z = MergeDict(x, y)

当使用这个新对象时,它将像合并词典一样行事,但它将有持续的创作时间和持续的记忆脚印,同时让原始词典无触摸。

当然,如果你使用结果很多,那么你会在某个时候达到创建一个真正的合并词典会是最快的解决方案的界限。

a = { 'x': 3, 'y': 4 }
b = MergeDict(a)  # we merge just one dict
b['x'] = 5
print b  # will print {'x': 5, 'y': 4}
print a  # will print {'y': 4, 'x': 3}

class MergeDict(object):
  def __init__(self, *originals):
    self.originals = ({},) + originals[::-1]  # reversed

  def __getitem__(self, key):
    for original in self.originals:
      try:
        return original[key]
      except KeyError:
        pass
    raise KeyError(key)

  def __setitem__(self, key, value):
    self.originals[0][key] = value

  def __iter__(self):
    return iter(self.keys())

  def __repr__(self):
    return '%s(%s)' % (
      self.__class__.__name__,
      ', '.join(repr(original)
          for original in reversed(self.originals)))

  def __str__(self):
    return '{%s}' % ', '.join(
        '%r: %r' % i for i in self.iteritems())

  def iteritems(self):
    found = set()
    for original in self.originals:
      for k, v in original.iteritems():
        if k not in found:
          yield k, v
          found.add(k)

  def items(self):
    return list(self.iteritems())

  def keys(self):
    return list(k for k, _ in self.iteritems())

  def values(self):
    return list(v for _, v in self.iteritems())

此外,当您使用.items() (Python 3.0 之前),您正在创建一个新的列表,包含从字典中的项目. 如果您的字典是大,那么它是相当多的顶部(两个大列表将被扔掉,一旦合并的字典创建)。更新() 可以更有效地工作,因为它可以通过第二个字典项目为项目。

在时间方面:

>>> timeit.Timer("dict(x, **y)", "x = dict(zip(range(1000), range(1000)))\ny=dict(zip(range(1000,2000), range(1000,2000)))").timeit(100000)
15.52571702003479
>>> timeit.Timer("temp = x.copy()\ntemp.update(y)", "x = dict(zip(range(1000), range(1000)))\ny=dict(zip(range(1000,2000), range(1000,2000)))").timeit(100000)
15.694622993469238
>>> timeit.Timer("dict(x.items() + y.items())", "x = dict(zip(range(1000), range(1000)))\ny=dict(zip(range(1000,2000), range(1000,2000)))").timeit(100000)
41.484580039978027

此外,字典创建的关键词论点仅在Python 2.3中添加,而复制()和更新()将在较旧版本中工作。

x = {'a': 1, 'b': 2}
y = {'b': 3, 'c': 4}

>>> z
{'a': 1, 'b': 3, 'c': 4}

z = {**x, **y}

z = {**x, 'foo': 1, 'bar': 2, **y}

>>> z
{'a': 1, 'b': 3, 'foo': 1, 'bar': 2, 'c': 4}

z = x.copy()
z.update(y) # which returns None since it mutates z

def merge_two_dicts(x, y):
    """Given two dictionaries, merge them into a new dict as a shallow copy."""
    z = x.copy()
    z.update(y)
    return z

z = merge_two_dicts(x, y)

def merge_dicts(*dict_args):
    """
    Given any number of dictionaries, shallow copy and merge into a new dict,
    precedence goes to key-value pairs in latter dictionaries.
    """
    result = {}
    for dictionary in dict_args:
        result.update(dictionary)
    return result

z = merge_dicts(a, b, c, d, e, f, g) 

和 g 的关键值对将先行于字典 a 到 f 等。

z = dict(x.items() + y.items())

>>> c = dict(a.items() + b.items())
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: unsupported operand type(s) for +: 'dict_items' and 'dict_items'

同样,在 Python 3 (viewitems() 在 Python 2.7) 中采取元素的合并也会失败,当值是不可破坏的对象(如列表,例如)。即使您的值是可破坏的,因为套件是无形的,行为与先例无定义。

>>> c = dict(a.items() | b.items())

>>> x = {'a': []}
>>> y = {'b': []}
>>> dict(x.items() | y.items())
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: unhashable type: 'list'

>>> x = {'a': 2}
>>> y = {'a': 1}
>>> dict(x.items() | y.items())
{'a': 2}

另一个你不应该使用的黑客:

z = dict(x, **y)

字典的目的是采取可触摸的密钥(例如,frozensets或tuples),但这种方法在Python 3中失败,当密钥不是线条时。

>>> c = dict(a, **b)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: keyword arguments must be strings

和

dict(a=1, b=10, c=11)

{'a': 1, 'b': 10, 'c': 11}

>>> foo(**{('a', 'b'): None})
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: foo() keywords must be strings
>>> dict(**{('a', 'b'): None})
{('a', 'b'): None}

我的答案: merge_two_dicts(x,y)实际上对我来说看起来更清楚,如果我们实际上对可读性感兴趣。

from copy import deepcopy

def dict_of_dicts_merge(x, y):
    z = {}
    overlapping_keys = x.keys() & y.keys()
    for key in overlapping_keys:
        z[key] = dict_of_dicts_merge(x[key], y[key])
    for key in x.keys() - overlapping_keys:
        z[key] = deepcopy(x[key])
    for key in y.keys() - overlapping_keys:
        z[key] = deepcopy(y[key])
    return z

>>> x = {'a':{1:{}}, 'b': {2:{}}}
>>> y = {'b':{10:{}}, 'c': {11:{}}}
>>> dict_of_dicts_merge(x, y)
{'b': {2: {}, 10: {}}, 'a': {1: {}}, 'c': {11: {}}}

{k: v for d in dicts for k, v in d.items()} # iteritems in Python 2.7

dict((k, v) for d in dicts for k, v in d.items()) # iteritems in Python 2

from itertools import chain
z = dict(chain(x.items(), y.items())) # iteritems in Python 2

from timeit import repeat
from itertools import chain

x = dict.fromkeys('abcdefg')
y = dict.fromkeys('efghijk')

def merge_two_dicts(x, y):
    z = x.copy()
    z.update(y)
    return z

min(repeat(lambda: {**x, **y}))
min(repeat(lambda: merge_two_dicts(x, y)))
min(repeat(lambda: {k: v for d in (x, y) for k, v in d.items()}))
min(repeat(lambda: dict(chain(x.items(), y.items()))))
min(repeat(lambda: dict(item for d in (x, y) for item in d.items())))

>>> min(repeat(lambda: {**x, **y}))
1.0804965235292912
>>> min(repeat(lambda: merge_two_dicts(x, y)))
1.636518670246005
>>> min(repeat(lambda: {k: v for d in (x, y) for k, v in d.items()}))
3.1779992282390594
>>> min(repeat(lambda: dict(chain(x.items(), y.items()))))
2.740647904574871
>>> min(repeat(lambda: dict(item for d in (x, y) for item in d.items())))
4.266070580109954

$ uname -a
Linux nixos 4.19.113 #1-NixOS SMP Wed Mar 25 07:06:15 UTC 2020 x86_64 GNU/Linux

词典中的资源

深深的定律:

from typing import List, Dict
from copy import deepcopy

def merge_dicts(*from_dicts: List[Dict], no_copy: bool=False) -> Dict :
    """ no recursion deep merge of two dicts

    By default creates fresh Dict and merges all to it.

    no_copy = True, will merge all dicts to a fist one in a list without copy.
    Why? Sometime I need to combine one dictionary from "layers".
    The "layers" are not in use and dropped immediately after merging.
    """

    if no_copy:
        xerox = lambda x:x
    else:
        xerox = deepcopy

    result = xerox(from_dicts[0])

    for _from in from_dicts[1:]:
        merge_queue = [(result, _from)]
        for _to, _from in merge_queue:
            for k, v in _from.items():
                if k in _to and isinstance(_to[k], dict) and isinstance(v, dict):
                    # key collision add both are dicts.
                    # add to merging queue
                    merge_queue.append((_to[k], v))
                    continue
                _to[k] = xerox(v)

    return result

使用:

print("=============================")
print("merge all dicts to first one without copy.")
a0 = {"a":{"b":1}}
a1 = {"a":{"c":{"d":4}}}
a2 = {"a":{"c":{"f":5}, "d": 6}}
print(f"a0 id[{id(a0)}] value:{a0}")
print(f"a1 id[{id(a1)}] value:{a1}")
print(f"a2 id[{id(a2)}] value:{a2}")
r = merge_dicts(a0, a1, a2, no_copy=True)
print(f"r  id[{id(r)}] value:{r}")

print("=============================")
print("create fresh copy of all")
a0 = {"a":{"b":1}}
a1 = {"a":{"c":{"d":4}}}
a2 = {"a":{"c":{"f":5}, "d": 6}}
print(f"a0 id[{id(a0)}] value:{a0}")
print(f"a1 id[{id(a1)}] value:{a1}")
print(f"a2 id[{id(a2)}] value:{a2}")
r = merge_dicts(a0, a1, a2)
print(f"r  id[{id(r)}] value:{r}")

到目前为止,我对列出的解决方案的问题是,在合并词典中,关键“b”的值为10,但在我的思维方式上,它应该是12。

import timeit

n=100000
su = """
x = {'a':1, 'b': 2}
y = {'b':10, 'c': 11}
"""

def timeMerge(f,su,niter):
    print "{:4f} sec for: {:30s}".format(timeit.Timer(f,setup=su).timeit(n),f)

timeMerge("dict(x, **y)",su,n)
timeMerge("x.update(y)",su,n)
timeMerge("dict(x.items() + y.items())",su,n)
timeMerge("for k in y.keys(): x[k] = k in x and x[k]+y[k] or y[k] ",su,n)

#confirm for loop adds b entries together
x = {'a':1, 'b': 2}
y = {'b':10, 'c': 11}
for k in y.keys(): x[k] = k in x and x[k]+y[k] or y[k]
print "confirm b elements are added:",x

结果:

0.049465 sec for: dict(x, **y)
0.033729 sec for: x.update(y)                   
0.150380 sec for: dict(x.items() + y.items())   
0.083120 sec for: for k in y.keys(): x[k] = k in x and x[k]+y[k] or y[k]

confirm b elements are added: {'a': 1, 'c': 11, 'b': 12}

在 Python 3.0 或更高版本中,您可以使用.ChainMap 集合多个字符或其他地图,以创建一个单一的可更新视图:

>>> from collections import ChainMap
>>> x = {'a':1, 'b': 2}
>>> y = {'b':10, 'c': 11}
>>> z = dict(ChainMap({}, y, x))
>>> for k, v in z.items():
        print(k, '-->', v)
    
a --> 1
b --> 10
c --> 11

更新 Python 3.5 或更高版本: 您可以使用 PEP 448 延伸字典包装和解包。

>>> x = {'a':1, 'b': 2}
>>> y = {'b':10, 'c': 11}
>>> {**x, **y}
{'a': 1, 'b': 10, 'c': 11}

更新 Python 3.9 或更高版本: 您可以使用 PEP 584 联盟运营商:

>>> x = {'a':1, 'b': 2}
>>> y = {'b':10, 'c': 11}
>>> x | y
{'a': 1, 'b': 10, 'c': 11}