在不影响输入字典的情况下返回一个合并。

def _merge_dicts(dictA: Dict = {}, dictB: Dict = {}) -> Dict:
    # it suffices to pass as an argument a clone of `dictA`
    return _merge_dicts_aux(dictA, dictB, copy(dictA))


def _merge_dicts_aux(dictA: Dict = {}, dictB: Dict = {}, result: Dict = {}, path: List[str] = None) -> Dict:

    # conflict path, None if none
    if path is None:
        path = []

    for key in dictB:

        # if the key doesn't exist in A, add the B element to A
        if key not in dictA:
            result[key] = dictB[key]

        else:
            # if the key value is a dict, both in A and in B, merge the dicts
            if isinstance(dictA[key], dict) and isinstance(dictB[key], dict):
                _merge_dicts_aux(dictA[key], dictB[key], result[key], path + [str(key)])

            # if the key value is the same in A and in B, ignore
            elif dictA[key] == dictB[key]:
                pass

            # if the key value differs in A and in B, raise error
            else:
                err: str = f"Conflict at {'.'.join(path + [str(key)])}"
                raise Exception(err)

    return result

灵感来自@andrew cooke的解决方案

换个答案怎么样?!?这也避免了突变/副作用:

def merge(dict1, dict2):
    output = {}

    # adds keys from `dict1` if they do not exist in `dict2` and vice-versa
    intersection = {**dict2, **dict1}

    for k_intersect, v_intersect in intersection.items():
        if k_intersect not in dict1:
            v_dict2 = dict2[k_intersect]
            output[k_intersect] = v_dict2

        elif k_intersect not in dict2:
            output[k_intersect] = v_intersect

        elif isinstance(v_intersect, dict):
            v_dict2 = dict2[k_intersect]
            output[k_intersect] = merge(v_intersect, v_dict2)

        else:
            output[k_intersect] = v_intersect

    return output

dict1 = {1:{"a":{"A"}}, 2:{"b":{"B"}}}
dict2 = {2:{"c":{"C"}}, 3:{"d":{"D"}}}
dict3 = {1:{"a":{"A"}}, 2:{"b":{"B"},"c":{"C"}}, 3:{"d":{"D"}}}

assert dict3 == merge(dict1, dict2)

这里有一个使用生成器的简单方法:

def mergedicts(dict1, dict2):
    for k in set(dict1.keys()).union(dict2.keys()):
        if k in dict1 and k in dict2:
            if isinstance(dict1[k], dict) and isinstance(dict2[k], dict):
                yield (k, dict(mergedicts(dict1[k], dict2[k])))
            else:
                # If one of the values is not a dict, you can't continue merging it.
                # Value from second dict overrides one in first and we move on.
                yield (k, dict2[k])
                # Alternatively, replace this with exception raiser to alert you of value conflicts
        elif k in dict1:
            yield (k, dict1[k])
        else:
            yield (k, dict2[k])

dict1 = {1:{"a":"A"},2:{"b":"B"}}
dict2 = {2:{"c":"C"},3:{"d":"D"}}

print dict(mergedicts(dict1,dict2))

这个打印:

{1: {'a': 'A'}, 2: {'c': 'C', 'b': 'B'}, 3: {'d': 'D'}}

这个问题的一个问题是字典的值可以是任意复杂的数据块。基于这些和其他答案，我得出了以下代码:

class YamlReaderError(Exception):
    pass

def data_merge(a, b):
    """merges b into a and return merged result

    NOTE: tuples and arbitrary objects are not handled as it is totally ambiguous what should happen"""
    key = None
    # ## debug output
    # sys.stderr.write("DEBUG: %s to %s\n" %(b,a))
    try:
        if a is None or isinstance(a, str) or isinstance(a, unicode) or isinstance(a, int) or isinstance(a, long) or isinstance(a, float):
            # border case for first run or if a is a primitive
            a = b
        elif isinstance(a, list):
            # lists can be only appended
            if isinstance(b, list):
                # merge lists
                a.extend(b)
            else:
                # append to list
                a.append(b)
        elif isinstance(a, dict):
            # dicts must be merged
            if isinstance(b, dict):
                for key in b:
                    if key in a:
                        a[key] = data_merge(a[key], b[key])
                    else:
                        a[key] = b[key]
            else:
                raise YamlReaderError('Cannot merge non-dict "%s" into dict "%s"' % (b, a))
        else:
            raise YamlReaderError('NOT IMPLEMENTED "%s" into "%s"' % (b, a))
    except TypeError, e:
        raise YamlReaderError('TypeError "%s" in key "%s" when merging "%s" into "%s"' % (e, key, b, a))
    return a

我的用例是合并YAML文件，其中我只需要处理可能的数据类型的子集。因此我可以忽略元组和其他对象。对我来说，合理的合并逻辑意味着

取代标量 添加列表 通过添加缺失键和更新现有键来合并字典

其他任何事情和不可预见的事情都会导致错误。

from collections import defaultdict
from itertools import chain

class DictHelper:

@staticmethod
def merge_dictionaries(*dictionaries, override=True):
    merged_dict = defaultdict(set)
    all_unique_keys = set(chain(*[list(dictionary.keys()) for dictionary in dictionaries]))  # Build a set using all dict keys
    for key in all_unique_keys:
        keys_value_type = list(set(filter(lambda obj_type: obj_type != type(None), [type(dictionary.get(key, None)) for dictionary in dictionaries])))
        # Establish the object type for each key, return None if key is not present in dict and remove None from final result
        if len(keys_value_type) != 1:
            raise Exception("Different objects type for same key: {keys_value_type}".format(keys_value_type=keys_value_type))

        if keys_value_type[0] == list:
            values = list(chain(*[dictionary.get(key, []) for dictionary in dictionaries]))  # Extract the value for each key
            merged_dict[key].update(values)

        elif keys_value_type[0] == dict:
            # Extract all dictionaries by key and enter in recursion
            dicts_to_merge = list(filter(lambda obj: obj != None, [dictionary.get(key, None) for dictionary in dictionaries]))
            merged_dict[key] = DictHelper.merge_dictionaries(*dicts_to_merge)

        else:
            # if override => get value from last dictionary else make a list of all values
            values = list(filter(lambda obj: obj != None, [dictionary.get(key, None) for dictionary in dictionaries]))
            merged_dict[key] = values[-1] if override else values

    return dict(merged_dict)



if __name__ == '__main__':
  d1 = {'aaaaaaaaa': ['to short', 'to long'], 'bbbbb': ['to short', 'to long'], "cccccc": ["the is a test"]}
  d2 = {'aaaaaaaaa': ['field is not a bool'], 'bbbbb': ['field is not a bool']}
  d3 = {'aaaaaaaaa': ['filed is not a string', "to short"], 'bbbbb': ['field is not an integer']}
  print(DictHelper.merge_dictionaries(d1, d2, d3))

  d4 = {"a": {"x": 1, "y": 2, "z": 3, "d": {"x1": 10}}}
  d5 = {"a": {"x": 10, "y": 20, "d": {"x2": 20}}}
  print(DictHelper.merge_dictionaries(d4, d5))

输出:

{'bbbbb': {'to long', 'field is not an integer', 'to short', 'field is not a bool'}, 
'aaaaaaaaa': {'to long', 'to short', 'filed is not a string', 'field is not a bool'}, 
'cccccc': {'the is a test'}}

{'a': {'y': 20, 'd': {'x1': 10, 'x2': 20}, 'z': 3, 'x': 10}}

字典的字典合并

由于这是一个规范的问题(尽管存在某些非泛化性)，所以我提供了规范的python方法来解决这个问题。

最简单的情况:“叶子是嵌套的字典，以空字典结尾”:

d1 = {'a': {1: {'foo': {}}, 2: {}}}
d2 = {'a': {1: {}, 2: {'bar': {}}}}
d3 = {'b': {3: {'baz': {}}}}
d4 = {'a': {1: {'quux': {}}}}

这是递归最简单的情况，我推荐两种简单的方法:

def rec_merge1(d1, d2):
    '''return new merged dict of dicts'''
    for k, v in d1.items(): # in Python 2, use .iteritems()!
        if k in d2:
            d2[k] = rec_merge1(v, d2[k])
    d3 = d1.copy()
    d3.update(d2)
    return d3

def rec_merge2(d1, d2):
    '''update first dict with second recursively'''
    for k, v in d1.items(): # in Python 2, use .iteritems()!
        if k in d2:
            d2[k] = rec_merge2(v, d2[k])
    d1.update(d2)
    return d1

我相信我更喜欢第二个，而不是第一个，但请记住，第一个的原始状态必须从它的起源重建。用法如下:

>>> from functools import reduce # only required for Python 3.
>>> reduce(rec_merge1, (d1, d2, d3, d4))
{'a': {1: {'quux': {}, 'foo': {}}, 2: {'bar': {}}}, 'b': {3: {'baz': {}}}}
>>> reduce(rec_merge2, (d1, d2, d3, d4))
{'a': {1: {'quux': {}, 'foo': {}}, 2: {'bar': {}}}, 'b': {3: {'baz': {}}}}

复杂情况:“叶子是任何其他类型的:”

所以如果它们以字典结尾，这是一个简单的合并结尾空字典的例子。如果不是，也不是那么微不足道。如果是字符串，怎么合并?集合也可以类似地更新，所以我们可以这样处理，但我们失去了它们合并的顺序。那么顺序重要吗?

因此，代替更多信息，最简单的方法是给它们一个标准的更新处理，如果两个值都不是dict:即第二个dict的值将覆盖第一个dict，即使第二个dict的值是None，而第一个dict的值是一个包含大量信息的dict。

d1 = {'a': {1: 'foo', 2: None}}
d2 = {'a': {1: None, 2: 'bar'}}
d3 = {'b': {3: 'baz'}}
d4 = {'a': {1: 'quux'}}

from collections.abc import MutableMapping

def rec_merge(d1, d2):
    '''
    Update two dicts of dicts recursively, 
    if either mapping has leaves that are non-dicts, 
    the second's leaf overwrites the first's.
    '''
    for k, v in d1.items():
        if k in d2:
            # this next check is the only difference!
            if all(isinstance(e, MutableMapping) for e in (v, d2[k])):
                d2[k] = rec_merge(v, d2[k])
            # we could further check types and merge as appropriate here.
    d3 = d1.copy()
    d3.update(d2)
    return d3

现在

from functools import reduce
reduce(rec_merge, (d1, d2, d3, d4))

返回

{'a': {1: 'quux', 2: 'bar'}, 'b': {3: 'baz'}}

适用于原问题:

我不得不删除字母周围的花括号，并将它们放在单引号中，以使其成为合法的Python(否则它们将在Python 2.7+中设置字面量)，并附加一个缺少的大括号:

dict1 = {1:{"a":'A'}, 2:{"b":'B'}}
dict2 = {2:{"c":'C'}, 3:{"d":'D'}}

rec_merge(dict1, dict2)现在返回:

{1: {'a': 'A'}, 2: {'c': 'C', 'b': 'B'}, 3: {'d': 'D'}}

匹配原始问题的期望结果(在改变后，例如{A}为'A')。