Code to locate the specific "Washington, D.C." entry that causes a constrain validation upon ingesting ROR.

main.py

"""
A brief script to indicate the "location" of a possibly misspelled 'Washington' 
in the current (v1.20-2023-02-28-ror-data.json) ROR dataset


:author: Athanasios Anastasiou
:date: Mar 2023
"""

import json


if __name__ == "__main__":
    data_file = "v1.20-2023-02-28-ror-data.json"

    # Load the data file
    with open(data_file, "r") as fd:
        data = json.load(fd)

    # Get all addresses[].geonames_city.id and name for 4140963
    q = list(filter(lambda x:4140963 in list(map(lambda y:y["geonames_city"]["id"] if "id" in y["geonames_city"] else "",x["addresses"])), data))
    # Isolate the id and city attributes from the rest of the data structure
    z = list(map(lambda x:list(map(lambda y:(x["id"], y["geonames_city"]["id"], y["geonames_city"]["city"]), x["addresses"]))[0] ,q))
    # The following step should return only one entry if it is unique. 
    # Unfortunately it returns two, which is why the db constrain in my system fails.
    print(set(map(lambda x:(x[1], x[2]), z)))
    # Now go back and search for that entry that has that misspelled "Washington"
    f = list(filter(lambda x: x[1]==4140963 and x[2]=="Washington", z))
    print(f)