem\uuuuuuuuuuuuuuuuuuuuuuuuuu
,那么get/set不起作用。我如何让它们工作?我当然不需要单独实现它们
好的,分别实现它们是这种方法的缺点,使用可变映射(参见公认的答案)的优点,但实际上没有那么多工作要做
首先,让我们考虑一下Python 2和Python 3之间的差异,创建一个单例(\u RaiseKeyError
),以确保我们知道是否实际获得了dict.pop
的参数,并创建一个函数以确保字符串键是小写的:
from itertools import chain
try: # Python 2
str_base = basestring
items = 'iteritems'
except NameError: # Python 3
str_base = str, bytes, bytearray
items = 'items'
_RaiseKeyError = object() # singleton for no-default behavior
def ensure_lower(maybe_str):
"""dict keys can be any hashable object - only call lower if str"""
return maybe_str.lower() if isinstance(maybe_str, str_base) else maybe_str
现在我们实现—我正在使用带有完整参数的super
,以便此代码适用于Python 2和3:
class LowerDict(dict): # dicts take a mapping or iterable as their optional first argument
__slots__ = () # no __dict__ - that would be redundant
@staticmethod # because this doesn't make sense as a global function.
def _process_args(mapping=(), **kwargs):
if hasattr(mapping, items):
mapping = getattr(mapping, items)()
return ((ensure_lower(k), v) for k, v in chain(mapping, getattr(kwargs, items)()))
def __init__(self, mapping=(), **kwargs):
super(LowerDict, self).__init__(self._process_args(mapping, **kwargs))
def __getitem__(self, k):
return super(LowerDict, self).__getitem__(ensure_lower(k))
def __setitem__(self, k, v):
return super(LowerDict, self).__setitem__(ensure_lower(k), v)
def __delitem__(self, k):
return super(LowerDict, self).__delitem__(ensure_lower(k))
def get(self, k, default=None):
return super(LowerDict, self).get(ensure_lower(k), default)
def setdefault(self, k, default=None):
return super(LowerDict, self).setdefault(ensure_lower(k), default)
def pop(self, k, v=_RaiseKeyError):
if v is _RaiseKeyError:
return super(LowerDict, self).pop(ensure_lower(k))
return super(LowerDict, self).pop(ensure_lower(k), v)
def update(self, mapping=(), **kwargs):
super(LowerDict, self).update(self._process_args(mapping, **kwargs))
def __contains__(self, k):
return super(LowerDict, self).__contains__(ensure_lower(k))
def copy(self): # don't delegate w/ super - dict.copy() -> dict :(
return type(self)(self)
@classmethod
def fromkeys(cls, keys, v=None):
return super(LowerDict, cls).fromkeys((ensure_lower(k) for k in keys), v)
def __repr__(self):
return '{0}({1})'.format(type(self).__name__, super(LowerDict, self).__repr__())
对于引用键的任何方法或特殊方法,我们都使用几乎是锅炉板的方法,但是,通过继承,我们可以免费获得方法:len
、clear
、items
、keys
、popitem
和value
。虽然这需要一些仔细的思考才能正确,但看到这一点是微不足道的
(注意,haskey
在Python2中被弃用,在Python3中被删除。)
以下是一些用法:
>>> ld = LowerDict(dict(foo='bar'))
>>> ld['FOO']
'bar'
>>> ld['foo']
'bar'
>>> ld.pop('FoO')
'bar'
>>> ld.setdefault('Foo')
>>> ld
{'foo': None}
>>> ld.get('Bar')
>>> ld.setdefault('Bar')
>>> ld
{'bar': None, 'foo': None}
>>> ld.popitem()
('bar', None)
我是否阻止酸洗工作,是否需要实施
\uuuu设置状态\uuuuu
等
酸洗
dict子类pickles很好:
>>> import pickle
>>> pickle.dumps(ld)
b'\x80\x03c__main__\nLowerDict\nq\x00)\x81q\x01X\x03\x00\x00\x00fooq\x02Ns.'
>>> pickle.loads(pickle.dumps(ld))
{'foo': None}
>>> type(pickle.loads(pickle.dumps(ld)))
<class '__main__.LowerDict'>
但是,编写一个\uu repr\uu
来提高代码的可调试性是很好的。理想的测试是eval(repr(obj))==obj
。如果您的代码很容易实现,我强烈建议您:
>>> ld = LowerDict({})
>>> eval(repr(ld)) == ld
True
>>> ld = LowerDict(dict(a=1, b=2, c=3))
>>> eval(repr(ld)) == ld
True
你看,这正是我们重新创建等效对象所需要的——这可能会出现在我们的日志或回溯中:
>>> ld
LowerDict({'a': 1, 'c': 3, 'b': 2})
结论
我应该只使用mutablemapping
(似乎不应该使用UserDict
或DictMixin
)?如果是,怎么做?这些文件并不是很有启发性
是的,还有几行代码,但它们的目的是全面的。我的第一个倾向是使用公认的答案,
如果它有问题,我会看看我的答案——因为它有点复杂,而且没有ABC帮助我获得正确的界面
在搜索性能时,过早优化会导致更大的复杂性。
MutableMapping
更简单,因此在其他条件相同的情况下,它可以获得一个直接的边缘。然而,为了展示所有的差异,让我们进行比较和对比
>>> ld
LowerDict({'a': 1, 'c': 3, 'b': 2})
my_dict[transform(key)]
class CIstr(unicode):
"""See https://stackoverflow.com/a/43122305/281545, especially for inlines"""
__slots__ = () # does make a difference in memory performance
#--Hash/Compare
def __hash__(self):
return hash(self.lower())
def __eq__(self, other):
if isinstance(other, CIstr):
return self.lower() == other.lower()
return NotImplemented
def __ne__(self, other):
if isinstance(other, CIstr):
return self.lower() != other.lower()
return NotImplemented
def __lt__(self, other):
if isinstance(other, CIstr):
return self.lower() < other.lower()
return NotImplemented
def __ge__(self, other):
if isinstance(other, CIstr):
return self.lower() >= other.lower()
return NotImplemented
def __gt__(self, other):
if isinstance(other, CIstr):
return self.lower() > other.lower()
return NotImplemented
def __le__(self, other):
if isinstance(other, CIstr):
return self.lower() <= other.lower()
return NotImplemented
#--repr
def __repr__(self):
return '{0}({1})'.format(type(self).__name__,
super(CIstr, self).__repr__())
def _ci_str(maybe_str):
"""dict keys can be any hashable object - only call CIstr if str"""
return CIstr(maybe_str) if isinstance(maybe_str, basestring) else maybe_str
class LowerDict(dict):
"""Dictionary that transforms its keys to CIstr instances.
Adapted from: https://stackoverflow.com/a/39375731/281545
"""
__slots__ = () # no __dict__ - that would be redundant
@staticmethod # because this doesn't make sense as a global function.
def _process_args(mapping=(), **kwargs):
if hasattr(mapping, 'iteritems'):
mapping = getattr(mapping, 'iteritems')()
return ((_ci_str(k), v) for k, v in
chain(mapping, getattr(kwargs, 'iteritems')()))
def __init__(self, mapping=(), **kwargs):
# dicts take a mapping or iterable as their optional first argument
super(LowerDict, self).__init__(self._process_args(mapping, **kwargs))
def __getitem__(self, k):
return super(LowerDict, self).__getitem__(_ci_str(k))
def __setitem__(self, k, v):
return super(LowerDict, self).__setitem__(_ci_str(k), v)
def __delitem__(self, k):
return super(LowerDict, self).__delitem__(_ci_str(k))
def copy(self): # don't delegate w/ super - dict.copy() -> dict :(
return type(self)(self)
def get(self, k, default=None):
return super(LowerDict, self).get(_ci_str(k), default)
def setdefault(self, k, default=None):
return super(LowerDict, self).setdefault(_ci_str(k), default)
__no_default = object()
def pop(self, k, v=__no_default):
if v is LowerDict.__no_default:
# super will raise KeyError if no default and key does not exist
return super(LowerDict, self).pop(_ci_str(k))
return super(LowerDict, self).pop(_ci_str(k), v)
def update(self, mapping=(), **kwargs):
super(LowerDict, self).update(self._process_args(mapping, **kwargs))
def __contains__(self, k):
return super(LowerDict, self).__contains__(_ci_str(k))
@classmethod
def fromkeys(cls, keys, v=None):
return super(LowerDict, cls).fromkeys((_ci_str(k) for k in keys), v)
def __repr__(self):
return '{0}({1})'.format(type(self).__name__,
super(LowerDict, self).__repr__())
class BatchCollection(dict):
def __init__(self, *args, **kwargs):
dict.__init__(*args, **kwargs)
class BatchCollection(dict):
def __init__(self, inpt={}):
super(BatchCollection, self).__init__(inpt)
### EXAMPLE
class BatchCollection(dict):
def __init__(self, inpt={}):
dict.__init__(*args, **kwargs)
def __setitem__(self, key, item):
if (isinstance(key, tuple) and len(key) == 2
and isinstance(item, collections.Iterable)):
# self.__dict__[key] = item
super(BatchCollection, self).__setitem__(key, item)
else:
raise Exception(
"Valid key should be a tuple (database_name, table_name) "
"and value should be iterable")
class MyDict(MutableMapping):
# ... the few __methods__ that mutablemapping requires
# and then this monstrosity
@property
def __class__(self):
return dict
def __am_i_me(self):
return True
@classmethod
def __is_it_me(cls, other):
try:
return other.__am_i_me()
except Exception:
return False
d = LowerDict() # prints "init", or whatever your print statement said
print '------'
splatted = dict(**d) # note that there are no prints here