How To Merge Multiple Duplicate Key Names Using Python In A Format Like Dictionary

I had data in a format like dictionary where I the data had multiple duplicate keys repeated multiple times with strings in a list as values, I want to merge all the keys with the

Solution 1:

• it's been established this is not a dict, it's a LR(1) grammar that is similar to a JSON grammar
• taking this approach parse and tokenise it with an LR parser
• https://lark-parser.readthedocs.io/en/latest/json_tutorial.html shows how to parse JSON
• needs a small adaptation so that duplicate keys work (consider a dict as a list, see code)
• have used pandas to take output from parser and reshape as you require

from lark import Transformer
from lark import Lark
import pandas as pd
json_parser = Lark(r"""
    ?value: dict
          | list
          | string
          | SIGNED_NUMBER      -> number
          | "true"             -> true
          | "false"            -> false
          | "null"             -> null

    list : "[" [value ("," value)*] "]"

    dict : "{" [pair ("," pair)*] "}"
    pair : string ":" value

    string : ESCAPED_STRING

    %import common.ESCAPED_STRING
    %import common.SIGNED_NUMBER
    %import common.WS
    %ignore WS

    """, start='value')
class TreeToJson(Transformer):
    def string(self, s):
        (s,) = s
        return s[1:-1]
    def number(self, n):
        (n,) = n
        return float(n)

    list = list
    pair = tuple
    dict = list # deal with issue of repeating keys...

    null = lambda self, _: None
    true = lambda self, _: True
    false = lambda self, _: False

js = """{
    "city":["New York", "Paris", "London"],
    "country":["India", "France", "Italy"],
    "city":["New Delhi", "Tokio", "Wuhan"],
    "organisation":["ITC", "Google", "Facebook"],
    "country":["Japan", "South Korea", "Germany"],
    "organisation":["TATA", "Amazon", "Ford"]
}"""    
    
tree = json_parser.parse(js)

pd.DataFrame(TreeToJson().transform(tree), columns=["key", "list"]).explode(
    "list"
).groupby("key").agg({"list": lambda s: s.unique().tolist()}).to_dict()["list"]

output

{'city': ['New York', 'Paris', 'London', 'New Delhi', 'Tokio', 'Wuhan'],
 'country': ['India', 'France', 'Italy', 'Japan', 'South Korea', 'Germany'],
 'organisation': ['ITC', 'Google', 'Facebook', 'TATA', 'Amazon', 'Ford']}