Given the dictionaries:
d1={'a':'a','b':'b','c':'c'}
d2={'b':'a','c':['d','f','g'],'e':'e'}
Can these two dictionaries be combined in such a way as to merge all common keys, and preserve all values? I.e. gives the output:
> print(d1.extend(d2))
{'a':'a','b':['b','a'],'c':['c','d','f','g'],'e':'e'}
I came up with the following, which seems to work, but is very un-pythonic.
def extend(d1, d2):
return_dict={}
for key, value in d1.items():
if key in d2:
value_d2=d2[key]
if value == value_d2:
continue
if type(value) == list and type(value_d2) == list:
value.extend(value_d2)
return_dict[key]=value
elif type(value) == list and type(value_d2) != list:
tmp=[value_d2]
tmp.extend(value)
return_dict[key]=tmp
elif type(value) != list and type(value_d2) == list:
tmp=[value]
tmp.extend(value_d2)
return_dict[key]=tmp
elif type(value) != list and type(value_d2) != list:
return_dict[key]=[value] [value_d2]
else:
return_dict[key]=value
for key, value in d2.items():
if key not in return_dict:
return_dict[key]=value
return return_dict
(the last elif should be an else, but I thought it was more readable this way)
Edit:
Instead of preserving all values, is it possible to preserve all keys, but remove duplicate values? I.e.
d1={'a':'a','b':'b','c':'c'}
d2={'b':'b','c':['d','f','g'],'e':'e'}
> print(d1.extend(d2))
{'a':'a','b':'b','c':['c','d','f','g'],'e':'e'}
CodePudding user response:
Use a collections.defaultdict
as temporary storage, like shown below:
from collections import defaultdict
d1 = {'a': 'a', 'b': 'b', 'c': 'c'}
d2 = {'b': 'a', 'c': ['d', 'f', 'g'], 'e': 'e'}
tmp = defaultdict(list)
for d in [d1, d2]:
for k, v in d.items():
if isinstance(v, list):
tmp[k].extend(v)
else:
tmp[k].append(v)
res = { k : v if len(v) > 1 else v[0] for k, v in tmp.items()}
print(res)
Output
{'a': 'a', 'b': ['b', 'a'], 'c': ['c', 'd', 'f', 'g'], 'e': 'e'}
An alternative, also using defaultdict, is to do:
tmp1 = defaultdict(list)
tmp2 = defaultdict(list)
tmp1.update(d1)
tmp2.update(d2)
tmp = {key: [*tmp1[key], *tmp2[key]] for key in tmp1.keys() | tmp2.keys()}
res = {k: v if len(v) > 1 else v[0] for k, v in tmp.items()}
print(res)
Both approaches work for Python 3.7.
UPDATE
As mentioned by @ShadowRanger you could use a set, instead of list:
tmp1 = defaultdict(set)
tmp2 = defaultdict(set)
tmp1.update(d1)
tmp2.update(d2)
tmp = {key: [*tmp1[key], *tmp2[key]] for key in tmp1.keys() | tmp2.keys()}
res = {k: v if len(v) > 1 else v[0] for k, v in tmp.items()}
print(res)
CodePudding user response:
You can use a helper function safe_combine
in combination with dict.union
operator |
available in Python 3.8 :
from __future__ import annotations
d1 = {'a': 'a', 'b': 'b', 'c': 'c'}
d2 = {'b': 'a', 'c': ['d', 'f', 'g'], 'e': 'e'}
def safe_combine(o1: str | list, o2: str | list):
return (o1 if isinstance(o1, list) else [o1]) \
(o2 if isinstance(o2, list) else [o2])
merged = {k: safe_combine(d1[k], d2[k]) if k in d1 and k in d2 else v
for k, v in (d1 | d2).items()}
print(merged)
Out:
{'a': 'a', 'b': ['b', 'a'], 'c': ['c', 'd', 'f', 'g'], 'e': 'e'}
NB: For Python versions earlier than 3.8, you can use the {**d1, **d2}
syntax instead of (d1 | d2)
.